Animal weight measurement system and method

Abstract

To provide a weight measurement system capable of measuring a plurality of types of weight. [Solution] The present disclosure relates to a weight measurement system for animals, characterized by comprising a weight data acquisition unit that acquires weight data from a weight measurement means, a weight calculation unit that calculates the weight of a measurement object related to the animal's behavior from the acquired weight data, and a behavior data generation unit that generates time-series behavior data of the animal based on behavior measurement data related to the animal.

Description

Technical Field

[0001] The present disclosure relates to an animal weight measurement system and method.

Background Art

[0002] In recent years, toilets capable of measuring the urine output of pets have been proposed.

[0003] Patent Document 1 discloses a cat toilet usage status management system including a cat toilet for animals and a management server.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The above-described technology can only measure the urine output and does not fully meet the needs of the pet owner.

[0006] Therefore, an object of the present disclosure is to provide a weight measurement system and method capable of changing the measurement target according to the wishes of the pet owner.

Means for Solving the Problems

[0007] According to the present disclosure, there is provided an animal weight measurement system including: a weight data acquisition unit that acquires weight data from a weight measurement means; a weight calculation unit that calculates the weight of a measurement target related to the behavior of the animal from the acquired weight data; and a behavior data generation unit that generates time-series behavior data of the animal based on the behavior measurement data related to the animal.

[0008] Also, according to the present disclosure, there is provided a method for a measurement target related to animal behavior, the method including: obtaining weight data from weight measurement means; calculating the weight of the measurement target related to the animal behavior from the obtained weight data; and generating time-series behavior data of the animal based on the behavior measurement data related to the animal.

Advantages of the Invention

[0009] According to the present disclosure, it is possible to change measurement targets such as food intake and excretion amount according to the wishes of the owner.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Embodiments for Carrying Out the Invention

[0011] The contents of the embodiments of the present disclosure will be listed and described. The present disclosure has the following configuration. (Item 1) A weight measurement system for animals, a weight data acquisition unit that acquires weight data from a weight measurement means, a weight calculation unit that calculates the weight of a measurement target related to the behavior of the animal from the acquired weight data, an action data generation unit that generates time-series action data of the animal based on action measurement data related to the animal, A weight measurement system, characterized by comprising: (Item 2) The weight measurement system according to Item 1, further comprising a weight information evaluation unit that evaluates the reliability of the weight information calculated by the weight calculation unit according to the time-series action data. (Item 3) The weight measurement system according to Item 1 or 2, further comprising a weight type identification unit that further identifies the measurement target of the weight information calculated by the weight calculation unit according to the time-series action data. (Item 4) The weight measurement system according to any one of Items 1 to 3, further comprising an individual identification unit that identifies an individual related to the weight measured by the weight calculation unit. (Item 5) The weight measurement system according to Item 4, wherein the individual identification unit identifies an individual related to the weight measured by the weight calculation unit according to the time-series behavior data. (Item 6) The weight measurement system according to any one of Items 1 to 5, further comprising a display control unit that outputs weight information including the weight of the measurement target to a user terminal. (Item 7) The weight measurement system according to Item 6, wherein the display control unit outputs the weight information together with behavior information based on the behavior data. (Item 8) The weight data acquisition unit acquires weight data from two or more of the weight measurement means, The weight calculation unit calculates the weight of the measurement target from the weight data acquired from each of the weight measurement means, The weight measurement system according to Item 6, wherein the display control unit displays the calculated weight information of each measurement target in a single time series. (Item 9) The weight measurement system according to any one of Items 1 to 8, further comprising an abnormality detection unit that detects an abnormality of the animal based on the calculated weight. (Item 10) A method for a measurement target related to the behavior of an animal, comprising: acquiring weight data from a weight measurement means; calculating the weight of the measurement target related to the behavior of the animal from the acquired weight data; generating time-series behavior data of the animal based on behavior measurement data related to the animal; and.

[0012] <Details of the Embodiment> Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0013] <Summary> The system according to an embodiment of the present disclosure uses weight data obtained from weight measurement means 8 including a weight sensor to manage the health of animals such as pets. The weight measurement means 8 is, for example, a device that measures the weight of an animal. The configuration of the device of the weight measurement means 8 is not particularly limited, and for example, it may include a platform on which an animal is placed and a sensor that measures the force received by the platform. The platform and the sensor do not necessarily have to be integrated. The weight measurement means 8 can be, for example, a weighing scale or the like. The weight measurement means 8 may have a shape that can carry pet items such as toilets, dishes, and water containers according to the application. The shape of the weight measurement means 8 is, for example, board-shaped as shown in FIG. 1. The weight measurement system of the present disclosure calculates the weight of an animal, the amount of excrement (feces and urine), the amount of food (rice and water), etc. from the time-series weight data acquired by the weight measurement means 8, and provides it to the user as weight information. At the same time, the accuracy of the calculated weight information can be improved by using the behavior data identified by analyzing the behavior measurement data related to the behavior of the animal obtained from an acceleration sensor or the like attached to the animal. Since the weight measurement system of the present disclosure can change the measurement target according to the selected measurement mode, the user can freely select the target to be measured without limiting the use of the weight measurement means 8. By routinely measuring these various weights related to animals, it becomes possible to manage the health of animals.

[0014] <Configuration> As shown in FIG. 2, the service providing system includes a server 1 that provides a service, and the weight measurement means 8, the communication terminal 2, and the user terminal 3 that are connected to the server 1 via a network such as the Internet. Further, the server 1 is connected to an analysis server 4 via a network. In FIG. 2, for convenience of explanation, one weight measurement means 8, communication terminal 2, user terminal 3, and analysis server 4 are each shown, but a plurality of terminals can be connected to the network of the present system.

[0015] Server 1 can provide services to user terminal 3 via an application. The user terminal 3 can download the application from Server 1 or another server, execute this application, and access Server 1 through web page browsing software such as a browser, thereby being able to send and receive information with Server 1 and receive services.

[0016] Communication terminal 2 can obtain weight data and behavior measurement data by performing short - range wireless communication with a weight measurement means 8 and an acceleration sensor (an example of sensor 5) attached to an animal, such as a cat 6. More specifically, first, as shown in FIG. 3, a collar - shaped (or pendant - shaped) wearable device is attached to the cat 6. The wearable device incorporates an acceleration sensor and / or a temperature sensor as sensor 5. Note that the device realizing sensor 5 is not limited, and for example, it is not particularly limited as long as it is a sensor that senses the movement and physiological phenomena of other animals. Also, although sensor 5 is assumed to be attached to an animal such as cat 6, such sensor 5 does not have to be attached to an animal, and it may be attached inside the animal's body or the like. The weight measurement means 8 and sensor 5 transmit data through short - range wireless communication such as BLUETOOTH (registered trademark) LOW ENERGY (BLE) to a receiving device 7 installed in the same house. The receiving device 7 transfers the data to a communication terminal 2 such as a router, and the communication terminal 2 transmits the data to Server 1 via a network. Note that the weight measurement means 8 and sensor 5 may directly transmit the data to the user terminal 3 through short - range wireless communication such as BLUETOOTH (registered trademark) LOW ENERGY (BLE). Here, as an example, the receiving device 7 can be equipped with an operating system based on Linux (registered trademark) and various sensors such as a temperature sensor for measuring the air temperature. However, such a device may of course be one that does not have an OS, such as an embedded chipset.

[0017] As shown in FIG. 3, the acceleration sensor 5 is a sensor that detects accelerations in three mutually perpendicular axial directions (x-axis, y-axis, and z-axis directions), and is built into a collar worn on the neck of a cat. As shown in FIG. 3, the front-rear direction of the cat is defined as the X direction, the left-right direction is defined as the Y direction, and the up-down direction is defined as the Z direction. The collar is attached to the cat so that acceleration signals in each direction can be detected according to the movement of the cat. The type of sensor is not limited to this, and any sensing device that can acquire information related to the movement of the cat, such as a gyro sensor or a motion sensor, can be adopted.

[0018] Returning to FIG. 2, the user terminal 3 may be a general-purpose computer such as a workstation or a personal computer, or may be a smartphone, a tablet, a mobile terminal, or other information terminals.

[0019] FIG. 4 is a functional block diagram of the server 1 according to the first embodiment of the present disclosure. Note that the illustrated configuration is an example, and other configurations may be provided.

[0020] As shown, the server 1 is connected to a database (not shown) and constitutes a part of the system. The server 1 may be a general-purpose computer such as a workstation or a personal computer, or may be logically realized by cloud computing.

[0021] The server 1 includes at least a control unit 10, a memory 11, a storage 12, a transmission / reception unit 13, an input / output unit 14, etc., and these are electrically connected to each other through a bus 15.

[0022] The control unit 10 is an arithmetic device that controls the overall operation of the server 1, controls the transmission and reception of data between each element, and performs information processing necessary for the execution and authentication processing of applications. For example, the control unit 10 is a CPU (Central Processing Unit), and executes programs stored in the storage 12 and expanded in the memory 11 to perform each information processing.

[0023] The memory 11 includes a main memory composed of a volatile memory device such as a DRAM (Dynamic Random Access Memory), and an auxiliary memory composed of a non-volatile memory device such as a flash memory or an HDD (Hard Disc Drive). The memory 11 is used as a work area of the processor 10 and stores a BIOS (Basic Input / Output System) executed when the server 1 is started, and various setting information and the like.

[0024] The storage 12 stores various programs such as application programs. A database (not shown) storing data used for each process may be constructed in the storage 12.

[0025] The transceiver unit 13 connects the server 1 to a network. Note that the transceiver unit 13 may be provided with a short-range communication interface for Bluetooth (registered trademark) and BLE (Bluetooth Low Energy).

[0026] The input / output unit 14 is an information input device such as a keyboard and a mouse, and an output device such as a display.

[0027] The bus 15 is commonly connected to the above elements and transmits, for example, an address signal, a data signal, and various control signals.

[0028] FIG. 5 is a diagram showing a software configuration example of the server of the weight measurement system of the present disclosure. The server includes a measurement mode input reception unit 51, a measurement mode determination unit 52, a weight data acquisition unit 53, an action measurement data detection unit 54, an action data generation unit 55, an action data management unit 56, a weight calculation unit 57, a weight information evaluation unit 58, a weight type identification unit 59, an individual identification unit 60, an abnormality detection unit 61, a display control unit 62, a measurement mode information storage unit 71, a weight data storage unit 72, a basic data storage unit 73, an action measurement data storage unit 74, an action data storage unit 75, and a weight information storage unit 76.

[0029] Note that the measurement mode input reception unit 51, measurement mode determination unit 52, weight data acquisition unit 53, behavior measurement data detection unit 54, behavior data generation unit 55, behavior data management unit 56, weight calculation unit 57, weight information evaluation unit 58, weight type identification unit 59, individual identification unit 60, and abnormality detection unit 61 are realized by the control unit 10 provided in the server reading the program stored in the storage 12 into the memory 11 and executing it. The measurement mode information storage unit 71, weight data storage unit 72, basic data storage unit 73, behavior measurement data storage unit 74, behavior data storage unit 75, and weight information storage unit 76 are realized as a part of the storage area provided by at least one of the memory 11 and the storage 12.

[0030] The measurement mode information storage unit 71 stores information related to the measurement mode. One or more measurement modes are registered. The measurement mode identifies at least one or more measurement targets. Representative ones include a meal amount measurement mode for measuring the meal amount, a water intake measurement mode for measuring the water intake, a defecation amount measurement mode for measuring the defecation amount, a urine output measurement mode for measuring the urine output, a body weight measurement mode for measuring the body weight, etc., and these can be combined. The measurement mode information storage unit 71 stores the ID of each mode, the mode name, the measurement target, the algorithm required when calculating the weight of the measurement target from the weight data, etc.

[0031] The weight data storage unit 72 stores the weight data acquired by the weight data acquisition unit 53 for each weight measurement means 8. The weight data is preferably time-series data stored together with time data.

[0032] The action data storage unit 75 stores the action data generated by the action data generation unit 55. As will be described later, it is preferable that the action data is time-series data stored together with time data. An ID or the like for associating the weight data and the action data, which are data to be analyzed in conjunction with each other, may be assigned. For example, the weight data obtained from the weight measurement means 8 owned by the same user may be associated with the action data of the animal raised by the user. Alternatively, the weight data obtained from one weight measurement means 8 may be associated with the action data of a plurality of animals.

[0033] The weight information storage unit 76 stores the weight information calculated by the weight calculation unit 57. FIG. 6 is a configuration example of the weight information stored in the weight information storage unit 76. For example, for each measurement date and time, the measurement target and the weight of the measurement target (e.g., food intake) may be stored as part of the weight information. In addition to this, the weight information may include information on the individual name or individual ID in the case of group feeding.

[0034] The measurement mode input reception unit 51 receives an input of a measurement mode to be selected from a plurality of measurement modes from the user. The input may be performed by a button or a touch panel provided in the weight measurement means 8, or may be input by the user terminal.

[0035] The measurement mode determination unit 52 is used when automatically setting the measurement mode without receiving a selection input from the user. The measurement mode determination unit 52 can determine the measurement mode based on the weight of the item placed on the weight measurement means 8. For example, the measurement mode determination unit 52 stores in advance the weights of a toilet, tableware, water container, bed, etc. that the user can use, and determines from the weight of the item placed on the weight measurement means 8 which of the toilet, tableware, water container, bed it is. Then, when the toilet is placed, the measurement mode determination unit 52 selects the excrement measurement mode, when the tableware is placed, the food intake measurement mode, when the water container is placed, the water intake measurement mode, when both the tableware and the water container are placed, the food intake & water intake measurement mode, etc., and can select the measurement mode set for each item.

[0036] The weight data acquisition unit 53 acquires weight data from the weight measurement means 8. The weight measurement means 8 and the server are connected by a communication network. The weight data is preferably acquired in time series. The acquired weight data is stored in the weight data storage unit 72 together with time information.

[0037] The behavior measurement data detection unit 54 receives the behavior measurement data detected by the sensor 5 and transmitted via the communication terminal 2 via the transceiver 13 of the server 1. The behavior measurement data is behavior measurement data related to an animal and is data obtained from the sensor 5 provided on the animal. As the behavior measurement data, for example, output data of the sensor 5 such as acceleration and temperature (body temperature) can be used. The received behavior measurement data may be stored in the behavior measurement data storage unit 74 of the storage 12 built in the server 1, or may be stored in the storage built in the analysis server 4 shown in FIG. 1.

[0038] Based on the received behavior measurement data, the behavior data generation unit 55 generates cat behavior data while cooperating with the analysis server 4 (or by a single process in this behavior data generation unit 55) as shown in FIG. 2. Further, the behavior data management unit 56 stores the generated behavior data in the behavior data storage unit 75 and manages such behavior data. The behavior data generated by the behavior data generation unit 55 is, for example, time-series behavior data.

[0039] Here, the behavior data may include exercise data, sleep data, meal data, toilet data, location data, etc., which are stored in the behavior data storage unit 75. More specifically, as exercise data, aggregated data such as whether there is exercise and the time, and how much activity is done in a day may be included. Also, as sleep data, aggregated data such as whether there is sleep and the time, and how much sleep is done in a day may be included. Also, as meal data, aggregated data such as the number of meals eaten and the time of each meal, and / or the number of times water is drunk and the time of each drink, along with the presence or absence of meal and water intake behaviors, may be included. Also, as toilet data, aggregated data such as the number of bowel movements and the time of each bowel movement, and / or the number of urinations and the time of each urination, along with the presence or absence of bowel and urination behaviors, may be included. Also, as location data, the direction of movement and the position where the cat was may be included. Also, as other data, the number of times water is drunk and the time of each drink, etc. may be included. Also, although not shown in the figure, data related to the surrounding environment such as the body temperature of the cat at the time of measurement and the room temperature where the cat is located can be acquired and stored in the behavior data storage unit 75.

[0040] Also, the basic data storage unit 73 stores the basic information of the animal. The basic data may include the name, species, age, gender, residence area, health information, owner information, etc. of the animal. Examples of health information include medical history, disease history, etc. Also, examples of owner information include information such as the gender, age, occupation, etc. of the owner.

[0041] The weight calculation unit 57 analyzes the weight data acquired by the weight data acquisition unit 53 and outputs the target weight information according to the measurement mode. An example of the weight calculation method in each measurement mode is shown below.

[0042] <Food Intake, Water Intake, and Body Weight Measurement Mode> Figure 7 shows an example of measuring food intake, water intake, and body weight. When an animal steps on the weight measuring means 8 to eat or drink water, the time-series weight data shows behavior as shown in Figure 7, for example. Specifically, the difference ΔW1 between the weight before the animal steps on the weight measuring means 8 and the weight when the animal steps on it can be the body weight of the animal. Also, the difference ΔW2 between the weight before the animal steps on the weight measuring means 8 and the weight when the animal gets off after finishing eating and drinking can be the amount of decrease in food or water, that is, the food intake and water intake. When there are fluctuations in the weight data due to the animal moving while it is on the weight measuring means 8, appropriate optimal values can be adopted, such as adopting the average value in the time series of the weight data or the weight data when there has been no movement for a certain period of time or more.

[0043] <Excretion amount and body weight measurement mode> Figure 8 shows an example of measuring excretion amount and body weight. When an animal enters the toilet on the weight measuring means 8 to defecate or urinate, the time-series weight data shows behavior as shown in Figure 8, for example. The difference ΔW3 between the weight when the animal enters the toilet and the weight when the animal comes out of the toilet can be the body weight of the animal. The body weight may also be the difference between the weight before the animal enters the toilet and the weight immediately after entering the toilet. Also, the difference ΔW4 between the weight before the animal enters the toilet and the weight after the animal comes out of the toilet can be the excretion amount. When there are fluctuations in the weight data due to the animal moving while it is in the toilet, appropriate optimal values can be adopted, such as adopting the average value in the time series of the weight data or the weight data when there has been no movement for a certain period of time or more.

[0044] <Body weight measurement mode> Figure 9 shows an example of measuring body weight. When an animal lies on a bed or relaxes on the bed or the like on the weight measuring means 8 to sleep or relax, the time-series weight data shows behavior as shown in Figure 9, for example. The difference ΔW5 between the weight when the animal enters the bed and the weight when the animal comes out of the bed can be the body weight of the animal.

[0045] As described above, the weight calculation unit 57 can estimate the weights of various measurement targets from the changes in the time-series weight data. The types of measurement targets and their calculation methods are not limited to those described above and can be arbitrarily set.

[0046] The weight information evaluation unit 58 evaluates the reliability of the weight information. The weight information evaluation unit 58 can evaluate the reliability of the weight information by comparing the weight information calculated by the weight calculation unit 57 with the behavior data. The weight information evaluation unit 58 refers to the behavior data in the time period (t1 to t2) when the weight information of the measurement target was acquired from the behavior data storage unit 75, and checks whether the behavior of the animal at that time matches the measurement target of the weight information. For example, when measuring in the food intake measurement mode, when the weight data fluctuates, as described above, the change amount of the weight data is determined as the "food intake", but if the behavior data in that time period (t1 to t2) indicates "eating" as shown in FIG. 10, it can be determined that the weight information is likely to be the food intake. On the other hand, if the behavior data in that time period is not "eating" (for example, "playing"), it is determined that the weight information may not indicate the food intake. In this way, when the behavior data in the same time period as the weight information matches the weight information, the weight information evaluation unit 58 determines that the weight information is reliable, and when they do not match, the weight information can be tagged or deleted as uncertain data.

[0047] In addition, the weight information evaluation unit 58 may also determine the reliability of the weight information based on past weight data. The weight information evaluation unit 58 determines the numerical range of the weights that can be obtained for each measurement target from past performance, and may determine it as an error if the measured weight is outside the range. Also, by machine learning using past weight data as teacher data to create reference weight data, it can also be determined as an error when the variation rate is large from the reference weight data.

[0048] When the weight type specifying unit 59 can distinguish between when eating rice, drinking water, defecating, and urinating, it can further specifically specify the weight information calculated by the weight calculation unit 57. For example, the weight type specifying unit 59 can specify the type based on the behavior data. For example, in the meal amount / water intake / weight measurement mode, when both a tableware and a water container are placed on the weight measurement means 8, ΔW2 indicates either the meal amount, the water intake amount, or the total of both. Here, if the behavior data from t1 to t2 indicates "meal", it can be determined that ΔW2 is the meal amount. Similarly, in the excretion amount / weight measurement mode, ΔW4 indicates either the defecation amount, the urination amount, or the total of both. However, if the behavior data in the time zone when the weight data was acquired is "defecation", it can be determined that ΔW4 is the defecation amount. In this way, the weight type specifying unit 59 can more specifically specify the measurement target of the weight information from the behavior data in the same time zone.

[0049] The weight type specifying unit 59 may specify the weight type based on past weight data. For example, a numerical range of possible weights for each measurement target may be determined from past records, and the type of the measured weight may be specified. Also, by machine learning using past weight data for which the weight type (such as meal or drinking water, feces or urine) is known as teacher data, reference weight data for each weight type may be created, and the weight type of the measured weight data may be estimated.

[0050] The individual identification unit 60 can determine, for example, which individual the weight information calculated by the weight calculation unit 57 is associated with in the case of group feeding. The individual identification unit 60 refers to the behavior data of each individual in the time period (t1 to t2) when the weight data of the measurement target is acquired, and identifies the individual to which the weight information should be associated. In the example shown in FIG. 11, from the behavior data of individual A and individual B at t1 to t2, it is determined that the weight data acquired by the weight measurement means 8 is that of individual A who was eating. In this way, the individual identification unit 60 can select the individual showing the behavior data that matches each weight information, and assign individual information to the weight information.

[0051] Also, the individual identification unit 60 may identify an individual from waveform information such as acceleration data obtained from the sensors of each individual. It is known that even for the same behavior, characteristics unique to the waveform appear for each individual. By comparing the characteristics with the waveforms for each behavior of each individual registered in advance for the behavior waveform data in the time period when the weight data of the measurement target is acquired, the individual can be identified.

[0052] As a method for identifying an individual, in addition to the above-described method, various methods may be adopted. For example, the identification of an individual may be performed by analyzing image information obtained by image acquisition means capable of photographing the weight measurement means 8. More specifically, image acquisition means such as a video camera captures a moving image over time, and the individual on the weight measurement means 8 is identified by image recognition. The individual identification unit 60 can identify the individual to which the weight information should be associated from the image data at the time when the weight data of the measurement target is acquired.

[0053] The individual identification unit 60 may also identify an individual near the weight measurement means 8 based on information obtained from the strength of radio waves such as BLUETOOTH LAW ENERGY (BLE) from data including individual information from an animal collar or the like. The weight measurement means 8 or its vicinity is provided with BLE reception means, and an individual closer can be recognized.

[0054] The individual identification unit 60 may identify an individual based on the weight information of the animal. By registering the weight of the individual in advance and referring to the information of the registered weight when calculating the weight in each measurement mode, the individual can be identified.

[0055] As described above, the individual identification unit 60 can identify an individual by a plurality of methods. One or more of these methods can be adopted, and individual identification may be performed by combining a plurality of methods.

[0056] When each calculated weight information satisfies a predetermined condition, the abnormality detection unit 61 notifies the user of the abnormality. For example, for each measurement target (food intake amount · number of meals, water intake amount · number of meals, defecation amount · number of meals, urine output amount · number of meals, weight), an appropriate range is set in advance. When the measured value is less than or higher than this range, such a measured value is determined to be "abnormal". When the abnormality detection unit 61 determines an abnormality, for example, the analysis server 4, the weight measurement means 8, etc. may transmit information indicating that an abnormality has been determined to the user terminal.

[0057] The display control unit 62 generates data constituting the screen displayed on the display of the user terminal 3. The display control unit 62 preferably displays the calculated weight information together with the time information. Further, as shown in FIG. 16, it is more preferable to display the weight information together with the action information.

[0058] FIG. 12 is a flowchart of the process in an embodiment of the present disclosure.

[0059] First, by the user selecting and inputting a measurement mode, the measurement mode input reception unit 51 receives the measurement mode (S101). The selection of the measurement mode is performed when the user starts using the weight measurement means 8 for the first time, or can be arbitrarily performed at the timing when the measurement target is to be changed. For example, the measurement modes that can be set may be displayed on the display unit provided on the weight measurement means 8 so that the user can select them. Also, the measurement modes that can be set may be displayed on the user terminal, and the measurement mode input reception unit 51 may receive the information selected by the user.

[0060] The measurement mode may be set by the measurement mode determination unit 52 instead of the measurement mode input reception unit 51 receiving the input from the user. Items such as a bed, tableware, and a water container may be placed on the weight measurement means 8 according to the measurement target. The measurement mode determination unit 52 measures the weight of the item placed on the weight measurement means 8, and recognizes which item is placed by comparing it with the weights of each item registered in advance. Then, a measurement mode is set for each placed item. Note that when no item is placed, it may be determined that it is a mode for measuring only the body weight. The measurement mode only needs to be able to define one or more measurement targets, and the measurement targets can be arbitrarily combined.

[0061] Subsequently, the weight data acquisition unit 53 acquires the weight data measured by the weight measurement means 8 over time. The weight data is stored in the weight data storage unit 72 together with the time information (S102).

[0062] The weight calculation unit 57 calculates the weight of a predetermined measurement target from the acquired weight data based on the set measurement mode (S103).

[0063] When not associating with the behavior data, the weight information including the weight calculated in S103 is stored in the weight information storage unit 76 and output to the user terminal at a predetermined timing (S105).

[0064] On the other hand, when linking with the behavior data, the generation of the animal's behavior data is performed in parallel with the acquisition of the weight data. The generation of the behavior data will be described later (S201 to S203).

[0065] The weight information evaluation unit 58 reads the behavior data at the time when the weight data of the measurement target is measured from the behavior data storage unit 75, and evaluates the reliability of the weight information (S104). If the behavior data in the same time period matches the measurement target, it is evaluated that the weight information is reliable. On the other hand, if it does not match, it is determined that the weight information is incorrect information. Similarly, the weight type identification unit 59 reads the behavior data at the time when the weight data of the measurement target is measured from the behavior data storage unit 75, and if it is possible to distinguish between eating and drinking, and between defecation and urination from the behavior data, the measurement target of the measured weight data is more specifically identified (S104).

[0066] In addition, in the case of group feeding, the individual identification unit 60 identifies the individual related to the weight information by linking the weight information with the behavior data (S104). The individual identification unit 60 reads the behavior data at the time when the weight data of the measurement target is measured from the behavior data storage unit 75, and identifies the individual whose behavior data in the same time period matches the measurement target. The identification of the individual may be performed by image analysis, radio wave intensity such as BLE, or weight, regardless of the behavior data. The display control unit outputs the weight information for each individual.

[0067] Hereinafter, the generation flow of the behavior data will be described. First, the behavior data generation unit 22 checks the measurement data detected by the behavior measurement data detection unit 54 (S201).

[0068] Subsequently, the behavior data generation unit 22 determines the behavior type based on the measurement data (S202). The method for determining the behavior type can be realized by several known behavior analysis methods. For example, the acceleration data (Gx, Gy, Gz) in the xyz-axis directions obtained from the acceleration sensor 5 is decomposed into a signal with vibration into a period and an amplitude for each moment using wavelet transform, and the periodicity of the signal at each moment is recognized as a behavior spectrum, and the behavior can be classified by comparing it with the pre-registered behavior elements according to the similarity of the spectra.

[0069] If there is no information on the pre-registered behavior elements, it can be recognized as a new behavior element and classified as data indicating abnormal behavior described later. The data indicating such abnormal behavior can be provided to, for example, a veterinarian. Or, for example, the acceleration data obtained from the acceleration sensor 5 is Fourier-transformed, and the average value or peak value of the frequency components calculated along the time axis is compared with the known frequencies corresponding to the behavior types (exercise, sleep, eating, toilet, etc.) of the same or another cat to identify the behavior, or based on the frequency components calculated by performing a fast Fourier transform (FFT) on the acceleration components, characteristic waveforms and spectrum values are extracted, and the behavior can be identified by comparing them with the known characteristic waveforms or spectrum values corresponding to the behavior types (exercise, sleep, eating, toilet, etc.) of the same or another cat. Also, the behavior type can be inferred by grasping the posture of the cat from the posture (θx, θy, θz) in each axis direction calculated by the acceleration sensor.

[0070] When the behavior type is determined, the behavior data generation unit 55 generates data indicating the behavior type as behavior data together with the date and time when the measurement data was measured (or the date and time when it was received, the date and time when the behavior data was generated) (S203).

[0071] Here, the flow of action type analysis will be further described with reference to FIG. 13. For the acceleration data 101 obtained from the acceleration sensor, data preprocessing is performed to convert it into the spectrum data obtained by the above-described wavelet transform or the component data obtained by Fourier transform or the like. The data preprocessed in this way is subsequently scored 103 by a binary model group. The binary model according to the present embodiment compares and analyzes with models of activities that can be specifically expressed (interpreted) such as a WALK model, a RUN model, an EAT model, a STAY model, etc., and scores which specific part of the preprocessed data 102 can be inferred as which action. For example, as shown in FIG. 14, the probability is scored by analyzing the input data with each model. In the illustrated example, “walking” is 91, “running” is 62, “eating” is 21, and “stopping” is 8. Since the highest score is 91 for “walking”, as a scoring result by the binary model group, it is classified as the action of “walking”.

[0072] Subsequently, returning to FIG. 13, scoring 104 by a multi-value model group is performed. The scoring by the multi-value model group according to the present embodiment determines, based on machine learning, which result of the binary model group should be prioritized when the results obtained by the binary models are antagonistic. For example, in the example according to FIG. 14, the results of “walking” being 91 and “running” being 62 are obtained, and the score of the evaluation of “running” is also relatively high. In this case, it is determined which binary model should be prioritized in this case from the combination of the input data to the past binary model group and the determination result. Thus, in the present embodiment, the accuracy of the data is improved by further evaluating the results of the binary model group specialized for the determination of each action by the multi-value model group.

[0073] Return to FIG. 13 and further correct the determined actions based on the rule base. For example, during a determination interval such as "eating" or "sleeping" that often continues for a certain period of time in the behavior of a cat, if the binary model determines an action that normally rarely occurs, such as "running", suddenly, or if the determination is impossible, the prediction result of the binary model for this interval is rejected, and a correction is made to estimate other actions according to the rules. When the correction is completed, the action label 106 registered in advance for the action is assigned.

[0074] In the present embodiment, in particular, in order to cope with individual differences and individual factors due to the environment of each animal, it is configured to receive feedback 107 from the user. Specifically, as shown in FIG. 15, while observing the animal being managed by oneself, the current action is recorded (manually). By associating the record with the data of the acceleration sensor, teacher data by visual observation or the like can be collected. The feedback data 108 obtained in this way is accumulated and used to improve the accuracy of the models in the binary model group.

[0075] <Modification Example> The case of using a plurality of weight measuring means 8 will be described. In this modification example, one user can place different animal items on each of the plurality of weight measuring means 8 to measure different measurement targets. An example is shown in FIG. 17. Place a food bowl and a water container on the first weight measuring means 8 to set it to the meal / water intake / weight measurement mode, and place a toilet on the second weight measuring means 8 to set it to the excretion amount / weight measurement mode. Calculate the weight of the measurement target for each weight data, and generate the first weight information and the second weight information. Then, the display control unit 62 can arrange the respective weight information in one time series and provide it to the user. According to this modification example, it is possible to simultaneously acquire the weight data of a plurality of measurement targets.

[0076] The above-described embodiments are merely examples for facilitating the understanding of the present disclosure, and are not for limiting the interpretation of the present disclosure. The present disclosure can be changed and improved without departing from its gist, and it goes without saying that equivalents thereof are included in the present disclosure.

Description of Symbols

[0077] 1 Server 2 Communication Terminal 3 User Terminal 4 Analysis Server 5 Sensor 6 Animal 7 Receiver 8 Weight Measurement Means

Claims

1. A weight measurement system for animals, comprising: a weight data acquisition unit that acquires, from the weight measurement means, a first weight at a time before the animal mounts the weight measurement means, a second weight at a time when the animal is mounted on the weight measurement means, and a third weight at a time when the animal dismounts from the weight measurement means; a measurement mode determination unit that determines a measurement mode according to the weight of an item placed on the weight measurement means; a weight calculation unit that calculates any one of a food intake amount, a water intake amount, the food intake amount and the water intake amount, a defecation amount, a urination amount, or an excretion amount based on a difference between the first and third weights according to the measurement mode; A weight measurement system characterized by comprising the above.

2. A weight measurement system for animals, comprising: a weight data acquisition unit that acquires, from the weight measurement means, a first weight at a time before the animal mounts the weight measurement means, a second weight at a time when the animal is mounted on the weight measurement means, and a third weight at a time when the animal dismounts from the weight measurement means; a weight calculation unit that calculates the body weight of the animal based on a difference between the first and second weights, and calculates at least one of the food intake amount and the water intake amount of the animal or the excretion amount of the animal based on a difference between the first and third weights; an action data generation unit that generates time-series action data of the animal based on action measurement data related to the animal; a weight type identification unit that identifies the type of weight calculated by the weight calculation unit based on a comparison between the time-series action data at the time when the weight data is acquired, generated by the action data generation unit, and the time-series weight information at the time, output by the weight calculation unit; A weight measurement system characterized by comprising the above.

3. A weight measurement method for animals, comprising: a step of acquiring, from the weight measurement means, a first weight at a time before the animal mounts the weight measurement means, a second weight at a time when the animal is mounted on the weight measurement means, and a third weight at a time when the animal dismounts from the weight measurement means; A step of determining a measurement mode according to the weight of an item placed on the weight measuring means; A step of calculating any one of a food intake amount, a water intake amount, the food intake amount and the water intake amount, a defecation amount, a urination amount, or an excretion amount based on the difference between the first and third weights according to the measurement mode; A weight measurement method, characterized in that a computer executes the method.

4. A step of obtaining a first weight at a time point before an animal mounts on the weight measuring means, a second weight at a time point when the animal is on the weight measuring means, and a third weight at a time point when the animal dismounts from the weight measuring means from the weight measuring means; A step of determining a measurement mode according to the weight of an item placed on the weight measuring means; A step of calculating any one of a food intake amount, a water intake amount, the food intake amount and the water intake amount, a defecation amount, a urination amount, or an excretion amount based on the difference between the first and third weights according to the measurement mode; A program for causing a computer to execute the method.

Images