TECHNICAL FIELD

[001] The present disclosure in general relates to validation of proficiency. More particularly, the present invention relates to a platform for validation of proficiency of a user for an activity. The present disclosure relates to species estimation, more particularly relates to a system and a method for estimating species density in a defined geographical location.

BACKGROUND

[002] In today's fast-paced world, there is a growing interest in activities and sports among individuals seeking to improve their skills, knowledge, and overall proficiency. Traditionally, people would rely on physical training sessions, face-to-face interactions, and local coaching to enhance their abilities. However, these conventional approaches often limit the opportunities for learning and growth due to geographical constraints, limited access to expert coaches, and lack of peer feedback.

[003] With the advancement of digital technologies and the wide spread availability of internet connectivity, online platforms have emerged as a popular medium for learning and skill development. Numerous platforms exist today, offering tutorials, video lessons, and pre-recorded content to aid users in their pursuit of proficiency. While these platforms have been beneficial, they often lack the dynamic interaction and personalized feedback that come from direct human engagement.

[004] There is a need, therefore, for an improved platform that enables individuals to engage in real-time, interactive sessions with peers, coaches, and mentors from around the world. Such a platform should provide a means for users to validate their proficiency, receive personalized feedback, and track their progress over time.

[005] Further there is a need in the art for a platform that enables peer to peer interaction, coach to student interaction, and/or validation of the proficiency of a user for an activity or a sport. OBJECTS OF THE INVENTION

[006] A primary object of the present disclosure is to provide a system and a method to calculate a probabilistic measurement of a user’s activities and abilities to perform specific activities within the Sports and Athletics domain.

[007] Another object of the present disclosure is to build a trust score to enable peer- to-peer transactions and the validity of a user.

[008] Yet another object of the present disclosure is to provide verified identity for an athlete, coach, parent (of under 18 athletes), institutions, admins of the institutions, academies, and retailers to carry out sensitive transactions and build a trusted network of subject matter experts.

SUMMARY

[009] Before the present disclosure for a platform for a validation of proficiency is described, it is to be understood that this application is not limited to the particular systems, and methodologies described, as there can be multiple possible embodiments which are not expressly illustrated in the present disclosure. It is also to be understood that the terminology used in the description is for the purpose of describing the particular versions or embodiments only and is not intended to limit the scope of the present application. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in determining or limiting the scope of the claimed subject matter.

[0010] In an implementation of the present disclosure an improved platform for proficiency validation of a user for an activity is disclosed. The platform comprises an ability to select the activity by the user. Further the user may be allowed to select a role for the defined activity and initial proficiency level. Based on the selected proficiency level the platform may be further configured to validate the proficiency level selected. The validation of the proficiency may be performed by a neural network. The neural network may be trained to capture various parameters and further assign a quantifiable value. Further based on the acceptance of the quantifiable value for the proficiency level by user, the same is published.

[0011] In another implementation a method for validation of proficiency of a user for an activity is disclosed. The method as disclosed comprises capturing a plurality of data for a set of defined parameters. Further the method comprises processing of the plurality of data by a neural network. The neural network may apply regression to the plurality of the data. Further the neural network may be trained to assign quantifiable value or score the processed data. Based on the origin of the data i.e., based on which parameter the data is associated with, the weightage may be assigned and further based on the weightage assigned to each data, the score may be calculated. Further the score may be shared with the user, upon the approval from the user the same may be published on the platform, as part of the profile information of the user.

BRIEF DESCRIPTION OF DRAWINGS

[0012] The detailed description is set forth with reference to the accompanying drawings. The use of the same reference numerals may indicate similar or identical items. Various embodiments may utilize elements and/or components other than those illustrated in the drawings, and some elements and/or components may not be present in various embodiments. Elements and/or components in the figures are not necessarily drawn to scale. Throughout this disclosure, depending on the context, singular and plural terminology may be used interchangeably.

[0013] Figure 1, illustrates an exemplary embodiment in accordance with the present disclosure.

[0014] Figure 2, illustrates an exemplary embodiment of the present platform, in accordance with the present disclosure.

[0015] Figure 3, illustrates the platform, in accordance with the present disclosure.

[0016] Figure 4, illustrates an exemplary embodiment method for proficiency test, in accordance with the disclosure.

[0017] Figure 5, illustrates an exemplary method for assigning a credibility score, in accordance with the present disclosure.

DETAILED DESCRIPTION

[0018] Some embodiments of the present disclosure, illustrating all its features, will now be discussed in detail. It must also be noted that as used herein and in the appended claims, the singular forms "a", "an" and "the" include plural references unless the context clearly dictates otherwise. Various modifications to the embodiment will be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. However, one of ordinary skill in the art will readily recognize that the present disclosure for a platform for a validation of proficiency for an activity is not intended to be limited to the embodiments illustrated but is to be accorded the widest scope consistent with the principles and features described herein.

[0019] In the field of data science, a commonly encountered task revolves around the prediction of binary outcomes, which is referred to as binary classification. The primary objective is to make accurate projections regarding the likelihood of a "favourable" or "unfavourable" outcome in future scenarios, such as a purchase, credit default, or customer churn event.

[0020] To achieve these predictive outcomes, diverse methodologies can be employed. Typically, a model generates outputs in the form of discrete classes (0 or 1, symbolizing favourable or unfavourable outcomes) or rankings (representing varying probabilities associated with specific outcomes). By establishing an optimal threshold based on these probabilities, it becomes possible to assign the appropriate class label and optimize the model's performance with respect to a specific quality measure or metric.

[0021] The present subject matter relates to a platform for a validation of proficiency for an activity selected by a user. The platform as disclosed enables peer to peer to interaction, coach/trainer to student/trainee interaction, e-commerce related functionality for selected activities. The platform may be further configured to generate and assign a score (credibility quote) for the user for a specifically selected activity.

[0022] The credibility score may be generated for each user as part of proficiency test provided by the platform. The proficiency test may be conducted as being language agnostic i.e. using a natural language processing, and sport specific to understand and verify the claimed proficiency of the individual. The credibility score further enables to determine whether the user is above a marked tolerance score for the claimed level of proficiency in the sport. The platform may assigned a specific weightage upon completion of the said parameter, wherein the weightage may range between 3% to 7%.

[0023] Further the credibility score may rely on another parameter based on completion of profile details by the user. Based on the level of completion neural network configured to assign the weightage for credibility score may assign between 5% to 10%. Further the neural network/ Al may also be configured to detect duplicate information, including photos. The credibility score may be further affected based on the association type. The neural network of the Al based on the types of association may assign a value or weightage, association types may relate to the different roles of people associated to a particular profile; athletes, coaches, parents, admins, academies, institutions, retailers, etc. each different association type and their endorsements of the profile, may count towards credibility score.

[0024] The credit score which is part of the proficiency test may be updated real time based on consistency of login on the platform, verification of activities such as posting of scores, achievements which would need endorsement/verification. The platform along with credibility score may be configured to capture and store documents pertaining to the activity or sport selected by the user, the transactions completed over the platform, to evaluate and validate the proficiency and score of the user.

[0025] In an aspect of the present invention a model may be provided for ranking, which signifies the degree of probability for a specific outcome. By determining an optimal threshold based on these probabilities, it becomes feasible to assign the appropriate class and optimize for a specific quality measure or metric.

[0026] Further in another aspect of the present disclosure a probability model may be utilized to assign a ranking or quality score. Further the probability model enables grouping of clients, products, bonds, or companies into different bands or buckets, all based on the predicted outcomes of the model. This form of scoring enables improved precision and granularity with the predictions, allowing for more detailed segmentation. By doing so, it becomes possible to make more informed decisions around risk, profitability, and performance, as well as optimize the actions to take with each of the groupings. The second method is known as “score-to-action”. This approach uses the model to make predictions and then takes an action based on the prediction. Examples of actions include: uploading Identity Documents, verifying a document, opening an account or carrying out a transaction. The benefit of this method is that it allows for real-time optimization and personalization of customer interactions, which can be leveraged across multiple channels (e.g., online and offline).

[0027] In accordance with the aspect of the disclosure the proficiency tests are accompanied by eyeball and head tracking to verify the credibility of the user’s answers and interactions with the question screens. Further, the credibility score may rely on another parameter based on the completion of profile details by the user. Based on the level of completion regression neural network configured to assign the weightage for the credibility score may assign between 5% to 10%.

[0028] Further, the neural network/AI may also be configured to detect duplicate information, including photos. The credibility score may be further affected based on the association type. The neural network of the Al based on the types of association may assign a value or weightage, association types may relate to the different roles of people associated with a particular profile; athletes, coaches, parents, admins, academies, institutions, retailers, etc each different association type and their endorsements of the profile may count towards the credibility score.

[0029] The creditability score may be a part of the proficiency test may be updated in real-time based on consistency of login on the platform, verification of activities such as posting of scores, and achievements which would need endorsement/verification. The platform along with the credibility score may be configured to capture and store documents pertaining to the activity or sport selected by the user, and the transactions completed over the platform, to evaluate and validate the proficiency and score of the user.

[0030] In accordance with an exemplary embodiment, a platform may be configured to communicate with a plurality of devices. The plurality of devices may be handheld devices or any system capable of capturing, storing, transmitting, and/or processing data, wherein data can include videos, photos, documents etc.

[0031] Further, the plurality of devices may have additional apparatus to enable the functions. The plurality of devices may be configured to communicate with the platform over a communication means. Employing the probabilities derived from predictive models, to assign rankings or quality scores akin to credit scores or credit ratings.

[0032] This scoring mechanism facilitates the categorization of clients, products, bonds, or companies into distinct bands or buckets, based on the predicted outcomes generated by the model. By leveraging this approach, organizations can effectively group entities and make informed decisions based on the assessed level of risk or potential for favourable outcomes associated with each entity.

[0033] Probability in the context of odds refers to the likelihood of an event occurring relative to the likelihood of its opposite event occurring. The calculation of odds can be performed using the formula: odds = p/(l-p), where p represents the probability of the event happening. Conversely, to determine the probability based on the odds, the following formula can be used: p = odds/(l+odds).

[0034] For instance, consider an event with a 15 out of 100 chances of occurring. In this case, the probability is 0.15, while the corresponding odds amount to 0.176. It is worth noting that higher probabilities correspond to more favourable odds. Linear regression is a mathematical technique that involves summing variables (x) multiplied by their respective weights (a) to predict a value (y). This relationship is commonly represented as y = b + ax.

[0035] In the context of binary classification, where there are two distinct classes (0 and 1), a sigmoid function is utilized to obtain a predicted value (y) ranging between 0 and 1. This can be expressed as y = LN (odds) or Sum(Bi*Xi) = LN(odds), where LN denotes the natural logarithm. The probability can be determined from the odds using the exponential function: odds = EXP(y), and subsequently, p = EXP(y)/(l+EXP(y)).

[0036] In various industries, a variety of scales are employed to assess and evaluate different phenomena. One widely adopted approach involves the utilization of a scorecard that assigns discrete scores, characterized by a logarithmic scaling pattern. This logarithmic scaling pattern exhibits a unique property where the odds, a measure of likelihood, double at every 20-point increment. To establish a meaningful connection between odds and scores, a linear transformation formula is typically employed. This formula takes the form:

Score = Offset + Factor * LN (odds). In this formulation, the score is determined by incorporating an offset value and a factor that contributes to the linear transformation process. The natural logarithm (LN) of the odds is multiplied by the factor and added to the offset to obtain the corresponding score. This linear transformation allows for the conversion of odds into scores, enabling a comprehensive assessment of the underlying data. By leveraging this approach, industries can effectively evaluate and compare different scenarios, entities, or events using a standardized scoring system.

[0037] The logarithmic scaling pattern and the linear transformation formula provide a robust framework for assigning scores based on odds, facilitating meaningful analysis and decision-making processes. The concept of "points to double the odds" or “PDO” holds great significance in this context. It represents the interval at which odds should be doubled, providing a valuable scaling mechanism for evaluating and comparing different scenarios. In the context of the formula, odds are defined as the ratio between occurrences classified as "Good" and those classified as "Bad". For instance, if a particular score, denoted as Z, corresponds to 100 occurrences classified as "Good" and 1 occurrence classified as "Bad" (100: 1), then a score of (Z+PDO) would represent a shift where 200 occurrences are classified as "Good" and 1 occurrence as "Bad" (odds=200: l).

[0038] This distinction between "Good" and "Bad" is of utmost importance. As mentioned earlier, in the construction of a model, the label 1 is assigned to events deemed "Good" (e.g., desirable clients), while the label 0 is assigned to events considered "Bad" (e.g., undesirable clients). This distinction plays a crucial role, as the label serves as the target variable during model development. The resulting model should be capable of providing the "probability of a client being good," which is equivalent to 1 minus the "probability of default." The scaling Factor, represented as PDO/LN (2), is determined by solving a system of equations. This Factor plays a crucial role in establishing the scaling relationship within the formula, enabling an accurate and meaningful transformation of odds into scores. By determining the appropriate scaling Factor, the formula ensures a consistent and standardized approach to score calculation.

Formulas: Score + PDO = Offset + Factor*LN (2*odds) & Score = Offset + Factor*LN(odds)

[0039] The offset value in the formula is associated with the score assigned when the probability reaches 0.5 or when the odds equal 1 (LN(odds) = 0). With the incorporation of the formula, the log-regression model outcomes can now be transformed into scores. To achieve this, the following steps can be followed:

— Assign a label of 1 to identify good clients and 0 to represent bad clients.

— Identify and select the relevant features required for model training.

— Train the log-regression model and obtain the coefficients (Bi) associated with the selected features.

— Replace the LN (odds) term in the formula with the expression Sum (Bi*Xi), which incorporates the feature coefficients.

[0040] Having performed the above steps, the primary objective now revolves around defining the necessary scaling factors. It is crucial to ensure that doubling the odds results in a score difference equivalent to PDO.

[0041] These alternative versions aim to convey the same information while presenting it in a paraphrased manner, providing a different perspective on the subject matter.

Example 1 : pdo = 20 offset = 200 factor = pdo/np.log(2)

# check double odds effect scorel= offset + factor*np.log(l) #p_bad=0.5, bad=good > odds=l score2= offset + factor*np.log(2) #p_bad=0,3(3) good=2 bad=l score3= offset + factor*np.log(4) #p_bad=0,2 good=4 bad=l print (f Difference 2 and 1 : {score2-scorel } \ nDifference 3 and 2: {score3- score2}’ )

Score from log regression score = offset+factor*sum(np.multiply(coefficients,np.array([l]+case _one))) print (f Score from regression: {round(score,0)}') #score from probability score = offset+factor*np.log(prob_good/(l-prob_good)) print (f Score from probability: {round(score,0)}')

[0042] Better (higher) score means higher probability of being good.

[0043] Figure 1, illustrates an exemplary embodiment of the present disclosure. In accordance with an exemplary embodiment, a platform 100, may be configured to communicate with a plurality of devices 102, — 102n. The plurality of devices 102, may be handheld devices or any system capable of capturing, storing, transmitting, and/or processing data, wherein data can include videos, photos, documents etc. Further the plurality of devices 102, may have additional apparatus to enable the functions.

[0044] The plurality of devices 102, may be configured to communicate with the platform 100 over a communication means 104. The communication meanl04 may include, WiFi, mobile networks or any other channels configured to send and receive data.

[0045] Figure 2, illustrates an exemplary embodiment of the present platform, in accordance with the disclosure. The platform 100, may be configured to capture a first data set of an user 202. The first data set of the user may comprise information related to profile of the user, including choice of activity/sport 204. Further the user may be required to select a role depending on the task selected 206. The role may be in form of performer, trainer, enthusiast.

[0046] The platform 100 may be further configured to verify and validate the level selected by the user for the task, by performing a proficiency test 208. Post conducting the proficiency test, the platform 100 may be configured to display and render the results 210. Further upon acceptance of the of validation score obtained in the proficiency test, same may be published 212.

[0047] Referring now to Figure 3, the platformlOO is illustrated in accordance with an embodiment of the present subject matter. In one embodiment, the platformlOO may include one processor 302, an input/output (I/O) interfaces 303, and one memory 304. The processor 302 may be implemented as microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor 302 is configured to fetch and execute computer- readable instructions stored in the memory 304.

[0048] The I/O interface 303 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I/O interface 303 may allow the platform 100 to interact with a user directly or through the client devices. Further, the I/O interface 303 may enable the platform 100 to communicate with other computing devices, such as web servers and external data servers (not shown). The VO interface 303 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. The VO interface 303 may include one or more ports for connecting a number of devices to one another or to another server.

[0049] The memory 304 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. The memory 304 may include modules 305 and database 312.

[0050] The programmed instructions/modules 305 include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement particular abstract data types. In one implementation, the modules 305 may include a calibration module 306, data module 308, and a randomising module 310.

[0051] The database 312, amongst other things, serves as a repository for storing data processed, received, and generated by one or more of the modules 305. The database 312 may also include other database 314.

[0052] Figure 4, illustrates an exemplary embodiment method for proficiency test, in accordance with the disclosure. The proficiency test may comprise, initiation of calibration test 402 performed by a calibration module 306, wherein physical aspect of the user need to perform the task are calibrated. For e.g. an user who has selected archery as an activity, the calibration module 306 may capture the eye movements. Further a data module 308 may be configured to retrieve relevant data pertaining to the selected task 404. Further randomising module 310, may randomly render the relevant data to the user to capture reaction, or inputs 406 to the relevant data to obtain intermediary data. Further the intermediary data may processed and analysed 408 to obtain final data. Further the final data may be compared against the proficiency selected by the user to validate the same 410 and further publish the same if accepted by the user 412.

[0053] Figure 5, illustrates an exemplary method for assigning a credibility score, in accordance with the present disclosure. The platform 100, may be configured to assign a credibility score to each profile on the platform 100. The method for assigning the credibility score comprises, receiving a real time request for credibility score 502.

Further retrieve data of the user with respect to selected or defined parameters 504. A neural network perform regression, processing and analysis of the plurality of data captured for each aspect of the defined parameters 506. For e.g. the parameters may include completion of proficiency test, user profile data, verified information from coaches or institutes, documentary evidence, etc.

[0054] Once the neural network processed the plurality of data for the defined parameters a score is generated and assigned to the user 508. Further based on the acceptance of the score by the user the same is displayed 510.