TECHNICAL FIELD

[0001] The present disclosure generally relates to systems and methods for estrus detection in milch animals. More particularly, the present disclosure relates to a system and method for estrus detection in milch animals with the system and the method being based on machine learning principles and techniques.

BACKGROUND

[0002] Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.

[0003] Milch animals are an important part of any economy and thus technologies associated with such aspects are of great interest. There are many aspects and limitations associated with this and one is the problem of low success rates of artificial insemination procedures. One important reason for the same is that the timing of the procedure plays an important parameter in the success rate. Currently the farmers/technicians use their traditional method of guessing/estimating the right time of insemination.

[0004] Second, attached to this limitation of artificial insemination is the problem of predicting the right time for feeding and the optimal mix of feed to ensure a good conception and best milk output. Many attempts have been made in the prior art to formulate a solution for the above-mentioned problems. While attempts have been based on many methods known in the art, machine learning based solutions leave open substantial room for improvement. For example, one limitation is that of learning the actual right time based on ground realities. [0005] There is, therefore, a need in the art to provide an efficient, improved, and cost-effective apparatus/system to overcome the above-mentioned problems, and, provide a reliable means for estrus detection.

OBJECTS OF THE PRESENT DISCLOSURE

[0006] Some of the objects of the present disclosure, which at least one embodiment herein satisfies are as listed herein below. [0007] It is an object of the present disclosure to provide a machine learning based system and method for estrus detection in milch animals.

[0008] It is another object of the present disclosure to provide a system and method for estrus detection in milch animals that affords optimum conditions for insemination in milch animals.

[0009] It is another object of the present disclosure to provide a machine learning based system and method for optimally managing nutrition in milch animals.

[0010] It is another object of the present disclosure to provide a machine learning based system and method for estrus detection in milch animals by means of sampling of various parameters associated with a respective milch animal.

SUMMARY

[0011] The present disclosure generally relates to systems and methods for estrus detection in milch animals. More particularly, the present disclosure relates to a system and method for estrus detection in milch animals with the system and the method being based on machine learning principles and techniques.

BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are included to provide a further understanding of the present disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0013] The diagrams are for illustration only, which thus is not a limitation of the present disclosure, and wherein:

[0014] FIG. 1 illustrates a schematic representation of an exemplary estrus detection system 100 for use in milch animals, in accordance with an embodiment of the present disclosure.

[0015] FIG. 2 illustrates yet again a schematic representation of the estrus detection system with a focus on a sampling functional aspect of the system 100, in accordance with an embodiment of the present disclosure.

[0016] FIG. 3A illustrates a schematic representation of an exemplary sampling functional aspect of the estrus detection system with a focus on a sampling functional aspect of the system, in accordance with an embodiment of the present disclosure. [0017] FIG. 3B illustrates varying timescales with regards to estimating a required parameter sampling rate, in accordance with an embodiment of the present disclosure.

[0018] FIG. 4 illustrates a plot indicating a possibility of converging on an undesired

HMM sample rather than a desired HMM sample with respect to the remote intelligence module of the cloud server system, in accordance with an embodiment of the present disclosure.

DETAILED DESCRIPTION

[0019] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.

[0020] Various terms as used herein are shown below. To the extent a term used in a claim is not defined below, it should be given the broadest definition persons in the pertinent art have given that term as reflected in printed publications and issued patents at the time of filing.

[0021] In some embodiments, the numerical parameters set forth in the written description and attached claims are approximations that can vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the invention are approximations, the numerical values set forth in the specific examples are reported as precisely as practicable. The numerical values presented in some embodiments of the invention may contain certain errors necessarily resulting from the standard deviation found in their respective testing measurements.

[0022] As used in the description herein and throughout the claims that follow, the meaning of “a,” “an,” and “the” includes plural reference unless the context clearly dictates otherwise. Also, as used in the description herein, the meaning of “in” includes “in” and “on” unless the context clearly dictates otherwise.

[0023] The recitation of ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise indicated herein, each individual value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g. “such as”) provided with respect to certain embodiments herein is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention otherwise claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the invention.

[0024] Groupings of alternative elements or embodiments of the invention disclosed herein are not to be construed as limitations. Each group member can be referred to and claimed individually or in any combination with other members of the group or other elements found herein. One or more members of a group can be included in, or deleted from, a group for reasons of convenience and/or patentability. When any such inclusion or deletion occurs, the specification is herein deemed to contain the group as modified thus fulfilling the written description of all groups used in the appended claims.

[0025] The present disclosure generally relates to systems and methods for estrus detection in milch animals. More particularly, the present disclosure relates to a system and method for estrus detection in milch animals with the system and the method being based on machine learning principles and techniques.

[0026] FIG. 1 illustrates a schematic representation of an exemplary estrus detection system 100 for use in milch animals, in accordance with an embodiment of the present disclosure. The estrus detection system 100 typically includes a target system 110, and a cloud server system 120. The target system 110 further includes a target animal 112 upon which a plurality of estrus onset measuring devices 114 are attached in addition to an insemination gun 116. Each of the plurality of estrus onset measuring devices 114 are configured to monitor and transmit first parameters associated with onset of estrus period in the given target animal 112, and are also configured to monitor and transmit second parameters associated with optimum feed input that can allow proper nutrition and which nutrition is focused on achieving further optimum conditions for the onset of the estrus period in the target animal 112. Typically, the measuring devices 114 are sensors known in the art and can be attached at various places on the target animal 112. In some embodiments, the plurality measuring devices 114 can include other mechanisms or devices that are capable of monitoring and transmitting the first parameters and the second parameters with respect to each of the plurality of measuring devices 114. [0027] The cloud server system 120 is based on machine learning principles and techniques, and includes a predicting module 122, a remote intelligence module 124, and an actuating module 126. The cloud server system 120 is typically operatively connected to the target system 110 by appropriate means known in the art and typically involves communication on at least an information level. In particular, the predicting module 122 and the actuating module 126 of the cloud server system 120 are operatively connected to the insemination gun 116 and are, in tandem or individually, configured to cause the insemination gun 116 to inseminate the target animal 112 after the onset of estrus period in the target animal 112. With regards to the modules 122, 124, 126, they are capable of operating in tandem or in conjunction with each other or otherwise can operate individually with regards to the respective functions as is heretofore described.

[0028] The plurality of estrus onset measuring devices 114 includes at least one such measuring device 114 in an embodiment and can include the mentioned plurality in other embodiments as can be seen in FIG. 1 which shows a target animal 112 have a first estrus onset measuring device 114-1 and an ‘n’ number of estrus onset measuring device 114-n. [0029] As can be appreciated, the target animal 112 is a female milch animal preferably cattle including cows, goats, buffaloes, and the like. In other embodiments, the target animal 112 can include other kinds and types of animals based on their respective application, and as can further be appreciated by a person skilled in the art.

[0030] In an embodiment, the insemination gun 116 can be a distinct mechanism with respect to the target system 110 and the cloud server system 120. In an embodiment, the insemination gun 116 is video insemination gun allowing a user to view respective portions of the target animal 112. This user can be a qualified professional known in the art.

[0031] The plurality of measuring devices 114 are close contact devices consisting of battery, small computer, sensors and are tied to the target animal 112 on foot, neck, tail or other body parts for good and faithful measurement. In principle, the location of these measuring devices 114 depends on the first parameters and the second parameters and as such, they can be located on various places associated with the target animal 112.

[0032] Referring again to FIG. 1, the estrus detection system 100 can include an ‘n’ number of target animals (indicated as 112-n) upon which a number of measuring devices (either the same as 114 or other devices known in the art) can be implemented.

[0033] FIG. 2 illustrates yet again a schematic representation of the estrus detection system 100 with a focus on a sampling functional aspect of the system 100, in accordance with an embodiment of the present disclosure. The sampling functional aspect of the estrus detection system 100 is based on machine learning principles and techniques, and in particular, those associated with Hidden Markov Models (hereinafter “HMM” and its respective derivatives). As shown in FIG. 2, the sampling functional aspect is derived and is associated with the predicting module 122 and the remote intelligence module 124. The sampling, learning, and prediction aspects can be governed by algorithm aspects including Baum-Welch estimation for finding hidden parameters associated with the HMM samples. [0034] The sampling function is performed with respect to the aforementioned first parameters and second parameters at varying timescales, and can include varying various degrees of sampling as shown. The sampling function is as known in the art and it may occur that various transmissions of the sampled respective parameters may be lost.

[0035] FIG. 3A illustrates a schematic representation of an exemplary sampling functional aspect of the estrus detection system 100 with a focus on a sampling functional aspect of the system 100 while FIG. 3B illustrates varying timescales with regards to estimating a required parameter sampling rates, in accordance with an embodiment of the present disclosure. In an embodiment, the measuring devices 114 (represented in FIG. 1) are tags known in the art and can include radio frequency (RF), infrared (IR), Bluetooth (BT), and other such systems or transmission systems known in the art. As mentioned, these tags can be attached to various portions of the target animal 112 and the portions or the locations on the target animal 112 can be based on the first parameters and the second parameters. [0036] FIG. 4 illustrates a plot indicating a possibility of converging on undesired and estimated HMM results rather than desired and estimated HMM results with respect to the remote intelligence module of the cloud server system, in accordance with an embodiment of the present disclosure. In particular, there is a need to ensure that the existence of a HMM at multiple timescales is detected and the appropriate one corresponding to a given estrus cycle is used. For instance, this is achieved by checking the consistency of the estimates across multiple random sampling at various rates. Referring now to FIG. 4, as can be appreciated, in a transition probability matrix of dimension 2x2, there may be two intended hidden states. For example, when ‘n’ samples are received from the target animal 112, a timescale of interest is initially identified and a candidate value of A[0,0] and A[l,l] is estimated following which an e-ball around this target is drawn as shown. Thus, for one iteration, there can be a random sampling of the ordered sequence to get a target timescale. For example, if the time-scale of one cycle is 25 days, then the 5 month data is sampled with probability 1/6, 2/6, 3/6, 4/6, 5/6, 1, and so on. For each probability, multiple sample sequences are taken and the estimates of A that are far away from each other are discarded. Finally, an appropriate average of these estimates are taken for use and is stored in the cloud server system 120 for further use.

[0037] In an embodiment, the estrus detection system 100 also can automatically label the various learnt parameters (first and second parameters) of the trained model used in the machine learning algorithm. These can be used at a later stage.

[0038] Thus, an aspect of the present disclosure pertains to a system with mounted- sensors (primary equipment, measuring device), a cloud server (predicting module, remote intelligence server), a video insemination gun (secondary equipment, verifying device) to learn and predict the right time to inseminate.

[0039] Another aspect of the present disclosure pertains to a system with mounted- sensors, a cloud server, a video insemination gun to learn and predict the right mix of feed to ensure the best animal health resulting into better conception and better milk yield.

[0040] Another aspect of the present disclosure pertains to a mechanism to alert the user including - alert on mobile app, sms, a beacon on the band, alerts on the insemination gun.

[0041] In an aspect, the primary equipment are close contact device consisting of battery, small computer, sensors and are tied to the animal on foot, neck, tail or other body parts for good and faithful measurement.

[0042] In an aspect, the system includes an intelligence server which can be cloud based or distributed model based.

[0043] Another aspect of the present disclosure pertains to a method to determine the target performance using the (a.P)-currcncy approach that ensures that the used machine learning algorithm provides a classification that is at least a% reliable and b time units recent, i.e., the estrus period has started at most b time units in past.

[0044] In an aspect, a method to estimate the required parameter sampling rates (by the sensors attached to cow) to achieve the set (a^)-currency performance A.

[0045] In an aspect, a method to ensure that the existence of hidden Markov model at multiple timescales is detected and the appropriate one corresponding to the Estrus cycle is used

[0046] In an aspect, a method to automatically label the various learnt parameters of the trained model used in machine learning algorithm.

[0047] Thus, the present disclosure solves the problem of low success rates of artificial insemination procedures. One important reason is that the timing of the procedure plays an important parameter in the success rate. Currently the farmers/technician use their traditional method of guessing/estimating the right time of insemination. Notwithstanding anything to the contrary in this document, the present disclosure includes a set of sensors mounted on cattle for instance and these sensors continuously send measured parameters to a cloud based server. The server uses machine learning algorithms to predict the right time of insemination and alerts the farmer about it. The present disclosure also provides a video enabled insemination gun to perform the actual procedure and to also record the procedure and analyze attendant conditions and the performance of the procedure.

[0048] The present disclosure attempts to improve the performance of a machine learning module by learning the actual and appropriate time based on ground realities. For example, the video enabled gun measures an appropriate time of insemination and communicates the same to a cloud server. By getting this measurement the performance of the prediction improves. The present disclosure also provides a solution by using measured parameters to predict the appropriate time for feeding in addition to an optimal mix of feed to ensure good conception and best milk output.

[0049] Embodiments of the present disclosure may be implemented entirely hardware, entirely software (including firmware, resident software, micro-code, etc.) or combining software and hardware implementation that may all generally be referred to herein as a “circuit,” “engine,” “component,” or “system.” Furthermore, aspects of the present disclosure may take the form of a computer program product comprising one or more computer readable media having computer readable program code embodied thereon.

[0050] Thus, it will be appreciated by those of ordinary skill in the art that the diagrams, schematics, illustrations, and the like represent conceptual views or processes illustrating systems and methods embodying this invention. The functions of the various elements shown in the figures may be provided through the use of dedicated hardware as well as hardware capable of executing associated software. Similarly, any switches shown in the figures are conceptual only. Their function may be carried out through the operation of program logic, through dedicated logic, through the interaction of program control and dedicated logic, or even manually, the particular technique being selectable by the entity implementing this invention. Those of ordinary skill in the art further understand that the exemplary hardware, software, processes, methods, and/or operating systems described herein are for illustrative purposes and, thus, are not intended to be limited to any particular named.

[0051] As used herein, and unless the context dictates otherwise, the term "coupled to" is intended to include both direct coupling (in which two elements that are coupled to each other contact each other) and indirect coupling (in which at least one additional element is located between the two elements). Therefore, the terms "coupled to" and "coupled with" are used synonymously. Within the context of this document terms "coupled to" and "coupled with" are also used euphemistically to mean “communicatively coupled with” over a network, where two or more devices are able to exchange data with each other over the network, possibly via one or more intermediary device.

[0052] It should be apparent to those skilled in the art that many more modifications besides those already described are possible without departing from the inventive concepts herein. The inventive subject matter, therefore, is not to be restricted except in the spirit of the appended claims. Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms “comprises” and “comprising” should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, components, or steps that are not expressly referenced. Where the specification claims refers to at least one of something selected from the group consisting of A, B, C .... and N, the text should be interpreted as requiring only one element from the group, not A plus N, or B plus N, etc.

[0053] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.

ADVANTAGES OF THE INVENTION

[0054] The present disclosure provides a machine learning based system and method for estrus detection in milch animals.

[0055] The present disclosure provides a system and method for estrus detection in milch animals that affords optimum conditions for insemination in milch animals.

[0056] The present disclosure provides a machine learning based system and method for optimally managing nutrition in milch animals. [0057] The present disclosure provides a machine learning based system and method for estrus detection in milch animals by means of sampling of various parameters associated with a respective milch animal.