BACKGROUND

[0001] Service providers (e.g., wireless, cellular, etc.) and device manufacturers are continually challenged to deliver value and convenience to consumers by, for example, providing compelling network services. One area of development has been in providing context awareness for applications and services determined, e.g., from devices (e.g., mobile devices, wearable devices, etc.) equipped with sensors (e.g., movement sensors) capable of collecting information regarding user contexts. Traditionally, however, recognizing contexts or activities (e.g., movement activities) from sensor information often has relied on classifiers that process large volumes of sensor information across a limited set of known or recognizable classes. Moreover, such traditional classifiers often have difficulty in presenting newly discovered classes or patterns in a natural language or human recognizable way. Accordingly, service providers and device manufacturers face significant technical challenges to enable efficient classification of sensor information that can be presented to users in a naturally recognizable form.

SOME EXAMPLE EMBODIMENTS

[0002] Therefore, there is a need for providing sensor information classification.

[0003] According to one embodiment, a method comprises processing and/or facilitating a processing of sensor information to determine one or more patterns indicated by the sensor information. The method also comprises causing, at least in part, a generation of at least one representation of the one or more patterns. The method further comprises causing, at least in part, a presentation of the at least one representation. The presentation includes, at least in part, a request to label the one or more patterns, to repeat the one or more patterns, or a combination thereof. The method further comprises causing, at least in part, a classification of the one or more patterns into one or more new classes based, at least in part, on one or more response inputs received in response to the request.

[0004] According to another embodiment, an apparatus comprises at least one processor, and at least one memory including computer program code for one or more computer programs, the at least one memory and the computer program code configured to, with the at least one processor, cause, at least in part, the apparatus to process and/or facilitate a processing of sensor information to determine one or more patterns indicated by the sensor information. The apparatus also causes, at least in part, a generation of at least one representation of the one or more patterns. The apparatus further causes, at least in part, a presentation of the at least one representation. The presentation includes, at least in part, a request to label the one or more patterns, to repeat the one or more patterns, or a combination thereof. The apparatus further causes, at least in part, a classification of the one or more patterns into one or more new classes based, at least in part, on one or more response inputs received in response to the request.

[0005] According to another embodiment, a computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause, at least in part, an apparatus to process and/or facilitate a processing of sensor information to determine one or more patterns indicated by the sensor information. The apparatus also causes, at least in part, a generation of at least one representation of the one or more patterns. The apparatus further causes, at least in part, a presentation of the at least one representation. The presentation includes, at least in part, a request to label the one or more patterns, to repeat the one or more patterns, or a combination thereof. The apparatus further causes, at least in part, a classification of the one or more patterns into one or more new classes based, at least in part, on one or more response inputs received in response to the request. [0006] According to another embodiment, an apparatus comprises means processing and/or facilitating a processing of sensor information to determine one or more patterns indicated by the sensor information. The apparatus also comprises means for causing, at least in part, a generation of at least one representation of the one or more patterns. The apparatus further comprises means for causing, at least in part, a presentation of the at least one representation. The presentation includes, at least in part, a request to label the one or more patterns, to repeat the one or more patterns, or a combination thereof. The apparatus further comprises means for causing, at least in part, a classification of the one or more patterns into one or more new classes based, at least in part, on one or more response inputs received in response to the request. [0007] In addition, for various example embodiments of the invention, the following is applicable: a method comprising facilitating a processing of and/or processing (1) data and/or (2) information and/or (3) at least one signal, the (1) data and/or (2) information and/or (3) at least one signal based, at least in part, on (including derived at least in part from) any one or any combination of methods (or processes) disclosed in this application as relevant to any embodiment of the invention.

[0008] For various example embodiments of the invention, the following is also applicable: a method comprising facilitating access to at least one interface configured to allow access to at least one service, the at least one service configured to perform any one or any combination of network or service provider methods (or processes) disclosed in this application.

[0009] For various example embodiments of the invention, the following is also applicable: a method comprising facilitating creating and/or facilitating modifying (1) at least one device user interface element and/or (2) at least one device user interface functionality, the (1) at least one device user interface element and/or (2) at least one device user interface functionality based, at least in part, on data and/or information resulting from one or any combination of methods or processes disclosed in this application as relevant to any embodiment of the invention, and/or at least one signal resulting from one or any combination of methods (or processes) disclosed in this application as relevant to any embodiment of the invention.

[0010] For various example embodiments of the invention, the following is also applicable: a method comprising creating and/or modifying (1) at least one device user interface element and/or (2) at least one device user interface functionality, the (1) at least one device user interface element and/or (2) at least one device user interface functionality based at least in part on data and/or information resulting from one or any combination of methods (or processes) disclosed in this application as relevant to any embodiment of the invention, and/or at least one signal resulting from one or any combination of methods (or processes) disclosed in this application as relevant to any embodiment of the invention.

[0011] In various example embodiments, the methods (or processes) can be accomplished on the service provider side or on the mobile device side or in any shared way between service provider and mobile device with actions being performed on both sides.

[0012] For various example embodiments, the following is applicable: An apparatus comprising means for performing a method of any of the claims. [0013] Still other aspects, features, and advantages of the invention are readily apparent from the following detailed description, simply by illustrating a number of particular embodiments and implementations, including the best mode contemplated for carrying out the invention. The invention is also capable of other and different embodiments, and its several details can be modified in various obvious respects, all without departing from the spirit and scope of the invention. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.

BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings:

[0015] FIG. 1 is a diagram of a system capable of providing sensor information classification, according to one embodiment;

[0016] FIGs. 2A and 2B are diagrams of a process for providing sensor information classification in an example use case using the system of FIG. 1, according to one embodiment;

[0017] FIG. 3 is a diagram of a components of a classification platform/classification module, according to one embodiment;

[0018] FIG. 4 is a workflow for providing sensor information classification in an example use case, according to one embodiment; [0019] FIG. 5 is a flowchart of a process for providing sensor information classification, according to one embodiment;

[0020] FIG. 6 is a flowchart of a process for determining unknown fragments of sensor information for providing sensor information classification, according to one embodiment;

[0021] FIG. 7 is a flowchart of a process for clustering fragments of sensor information for providing sensor information classification, according to one embodiment;

[0022] FIG. 8 is a flowchart of a process for providing sensor information classification based on body location of wearable devices, according to one embodiment;

[0023] FIG. 9 is a diagram illustrating an example feature space, according to one embodiment; [0024] FIG. 10 is an example representation of a pattern or activity, according to one embodiment;

[0025] FIG. 1 1 is a diagram of example user interfaces for providing sensor information classification, according to various embodiments; [0026] FIG. 12 is a diagram of hardware that can be used to implement an embodiment of the invention;

[0027] FIG. 13 is a diagram of a chip set that can be used to implement an embodiment of the invention; and

[0028] FIG. 14 is a diagram of a mobile terminal (e.g., handset) that can be used to implement an embodiment of the invention.

DESCRIPTION OF SOME EMBODIMENTS

[0029] Examples of a method, apparatus, and computer program for providing sensor information classification are disclosed. In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It is apparent, however, to one skilled in the art that the embodiments of the invention may be practiced without these specific details or with an equivalent arrangement. In other instances, well-known structures and devices are shown in block diagram form in order to avoid unnecessarily obscuring the embodiments of the invention. [0030] FIG. 1 is a diagram of a system capable of providing sensor information classification, according to one embodiment. As noted above, there is increasing development and interest in providing context awareness to applications and/or services. In one embodiment, context awareness refers to obtaining comprehensive information about the immediate situation or environment - e.g., the people, roles, activities, times, places, devices, etc. associated with the situation or environment. For example, service providers can use context awareness algorithms to implement user interfaces that are adaptive to a context (e.g., providing an optimized user interface for when a user is driving).

[0031] Traditionally, an approach for developing activity or context recognition algorithms is based on supervised machine learning techniques. By way of example, one workflow for a supervised machine learning technique includes, e.g., at the stage of algorithm development, defining a fixed list of activities (e.g., patterns or classes related to movements such as walking, running, sitting, standing, etc.) that should be recognizable. Then, typically, a focus group of humans (e.g., using sensor-equipped devices) repeatedly performs each activity from the list in a standardized behavior while wearing the sensor- equipped devices until mathematically/statistically significant examples of the activity have been collected. The sensor information or data collected from this focus group during the repeated activities is analyzed to generate, for instance, a training dataset. This dataset then is used for off-line training of a classifier that recognizes the activities (e.g., during real-time operation).

[0032] However, the specificity of the machine learning techniques used in traditional approaches typically requires a large amount of data for reliable activity recognition. Moreover, the traditional techniques also typically should have data for different devices, different models of a concrete device, different users, different ways of doing an activity by each user, etc. This typically requires a substantial investment in resources to acquire such data or information. As a result, many providers and/or device manufacturers limit themselves to a restricted list of classes for recognition. For example, with respect to recognizing movement-related activities or patterns in sensor information, the restricted list typically includes walking, running, driving, resting, and/or classes depending on device type.

[0033] One approach to addressing the challenge of extending the quantity of recognizable classes is by enabling the addition of new classes (e.g., activity classes) during the usage of devices that are performing the recognition and/or otherwise classifying patterns of sensor information to generate the new classes. However, enabling such an approach causes the following subproblems:

Subproblem 1 : How to select data related to a previously undefined or new class based on sensor information or signals for a device (e.g., a wearable device)?

Subproblem 2: How to obtain a name/description for the new class in natural language automatically?

Subproblem 3: How to provide reliability to a new classifier? (e.g., adding new classes can lead to a decrease in recognition accuracy) Subproblem 4: How to collect the dataset containing data for new classes from a significant number of users?

Subproblem 5: Where should the new classifier be trained? (e.g., wearable or mobile devices collecting the sensor information by themselves may have relatively small computation power and/or related resources such as memory, bandwidth, etc.)

[0034] To address these problems, a system 100 of FIG. 1 introduces a capability to recognize and label unknown patterns (e.g., unknown movement patterns) indicated in sensor information. For example, in some applications and/or services (e.g., particularly in entertainment applications and/or services), inertial sensors are typically used to capture movement information or data. However, identifying the activity class name may not be possible based on viewing the patterns calculated from inertial sensor information or signals because the signals are non-visual objects in their native form. In one embodiment, the system 100 introduces a capability to translate the sensor information that is to be classified into a representation that can be more easily perceived or interpreted by users (e.g., as an animation, descriptive text, etc.).

[0035] In one embodiment, the system 100 then engages users by presenting the representations of the unknown pattern or activity to the user and requesting that the users provide a response such as repeating and/or labeling the pattern. The system 100, for instance, can determine that the presented representation of an unknown pattern or activity is perceived or otherwise understood by a user if the user is able to repeat the presented activity. For example, if the representation is an animation of a person sitting down, the system 100 can monitor a sensor stream from the responding user's device (e.g., a wearable device) to determine whether the user has performed the same or similar motion. [0036] In addition or alternatively, the system 100 can also request that the responding user provide a label or name for the observed pattern. In one embodiment, the system 100 can consolidate the suggested labels or names collected from a multiple users viewing the representation, pattern, and/or activity to generate a consensus natural language name for the new activity class. For example, the responses to the presentation of the representation (e.g., repetition, labeling, etc.) can be collected via one or more crowdsourcing techniques, services, etc. [0037] As shown in FIG. 1, in one embodiment, the system 100 includes user equipment (UEs) lOla-lOln (also collectively referred to as UEs 101) (e.g., mobile devices, wearable devices, etc.) having connectivity to a classification platform 103 for providing sensor information classification of sensor information collected from one or more sensors 107a- 107n (also collectively referred to as sensors 107) associated with the UEs 101. In one embodiment, the UEs 101 also include respective classification modules 109a-109n (also collectively referred to as classification module 109) for performing all or a portion of the functions of the classification platform 103 locally at the UEs 101. In one embodiment, the classification module 107 can operate in place of or in conjunction with (e.g., in a client- server architecture) the classification platform 103.

[0038] In one embodiment, the UEs 101 may respectively execute applications 1 Hal l In (also collectively referred to as applications 1 1 1) that interact with the classification platform 103 and/or the classification module 107 to present representations of unknown patterns or activities, and to receive interaction responses from users observing the representations. In one embodiment, the applications 109 are implemented as gaming applications that will present the classification functions as part of a gaming activity. For example, representations of unknown patterns or activities can be presented in game for identification of the pattern. In one embodiment, the user first views animation of the activity in the display of the UE 101. The aim of the game, for instance, can be to repeat the movement (as shown in animation) as much as possible in a similar way and to identify the activity. Although the classification module 109 is depicted as a separate component of the UE 101, it is contemplated that classification module 109 or at least some of its functions can be incorporated in or performed by the application 103.

[0039] In one embodiment, the classification platform 103 and/or classification module 109 may store pattern representations, pattern classification results, class names or labels, datasets, and/or other information related to providing sensor information classification in the database 1 13. In addition or alternatively, the pattern representations, pattern classification results, class names or labels, datasets, and/or other related information may be synchronized with and/or retrieved from a services platform 115, services 117a- 117m (also collectively referred to as services 117), content providers 1 19a- 1 19k (also collectively referred to as content providers 1 19), and/or any other cloud component of the system 100. In this way, the classification platform 103 can share pattern classification information with multiple UEs 101 to enable, for instance, crowdsourced approaches to sensor information classification.

[0040] In one embodiment, the classification platform 103, the classification modules 109, and/or the applications 1 11 communicate with the service platform 1 15, the services 1 17, and/or the content providers 119 to access services and/or content related to providing sensor information classification including providing gaming applications and/or any other type of application that generate and/or use sensor information classification results or can present representations of patterns or activities for classification. In one embodiment, the service platform 1 15, services 117, and/or content providers 119 may also provide data (e.g., contextual data, user history data, user preference data, crowdsourcing information, device capability information, etc.) for providing sensor information classification. By way of example, the services platform 113 may include social networking services, content (e.g., audio, video, images, etc.) provisioning services, application services, storage services, contextual information determination services, location based services, information (e.g., weather, news, etc.) based services, etc. In one embodiment, the service platform 1 15, services 117, and/or content providers 1 19 may provide content for generating representations (e.g., animations, text descriptions, etc.) of patterns and/or activities to classify. By way of example, the content provided may be any type of content, such as mapping content, navigation content, textual content, audio content, video content, image content, etc. In one embodiment, the service platform 115, the content providers 1 17 may also provide a consistent, standard interface to providing sensor information classification among multiple devices.

[0041] By way of example, the communication network 105 of system 100 includes one or more networks such as a data network, a wireless network, a telephony network, or any combination thereof. It is contemplated that the data network may be any local area network (LAN), metropolitan area network (MAN), wide area network (WAN), a public data network (e.g., the Internet), short range wireless network, or any other suitable packet- switched network, such as a commercially owned, proprietary packet-switched network, e.g., a proprietary cable or fiber-optic network, and the like, or any combination thereof. In addition, the wireless network may be, for example, a cellular network and may employ various technologies including enhanced data rates for global evolution (EDGE), general packet radio service (GPRS), global system for mobile communications (GSM), Internet protocol multimedia subsystem (IMS), universal mobile telecommunications system (UMTS), etc., as well as any other suitable wireless medium, e.g., worldwide interoperability for microwave access (WiMAX), Long Term Evolution (LTE) networks, code division multiple access (CDMA), wideband code division multiple access (WCDMA), wireless fidelity (WiFi), wireless LAN (WLAN), Bluetooth®, Internet Protocol (IP) data casting, satellite, mobile ad-hoc network (MANET), and the like, or any combination thereof.

[0042] The UE 101 may be any type of wearable terminal, mobile terminal, fixed terminal, or portable terminal including a mobile handset, wearable device, station, unit, device, multimedia computer, multimedia tablet, Internet node, communicator, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, personal communication system (PCS) device, personal navigation device, personal digital assistants (PDAs), audio/video player, digital camera/camcorder, positioning device, television receiver, radio broadcast receiver, electronic book device, game device, or any combination thereof, including the accessories and peripherals of these devices, or any combination thereof. It is also contemplated that the UE 101 can support any type of interface to the user (such as "wearable" circuitry, etc.).

[0043] Further, the UE 101 may include various sensors 107 for collecting data associated with a user's environment, context, activity, etc. In one embodiment, the sensors may inertial sensors, location sensors, and the like for determining a movement or activity of a user. In addition, the sensors 107 may determine and/or capture audio, video, images, atmospheric conditions, device location, user mood, ambient lighting, user physiological information, device movement speed and direction, and the like. In another embodiment, the sensors 107 may include, light sensors, orientation sensors, altitude sensors, acceleration sensors, tilt sensors, moisture sensors, pressure sensors, audio sensors (e.g., microphone), etc. Although the various embodiments are discussed with respect to sensor information related to classifying movement or activity patterns, it is contemplated that the various approached described herein are also applicable to classifying patterns in images, audio samples, and/or other media items.

[0044] By way of example, the UE 101, the classification platform 103, the classification modules 109, and the applications 111 may communicate with each other and other components of the system 100 using well known, new or still developing protocols. In this context, a protocol includes a set of rules defining how the network nodes within the communication network 115 interact with each other based on information sent over the communication links. The protocols are effective at different layers of operation within each node, from generating and receiving physical signals of various types, to selecting a link for transferring those signals, to the format of information indicated by those signals, to identifying which software application executing on a computer system sends or receives the information. The conceptually different layers of protocols for exchanging information over a network are described in the Open Systems Interconnection (OSI) Reference Model.

[0045] Communications between the network nodes are typically effected by exchanging discrete packets of data. Each packet typically comprises (1) header information associated with a particular protocol, and (2) payload information that follows the header information and contains information that may be processed independently of that particular protocol. In some protocols, the packet includes (3) trailer information following the payload and indicating the end of the payload information. The header includes information such as the source of the packet, its destination, the length of the payload, and other properties used by the protocol. Often, the data in the payload for the particular protocol includes a header and payload for a different protocol associated with a different, higher layer of the OSI Reference Model. The header for a particular protocol typically indicates a type for the next protocol contained in its payload. The higher layer protocol is said to be encapsulated in the lower layer protocol. The headers included in a packet traversing multiple heterogeneous networks, such as the Internet, typically include a physical (layer 1) header, a data-link (layer 2) header, an internetwork (layer 3) header and a transport (layer 4) header, and various application (layer 5, layer 6 and layer 7) headers as defined by the OSI Reference Model.

[0046] In one embodiment, the classification platform 103, the classification modules 109, and/or the applications 1 11 may interact according to a client-server model. According to the client-server model, a client process sends a message including a request to a server process, and the server process responds by providing a service (e.g., context-based grouping, social networking, etc.). The server process may also return a message with a response to the client process. Often the client process and server process execute on different computer devices, called hosts, and communicate via a network using one or more protocols for network communications. The term "server" is conventionally used to refer to the process that provides the service, or the host computer on which the process operates.

Similarly, the term "client" is conventionally used to refer to the process that makes the request, or the host computer on which the process operates. As used herein, the terms "client" and "server" refer to the processes, rather than the host computers, unless otherwise clear from the context. In addition, the process performed by a server can be broken up to run as multiple processes on multiple hosts (sometimes called tiers) for reasons that include reliability, scalability, and redundancy, among others.

[0047] FIGs. 2 A and 2B are diagrams a process for providing classification in an example use case using the system of FIG. 1, according to one embodiment. More specifically, the example of FIGs. 2A and 2B illustrate a use case in which a classification of movement or activity patterns are performed using a game application with sensor information collected from wrist-worn devices equipped with sensor including, e.g., a three- axes accelerometer, gyroscope and magnetometer. It is noted that although the approaches described below are with respect to activity or motion detection within a game context, it is contemplated that the approaches are applicable to any type of classification (e.g., movement patterns, image patterns, audio patterns, etc.) using sensor information collected from any type of sensor. In addition, it is contemplated that the approaches may be applied without a game context.

[0048] In one embodiment, the classification process of FIGs. 2A and 2B include five phases: (1) phase 201 of FIG. 2A for building initial classifiers offline; (2) phase 203 of FIG. 2A for collecting unknown patterns or activity; (3) phase 205 of FIG. 2A for processing the unknown patterns into representations; (4) phase 207 of FIG. 2B for determining responses to the presented representations; and (5) phase 209 of FIG. 2B for generating new classes based on the responses.

[0049] As noted, phase 201 is building of initial classifier for activity recognition. In one embodiment, phase 201 is performed once and offline. For example, a classifier 211 is trained and the parameters adjusted based on preliminary collected labeled dataset 213 using, e.g., supervised machine learning. In one embodiment, the classifier 21 1 is able to classify several activities (e.g., known classes), as well as an Unknown class (e.g., also known as a NULL class). In one embodiment, the Unknown class includes all other activities except the classes that have been preconfigured or trained as known to the classifier 21 1. For example, initially the classifier 211 can be trained for the following classes: stationary, walking, driving and typing. According, sensor information indicating other activities (e.g., writing, eating and badminton playing) should be classified as Unknown activity by the classifier 211. In embodiment, the classifier 211 can use any classification and/or training algorithm to perform the classification process including, but not limited to, for example, k-nearest neighbors (kNN), support vector machine (SVM), ensembles of decisions trees, and the like. After training, the activity classifier 21 1 is installed on wearable devices 215a-215n (also collectively referred to as wearable devices 215) (e.g., equivalent to the UEs 101 of FIG. 1).

[0050] In one embodiment, phase 203 is performed on the wearable device 215. By way of example, sensors signals or information collected by the wearable device 215 are used for activity classification. For example, the sensor information can include signals for the three-axes accelerometer, gyroscope, magnetometer, and/or any other sensor type equipped on or accessible to the wearable device 215. In process 217, the wearable device 215 uses, for instance, its installed classifier 211 to perform activity recognition. At process 219, if a determined activity is classified as unknown, then wearable device 215 can send the unknown fragments of sensor information or signals to a cloud classification service 223 (e.g., the classification platform 103) for analysis (at process 221).

[0051] In one embodiment, phase 205 is performed by the cloud classification service 223 for information received from all devices 215 connected with the cloud 223. In one embodiment, when enough fragments of sensor information and/or signals, which are attributed to the class Unknown, are accumulated, several numerical features are calculated from these fragments. After the numerical features are calculated, clustering is carried out in feature space (at process 225). In one embodiment, the numerical features may be calculated in a time or frequency domain for separate axis or for magnitude of accelerometer and/or gyroscope and/or magnetometer. By way of example, in a time domain, the numerical features may be statistical moments and/or zero crossing rate. In one embodiment, a Fast Fourier transform (FFT) may be applied to transform the signal fragments to a frequency domain. By way of example, in the frequency domain energy, entropy and/or peak position may be calculated for various portions of the spectrum and/or sub-bands as the numerical features. In one embodiment, some filtering for raw signal fragments before calculation of features may be applied. [0052] In one embodiment, the clustering of the numerical features may be performed using any clustering technique including, but not limited to, for example, Mean-shift, various versions of k-Means, and/or hierarchical clustering. By way of example, an aim of the clustering is discovering of compact popular class (e.g., clusters that have small size and include plenty of points which correspond to fragments of signals). In one embodiment, clustering may be applied for a subset of points to decrease computational complexity. In other words, the cloud classification service 223 may use only part of the total amount of fragments accumulated in the cloud 223 for clustering.

[0053] Typically, popular classes discovered during the clustering process include many points, which have one-to-one mapping with fragments of signals. Accordingly, in one embodiment, one or more representative fragments are selected for the popular class(es) (at process 227). In one embodiment, the representative fragment may be a fragment that is closest to the center point of a cluster that the fragment is to represent.

[0054] In another embodiment, the fragment may be selected by random. In another embodiment, one option is restoration of a representative signal fragment from the features which correspond center mass of the cluster. For example, if central features are Fourier coefficients, then Inverse Fourier Transform may be applied to restore the features to a representative signal fragment.

[0055] In an example wherein the signals are motion related signals, the representative fragment of sensor signals reflect some motion. Accordingly, in one embodiment, a representation can be generated to visualize the motion (at process 229). For example, a 3D animation that depicts an avatar carrying out motion recorded in the representative fragment can be generated. In one embodiment, a kinematic model of the avatar can be used to generate the animation. For example, if the representative signal fragment was collected from a wrist-worn device on worn on a right hand, then the movement of wrist can be used for animating movement of whole arm.

[0056] In one embodiment, sensor fusion algorithms for signals of 3 -axes accelerometer, gyroscope and magnetometer can be used to obtain acceleration samples with removed gravity component in a world coordinate system (e.g., in coordinate system connected with Earth, where z axis is directed upward, x axis is directed to North and y axis is directed to West, for example). Based on the simplest uniformly accelerated motion model (V = V0 + at; S = V*t), the cloud 223 is able to calculate displacement of wearable device (e.g., wrist in this example) in each frame of motion. In one embodiment, linear acceleration values can be smoothed by means of, for instance, Kalman or Alpha-Beta filter in order to suppress unnatural jitter on animation. [0057] Next step is estimation of one or several the best viewpoints (or virtual camera positions) for viewing of the animation for identification of avatar activity (at process 231). For example, some movements can be invisible for some viewpoints. Accordingly, in one embodiment, the cloud classification service 223 can determine one or more viewpoints which allow a user to see all device movements. In one embodiment, the animation may be interactive to enable a user to dynamically select a viewpoint during playback of the animation or representation.

[0058] A process 233, the animation is deployed to wearable devices 215 of users, who participated in game or otherwise agree to perform classification. In addition or alternatively, the animation or representation can be sent to the users' smartphones or tablets or other devices 237, which are capable of presenting the animation or other representation of the sensor information fragment. In one embodiment, the animation may be sent as 3D models and list of virtual camera positions for rendering on the device. In other embodiments, the animation can be sent as ready-to-view video file or set of video files. [0059] In one embodiment, phase 207 shows the process that takes place on the user's wearable device after the representation or animation of an unknown signal fragment is generated. For example, a user/player is asked to view the animation on the user's device (e.g., wearable device 215 and/or device 237) (at process 239). Then, the player is asked to perform the same movement, making this reproduction as close as possible to the motion shown on the screen (at process 241). In case, the player is able to perform the movement in similar way (measured by some metric); the player either is claimed as a candidate to win or is awarded with game scores or some similar incentive. Then, the player is asked to name and/or describe the activity (at process 243). In one embodiment, the Player's response input including the player's suggested name and/or description (e.g., representing the player's opinion) is sent to the cloud 223. In one embodiment, the player later obtains additional rewards in game from the cloud 223 depending, for instance, on how his opinion about the activity name is consistent with the opinion of other players.

[0060] In some embodiments, the game or service can be extended with users who are doing new classes of activities on purpose. Other players and/or users can try to repeat them and, for instance, receive points if they are successful. In one embodiment, the most and/or best repeatable activities can be utilized in new versions of classifiers. In another embodiment, players can produce verbal descriptions of the class of activity in an attempt for others to repeat the activity based on the description instead of the animation as the representation of the activity.

[0061] As shown, phase 209 is performed in the cloud 223. In one embodiment, players' or users' opinions regarding an activity or pattern class are consolidated in the cloud 223. In one embodiment, the opinions or responses may originate from players of different nations. Accordingly, the suggested name or description of the activity may be provided in different languages. For example, a Russian-speaking player may write: "OH ecT", which translates to "He is eating". Therefore, in one embodiment, the cloud 223 can translate player's opinions from different languages to a specified language (at process 245). In one embodiment, players may use synonyms, for example: "eat", "meal", "devour" to describe the same activity. Accordingly, various synonymous names can be converted to single name (at process 247). After that voting of alternative names is performed (at process 249). In one embodiment, if a version of a name is prevalent then the version is selected as the representative name for the considered activity class. [0062] In one embodiment, the initial labeled dataset 213 is combined with a dataset of new labeled class(es) 251 that, for instance, was obtained in the previous phases. The new combined dataset 253 is used for classifier training (at process 255). In one embodiment, the cloud 223 can estimate how addition of new class(es) influences classification quality. For this purpose, classification quality metrics are calculated in a cross-validation procedure (at process 257). By way of example, the classification quality metrics include, but are not limited to, a number of false positive errors, number of false negative errors, precision, recall, and/or F-score. If classification quality is good, e.g. it is above a threshold value (at process 259), then classifier is updated on all wearable devices 215 (at process 261).

[0063] FIG. 3 is a diagram of components of a classification platform/classification module, according to one embodiment. By way of example, the classification platform 103 and/or classification module 109 include one or more components for providing classification. It is contemplated that the functions of these components may be combined in one or more components or performed by other components of equivalent functionality. In one embodiment, the classification platform 103 and/or the classification module 109 may perform the functions discussed with respect to the various embodiments described herein independently or in cooperation. In one embodiment, the classification platform 103 and/or classification module 109 includes a fragment accumulation module 301, a clustering module 303, a representation generation module 305, a response opinion module 307, and a classifier module 309. The functions of these modules 301-309 are discussed below with respect to the workflow of FIG. 4 which is a workflow for providing classification in an example use case, according to one embodiment. [0064] As shown in FIG. 4, at step 401, activity recognition algorithms executing inside, for instance, wearable devices (e.g., a UE 101) perform classification based sensor information or signals collected from there sensors (e.g., sensors 105). In one embodiment, the wearable devices send fragments of the sensor signals that are classified in an Unknown class to the cloud (e.g., the fragment accumulation module 301). In one embodiment, the fragment accumulation module 301 can receive fragments from multiple wearable devices with connectivity to the classification platform 109. By way of example, multiple different activities may be pooled into the Unknown class and sent to the fragment accumulation module 301. In one embodiment, the fragment accumulation can determine when a threshold amount of sensor information fragments have been accumulated to trigger classification. In this way, the sensor information fragments can be processed on a batch basis. In addition or alternatively, the fragment accumulation module can pass along the sensor fragments received for processing on a streaming or substantially real-time basis.

[0065] At step 403, the clustering module 303 processes the accumulated sensor fragment information to calculate numerical features of the fragments as described above. The clustering module 303 then clusters the sensor information fragments in feature space according to the calculated numerical features. In one embodiment, the clustering module 303 processes the clusters of the feature space to discover, for instance, a compact popular cluster. In other words, the clustering module 303 searches for a cluster that has small size and includes plenty of members, which correspond to fragments of signals. By way of example, the clustering module 303's operation is based on an assumption that the compact popular cluster corresponds to a popular activity class for many users, but the current classifier is unable to recognize it. In one embodiment, more than one clusters might be extracted simultaneously. In one embodiment, the clustering module 303 can be configured to limit the number of clusters or new classes to extract if a degradation of classification quality resulting from the increased number of classes is detected.

[0066] In many cases, the extracted cluster or popular new class includes many fragments of signals. These fragments are similar but may often have differences. Accordingly, at step 405, the clustering module 303 can select of a representative fragment for the popular class. In one embodiment, the clustering module 303 may determine the fragment that corresponds to the closest point at the center of cluster, and then designate that fragment as the representative fragment. In addition or alternatively, the clustering module 303 can determine a representative numerical feature that is closest to a center point of the cluster of interest, and then reverse calculate to restore a sensor information or signal fragment from the numerical feature.

[0067] In one embodiment, where the sensor signals reflect some motion or other pattern that is to be visualized or otherwise presented, the representation generation module 305 processes the sensor information fragment create a representation. In this example, at step 407, the representation generation module 305 prepares a 3D animation of an avatar that carries out the motion or feature recorded in or indicated by the representative fragment of signals.

[0068] In one embodiment, at step 409, the representation generation module 305 also estimates of one or several viewpoints (or virtual camera positions) for viewing of the animation for identification of avatar activity. The viewpoints, for instance, can be selected to provide a viewer of the animation or representation a clear or unobstructed view of the motion as performed by the avatar.

[0069] At step 41 1, the response opinion module 307 distributes the representation (e.g., the 3D-animation) of the fragment among participating users. For example, in the game context, the animation is distributed to the wearable devices of users participate in the game.

[0070] In an embodiment in which the classification is performed in the context of a game, the response opinion module 307 can optionally perform the steps described below.

[0071] In step 413, the response opinion module 307 causes the game application to demonstrate the animation and asks the players to give a name of animated activity. A player views animation of the motion (that corresponds to activity) on a display of his device, for example smartphone or tablet. In one embodiment, the player tries to perform the movement represented by the animation as similar as possible. Player who is done this with a good degree of similarity is granted with ability to name and to describe the activity and/or another reward within the context of the game (for example an extra life, a virtual good, extra credit and so on). [0072] In one embodiment, a player is awarded with scores depending on quality of performing movement, quality of description, and similarity to previously stored descriptions from other users. Game outcomes (that is activity name and description) are sent to the response opinion module 307. Thus, the response opinion module 307 facilitates labeling by crowdsourcing through the game.

[0073] At step 415, the response opinion module 307 consolidates the players' responses and opinions. In one embodiment, the consolidation comprises translation from national languages to specified language, for example, English, analysis of synonymous names, spell checking, voting of alternative names, and the like. In one embodiment, the absolute winner of voting is selected as name for considered activity class. In other embodiments, the response opinion module 307 can use any other process or algorithm for processing the opinions or responses to designate a name for the class or pattern in question.

[0074] Finally, at step 417, the classifier module 309 retrains the initial classifier and then deploys the updated classifier to associated devices (e.g., participating wearable devices and/or UEs 101).

[0075] FIGs. 5-8 below describe the processes for providing classification on a general level outside of a gaming context. In addition, it is contemplated that the patterns can be any pattern indicated or represented in the sensor information and are not limited to movement or activity-based patterns highlighted in some of the embodiments above. For example, as previously noted, the approaches of the various embodiments are also applicable to recognition of images, audio (music), and/or other patterns via crowdsourcing.

[0076] FIG. 5 is a flowchart of a process for providing classification, according to one embodiment. In one embodiment, the classification platform 103 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 13. In addition or alternatively, the classification module 109 may perform all or a portion of the process 500, and may also be implemented in the chip set including the processor and the memory as shown in FIG. 13.

[0077] In step 501 , the classification platform 103 processes and/or facilitates a processing of sensor information to determine one or more patterns indicated by the sensor information. In one embodiment, the one or more patterns include, at least in part, one or more movement patterns, one or more image patterns, one or more audio patterns, or a combination thereof. By way of example, in the context of movement, patterns can be identified as specific movement activities such as running, walking, driving, etc. Examples of image patterns include, visual patterns, objects, color, quality, etc.; and examples of audio patterns include musical passages, notes, speech, etc. As previously noted, in one embodiment, the patterns relate to unknown patterns (e.g., patterns that do not fall into any known classes) (see process 600 of FIG. 6 for a discussion of accumulating unknown sensor fragments). However, it is contemplated that the approach of the various embodiments described herein can also be applied to known classes (e.g., to verify or validate previous classifications, or to refine or improve the quality of previous classifications).

[0078] In step 503, the classification platform 103 causes, at least in part, a generation of at least one representation of the one or more patterns. In one embodiment, the classification platform 103 causes, at least in part, a generation of at least one animation, at least one textual description, or a combination thereof to present as the at least one representation. It is noted animations and text descriptions are provided as examples of possible representations of the patterns and not as limitation. In one embodiment, type of representation can be based on the capabilities of the user or the user's device. For example, the classification platform 103 can provide audio based representations to sight- impaired users or to users in context where viewing the display is not available or advised (e.g., while driving).

[0079] In step 505, the classification platform 103 causes, at least in part, a presentation of the at least one representation, wherein the presentation includes, at least in part, a request to label the one or more patterns, to repeat the one or more patterns, or a combination thereof. As previously described, one context for presenting the representation is within a game. However, it is contemplated that the representation can be presented to the user directly as a labeling or classification exercise with the game elements. [0080] In one embodiment, the classification platform 109 processes and/or facilitates a processing of the at least one representation via one or more classification systems to generate one or more suggested labels for the one or more patterns, the one or more new classes, or a combination thereof. In one embodiment, the presentation of the at least one representation further includes, at least in part, the one or more suggested labels. For example, if the representation is an animation, the classification platform 103 can pass the generated animations through a video classification system. The obtained video labels can then be used as suggestions to responding users. In cases, where the sensor information includes actual videos or images (e.g., via camera sensors such as head-mounted cameras), the accompanying video or images can be separately classified to determine suggested labels.

[0081] In one embodiment, the classification platform 109 causes, at least in part, a presentation of a request to at least one second user to label the one or more patterns, to repeat the one or more patterns based on the at least one description to verify the one or more response inputs.

[0082] In one embodiment, the classification platform 109 receives the one or more response inputs from at least one crowdsourcing application, at least one crowdsourcing labeling engine or a combination thereof. For example, the classification platform 109 can feed the representation of the sensor fragments, rather than the fragments themselves, through labeling engines to provide additional information classifying the representations and ultimately the underlying sensor fragments. In another embodiment, animations generated from known classes could be used to identify malicious crowdsourcing participants that provide spammed or misleading annotations.

[0083] In step 509, the classification platform 103 processes and/or facilitates a processing of the one or more response inputs to determine at least one natural language label for the one or more new classes. As previously discussed, in one embodiment, determining natural language labels can include additional semantic analysis including translations between languages, reconciling synonyms, adapting to colloquial use of language, etc.

[0084] In step 507, the classification platform 103 causes, at least in part, a classification of the one or more patterns into one or more new classes based, at least in part, on one or more response inputs received in response to the request. For example, the classification platform 103 can consolidate all responses or opinions that described a pattern of interest to select or designate a consensus label or classification. In one embodiment, the consensus label or name for the new class can be determined by voting, applying one or more selection rules or criteria, and the like.

[0085] FIG. 6 is a flowchart of a process for determining unknown fragments of sensor information for providing classification, according to one embodiment. In one embodiment, the classification platform 103 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 13. In addition or alternatively, the classification module 109 may perform all or a portion of the process 500, and may also be implemented in the chip set including the processor and the memory as shown in FIG. 13.

[0086] In step 601, the classification platform 103 causes, at least in part, an application of at least one classifier to the sensor information to determine one or more fragments of the sensor information that are classified into at least one unknown class. In one embodiment, the classification platform 103 cases the application of a classifier by initiating installation of the classifier at sensor information collection devices (e.g., wearable devices, mobile devices, etc.) that can then perform the classification locally. In one embodiment, the devices classify sensor information fragments and then transmit the fragments that are in an unknown class to the classification platform 103.

[0087] In step 603, the classification platform 103 causes, at least in part, an accumulation of the one or more fragments for the classification of the one or more patterns. In one embodiment, the classification platform 103 receives sensor information fragments from multiple fragments as they are classified as unknown. The classification platform 103, for instance, accumulates the fragments from participating devices, until the fragments reach a threshold level or amount. Then the classification platform 103 can proceed with determining potential new classes as described above.

[0088] In step 605, the classification platform 103 optionally retrains the classifier based on the new classes. In one embodiment, as new classes are discovered, the classification platform 103 retrains the initial classifiers with the new classes and then redeploys the classifiers to participating devices. In this way, the classification platform 103 can potentially reduce the number of unknown fragments that it receives and avoid reclassification or previously discovered new classes.

[0089] FIG. 7 is a flowchart of a process for clustering fragments of sensor information for providing classification, according to one embodiment. In one embodiment, the classification platform 103 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 13. In addition or alternatively, the classification module 109 may perform all or a portion of the process 500, and may also be implemented in the chip set including the processor and the memory as shown in FIG. 13. [0090] In step 701, the classification platform 103 causes, at least in part, a clustering of the one or more fragments into one or more clusters of at least one feature space. As previously described, in one embodiment, the classification platform 103 calculates numerical features from the fragments using one or more transformations. By way of example, the transformations can be applied in a time domain, a frequency domain, and/or any other designated domain. The numerical features then mapped and clustered into a feature space based on the calculated numerical features.

[0091] In step 703, the classification platform 103 causes, at least in part, a selection of the one or more patterns for the classification based, at least in part, on cluster size information, cluster popularity information, or a combination thereof. In other words, the classification platform 103 looks for the cluster or clusters that are most compact and dense in population (e.g., with the most number of member fragments). Compact and popular clusters generally indicate repeatable patterns (e.g., repeatable movements) that are commonly performed by users and that may have not otherwise been classified. [0092] In step 705, the classification platform 103 determines at least one representative fragment from among the one or more fragments in the one or more clusters. The classification platform 103 can use any means to select a representative fragment including, e.g., selecting fragments from the center point of clusters, selecting fragments randomly, restoring a representative fragments from representative numerical features, etc. In one embodiment, the classification platform 103 causes, at least in part, a designation of the at least one representative fragment to represent the one or more new classes.

[0093] FIG. 8 is a flowchart of a process for providing classification based on body location of wearable devices, according to one embodiment. In one embodiment, the classification platform 103 performs the process 500 and is implemented in, for instance, a chip set including a processor and a memory as shown in FIG. 13. In addition or alternatively, the classification module 109 may perform all or a portion of the process 500, and may also be implemented in the chip set including the processor and the memory as shown in FIG. 13.

[0094] In one embodiment, the sensor information is collected from one or more wearable devices. Accordingly, in step 801, the classification platform 103 determines one or more body locations at which the one or more wearable devices is worn. In one embodiment, wearable devices and/or mobile devices can be worn or carried on different parts of the body (e.g., on wrists, in pockets, etc.). The body location, for instance, can have an impact on the classification of the results or the nature of the movement or activity indicated by the sensor information. Accordingly, in one embodiment, the sensor information can include information about the exact model and/or body location of the collecting device. In some embodiments, the body location can also be detected by classification algorithms.

[0095] In step 803, the classification platform 103 determines the one or more patterns indicated by the sensor information, the generation of the at least one representation, the classification of the one or more patterns, or a combination thereof is based, at least in part, on the one or more body locations.

[0096] FIG. 9 is a diagram illustrating an example feature space, according to one embodiment. In one embodiment, the feature space 900 is constructed by clustering unknown sensor fragments. More specifically, numerical features of the sensor fragments are calculated in one or more domains to facilitate the clustering. As previously described, the numerical features can based on transforming the sensor fragments in a time domain and/or a frequency domain. The resulting numerical features a plotted in the feature space 900 and indicated by the "x" and "+" markers.

[0097] In one embodiment, the classification platform 103 applies one or more clustering techniques (e.g., mean-shift, k-Means, hierarchical, etc.) and identifies a cluster 901 of unknown sensor fragments indicated by the "+" symbol. For example, the sensor fragments grouped in the cluster 901 may correspond to a common activity such as eating. Other fragments indicated by the "x" symbols remain unclustered and correspond to more rare activities such as handshaking, door opening, etc.

[0098] In this case, the discovered cluster 901 includes many fragments. Based on the dispersion of mapping of the fragments in the cluster 901, the fragments are similar but have differences. Accordingly, the classification platform 103 can select fragment 903 from the center point of the cluster 901 as the representative fragment.

[0099] FIG. 10 is an example representation of a pattern or activity, according to one embodiment. In the example of FIG. 10, the classification platform 103 has generated a representation 1001 of an unknown activity. The representation 1001 , for instance, is a 3D animation of an avatar 1003 hitting a ball 1005. In one embodiment, the classification converts the inertial sensor information collected from, for instance, a wrist-worn device to infer real world coordinates for hand and/or body positions for animating the avatar.

[00100] In this embodiment, the classification platform 103 has passed the resulting animation to a video classification system (e.g., a sports classification system) that has tentatively classified the motion indicated in the animation as hitting a ball. Accordingly, as a means of providing a suggested label or classification, the classification platform 103 has rendered the ball 1005 in combination with the avatar even though there is no indication of a ball in the sensor fragments. The representation 1001 can then be presented to the users as shown in FIG. 1 1 below. [00101] FIG. 1 1 is a diagram of example user interfaces for providing classification, according to various embodiments. As shown, user interface 1101 presents a user with an animation (e.g., the representation 1001 of FIG. 10) depicting an unknown activity being performed by an avatar. The user is asked to repeat the activity while wearing an activity tracker (e.g., a wrist-worn sensor device) while attempting to perform the activity. [00102] In one embodiment, sensor information is collected from the user is collected from the activity tracker and then compared to the sensor fragment associated with the animation. If the sensor information matches the sensor fragment of the animation within threshold criteria, the user is deemed to have successfully performed the activity as indicated in user interface 1 103. [00103] Because the user has successfully performed the activity, the user is also given the opportunity to provide a label or description of the activity as indicated by the request in user interface 1103. User interface 1105 depicts the user's input "Playing Volleyball" which is submitted to the classification platform 103 for consolidation. For example, if the user's response is voted most highly by the other users or otherwise matches the responses of other users, the classification platform 103 can label the unknown activity as "Playing Volleyball" and establish a new class for its activity classifier.

[00104] The processes described herein for providing classification may be advantageously implemented via software, hardware, firmware or a combination of software and/or firmware and/or hardware. For example, the processes described herein, may be advantageously implemented via processor(s), Digital Signal Processing (DSP) chip, an

Application Specific Integrated Circuit (ASIC), Field Programmable Gate Arrays (FPGAs), etc. Such exemplary hardware for performing the described functions is detailed below. [00105] FIG. 12 illustrates a computer system 1200 upon which an embodiment of the invention may be implemented. Although computer system 1200 is depicted with respect to a particular device or equipment, it is contemplated that other devices or equipment (e.g., network elements, servers, etc.) within FIG. 12 can deploy the illustrated hardware and components of system 1200. Computer system 1200 is programmed (e.g., via computer program code or instructions) to provide classification as described herein and includes a communication mechanism such as a bus 1210 for passing information between other internal and external components of the computer system 1200. Information (also called data) is represented as a physical expression of a measurable phenomenon, typically electric voltages, but including, in other embodiments, such phenomena as magnetic, electromagnetic, pressure, chemical, biological, molecular, atomic, sub-atomic and quantum interactions. For example, north and south magnetic fields, or a zero and non-zero electric voltage, represent two states (0, 1) of a binary digit (bit). Other phenomena can represent digits of a higher base. A superposition of multiple simultaneous quantum states before measurement represents a quantum bit (qubit). A sequence of one or more digits constitutes digital data that is used to represent a number or code for a character. In some embodiments, information called analog data is represented by a near continuum of measurable values within a particular range. Computer system 1200, or a portion thereof, constitutes a means for performing one or more steps of providing classification. [00106] A bus 1210 includes one or more parallel conductors of information so that information is transferred quickly among devices coupled to the bus 1210. One or more processors 1202 for processing information are coupled with the bus 1210.

[00107] A processor (or multiple processors) 1202 performs a set of operations on information as specified by computer program code related to providing classification. The computer program code is a set of instructions or statements providing instructions for the operation of the processor and/or the computer system to perform specified functions. The code, for example, may be written in a computer programming language that is compiled into a native instruction set of the processor. The code may also be written directly using the native instruction set (e.g., machine language). The set of operations include bringing information in from the bus 1210 and placing information on the bus 1210. The set of operations also typically include comparing two or more units of information, shifting positions of units of information, and combining two or more units of information, such as by addition or multiplication or logical operations like OR, exclusive OR (XOR), and AND. Each operation of the set of operations that can be performed by the processor is represented to the processor by information called instructions, such as an operation code of one or more digits. A sequence of operations to be executed by the processor 1202, such as a sequence of operation codes, constitute processor instructions, also called computer system instructions or, simply, computer instructions. Processors may be implemented as mechanical, electrical, magnetic, optical, chemical or quantum components, among others, alone or in combination.

[00108] Computer system 1200 also includes a memory 1204 coupled to bus 1210. The memory 1204, such as a random access memory (RAM) or any other dynamic storage device, stores information including processor instructions for providing classification. Dynamic memory allows information stored therein to be changed by the computer system 1200. RAM allows a unit of information stored at a location called a memory address to be stored and retrieved independently of information at neighboring addresses. The memory 1204 is also used by the processor 1202 to store temporary values during execution of processor instructions. The computer system 1200 also includes a read only memory (ROM) 1206 or any other static storage device coupled to the bus 1210 for storing static information, including instructions, that is not changed by the computer system 1200. Some memory is composed of volatile storage that loses the information stored thereon when power is lost. Also coupled to bus 1210 is a non-volatile (persistent) storage device 1208, such as a magnetic disk, optical disk or flash card, for storing information, including instructions, that persists even when the computer system 1200 is turned off or otherwise loses power.

[00109] Information, including instructions for providing classification, is provided to the bus 1210 for use by the processor from an external input device 1212, such as a keyboard containing alphanumeric keys operated by a human user, or a sensor. A sensor detects conditions in its vicinity and transforms those detections into physical expression compatible with the measurable phenomenon used to represent information in computer system 1200. Other external devices coupled to bus 1210, used primarily for interacting with humans, include a display device 1214, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a light emitting diode (LED) display, an organic LED (OLED) display, a plasma screen, or a printer for presenting text or images, and a pointing device

1216, such as a mouse, a trackball, cursor direction keys, or a motion sensor, for controlling a position of a small cursor image presented on the display 1214 and issuing commands associated with graphical elements presented on the display 1214. In some embodiments, for example, in embodiments in which the computer system 1200 performs all functions automatically without human input, one or more of external input device 1212, display device 1214 and pointing device 1216 is omitted. [00110] In the illustrated embodiment, special purpose hardware, such as an application specific integrated circuit (ASIC) 1220, is coupled to bus 1210. The special purpose hardware is configured to perform operations not performed by processor 1202 quickly enough for special purposes. Examples of ASICs include graphics accelerator cards for generating images for display 1214, cryptographic boards for encrypting and decrypting messages sent over a network, speech recognition, and interfaces to special external devices, such as robotic arms and medical scanning equipment that repeatedly perform some complex sequence of operations that are more efficiently implemented in hardware.

[00111] Computer system 1200 also includes one or more instances of a communications interface 1270 coupled to bus 1210. Communication interface 1270 provides a one-way or two-way communication coupling to a variety of external devices that operate with their own processors, such as printers, scanners and external disks. In general the coupling is with a network link 1278 that is connected to a local network 1280 to which a variety of external devices with their own processors are connected. For example, communication interface 1270 may be a parallel port or a serial port or a universal serial bus (USB) port on a personal computer. In some embodiments, communications interface 1270 is an integrated services digital network (ISDN) card or a digital subscriber line (DSL) card or a telephone modem that provides an information communication connection to a corresponding type of telephone line. In some embodiments, a communication interface 1270 is a cable modem that converts signals on bus 1210 into signals for a communication connection over a coaxial cable or into optical signals for a communication connection over a fiber optic cable. As another example, communications interface 1270 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN, such as Ethernet. Wireless links may also be implemented. For wireless links, the communications interface 1270 sends or receives or both sends and receives electrical, acoustic or electromagnetic signals, including infrared and optical signals, that carry information streams, such as digital data. For example, in wireless handheld devices, such as mobile telephones like cell phones, the communications interface 1270 includes a radio band electromagnetic transmitter and receiver called a radio transceiver. In certain embodiments, the communications interface 1270 enables connection to the communication network 105 for providing classification to the UE 101.

[00112] The term "computer-readable medium" as used herein refers to any medium that participates in providing information to processor 1202, including instructions for execution. Such a medium may take many forms, including, but not limited to computer- readable storage medium (e.g., non-volatile media, volatile media), and transmission media. Non-transitory media, such as non-volatile media, include, for example, optical or magnetic disks, such as storage device 1208. Volatile media include, for example, dynamic memory 1204. Transmission media include, for example, twisted pair cables, coaxial cables, copper wire, fiber optic cables, and carrier waves that travel through space without wires or cables, such as acoustic waves and electromagnetic waves, including radio, optical and infrared waves. Signals include man-made transient variations in amplitude, frequency, phase, polarization or other physical properties transmitted through the transmission media. Common forms of computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, CDRW, DVD, any other optical medium, punch cards, paper tape, optical mark sheets, any other physical medium with patterns of holes or other optically recognizable indicia, a RAM, a PROM, an EPROM, a FLASH-EPROM, an EEPROM, a flash memory, any other memory chip or cartridge, a carrier wave, or any other medium from which a computer can read. The term computer-readable storage medium is used herein to refer to any computer-readable medium except transmission media.

[00113] Logic encoded in one or more tangible media includes one or both of processor instructions on a computer-readable storage media and special purpose hardware, such as ASIC 1220. [00114] Network link 1278 typically provides information communication using transmission media through one or more networks to other devices that use or process the information. For example, network link 1278 may provide a connection through local network 1280 to a host computer 1282 or to equipment 1284 operated by an Internet Service Provider (ISP). ISP equipment 1284 in turn provides data communication services through the public, world-wide packet-switching communication network of networks now commonly referred to as the Internet 1290. [00115] A computer called a server host 1292 connected to the Internet hosts a process that provides a service in response to information received over the Internet. For example, server host 1292 hosts a process that provides information representing video data for presentation at display 1214. It is contemplated that the components of system 1200 can be deployed in various configurations within other computer systems, e.g., host 1282 and server 1292.

[00116] At least some embodiments of the invention are related to the use of computer system 1200 for implementing some or all of the techniques described herein. According to one embodiment of the invention, those techniques are performed by computer system 1200 in response to processor 1202 executing one or more sequences of one or more processor instructions contained in memory 1204. Such instructions, also called computer instructions, software and program code, may be read into memory 1204 from another computer-readable medium such as storage device 1208 or network link 1278. Execution of the sequences of instructions contained in memory 1204 causes processor 1202 to perform one or more of the method steps described herein. In alternative embodiments, hardware, such as ASIC 1220, may be used in place of or in combination with software to implement the invention. Thus, embodiments of the invention are not limited to any specific combination of hardware and software, unless otherwise explicitly stated herein.

[00117] The signals transmitted over network link 1278 and other networks through communications interface 1270, carry information to and from computer system 1200. Computer system 1200 can send and receive information, including program code, through the networks 1280, 1290 among others, through network link 1278 and communications interface 1270. In an example using the Internet 1290, a server host 1292 transmits program code for a particular application, requested by a message sent from computer 1200, through Internet 1290, ISP equipment 1284, local network 1280 and communications interface 1270. The received code may be executed by processor 1202 as it is received, or may be stored in memory 1204 or in storage device 1208 or any other non- volatile storage for later execution, or both. In this manner, computer system 1200 may obtain application program code in the form of signals on a carrier wave. [00118] Various forms of computer readable media may be involved in carrying one or more sequence of instructions or data or both to processor 1202 for execution. For example, instructions and data may initially be carried on a magnetic disk of a remote computer such as host 1282. The remote computer loads the instructions and data into its dynamic memory and sends the instructions and data over a telephone line using a modem. A modem local to the computer system 1200 receives the instructions and data on a telephone line and uses an infra-red transmitter to convert the instructions and data to a signal on an infra-red carrier wave serving as the network link 1278. An infrared detector serving as communications interface 1270 receives the instructions and data carried in the infrared signal and places information representing the instructions and data onto bus 1210. Bus 1210 carries the information to memory 1204 from which processor 1202 retrieves and executes the instructions using some of the data sent with the instructions. The instructions and data received in memory 1204 may optionally be stored on storage device 1208, either before or after execution by the processor 1202.

[00119] FIG. 13 illustrates a chip set or chip 1300 upon which an embodiment of the invention may be implemented. Chip set 1300 is programmed to provide classification as described herein and includes, for instance, the processor and memory components described with respect to FIG. 12 incorporated in one or more physical packages (e.g., chips). By way of example, a physical package includes an arrangement of one or more materials, components, and/or wires on a structural assembly (e.g., a baseboard) to provide one or more characteristics such as physical strength, conservation of size, and/or limitation of electrical interaction. It is contemplated that in certain embodiments the chip set 1300 can be implemented in a single chip. It is further contemplated that in certain embodiments the chip set or chip 1300 can be implemented as a single "system on a chip." It is further contemplated that in certain embodiments a separate ASIC would not be used, for example, and that all relevant functions as disclosed herein would be performed by a processor or processors. Chip set or chip 1300, or a portion thereof, constitutes a means for performing one or more steps of providing user interface navigation information associated with the availability of functions. Chip set or chip 1300, or a portion thereof, constitutes a means for performing one or more steps of providing classification.

[00120] In one embodiment, the chip set or chip 1300 includes a communication mechanism such as a bus 1301 for passing information among the components of the chip set 1300. A processor 1303 has connectivity to the bus 1301 to execute instructions and process information stored in, for example, a memory 1305. The processor 1303 may include one or more processing cores with each core configured to perform independently.

A multi-core processor enables multiprocessing within a single physical package. Examples of a multi-core processor include two, four, eight, or greater numbers of processing cores. Alternatively or in addition, the processor 1303 may include one or more microprocessors configured in tandem via the bus 1301 to enable independent execution of instructions, pipelining, and multithreading. The processor 1303 may also be accompanied with one or more specialized components to perform certain processing functions and tasks such as one or more digital signal processors (DSP) 1307, or one or more application-specific integrated circuits (ASIC) 1309. A DSP 1307 typically is configured to process real-world signals (e.g., sound) in real time independently of the processor 1303. Similarly, an ASIC 1309 can be configured to performed specialized functions not easily performed by a more general purpose processor. Other specialized components to aid in performing the inventive functions described herein may include one or more field programmable gate arrays (FPGA) (not shown), one or more controllers (not shown), or one or more other special-purpose computer chips.

[00121] In one embodiment, the chip set or chip 1300 includes merely one or more processors and some software and/or firmware supporting and/or relating to and/or for the one or more processors.

[00122] The processor 1303 and accompanying components have connectivity to the memory 1305 via the bus 1301. The memory 1305 includes both dynamic memory (e.g., RAM, magnetic disk, writable optical disk, etc.) and static memory (e.g., ROM, CD-ROM, etc.) for storing executable instructions that when executed perform the inventive steps described herein to provide classification. The memory 1305 also stores the data associated with or generated by the execution of the inventive steps.

[00123] FIG. 14 is a diagram of exemplary components of a mobile terminal (e.g., handset) for communications, which is capable of operating in the system of FIG. 1, according to one embodiment. In some embodiments, mobile terminal 1401, or a portion thereof, constitutes a means for performing one or more steps of providing classification. Generally, a radio receiver is often defined in terms of front-end and back-end characteristics. The front-end of the receiver encompasses all of the Radio Frequency (RF) circuitry whereas the back-end encompasses all of the base-band processing circuitry. As used in this application, the term "circuitry" refers to both: (1) hardware-only implementations (such as implementations in only analog and/or digital circuitry), and (2) to combinations of circuitry and software (and/or firmware) (such as, if applicable to the particular context, to a combination of processor(s), including digital signal processor(s), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions). This definition of "circuitry" applies to all uses of this term in this application, including in any claims. As a further example, as used in this application and if applicable to the particular context, the term "circuitry" would also cover an implementation of merely a processor (or multiple processors) and its (or their) accompanying software/or firmware. The term "circuitry" would also cover if applicable to the particular context, for example, a baseband integrated circuit or applications processor integrated circuit in a mobile phone or a similar integrated circuit in a cellular network device or other network devices.

[00124] Pertinent internal components of the telephone include a Main Control Unit (MCU) 1403, a Digital Signal Processor (DSP) 1405, and a receiver/transmitter unit including a microphone gain control unit and a speaker gain control unit. A main display unit 1407 provides a display to the user in support of various applications and mobile terminal functions that perform or support the steps of providing classification. The display 1407 includes display circuitry configured to display at least a portion of a user interface of the mobile terminal (e.g., mobile telephone). Additionally, the display 1407 and display circuitry are configured to facilitate user control of at least some functions of the mobile terminal. An audio function circuitry 1409 includes a microphone 1411 and microphone amplifier that amplifies the speech signal output from the microphone 141 1. The amplified speech signal output from the microphone 1411 is fed to a coder/decoder (CODEC) 1413.

[00125] A radio section 1415 amplifies power and converts frequency in order to communicate with a base station, which is included in a mobile communication system, via antenna 1417. The power amplifier (PA) 1419 and the transmitter/modulation circuitry are operationally responsive to the MCU 1403, with an output from the PA 1419 coupled to the duplexer 1421 or circulator or antenna switch, as known in the art. The PA 1419 also couples to a battery interface and power control unit 1420.

[00126] In use, a user of mobile terminal 1401 speaks into the microphone 1411 and his or her voice along with any detected background noise is converted into an analog voltage. The analog voltage is then converted into a digital signal through the Analog to Digital Converter (ADC) 1423. The control unit 1403 routes the digital signal into the DSP 1405 for processing therein, such as speech encoding, channel encoding, encrypting, and interleaving. In one embodiment, the processed voice signals are encoded, by units not separately shown, using a cellular transmission protocol such as enhanced data rates for global evolution (EDGE), general packet radio service (GPRS), global system for mobile communications (GSM), Internet protocol multimedia subsystem (IMS), universal mobile telecommunications system (UMTS), etc., as well as any other suitable wireless medium, e.g., microwave access (WiMAX), Long Term Evolution (LTE) networks, code division multiple access (CDMA), wideband code division multiple access (WCDMA), wireless fidelity (WiFi), satellite, and the like, or any combination thereof.

[00127] The encoded signals are then routed to an equalizer 1425 for compensation of any frequency-dependent impairments that occur during transmission though the air such as phase and amplitude distortion. After equalizing the bit stream, the modulator 1427 combines the signal with a RF signal generated in the RF interface 1429. The modulator 1427 generates a sine wave by way of frequency or phase modulation. In order to prepare the signal for transmission, an up-converter 1431 combines the sine wave output from the modulator 1427 with another sine wave generated by a synthesizer 1433 to achieve the desired frequency of transmission. The signal is then sent through a PA 1419 to increase the signal to an appropriate power level. In practical systems, the PA 1419 acts as a variable gain amplifier whose gain is controlled by the DSP 1405 from information received from a network base station. The signal is then filtered within the duplexer 1421 and optionally sent to an antenna coupler 1435 to match impedances to provide maximum power transfer. Finally, the signal is transmitted via antenna 1417 to a local base station. An automatic gain control (AGC) can be supplied to control the gain of the final stages of the receiver. The signals may be forwarded from there to a remote telephone which may be another cellular telephone, any other mobile phone or a land-line connected to a Public Switched Telephone Network (PSTN), or other telephony networks.

[00128] Voice signals transmitted to the mobile terminal 1401 are received via antenna 1417 and immediately amplified by a low noise amplifier (LNA) 1437. A down-converter 1439 lowers the carrier frequency while the demodulator 1441 strips away the RF leaving only a digital bit stream. The signal then goes through the equalizer 1425 and is processed by the DSP 1405. A Digital to Analog Converter (DAC) 1443 converts the signal and the resulting output is transmitted to the user through the speaker 1445, all under control of a Main Control Unit (MCU) 1403 which can be implemented as a Central Processing Unit (CPU) (not shown). [00129] The MCU 1403 receives various signals including input signals from the keyboard 1447. The keyboard 1447 and/or the MCU 1403 in combination with other user input components (e.g., the microphone 141 1) comprise a user interface circuitry for managing user input. The MCU 1403 runs a user interface software to facilitate user control of at least some functions of the mobile terminal 1401 to provide classification. The MCU 1403 also delivers a display command and a switch command to the display 1407 and to the speech output switching controller, respectively. Further, the MCU 1403 exchanges information with the DSP 1405 and can access an optionally incorporated SIM card 1449 and a memory 1451. In addition, the MCU 1403 executes various control functions required of the terminal. The DSP 1405 may, depending upon the implementation, perform any of a variety of conventional digital processing functions on the voice signals. Additionally, DSP 1405 determines the background noise level of the local environment from the signals detected by microphone 141 1 and sets the gain of microphone 1411 to a level selected to compensate for the natural tendency of the user of the mobile terminal 1401.

[00130] The CODEC 1413 includes the ADC 1423 and DAC 1443. The memory 1451 stores various data including call incoming tone data and is capable of storing other data including music data received via, e.g., the global Internet. The software module could reside in RAM memory, flash memory, registers, or any other form of writable storage medium known in the art. The memory device 1451 may be, but not limited to, a single memory, CD, DVD, ROM, RAM, EEPROM, optical storage, magnetic disk storage, flash memory storage, or any other non-volatile storage medium capable of storing digital data.

[00131] An optionally incorporated SIM card 1449 carries, for instance, important information, such as the cellular phone number, the carrier supplying service, subscription details, and security information. The SIM card 1449 serves primarily to identify the mobile terminal 1401 on a radio network. The card 1449 also contains a memory for storing a personal telephone number registry, text messages, and user specific mobile terminal settings.

[00132] While the invention has been described in connection with a number of embodiments and implementations, the invention is not so limited but covers various obvious modifications and equivalent arrangements, which fall within the purview of the appended claims. Although features of the invention are expressed in certain combinations among the claims, it is contemplated that these features can be arranged in any combination and order.