Livestock health condition management system, livestock wearable device, livestock health condition management method and program

Abstract

To provide a technique capable of accurately detecting a health condition of livestock to be managed with a simple system configuration.SOLUTION: A health condition management system for livestock according to the present invention comprises: detection means including a temperature sensor and an acceleration sensor, fitted to a livestock to be managed, and acquiring body surface temperature information of the livestock, posture information of the livestock, and activity amount information of the livestock; and diagnosis means for diagnosing a health condition of the livestock on the basis of the body surface temperature information of the livestock, the posture information of the livestock, and the activity amount information of the livestock.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a livestock health condition management system, a livestock wearable device, a livestock health condition management method, and a program. [Background technology]

[0002] In recent years, while the number of people engaged in livestock farming has decreased and the population has been aging, the number of livestock kept per household has been increasing, making it difficult to allocate sufficient time to observe each animal. In addition, price competition for livestock products with overseas countries is expected to intensify in the future, making labor-saving and cost-reduction in livestock production an urgent issue. For this reason, there is a high need for technology that can constantly monitor the health of a large number of livestock.

[0003] In response to this, technologies have been proposed that use wearable devices attached to the cows and information obtained from location sensors installed within the management area to manage whether the cows are eating, drinking, walking, lying down, running, standing still, in heat, or ruminating (e.g., Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-7613 A Summary of the Invention [Problem to be solved by the invention]

[0005] According to the method described in the above patent document, it is possible to manage the activity state of the managed livestock without relying on human labor. However, the technology described in the above document can determine whether a cow is in heat, but cannot accurately determine its health state. In addition, a means for detecting the location of the managed cow is required, resulting in a large-scale system. Furthermore, there is a lot of information to be processed to determine the activity state of the cow, which makes the algorithm more complex, and there is a risk that the system will be expensive.

[0006] In view of the above problems, an object of the present invention is to provide a technique that enables accurate knowledge of the health condition of managed livestock using a simple system configuration. [Means for solving the problem]

[0007] In order to solve the above problems, the present invention provides a livestock health condition management system, comprising: a detection means having a temperature sensor and an acceleration sensor, attached to a livestock to be managed, and configured to acquire body surface temperature information, posture information, and activity amount information of the livestock; A diagnostic means for diagnosing the health condition of the livestock based on the body surface temperature information of the livestock, the posture information of the livestock, and the activity amount information of the livestock; has.

[0008] Note that "livestock body surface temperature information," "livestock posture information," and "livestock activity information" refer to general information relating to livestock body surface temperature, general information relating to livestock posture, and general information relating to livestock activity, respectively.

[0009] The detection means may be, for example, a wearable device attached to a livestock. A simple system configuration including a wearable device that can measure the temperature and posture of livestock and a computing device that is attached to each livestock and calculates the livestock's body surface temperature, posture, and activity level from the output information of the sensor makes it possible to accurately grasp the health condition of livestock.

[0010] The posture information of the livestock may include information on whether the livestock is in an upright position or a lying position, the acceleration sensor may be a three-dimensional acceleration sensor, the detection means may include a posture index calculation means attached to the tail of the livestock and calculating roll angle information of the tail of the livestock from the output of the three-dimensional acceleration sensor, and the diagnosis means may include a posture state determination means for determining whether the livestock is in an upright position or a lying position based on the roll angle information. Note that "upright position" refers to an upright position, and "lying position" refers to a lying position.

[0011] By configuring the detection means in this way, it becomes possible to attach the wearable device to livestock non-invasively and with low burden. In addition, since it is possible to determine whether the posture of the livestock is standing or lying down based on the roll angle of the tail obtained from the three-dimensional acceleration sensor, a separate component for detecting the posture can be omitted.

[0012] The diagnostic means may further include a body temperature index calculation unit that extracts the highest value of the body surface temperature of the livestock within a most recent first specified time period, and calculates the difference between the highest value and the average value of the highest values ​​of the body surface temperature of the livestock within the same time period as the most recent first specified time period for each day within a specified number of days prior to the day to which the most recent first specified time period belongs when the highest value was extracted; a posture index calculation unit that calculates the total value of the time the livestock is upright or lying down within a second specified time period; an activity index calculation unit that calculates the total value of the activity level of the livestock within a third specified time period; and a health condition determination unit that determines whether the health condition of the livestock falls into any of a plurality of preset status types based on the way in which the calculated values ​​fluctuate.

[0013] Alternatively, the diagnosis means may include a body temperature index calculation unit that extracts the maximum value of the body surface temperature of the livestock within a most recent first specified time period, and calculates a difference between the maximum value and an average value of the maximum values ​​of the body surface temperature of the livestock within the same time period as the most recent first specified time period for each day within a specified number of days prior to the day to which the most recent first specified time period belongs, and a body temperature index calculation unit that calculates a total value of the time the livestock is in an upright position or a lying position within a most recent fourth specified time period, and a fourth specified time period prior to the fourth specified time period and further in the past. the total amount of activity of the livestock within a fifth specified time period that is further back than the fifth specified time period; and a health condition determination unit that determines whether the health condition of the livestock falls within any of a plurality of preset statuses based on how the calculated values ​​fluctuate.

[0014] It should be noted that the above-mentioned first, second, third, fourth, and fifth predetermined times may all or partly be the same time. Also, the "multiple types of status" referred to here may include classifications such as normal, estrus, parturition, febrile disease, milk fever, and hoof fever. By determining the health condition of livestock through such processing, anyone can easily understand the health condition of livestock.

[0015] The activity amount information includes a number of posture changes of the livestock, and the diagnosis means further includes a posture change number calculation unit that calculates the number of posture changes of the livestock based on the roll angle information, and the health condition determination unit determines whether the health condition of the livestock is in one of a plurality of preset statuses by using information on how the number of posture changes of the livestock changes. The method may be one that determines whether the above applies.

[0016] Information on the roll angle of a livestock's tail can be used to calculate the number of times the livestock changes position (for example, from standing to lying down), so by using this information in combination, the health of livestock can be determined more accurately.

[0017] The health condition determination unit may be a trained model trained by a machine learning technique.

[0018] In addition, the detection means and the diagnosis means may be separate devices each equipped with a wireless communication means, and the detection means may transmit information including at least the output values ​​of the temperature sensor and the acceleration sensor to the diagnosis means via the wireless communication means.

[0019] With such a configuration, the detection means can be simplified, the burden on livestock can be further reduced, and the cost of each wearable device can be reduced.

[0020] The diagnostic means may further include an output means for outputting the diagnostic result of the health condition of the livestock. The output means may include a wireless communication means for transmitting the diagnostic result of the health condition of the livestock to another device by wireless communication.

[0021] With this configuration, it is possible to transmit the results of health diagnosis to a portable information terminal, for example, and it is possible to grasp the health conditions of livestock in real time without being restricted by location.

[0022] In addition, a livestock health information management method according to the present invention includes the steps of: A detection step of acquiring body surface temperature information of the livestock to be managed, posture information of the livestock, and activity amount information of the livestock; and a diagnosis step of diagnosing the health condition of the livestock based on body surface temperature information, posture information, and activity amount information of the livestock.

[0023] In addition, the posture information of the livestock may include tail roll angle information of the livestock, and the diagnosis step may further include a step of determining whether the livestock is in an upright position or a lying position based on the tail roll angle information of the livestock.

[0024] The diagnosis step includes a body temperature index calculation step, a posture index calculation step, an activity index calculation step, and a health condition determination step. In the body temperature index calculation step, the maximum value of the body surface temperature of the livestock within a most recent first specified time period is extracted, and the difference between the maximum value and the average value of the maximum body surface temperature of the livestock within the same time period as the most recent first specified time period for each day within a specified number of days prior to the day to which the most recent first specified time period belongs, and the average value of the maximum body surface temperature within the same time period for each day within the specified number of days prior to the day to which the most recent first specified time period belongs. In the posture index calculation step, a total value of the time that the livestock is upright or lying down within a second predetermined time period is calculated, and in the activity index calculation step, a total value of the activity of the livestock within a third predetermined time period is calculated. In the health condition determination step, it may be determined whether the health condition of the livestock falls into any of a plurality of preset statuses based on how the values ​​calculated in each of the body temperature index calculation step, the posture index calculation step, and the activity index calculation step vary.

[0025] Alternatively, the diagnosis step includes a body temperature index calculation step, a posture index calculation step, an activity amount index calculation step, and a health condition determination step, and in the body temperature index calculation step, a maximum value of the body surface temperature of the livestock within a most recent first predetermined time period is extracted, and the maximum a difference value between the maximum body surface temperature of the livestock in the same time period as the time period to which the most recent first specified time belongs for each day within a specified number of days prior to the day to which the most recent first specified time belongs when the maximum value was extracted, and an average of the maximum body surface temperature of the livestock in the same time period for each day within the specified number of days prior to the day to which the most recent first specified time belongs; and a difference value between the maximum body surface temperature of the livestock in the same time period for each day within the specified number of days prior to the day to which the most recent first specified time belongs when the maximum value was extracted, and an average of the maximum body surface temperature of the livestock in the same time period for each day within the specified number of days prior to the day to which the most recent first specified time belongs; and In the activity index calculation step, a ratio of the total activity value of the livestock within a most recent fifth specified time period to the total activity value of a fifth specified time period that is even earlier than the fifth specified time period, and in the health condition determination step, a ratio of the total activity value of the livestock within a most recent fifth specified time period to the total activity value of a fifth specified time period that is earlier than the fifth specified time period, may be calculated, and in the health condition determination step, a determination is made as to whether the health condition of the livestock falls within any of a plurality of preset status types based on how the values ​​calculated in each of the body temperature index calculation step, the posture index calculation step, and the activity index calculation step fluctuate.

[0026] In addition, the activity information may include the number of posture changes of the livestock, and the diagnosis step may further include a posture change number calculation step of calculating the number of posture changes of the livestock based on the roll angle information, and the health condition determination step may also use information on how the number of posture changes of the livestock fluctuates to determine whether the health condition of the livestock falls into any of a plurality of preset status types.

[0027] Furthermore, the present invention can also be understood as a program for causing an information processing device to execute each of the above methods, or a computer-readable recording medium on which such a program is non-transiently recorded.

[0028] In addition, the method for creating a trained model according to the present invention includes the steps of: A method for creating a trained model for determining the health condition of livestock to be managed, comprising: A step of inputting body surface temperature information of the livestock, posture information of the livestock, and activity amount information of the livestock over a predetermined period of time; and outputting a status indicating the health condition of the livestock based on a combination of the input information.

[0029] The method for creating the trained model includes the steps of: The body surface temperature information of the livestock, the posture information of the livestock, and the activity amount information of the livestock over the predetermined period are set as training data; Using a learning data set, status information indicating the health condition of the livestock that is preset in response to a combination of the way in which the body surface temperature information of the livestock, the posture information of the livestock, and the activity amount information of the livestock fluctuate within the predetermined period is used as correct answer data. It may also be a method of having a model to be trained learn.

[0030] In addition, the trained model according to the present invention is A trained model for determining the health status of livestock to be managed, For a predetermined period of time, input of the body surface temperature information of the livestock, the posture information of the livestock, and the activity amount information of the livestock, The present invention is characterized in that a status indicating the health condition of the livestock, which is preset in response to a combination of the way in which the body surface temperature information of the livestock, the posture information of the livestock, and the activity level information of the livestock change during the specified period, is output.

[0031] The present invention can be achieved by combining the above-described configurations and processes as long as no technical contradiction occurs. Effect of the Invention

[0032] According to the present invention, the health conditions of livestock subject to management can be known with high accuracy using a simple system configuration. [Brief description of the drawings]

[0033] [Figure 1] FIG. 1 is a diagram showing an outline of a configuration example of a livestock health management system according to the first embodiment. [Diagram 2]FIG. 2 is a functional block diagram showing an outline of the functional configuration of the livestock health management system according to the first embodiment. [Diagram 3] FIG. 3 is a diagram showing the positional relationship between the acceleration detection axes of the acceleration sensor according to the first embodiment and the cow's tail. [Figure 4] FIG. 4 is a table showing an example of the relationship between the type of health condition of a cow determined by the health condition determination unit of embodiment 1 and the change in the cow's body surface temperature, the change in lying (supine) time, and the change in activity level. [Diagram 5] FIG. 5 is an explanatory diagram in which the experimental data of Experimental Example 1 is graphed. [Figure 6] FIG. 6 is an explanatory diagram in which the experimental data of Experimental Example 2 is graphed. [Figure 7] FIG. 7 is a flowchart showing the overall flow of health condition management processing in the livestock health management system according to the first embodiment. [Figure 8] FIG. 8 is a flowchart showing a subroutine of the health condition diagnosis process according to the first embodiment. [Figure 9] FIG. 9 is a block diagram showing the functional configuration of a livestock health management system according to a modified example of the first embodiment. [Figure 10] FIG. 10 is a flowchart showing a subroutine of the health condition diagnosis process according to the modified example of the first embodiment. [Figure 11] FIG. 11 is an explanatory diagram in which the experimental data of Experimental Example 3 is graphed. [Figure 12] FIG. 12 is an explanatory diagram in which the experimental data of Experimental Example 4 is graphed. [Figure 13] FIG. 13 is an explanatory diagram in which the experimental data of Experimental Example 5 is graphed. [Figure 14] FIG. 14 is a diagram showing an outline of a configuration example of a livestock health management system according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0034] Hereinafter, specific embodiments of the present invention will be described with reference to the drawings.

[0035] <Embodiment 1> First, a first embodiment of the present invention will be described with reference to Figures 1 to 8. However, unless otherwise specified, the dimensions, materials, shapes, relative positions, and the like of the components described in this embodiment are not intended to limit the scope of the present invention to those alone.

[0036] (System Configuration) FIG. 1 is a diagram showing an overview of a livestock health management system 1 according to this embodiment, and FIG. 2 is a block diagram showing the functional configuration of the livestock health management system 1. As shown in FIG. 1, the livestock health management system 1 has a wearable device 110 attached to the livestock, and an information processing terminal 220 that communicates information with the wearable device 110 via wireless communication. Any known technology can be used for the wireless communication, and for example, Wi-Fi (registered trademark), Bluetooth (registered trademark), ZigBee (registered trademark), etc. can be adopted. In addition, communication is performed via a public wireless communication network such as LTE (Long Term Evolution). It is also possible.

[0037] (Wearable Devices) In this embodiment, the wearable device 110 is attached to the cow near the base of the tail. For this reason, the wearable device 110 is attached to a sensor module (not shown). The device has a belt section. The sensor module is disposed integrally with the belt section or detachably attached, and the belt section is wrapped around the base of the cow's tail to secure the wearable device 110. The wearable device 110 also has a battery that supplies power to the sensors, control section, etc. The battery may be a rechargeable secondary battery.

[0038] 2, wearable device 110 includes functional units, such as a temperature sensor 111, an acceleration sensor 112, a storage unit 113, a communication unit 114, and a control unit 115. In this embodiment, wearable device 110 corresponds to a detection unit.

[0039] Temperature sensor 111 measures the body surface temperature of the managed cow every specified time (for example, every two minutes) and outputs the temperature. Acceleration sensor 112 is a so-called three-dimensional acceleration sensor that can measure acceleration in the three axial directions of the X-axis, Y-axis, and Z-axis, and outputs acceleration in the three axial directions of the cow's tail. Figure 3 shows the relationship between the directions of the three axes and the cow's tail in this embodiment. As shown in Figure 3, this embodiment will be described assuming that the Y-axis is taken as an extension of the base of the cow's tail and the tail.

[0040] The storage unit 113 is a memory device such as a RAM (Random Access Memory) or a ROM (Read only memory), and stores programs executed by the control unit 115 described later, timing information for measurements by each sensor, measurement values ​​by each sensor, etc.

[0041] The communication unit 114 includes a communication antenna and a wireless communication processing means (neither shown) for communicating information with the information processing terminal 120 by a wireless communication method. The wireless communication processing unit of the communication unit 114 converts data transmitted from the control unit 115 described later into a wireless communication signal, and transmits the signal from the antenna. As a result, the wearable device 110 transmits, via the communication unit 114, to the information processing terminal 120, body surface temperature information (e.g., body surface temperature every two minutes), posture information (e.g., posture index described later), and activity amount information (e.g., activity amount index described later) of the cow acquired by each sensor.

[0042] The control unit 115 includes a CPU (Central Processing Unit) and is The function module 1153 controls each functional module of the mobile device 110. The function module 1153 also includes a posture index calculation module 1151 and an activity index calculation module 1152.

[0043] The posture index calculation unit 1151 calculates the average value of the roll angle of the cow's tail for each predetermined time (for example, 2 minutes) as the posture index based on the output value obtained from the acceleration sensor 112. For example, this may be obtained from the average value of the X-axis and Z-axis acceleration of the cow's tail measured by the acceleration sensor 112 for each predetermined time. The posture index is included in the posture information transmitted to the information processing terminal 120.

[0044] The activity index calculation unit 1152 calculates the activity index of the cow based on the output value obtained from the acceleration sensor 112. Specifically, the standard deviation of the minimum value of the activity amount of the cow for a predetermined time (e.g., 2 minutes) is calculated, and this is set as the activity index. Note that this activity index is included in the activity amount information transmitted to the information processing terminal 120.

[0045] (Information processing terminal) The information processing terminal 120 includes a control unit 121, a communication unit 122, a storage unit 123, an input unit 124, and a display unit 125. The information processing terminal 120 can be configured as a computer equipped with a CPU, RAM, ROM, etc., and can employ a general-purpose information processing device such as a personal computer. In this embodiment, the information processing terminal 120 corresponds to the diagnostic means.

[0046] The control unit 121 controls each unit of the information processing terminal 120, and further includes the following functional modules: a body temperature index calculation unit 1211, a posture index calculation unit 1212, an activity amount index calculation unit 1213, and a health condition determination unit 1214. Each functional module will be described later.

[0047] The communication unit 122 includes a communication antenna and a wireless communication processing unit (neither of which is shown) for communicating information with the communication unit 114 of the wearable device 110 by wireless communication. As a result, the information processing terminal 120 acquires information from the wearable device 110 via the communication unit 122.

[0048] The memory unit 123 is composed of a large-capacity storage device such as a RAM, a ROM, an HDD (Hard Disk Drive) or an SSD (Solid State Drive), and stores various information such as the program executed by the control unit 121, information obtained from the wearable device 110, and historical information on the health condition of the cow.

[0049] The input unit 124 is an input means for accepting user operations on the information processing terminal 120, and may be any known input means such as a keyboard, a mouse, or a touch panel display (none of which are shown).

[0050] The display unit 125 is an output device that displays various information, including the health condition of the managed cows diagnosed by the control unit 121, and may be, for example, a liquid crystal display monitor.

[0051] (Health status determination function module) Next, the functional modules of the control unit 121 will be described. The body temperature index calculation unit 1211 calculates a body temperature index, and calculates a body temperature index based on the body temperature index. More specifically, the maximum value of the body surface temperature of the cow in the most recent hour is calculated (extracted) as a body temperature index from the body surface temperature information stored in the memory unit 123, and the difference value between the extracted body temperature index and the average value of the maximum value of the body surface temperature of the cow in the same time period as the time period of each day in the three days before the day to which the body temperature index is extracted belongs is calculated as the body temperature index. Specifically, for example, if the current time is 14:00, the maximum value of the body surface temperature in the one hour period from 13:00 to 14:00 is extracted, and the maximum value is stored in the memory unit 123. Then, the average value of the maximum value of the body surface temperature between 13:00 and 14:00 for the past three days is obtained from the memory unit 123, and the difference between the average value and the maximum value of the body surface temperature between 13:00 and 14:00 on the current day extracted earlier is calculated.

[0052] The posture index calculation unit 1212 calculates the total time that the cow is in a lying position within a predetermined time (for example, the past 24 hours) as the posture index based on the posture index of the cow stored in the memory unit 123. Specifically, for example, if the posture index of the cow's tail (for example, the average value of the roll angle over 2 minutes) is less than -0.4 or exceeds +0.4, the cow's posture is determined to be lying, and if it is -0.4 or more and +0.4 or less, the cow's posture is determined to be standing. Then, the total time that the cow is in a lying position within a predetermined time (for example, the past 24 hours) is calculated and this is set as the posture index. That is, in this embodiment, the posture index calculation unit is configured to also function as the posture state determination means. The posture index may be the total time that the cow is in a standing position within a predetermined time instead of the lying position time.

[0053] Furthermore, the activity amount index calculation unit 1213 calculates the total value of the activity amount index of the cow within a predetermined time period (for example, the past 24 hours) based on the activity amount information of the cow stored in the memory unit 123 as the activity amount index.

[0054] The health condition determination unit 1214 determines whether the health condition of the cow falls into one of a plurality of preset statuses based on the way in which the calculated body temperature index, posture index, and activity index change. It is determined whether this is the case. Specifically, for example, if the body temperature index decreases, the posture index increases, and the activity index decreases, it is determined that parturition is approaching. The result of this determination is then output as the diagnosis result of the cow's health condition. The health condition determination unit 1214 can employ artificial intelligence (learning model) that has been trained by machine learning such as deep learning.

[0055] Fig. 4 is a table showing an example of the relationship between the type of cow's health condition determined by the health condition determination unit 1214 of this embodiment and the change in the cow's body surface temperature (body temperature index), the change in the lying time (posture index), and the change in the activity index. As shown in Fig. 4, in this embodiment, the cow is determined to be in "normal", "estrus", "parturition", "feverish disease", "milk fever", or "hoof fever" depending on how each index increases or decreases.

[0056] Here, when the health condition assessment unit 1214 is an artificial intelligence, a trained model can be used that has been trained using a learning dataset in which each of the above indicators over a predetermined period (e.g., the past three days) is used as training data, and each of the above health conditions that are preset in response to a combination of how each indicator fluctuates over the predetermined period is used as correct answer data.

[0057] In addition, when livestock are kept under conditions where their behavior is restricted, such as tethering, their activity level will not increase significantly even if they are in heat, but even in such a case, it is considered that the time spent in an upright position will be extended. Therefore, by combining the posture information with the activity level, it is possible to detect changes in health status that may be overlooked only by changes in activity level. In addition, by making a judgment based on such a combination, it is possible to set strict thresholds for determining the health status for each of the posture information and the activity level information, so that changes in health status can be detected with high accuracy. In addition, at the time of parturition, the three indices of body temperature index, posture index, and activity level index can be used depending on the breeding style of the livestock at the time of parturition (whether to complete parturition while tied or to be moved to a parturition box) and the size of the box if it is moved to the parturition box, thereby making it possible to flexibly respond to various types of breeding.

[0058] The following is experimental data obtained by attaching the wearable device 110 to the tail of a cow.

[0059] (Experimental Example 1) Figure 5 is a graph showing the body temperature index, posture index, and activity index of a cow before and after estrus in chronological order. Figure 5 shows that the cow is in estrus when the following conditions are met: the body temperature index suddenly increases, the posture index decreases, and the activity index increases.

[0060] (Experimental Example 2) Figure 6 is a graph showing the body temperature index, posture index, and activity index of a cow before and after calving in chronological order. From Figure 6, we can see that a cow calves when the following conditions are met: the body temperature index rises, then drops sharply, then rises slightly, the posture index drops sharply, and the activity index rises.

[0061] From the above experimental examples, it can be seen that there is a clear correlation between the amount of fluctuation (the manner of fluctuation) between each index in important events in health management such as estrus and parturition.

[0062] (Processing flow) Next, the flow of processing for managing the health conditions of cows by the livestock health management system 1 in this embodiment will be described with reference to Figures 7 and 8. Figure 7 is a flowchart showing the flow of the overall health management processing by the livestock health management system 1. As shown in Figure 7, first, the temperature sensor 111 of the wearable device 110 measures the body temperature of the managed cow at predetermined time intervals. The surface temperature is detected (step S101). The acceleration sensor 112 detects the acceleration of the X-axis, Y-axis, and Z-axis of the tail of the cow (step S102). Furthermore, based on the values ​​detected in step S102, the posture index calculation unit 1151 calculates the average value of the roll angle of the tail of the cow for each predetermined time period (step S103), and the activity index calculation unit 1152 calculates the activity index of the cow (step S104). The body surface temperature information, posture information, and activity information thus obtained are then transmitted to the information processing terminal 120 via the communication unit 130 (step S105), and the control unit 121 of the information processing terminal 120 performs a health condition diagnosis process for the cow (step S106). The routine ends once at the above, but the routine is repeatedly executed as needed. This makes it possible to grasp and manage the health condition of the cow in real time.

[0063] In this embodiment, the processes from step S101 to step S104 correspond to the detection step. Note that the processes from step S101 to step S104 do not necessarily have to be executed in this order, and the order of the processes from step S101 to step S102 to step S104 may be interchanged. Also, the order of the processes from step S103 to step S104 may be reversed.

[0064] Next, the subroutine of the health condition diagnosis process of step S106 will be described. FIG. 8 is a flow chart showing the flow of the health condition diagnosis process of the cow executed by the information processing terminal 120. As shown in FIG. 8, first, the body temperature index calculation unit 1211 extracts the maximum value of the body surface temperature within a predetermined time based on the body surface temperature information stored in the memory unit 123 (step S111), and calculates a body temperature index based on this (step S112). Next, the posture index calculation unit 1212 judges whether the cow is standing or lying down every predetermined time (step S113), and calculates a posture index based on this (step S114). Furthermore, the activity amount index calculation unit 1213 calculates an activity amount index (step S115). Next, the health condition judgment unit 1214 executes a health condition judgment process (step S116), and the judgment result is output to the display unit 125 (step S117), and the routine is temporarily terminated. It should be noted that the body temperature index, posture index, activity index, and health condition determination process have already been explained, and therefore detailed explanations thereof will be omitted here.

[0065] In this embodiment, the processes from step S111 to step S116 correspond to the diagnosis step. Steps S111 and S112 correspond to the body temperature index calculation step, steps S113 and S114 correspond to the posture index calculation step, step S115 corresponds to the activity index calculation step, and step S116 corresponds to the health condition determination step. Note that the order of the body temperature index calculation step, posture index calculation step, and activity index calculation step may be interchanged.

[0066] According to the livestock health management system 1 configured as above, if a livestock is fitted with a wearable device 110 having a simple configuration, the health condition of the livestock to which the module is attached can be known even if the livestock is located away from the livestock. In addition, because the health condition of the livestock is automatically diagnosed, even those with little biological or medical knowledge about livestock can manage the health of the livestock.

[0067] <Variation 1> In the above embodiment, the activity index is the sum of the activity indices of the cows within a specified time period, and the posture index is the sum of the time the livestock spends lying down within a specified time period, but the indices are not necessarily limited to this.

[0068] For example, the activity index is calculated by dividing the total activity index value of livestock within a specified time period in the past (e.g., 24 hours) by the total activity index value within the same specified time period in the past (e.g., 4 hours from 24 hours before the specified time). Alternatively, the activity index may be calculated as a ratio (activity ratio) of the total activity index value for the previous 8 hours (the previous 8 hours).

[0069] Also, the amount of activity may be determined as the number of tail movements, and the activity index may be determined based on the degree of tail lift. Specifically, the activity index may be determined as the ratio (Y-axis ratio) between the average acceleration on the Y-axis within a predetermined time in the past (e.g., 6 hours) and the average acceleration on the Y-axis within the same predetermined time from the predetermined time to the past (e.g., between 6 hours and 12 hours). Note that the activity ratio and the Y-axis ratio may not be used as an activity index either one of them, but may be used in combination.

[0070] The posture index may also be the ratio (standing time ratio) of the total standing time of the livestock in a given time period in the past (e.g., 24 hours) to the total standing time in the same given time period from the given time period to the past (e.g., from 24 hours to 48 hours). It is of course possible to use the lying time instead of the standing time.

[0071] <Variation 2> Furthermore, the information used by the health condition determination unit 1214 to determine the health condition of the livestock is not limited to the body temperature index, posture index, and activity index, and other information can also be used to determine the health condition. Such a modified livestock health management system 11 will be described below with reference to Figures 9 and 10. Figure 9 is a block diagram showing the functional configuration of the livestock health management system 11 according to this modified example, and Figure 10 is a flowchart showing a subroutine for health condition diagnosis processing according to this modified example.

[0072] 9, a livestock health management system 11 according to this modification is configured such that an information processing terminal 1200 includes a posture change count calculation unit 1215. Since other points are similar to the health management system 1 of embodiment 1, the same configurations and processes as those of the health management system 1 of embodiment 1 are denoted by the same reference numerals and descriptions thereof will be omitted.

[0073] The posture change count calculation unit 1215 is a functional unit that counts the number of posture changes (e.g., changes between standing and lying) of the livestock based on the roll angle information of the livestock's tail obtained from the acceleration sensor 112, and calculates the ratio (posture change count ratio) of the number of posture changes of the livestock within a specified time in the past (e.g., 24 hours) to the number of posture changes within the same specified time even earlier than the specified time (e.g., between 24 hours and 48 hours ago).

[0074] 10, in the subroutine for health condition determination processing according to this modification, after the body temperature index, posture index, and activity amount index are calculated in the processing of steps S111 to S115, the posture change count ratio is calculated (S121). Then, the health condition determination unit 1214 performs the health condition determination processing using the body temperature index, posture index, activity amount index, and the posture change count ratio (S116), and the diagnosis result is output (S117).

[0075] The following is experimental data obtained by attaching wearable devices 110 to the tails of multiple livestock.

[0076] (Experimental Example 3) Figure 11 is a graph showing a time series of the body temperature index, activity ratio (activity index), standing time ratio (posture index), and lying down count ratio (i.e., posture change count ratio) of cows before and after estrus, with a sample size of 25. Figure 11 shows that cows are in estrus when the following conditions are met: the body temperature index, activity ratio, and standing time ratio suddenly increase, and the lying down count ratio decreases and then suddenly increases again.

[0077] (Experimental Example 4) Figure 12 shows the body temperature index, activity ratio, and standing time of cows before and after parturition for 30 samples. 12 is a graph showing the time series of the standing time ratio, lying time ratio, and Y-axis ratio (activity index). From Fig. 12, we can see that cows give birth when the following conditions are met: the body temperature index drops, the activity ratio and standing time ratio rise sharply, and the Y-axis ratio drops sharply.

[0078] (Experimental Example 5) Figure 13 is a graph showing the time series of body temperature index, activity ratio, lying time ratio (posture index), and posture change count ratio before and after pig parturition, with the number of samples being 9. Figure 13 shows that pigs parturition occurs when the following conditions are met: the body temperature index gradually declines and then rises, the activity ratio and posture change count ratio rise sharply, and the lying time ratio decreases.

[0079] As in the above experimental examples, even when activity ratio, standing (or lying) time ratio, number of posture change ratio, and Y-axis ratio are used, it is clear that there is a clear correlation between the way these change and important events in health management such as estrus and parturition.

[0080] <Embodiment 2> Next, another embodiment of the present invention will be described with reference to Fig. 12. Fig. 12 is a schematic diagram showing an example of the configuration of a livestock health condition management system 2 according to this embodiment. As shown in Fig. 12, the livestock health condition management system 2 is configured to include wearable devices 210a, 210b, 210c, 210d, ... attached to multiple cows, an information processing terminal 220, and a mobile information terminal 230, which are connected to each other by a network N. The network N may be, for example, a WAN (Wide Area Network), which is a global public communication network such as the Internet, or other public communication networks such as LTE. In addition, the network N may include a wireless communication network such as Wi-Fi, and may include a signal relay device as necessary.

[0081] The mobile information terminal 230 may be any device based on a desired known technology, and may be, for example, a notebook PC, a tablet terminal, a smartphone, etc. The configurations of the wearable devices 210a, 210b, 210c, 210d, etc. and the information processing terminal 220 are similar to those in the first embodiment, and therefore detailed description thereof will be omitted. Note that the communication units of the wearable device 210 and the information processing terminal 220 connect to the network N to perform information communication.

[0082] In the livestock health condition management system 2 in this embodiment, each of the multiple wearable devices transmits body surface temperature information, posture information, and activity amount information together with an identification signal capable of identifying each wearable device to the information processing terminal 220 via the network N. The information processing terminal 220 then executes a health condition diagnosis process for each wearable device 210 identified by the identification information.

[0083] The information processing terminal 220 transmits the diagnosis result to the mobile information terminal 230 based on a predetermined rule. For example, it can be set so that only when there is a cow whose health condition has been diagnosed as being other than "normal", the diagnosis result is transmitted together with the identification information (i.e., in a manner that allows the cow to be identified). Alternatively, it can be set so that the health information of desired cows is transmitted periodically, or any information (for example, a list of the health conditions of the managed cows) can be transmitted in response to a user operation.

[0084] According to the livestock health condition management system 2 configured as above, the user can obtain information on the health condition of cattle in real time from anywhere using the mobile information terminal 230. In addition, since a large number of cattle can be managed automatically at once, it is possible to significantly reduce personnel costs. In addition, since the configuration of each wearable device 210 is simple, the cost of the equipment can be reduced.

[0085] <Other> The above description of each example is merely illustrative of the present invention, and the present invention is not limited to the specific embodiments described above. Various modifications and combinations of the present invention are possible within the scope of the technical concept thereof.

[0086] For example, in the second embodiment, a configuration may be used that includes a plurality of portable information terminals, or conversely, a configuration may be used in which a network and a portable information terminal are not included in the configuration, and a plurality of wearable devices directly communicate with an information processing terminal. Also, the information processing terminal may be a cloud server or the like, and may be centrally managed by a business operator.

[0087] Moreover, the calculation of each index and each parameter and each judgment process may be performed by either the wearable device or the information processing terminal. For example, in each of the above embodiments, the calculation of the body temperature index is performed by the information processing terminal, but this may be calculated by the wearable device. Also, as for information regarding posture, the judgment process of whether the cow is standing or lying down based on the posture index may be performed by the wearable device, and the judgment result may be sent to the information processing terminal. Alternatively, the posture index and the activity index may also be calculated by the information processing terminal. Furthermore, it is also possible to complete all the health condition diagnosis processes performed by the information processing terminal by the wearable device, and to transmit only the diagnosis results to an external device.

[0088] In the above embodiment, the posture index is calculated by determining the roll angle of the cow's tail from the X-axis and Z-axis acceleration of a three-dimensional acceleration sensor, but it may be calculated by other methods. For example, a one-axis or two-axis acceleration sensor may be used to determine the cow's posture state from the frequency of tail movement.

[0089] In the above embodiment, cows are treated as livestock to be managed, but the livestock to be managed is not limited to cows, and the present invention can be applied to other animals such as horses, sheep, goats, pigs, etc. Furthermore, the classification of health conditions is not limited to those given in the above example.

[0090] In the above embodiment, the health condition determination unit is exemplified as an artificial intelligence that performs machine learning, but the invention is not limited to this and may be a so-called expert system. Also, the invention is not limited to artificial intelligence and may be one that performs determination processing using a threshold value according to a predetermined program. [Explanation of symbols]

[0091] 1, 2 Livestock Health Management System 110, 210: Wearable devices 120, 220, 1200... Information processing terminal 115, 121... Control unit 230 Mobile information terminal

Claims

1. a detection means including a temperature sensor and a three-dimensional acceleration sensor, attached to the tail of a livestock to be managed, which is any one of a cow, a pig, a horse, a sheep, and a goat, for acquiring body surface temperature information, posture information, and activity amount information of the livestock; A diagnostic means for diagnosing the health condition of the livestock based on the body surface temperature information of the livestock, the posture information of the livestock, and the activity amount information of the livestock; It has the detection means includes a posture index calculation means for calculating roll angle information of the tail of the livestock from an output of the three-dimensional acceleration sensor, The diagnostic means comprises: a body temperature index calculation unit that extracts the maximum body surface temperature of the livestock within a most recent first specified time period, and calculates a body temperature index that is the difference between the maximum body temperature and the average maximum body surface temperature of the livestock within the same time period as the most recent first specified time period for each day within a specified number of days prior to the day to which the most recent first specified time period belongs; a posture state determination unit that determines whether the livestock is in at least an upright position or a lying position based on the roll angle information; a posture index calculation unit that calculates a first posture index, which is a total value of a time during which the livestock is in an upright position or a time during which the livestock is in a lying position within a second predetermined time; An activity amount index calculation unit that calculates a first activity amount index that is a total value of the activity amount of the livestock within a third predetermined time period; and a health condition determination unit that determines whether the health condition of the livestock corresponds to any one of a plurality of preset statuses based on how the body temperature index, the first posture index, and the first activity amount index change. Livestock health management system.

2. a detection means including a temperature sensor and a three-dimensional acceleration sensor, attached to the tail of a livestock to be managed, which is any one of a cow, a pig, a horse, a sheep, and a goat, for acquiring body surface temperature information, posture information, and activity amount information of the livestock; A diagnostic means for diagnosing the health condition of the livestock based on the body surface temperature information of the livestock, the posture information of the livestock, and the activity amount information of the livestock; It has the detection means includes a posture index calculation means for calculating roll angle information of the tail of the livestock from an output of the three-dimensional acceleration sensor, The diagnostic means comprises: a body temperature index calculation unit that extracts the maximum body surface temperature of the livestock within a most recent first specified time period, and calculates a body temperature index that is the difference between the maximum body temperature and the average maximum body surface temperature of the livestock within the same time period as the most recent first specified time period for each day within a specified number of days prior to the day to which the most recent first specified time period belongs; a posture state determination unit that determines whether the livestock is in at least an upright position or a lying position based on the roll angle information; a posture index calculation unit that calculates a second posture index, which is a ratio between a total value of a time during which the livestock is in an upright position or a lying position within a most recent fourth predetermined time period and a total value of a time during which the livestock is in the same posture as a posture alternatively selected from the upright position or the lying position within a fourth predetermined time period from before the fourth predetermined time period; an activity amount index calculation unit that calculates a second activity amount index that is a ratio between a total value of an activity amount of the livestock within a most recent fifth predetermined time period and a total value of an activity amount of the livestock within a fifth predetermined time period that is further in the past from before the fifth predetermined time period; and a health condition determination unit that determines whether the health condition of the livestock corresponds to any one of a plurality of preset statuses based on how the body temperature index, the second posture index, and the second activity amount index change. Livestock health management system.

3. The activity amount information includes a number of posture changes of the livestock, The diagnosis means further includes a posture change frequency calculation unit that calculates a number of posture changes of the livestock based on the roll angle information, The health condition determination unit determines whether the health condition of the livestock corresponds to any one of a plurality of preset statuses by using information on how the number of posture changes of the livestock fluctuates.

3. A livestock health condition management system according to claim 1 or 2.

4. The health condition determination unit is a trained model trained by a machine learning technique. A livestock health condition management system according to any one of claims 1 to 3.

5. the detection means and the diagnosis means are separate devices each equipped with a wireless communication means; the detection means transmits information including at least the output values ​​of the temperature sensor and the acceleration sensor to the diagnosis means via the wireless communication means; A livestock health condition management system according to any one of claims 1 to 4.

6. The diagnostic means further includes an output unit that outputs a diagnosis result of the health condition of the livestock. A livestock health condition management system according to any one of claims 1 to 5.

7. The output unit includes a wireless communication means for wirelessly transmitting the diagnosis result of the health condition of the livestock to another device. The livestock health condition management system according to claim 6.

8. the wireless communication means transmits a diagnosis result to the other device together with information identifying the livestock only when the livestock is diagnosed as being in an abnormal health state; The livestock health condition management system according to claim 7.

9. In the information processing device, A detection step of acquiring body surface temperature information of a livestock to be managed, which is any one of cows, pigs, horses, sheep, and goats, posture information of the livestock including roll angle information of the tail of the livestock calculated from an output of a three-dimensional acceleration sensor attached to the tail of the livestock, and activity amount information of the livestock; A diagnosis step of diagnosing the health condition of the livestock based on the body surface temperature information of the livestock, the posture information of the livestock, and the activity amount information of the livestock; It has The diagnosis step includes: The method includes a body temperature index calculation step, a posture state determination step, a posture index calculation step, an activity amount index calculation step, and a health state determination step, In the body temperature index calculation step, the maximum value of the body surface temperature of the livestock within a most recent first specified time period is extracted, and a difference value between the maximum value and an average value of the maximum body surface temperature of the livestock within the same time period as the most recent first specified time period for each day within a specified number of days prior to the day to which the most recent first specified time period belongs, and an average value of the maximum body surface temperature within the same time period for each day within the specified number of days prior to the day to which the most recent first specified time period belongs, is calculated; In the posture state determination step, it is determined whether the livestock is at least in an upright position or a lying position based on roll angle information of the tail of the livestock; In the posture index calculation step, a total value of a time during which the livestock is in an upright position or a time during which the livestock is in a lying position within a second predetermined time is calculated, In the activity amount index calculation step, a total value of the activity amount of the livestock within a third predetermined time period is calculated, In the health condition determination step, it is determined whether the health condition of the livestock corresponds to any one of a plurality of preset statuses based on the manner in which the values ​​calculated in each step of the body temperature index calculation step, the posture index calculation step, and the activity amount index calculation step vary. A method for managing the health condition of livestock using an information processing device.

10. In the information processing device, A detection step of acquiring body surface temperature information of a livestock to be managed, which is any one of cows, pigs, horses, sheep, and goats, posture information of the livestock including roll angle information of the tail of the livestock calculated from an output of a three-dimensional acceleration sensor attached to the tail of the livestock, and activity amount information of the livestock; A diagnosis step of diagnosing the health condition of the livestock based on the body surface temperature information of the livestock, the posture information of the livestock, and the activity amount information of the livestock; It has The diagnosis step includes: The method includes a body temperature index calculation step, a posture state determination step, a posture index calculation step, an activity amount index calculation step, and a health state determination step, In the body temperature index calculation step, the maximum value of the body surface temperature of the livestock within a most recent first specified time period is extracted, and a difference value between the maximum value and an average value of the maximum body surface temperature of the livestock within the same time period as the most recent first specified time period for each day within a specified number of days prior to the day to which the most recent first specified time period belongs, and an average value of the maximum body surface temperature within the same time period for each day within the specified number of days prior to the day to which the most recent first specified time period belongs, is calculated; In the posture state determination step, it is determined whether the livestock is at least in an upright position or a lying position based on roll angle information of the tail of the livestock; In the posture index calculation step, a ratio is calculated between a total value of a time during which the livestock is in an upright position or a lying position within a most recent fourth predetermined time period and a total value of a time during which the livestock is in the same posture as a posture alternatively selected from the upright position or the lying position within a fourth predetermined time period from before the most recent fourth predetermined time period and further in the past, In the activity amount index calculation step, a ratio is calculated between a total value of the activity amount of the livestock within a most recent fifth predetermined time period and a total value of the activity amount within a fifth predetermined time period from before the most recent fifth predetermined time period to a more recent fifth predetermined time period; In the health condition determination step, it is determined whether the health condition of the livestock corresponds to any one of a plurality of preset statuses based on the manner in which the values ​​calculated in each step of the body temperature index calculation step, the posture index calculation step, and the activity amount index calculation step vary. A method for managing the health condition of livestock using an information processing device.

11. The activity amount information includes a number of posture changes of the livestock, The diagnosis step further includes a posture change number calculation step of calculating a number of posture changes of the livestock based on roll angle information of the tail of the livestock, In the health condition determination step, whether the health condition of the livestock corresponds to any one of a plurality of preset statuses is determined using information on how the number of posture changes of the livestock changes. A method for managing the health condition of livestock by the information processing device according to claim 9 or 10.

12. A program for causing an information processing device to execute each of the steps in the method for managing the health condition of livestock by an information processing device according to any one of claims 9 to 11.

Images