Animal action recording device, animal action recording method, and program

By combining the data of acceleration sensors, angular velocity sensors and position information in the animal movement recording device, using the learning completion model to estimate and correct animal postures, the problem of insufficient posture estimate accuracy in the prior art is solved, and changes in animal health status are achieved high-precision prediction.

CN119072230APending Publication Date: 2024-12-03FURUKAWA ELECTRIC CO LTD +1
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202380032070.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-03-31
Filing Date
2023-03-31
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the existing animal health management technology, the posture estimation accuracy based on acceleration data and air pressure data is insufficient, resulting in the inability to accurately predict changes in the animal's health status, such as the omen/delivery prediction of male-borne cattle are easily missed.

Method used

An animal action recording device is designed, combining acceleration sensors and angular velocity sensors to obtain data, and perform action estimation by learning the model and position information, and correcting the estimation results to improve the accuracy of posture estimation. The device can record the animal's actions and predict periods of disease, estrus, childbirth, falls, growth and weaning.

Benefits of technology

It achieves high-precision and efficient grasp of animal actions, improves the accuracy of prediction of changes in animal health status, and reduces the situation of missed predictions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119072230A_ABST
    Figure CN119072230A_ABST
Patent Text Reader

Abstract

The present invention makes it possible to efficiently grasp the action of an animal with high precision. This animal behavior recording device (100) is provided with a processing unit (110) that acquires animal behavior information, which is information indicating the behavior of an animal, acquires animal position information, which is information indicating the position of the animal, and estimates the behavior of the animal on the basis of the animal behavior information and the animal position information. And recording the action according to a time sequence. The animal behavior information may be both or any one of acceleration data acquired by an acceleration sensor provided in the animal and angular velocity data acquired by an angular velocity sensor provided in the animal. The processing unit (110) can estimate the action of the animal on the basis of either the animal behavior information or the animal position information, and corrects the estimated action using the other information.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to an animal behavior recording device, an animal behavior recording method and a program. Background Art

[0002] In order to continue to operate a stable dairy farming business, it is important to efficiently manage the health of the animals being raised. For example, Patent Documents 1 and 2 describe a technology that installs an air pressure sensor or an acceleration sensor on an animal, estimates the posture based on the measurement data, and determines the health status of the animal or detects the occurrence of an abnormality.

[0003] [Prior Technical Literature]

[0004] (Patent Document)

[0005] Patent Document 1: Japanese Patent Application Publication No. 2017-060407

[0006] Patent Document 2: Japanese Patent Application Publication No. 2020-198829 Summary of the invention

[0007] [Problems to be solved by the invention]

[0008] However, the techniques of Patent Documents 1 and 2 using acceleration data and air pressure data have the following problems: the estimation accuracy of the posture of the managed animal is not sufficient, and the prediction of health status changes based on the posture cannot be obtained with sufficient accuracy. The inability to predict the posture of the animal with sufficient accuracy may also lead to the omission of signs of estrus / parturition in multiparous cattle, for example.

[0009] One of the purposes of the present invention is to provide an animal behavior recording device, an animal behavior recording system, an animal behavior recording method and a program, which can grasp the behavior of animals with high precision and efficiency.

[0010] [Technical means to solve the problem]

[0011] One aspect of the present invention is an animal action recording device comprising: an animal behavior information acquisition unit, which acquires information indicating the behavior of animals raised in a predetermined breeding area, namely, animal behavior information; an animal position information acquisition unit, which acquires information indicating the location of the aforementioned animal, namely, animal position information; and an animal action recording unit, which estimates the action of the aforementioned animal based on the aforementioned animal behavior information and the aforementioned animal position information, and records the action in a time series.

[0012] Optionally, the aforementioned animal behavior information is both or either one of acceleration data obtained by an acceleration sensor provided on the aforementioned animal and angular velocity data obtained by an angular velocity sensor provided on the aforementioned animal, and the aforementioned animal action recording unit comprises: an action estimating unit, which estimates the action of the aforementioned animal based on the aforementioned acceleration data and angular velocity data or either one of them; and an estimation result correction unit, which corrects the action of the aforementioned animal estimated by the aforementioned action estimating unit based on the aforementioned animal position information.

[0013] Optionally, a storage unit is provided, which stores information on the positions of multiple types of settings required for raising animals and arranged in the above-mentioned breeding area, and the above-mentioned estimation result correction unit determines the type of setting at the position where the animal as the object is located based on the stored information on the position of the above-mentioned setting and the above-mentioned animal position information, and corrects the action of the above-mentioned animal estimated by the above-mentioned action estimation unit based on the determined type of the above-mentioned setting.

[0014] Optionally, the aforementioned animal behavior information is both or either one of acceleration data obtained by an acceleration sensor provided on the aforementioned animal and angular velocity data obtained by an angular velocity sensor provided on the aforementioned animal, and the aforementioned animal behavior recording unit comprises: a behavior estimating unit, which estimates the location of the aforementioned animal and the behavior of the aforementioned animal in the location based on the aforementioned animal position information; and an estimation result correction unit, which compares the estimated location of the aforementioned animal and the behavior of the aforementioned animal with the acquired aforementioned animal behavior information for correction.

[0015] Optionally, a storage unit is provided, which stores information on the positions of multiple types of settings required for raising animals and arranged in the aforementioned breeding area, and the aforementioned behavior inference unit determines the type of setting at the position where the target animal is located based on the stored information on the positions of the aforementioned settings and the aforementioned animal position information, and infers the behavior of the aforementioned target animal based on the determined type of the aforementioned setting.

[0016] Optionally, the behavior estimating unit estimates the behavior of the animal using a learned model that has learned the relationship between the acceleration data and the angular velocity data obtained from the animal, or any one of them, and the behavior of the animal classified into a plurality of types.

[0017] Optionally, the behavior estimating unit estimates the behavior of the animal based on the behavior of the animal and the acceleration data and angular velocity data acquired from the animal, or a statistical correspondence between the acceleration data and the angular velocity data or any one of them.

[0018] Optionally, the animal position information is calculated based on an arrival direction of radio waves, which are radio waves transmitted by an acceleration sensor and an angular velocity sensor or any one of them provided on the animal via a communication unit.

[0019] Optionally, the action records of the animal recorded in time series by the animal action recording unit are used to predict at least one period of the animal's disease, estrus, delivery, fall, growth and weaning.

[0020] Optionally, the animal behavior information includes at least one of output data from an air pressure sensor and an acoustic sensor provided on the animal or any one of them, and biological information obtained from the animal.

[0021] Another aspect of the present invention is an animal action recording method, wherein an information processing device obtains information representing the behavior of an animal, namely, animal behavior information, obtains information representing the location of the aforementioned animal, namely, animal location information, and infers the action of the aforementioned animal based on the aforementioned animal behavior information and the aforementioned animal location information, and records the action in a time series.

[0022] Another aspect of the present invention is a program that enables an information processing device to perform the following processing: a process of obtaining information representing the behavior of an animal, namely, animal behavior information; a process of obtaining information representing the location of the aforementioned animal, namely, animal position information; and, based on the aforementioned animal behavior information and the aforementioned animal position information, inferring the action of the aforementioned animal and recording the action in a time series.

[0023] (Effects of the Invention)

[0024] According to the present invention, the behavior of animals can be grasped with high accuracy and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a schematic diagram illustrating the overall configuration of an animal behavior recording system in one embodiment of the present invention.

[0026] Figure 2 This is a block diagram showing the functional overview of an animal behavior recording system in one embodiment of the present invention.

[0027] Figure 3 This is a block diagram illustrating the configuration of hardware and functional blocks of an animal behavior recording device in one embodiment of the present invention.

[0028] Figure 4 This is a block diagram illustrating the configuration of hardware and functional blocks of a sensor device and a position detector in one embodiment of the present invention.

[0029] Figure 5This is an explanatory diagram illustrating the correspondence between animal behavior and sensor data.

[0030] Figure 6 This is a diagram showing a structural example of a setting object position information table.

[0031] Figure 7 This is a diagram showing an example of behavior records acquired by the animal behavior recording system in one embodiment of the present invention.

[0032] Figure 8 This is a diagram showing an example of behavior records acquired by the animal behavior recording system in one embodiment of the present invention.

[0033] Fig. 9 This is a diagram showing a configuration example of a processing target data storage unit.

[0034] Fig.10 This is a flowchart showing an example of a behavior estimation process executed by the animal behavior recording device in one embodiment of the present invention.

[0035] Fig.11 This is a flowchart showing an example of a behavior estimation correction process executed by the animal behavior recording device in one embodiment of the present invention.

[0036] Fig.12 This is a flowchart showing an example of data acquisition processing in another embodiment of the present invention.

[0037] Fig.13 This is a flowchart showing an example of behavior estimation processing and estimation result correction processing in another embodiment of the present invention.

[0038] Fig.14 This is a diagram showing an evaluation example of the action record result in this embodiment.

[0039] Fig.15 This is a graph illustrating the action record results in this embodiment. DETAILED DESCRIPTION

[0040] Hereinafter, the present invention will be described in conjunction with its embodiments and with reference to the accompanying drawings. In addition, the present invention is not limited to the following embodiments. In addition, the figures referred to in the following description are merely schematically showing shapes, sizes, and positional relationships to the extent that the contents of the present disclosure can be understood. That is, the present invention is not limited to the shapes, sizes, and positional relationships illustrated in the figures.

[0041] (Implementation Method)

[0042] <Animal behavior recording system 1>

[0043] Figure 1Schematic diagram illustrating the overall structure of an animal behavior recording system 1 in one embodiment of the present invention. Figure 1 As shown, the animal behavior recording system 1 of this embodiment has the function of recording the behavior of, for example, a cow C raised by a dairy farmer in a time series. The animals to be recorded are not limited to the cow C, but may include all animals that are useful for obtaining and using behavior records, including animals that fall into the category of so-called economic animals, such as pigs, sheep, horses, and goats, animals raised in zoos, and so-called pets.

[0044] Figure 1 FIG. 1 is a plan view schematically showing a rectangular cowshed CB arranged in a cowshed. Figure 1 , a situation in which one cow C is kept in the cowshed CB is shown, but usually a plurality of cows C are kept in one cowshed CB.

[0045] In the cowshed CB, there are provided facilities such as feeding places F, nursing places M, and drinking places W at appropriate locations, so that the cow C can eat feed (eating action), drink milk (sucking action), and drink water (drinking action) at each location. In addition, the arrangement of these feeding places F, nursing places M, and drinking places W in the cowshed CB is not limited to Figure 1 For example, it can be decided appropriately.

[0046] The sensor device 200 having a three-axis acceleration sensor and a three-axis angular velocity sensor is mounted on the cow C to obtain acceleration data and angular velocity data reflecting the movement and body changes of the cow C. The sensor device 200 is provided with a data transmission function, and the acquired acceleration data and angular velocity data are transmitted, for example, by near field communication (NFC). In addition, the acquired and transmitted data may be only one of the acceleration data and the angular velocity data.

[0047] An animal behavior recording device 100 is installed near a cowshed including a cowshed CB, such as a management building of a dairy cattle owner. The animal behavior recording device 100 is an information processing device equipped with the main function of animal behavior recording in this embodiment. The animal behavior recording device 100 receives acceleration data and angular velocity data from a sensor device 200 mounted on the cow C, and analyzes the behavior of the cow C based on the received data.

[0048] A position detector 300 is provided in the cattle pen CB. The position detector 300 is a device that receives radio waves transmitted by the sensor device 200 and generates data for the animal behavior recording device 100 to analyze the position of the sensor device 200 as a transmission source, that is, the position of the cow C in the cattle pen CB. Figure 1In the example, two position detectors 300 are installed at appropriate locations in the cattle pen CB to detect the angle of the radio waves coming from the sensor device 200 and send them to the animal behavior recording device 100. The animal behavior recording device 100 uses the angle data from each position detector 300 to analyze and obtain the position of the cow C in the cattle pen CB. Based on the acceleration data, angular velocity data and position information in the cattle pen CB obtained for the cow C, the animal behavior recording device 100 determines the behavior of the cow C in the cattle pen CB and records it in a time series. Figure 1 As shown in the example, for convenience, the X-axis, Y-axis and Z-axis orthogonal to the plane coordinate system can be set in the cattle pen CB. The animal behavior recording device 100 can also be configured to be able to communicate with an external communication network N such as the Internet, a wide area network (WAN), and a local area network (LAN). The structure and function of the animal behavior recording device 100, the sensor device 200, and the position detector 300 will be described below with reference to the related diagrams.

[0049] Figure 2 It is shown in Figure 1 The general structure and functions of the animal behavior recording system 1 of the present embodiment are shown. The animal behavior recording system 1 of the present embodiment includes an animal behavior recording device 100. In the animal behavior recording device 100, sensor data is input from a sensor device 200 mounted on a cow C, and radio wave reception angle data from the sensor device 200 is input from a position detector 300 provided in a cowshed CB. The animal behavior recording device 100 analyzes the input sensor data, specifically, the three-axis acceleration data and the three-axis angular velocity data, by means of a sensor data analysis function F1, and estimates the behavior of the cow C in a time series by means of a behavior estimation function F2 based on the analysis results.

[0050] On the other hand, the animal behavior recording device 100 calculates the position information of the cow C in the cattle pen CB by means of the position information calculation function F4 based on the radio wave reception angle data input by means of the position data analysis function F3 and the installation position of the position detector 300. The estimated result correction function F5 of the animal behavior recording device 100 performs correction processing to improve the accuracy of the estimated behavior based on the processing results of the behavior estimation function F2 and the position information calculation function F4, and the corrected behavior record is recorded in a time series by means of the behavior recording function F6. In addition, a structure can also be adopted in which the behavior of the cow C is estimated based on the position information and the estimated result is corrected by means of the analysis result of the sensor data, which will be described below.

[0051] <Animal Behavior Recording Device 100, Sensor Device 200, Position Detector 300>

[0052] Next, the structures and functions of the animal behavior recording device 100 , the sensor device 200 , and the position detector 300 in this embodiment will be described in detail. Figure 3 , Figure 4 Each of the block diagrams exemplifies the hardware and functional block configurations of the animal behavior recording device 100 , the sensor device 200 , and the position detector 300 in one embodiment of the present invention.

[0053] <<Sensor device 200, position detector 300>>

[0054] First, refer to Figure 4 , the sensor device 200 and the position detector 300 in this embodiment are explained. The sensor device 200 is a device that is mounted on an appropriate part of the body of the cow C, and converts the movement of the cow C and the changes of various parts of the body of the cow C included in the behavior of the cow C into physical quantities and outputs them. In this embodiment, the sensor device 200 is fixed to the neck of the cow C, for example, by a collar, and can also be configured to be installed at other parts, such as the ears. Information indicating the movement caused by the cow C walking, the changes accompanying various actions such as getting up, the changes of various parts of the body accompanying shaking the head, rumination, etc., can be collectively captured as animal behavior information.

[0055] like Figure 4As shown in the example, the sensor device 200 includes a three-axis acceleration sensor 210, a three-axis angular velocity sensor 220, a processing unit 230, and a communication unit 240. The three-axis acceleration sensor 210 and the three-axis angular velocity sensor 220 are sensors for measuring acceleration in the three-axis directions of x, y, and z, and angular velocity around the three-axis directions of x, y, and z, respectively, and can obtain the acceleration in each axis and the angular velocity around each axis as, for example, an output voltage signal. The processing unit 230 includes: a sensor data acquisition unit 231, which receives the output signals from the three-axis acceleration sensor 210 and the three-axis angular velocity sensor 220, performs prescribed processing such as analog-digital (AD) conversion, and converts them into digital data; and a sensor data sending unit 232, which sends the digital data of the three-axis acceleration and the three-axis angular velocity generated by the sensor data acquisition unit 231 to the outside. The processing unit 230 includes an AD conversion circuit that receives analog signals from the acceleration sensor 210 and the angular velocity sensor 220 and converts them into digital signals, and a sensor data sending unit 232 that converts the digital data after AD conversion into a predetermined format and sends it out. The sensor data acquisition unit 231 and the sensor data sending unit 232 are controlled by a processor such as a central processing unit (CPU). In addition, as the acceleration sensor and the angular velocity sensor, a device that is modularized including various conversion circuits for sensor output signals can be appropriately used.

[0056] The communication unit 240 has a function of receiving digital data representing the sensor output signal from the sensor data sending unit 232 of the processing unit 230 and wirelessly transmitting it by a prescribed communication method. In the present embodiment, the communication unit 240 is configured as a communication module having a communication function based on Bluetooth (registered trademark). The digital data from the sensor data sending unit 232 sent by the communication unit 240 is sent as a Bluetooth data packet and received by the animal behavior recording device 100. In addition, the Bluetooth data packet is also received by the position detector 300 provided in the cattle pen CB. In addition, the above-mentioned communication method is an example and is not limited thereto.

[0057] The position detector 300 functions as a locator for utilizing the direction detection function included in Bluetooth 5.1, for example. Figure 4As shown, the position detector 300 can be configured to include a processing unit 310 including a processor, an antenna array 320, and a communication unit 330. The processing unit 310 can include a radio wave receiving unit 311 and a receiving angle calculation unit 312 as functional blocks. In Bluetooth 5.1, the angle of arrival of the Bluetooth signal can be obtained by the angle of arrival (AoA) of the radio wave. In the digital signal of Bluetooth 5.1, a monotonic sine wave of a fixed period called constant tone extension (CTE) is included after conventional data communication. The position detector 300 has the following functions: the CTE is received by the radio wave receiving unit 311 via the antenna array 320 including multiple antennas, and the incident angle of the Bluetooth signal is calculated in the receiving angle calculation unit 312 based on the difference in the phase angle of the received wave at each antenna. As described later, the reception angle data calculated by the reception angle calculation unit 312 of the position detector 300 is transmitted to the animal behavior recording device 100 via the communication unit 330. In addition, the position detection method for detecting the position of the sensor device 200 is not limited to the method using the Bluetooth function, and other available methods such as a position detection method using a satellite positioning system such as the Global Positioning System (GPS) and a position determination method based on a captured image of the cow C in the cowshed CB can be used.

[0058] <<Animal behavior recording device 100>>

[0059] Next, the animal behavior recording device 100 will be described. Figure 3 As shown, the animal behavior recording device 100 is an information processing device such as a server computer or a personal computer, and includes a processing unit 110, a storage unit 120, an input / output unit 130, a data interface (data IF (Interface)) unit 140, and a communication unit 150. The processing unit 110, the storage unit 120, the input / output unit 130, the data IF unit 140, and the communication unit 150 are connected by a bus which is an internal communication line not shown in the figure.

[0060] The processing unit 110 is a computing device composed of a processor such as a CPU, and reads various programs and data from a storage unit 120 described later to execute them, thereby realizing the functions of the animal behavior recording device 100. In this embodiment, the processing unit 110 performs data processing of each functional unit of the sensor data receiving unit 111, the sensor data analyzing unit 112, the position data receiving unit 113, the position data analyzing unit 114, the behavior estimation unit 115, the estimation result correction unit 116, the estimation result recording unit 117, and the behavior record output unit 118. The operation of each functional unit will be described below.

[0061] The storage unit 120 is a storage area for various programs and various data for making the hardware group function as the animal behavior recording device 100, and can be composed of a read-only memory (ROM), a random access memory (RAM), a flash memory, a semiconductor drive (SSD) or a hard disk (HDD), etc. Specifically, the storage unit 120 stores programs for making the processing unit 110 execute various functions of the present embodiment (control programs of the animal behavior recording device 100), various parameters, data used in behavior estimation, data related to the cattle C as the processing object, operation input data input from the outside, and generated behavior record data.

[0062] The input / output unit 130 includes various input devices such as a keyboard, a mouse, a touch panel, and a microphone for inputting data from the outside to the animal behavior recording device 100 , and output devices such as a monitoring display and a speaker for outputting and displaying the behavior recording data.

[0063] The data IF unit 140 has a function of controlling data communication among the processing unit 110 , the storage unit 120 , the input / output unit 130 , and the communication unit 150 .

[0064] The communication unit 150 is a communication module for transmitting and receiving various data between the sensor device 200 and the position detector 300, and is constituted as hardware such as a network interface card (NIC). The communication unit 150 can also be used to communicate with the animal behavior recording device 100. Figure 1 Execution of communication between the external communication network N illustrated in FIG.

[0065] Next, the functions of the animal behavior recording device 100 realized by each program executed by the processing unit 110 will be described.

[0066] The sensor data receiving unit 111 has the following function: receiving sensor data obtained from the sensor of the sensor device 200 mounted on the cow C. In the present embodiment, the sensor data is received every 0.2 to 10 seconds, but the time interval is not limited. In addition, the sensor data here refers to digital data obtained based on the output signals from the three-axis acceleration sensor and the three-axis angular velocity sensor of the sensor device 200.

[0067] The sensor data analysis unit 112 has the following functions: based on the three-axis acceleration sensor data (αx, αy, αz) and three-axis angular velocity sensor data (ωx, ωy, ωz) received from the sensor device 200 mounted on the cow C for 0.2 to 10 seconds, extract the length required to estimate the behavior and action of the cow C. As mentioned above, the data obtained from the sensor device 200 can be any one or both of the three-axis acceleration and the three-axis angular velocity. In addition, as sensor data, it is appropriate to use the image data of the cow C obtained by the camera, the air pressure data near the sensor device 200 mounted on the cow C, the sound data recorded around the cow C, the body temperature, heart rate, respiratory rate, blood pressure and other biological information related to the cow C.

[0068] The position data receiving unit 113 has a function of receiving position data from the position detector 300. As described above, the position data is, for example, the position coordinates of each position detector 300 in the cattle pen CB and the radio wave reception angle data from the sensor device 200 calculated by the reception angle calculation unit 312 of each position detector 300. The position coordinate data of the position detector 300 may also be stored in the storage unit 120 as a parameter in advance.

[0069] The position data analysis unit 114 calculates the position of the sensor device 200 in the cattle pen CB using the position coordinate data and the radio wave reception angle of the position detector 300 received and acquired by the position data receiving unit 113. Figure 1 As shown, if two sets of position detectors 300 are used, the position of the sensor device 200 as the radio wave transmission source can be obtained as the intersection of straight lines drawn from the positions of each position detector 300 according to the radio wave reception angle. According to the need for the position measurement accuracy of the sensor device 200, additional position detectors 300 can also be provided. By matching the obtained position of the sensor device 200 with the plane coordinates pre-set in the cattle pen CB, it can be determined where the cow C equipped with the sensor device 200 is in the cattle pen CB. In addition, the above-mentioned position detection method of the sensor device 200 is an example, and other methods can also be used, such as calculating the position coordinates based on the positioning satellite signal of GPS, and using the radio waves from the mobile communication base station.

[0070] The behavior estimation unit 115 has the following functions: estimating the behavior of the cow C based on the sensor data obtained in the sensor data analysis unit 112 (in this embodiment, the three-axis acceleration data and the three-axis angular velocity data measured by the sensor device 200) or the position information of the sensor device 200 in the cattle pen CB obtained in the position data analysis unit 114.

[0071] <Behavior estimation based on sensor data>

[0072] In the present embodiment, when estimating the behavior of the cow C based on the sensor data, a learning model is used, wherein the learning model is created using training data that establishes a correspondence between a data set including the sensor data and the behavior of the cow C when the sensor data is obtained. In the present embodiment, the learning model is stored in the behavior estimation model storage unit 121 of the storage unit 120. Figure 5 2 shows a configuration example of training data used in the behavior estimation process. Figure 5 The training data illustrated in the example is schematically shown, and the acceleration / angular velocity corresponding to each action type refers to a group of multiple acceleration / angular velocity values ​​obtained within a fixed time, rather than a group of one value. In other words, the group corresponding to each action type can be said to be a set of acceleration / angular velocity value groups that serve as the basis for determining the action type. Figure 5 In the training data, the actions of cow C determined based on sensor data are classified into 12 action types, namely, "drinking water", "eating (milk powder)", "eating (hay)", "ruminating", "sucking milk", "shaking head", "moving (walking)", "moving (running)", "standing up", "lying down", "coughing", and "lying down / standing state", and the corresponding groups of three-axis acceleration data and three-axis angular velocity data are established in correspondence with each action type. The training data can be created by marking the action type based on the dynamic image data for the dynamic image data recording the action of cow C and the group of sensor data obtained corresponding to the dynamic image data. In this embodiment, as a specific machine learning architecture, a neural network using long short-term memory (LSTM) is adopted. Among them, it is also possible to use other machine learning methods or rule-based judgment processing. For example, a set of past values ​​of acceleration data and angular velocity data corresponding to each action type can be created in the form of a statistical correspondence between the two, and the newly acquired sensor data can be compared with such a set to infer the action type.

[0073] <Behavior estimation based on location information>

[0074] The behavior estimation of the cow C can also be performed based on the position information of the cow C in the cowshed CB. The position data analysis unit 114 of the animal behavior recording device 100 can be used to find out where the sensor device 200 is located in the cowshed CB, that is, where the cow C is in the cowshed CB, based on the position data from the position detector 300 set in the cowshed CB. For example, when the position information about the cow C indicates that the cow C is at the "feeding place", "nursing place" and "drinking place" in the cowshed CB, it can be estimated that the cow C is taking the actions of "eating", "sucking milk" and "drinking water" respectively. In addition, since the temporal change of the position information of the cow C can be detected, the presence or absence of the change in the position information and its speed can be used to determine whether the cow C is taking actions such as "moving (walking)", "moving (running)", "lying down / standing". The data used for behavior estimation based on the position information is stored in the position information analysis data storage unit 122 of the storage unit 120. The position information analysis data includes planar position coordinates indicating the ranges of “feeding place”, “nursing place”, and “drinking place” for determining the location of the cow C in the cowshed CB. Figure 6 2 shows a configuration example of a setting object position information table indicating the setting position of each setting object set in the cattle pen CB. Figure 6 The object position information table 1221 illustrated in FIG. 1 is stored in the position information analysis data storage unit 122, and stores the types of objects associated with the position information indicating the positions in the cattle pen CB. Figure 6 In the example, for example, the position of the "feeding place F" in the cattle pen CB is represented by the position information of (X11~X12, Y11~Y12). This means that in the cattle pen CB, the "feeding place F" is located in the area determined by the four position coordinates (X11, Y11), (X11, Y12), (X12, Y11), (X12, Y12). The action estimation unit 115 can determine whether the cow C is near any setting by comparing the position data from the sensor device 200 mounted on the cow C with the position information of the setting recorded in the setting position information table 1222. For example, if it is determined that the cow C is near the feeding place F, it can be estimated that the cow C is taking action to eat. In the setting position information table 1221, settings that are considered to help improve the accuracy of the action estimation of the cow C, or specific places in the cattle pen CB, can be recorded, without being limited to the settings exemplified above.

[0075] The estimation result correction unit 116 has the following function: considering the estimation result from another point of view, the behavior type of the cow C estimated by the behavior estimation unit 115 is corrected. As mentioned above, in this embodiment, the behavior estimation unit 115 is configured to estimate the behavior type of the cow C in a time series based on the three-axis acceleration data and the three-axis angular velocity data obtained from the sensor device 200 mounted on the cow C, or the position information of the cow C based on the position data from the position detector 300 set in the cowshed CB. The estimation result correction unit 116 uses different estimation logics to correct the behavior type of the cow C estimated based on the sensor data or the position information. In this embodiment, the estimation result correction unit 116 verifies and corrects the behavior type of the cow C estimated based on the sensor data based on the position information, and verifies and corrects the behavior type of the cow C estimated based on the position information based on the sensor data. By correcting the behavior estimation result, the estimation accuracy of the behavior type of the cow C can be improved. In addition, other viewpoints can be further introduced in the correction process in the estimation result correction unit 116. For example, regarding the estimation result of the action type recorded in time series, when a "movement (walking)" is recorded mixed in the middle of the continuous recording of "eating", the mixed "movement (walking)" lacks continuity with the previous and next action types and is therefore considered to be noise. The correction of the action estimation result can also be verified from the viewpoint of the continuity of the recording of such action types.

[0076] The estimation result recording unit 117 has a function of recording the corrected action type estimation results obtained by the estimation result correction unit 116 in time series. The corrected action type estimation results are stored in the action record storage unit 123 of the storage unit 120 in time series. The structure of the action record storage unit 123 is shown in FIG. Figure 7 , Figure 8 . Figure 7 This is an example of a case where behavior estimation is performed based on acceleration data and angular velocity data, and the behavior estimation result is corrected using position information. Figure 8 This is an example of a situation where behavior estimation is performed based on position information and correction is applied using acceleration data and angular velocity data. Figure 7 In the example, the identifier assigned to each cow C, i.e., the individual identification (ID), is recorded in association with the year, month, day and time of the record, the acceleration data and angular velocity data at that time, and the type of behavior estimated based on it. In addition, for each record, the position of the cow C in the cowshed CB obtained at the corresponding year, month, day and time, the place where the cow C stayed, and the type of behavior corrected by the position information are recorded. Refer to Figure 7, then for cow C with individual ID "001", "feeding" is recorded as the action type estimated based on the acceleration data and angular velocity data. Since it matches the "feeding place" estimated based on the position of cow C, it is also recorded as "feeding" in the corrected action type. In contrast, referring to the third record, the action type estimated based on the acceleration data and angular velocity data is "sucking milk", while the staying place estimated based on the position is "feeding place", which does not match the previously estimated action type. In this case, in this embodiment, the information of the staying place estimated based on the position, namely the "feeding place", is given priority, and the action type is corrected to "feeding". On the other hand, in Figure 8 In the example, the identifier assigned to each cow C, i.e., the individual ID, is associated with the date and time of the record, the location information at that time and the estimated place of stay based on it, and whether it is moving. In addition, for each record, the acceleration data and angular velocity data of the cow C obtained at the corresponding date and time, the action type estimated therefrom, and the corrected action type are recorded. Figure 8 , for the cow C with individual ID "001", according to the location information, it is recorded that it stayed at the "feeding place" and "did not move". Since this matches the action type inferred from the acceleration data and angular velocity data of cow C, that is, "eating", it is also recorded as "eating" in the corrected action type. In contrast, referring to the fourth record, regarding the place of stay inferred from the location information, "drinking place" is recorded, and regarding movement, "none" is recorded, and the action type inferred from the acceleration data and angular velocity data is "standing state". In this case, as the corrected estimated action type, it is considered that the cow is actually stationary and does nothing even at the drinking place, so the action type is recorded as "resting". In addition, since the type of animal action type and the correction strategy of the action type can be changed according to the target animal, the purpose of the action record, etc., the structure of the action record storage unit 123 can also be freely changed accordingly.

[0077] The behavior record output unit 118 performs output processing such as reading the behavior record of the animal recorded in the behavior record storage unit 123 in response to an input operation from the input / output unit 130 or the like and displaying the animal behavior record on a display.

[0078] The processing target data storage unit 124 stores individual information about each cow C that is the target of the behavior record. Fig. 9 2 shows a configuration example of the processing target data storage unit 124. Fig. 9In the processing object data storage unit 124 illustrated in the example, the sensor device ID, which is a unique identifier of the sensor device 200, the type of cattle indicating the type of cattle, the gender, age, health status, and medical history items are recorded, corresponding to the individual ID of each cow C that is assigned as an identifier to the object of the action record. The sensor device ID is attached to the sensor data sent from each sensor device 200 installed on the cow C to the animal action recording device 100, so that it is possible to identify which sensor device 200 has obtained the received sensor data. Since the sensor device ID is also received in the position detector 300, the position of a specific sensor device 200 can be associated with the sensor device ID. In addition to recording the health status as an evaluation value as shown in the figure, it can also be recorded specifically in text. Medical records can also be recorded in an appropriate format. The record items of the processing object data storage unit 124 are not subject to Fig. 9 The constraints of the example can be determined appropriately.

[0079] <Data processing by the animal behavior recording device 100>

[0080] Next, the data processing executed by the animal behavior recording device 100 in this embodiment will be described. The animal behavior recording device 100 mainly executes a behavior estimation process and a behavior estimation result correction process.

[0081] <<Behavior estimation processing based on sensor data>>

[0082] exist Fig.10 2 is a flowchart showing an example of a process flow of a behavior estimation process executed by the animal behavior recording device 100 in this embodiment. The behavior estimation process is started when the animal behavior recording device 100 is powered on and started, for example.

[0083] Fig.10 The behavior estimation process illustrated in FIG. 1 is executed at predetermined time intervals for each cow C kept in the cowshed CB, specifically, for the sensor device 200 attached to each cow C (a loop of step S11 ).

[0084] The sensor data receiving unit 111 of the animal behavior recording device 100 receives sensor data from the triaxial acceleration sensor and the triaxial angular velocity sensor from the sensor device 200 mounted on the cow C (step S12 ).

[0085] The sensor data analysis unit 112 calculates triaxial acceleration data and triaxial angular velocity data based on the sensor data received from the triaxial acceleration sensor and the triaxial angular velocity sensor (step S13 ).

[0086] The action estimation unit 115 applies the learning model obtained by pre-learning the correspondence between the action type of cow C and the three-axis acceleration data and the three-axis angular velocity data to the three-axis acceleration data and the three-axis angular velocity data obtained in step S13 to obtain the estimation result of the action type (step S14).

[0087] The action estimating unit 115 stores the action type estimated in step S14 in the action record storage unit 123 of the storage unit 120 (step S15 ).

[0088] The position data receiving unit 113 receives the planar position coordinates of the position detector 300 and the radio wave reception angle of the sensor device 200 received by the position detector 300 from the position detector 300 installed in the cowshed CB (step S16 ).

[0089] The position data analysis unit 114 calculates the position of the sensor device 200 in the cattle pen CB as position information indicating the location of the cow C based on the position coordinates and the reception angle of the position detector 300 received from the position detector 300 (step S17 ).

[0090] The behavior estimation unit 115 estimates the behavior type of the cow C based on the position information calculated in step S17 (step S18).

[0091] The behavior estimation unit 115 stores the location information and the behavior type estimated in step S18 in the behavior record storage unit 123 (step S19). As described above, the above processing is repeatedly performed at a predetermined time interval for each cow C during the operation of the animal behavior recording device 100, and the behavior record of each cow C is accumulated.

[0092] <<Correction processing of action estimation results>>

[0093] Next, a behavior estimation result correction process of correcting the behavior type of the cow C estimated by the behavior estimation unit 115 will be described. Fig.11 This is a flowchart showing an example of the processing flow of the action estimation result correction processing. Fig.11 The behavior estimation result correction process illustrated in FIG. 1 is started when the animal behavior recording device 100 is powered on and started, similarly to the behavior estimation process, and is continuously executed while the animal behavior recording device 100 is operating.

[0094] In the animal behavior recording device 100, the loop process of step S21 is executed at a fixed time interval for each cow C in the cowshed CB. In the present embodiment, the time interval is set to 1 hour.

[0095] The estimation result correction unit 116 first counts the types of actions recorded in the last hour and performed in a very short period of time, here the number of "coughing" and "moving (running)" (step S22). This is to prevent erroneous judgment as noise by verifying from the perspective of the continuity of the action described later.

[0096] The estimation result correction unit 116 compares the action type estimated from the sensor data with the action type estimated from the position information using the time of each record in the action record storage unit 123 as a key (step S23). When it is determined that the two action types are inconsistent (step S24: YES), the estimation result correction unit 116 performs correction using the action type estimated from the position information as the estimation result (step S25). When it is determined that the two action types are not inconsistent (step S24: NO), the process proceeds to step S26.

[0097] The estimation result correction unit 116 of the animal behavior recording device 100 verifies the continuity of the corrected estimation results recorded in the behavior record storage unit 123. Specifically, the estimation result correction unit 116 refers to the corrected estimation results of the behavior types recorded in the behavior record storage unit 123 within the past minute, investigates whether there are items that are determined to be discontinuous in the recorded behavior types, and performs correction to ensure continuity. An example of correction for ensuring continuity is a situation where other behavior types such as "moving (walking)" are recorded in the middle of recording "eating (hay)" within a certain period of time. In this case, the record of "moving (walking)" is corrected to "eating (hay)" from the perspective of continuity.

[0098] As described above, the above process is repeatedly performed for each cow C at a fixed time interval, for example, every hour, during the operation of the animal behavior recording device 100. In addition, when the estimated behavior type has a defect in continuity, the defect can sometimes be corrected by correcting the estimated result using position information. In consideration of this situation, the verification of the behavior type from the perspective of continuity can also be omitted.

[0099] <Animal behavior recording system according to other embodiments>

[0100] Next, an animal behavior recording system 1 according to another embodiment of the present invention will be described. The basic structure of the animal behavior recording system 1 of this embodiment is similar to that of the aforementioned Figures 1 to 11 The described embodiment (hereinafter, for convenience, sometimes referred to as the "first embodiment") is the same, so here, in this embodiment (hereinafter, for convenience, sometimes referred to as the "second embodiment"), the focus will be on the differences from the first embodiment.

[0101] The animal behavior recording system 1 in the second embodiment has Figure 1 The structure of the first embodiment described above is substantially the same as that of the first embodiment, and has a function of estimating the behavior of the cow C in the cowshed CB based on the three-axis acceleration data and the three-axis angular velocity data from the sensor device 200 and the position data from the position detector 300, and recording it in time series. The structures of the animal behavior recording device 100, the sensor device 200, and the position detector 300 in the second embodiment are respectively the same as those in the reference 1. Figure 2 , Figure 3 The first embodiment described is the same.

[0102] <Data Processing Executed by the Animal Behavior Recording Device 100 in the Second Embodiment>

[0103] In the second embodiment, the process of estimating the behavior of the animal and the process of correcting the estimated result are different from those in the first embodiment. The following describes the behavior estimation process and the estimation result correction process performed by the animal behavior recording device 100 in the second embodiment. The behavior estimation process in the present embodiment is configured to first perform a rough behavior estimation based on the location of the cow C in the cowshed CB and whether the cow C is moving, and apply the required correction to the behavior estimation based on the sensor data received from the sensor device 200 at this time. Specifically, in the present embodiment, the position data from the position detector 300 and the sensor data from the sensor device 200 of the cow C are recorded at relatively short time intervals. Based on the recorded position information, the animal behavior recording device 100 repeatedly performs the behavior estimation process and the estimation result correction process at longer time intervals.

[0104] <<Data acquisition processing>>

[0105] exist Fig.12 1 shows an example of a processing flow of the data acquisition process executed by the animal behavior recording device 100 in this embodiment as a flowchart. The data acquisition process is started when the animal behavior recording device 100 is powered on and started, for example.

[0106] Fig.12 The data acquisition process illustrated in the example is performed at a fixed time interval for each cow C raised in the cowshed CB. Specifically, the process of steps S32 to S35 is performed for each sensor device 200 installed on each cow C (a loop of step S31). For example, in the present embodiment, for each sensor device 200, the execution time interval of the data acquisition process is about 0.01 seconds to 1 minute, but it is not limited to this, and the execution time interval can be appropriately determined.

[0107] The position data receiving unit 113 receives the planar position coordinates of the position detector 300 and the radio wave reception angle from the sensor device 200 received by the position detector 300 from the position detector 300 installed in the cowshed CB (step S32 ).

[0108] The position data analysis unit 114 calculates the position of the sensor device 200 in the cattle pen CB based on the position coordinates and receiving angle of the position detector 300 received from the position detector 300 as position information indicating the location of the cow C, and records it in the action record storage unit 123 (step S33).

[0109] The sensor data receiving unit 111 of the animal behavior recording device 100 receives output data signals from the triaxial acceleration sensor and the triaxial angular velocity sensor from the sensor device 200 mounted on the cow C (step S34 ).

[0110] The sensor data analysis unit 112 calculates the three-axis acceleration data and the three-axis angular velocity data based on the output data signals received from the three-axis acceleration sensor and the three-axis angular velocity sensor, and records the calculated data in the action record storage unit 123 (step S35 ).

[0111] Through the above data acquisition process, basic data for executing the animal behavior estimation process in the second embodiment is collected.

[0112] <<Action estimation processing / Estimation result correction processing>>

[0113] Next, the behavior estimation process and the estimation result correction process performed by the animal behavior recording device 100 of this embodiment will be described. Fig.13 2 shows an example of a process flow of the behavior estimation process and the estimation result correction process in this embodiment. The behavior estimation process and the estimation result correction process are started after a fixed time has passed since the data acquisition process of the animal behavior recording device 100 was started, for example.

[0114] Fig.13 The behavior estimation process and estimation result correction process illustrated in the example are performed at a fixed time interval for each cow C raised in the cowshed CB, specifically, for the sensor device 200 installed on each cow C (a loop of step S41). For example, in this embodiment, the execution time interval of the behavior estimation process and estimation result correction process for each cow C is 1 hour. Fig.12 After one hour has passed since the start of the data acquisition process illustrated in the example, the action estimation process and the estimation result correction process are started and then executed every one hour. However, the execution time interval is not limited to this and may be determined appropriately.

[0115] The behavior estimation unit 115 of the animal behavior recording device 100 estimates whether the cow C is moving and the location of the cow C in the cowshed CB based on the location information recorded in the behavior record storage unit 123 (step S42). As mentioned above, in the present embodiment, in the data acquisition process, the acquisition of location information and sensor data is performed at time intervals of about 0.2 to 1 second. If data acquisition is performed every second, 3600 sets of data per hour will be accumulated for each sensor device 200. The behavior estimation unit 115 estimates the behavior of the cow C installed with each sensor device 200 based on the data accumulated in the behavior record storage unit 123 in the last hour. In step S42, first, the location information recorded in time series is used to estimate whether the cow C is moving in the cowshed CB at the time of each data acquisition and the location of the cow C in the cowshed CB.

[0116] The estimation result correction unit 116 compares the behavior type of the cow C estimated based on the sensor data with the estimation result estimated in step S42, whether the cow C was moving in the cowshed CB when each data was acquired, and where the cow C was in the cowshed CB (step S43). The correction strategy for the behavior type corresponding to the comparison result can be appropriately specified. As an example, it is as follows.

[0117] When it is estimated based on the position information that "cow C has hardly moved" and is "located in a resting place in the cowshed CB (a place other than the feeding place, nursing place, and drinking place)", the action type is estimated to be either "lying down" or "standing" indicating rest, or "ruminating" with little body movement. Similarly, when it is estimated based on the position information that "cow C has hardly moved" and is "located in the feeding place in the cowshed CB", the action type is estimated to be either "lying down" or "standing" indicating rest, or "ruminating" or "feeding" with little body movement. In addition, when it is estimated based on the position information that "cow C is moving", the action type is estimated to be either "moving (walking)" or "moving (running)".

[0118] The estimation result correction unit 116 records the action type determined in step S43 by taking into account the action type estimated based on the sensor data in the action determined based on the position information in the action record storage unit 123 (step S44 ).

[0119] According to the animal behavior recording device 100 in the second embodiment described above, by first understanding the behavior of the cow C in the cowshed CB based on the position information and comparing it with the behavior type estimated based on the sensor data at the same time, reasonable correction can be performed.

[0120] <Results of Behavior Type Estimation of Cow C According to Embodiment of the Present Invention>

[0121] Fig.14 2 illustrates an example of the result of estimating the behavior type of a cow C obtained by the animal behavior recording device 100 according to the first embodiment of the present invention. Fig.14 , the processing results when the action type is estimated as "sucking milk" or "eating food". For each action type, the histogram shows the first estimation result based on the sensor data, the correction result by the continuity verification, and the final correction result by the continuity and position information. Fig.14 The horizontal axis of the graph is the difference between the actual sucking time and feeding time measured from the video images in the last 24 hours and the predicted time calculated every hour. In the case of any action type, it is shown that the difference between the actual action time and the actual action time is reduced (the frequency of the difference time being 0 is increased) by continuously verifying the one-time estimation result and then correcting it based on the position information, and the prediction accuracy of the action type is improved.

[0122] <Behavior recording by the animal behavior recording device 100>

[0123] exist Fig.15 1 shows a graph showing temporal changes in the behavior types recorded by the animal behavior recording device 100 of the first embodiment. Such a graph can be displayed on a display or the like by input operation from the input / output unit 130 of the animal behavior recording device 100, for example. Fig.15 The example shows the action records of each cow in the cowshed CB where four cows 1 to 4 are kept. In each chart, the action types are roughly divided into four modes: (a) eating-related actions including eating / drinking / sucking milk, (b) resting including standing and lying down, (c) rumination, and (d) movement including walking and running. The temporal changes in their frequencies are shown for each cow in a line graph. This record of the action type of each cow can be used, for example, to predict changes in the physical condition of cow C and the diseases and childbirth that can be predicted based on the changes in the physical condition. For example, if we focus on Fig.15 The action record of Cow 4 shown by the dotted line in the figure is shown by the dotted line respectively. It is observed that (b) in terms of rest, it is judged to be resting more frequently than other cows, and (d) in terms of movement, it is moving less frequently than other cows. It can be considered that this implies that the activity level of Cow 4 has become low-key due to some changes in physical condition. In this way, based on the temporal changes in the action type of Cow C recorded by the animal action recording device 100 according to the embodiment of the present invention, changes in the physical condition of Cow C, signs of disease, estrus, delivery, weaning, etc. can be known. For example, if a generated Fig.15The learning completion model that has been learned by establishing correspondence between the change patterns of the action types (a) to (d) illustrated in the figure and the physical condition changes, diseases, estrus, parturition, and weaning observed for each cow C can capture signs of physical condition changes, diseases, etc. of the cow C based on the action types recorded by the animal action recording device 100.

[0124] According to the above-described embodiment, the following effects are achieved.

[0125] The animal behavior recording device 100 of the present embodiment includes a processing unit 110, which obtains information indicating the behavior of an animal, namely, animal behavior information, obtains information indicating the location of the aforementioned animal, namely, animal position information, and infers the action of the aforementioned animal based on the aforementioned animal behavior information and the aforementioned animal position information, and records the action in a time series.

[0126] In this way, the behavior of animals can be grasped with high precision and efficiency.

[0127] Optionally, the animal behavior information is acceleration data obtained by an acceleration sensor 210 provided in a sensor device 200 of the animal, and angular velocity data obtained by an angular velocity sensor 220, or either one of them, and the processing unit 110 comprises: an action estimation unit 115 for estimating the action of the animal based on the acceleration data and angular velocity data or either one of them; and an estimation result correction unit 116 for correcting the action of the animal estimated by the action estimation unit 115 based on the animal position information.

[0128] In this way, the behavior of the animal estimated based on the acceleration data and the angular velocity data or any one of them is corrected based on the above-mentioned animal position information, thereby improving the estimation accuracy of the animal's behavior.

[0129] Optionally, a storage unit 120 is provided, and the storage unit 120 stores information on the positions of multiple types of facilities required for raising cattle C, which are arranged in the cattle pen CB. The estimation result correction unit 116 determines the type of facilities at the position where the target cattle C is located based on the stored information on the positions of the facilities and the position information of the cattle C, and corrects the behavior of the cattle C estimated by the behavior estimation unit 115 based on the determined type of facilities. The so-called facilities are feeding places F, nursing places M, drinking places W, etc.

[0130] In this way, the estimated behavior of the cow C is corrected according to the type of the installation object corresponding to the position of the cow C, thereby improving the accuracy of the estimated behavior of the cow C.

[0131] Optionally, the animal behavior information is both or either one of acceleration data obtained by an acceleration sensor provided on the animal and angular velocity data obtained by an angular velocity sensor provided on the animal, and the processing unit 110 comprises: a behavior estimation unit 115 for estimating the location of the animal and its behavior in the location based on the animal position information; and an estimation result correction unit 116 for comparing the estimated location of the animal and its behavior with the acquired animal behavior information for correction.

[0132] In this way, the behavior of the animal estimated based on the above-mentioned animal position information is corrected based on the acceleration data and the angular velocity data or either of them, thereby improving the estimation accuracy of the animal's behavior.

[0133] Optionally, there is a storage unit 120 storing information on the positions of multiple types of facilities required for raising cattle C arranged in the cattle pen CB, and the behavior inference unit 115 determines the type of facilities at the position where the target cattle C is located based on the stored information on the positions of the facilities and the position information of the cattle C, and infers the behavior of the aforementioned target cattle C based on the determined type of facilities.

[0134] In this way, the behavior of the cow C can be estimated with high accuracy based on the type of the installation object corresponding to the position of the cow C.

[0135] Optionally, the behavior estimation unit 115 estimates the behavior of the animal using a learned model that has learned the relationship between the acceleration data and the angular velocity data obtained from the animal or any one of them and the behavior of the animal classified into a plurality of types.

[0136] In this way, the architecture of machine learning can be used to improve the accuracy of the animal behavior estimation result based on the above-mentioned acceleration data and angular velocity data or either of them obtained from the animal.

[0137] Optionally, the behavior estimating unit 115 estimates the behavior of the animal based on the behavior of the animal and the acceleration data and angular velocity data acquired from the animal or a statistical correspondence between the acceleration data and the angular velocity data or any one of them.

[0138] In this way, based on the aforementioned statistical correspondence, the accuracy of the animal behavior estimation result based on the aforementioned acceleration data and angular velocity data or either of them obtained from the animal can be improved.

[0139] Optionally, the animal position information is calculated based on an arrival direction of radio waves, which are radio waves transmitted by an acceleration sensor and an angular velocity sensor or any one of them provided on the animal via a communication unit.

[0140] In this way, the position information of the animal can be acquired by using the radio waves for data transmission from the sensor device 200 installed on the animal.

[0141] Optionally, the action record of the animal recorded in time series by the processing unit 110 is used to predict at least one period of the animal's disease, estrus, delivery, fall, growth and weaning.

[0142] In this way, based on the animal's behavior records, events such as animal illness, estrus, birth, fall, growth, and weaning can be known in a timely and thorough manner.

[0143] Optionally, the animal behavior information includes at least one of output data from an air pressure sensor and an acoustic sensor provided on the animal or any one of them, and biological information obtained from the animal.

[0144] In this way, basic data for estimating the behavior of the animal increases, so the accuracy of behavior estimation can be improved.

[0145] The above series of processing can be performed by hardware or software. In other words, Figure 2 , Figure 3 The functional structure is merely an example and is not particularly limited. That is, as long as the animal behavior recording device 100 has a function that can execute the above series of processing as a whole, the function blocks used to implement the function are not particularly limited. Figure 2 , Figure 3 In addition, a functional block can be composed of a hardware unit, a software unit, or a combination of them. The functional structure in the present embodiment is realized by a processor that performs arithmetic processing. The processor that can be used in the present embodiment includes, in addition to processors composed of various processing devices such as single processors, multi-processors, and multi-core processors, processors composed of these various processing devices and processing circuits such as application specific integrated circuits (ASIC) or field programmable gate arrays (FPGA).

[0146] When a series of processes are performed by software, the program constituting the software is installed from a network or a recording medium to a computer, etc. The computer may also be a computer embedded in dedicated hardware. In addition, the computer may also be a computer capable of performing various functions by installing various programs, such as a general-purpose personal computer.

[0147] The recording medium containing such a program is composed not only of removable media such as Universal Serial Bus (USB) memory distributed separately from the device body in order to provide the program to the user, but also of recording media provided to the user in a state pre-embedded in the device body. The removable medium is composed of, for example, a magnetic disk (including a floppy disk), an optical disk, or a magneto-optical disk. The optical disk is composed of, for example, a compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a Blu-ray (registered trademark) Disc, etc. The magneto-optical disk is composed of a mini-disk (MD), etc. In addition, the recording medium provided to the user in a state pre-embedded in the device body is composed of, for example, a ROM on which the program is recorded or a hard disk contained in the storage unit 120.

[0148] In the present specification, the steps describing the program recorded in the recording medium naturally include processing performed in time series according to the order, and also include processing that is not necessarily processed in time series but is executed in parallel or independently.

[0149] Several embodiments of the present invention have been described above, but these embodiments are merely illustrative and do not limit the technical scope of the present invention. The present invention may adopt various other embodiments, and the above-mentioned embodiments and the various structures of the modified examples may be combined. Furthermore, various changes such as omission or substitution may be made without departing from the scope of the present invention. These embodiments and their modifications are included in the scope or gist of the invention described in this specification, etc., and are included in the invention described in the claims and the scope of their equivalents.

[0150] Reference numerals

[0151] 1Animal Action Recording System

[0152] 100 Animal Action Recording Devices

[0153] 110 Processing Department

[0154] 115 Action Presumption Department

[0155] 116 Estimation Result Correction Unit

[0156] 120 Storage Department

[0157] 121 Action estimation model storage unit

[0158] 123 Action Record Storage Department

[0159] 200 sensor devices

[0160] 210 three-axis acceleration sensor

[0161] 220 three-axis angular velocity sensor

[0162] 300 position detector

Claims

1. An animal behavior recording device, comprising: An animal behavior information acquisition unit that acquires information indicating the behavior of animals raised in a predetermined breeding area, namely, animal behavior information; an animal position information acquisition unit, which acquires information indicating the position of the animal, namely, animal position information; and The animal behavior recording unit estimates the behavior of the animal based on the animal behavior information and the animal position information, and records the behavior in a time series.

2. The animal behavior recording device according to claim 1, wherein: The animal behavior information is acceleration data acquired by an acceleration sensor installed in the animal, and angular velocity data acquired by an angular velocity sensor installed in the animal, or either one of them. The animal behavior recording unit includes: a behavior estimating unit that estimates the behavior of the animal based on the acceleration data and the angular velocity data or any one of them; and an estimation result correction unit that corrects the behavior of the animal estimated by the behavior estimating unit based on the animal position information.

3. The animal behavior recording device according to claim 2, comprising a storage unit for storing information on positions of a plurality of types of installation objects required for raising animals and arranged in the raising area. The estimation result correction unit determines the type of the setting at the location of the target animal based on the stored information on the location of the setting and the animal location information, and corrects the behavior of the animal estimated by the behavior estimation unit based on the determined type of the setting.

4. The animal behavior recording device according to claim 1, wherein: The animal behavior information is acceleration data acquired by an acceleration sensor installed in the animal, and angular velocity data acquired by an angular velocity sensor installed in the animal, or either one of them. The animal behavior recording unit comprises: a behavior estimation unit, which estimates the location of the animal and its behavior in the location based on the animal position information; and an estimation result correction unit, which compares the estimated location of the animal and its behavior with the acquired animal behavior information for correction.

5. The animal behavior recording device according to claim 4, comprising a storage unit for storing information on positions of a plurality of types of installation objects required for raising animals and arranged in the raising area. The behavior estimating unit determines the type of the object at the location of the target animal based on the stored location information of the object and the animal location information, and estimates the behavior of the target animal based on the determined type of the object.

6. The animal behavior recording device according to any one of claims 2 to 5, wherein: The behavior estimating unit estimates the behavior of the animal using a learned model that has learned the relationship between the acceleration data and the angular velocity data acquired from the animal or either of them and the behavior of the animal classified into a plurality of types.

7. The animal behavior recording device according to any one of claims 2 to 5, wherein: The behavior estimating unit estimates the behavior of the animal based on the behavior of the animal and the acceleration data and the angular velocity data acquired from the animal, or a statistical correspondence between the acceleration data and the angular velocity data or any one of them.

8. The animal behavior recording device according to any one of claims 2 to 7, wherein: The animal position information is calculated based on the arrival direction of radio waves transmitted by an acceleration sensor and an angular velocity sensor or any one of them provided in the animal via a communication unit.

9. The animal behavior recording device according to any one of claims 1 to 8, wherein: The behavior record of the animal recorded in time series by the animal behavior recording unit is used to predict at least one period of disease, estrus, delivery, fall, growth and weaning of the animal.

10. The animal behavior recording device according to any one of claims 1 to 9, wherein: The animal behavior information includes at least one of output data from an air pressure sensor and an acoustic sensor provided on the animal or any one of them, and biological information acquired from the animal.

11. A method for recording animal behavior, The information processing device acquires animal behavior information which is information indicating the behavior of animals kept in a predetermined keeping area. obtaining information indicating the location of the animal, i.e., animal location information, Based on the aforementioned animal behavior information and the aforementioned animal location information, the actions of the aforementioned animals are inferred and the actions are recorded in a time series.

12. A program causing an information processing device to execute the following processing: Processing of acquiring information indicating the behavior of animals kept in a predetermined keeping area, namely, animal behavior information; A process of obtaining information indicating the location of the aforementioned animal, namely, animal location information; and, Based on the aforementioned animal behavior information and the aforementioned animal position information, the action of the aforementioned animal is estimated, and the action is recorded in a time series.

Citation Information

Patent Citations

  • Pig behavior monitoring method and device

    CN105193420A

  • Behavior specification device, behavior specification method, and program

    JP2019062822A

  • Health state management system and management method for cattle and health state management program

    JP2019122368A

  • Animal behavior estimation device, animal behavior estimation method, and program

    JP2021141876A

  • Animal behavior estimation system, animal behavior estimation support device, animal behavior estimation method, and program

    JP2021144631A