JP6096738B2 - Animal abnormality detection device, animal abnormality detection method, and program - Google Patents

Description

  The present invention relates to an animal abnormality detection device that detects an abnormality of an animal.

  In a conventional apparatus for monitoring an animal, an apparatus for detecting an abnormal state using a sensor with respect to the animal has been developed (for example, see Patent Document 1).

JP 2012-93936 A

  However, conventional devices for monitoring animals have a problem that abnormalities can be detected only for specific types of animals.

  In view of the above problems, an object of the present invention is to detect abnormalities in many types of animals.

Animals abnormality detection apparatus according to an aspect of the present invention, a search observation data receiving means for receiving a search animal observation data comprising one or more observations of the time series of animal, search animals search observation data receiving means has received transmits and animals abnormality information specifying means for specifying the animals abnormality information containing the animal observation data corresponding to the observation data, when the animals abnormality information specifying means has identified animals abnormality information, abnormality information is information about abnormal And an anomaly information transmitting means.

An animal abnormality detection method according to one aspect of the present invention is an animal abnormality detection method processed using search observation data receiving means, animal abnormality information specifying means, and abnormality information transmission means, wherein search observation data receiving means The search observation data receiving step for receiving the search animal observation data including one or more observation data of the animal time series, and the animal abnormality information specifying means correspond to the search animal observation data received by the search observation data reception step. An anomaly information identifying step that identifies animal anomaly information including animal observation data and an anomaly that transmits anomaly information that is information relating to anomalies when the anomaly information transmitting means identifies the anomaly information in the anomaly information identifying step. An animal abnormality detection method comprising: an information transmission step.

According to one aspect of the present invention, there is provided a program for searching observation data receiving means for receiving search animal observation data including one or more observation data of time series of animals, and search animal observation data received by the search observation data receiving means. Anomaly information identifying means for identifying animal anomaly information including animal observation data corresponding to, and anomaly information transmitting means for transmitting anomaly information that is information relating to anomalies when the animal anomaly information identifying means identifies animal anomaly information It is a program to make it function as.

  According to the animal abnormality detection device and the like according to the present invention, it is possible to detect abnormality of many kinds of animals.

Conceptual diagram of a system including an animal abnormality detection device according to Embodiment 1 Block diagram of an animal abnormality detection device in the same embodiment The figure which shows an example of the sensor data stored in the sensor data storage means in the embodiment The figure for demonstrating the method in which the feature-value data acquisition means in the embodiment acquires a feature-value The figure for demonstrating the method in which the state label setting means in the same embodiment and the action label setting means set a label The figure for demonstrating the method in which the state rule acquisition means and action rule acquisition means in the embodiment acquire a rule The flowchart which shows operation | movement of the animal abnormality detection apparatus in the embodiment The figure which shows an example of the animal abnormality information stored in the animal abnormality information storage means in the embodiment The figure which shows an example of the animal classification information stored in the animal classification information storage means in the embodiment The figure which shows an example of the display of the user's terminal device in the embodiment The figure which shows an example of the external appearance of the computer system in the embodiment The figure which shows an example of a structure of the computer system in the embodiment

  Hereinafter, embodiments of an animal abnormality detection device and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.

(Embodiment 1)
In this embodiment, an animal abnormality detection device that receives time series data for animals, searches for animal abnormality information corresponding to the time series data, and transmits abnormality information when the animal abnormality information is specified. 1 will be described.

  FIG. 1 is a conceptual diagram of a system including an animal abnormality detection device 1 according to the present embodiment. The system including the animal abnormality detection device 1 includes the animal abnormality detection device 1 and a user terminal device 2. In addition, the system including the animal abnormality detection device 1 may further include a specialist's terminal device 3. In FIG. 1, an animal abnormality detection device 1, one or more user terminal devices 2, and one or more specialist terminal devices 3 are connected via a network 100. The network 100 is a wired or wireless communication line, such as the Internet, an intranet, a LAN (Local Area Network), a public telephone line, or the like. Further, the user terminal device 2 and the specialist terminal device 3 may be any terminals that can be connected to the network 100. For example, the terminal device 2 of the user and the terminal device 3 of the specialist may be a desktop personal computer, a notebook personal computer, a smartphone, or a PDA. The user terminal device 2 is a terminal that can acquire information acquired by sensors such as a camera, a microphone, and a thermometer. The user terminal device 2 may acquire information acquired by the sensor via a wired or wireless connection means, or may acquire information acquired by the sensor via a storage medium such as a memory card. good. Each sensor acquires information about animals such as squirrels.

  FIG. 2 is a block diagram of the animal abnormality detection device 1 according to the present embodiment. The animal abnormality detection device 1 includes animal abnormality information storage means 101, search observation data reception means 102, animal type information storage means 103, animal abnormality information identification means 104, abnormality information transmission means 105, sensor data storage means 106, feature amount data. An acquisition unit 107, a state rule acquisition unit 108, a behavior rule acquisition unit 109, and an animal abnormality information storage unit 110 are provided. Further, the state rule acquisition unit 108 includes a state label setting unit 21 and a state rule specifying unit 22. The behavior rule acquisition unit 109 includes a behavior label setting unit 23 and a behavior rule specifying unit 24.

  The animal abnormality information storage means 101 stores one or more animal abnormality information. The animal abnormality information includes animal observation data including one or more observation data in time series of animals, and animal individual information that is information related to the attributes of the individual animals. The animal observation data is preferably observation data when there is an abnormality. “Abnormal” is a case of having a medical or surgical disease. The time-series observation data is data in which data acquired by various sensors at a predetermined interval is continuous. The predetermined interval may be constant or indefinite. The predetermined interval may be, for example, once every second or once every 10 seconds. The predetermined interval may be equal to or less than an interval necessary for acquiring the state rule or the behavior rule. The time series observation data of animals is preferably a moving image of the observation object captured by the camera and a sound obtained by collecting the sound emitted by the observation object with a microphone, etc., but the data acquired using various sensors Anything is fine. For example, time-series observation data of time-series animals may be time-series data indicating body temperature measured by thermography, or may be time-series data of positions acquired by GPS attached to a target, It may be time-series data indicating the angle of the target acquired from a gyro sensor attached to the target, or may be time-series data of a pulse acquired with a pulse meter attached to an observation target that is an animal. Note that the sound emitted from the observation target may be a sound such as a cry generated from the observation target, or may be a sound generated when the observation target operates. The sound generated by the movement of the observation target may be, for example, the sound of a squirrel breaking a sunflower seed, or the sound of a raccoon washing food. Sounds that rub against the road surface. In addition, the time-series observation data of animals acquired using various sensors may be the data acquired using various sensors as they are, and are calculated from the data acquired using the various sensors. It may be data that has been processed. Observation target data that is data calculated from data acquired using a sensor is, for example, time-series three-dimensional coordinate data indicating the movement history of an observation target acquired using two or more video cameras. May be. The time-series observation data may be data obtained by converting the data acquired by the sensor as described above into data of a different format. The data converted into a different format may be feature data obtained by dividing the waveform data acquired by the sensor for each predetermined period and arranging characteristic values in each divided period in time series, Data obtained by classifying the characteristic values and assigning labels to the respective classifications to obtain labels obtained in time series may be used. Details of the feature amount data and data in which labels are arranged in time series will be described later.

  The animal individual information is information including a plurality of pieces of information related to the attributes of the animals. For example, the information related to the attribute included in the animal individual information may be information indicating the type of animal, information indicating the sex of the animal, information indicating the age of the animal, May be information indicating the past medical history, information indicating the size of the animal, information indicating the weight of the animal, or the like. The animal individual information is a target to be searched using information received by the search observation data receiving means 102. In addition, each information regarding an attribute may have only one value, and may have a plurality of values. The information indicating the type of animal may include, for example, only “squirrel” or may include “squirrel” and “chipmunk”. The information indicating the age of the animal may include, for example, only “4 years old” or “4 years old” and “5 years old”. When searching for animal individual information, there may be two types of information that will not hit if they do not always match, and two types of information that will not hit if they do not match, but will match if other information matches. Information that does not hit if it does not necessarily match may be, for example, the type of animal. If other information matches, the hit information may be the age of the animal, past medical history, weight, etc. Note that the match in this case may be said to match that one or more of the values match when the attribute information has a plurality of values.

  The animal abnormality information may also include environmental observation data that is observation data regarding the external environment at the same time as the animal observation data included in the animal abnormality information. The external environment is an event related to the environment around the observation target. The surrounding environment may be anything as long as it is in an area that affects the observation target. The surrounding environment may be around the target cage, or a room where the cage is placed. The environmental observation data may be anything as long as it is data related to the external environment acquired using various sensors. For example, the environmental observation data may be a moving image taken by a camera, time-series data indicating sound collected by a microphone, or time-series data indicating temperature acquired by a thermometer. It may be time-series data indicating precipitation acquired by the rain gauge, or time-series data indicating atmospheric pressure acquired by the barometer, and the wind intensity acquired by the anemometer. May be time-series data or the like. Moreover, the environmental observation data acquired using various sensors may be the data acquired using the various sensors as they are, and are data calculated from the data acquired using the various sensors. There may be. In addition, environmental observation data, which is data calculated from data acquired using a sensor, indicates, for example, a temperature difference several hours ago from the current time series calculated from a temperature history acquired by a thermometer. It may be data, or data indicating a time-series temperature difference calculated from indoor and outdoor temperatures acquired by two or more thermometers. Since each sensor used for acquiring animal time-series observation data and environment observation data is a known technique, detailed description thereof is omitted. The environmental observation data may be data obtained by converting data acquired by the above-described sensor into data of a different format. Data converted to a different format may be external environment feature data in which waveform data acquired by a sensor is divided every predetermined period and characteristic values in each divided period are arranged in time series. Well, it is possible to classify the characteristic values and assign labels to each classification, and the data to be obtained may be data arranged in chronological order, or may be one characteristic value, A single label may be used. Details of the feature amount data and data in which labels are arranged in time series will be described later.

  The animal abnormality information may include animal abnormality detection information indicating the contents of the abnormality corresponding to the animal observation data included in the animal abnormality information. The animal abnormality detection information is the content of the abnormality that can be understood from the animal observation data. For example, the animal abnormality detection information may be “how to walk is not common”, “cannot lie down”, or the like. The animal abnormality detection information is stored in the animal abnormality information storage unit 101 using information that associates the waveform of the animal observation data, the feature amount data, or the arrangement of the labels with the animal abnormality detection information, which is stored in a storage unit (not shown). Alternatively, after the animal abnormality detection information determined by a person is received by a reception unit (not shown), a storage unit (not shown) may be stored in the animal abnormality information storage unit 101.

  The animal abnormality information may include diagnostic information indicating a diagnosis result of a specialist corresponding to the animal observation data included in the animal abnormality information. The specialist may be a veterinarian or may have medical knowledge other than the veterinarian for the animal to be diagnosed. The specialist may make a diagnosis by looking at the animal observation data, or may diagnose the target animal from which the animal observation data has been acquired. The diagnostic information may be accumulated in the animal abnormality information storage unit 101 by a storage unit (not shown) after the reception unit (not shown) receives the diagnostic information transmitted from the terminal device 3 of the specialist.

  When the animal abnormality information storage unit 110 stores animal abnormality information, the animal abnormality information storage unit 101 stores animal observation data including two or more observation data. The observation data in this case is feature amount data or data in which labels are arranged in time series.

  The animal abnormality information storage means 101 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium. The animal abnormality information may be accumulated by the animal abnormality information accumulation unit 110, may be accumulated via a recording medium, or after receiving the animal abnormality information transmitted via a communication line or the like by a reception unit (not shown). It may be accumulated by an accumulation unit (not shown).

  The search observation data receiving means 102 receives search animal observation data including one or more observation data in time series of animals, and search animal individual information related to the attributes of individual animals. Information received by the search observation data receiving unit 102 includes information acquired by the user's terminal device 2 constantly monitoring animals and information acquired selectively during a specific period. That is, the search observation data receiving unit 102 may receive animal observation data or the like in an endless manner, or may receive animal observation data for a specific period from the user terminal device 2. The selectively acquired information may be information for a period when the animal is determined to be abnormal by the user, or may be information for a scheduled period. The information of the scheduled period may be information acquired in a fixed period such as 10 minutes from 12:00 every day, for example. The search observation data receiving means 102 may receive search animal observation data, search animal individual information, and search environment observation data that is observation data related to the external environment at the same time as the search animal observation data. The search animal observation data may be data acquired by a sensor, or may be data acquired based on data acquired by a sensor. The search animal observation data received by the search observation data receiving unit 102 is data serving as a search key for searching the animal observation data stored in the animal abnormality information storage unit 101. Therefore, the details of the retrieved animal observation data are the same as the animal observation data. The retrieved animal observation data is preferably data in the same format as the animal observation data, but may be data in a different format. The search animal individual information may be information input by the user at the user terminal device 2 or may be information set in advance at the user terminal device 2. The search animal individual information received by the search observation data receiving means 102 is data serving as a search key for searching for animal individual information stored in the animal abnormality information storage means 101. The retrieved animal individual information is information including a plurality of information related to the attributes of the animal individual. For example, the information on the attribute included in the search animal individual information may be information indicating the type of animal, may be information indicating the sex of the animal, may be information indicating the age of the animal, It may be information indicating the past medical history of the animal, information indicating the size of the animal, information indicating the weight of the animal, or the like. The search environment observation data received by the search observation data receiving unit 102 is data serving as a search key for searching the environment observation data stored in the animal abnormality information storage unit 101. The details of the retrieval environment observation data are the same as the environment observation data. The search environment observation data is preferably data in the same format as the environment observation data, but may be data in a different format.

  The search observation data receiving means 102 may receive the search animal observation data and the search animal individual information in association with each other. Receiving in association may be receiving the search animal observation data and the search animal individual information at the same time, and receiving the search animal observation data including the same ID and the search animal individual information separately. Alternatively, the search animal observation data and the search animal individual information may be received in order. The search observation data receiving means 102 is usually realized by a wireless or wired communication means, but may be realized by a means for receiving a broadcast.

  The animal type information storage means 103 stores one or more animal type information. The animal type information is information indicating the type of a similar animal. The animal type information may be expressed in any manner as long as it is information that can express that an animal type different from a certain animal type is similar. For example, the animal type information may be expressed so as to indicate the type of one-to-one similar animal such as “chipmunk, squirrel” or “chipmunk, Japanese squirrel”. “” May be expressed as a group of a plurality of animal types. The animal type information storage means 103 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium. The process in which the animal type information is stored in the animal type information storage means 103 does not matter. For example, the animal type information may be stored in the animal type information storage unit 103 via a recording medium, and the animal type information transmitted via a communication line or the like is stored in the animal type information storage unit 103. Alternatively, the animal type information input via the input device may be stored in the animal type information storage unit 103.

  The animal abnormality information specifying unit 104 specifies animal abnormality information including animal observation data and animal individual information corresponding to the search animal observation data and the search animal individual information received by the search observation data receiving unit 102. Further, the animal abnormality information specifying unit 104 may further specify animal abnormality information including animal observation data, animal individual information, and environment observation data corresponding to the retrieved environment observation data. The animal abnormality information specifying means 104 includes the animal observation data and the animal individual information when the search animal observation data corresponds to the animal observation data and the search animal individual information corresponds to the animal individual information. Animal abnormality information may be specified. In addition, when the environmental observation data is stored in the animal abnormality information storage unit 101 and the search observation data reception unit 102 also receives the search environment observation data, the animal abnormality information identification unit 104 determines that the search animal observation data and the animal When observation data corresponds, search animal individual information and animal individual information correspond, and search environment observation data and environmental observation data correspond, the animal observation data, the animal individual information, and the environment observation Animal abnormality information including data may be specified.

  “The search animal observation data and the animal observation data correspond” may be that the search animal observation data and the animal observation data completely match or a part of the data may match. . “Some data matches” means that if there are more types of observation data included in the search animal observation data than types of observation data included in the animal observation data, The observation data of the part type may coincide with all types of observation data included in the animal observation data. “Some data matches” is included in the search animal observation data when the type of observation data included in the search animal observation data is different from the type of observation data included in the animal observation data. It may be that observation data and observation data included in the same kind of animal observation data match. Note that “match” when determining the correspondence between the retrieved animal observation data and the animal observation data may include an error equal to or less than a predetermined threshold. For example, when the observation data is a waveform, the animal abnormality information specifying unit 104 increases the waveform of the observation data included in the search animal observation data and the waveform of the observation data included in the animal observation data at the same timing, If a falling waveform is acquired, it may be determined that the values match without considering the difference in the amplitude, and if the same amplitude is acquired, if they match without considering the length of the period You may judge. In addition, when the observation data is feature quantity data or a list of labels, the observation data included in the search animal observation data includes a list of values of the observation data included in the animal observation data. It may be determined that they match.

  “The searched animal individual information and the animal individual information correspond” may be that the information included in the searched animal individual information matches the information included in the animal individual information. For example, when the animal type is included in the search animal individual information and the animal individual information, the animal type in the search animal individual information matches the animal type in the animal individual information. Note that “the search animal individual information corresponds to the animal individual information” may be that part of the information matches. “Some information matches” means that when the type of information included in the search animal individual information is greater than the type of information included in the animal individual information, some of the information included in the search animal individual information The information may match all information included in the animal individual information. In addition, “partial information matches” means that the information included in the search animal individual information is different when the type of information included in the search animal individual information is different from the type of information included in the animal individual information. It may be that the information included in the common type of animal individual information matches. If each piece of information included in the animal individual information has a plurality of values, the information included in the searched animal individual information is one of the plurality of values of the information included in the animal individual information. When they match, the animal abnormality information specifying unit 104 may determine that it corresponds. In addition, when the animal individual information includes “information that does not necessarily hit if it does not match” and the information does not match, the animal abnormality information specifying unit 104 determines that the other information is the searched animal individual. Even if the information matches each information, it may not be determined that the information corresponds. Note that the “match” when determining the correspondence between the retrieved animal individual information and the animal individual information may include an error. When the animal type is included in the retrieved animal individual information and the animal individual information, the animal abnormality information specifying unit 104 determines whether the animal type is the same as the animal type information. The animal abnormality information including the animal individual information including the type and the animal observation data corresponding to the retrieved animal data may be specified. In addition, when the age of the animal is included in the search animal individual information and the animal individual information, the animal abnormality information specifying unit 104 determines a predetermined threshold value when determining whether the animal age is the same. The following age differences may be determined to match.

  “The search environment observation data and the environment observation data correspond” means that the search environment observation data matches the environment observation data. Note that “match” when determining the correspondence between the retrieved environment observation data and the environment observation data may include an error equal to or less than a predetermined threshold. For example, when the environmental observation data is a waveform, the animal abnormality information specifying unit 104 acquires a waveform in which the waveform of the search environment observation data and the waveform of the environmental observation data rise and fall at the same timing. In addition, it may be determined that they match without considering the difference of the swing width, and when the same swing width is acquired, it may be determined that they match without considering the length of the period. In addition, when the environmental observation data is feature amount data or in a line of labels, it may be determined that the search environment observation data matches when the environmental observation data is included in the data. . In addition, when the environmental observation data is a feature value data value or a label, it may be determined that the search environment observation data data matches the environmental observation data data. . Further, the animal abnormality information specifying unit 104 determines whether or not observation data of different formats correspond, after converting the data into the same format. When converting the format of the observation data, the animal abnormality information specifying unit 104 may convert the format by causing the feature amount data acquisition unit 107, the state rule acquisition unit 108, and the behavior rule acquisition unit 109 to process the format. The animal abnormality information specifying unit 104 can be usually realized by an MPU, a memory, or the like. The processing procedure of the animal abnormality information specifying means 104 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The abnormality information transmitting unit 105 transmits abnormality information that is information relating to abnormality when the animal abnormality information specifying unit 104 specifies animal abnormality information. Animal abnormality information is information indicating an abnormality. The abnormality information may include the animal abnormality detection information included in the animal abnormality information specified by the animal abnormality information specifying unit 104, and the diagnosis included in the animal abnormality information specified by the animal abnormality information specifying unit 104. Information may be included. The abnormality information transmitting means 105 may transmit the abnormality information to the terminal device 2 of the user who transmitted the search animal observation data or the like, or may transmit it to another terminal device set in advance by the user. You may transmit to the terminal device which is not shown which has transmitted the transmission request regarding the abnormality information received in the section. Moreover, the abnormality information transmission means 105 may transmit abnormality information to the specialist's terminal device 3. In addition, when transmitting to the terminal device 3 of a specialist, each data which the search observation data receiving means 102 received may also be transmitted. The abnormality information transmitting unit 105 may be usually realized by a wireless or wired communication unit.

  The sensor data storage means 106 is data acquired by the sensor when there is an abnormality in the animal, sensor data that is one or more types of data in time series, and an animal individual that is information on the attributes of the individual animal. Information is stored in association with each other. The sensor data storage means 106 may store time-series sensor data related to the external environment. The sensor data is data acquired by various sensors. The observation data described above may be data as it is acquired using various sensors, or may be data calculated based on data acquired using the various sensors. The data is as-is data acquired using various sensors. The details of the animal individual information stored in the sensor data storage means 106 are the same as the animal individual information stored in the animal abnormality information storage means 101.

  The sensor data storage means 106 may store two or more types of time-series sensor data. When two or more types of time-series sensor data are stored in the sensor data storage unit 106, for example, sensor data as illustrated in FIG. 3 is stored in the sensor data storage unit 106. Each sensor data stored in the sensor data storage means 106 is data including a common period. In other words, for example, two or more types of time-series sensor data observed in an arbitrary period such as a period from 00: 00: 00: 00 on January 1, 2013 to 00: 00: 5 are stored. Is preferred. Further, the sensor data storage means 106 is preferably stored so that information of each sensor data at a specific time point included in a period common to each time-series sensor data can be synchronized. In order to synchronize each time-series sensor data, each time-series sensor data may have information necessary for synchronization, such as a time code, for example. Hereinafter, the sensor data storage unit 106 will mainly be described on the assumption that two types of sensor data for animals and one type of sensor data relating to the external environment are stored. The sensor data storage means 106 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium. The process in which sensor data is stored in the sensor data storage means 106 does not matter. For example, sensor data may be stored in the sensor data storage unit 106 via a recording medium, and sensor data transmitted via a communication line or the like is stored in the sensor data storage unit 106. Alternatively, sensor data input via an input device may be stored in the sensor data storage unit 106. “Two or more types of sensor data” indicates sensor data acquired by two or more types of different sensors.

  The feature amount data acquisition unit 107 acquires two or more types of feature amount data that is time-series data of characteristic values from one type of time-series sensor data stored in the sensor data storage unit 106. The feature data acquisition unit 107 may also acquire external environment feature data that is time-series data of characteristic values from time-series sensor data related to the external environment. For example, as shown in FIG. 4, the feature amount data is data in which sensor data is divided every predetermined period and characteristic values in the divided periods are arranged in time series. The value of the feature amount data may be a maximum value in a predetermined period, a minimum value in a predetermined period, an average value of a waveform in a predetermined period, or a waveform in a predetermined period. May be a characteristic value obtained by Fourier-transforming a waveform in a predetermined period, or may be a value obtained by differentiating a movement amount in a predetermined period with time. It may be a value obtained by differentiating the movement amount in the period twice with respect to time, or may be a value acquired by another algorithm. The feature amount data may be a value associated with the value acquired as described above. For example, the feature amount data acquisition unit 107 may acquire the value of feature amount data corresponding to each value acquired as described above, using a correspondence table stored in a storage unit (not shown). Specifically, the feature amount data acquisition unit 107 may acquire feature amount data related to the volume of a call using a correspondence table that divides the volume into five levels of feature amount data. The feature amount data may be a numerical value obtained by rounding an arbitrary digit from the value acquired as described above. The method of rounding the value may be rounding off, rounding down, or rounding up.

  When two or more types of time-series observation data for the observation target are stored in the sensor data storage unit 106, the feature data acquisition unit 107 stores the observation data stored in the sensor data storage unit 106. Three or more types of feature amount data may be acquired from two or more types of time-series sensor data. When the feature data acquisition unit 107 acquires feature data from two or more types of time-series sensor data, two or more types of feature data are acquired from one type of time-series sensor data. One or more types of feature data may be acquired from each of the time series sensor data other than the time series sensor data. That is, the feature amount data acquisition unit 107 may acquire (M + 1) or more types of feature amount data from M types of time-series sensor data using M types of time-series sensor data. M is a natural number of 1 or more. Therefore, it may be considered that time-series sensor data used for acquiring feature data that is not used for acquiring a state rule or an action rule is not included in M types of time-series sensor data. Hereinafter, the case where two or more types of time-series sensor data are stored in the sensor data storage means 106 will be mainly described.

  The feature amount data acquisition unit 107 may or may not acquire the state feature amount data that is the feature amount data related to the state and the action feature amount data that is the feature amount data related to the action from the sensor data. When two or more types of time-series observation data for the observation target are stored in the sensor data storage unit 106, the feature amount data acquisition unit 107 includes N or more types of state feature amount data and sensor data. , (3-N) or more types of behavior feature data may be acquired. N is 1 or 2. The state feature amount data may be data used to acquire a state rule. The state rule is information including a sequence of feature value data values, labels, and the like regarding the state of the animal. The state rule may be, for example, information indicating a state during a meal, information indicating a state during drinking, information indicating a state during urination, and a state during defecation. It may be information indicating, information indicating a sleeping state, or information indicating other states. Further, the behavior feature amount data may be data used for acquiring a behavior rule. The behavior rule is information composed of a sequence of feature value data, labels, and the like regarding animal behavior. For example, the behavior rule may be information indicating an action whose position is periodically changed, may be information indicating a running action, or may be information indicating an action that makes a cry. For example, it may be information indicating a jumping action. The difference between the state feature amount data and the behavior feature amount data may be that the predetermined period for dividing the sensor data is different in the process of acquiring the feature amount data, and the process for acquiring the feature amount data is different. It may be different, the sensor data for acquiring the feature data may be different, or a combination of two or more of the above differences. The difference in the case where the predetermined period for dividing the sensor data is different is that the predetermined period in the process for acquiring the behavior feature quantity data is shorter than the predetermined period in the process for acquiring the state feature quantity data. good. For example, when the predetermined period in the process of acquiring state feature data is 10 seconds, the predetermined period in the process of acquiring behavior feature data may be 1 second or the like. For example, when the process for acquiring feature data is different, for example, when the process of acquiring state feature data is a process of acquiring an integral value, the process of acquiring action feature data is a differential value. It may be the process of acquiring. The difference in the case where the sensor data for acquiring the feature data is different is that the sensor data used for acquiring the state feature data is different from the sensor data used for acquiring the behavior feature data in advance. It may be. For example, the processing in the feature amount data acquisition unit 107 may be determined in advance, such as acquiring state feature amount data and action feature amount data from a camera and acquiring action feature amount data from a microphone.

  The “two or more types of feature data” may be considered as two or more feature data acquired by different processes. When two pieces of feature amount data acquired by different processes are the same feature amount data, they may be considered as two types of feature amount data or may be considered as one type of feature amount data. The feature amount data acquisition unit 107 can be usually realized by an MPU, a memory, or the like. The processing procedure of the feature data acquisition unit 107 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The state rule acquisition unit 108 acquires a state rule, which is a rule related to the target state, using one or more types of feature amount data acquired by the feature amount data acquisition unit 107. When the feature amount data acquisition unit 107 acquires two or more types of feature amount data from one type of sensor data, the state rule acquisition unit 108 uses at least one type of the two or more types of feature amount data. The state rule may be acquired. When acquiring a state rule from one type of feature quantity data, the state rule acquisition means 108, when two or more consecutive values in the feature quantity data repeatedly appear in a predetermined period, You may acquire the state rule which is the value of quantity data. When the feature quantity data acquisition unit 107 acquires three or more types of feature quantity data from two or more types of time-series sensor data, the state rule acquisition unit 108 includes the three or more types of feature quantity data. The state rule may be acquired using any N or more types of feature amount data. N is 1 or 2 as described above. When acquiring a state rule from two or more types of feature quantity data, the state rule acquisition unit 108 repeats a combination of one or two or more consecutive values in the two or more types of feature quantity data in a predetermined period. When appearing, a state rule that is a combination of consecutive values may be acquired. Further, when the feature amount data acquisition unit 107 acquires state feature amount data, the state rule acquisition unit 108 may acquire the state rule from the state feature amount data as described above.

  Further, the state rule acquisition unit 108 may acquire a state rule for each value of the external environment feature value data or for each classification of the value of the external environment feature value data. “Acquisition of a state rule for each value of external environment feature amount data” means acquisition of a state rule for each value acquired by the feature amount data acquisition means 107. For example, when the sensor data related to the external environment is sensor data related to the temperature, the state rule acquisition unit 108 acquires a state rule when the temperature is 30 degrees and a state rule when the temperature is 31 degrees. Also good. “Acquisition of state rules for each classification of values of external environment feature data” classifies the values acquired by the feature data acquisition means 107 into two or more classifications, and acquires the state rules for each classification. is there. For example, when the sensor data related to the external environment is sensor data related to air temperature, the state rule acquisition unit 108 includes a state rule when the air temperature is 30 degrees or higher and a state rule when the air temperature is 20 degrees or higher and lower than 30 degrees. May be acquired respectively. In addition to the above, the classification of the value of the external environment feature value data may be a classification such as whether it is raining or not when the sensor data related to the external environment is sensor data related to precipitation. When the sensor data related to the environment is sensor data related to voice, it may be classified as a library level, a living sound level, a construction site level, or the like, or other classifications. The state rule acquisition unit 108 can be usually realized by an MPU, a memory, or the like. The processing procedure of the state rule acquisition means 108 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The state rule acquisition unit 108 may acquire a state rule by adding a label to the feature amount data by the processing of the state label setting unit 21 and the state rule specifying unit 22. Note that the feature amount data referred to here may be state feature amount data. As shown in FIG. 5, the state label setting means 21 classifies the feature value data values into a plurality of groups, and sets the same state label to the feature value data values belonging to the same group. The state label setting means 21 may set a state label for any N or more types of feature amount data among three or more types of feature amount data. N is 1 or 2 as described above. There is no limitation on the criteria by which the state label setting means 21 classifies the value of the feature data. For example, the state label setting unit 21 may classify each feature value data value into a group, or may classify feature value data values into groups for each predetermined value range. The value of the feature amount data may be classified into groups according to the above. The rule determined in advance may be a rule for classifying into groups of even feature value data values and odd feature value data values. Or a rule for classifying them into groups. The status label is information that can identify the classified group. That is, the status label may be any information as long as it is information that can uniquely identify the group. By using the state label, a plurality of feature value data values can be set as one label, and information can be rounded rather than using feature value data values. That is, setting the state label facilitates discovery of the state rule.

  Note that the state label setting unit 21 may group two or more continuous feature value data values into one group. The state label setting means 21 may set one state label for two or more consecutive feature value data values when two or more consecutive feature value data values are grouped into a group. Specifically, the state label setting means 21 reads “value of feature quantity data indicating activity / value of feature quantity data indicating suspension / value of feature quantity data indicating suspension / feature data indicating activity”. Feature values such as “value of feature data indicating activity / value of feature data indicating stop / value of feature data indicating activity” Data values may be summarized. When the values of the feature amount data are collected, for example, in the above-described case, the state label setting unit 21 can set a label so as not to stick to the stopped period.

  For example, the state rule specifying unit 22 obtains a state rule from an array of N or more types of state labels set by the state label setting unit 21 as shown in FIG. When acquiring a state rule from a sequence of one type of state label, the state rule specifying unit 22 determines that when two or more continuous state labels in the state label sequence repeatedly appear in a predetermined period, A state rule that is a state label may be acquired. When acquiring a state rule from a sequence of two or more types of state labels, the state rule specifying unit 22 determines that a combination of one or two or more continuous state labels in the sequence of two or more types of state labels is predetermined. When it repeatedly appears in the period, a state rule that is a combination of the continuous state labels may be acquired. For example, the state rule specifying unit 22 may acquire the state rule by dividing the arrangement of the state labels into a plurality of periods and performing frequent pattern mining. The state rule may be acquired by changing multiple times and performing frequent pattern mining in the same manner. In addition, since frequent pattern mining is a well-known technique, it abbreviate | omits about the detailed description.

  The behavior rule acquisition unit 109 uses the one or more types of feature amount data acquired by the feature amount data acquisition unit 107 to acquire an action rule that is a rule related to the target behavior. When the feature data acquisition unit 107 acquires two or more types of feature data from one type of sensor data, the behavior rule acquisition unit 109 uses at least one or more of the two or more types of feature data. You may get the rules of action. When acquiring a behavior rule from one type of feature value data, the behavior rule acquisition unit 109 causes the continuous feature to appear when two or more consecutive values in the feature value data repeatedly appear in a predetermined period. You may acquire the action rule which is the value of quantity data. Note that when the feature quantity data acquisition unit 107 acquires three or more types of feature quantity data from two or more types of time-series sensor data, the behavior rule acquisition unit 109 includes the three or more types of feature quantity data. The action rule may be acquired using any (3-N) or more feature quantity data. N is 1 or 2 as described above. When acquiring a behavior rule from two or more types of feature data, the behavior rule acquisition unit 109 repeats a combination of one or two or more consecutive values in the two or more types of feature data in a predetermined period. When appearing, you may acquire the action rule which is the combination of the continuous value. Further, when the feature amount data acquisition unit 107 acquires behavior feature amount data, the behavior rule acquisition unit 109 may acquire a behavior rule from the behavior feature amount data. The behavior rule acquisition unit 109 may acquire the behavior rule by using all the feature amount data not used by the state rule acquisition unit 108 among the feature amount data acquired by the feature amount data acquisition unit 107. The action rule may be acquired using one or more feature quantity data at least partly different from the type of feature quantity data used by the means 108, and the action rule using one or more feature quantity data satisfying both of the above. You may get That is, the state rule acquisition unit 108 and the behavior rule acquisition unit 109 perform processing so that all feature amount data acquired by the feature amount data acquisition unit 107 is used to acquire either the state rule or the behavior rule. May be performed. Further, the behavior rule may be a rule within a period in which the state rule is acquired. That is, if the state rule acquisition unit 108 has acquired the state rule of the period x from the time point t to the time point (t + x), the behavior rule acquisition unit 109 determines that the period x from the time point t to the time point (t + x). You may obtain less action rules. Note that x is an arbitrary period.

  Further, the behavior rule acquisition unit 109 may acquire a behavior rule for each value of the external environment feature value data or for each classification of the value of the external environment feature value data. “Acquiring an action rule for each value of the external environment feature value data” means acquiring an action rule for each value acquired by the feature value data acquisition unit 107. For example, when the sensor data related to the external environment is sensor data related to the temperature, the behavior rule acquisition unit 109 acquires the behavior rule when the temperature is 30 degrees and the behavior rule when the temperature is 31 degrees, respectively. Also good. “Acquire action rules for each classification of values of external environment feature data” classifies the values acquired by the feature data acquisition means 107 into two or more classifications, and acquires the behavior rules for each classification. is there. For example, when the sensor data related to the external environment is sensor data related to the temperature, the behavior rule acquisition unit 109 includes a behavior rule when the temperature is 30 degrees or more and a behavior rule when the temperature is 20 degrees or more and less than 30 degrees. May be acquired respectively. In addition to the above, the classification of the value of the external environment feature value data may be a classification such as whether it is raining or not when the sensor data related to the external environment is sensor data related to precipitation. When the sensor data related to the environment is sensor data related to voice, it may be classified as a library level, a living sound level, a construction site level, or the like, or other classifications. The behavior rule acquisition unit 109 can be usually realized by an MPU, a memory, or the like. The processing procedure of the behavior rule acquisition unit 109 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The behavior rule acquisition unit 109 may acquire a behavior rule by assigning a label to the feature amount data by the processing of the behavior label setting unit 23 and the behavior rule specifying unit 24. Note that the feature amount data referred to here may be behavior feature amount data. As shown in FIG. 5, the action label setting unit 23 classifies the feature value data values into a plurality of groups, and sets the same action label to the feature value data values belonging to the same group. The action label setting means 23 may set an action label for any (3-N) or more types of feature quantity data among three or more types of feature quantity data. N is 1 or 2 as described above. There is no limitation on the criteria by which the action label setting unit 23 classifies the value of the feature amount data. For example, the action label setting unit 23 may classify the feature value data into groups, or may classify the feature value data values into groups for each predetermined value range. The value of the feature amount data may be classified into groups according to the above. The rule determined in advance may be a rule for classifying into groups of even feature value data values and odd feature value data values. Or a rule for classifying them into groups. The action label is information that can identify the classified group. That is, the action label may be any information as long as the information can uniquely identify the group. By using the action label, a plurality of feature value data values can be set as one label, and information can be rounded rather than using the feature value data value. In other words, setting action labels facilitates discovery of action rules.

  Note that the action label setting means 23 may group two or more consecutive feature value data values into one group. The action label setting means 23 may set one action label to the values of two or more consecutive feature quantity data when the values of two or more consecutive feature quantity data are grouped into a group. Specifically, the action label setting unit 23 determines that “the value of feature data indicating a running action, the value of feature data indicating a walking action, the value of feature data indicating a walking action, The value of the feature value data such as “value of feature value data indicating the action being performed” is the value of the feature value data indicating the action being performed, the value of the feature value data indicating the action being performed, and the running. The value of feature amount data may be collected as “value of feature amount data indicating behavior”. Summarizing the values of the feature amount data, for example, in the case described above, the action label setting unit 23 can set a label so as not to stick to the walking period.

  For example, the behavior rule specifying unit 24 acquires a behavior rule from a sequence of (3-N) types of behavior labels set by the behavior label setting unit 23 as illustrated in FIG. 6. N is 1 or 2 as described above. When acquiring a behavior rule from a sequence of one type of behavior label, the behavior rule specifying means 24, when two or more consecutive behavior labels in the sequence of the behavior label repeatedly appear in a predetermined period, You may acquire the action rule which is an action label. In addition, when obtaining a behavior rule from a sequence of two or more types of behavior labels, the behavior rule specifying unit 24 determines that a combination of one or two or more consecutive behavior labels in the sequence of the two or more types of behavior labels is predetermined. When it repeatedly appears in the period, an action rule that is a combination of consecutive action labels may be acquired. For example, the behavior rule specifying unit 24 may acquire the behavior rule by dividing the sequence of behavior labels into a plurality of periods and performing frequent pattern mining. The behavior rule may be acquired by changing multiple times and performing frequent pattern mining in the same manner.

  The animal abnormality information accumulating unit 110 includes one or more types of observation data that are state rules acquired by the state rule acquisition unit 108 and one or more types of observation data that are action rules acquired by the behavior rule acquisition unit 109. The animal abnormality information storage unit 101 stores animal abnormality information including animal observation data including the above and animal individual information associated with the sensor data used to acquire the observation data. Further, the animal abnormality information storage unit 110 may accumulate animal abnormality information including each external environment feature amount data or the classification of the value of the external environment feature amount data in the animal abnormality information storage unit 101. When the animal abnormality information identifying unit 104 identifies the animal abnormality information accumulated by the animal abnormality information accumulating unit 110, the retrieved animal observation data received by the retrieval observation data receiving unit 102 is one or more waveform data, or 2 This is the above-described feature amount data, or an array of labels in which two or more feature amounts are classified. The animal abnormality information accumulating means 110 can be usually realized by an MPU, a memory or the like. The processing procedure of the animal abnormality information accumulating means 110 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  FIG. 7 is a flowchart showing an example of the operation of the animal abnormality detection device 1 in the present embodiment. Hereinafter, the operation will be described with reference to FIG. In this flowchart, a case where two or more types of sensor data for the observation target are stored in the sensor data storage unit 106 will be described.

  (Step S201) The search observation data receiving means 102 determines whether or not the search animal observation data, the search animal individual information, and the search environment observation data have been received. If received, the process proceeds to step S202. If not received, the process proceeds to step S206.

  (Step S202) The animal abnormality information specifying unit 104 searches for animal abnormality information corresponding to the retrieved animal observation data received in step S201.

  (Step S203) The abnormality information transmitting means 105 determines whether or not there is animal abnormality information corresponding to the searched animal observation data received in Step S201 as a result of searching in Step S202. If there is corresponding animal abnormality information, the process proceeds to step S204. If there is no corresponding animal abnormality information, the process returns to step S201.

  (Step S204) The abnormality information transmitting means 105 transmits the abnormality information specified as a result of searching in Step S202 to the terminal that has transmitted the search animal observation data received in Step S201.

  (Step S205) The abnormality information transmitting unit 105 transmits the abnormality information identified as a result of the search in Step S202 to the specialist's terminal device 3. Then, the process returns to step S201.

  (Step S206) It is determined whether or not sensor data is stored in the sensor data storage means 106. If sensor data is stored, the process proceeds to step S207, and if not stored, the process returns to step S201.

  (Step S207) The feature amount data acquisition unit 107 acquires three or more types of feature amount data from the two types of sensor data stored in the sensor data storage unit 106.

  (Step S <b> 208) The feature data acquisition unit 107 acquires external environment feature data from sensor data related to the external environment stored in the sensor data storage unit 106.

  (Step S209) The state label setting means 21 classifies the feature amount data acquired in step S207 into groups for each value of the feature amount data, and sets a state label for each classified group.

  (Step S210) The state rule specifying means 22 specifies a state rule for each value of the external environment feature quantity data from the arrangement of the state labels set in step S209.

  (Step S211) The action label setting unit 23 classifies the feature amount data acquired in step S207 into groups for each value of the feature amount data, and sets an action label for each classified group.

  (Step S212) The behavior rule specifying means 24 specifies a behavior rule for each value of the external environment feature value data from the sequence of behavior labels set in step S211.

  (Step S213) The animal abnormality information accumulating means 110 corresponds to the animal observation data including the state rule specified in Step S210 and the behavior rule specified in Step S212, and the sensor data used when acquiring the animal observation data. Animal abnormality information including the attached animal individual information and the classification of the value of the external environment feature value data is accumulated in the animal abnormality information storage means 101. The animal abnormality information accumulating unit 110 deletes the sensor data used when acquiring the animal observation data included in the accumulated animal abnormality information from the sensor data storage unit 106. Then, the process returns to step S201.

  Hereinafter, a specific operation of the animal abnormality detection device 1 in the present embodiment will be described. In addition, the information of each drawing shown in this specific example is prepared for convenience of explanation, and does not indicate actual data. In this specific example, it is assumed that the animal abnormality information is stored in the animal abnormality information storage unit 101 by performing the processing from step S206 to step S213 in the flowchart.

  In this specific example, it is assumed that the animal abnormality information storage unit 101 stores the table shown in FIG. The table of FIG. 8 includes animal abnormality information ID, observation data, observation data regarding the external environment, animal abnormality detection information, animal individual information, and diagnosis information. For example, the animal abnormality information ID “1” includes observation data “[state rule: a1 a2 a1] [behavior rule: b1 b3 b2] [behavior rule: c3 c1 c1]” and observation data “D3” regarding the external environment. The animal abnormality detection information “periodically stops moving”, the animal individual information “[type: dog] [age: 6 years old] [sex: female]”, and diagnostic information “fever” are registered. In this specific example, it is assumed that the observation data is a rule acquired by the state rule acquisition unit 108 and the behavior rule acquisition unit 109. In this specific example, the observation data related to the external environment is assumed to be a classification of values of the external environment feature value data acquired by the feature value data acquisition unit 107.

  In this specific example, it is assumed that the animal type information storage means 103 stores the table shown in FIG. The table in FIG. 9 has a type name and a corresponding type name. For example, as the first information, a type name “squirrel” and a corresponding type name “chipmunk” are registered. This is information for the animal abnormality information specifying means 104 to handle “squirrel” and “chipmunk” as the matching animal type.

  The user feels abnormalities in the squirrel that has stopped moving in the cage, and captures data relating to the appearance of the squirrel from the camera and microphone, and data relating to the external environment from the thermometer to the user's terminal device 2. It is assumed that the user clicks the send button on the search animal observation data transmission screen. The user's terminal device 2 includes search animal observation data including observation data of two types of waveforms of video and audio, search environment observation data of a waveform related to temperature, and search animal individual information “[type: squirrel” registered in advance. ] [Age: 4 years old] [Gender: Male] "in association with each other. Then, the search animal observation data transmitted from the user's terminal device 2 is received by the search observation data receiving means 102 (step S201).

  The animal abnormality information specifying unit 104 uses the observation data of each waveform received by the search observation data receiving unit 102 as the feature amount data acquiring unit 107, the state label setting unit 21 included in the state rule acquiring unit 108, and the behavior rule acquiring unit. The action label setting means 23 included in 109 converts the label arrangement. At this time, the animal observation data received by the search observation data receiving means 102 is “[state rule: a1 a1 a3 a2 a1 a3 a1 a3 a2] [behavior rule: b1 b1 b1 b1 b1 b1 b1 b1 b1] [behavior rule: c4 c1 c4 c1 c4 c1 c4 c1] ”, and the environment observation data is converted to“ D2 D2 D2 ”. The animal abnormality information specifying means 104 searches for the converted observation data and animal abnormality information corresponding to the searched animal individual information. First, the animal abnormality information specifying unit 104 determines that the animal abnormality information ID “1” does not correspond because the searched animal individual information and the animal individual information do not match at all. Next, the animal abnormality information identification unit 104 determines the animal abnormality information ID “2”. The type of the animal individual information of the animal abnormality information ID “2” is “chipmunk” and is different from the type “squirrel” included in the searched animal individual information. However, “squirrel” and “chipmunk” are registered as corresponding type names in the animal type information storage unit 103. Therefore, the animal abnormality information specifying unit 104 determines that the type included in the searched animal individual information matches the type of the animal individual information with the animal abnormality information ID “2”. The age of the animal individual information with the animal abnormality information ID “2” is “3 years old”, which is different from the age “4 years old” included in the searched animal individual information. However, the difference between “4 years old” and “3 years old” is 1 year old, which can be regarded as an error range. Therefore, the animal abnormality information specifying unit 104 determines that the age included in the searched animal individual information matches the age of the animal individual information of the animal abnormality information ID “2”. Further, the animal abnormality information specifying unit 104 determines that the sex included in the searched animal individual information and the sex of the animal individual information of the object abnormality information ID “2” are the same “male”, and therefore match. . Then, the animal abnormality information specifying unit 104 includes each observation data of the object abnormality information ID “2” included in the search animal observation data, and observation data related to the external environment is also included in the search environment observation data. The information ID “2” is identified as the corresponding animal abnormality information (step S202).

  The abnormality information transmission means 105 sends the animal abnormality detection information “no motion” of the same part abnormality information ID “2” specified by the animal abnormality information specification means 104 and the diagnosis information “bone fracture” to the user terminal device 2. Transmit (step S203 to step S204). Then, it is displayed on the user terminal device 2 as shown in FIG. Then, the abnormality information transmitting unit 105 includes the animal abnormality detection information “no motion” of the same value abnormality information ID “2”, the diagnosis information “fracture”, the animal observation data received by the search observation data receiving unit 102, and The environmental observation data and the searched animal individual information are transmitted to the terminal device 3 of the specialist (step S205). Then, on the terminal device 3 of the specialist, search animal observation data, search animal individual information, search environment observation data, and the like are displayed.

  Hereinafter, when the sensor data storage means 106 stores sensor data that is a moving image of a squirrel captured in a camera in an abnormal state and animal solid information of the squirrel, the animal abnormality information storage means A process for accumulating animal abnormality information in 101 will be specifically described. In this specific example, it is assumed that the camera is arranged so that all the inside of the cage can be photographed from the upper part of the squirrel cage. The feature amount data acquisition unit 107 performs background difference processing from sensor data that is a moving image, thereby obtaining feature amount data “A, B, C, C, C, C, A... Assume that the feature amount data “Z, Z, Y, Z, Z, X, Y. In this specific example, “C, C, C, C” periodically appears in the feature amount data relating to the position of the squirrel, and in the same period as “C, C, C, C”, It is assumed that “Z, Z, X” appears periodically in the feature amount data regarding the posture. Here, “C” is a feature value data value indicating the position of the toilet, “Z” is a feature value data value indicating that it is lying down, and “X” is a look around. It is assumed that the value is feature value data indicating The state rule acquisition unit 108 acquires the state rule “C, C, C, C” from the feature amount data regarding the position of the squirrel. Then, the behavior rule acquisition unit 109 acquires the behavior rule “Z, Z, X” corresponding to the state rule “C, C, C, C”. Then, the animal abnormality information accumulating unit 110 includes animal abnormality information including animal observation data including the acquired state rules and behavior rules, and animal individual information corresponding to the sensor data used to acquire the respective rules. And is stored in the animal abnormality information storage means 101. Note that the state rule “C, C, C, C” output in this specific example indicates staying in the toilet, and the action rule “Z, Z, X” Suppose that you are looking around.

  Further, in the sensor data storage means 106, sensor data that is a moving image obtained by photographing a squirrel in an abnormal state with a camera, sensor data that is a sound collected by a microphone from a squeak generated by the squirrel, and The processing for accumulating animal abnormality information in the animal abnormality information storage means 101 will be specifically described in the case where animal solid information of squirrels is stored. In addition, in this specific example, the description which overlaps with the specific example demonstrated previously may be abbreviate | omitted. In this specific example, it is assumed that the microphone is arranged in the immediate vicinity of the squirrel cage. The feature amount data acquisition unit 107 performs background difference processing from sensor data that is a moving image, thereby obtaining feature amount data “A, B, C, C, C, C, A... The feature amount data “Z, Z, Y, Z, Z, X, Y...” Regarding the squirrel posture is acquired, and the feature amount data “0, "0, 0, 0, 0, 1, 0 ..." is acquired (step S207). In this specific example, it is assumed that “0, 0, 1” also appears periodically during the period in which “Z, Z, X” appears in the period in which “C, C, C, C” appears. . Here, “0” is a value of feature amount data indicating that no cry is raised, and “1” is a value of feature amount data indicating that a cry is raised. The state rule acquisition unit 108 acquires the state rule “C, C, C, C” from the feature amount data relating to the position of the squirrel (step S209 to step S210). Then, the behavior rule acquisition unit 109 acquires a behavior rule [“Z, Z, X” “0, 0, 1”] corresponding to the state rule “C, C, C, C” (from step S211 to step S212). ). Then, the animal abnormality information accumulating unit 110 includes animal abnormality information including animal observation data including the acquired state rules and behavior rules, and animal individual information corresponding to the sensor data used to acquire the respective rules. Are accumulated in the animal abnormality information storage means 101 (step S213). In addition, the state rule “CCCC” output in this specific example indicates staying in the toilet, and the action rule [“Z, Z, X” “0, 0, 1”] Let ’s say you ’re looking around and making a cry.

  In the present embodiment, the animal abnormality information specifying unit 104 can specify the animal abnormality information corresponding to the search observation data and the search animal individual information transmitted from the user terminal device 2. Thereby, abnormality of many kinds of animals can be detected. In addition, the user can obtain a guideline for determining whether or not there is an abnormality in the state of the animal without the intervention of a specialist. In the present embodiment, since the animal type information is stored in the animal type information storage means 103, one animal abnormality information can be applied to a plurality of similar animals. Thereby, even if it is a minor animal with which it is hard to collect animal abnormality information, if there is animal abnormality information of a similar animal, the abnormality of the minor animal can be detected. In this embodiment, when the environmental observation data is stored in the animal abnormality information storage unit 101, the animal abnormality information identification unit 104 takes into account the observation data related to the external environment from the user terminal device 2. Animal abnormality information corresponding to the observation data sent can be identified. Thereby, it becomes possible to search the animal abnormality information with high accuracy. In this embodiment, when the animal abnormality detection information is stored in the animal abnormality information storage unit 101, the abnormality information transmission unit 105 can transmit information including the animal abnormality detection information. Thereby, the user can obtain information about abnormality. In this embodiment, when diagnostic information is stored in the animal abnormality information storage unit 101, the abnormality information transmission unit 105 can transmit diagnostic information for similar cases in the past. As a result, the user can virtually receive a medical examination from a specialist. Further, in the present embodiment, the search observation data receiving means 102 can receive search animal observation data and the like for a certain period from the time when the user feels abnormal. As a result, even if the user does not always turn on the device, the user can turn on the power only when necessary and perform an operation. In the present embodiment, the abnormality information transmitting unit 105 also transmits abnormality information to the specialist's terminal device. Thereby, when an abnormality is detected, it is possible to notify a specialist immediately. In the present embodiment, the animal abnormality information accumulating unit 110 can accumulate animal abnormality information converted from sensor data into feature amount data. Thereby, the amount of data stored in the animal abnormality information storage unit 101 can be compressed, and the search efficiency of the animal abnormality information identification unit 104 can be increased.

  In this embodiment, the case where the sensor data storage unit 106, the feature amount data acquisition unit 107, the state rule acquisition unit 108, the behavior rule acquisition unit 109, and the animal abnormality information storage unit 110 are provided has been described. The detection apparatus 1 may not include the sensor data storage unit 106, the feature amount data acquisition unit 107, the state rule acquisition unit 108, the behavior rule acquisition unit 109, and the animal abnormality information storage unit 110. If the sensor data storage unit 106, the feature amount data acquisition unit 107, the state rule acquisition unit 108, the behavior rule acquisition unit 109, and the animal abnormality information storage unit 110 are not provided, the animal abnormality information storage unit 101 includes Animal abnormality information may be accumulated via storage means, communication lines, etc.

  In the present embodiment, the case where the state rule acquisition unit 108 and the behavior rule acquisition unit 109 are provided has been described. However, the animal abnormality detection apparatus 1 includes the state rule acquisition unit 108 and the behavior rule acquisition unit 109. It is not necessary. When the state rule acquisition unit 108 and the behavior rule acquisition unit 109 are not provided, the search observation data reception unit 102 receives each observation data that is waveform data or feature amount data.

  In the present embodiment, the case where the feature amount data acquisition unit 107 is provided has been described. However, the animal abnormality detection device 1 may not include the feature amount data acquisition unit 107. When the feature data acquisition unit 107 is not provided, the search observation data reception unit 102 receives each observation data that is waveform data.

  In the present embodiment, the case has been described in which the feature amount data acquisition unit 107 acquires external environment feature amount data. However, the feature amount data acquisition unit 107 does not have to acquire external environment feature amount data. . If the feature data acquisition unit 107 does not acquire external environment feature data, the sensor data storage unit 106 may not store sensor data related to the external environment. The means 109 may acquire each rule only from the feature amount data.

  In the present embodiment, the case where the state label setting unit 21 and the state rule specifying unit 22 are included has been described. However, the animal abnormality detection device 1 does not include the state label setting unit 21 and the state rule specifying unit 22. May be. When the state label setting unit 21 and the state rule specifying unit 22 are not included, the state rule acquisition unit 108 may acquire the state rule without setting a label from the feature amount data.

  Although the case where the action label setting means 23 and the action rule specifying means 24 are included has been described, the animal abnormality detection device 1 may not include the action label setting means 23 and the action rule specifying means 24. When the behavior label setting unit 23 and the behavior rule specifying unit 24 are not included, the behavior rule acquisition unit 109 may acquire the behavior rule without setting a label from the feature amount data.

  Moreover, the software which implement | achieves the animal abnormality detection apparatus 1 in this Embodiment is the following programs. In other words, the program stores in the animal abnormality information storage means for storing animal abnormality information including animal observation data including one or more observation data of time series of animals and animal individual information that is information related to the attributes of the animals. A search observation data receiving means and a search observation data receiving means for receiving search animal observation data including one or more observation data of time series of animals and search animal individual information relating to attributes of individual animals. When the animal abnormality information identifying means for identifying the animal abnormality information including the animal observation data and the animal individual information corresponding to the received retrieved animal observation data and the retrieved animal individual information, the animal abnormality information identifying means identifies the animal abnormality information. And a program for functioning as abnormality information transmitting means for transmitting abnormality information that is information relating to abnormality.

  In the present embodiment, each process (each function) may be realized by centralized processing by a single device (system), or by distributed processing by a plurality of devices. May be. In the present embodiment, it goes without saying that two or more communication means existing in one apparatus may be physically realized by one means.

  In the present embodiment, each component may be configured by dedicated hardware, or a component that can be realized by software may be realized by executing a program. For example, each component can be realized by a program execution unit such as a CPU reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

  In the program, the functions realized by the program do not include functions that can be realized only by hardware. For example, functions that can be realized only by hardware such as a modem and an interface card in an acquisition unit that acquires information, an output unit that outputs information, and the like are not included in the functions realized by the program.

  FIG. 11 is a schematic diagram showing an example of the external appearance of a computer that executes the program and implements the present invention according to the embodiment. The embodiment described above can be realized by computer hardware and a computer program executed on the computer hardware.

  In FIG. 11, a computer system 1100 includes a computer 1101 including a CD-ROM drive 1105 and an FD drive 1106, a keyboard 1102, a mouse 1103, and a monitor 1104.

  FIG. 12 is a diagram showing an internal configuration of the computer system 1100. In FIG. 12, in addition to the CD-ROM drive 1105 and the FD drive 1106, a computer 1101 is connected to an MPU 1111, a ROM 1112 for storing a program such as a boot-up program, and an MPU 1111 to temporarily issue instructions of an application program And a hard disk 1114 for accumulating application programs, system programs, and data, an MPU 1111, a ROM 1112, and a bus 1115 for interconnecting the ROM 1112 and the like. The computer 1101 may include a network card (not shown) that provides connection to the LAN.

  A program for causing the computer system 1100 to execute the functions of the present invention according to the above-described embodiment is stored in the CD-ROM 1121 or the FD 1122, inserted into the CD-ROM drive 1105 or the FD drive 1106, and transferred to the hard disk 1114. May be. Instead, the program may be transmitted to the computer 1101 via a network (not shown) and stored in the hard disk 1114. The program is loaded into the RAM 1113 when executed. The program may be loaded directly from the CD-ROM 1121, the FD 1122, or the network.

  The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 1101 to execute the functions of the present invention according to the above-described embodiment. The program may include only a part of an instruction that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 1100 operates is well known and will not be described in detail.

  The present invention is not limited to the above-described embodiments, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention. Further, “means” of each means in the present invention may be read as “part” or “circuit”.

  As described above, the animal abnormality detection device and the like according to the present invention have an effect of detecting abnormalities in many types of animals and are useful as animal abnormality detection devices and the like.

DESCRIPTION OF SYMBOLS 1 Animal abnormality detection apparatus 101 Animal abnormality information storage means 102 Search observation data reception means 103 Animal classification information storage means 104 Animal abnormality information specification means 105 Abnormality information transmission means 106 Sensor data storage means 107 Feature quantity data acquisition means 108 State rule acquisition means 109 Action rule acquisition means 110 Animal abnormality information storage means 21 State label setting means 22 State rule specifying means 23 Action label setting means 24 Action rule specifying means

Claims (11)

Animal abnormality information storage means storing animal abnormality information including animal observation data including one or more observation data of time series of animals, and diagnostic information indicating diagnosis results corresponding to the animal observation data;
Search observation data receiving means for receiving search animal observation data including one or more observation data of time series of animals,
Animal abnormality information specifying means for specifying animal abnormality information including animal observation data corresponding to the search animal observation data received by the search observation data receiving means;
When the animal abnormality information specifying means specifies animal abnormality information, the abnormality information transmitting means transmits abnormality information that is abnormality information that is information relating to the abnormality and includes the diagnosis information corresponding to the specified animal abnormality information. When,
An animal abnormality detection device comprising: Animal type information storage means for storing one or more animal type information indicating the types of similar animals;
Search observation data receiving means for receiving search animal observation data including one or more observation data of time series of animals, and the animal type information;
Animal abnormality information for specifying animal abnormality information including animal observation data corresponding to the search animal observation data received by the search observation data receiving means or animal observation data corresponding to the animal type similar to the animal type information Specific means,
When the animal abnormality information specifying means specifies animal abnormality information, abnormality information transmitting means for transmitting abnormality information that is information relating to the abnormality,
An animal abnormality detection device comprising: Animals abnormality information storing means for animals abnormality information including one or more observations of the time series of the animal is stored,
Animals abnormality detection device according to claim 2 having a. Before Symbol animals abnormality information further comprises one or more observation data indicating the action rule is rules for one or more observations and animal behavior indicates that state rule is rule about the state of the animal,
The animal abnormality detection apparatus as described in any one of Claims 1-3 . Using the feature amount data is time-series data of feature specific value obtained from the sensor data is one or more time-series data, and state rule obtaining means for obtaining a state rule is rules for animal's condition ,
Using pre Symbol feature data, further comprising the action rule obtaining means for obtaining the action rule is rule regarding animal behavior,
The animal abnormality detection apparatus as described in any one of Claims 1-4 . Before Symbol animals abnormality information also includes the environmental monitoring data are observation data relating to animal observation data at the same timing of the external environment included in the animal abnormality information,
Prior Symbol Search observation data receiving means, wherein the search animal observation data, a search animal information about the attributes of an animal individual, and a search environment observation data is observed data about the external environment of the search animal observation data at the same time It received,
Before SL Animals abnormality information specifying means includes the search observation data receiving means and the search animal observation data received search individual animal information retrieval animal observations and animal information corresponding to the environmental monitoring data and the environmental monitoring data Identify animal anomaly information ,
The animal abnormality detection device according to any one of claims 1 to 5 . Before Symbol animals abnormality information includes an animal anomaly detection information indicating abnormality of the contents corresponding to the animal observation data included in the animal abnormality information,
Before SL abnormality information transmitting means transmits abnormality information including animal anomaly detection information is the animal abnormality information specifying means is included in the animal abnormality information identified,
The animal abnormality detection device according to any one of claims 1 to 6 . Animal abnormality information storage means storing animal abnormality information including animal observation data including one or more observation data of time series of animals and diagnosis information indicating diagnosis results corresponding to the animal observation data, and search observation data An animal abnormality detection method processed using a receiving means, an animal abnormality information specifying means, and an abnormality information transmitting means ,
Previous Symbol Search observation data receiving unit, a retrieval observation data receiving step of receiving a search animal observation data comprising one or more observations of the time series of animals,
Previous SL animals abnormality information specifying means, and animals abnormality information specifying step of specifying an animal abnormality information containing animal observation data corresponding to the search animal observation data the retrieval observation data receiving step receives,
Previous SL abnormality information transmitting unit, when identifying the animal abnormality information in said animal anomaly information specifying step, an abnormality information which is information related to abnormal, abnormality including the diagnostic information corresponding to the identified animal abnormality information an abnormality information transmitting step of transmitting information,
Animal abnormality detection method comprising a. Computer capable of accessing animal abnormality information storage means storing animal abnormality information including animal observation data including one or more time-series observation data of animals and diagnosis information indicating diagnosis results corresponding to the animal observation data the,
A search observation data receiving means for receiving a search animal observation data comprising one or more observations of the time series of animals,
And animal abnormality information specifying unit that is pre-Symbol Search observation data receiving means to identify the animal abnormality information containing animal observation data corresponding to the search animal observation data received,
If the previous SL animals abnormality information specifying means has specified the animals abnormality information, an abnormality information which is information related to abnormal, the abnormality information transmission for transmitting anomaly information including the diagnostic information corresponding to the identified animal abnormality information Means ,
Program to function as a. Animal type information storage means for storing one or more animal type information indicating the types of similar animals;
An animal abnormality detection method processed using search observation data reception means, animal abnormality information identification means, and abnormality information transmission means,
The search observation data receiving means receives search animal observation data including one or more observation data of time series of animals, and the search observation data reception step means for receiving the animal type information,
An animal abnormality including animal observation data corresponding to the animal observation data corresponding to the search animal observation data received in the search observation data receiving step or animal observation data corresponding to the similar animal type in the animal type information. An animal abnormality information identification step for identifying information;
Anomaly information transmitting means, when the animal anomaly information specifying means identifies animal anomaly information, anomaly information transmitting step for transmitting anomaly information that is information relating to anomalies;
An animal abnormality detection method comprising: A computer accessible to animal type information storage means for storing one or more animal type information indicating the type of similar animals;
Search observation data receiving means for receiving search animal observation data including one or more observation data of time series of animals, and the animal type information;
Animal abnormality information for specifying animal abnormality information including animal observation data corresponding to the search animal observation data received by the search observation data receiving means or animal observation data corresponding to the animal type similar to the animal type information Specific means,
When the animal abnormality information specifying means specifies animal abnormality information, abnormality information transmitting means for transmitting abnormality information that is information relating to the abnormality,
Program to function as.

Images