Description:TECHNICAL FIELD
[0001] The present disclosure relates generally to wearable devices for verifying identity of mammals. In particular, the present disclosure relates to a system and a method for processing behavioural data to verify identity of mammals.

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] The identification of mammals is a challenging task as it requires a reliable and accurate method to uniquely identify mammals from a group. Existing solutions that use bar codes or radio-frequency identification (RFID) on tags attached to mammals cannot be scaled very well. Particularly, such solutions require the ear tag to be brought very close to the scanning devices. Such ear tags that are typically attached to the mammal’s ear cannot collect behavioural data of said mammals including health data, location data, activity data, etc. Collection of such data would necessarily require use of more sophisticated smart wearable devices. However, existing wearable devices suffer from the limitations of being too expensive, consuming significant amounts of energy, having limited communication range, collecting insufficient health and activity data, being incapable of detecting anomalies in the mammal’s behaviour, etc.
[0004] Additionally, such mammal tracking devices do not use in-built security and are susceptible to tampering. For instance, smart wearable devices or Internet of Things (IoT) devices can be easily tampered such that health and activity data of a first mammal can be passed off as health and activity data of a second bovine mammal, simply by attaching the tracking device of the first mammal to the second bovine mammal. In such cases, it is difficult to verifiably associate the health and activity data to the correct bovine mammal, and to identify incidences of such tampering.
[0005] Tracking mammals using IoT devices may also require setting up an infrastructure having multiple data aggregation devices installed in various locations in the geographical area of interest such the that the data collected by the tracking devices can be compiled and processed. However, existing infrastructures are inflexible and cannot be easily adapted for changes in hardware specifications of the tracking devices, or for the introduction of new services that can be provided through the existing infrastructure.
[0006] There is, therefore, a need for a device that addresses the aforementioned shortcomings of existing solutions.

OBJECTS OF THE INVENTION
[0007] Some of the objects of the present disclosure, which at least one embodiment herein satisfies are listed herein below.
[0008] An object of the present disclosure is to provide a system and a method for verifying identity of mammals.
[0009] Another object of the present disclosure is to provide a system and a method for verifying identity using behavioural data of said mammals.
[0010] Another object of the present disclosure is to provide a system and a method for verifying identity of mammals that is not susceptible to tampering.
[0011] Another object of the present disclosure is to provide a system and a method for verifying identity of mammals that can detect anomalies in mammal behaviour.
[0012] Another object of the present disclosure is to provide a system and a method for verifying identity of mammals that can be updated to provide new services based on behavioural data of the bovine mammal.
[0013] Another object of the present disclosure is to provide a system and a method for determining whether the mammals subject to tracking is dead or alive.
[0014] Another object of the present disclosure is to provide a system and a method to verify identity of the mammals such that a register of attendance of said mammals can be maintained.
[0015] Another object of the present disclosure is to provide a system and a method to track the movement of the mammals as said mammals move from one location to another.
[0016] Yet another object of the present disclosure is to provide a system and a method for verifying identity of mammals that can be updated to be made compatible tracking units having a plurality of hardware specifications.
[0017] The other objects and advantages of the present invention will be apparent from the following description when read in conjunction with the accompanying drawings, which are incorporated for illustration of the preferred embodiments of the present invention and are not intended to limit the scope thereof.

SUMMARY
[0018] Aspects of the present disclosure relate generally to wearable devices of verifying identity of mammals. In particular, the present disclosure relates to a system and a method for processing behavioural data to verify identity of mammals.
[0019] In an aspect, the system for processing behavioural data to verify identity of mammals may include one or more tracking units where each tracking unit may be attached to a corresponding mammal from a set of mammals, the tracking units being configured to collect one or more behavioural data of said bovine mammal. The system may include one or more data aggregation units distributed over a geographical area of interest, said one or more data aggregation units configured to receive the one or more behavioural data from the tracking units when said tracking units may be within the detection range of the one or more data aggregation units. The system can include a data processing unit configured to uniquely identify the identity of the mammals based on the one or more behavioural data received by the one or more data aggregation units.
[0020] In an embodiment, the one or more behavioural data of the mammals comprise any one or more of sleep duration value, eat duration value, walk duration value, body temperature value, orientation attribute, location attributes, movement attribute and vitals health indicator attributes, the tracking units being configured to record each of the one or more behavioural data over one or more periodic time intervals of a predetermined duration.
[0021] In an embodiment, each of the one or more tracking units may include any one or more of: a set of sensors configured to collect the one or more behavioural data, a data storage module that stores the one or more behavioural data, a power source unit that provides power to the tracking unit, a data transmission unit to transmit data to the one or more data aggregation units when said tracking units may be within the detection range of said one or more data aggregation units, and an anomaly detection unit configured to detect any anomalous behavioural data collected by the set of sensors in the most recent time interval.
[0022] In an embodiment, the tracking units may be configured to transmit the one or more behavioural data and the one or more data aggregation units when an anomaly in any of the one or more behavioural data may be detected, the tracking units being configured to detect anomaly by comparing the one or more behavioural data collected in the most recent time interval with the one or more behavioural data collected in one or more of preceding time intervals a set similarity-based algorithm.
[0023] In an embodiment, the tracking units may include a unique ID attribute such that the data processing unit uniquely identifies the identity of each mammal from the set of mammals based on the unique ID attribute of the tracking units and the one or more behavioural attributed collected therefrom.
[0024] In an embodiment, the one or more data aggregation units may include a service discovery module that updates said one or more data aggregation units such that one or more of the tracking units having a plurality of hardware specifications are compatible with said one or more data aggregation units, and such that the one or more data aggregation units provide new services to the system.
[0025] In an embodiment, the data processing unit may include a processor coupled to a memory, the memory having processor-executable instructions. The processor-executable instructions, when executed, may cause the processor to receive the one or more behavioural data from the one or more data aggregation units. The processor may retrieve a set of mammal identity data indicative of the one or more behavioural data collected by each of the tracking units over a predetermined learning duration for the corresponding mammal such that each of said mammals may be uniquely identifiable using the set of mammal identity data. The processor may compare the one or more behavioural data and the set of mammal identity data, and resolve the identity of the mammal associated with the tracking units based on similarity between the one or more behavioural data and the set of mammal identity data.
[0026] In an embodiment, the similarity may be determined by passing the one or more behavioural data and the set of mammal identity data through a knowledge engine having a set of predefined inference rules such that the identity of the mammal associated with the tracking units may be verified when a similarity value determined by the knowledge engine may be greater than a predetermined similarity threshold.
[0027] In an aspect, a method for processing behavioural data to verify identity of mammals may include collecting, by one or more tracking units, one or more behavioural data of a set of mammals, where each tracking units being attached to a corresponding mammal from said set of bovine mammal. The method may include receiving, by one or more data aggregation units, the one or more behavioural data from the tracking units when said tracking units may be within the detection range of the one or more data aggregation units. The method can include uniquely identifying, by a data processing unit, the identity of the mammal based on the one or more behavioural data received by the one or more data aggregation units.
[0028] In an embodiment, the tracking units may be configured to sync the one or more behavioural data and the one or more data aggregation unit when an anomaly in any of the one or more behavioural data may be detected. The tracking units may be configured to detect anomaly by comparing the one or more behavioural data collected in the most recent time interval with the one or more behavioural data collected in one or more of preceding time intervals using a set similarity-based algorithm.
[0029] In an embodiment, uniquely identifying the identity of the mammal may include retrieving, by the data processing unit, a set of mammal identity data indicative of the one or more behavioural data collected by each of the tracking units over a predetermined learning duration for the corresponding mammal such that each of said mammals may be uniquely identifiable using the set of mammal identity data. The method can include comparing, by the data processing unit, the one or more behavioural data and the set of mammal identity data. The method may include resolving, by the data processing unit, the identity of the mammal associated with the tracking units based on similarity between the one or more behavioural data and the set of mammal identity data.
[0030] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.

BRIEF DESCRIPTION OF THE DRAWINGS
[0031] 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.
[0032] FIG. 1 illustrates an exemplary network architecture for implementing a proposed system for processing behavioural data to verify identity of mammals, according to the embodiments of the present disclosure.
[0033] FIG. 2 illustrate an exemplary circuit diagram of the one or more tracking units, according to embodiments of the present disclosure.
[0034] FIG. 3 illustrates an exemplary block representation of the one or more aggregation units of the present disclosure, according to the embodiments of the present disclosure.
[0035] FIG. 4 illustrates an exemplary block representation of the data processing unit of the present disclosure, according to the embodiments of the present disclosure.
[0036] FIG. 5 illustrates a flow chart depicting a method for processing behavioural data to verify identity of mammals, according to embodiments of the present disclosure.
[0037] FIG. 6 illustrates a flow chart depicting a method 400 for processing behavioural data to verify identity of mammals, according to embodiments of the present disclosure.

DETAILED DESCRIPTION
[0038] 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.
[0039] The word “exemplary” and/or “demonstrative” is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and/or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive—in a manner similar to the term “comprising” as an open transition word—without precluding any additional or other elements.
[0040] As used herein, “connect,” “configure,” “couple,” and its cognate terms, such as “connects,” “connected,” “configured,” and “coupled” may include a physical connection (such as a wired/wireless connection), a logical connection (such as through logical gates of semiconducting device), other suitable connections, or a combination of such connections, as may be obvious to a skilled person.
[0041] As used herein, “send,” “transfer,” “transmit,” and their cognate terms like “sending,” “sent,” “transferring,” “transmitting,” “transferred,” “transmitted,” etc. include sending or transporting data or information from one unit or component to another unit or component, wherein the content may or may not be modified before or after sending, transferring, transmitting.
[0042] Reference throughout this specification to “one embodiment” or “an embodiment” or “an instance” or “one instance” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0043] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term “and/or” includes any and all combinations of one or more of the associated listed products.
[0044] Embodiments explained herein relate generally to wearable devices of verifying identity of mammals. In particular, the present disclosure relates to a system and a method for processing behavioural data to verify identity of mammals.
[0045] In an aspect, the system for processing behavioural data to verify identity of mammals may include one or more tracking units with each tracking units being attached to a corresponding mammal from a set of mammals, the tracking units being configured to collect one or more behavioural data of said bovine mammal. The system may include one or more data aggregation units distributed over a geographical area of interest, said one or more data aggregation units configured to receive the one or more behavioural data from the tracking units when said tracking units may be within the detection range of the one or more data aggregation units. The system can include a data processing unit configured to uniquely identify the identity of the mammals based on the one or more behavioural data received by the one or more data aggregation units.
[0046] In an aspect, a method for processing behavioural data to verify identity of mammals may include collecting, by one or more tracking units, one or more behavioural data of a set of mammals, where each tracking unit may be attached to a corresponding mammal from said set of mammals. The method may include receiving, by one or more data aggregation units, the one or more behavioural data from the tracking units when said tracking units may be within the detection range of the one or more data aggregation units. The method can include uniquely identifying, by a data processing unit, the identity of the mammal based on the one or more behavioural data received by the one or more data aggregation units.
[0047] FIG. 1 illustrates an exemplary network architecture for implementing a proposed system for processing behavioural data to verify identity of mammals, according to the embodiments of the present disclosure. As shown therein, the system 100 includes one or more tracking units 160-1, 160-2, 160-3, and 160-4 (collectively referred to as the tracking units 160), one or more data aggregation units 130-1 and 130-2 (collectively referred to as data aggregation units 130), a data processing unit 110 and a server 118. In an embodiment, the data processing unit 110 may be communicatively connected with the server 118 and the data aggregation units 130.
[0048] In an embodiment, the data processing unit 110 may be implemented by way of a single device or a combination of multiple devices that may be operatively connected or networked together. For example, the data processing unit 110 may be implemented by way of a standalone device such as the server 118, and the like, and may be communicatively coupled to the data aggregation units 130. In an embodiment, the server 118 may include, but is not limited to, a stand-alone server, a remote server, a cloud computing server, a dedicated server, a rack server, a server blade, a server rack, a bank of servers, a server farm, hardware supporting a part of a cloud service or system, a home server, hardware running a virtualized server, one or more processors executing code to function as a server, one or more machines performing server-side functionality as described herein, at least a portion of any of the above, some combination thereof, and the like. In another example, the data processing unit 110 may be implemented in each of the data aggregation units 130. In yet another example, the data processing unit 110 may be implemented on including, but not limited to, a mobile device, a smart-phone, a Personal Digital Assistant (PDA), a tablet computer, a phablet computer, a wearable computing device, a Virtual Reality/Augmented Reality (VR/AR) device, a laptop, a desktop, a server, and the like.
[0049] In an aspect, the system 100 for processing behavioural data to verify identity of mammals may include the one or more tracking units 170 with each tracking units 170 being attached to a corresponding mammal from a set of mammals. In an embodiment, the tracking units 170 may be configured to collect one or more behavioural data of said set of mammals. In an embodiment, each of the one or more tracking units 170 may include a set of sensors configured to collect the one or more behavioural data. In an embodiment, the one or more behavioural data of the mammals may include, but not be limited to, sleep duration value, eat duration value, walk duration value, body temperature value, orientation attribute, location attributes, movement attribute and vitals health indicator attributes. In an embodiment, the tracking units 170 may be configured to record each of the one or more behavioural data over one or more periodic time intervals of a predetermined duration. In an example, the tracking units 170 may record the one or more behavioural data at predetermined time intervals of 30 mins. In other embodiments, each of the one or more behavioural data may be recorded at different periodic time intervals. In an example, sleep duration value, eat duration value, and walk duration value may be recorded in periodic time intervals of 30 mins while vitals health indicator attributes may be recorded at intervals of 10 seconds.
[0050] In an embodiment, the one or more tracking units 170 may be configured to be in a learning mode where said tracking units 170 collect the one or more behavioural data over the predetermined learning duration. In an embodiment, the one or more behavioural data collected during the learning duration may be indicative of the corresponding mammal identity data, and may be stored along with a unique ID attribute of the tracking unit 170 in a database, such as a database 220 as shown in FIG. 4. In an embodiment, the database may be associated with the data processing unit 110. In an embodiment, the tracking units 170 may be configured to transmit the one or more behavioural data and the one or more data aggregation units 130 when an anomaly in any of the one or more behavioural data may be detected. In an embodiment, the tracking units 170 may be configured to detect anomaly by comparing the one or more behavioural data collected in the most recent time interval with the one or more behavioural data collected in one or more of preceding time intervals using a set similarity-based algorithm including, but not limited to, the Jaccard similarity algorithm.
[0051] In an embodiment, each of the tracking units 170 may include a corresponding unique ID attribute such that the data processing unit 110 uniquely identifies the identity of each mammal from the set of mammals based on the unique ID attribute of the tracking units 170 and the one or more behavioural attributed collected therefrom. In an embodiment, the unique ID attribute may be used by the data processing unit 110 to retrieve a set of mammal identity data stored therein.
[0052] The system 100 may include the one or more data aggregation units 130 distributed over a geographical area of interest. In an embodiment, the one or more data aggregation units 130 may be configured to receive the one or more behavioural data from the tracking units 170 when said tracking units 170 is within the detection range of the one or more data aggregation units 130. In an example, the data aggregation units 130 may be distributed across including, but not limited to, a farm, a ranch, and the like. In another example, the data aggregation units 130 may be configured in locations mammals tend to ruminate such that when said mammals ruminate within the detection range of said data aggregation units 130, the one or more behavioural data collected by the tracking unit 170 attached to the mammals is received by the data aggregation units 130. In an embodiment, the one or more data aggregation units 130 may be configured to track the movement of the mammals as said mammals move from a first geographical area of interest associated with a first data aggregation unit 130-1 to a second geographical area of interest associated with a second geographical area of interest.
[0053] In an embodiment, the one or more data aggregation units 130 may include a service discovery module, such as a service discover module 146 as shown in FIG. 3, that updates said one or more data aggregation units 130 such that one or more of the tracking units 170 having a plurality of hardware specifications are compatible with said one or more data aggregation units 130, and such that the one or more data aggregation units 130 provide new services to the system 100.
[0054] In an embodiment, the data aggregation units 130 and the data processing unit 110 may be communicatively coupled to exchange the one or more behavioural data as a set of including, but not limited to, signals, data packets, and the like, via the communication network 106. In an embodiment, the communication network 106 may be a wired communication network or a wireless communication network. The wireless communication network may be any wireless communication network capable of transferring data between entities of that network such as, but is not limited to, Bluetooth, Near Field Communication (NFC), Wireless Fidelity (Wi-Fi), Light Fidelity (Li-Fi), Zigbee, a carrier network including, but is not limited to, a circuit-switched network, a public switched network, a Content Delivery Network (CDN) network, a Long-Term Evolution (LTE) network, a New Radio (NR), a Global System for Mobile Communications (GSM) network and a Universal Mobile Telecommunications System (UMTS) network, an Internet, intranets, Local Area Networks (LANs), Wide Area Networks (WANs), mobile communication networks, combinations thereof, and the like. The wired communication network may be any wired communication network capable of transferring data between entities of that network such as, but is not limited to, an Ethernet network, a Digital Subscriber Line (DSL) network, a coaxial cable network, a fiber optic network, a Power Line Communication (PLC) network, combinations thereof, and the like.
[0055] In an embodiment, the system 100 can include the data processing unit 110 configured to uniquely identify the identity of the mammals based on the one or more behavioural data received by the one or more data aggregation units 130. In an embodiment, the data processing unit 110 may include a processor coupled to a memory, such as a third processor 212 and a third memory 214 respectively as shown in FIG. 4. In an embodiment, the memory may processor-executable instructions. The processor-executable instructions may cause the data processing unit 110, by the processor, to receive the one or more behavioural data from the one or more data aggregation units 130. In an embodiment, data processing unit 110 may retrieve a set of mammal identity data indicative of the one or more behavioural data collected by each of the tracking units 170 over a predetermined learning duration for the corresponding mammal such that each of said mammals may be uniquely identifiable using the set of mammal identity data.
[0056] In an embodiment, the data processing unit 110 may retrieve the mammal identity data based on the unique ID attribute of the tracking unit 170 from which the one or more behavioural data was received. In an embodiment, the data processing unit 110 may compare the one or more behavioural data and the set of mammal identity data. In an embodiment, the data processing unit 110 may determine a similarity value based on the comparison. In an embodiment, the data processing unit 110 may resolve the identity of the mammal associated with the tracking units based on similarity between the one or more behavioural data and the set of mammal identity data.
[0057] In an embodiment, the similarity may be determined by passing the one or more behavioural data and the set of mammal identity data through a knowledge engine, such as a inference rules module 214 as shown in FIG. 4, having a set of predefined inference rules such that the identity of the mammal associated with the tracking units 170 may be verified when the similarity value determined by the knowledge engine may be greater than a predetermined similarity threshold. In an example, the knowledge engine may be indicative of a pretrained machine learning model that determines a class to the input behavioural data, where each class corresponding to the identity of the mammals. In such examples, the machine learning model may learn the set of inference rules by updating the weights therein during training. In other examples, the knowledge engine may be an expert system having one or more inference rules, where a combination of inference rules may be applied to the one or more behavioural data and the set of mammal identity data to determine the similarity value. In such examples, the input behavioural data may be transformed into a data structure appropriate for processing by said expert system.
[0058] In such embodiment, the system 100 may allow for verifiably collecting, storing and retrieving of behaviour data associated with the bovine mammal. In an exemplary embodiment, to verify the behavioural data of a particular bovine mammal, the one or more behavioural data collected from the tracking unit 170 attached to said mammal may be deliberately synced with the data aggregation unit 130 and subsequently processed by the data processing unit 110 to determine identity of said bovine mammal. The system 100 may be able to identify incidences of tampering or replacement of tracking units 170 between mammals. For instance, if a first tracking unit 170-1 of a first mammal and a second tracking unit 170-2 of a second mammal are switched, the system 100 may be able to accurately determine and verify the identity of the respective mammals based on the behavioural data collected from said tracking units 170. While the foregoing embodiments have been disclosed in the context of mammals, the system 100 may be suitably adapted by those skilled in the art to verify the identity of including, but not limited to, ruminant mammals such as cattle, sheep, goat, horses, etc., domesticated mammals such as cats, dogs, rabbits, hamsters, etc., and wild mammals such as elephants, lions, bears, monkeys, etc. In an embodiment, the system 110 may be used to verify identity of bovine mammals in a farm, and track and monitor its movement and health. In other embodiments, the tracking unit 170 may be attached to wild mammals to track its health and movement. In such embodiments, obtaining the behavioural data may aid in conservation efforts for endangered species among wild mammals.
[0059] FIG. 2 illustrate exemplary circuit diagram of the one or more tracking units 170, according to embodiments of the present disclosure. As shown, each of the tracking units 170 may include a power source unit 172, a battery 174, a first processor 176, a set of sensors 178-1 to 178-6, and a data transmission unit 180. In an embodiment, the set of sensors 178 may include a blood pressure monitor 178-1, a heart rate monitor 178-2, a pulse oximeter 178-3, a temperature sensor 178-4, and one or more accelerometer and gyroscope modules 178-5 and 178-6.
[0060] In an embodiment, the power source unit 172 may be indicative of a solar cell. In other embodiments, the power source 172 may be indicative of including, but not limited to a piezoelectric module, a thermoelectric module, a fuel cell, a conventional battery, or a combination thereof. In an embodiment, the power source unit 172 may provide power to the tracking unit 170.
[0061] In an embodiment, the tracking units 170 may be configured to collect the one or more behavioural data through the set of sensors 178. In an embodiment, the tracking units 170 may also include a data storage module that stores the one or more behavioural data. In an embodiment, the data storage module may store the one or more behavioural data collected at each time interval. In an embodiment, the data storage module may be configured to store the one or more behavioural data collected during preceding ‘N’ time intervals, where ‘N’ may be determined based on accuracy requirements of the anomaly detection unit. In an embodiment, the tracking units 170 may include a data transmission unit 180 to transmit data to the one or more data aggregation units 130 when said tracking units 170 may be within the detection range of said one or more data aggregation units 130. In an embodiment, the data transmission unit 180 may be indicative of a Bluetooth communication module as shown in FIG. 2. In other embodiments, the data transmission unit 180 may be indicative of including, but not limited to, a Bluetooth communication module, a Global System for Mobile communication (GSM) module, an infrared communication module, a Wi-Fi communication module, or the like.
[0062] In an embodiment, the first processor 176 may be coupled to a first memory that may have one or more processor-executable instructions to collect the one or more behavioural data from the set of sensors 178, store said behavioural data in the data storage module, and transmit the behavioural data to the data aggregation units 130. In an embodiment, the tracking units 170 may also include an anomaly detection unit configured to detect any anomalous behavioural data collected by the set of sensors in the most recent time interval. In an embodiment, the anomaly detection unit may be coupled to the first processor 176 of the tracking units 170. In an embodiment, the data storage module and the anomaly detection module may be implemented within a first processing engine associated with the tracking units 170. In an embodiment, the tacking units 170 may also include a first interface configured to allow the first processor to receive and transmit data.
[0063] FIG. 3 illustrates an exemplary block representation of the one or more data aggregation units 130 of the present disclosure, according to the embodiments of the present disclosure. As shown, the data aggregation units 130 may include a second processor 132, a second memory 134, a second interface 136 and a second processing engine 140. In an embodiment, the second processing engine 140 may include a detecting module 142, a transmitting module 144, the service discovery module 146 and other modules 148.
[0064] In an embodiment, the second processing engine 140 may be stored within the second memory 134. In an example, the second processing engine 140 may be communicatively coupled to the processor 112 configured in the system 100. In other embodiments, the second processing engine 140 may also be present outside the memory 134, as shown in FIG. 3, and implemented as hardware. In such embodiments, the second processing engine 140 may be indicative of including, but not limited to, an Application-Specific Integrated Circuit (ASIC), an electronic circuit, a processor (shared, dedicated, or group) and memory that execute one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality.
[0065] In an embodiment, the detecting module 142 may be configured to detect the tracking units 170 in the area of interest. In an embodiment, the detecting module 142 may be coupled to the wireless detection unit 138. In an embodiment, the wireless detection unit 138 may be configured to establish wireless communication with the one or more tracking units 170, and receive the one or more behavioural data therefrom.
[0066] In an embodiment, the transmitting module 144 may be configured to transmit the one or more behavioural data to the data processing unit 110. In an embodiment, the transmitting module 144 may be configured to allow the one or more behavioural data through the communication network 106.
[0067] In an embodiment, the one or more data aggregation units 130 may include a service discovery module 146 that updates said one or more data aggregation units 130 such that one or more of the tracking units 170 having a plurality of hardware specifications are compatible with said one or more data aggregation units 130, and such that the one or more data aggregation units 130 provide new services to the system 100. In an embodiment, the service module 146 may update the one or more data aggregation unit 130 by receiving one or more processor-executable instructions from the data processing unit 110. In an embodiment, the service discovery module 146 may enable compatibility of the data aggregation units 130 with legacy and new tracking units 170. In an example, when upgraded tracking units 170 having enhanced hardware specifications are deployed in the system 100, the service discovery module 146 may allow the data aggregation units 130 to receive one or more processor-executable instructions for receiving and processing the one or more behavioural data from said upgraded tracking units 170. Further, the service discovery module 146 may also enable the data aggregation unit 130 to provide new services to system 100. In an example, the data aggregation unit 130 may receive one or more processor-executable instructions to perform an attendance check for the mammals in a farm or a ranch.
[0068] FIG. 4 illustrates an exemplary block representation of the data processing unit 110 of the present disclosure, according to the embodiments of the present disclosure. As shown, the data processing unit 110 may include a third processor 202, a third memory 204, a third interface 206 and a third processing engine 208. In an embodiment, the third processing engine 208 may include a receiving module 210, a retrieving module 212, the inference rule module 214, a resolving module 216 and other modules 218.
[0069] In an embodiment, the third processing engine 208 may be stored within the second memory 204. In an example, the third processing engine 208 may be communicatively coupled to the processor 202 configured in the system 100. In other embodiments, the third processing engine 208 may also be present outside the memory 204, as shown in FIG. 4, and implemented as hardware. In such embodiments, the third processing engine 208 may be indicative of including, but not limited to, an Application-Specific Integrated Circuit (ASIC), an electronic circuit, a processor (shared, dedicated, or group) and memory that execute one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality.
[0070] In an embodiment, the receiving module 210 may be configured to receive the one or more behaviour data from the one or more data aggregation units 130. In an embodiment, the retrieving module 212 may be configured to retrieve a set of mammal identity data based on the unique ID attribute of the tracking units 170 and the one or more behavioural data. In an embodiment, each mammal identity data from the set of mammal identity data may be indicative of the one or more behavioural data of a mammal collected by the corresponding tracking unit 170 during the learning mode. In an embodiment, the mammals may be uniquely identifiable based on the corresponding mammal identity data. In an embodiment, the retrieving module 212 may also be coupled to a database 220. In an embodiment, the database 220 may be configured to store the set of mammal identity data as data. The data may be organized using data models, such as relational or hierarchical data models. The data may also include temporary data and temporary files, generated by the third processing engines 208 for performing the various functions of the data processing unit 110. In an embodiment, the data processing unit 110 may be configured to retrieve the set of mammal identity data from the database 220 to verify the identity of the mammal by comparing the retrieved mammal identity data with the one or more behavioural data collected by the tracking unit 170.
[0071] In an embodiment, the inference rule module 214 may include a set of predefined inference rules that may be used to compare the retrieved set of mammal identity data and the one or more behavioural data received from the data aggregation unit 130. In an embodiment, the inference rule module 214 may be indicative of a knowledge engine. In an embodiment, the knowledge engine may be an expert system having one or more inference rules, where a combination of inference rules may be applied to the one or more behavioural data and the set of mammal identity data to determine the similarity value. In such examples, the input behavioural data may be transformed into a data structure appropriate for processing by said expert system. In other embodiments, the knowledge engine may be indicative of a pretrained machine learning model that determines a class to the input behavioural data, where each class corresponds to the identity of the mammals. In such examples, the machine learning model may learn the set of inference rules by updating the weights therein during training.
[0072] In an embodiment, the resolving module 216 may resolve the identity of the mammal associated with the tracking unit based on similarity between the one or more behavioural data and the set of mammal identity data. In an embodiment, the identity of the mammal associated with the tracking unit may be verified when a similarity score determined by the inference rule module 214 is greater than a predetermined similarity threshold.
[0073] In an embodiment, the first processor 176, the second processor 132 and the third processor 202 may be implemented as any one or more of microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, Application Specific Integrated Circuits (ASIC) and/or any devices that manipulate data based on operational instructions. Among other capabilities, the first processor 176, the second processor 132 and the third processor 202 may be configured to fetch and execute computer-readable instructions stored in the first memory, the second memory 134 and the third memory 204 respectively. The first memory, the second memory 134 and the third memory 204 may store one or more computer-readable instructions or routines, which may be fetched and executed to create or share the data units over a network service or wired communication means. The first memory, the second memory 134 and the third memory 204 may include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as EPROM, flash memory, and the like.
[0074] In an embodiment, each of the tracking units 170, the one or more data aggregation units 130 and the data processing unit 110 may also include a first input-output (I/O) interface, a second I/O interface 136 and a third I/O interface 206 respectively for receipt of input signals and transmission of output signals therefrom. In an embodiment, the input signals and the output signals may be in the form of including, but not limited to, electrical signals, digital signals, optical signals, radio signals, and any combination thereof. In an embodiment, the input signals and output signals may be used to exchange including, but not limited to, data packets, bits, signals, and the like.
Exemplary Scenario
[0075] In an example, the one or more behavioural data of mammals collected by a corresponding tracking unit 170 may be as shown in Table 1.
Day Activity
Day-1 EEEEEEEEEEWWWWWWWWWWWSSSEEEEEEEEWWWWWWSSSSS
Day-2 EEEEEEEEWWWWWWWWWWWWSSSSSEEEEEEWWWWWWSSSSSS
Day-3 EEEEEEEEEEEEWWWWWWWWSSSSSEEEEEEWWWWWWSSSSSSS
Day-4 EEEEEEEEEEWWWWWWWWWWSSSEEEEEEEEWWWWWWSSSSSS
Day-5 EEEEEEEEEEWWWWWWWWWWSSSEEEEEEEEWWWWWWSSSSSS
Day-6 WWWWWWWEEEEWWWWWWWWSSWWWWWWEEEEESSSWWWWSSS
Table 1: Behavioural data collected by a tracking unit at periodic intervals across six days
[0076] The aforementioned table is indicative of the one or more behavioural data of a mammal collected by the corresponding tracking unit 170 at periodic time intervals for 6 days. In the activity column of the table, letter ‘E’ may indicate the mammal was eating, letter ‘W’ may indicate the mammal was walking, and letter ‘S’ may indicate the mammal was sleeping during the periodic time interval. In an example, the corresponding tracking unit 170 may be configured to be in the learning mode such that the behavioural data collected for Days 1-4 form the set of mammal identity data for the mammal being subject to tracking. In such examples, the identity of the mammal may be verified based on the one or more behavioural data collected by the corresponding tracking unit 170. Here, the anomaly detection unit in said tracking unit 170 may compare the behavioural data collected in the most recent time interval with the one or more behavioural data collected in one or more of preceding time intervals. In the foregoing example, the anomaly detection unit may compare the behavioural data collected on Day-5 with the behavioural data collected on Days 1-4. In an embodiment, the anomaly detection unit may use a set similarity-based algorithm including, but not limited to, the Jaccard similarity algorithm. In the foregoing example, the anomaly detection unit may determine a higher similar value for the behavioural data compared due to their similarity.
[0077] Thereon, the tracking unit 170 may collect the behavioural data for Day-6. In the foregoing example, the anomaly detection unit may compare the similarity between the behavioural data collected on Day-6 with behavioural data collected on Days 1-5. In the foregoing example, the anomaly detection unit may determine a low similarity value due to their dissimilarity. In such examples, the tracking unit 170 may initiate a force sync with the one or more data aggregation units 130 to indicate the detection of an anomaly. Further, in such examples, the anomaly may be caused by tampering of the tracking unit 170, such as when the tracking unit 170 attached to a first mammal for which the set of mammal identity data was collected is removed from the first mammal and attached to a second bovine mammal. When such anomaly is intimated to the data aggregation units 130, said data aggregation units 130 may collect the one or more behavioural data and transmit said behavioural data to the data processing unit 110. Thereon, the data processing unit 110 may determine a similarity value using the knowledge engine, and resolve the identity of the mammal based on the similarity value.
[0078] FIG. 5 illustrates a flow chart depicting a method 300 for processing behavioural data to verify identity of mammals, according to embodiments of the present disclosure.
[0079] At step 302, the method 300 includes collecting, by one or more tracking units 170, one or more behavioural data of a set of mammals, where each tracking unit may be attached to a corresponding mammal from said set of mammals.
[0080] At step 304, the method 300 includes receiving, by one or more data aggregation units 130, the one or more behavioural data from the tracking unit when said tracking unit is within the detection range of the one or more data aggregation units.
[0081] At step 306, the method 300 include uniquely identifying, by a data processing unit 110, the identity of the mammal based on the one or more behavioural data received by the one or more data aggregation units.
[0082] In an embodiment, the step 306 of the method 300 may further include sub-steps 308-312. At step 308, the method 300 includes retrieving, by the data processing unit 110, a set of mammal identity data indicative of the one or more behavioural data collected by each of the tracking units 170 over a predetermined learning duration for the corresponding mammal such that each of said mammals may be uniquely identifiable using the set of mammal identity data.
[0083] At step 310, the method 300 includes comparing, by the data processing unit 110, the one or more behavioural data and the set of mammal identity data.
[0084] At step 312, the method 300 includes resolving, by the data processing unit 110, the identity of the mammal associated with the tracking unit based on similarity between the one or more behavioural data and the set of mammal identity data.
[0085] The order in which the method 300 is described is not intended to be construed as a limitation, and any number of the described method blocks may be combined or otherwise performed in any order to implement the method 300 or an alternate method. Additionally, individual blocks or steps may be deleted from the method 300 without departing from the scope of the present disclosure described herein. Furthermore, the method 300 may be implemented in any suitable hardware, software, firmware, or a combination thereof that exists in the related art or that is later developed. The method 300 describes, without limitation, the implementation of the system 100. A person of skill in the art will understand that method 300 may be modified appropriately for implementation in various manners without departing from the scope of the disclosure.
[0086] FIG. 6 illustrates a flow chart depicting a method 400 for processing behavioural data to verify identity of mammals, according to embodiments of the present disclosure.
[0087] At step 402, the method 400 includes collecting, by a tracking unit 170 attached to a bovine mammal, one or more behavioural data for a predetermined learning duration.
[0088] At step 404, the method 400 includes storing, by the tracking unit 170, the one or more behavioural data collected during the learning duration in a database. In an embodiment, the database may be indicative of the database 220. In other embodiments, the one or more behavioural data collected during the learning duration may be stored in a database associated with the tracking unit 170.
[0089] At step 406, the method 400 includes generating a set of mammal identity data based on the one or more behavioural data. In an embodiment, the set of mammal identity data may be generated wither by the tracking unit 170 or the data processing unit 110 based on whether the one or more behavioural data was stored in said tracking unit 170 or the data processing unit 110. In an embodiment, the set of mammal identity data may be unique to each bovine mammal.
[0090] Therefore, the present disclosure solves the need for a system and a method for processing behavioural data to verify identity of mammals that addresses the aforementioned shortcomings of existing solutions.
[0091] 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
[0092] The present disclosure provides a system and a method for verifying identity of mammals.
[0093] The present disclosure provides a system and a method for verifying identity using behavioural data of said mammals.
[0094] The present disclosure provides a system and a method for verifying identity of mammals that is not susceptible to tampering.
[0095] The present disclosure provides a system and a method for verifying identity of mammals that can detect anomalies in mammal behaviour.
[0096] The present disclosure provides a system and a method for verifying identity of mammals that can be updated to provide new services based on behavioural data of the bovine mammal.
[0097] The present disclosure provides a system and a method for determining whether the mammals subject to tracking is dead or alive.
[0098] The present disclosure provides a system and a method to verify identity of the mammals such that a register of attendance of said mammals can be maintained.
[0099] The present disclosure provides a system and a method to track the movement of the mammals as said mammals move from one location to another.
[00100] The present disclosure provides a system and a method for verifying identity of mammals that can be updated to be made compatible tracking units having a plurality of hardware specifications.

, Claims:1. A system for processing behavioral data to verify identity of mammals, the system comprises:
one or more tracking units with each tracking unit being attached to a corresponding mammal from a set of mammals, the tracking units being configured to collect one or more behavioral data of said bovine mammal;
one or more data aggregation units distributed over a geographical area of interest, said one or more data aggregation units configured to receive the one or more behavioral data from the tracking units when said tracking units are within the detection range of the one or more data aggregation units; and
a data processing unit configured to uniquely identify the identity of the mammals based on the one or more behavioral data received by the one or more data aggregation units.
2. The system as claimed in claim 1, wherein the one or more behavioral data of the mammals comprise any one or more of sleep duration value, eat duration value, walk duration value, body temperature value, orientation attribute, location attributes, movement attribute and vitals health indicator attributes, the tracking unit being configured to record each of the one or more behavioral data over one or more periodic time intervals of a predetermined duration.
3. The system as claimed in claim 1, wherein each of the one or more tracking units comprise any one or more of:
a set of sensors configured to collect the one or more behavioral data;
a data storage module that stores the one or more behavioral data;
a power source unit that provides power to the tracking unit;
a data transmission unit to transmit data to the one or more data aggregation units when said tracking units are within the detection range of said one or more data aggregation units; and
an anomaly detection unit configured to detect any anomalous behavioral data collected by the set of sensors in the most recent time interval.
4. The system as claimed in claim 1, wherein the tracking units are configured to transmit the one or more behavioral data with the one or more data aggregation units when an anomaly in any of the one or more behavioral data is detected, the tracking units being configured to detect anomaly by comparing the one or more behavioral data collected in the most recent time interval with the one or more behavioral data collected in one or more of preceding time intervals using a set similarity-based algorithm.
5. The system as claimed in claim 1, wherein the tracking unit comprises a unique ID attribute such that the data processing unit uniquely identifies the identity of each mammal from the set of mammals based on the unique ID attribute of the tracking unit and the one or more behavioral attributed collected therefrom.
6. The system as claimed in claim 1, wherein the one or more data aggregation units comprise a service discovery module that updates said one or more data aggregation units such that one or more of the tracking units having a plurality of hardware specifications are compatible with said one or more data aggregation units, and such that the one or more data aggregation units provide new services to the system.
7. The system as claimed in claim 1, wherein the data processing unit comprises a processor coupled to a memory, the memory having processor-executable instructions, which, when executed, causes the processor to:
receive the one or more behavioral data from the one or more data aggregation units;
retrieve a set of mammal identity data indicative of the one or more behavioral data collected by each of the tracking units over a predetermined learning duration for the corresponding mammal such that each of said mammals are uniquely identifiable using the set of mammal identity data;
compare the one or more behavioral data with the set of mammal identity data; and
resolve the identity of the mammal associated with the tracking unit based on similarity between the one or more behavioral data with the set of mammal identity data.
8. The system as claimed in claim 7, wherein the similarity is determined by passing the one or more behavioral data and the set of mammal identity data through a knowledge engine having a set of predefined inference rules such that the identity of the mammal associated with the tracking unit is verified when a similarity score determined by the knowledge engine is greater than a predetermined similarity threshold.
9. A method for processing behavioral data to verify identity of mammals, the method comprising:
collecting, by one or more tracking units, one or more behavioral data of a set of mammals, each tracking unit being attached to a corresponding mammal from said bovine mammal;
receiving, by one or more data aggregation units, the one or more behavioral data from the tracking unit when said tracking unit is within the detection range of the one or more data aggregation units; and
uniquely identifying, by a data processing unit, the identity of the mammal based on the one or more behavioral data received by the one or more data aggregation units.
10. The method as claimed in claim 8, wherein the tracking units are configured to sync the one or more behavioral data with the one or more data aggregation unit when an anomaly in any of the one or more behavioral data is detected, the tracking units being configured to detect anomaly by comparing the one or more behavioral data collected in the most recent time interval with the one or more behavioral data collected in one or more of preceding time intervals a set similarity-based algorithm.
11. The method as claimed in claim 8, wherein uniquely identifying the identity of the mammal comprises:
retrieving, by the data processing unit, a set of mammal identity data indicative of the one or more behavioral data collected by each of the tracking units over a predetermined learning duration for the corresponding mammal such that each of said mammals are uniquely identifiable using the set of mammal identity data;
comparing, by the data processing unit, the one or more behavioral data with the set of mammal identity data; and
resolving, by the data processing unit, the identity of the mammal associated with the tracking unit based on similarity between the one or more behavioral data with the set of mammal identity data.