Information processing device, information processing method, learning device, learning method, and computer-readable recording medium

Abstract

This information processing device comprises: an acquisition unit that acquires first biological information from a sensor worn by a target animal performing an activity together with a human; and an emotion estimation unit that receives input of the first biological information and first person identification information for identifying a person performing an activity together with the target animal, and estimates the emotion of the target animal.

Description

Information processing device, information processing method, learning device, learning method, and computer-readable recording medium

[0001] The present disclosure relates to an information processing device, an information processing method, a learning device, a learning method, and a computer-readable recording medium that estimates the emotions of an animal.

[0002] Currently, communication between humans and animals that work alongside them is based on commands given by humans to the animals and the animals' behavior (their work in response to the commands), but from the perspective of mutual understanding, further improvements in communication are required.

[0003] As a related technique, Patent Document 1 discloses a notification control system that appropriately notifies notification recipients according to the emotions of a pet. The notification control system in Patent Document 1 analyzes the emotions of an animal based on at least one of animal information that indicates the emotion of the animal, such as the animal's voice, body movement, and biological information.

[0004] As a related technology, Patent Document 2 discloses an animal intention determination system that automatically and highly accurately determines the intention of an animal without requiring any particular skill or experience. According to the animal intention determination system of Patent Document 2, the intention of the target animal is determined by using biometric information detected from the target animal and referring to the degree of correlation between reference biometric information detected in advance from each animal and the animal's intention.

[0005] JP 2019-091233 A JP 2022-101297 A

[0006] The systems disclosed in Patent Documents 1 and 2 simply determine the emotions and intentions of animals. However, the systems disclosed in Patent Documents 1 and 2 do not improve communication between humans and animals that interact with the humans. In particular, they do not improve communication between humans and animals to enable animals to work more efficiently.

[0007] One example of a purpose of the present disclosure is to improve communication with animals that interact with humans.

[0008] In order to achieve the above object, an information processing device according to one aspect of the present disclosure is characterized by having an acquisition unit that acquires first biometric information from a sensor worn by a target animal that is active together with a human; and an emotion estimation unit that receives input of first person identification information that identifies a person that is active together with the target animal and the first biometric information and estimates the emotion of the target animal.

[0009] In addition, in order to achieve the above object, an information processing method according to one aspect of the present disclosure is characterized in that an information processing device acquires first biometric information from a sensor worn by a target animal that is active together with a human, inputs first person identification information that identifies a person that is active together with the target animal and the first biometric information, and estimates the emotion of the target animal.

[0010] In addition, in order to achieve the above object, a computer-readable recording medium having a program recorded thereon according to one aspect of the present disclosure is characterized in that it causes a computer to execute a process of acquiring first biometric information from a sensor worn by a target animal that is active together with a human, inputting first person identification information that identifies a person that is active together with the target animal and the first biometric information, and estimating the emotions of the target animal.

[0011] In addition, in order to achieve the above object, a learning device according to one aspect of the present disclosure is characterized by having a learning unit that inputs learning data in which pre-registered person identification information for identifying a person, animal identification information for identifying an animal, biometric information of the animal, and emotional information representing the emotion of the animal are associated, and learns a learning model for estimating the emotion of the animal.

[0012] In addition, in order to achieve the above object, a learning method according to one aspect of the present disclosure is characterized in that a learning device inputs learning data having person identification information for identifying a person who has been registered in advance, animal identification information for identifying an animal who has been recorded in advance, biometric information of the animal, and emotion information representing the emotion of the animal, and learns a learning model for estimating the emotion of the animal.

[0013] Furthermore, in order to achieve the above object, a computer-readable recording medium having a program recorded thereon according to one aspect of the present disclosure is characterized in that it causes a computer to execute a process of inputting learning data having person identification information for identifying a person who has been registered in advance, animal identification information for identifying a pre-recorded animal, biometric information of the animal, and emotion information representing the emotion of the animal, and learning a learning model for estimating the emotion of the animal.

[0014] As described above, according to the present disclosure, communication with animals that interact with humans can be improved.

[0015] FIG. 1 is a diagram illustrating an example of an information processing device. FIG. 2 is a diagram illustrating an example of a system having an information processing device. FIG. 3 is a diagram illustrating an example of a user interface that outputs the emotions of an animal. FIG. 4 is a diagram illustrating an example of a user interface that adds information that represents emotions to an animal. FIG. 5A is a diagram illustrating an example of the operation of an information processing device. FIG. 5B is a diagram illustrating an example of the operation of an information processing device. FIG. 6 is a diagram illustrating an example of the operation of a learning device. FIG. 7 is a diagram illustrating an example of a computer that realizes the information processing device and the learning device according to the embodiment.

[0016] Hereinafter, embodiments will be described with reference to the drawings. In the drawings described below, elements having the same or corresponding functions are denoted by the same reference numerals, and repeated description thereof may be omitted.

[0017] (Embodiment) The configuration of an information processing device in an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining an example of an information processing device.

[0018] 1 is a device for improving communication with animals that interact with humans (a device that estimates the emotions of animals and presents them to a user: an animal emotion presentation device). Also, as shown in FIG. 1, the information processing device 10 has an acquisition unit (acquisition means) 11 and an emotion estimation unit (emotion estimation means) 12.

[0019] Possible examples of animals that work together with humans include guide dogs, police dogs, explosive detection dogs, drug detection dogs, quarantine detection dogs, disaster rescue dogs, etc. Note that animals that work together with humans are not limited to dogs, and may also include birds (such as carrier pigeons), cats, falcons, and other living creatures.

[0020] In the operation phase, the acquisition unit 11 acquires biometric information (first biometric information) from a sensor worn by a target animal that is active with a human. The emotion estimation unit 12 inputs person identification information (first person identification information) that identifies a person active with the target animal and the biometric information, and estimates the emotion of the target animal toward the person.

[0021] In this way, in the embodiment, when the person interacting with the animal changes, the animal's emotions also change, so by estimating the animal's emotions for each person, communication between humans and animals can be further improved.

[0022] [System Configuration] Next, the configuration of the information processing device 10 in the embodiment will be described in more detail with reference to Fig. 2. Fig. 2 is a diagram showing an example of a system including an information processing device.

[0023] 2 , the system 100 according to the embodiment includes an information processing device 10 and a sensor 20. The information processing device 10 also includes an imaging device 15, a sensor 16, a storage device 17, an input device 18, an output device 19, an acquisition unit 11, a feeling estimation unit 12, an editing unit 13, and a learning unit 14.

[0024] The information processing device 10 is, for example, an information processing device such as a CPU (Central Processing Unit), a programmable device such as an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), or a circuit equipped with one or more of these, a personal computer, or a mobile terminal.

[0025] In the example of Fig. 2, an example in which all functions are integrated is shown, but the animal emotion display processing unit (acquisition unit 11, emotion estimation unit 12, editing unit 13, learning unit 14) in the dashed line area in Fig. 2 may be provided in one or more separate information processing devices. Specifically, the animal emotion display processing unit may be provided in a server computer, and the server computer and mobile terminal may communicate via a network to realize the animal emotion display device.

[0026] The network is a general network constructed using communication lines such as the Internet, a LAN (Local Area Network), a dedicated line, a telephone line, an in-house network, a mobile communication network, Bluetooth (registered trademark), or Wi-Fi (Wireless Fidelity) (registered trademark).

[0027] The sensor 20 acquires biological information of the animal and transmits it to the information processing device 10. Note that, in the example of Fig. 2, only one sensor 20 is shown for ease of explanation, but a plurality of sensors may be used.

[0028] The biological information may be, for example, one or more of information representing brain waves, heart rate, body temperature, vocalizations, eating and drinking, tail movements, and whole-body movements, but is not limited to the above-mentioned biological information.

[0029] The sensor 20 may be a dedicated wearable sensor that is attached to an animal, such as a hat-type sensor that is attached to the animal's head, a collar-type sensor that is attached to the animal's neck, a body-type sensor that is attached to the animal's body, or a tail-type sensor that is attached to the animal's tail.

[0030] The hat-type wearable sensor is a sensor that acquires, for example, brain waves. The collar-type wearable sensor is a sensor that acquires, for example, cries (audio waveforms) and eating and drinking (waveforms representing throat movement). The torso-type wearable sensor is a sensor that acquires, for example, heart rate and body temperature. The tail-type wearable sensor is a sensor that acquires information about tail movement (information representing the speed, direction, etc. of the tail) using, for example, a gyro sensor. Note that tail movement and whole-body movement may be measured by image processing using, for example, moving images of the target animal captured using the imaging device 15.

[0031] The information processing device will be described in detail. The imaging device 15 outputs images captured in time series. The imaging device 15 is, for example, a camera, or a device equipped with a camera and LiDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging). Examples of the camera include a monocular camera (e.g., a wide-angle camera, a fisheye camera, a spherical camera), a compound eye camera (e.g., a stereo camera, a multi-camera), and an RGB-D camera (e.g., a depth camera, a Time of Flight camera). In the example of FIG. 2, the imaging device 15 is provided inside the information processing device 10, but it may also be provided outside the information processing device 10.

[0032] The sensor 16 is a sensor for acquiring environmental information. In the example of Fig. 2, the sensor 16 is provided inside the information processing device 10, but it may be provided outside the information processing device 10. The sensor 16 may also be provided on the animal side.

[0033] The environmental information may be, for example, one or more of information indicating temperature, humidity, and noise measured by a thermometer, a hygrometer, or a sound level meter. However, the environmental information is not limited to temperature, humidity, and noise, and may include information for grasping the environment, such as the current weather and weather forecast.

[0034] The storage device 17 is a database, a server computer, a circuit having a memory, etc. The storage device 17 stores information such as biological information, environmental information, learning models, and parameters. In the example of Fig. 2, the storage device 30 is provided inside the information processing device 10, but it may also be provided outside the information processing device 10.

[0035] The input device 18 is, for example, a device such as a touch panel, a mouse, or a keyboard. The output device 19 acquires output information (described later) converted into an outputtable format and outputs images, sounds, and the like generated based on the output information. The output device 19 is, for example, an image display device using a liquid crystal, an organic electroluminescence (EL) display, or a cathode ray tube (CRT). Furthermore, the image display device may also include an audio output device such as a speaker. The output device 19 may also be a printing device such as a printer.

[0036] The animal emotion display processing unit will now be described. During the operation phase, the acquisition unit 11 acquires various types of biometric information from the sensor 20 worn by the target animal that is active together with humans. Also during the operation phase, the acquisition unit 11 acquires various types of environmental information from the sensor 16 to grasp the current surrounding environment of the target animal. Furthermore, the acquisition unit 11 stores the biometric information and environmental information in the storage device 17.

[0037] In the operation phase, the emotion estimation unit 12 inputs person identification information identifying a person who is engaged in an activity with the target animal, biological information of the target animal, and environmental information into a learning model for estimating the emotion of the target animal, and estimates the emotion of the target animal. Note that the person identification information is stored, for example, in the information processing device 10 owned by the person who is engaged in an activity with the target animal.

[0038] The emotion estimation unit 12 also stores emotion information representing the estimated emotion of the target animal, which is output from the learning model, in the storage device 17. Furthermore, the emotion estimation unit 12 outputs an emotion confirmation screen (user interface) for confirming the emotion of the animal to the output device 19.

[0039] Emotion information is information that represents, for example, the joy, anger, sadness, happiness, etc. However, the emotional information is not limited to joy, anger, sadness, happiness, etc. It may also include a series of emotional disturbances (emotions that change in a short period of time) such as fear, stress, uncertainty, and confidence.

[0040] FIG. 3 is a diagram illustrating an example of an emotion confirmation screen that displays the emotions of an animal. The example in FIG. 3 is a diagram that quantifies and graphs the emotions of an animal. The example in FIG. 3 also shows that the animal's emotions are in the joy and happiness range. By displaying the emotions of an animal in this way, people who interact with animals can visually grasp the animal's emotions, which improves communication and enables them to give appropriate instructions to the animal.

[0041] Emotions such as joy, anger, sadness, and happiness can be quantified by inputting data acquired from various sensors into a deep neural network and outputting a probability distribution of each emotion from the final layer.

[0042] FIG. 4 is a diagram illustrating an example of an emotion confirmation screen that adds information representing an animal's emotion. The example in FIG. 4 shows that an area where an animal is expressing emotion is detected using image processing, and then, using AR (Augmented Reality) processing or the like, an indication 41 (circle and [ear]), an indication 42 (circle and [tail]), an indication 43 (shaded area), and an indication 44 ([belief]) representing the animal's emotion are added to the detected area. By adding information to animals in this way, people who interact with animals can visually grasp the animal's emotion, thereby improving communication and enabling them to give appropriate instructions to the animal.

[0043] Furthermore, the user interface may display, for example, "Ears: Listening carefully to something" as an explanation for [Ears], or may play a sound. Furthermore, the user interface may display, for example, "Tail: Happy, calling attention" as an explanation for [Tail], or may play a sound. Note that explanations may also be added to parts other than the ears and tail. In the example of FIG. 4, display 43 indicates that the dog's vocalization (barking) has been detected. Furthermore, in the example of FIG. 4, display 44 indicates that the dog has vocalized (barked) with confidence.

[0044] In the operation phase, if the emotion of the target animal displayed on the emotion confirmation screen differs from the emotion felt by the person (user) interacting with the animal, the editorial department 13 outputs to the output device 19 (presents to the user) an emotion correction screen (user interface) for correcting the emotion of the animal displayed on the emotion confirmation screen.

[0045] Specifically, first, the editing unit 13 acquires a correction instruction to correct the emotion of the animal output on the emotion confirmation screen. The correction instruction is output, for example, by the user selecting a correction instruction area (button display) displayed on the emotion confirmation screen using the input device 18. Next, the editing unit 13 outputs the emotion correction screen to the output device 19 (presents it to the user).

[0046] The user then uses the input device 18 to modify the emotion modification screen from the estimated emotion of the animal to the emotion felt by the person (user).

[0047] Thereafter, the editing unit 13 acquires corrected emotion information obtained by correcting the estimated emotion of the animal, associates the corrected emotion information with the person identification information of the person, the animal identification information of the animal, the animal's biological information, and the environmental information, generates re-learning data to be used in re-learning, and stores the generated re-learning data in the storage device 17.

[0048] In the learning phase, the learning unit (learning device) 14 inputs pre-registered learning data into a learning model for estimating the emotions of animals and performs learning. The pre-registered learning data is learning data in which person identification information (second person identification information) that identifies a pre-registered person, animal identification information that identifies a pre-registered animal, biometric information (second biometric information) of the pre-registered animal, and emotion information that represents the emotion of the pre-registered animal are associated with each other.

[0049] The pre-registered learning data may also include pre-registered environmental information. In the learning phase, the emotion information is a label that represents the emotion of the animal, such as joy, anger, sadness, or pleasure.

[0050] Furthermore, in the re-learning phase, if the result of emotion estimation of the target animal differs from the emotion perceived by the person who is active with the target animal, the learning unit 14 re-learns using the corrected emotion information. Specifically, the learning unit 14 re-learns using the re-learning data generated by the editing unit 13.

[0051] In this way, relearning allows the emotions to be corrected successively, improving the accuracy of the emotion estimation for each person. As a result, communication between the person (user) and the animal improves, making it possible to give appropriate instructions to the animal.

[0052] [Device Operation] Next, the operation of the information processing device and learning device in the embodiment will be described using Figures 5A, 5B, and 6. Figures 5A and 5B are diagrams for explaining an example of the operation of the information processing device. Figure 6 is a diagram for explaining an example of the operation of the learning device. In the following description, reference will be made to the diagrams as appropriate. Furthermore, in the embodiment, the information processing method and learning method are implemented by operating the information processing device and learning device. Therefore, the description of the information processing method and learning method in the embodiment will be replaced with the description of the operation of the information processing device and learning device below.

[0053] 5A , first, in the operation phase, the acquisition unit 11 acquires biometric information (first biometric information) from a sensor worn by a target animal that is active with a human (step A1). The emotion estimation unit 12 inputs person identification information (first person identification information) that identifies a person active with the target animal and the biometric information, and estimates the emotion of the target animal toward the person (step A2).

[0054] The detailed operation of the information processing device will now be described. Specifically, as shown in FIG. 5B , first, in the operation phase, the acquisition unit 11 acquires various types of biometric information from the sensor 20 worn by the target animal that is active with humans (step A1′). Also, in step A1′, the acquisition unit 11 acquires various types of environmental information from the sensor 16 in the operation phase to grasp the current environment. Then, in step A1′, the acquisition unit 11 further stores the biometric information and environmental information in the storage device 17.

[0055] Next, in the operation phase, the emotion estimation unit 12 inputs person identification information that identifies a person who is active with the target animal, the biological information of the target animal, and the environmental information into a learning model for estimating the emotion of the target animal, and estimates the emotion of the target animal (step A2'). After that, in step A2', the emotion estimation unit 12 stores emotion information that represents the estimated emotion of the target animal, output from the learning model, in the storage device 17.

[0056] Next, the feeling estimation unit 12 outputs the animal's feeling to the output device 19 using a feeling confirmation screen for confirming the animal's feeling (step A3). Specifically, a display such as that shown in FIGS. 3 and 4 is produced.

[0057] Next, if the user wishes to modify the animal's emotion displayed on the emotion confirmation screen, the editing unit 13 acquires a modification instruction (step A4: Yes). Next, the editing unit 13 outputs the emotion modification screen to the output device 19 (presents it to the user) (step A5). The user then uses the emotion modification screen to modify the estimated animal's emotion to the emotion felt by the person (user). Note that if the user does not wish to modify the animal's emotion displayed on the emotion confirmation screen, the animal emotion presentation process ends (step A4: No).

[0058] Next, the editing unit 13 acquires revised emotion information that has revised the estimated emotion of the animal, and associates the revised emotion information with the person identification information of the person, the animal identification information of the animal, the animal's biological information, and the environmental information to generate relearning data to be used in relearning (step A6). The editing unit 13 then stores the generated relearning data in the storage device 17.

[0059] Next, in the re-learning phase, the learning unit 14 performs re-learning using the re-learning data generated by the editing unit 13 (step A7).

[0060] The operation of the learning device (learning of the learning model) will now be described. As shown in Fig. 6, first, in the learning phase, the learning unit 14 acquires pre-registered learning data (step B1).

[0061] The learning unit 14 inputs the acquired learning data into a learning model for estimating the emotion of an animal and performs learning (step B2).Then, the learning unit 14 stores the learned learning model in the storage device 17 (step B3).

[0062] [Effects of the embodiment] As described above, according to the embodiment, when the person interacting with an animal changes, the animal's emotions also change. Therefore, by estimating the animal's emotions for each person, communication between humans and animals can be further improved.

[0063] Furthermore, by relearning, emotions are corrected successively, improving the accuracy of emotion estimation for each person. As a result, communication between the person (user) and the animal improves, making it possible to give appropriate instructions to the animal.

[0064] Furthermore, in addition to proper training, the purpose of the working animal, for example, a drug detection dog, can be improved in detection accuracy.

[0065] [Program] The program in the embodiment may be a program that causes a computer to execute steps A1 to A7 and B1 to B3 shown in Figures 5A, 5B, and 6. By installing and executing this program in a computer, the information processing device, learning device, information processing method, and learning method in the embodiment can be realized. In this case, the processor of the computer functions as the various processes, acquisition unit 11, emotion estimation unit 12, editing unit 13, and learning unit 14 described above and performs processing.

[0066] The program in the embodiment may be executed by a computer system constructed by a plurality of computers. In this case, for example, each computer may function as any one of the acquisition unit 11, emotion estimation unit 12, editing unit 13, and learning unit 14.

[0067] [Physical Configuration] A computer that realizes an information processing device and a learning device by executing a program in the embodiment will now be described with reference to Fig. 7. Fig. 7 is a diagram for explaining an example of a computer that realizes an information processing device and a learning device in the embodiment.

[0068] 7, the computer 110 includes a CPU (Central Processing Unit) 111, a main memory 112, a storage device 113, an input interface 114, a display controller 115, a data reader / writer 116, and a communication interface 117. These components are connected to each other via a bus 121 so as to be able to communicate data with each other. Note that the computer 110 may include a GPU or an FPGA in addition to or instead of the CPU 111.

[0069] The CPU 111 loads a program in the embodiment, which is composed of a group of codes and stored in the storage device 113, into the main memory 112 and executes each code in a predetermined order to perform various calculations. The main memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory).

[0070] The program in the embodiment is provided in a state stored in a computer-readable recording medium 120. The program in the embodiment may be distributed over the Internet connected via the communication interface 117.

[0071] Specific examples of the storage device 113 include a hard disk drive and a semiconductor storage device such as a flash memory. The input interface 114 mediates data transmission between the CPU 111 and input devices 118 such as a keyboard and a mouse. The display controller 115 is connected to a display device 119 and controls the display on the display device 119.

[0072] The data reader / writer 116 mediates data transmission between the CPU 111 and the recording medium 120, reads programs from the recording medium 120, and writes processing results from the computer 110 to the recording medium 120. The communication interface 117 mediates data transmission between the CPU 111 and other computers.

[0073] Specific examples of the recording medium 120 include general-purpose semiconductor storage devices such as CF (Compact Flash (registered trademark)) and SD (Secure Digital), magnetic recording media such as flexible disks, or optical recording media such as CD-ROMs (Compact Disk Read Only Memory).

[0074] The information processing device and learning device in the embodiments can be realized not only by a computer with a program installed, but also by hardware corresponding to each part, such as an electronic circuit. Furthermore, the information processing device and learning device may be realized in part by a program and in the remaining part by hardware. In the embodiments, the computer is not limited to the computer shown in FIG. 7.

[0075] [Supplementary Note] The following supplementary note is further disclosed regarding the above-described embodiment. Some or all of the above-described embodiment can be expressed by (Supplementary Note 1) to (Supplementary Note 33) described below, but is not limited to the following descriptions.

[0076] (Supplementary Note 1) An information processing device having: an acquisition unit that acquires first biometric information from a sensor worn by a target animal that interacts with a human; and an emotion estimation unit that receives input of first person identification information that identifies a person that interacts with the target animal and the first biometric information, and estimates the emotion of the target animal.

[0077] (Supplementary Note 2) The information processing device according to Supplementary Note 1, further comprising a learning unit that, in a learning phase, inputs learning data associated with pre-registered second person identification information of a person, animal identification information for identifying an animal, second biometric information of the animal, and emotion information representing the emotion of the animal into a learning model for estimating the emotion of the target animal, and performs learning.

[0078] (Supplementary Note 3) The information processing device according to Supplementary Note 2, wherein, in the re-learning phase, if a result of emotion estimation of the target animal differs from an emotion perceived by a person interacting with the target animal, the learning unit re-learns using corrected emotion information.

[0079] (Supplementary Note 4) The information processing device according to Supplementary Note 2, wherein the first biological information and the second biological information include any one or more of information representing brain waves, heart rate, body temperature, vocalizations, eating and drinking, tail movements, and whole-body movements.

[0080] (Supplementary Note 5) The information processing device according to Supplementary Note 3, wherein the emotion information is a label representing at least joy, anger, sadness, or pleasure of the animal.

[0081] (Supplementary Note 6) The information processing device according to Supplementary Note 3, wherein the emotion information is a label representing at least fear, stress, and confusion of the animal.

[0082] (Supplementary Note 7) The information processing device according to Supplementary Note 3, further comprising a user interface that outputs a result of emotion estimation of the target animal and is used for the relearning.

[0083] (Supplementary Note 8) An information processing method, comprising: an information processing device acquiring first biometric information from a sensor worn by a target animal that is active together with a human; inputting first person identification information that identifies a person that is active together with the target animal and the first biometric information; and estimating the emotion of the target animal.

[0084] (Supplementary Note 9) The information processing method according to Supplementary Note 8, wherein the information processing device, in a learning phase, inputs learning data, which associates pre-registered second person identification information of a person, animal identification information that identifies an animal, second biometric information of the animal, and emotion information that represents the emotion of the animal, into a learning model for estimating the emotion of the target animal, and performs learning.

[0085] (Supplementary Note 10) The information processing method according to Supplementary Note 9, wherein, in the re-learning phase, if the result of emotion estimation of the target animal differs from the emotion perceived by a person interacting with the target animal, the information processing device re-learns using corrected emotion information.

[0086] (Supplementary Note 11) The information processing method according to Supplementary Note 9, wherein the first biological information and the second biological information include any one or more of information representing brain waves, heart rate, body temperature, vocalizations, eating and drinking, tail movements, and whole-body movements.

[0087] (Supplementary Note 12) The information processing method according to Supplementary Note 10, wherein the emotion information is a label representing at least joy, anger, sadness, or pleasure of the animal.

[0088] (Supplementary Note 13) The information processing method according to Supplementary Note 10, wherein the emotion information is a label representing at least fear, stress, and confusion of the animal.

[0089] (Supplementary Note 14) The information processing method according to Supplementary Note 10, further comprising: a user interface that outputs a result of emotion estimation of the target animal and is used for the relearning.

[0090] (Supplementary Note 15) A computer-readable recording medium having recorded thereon a program for causing a computer to execute the following process: acquiring first biometric information from a sensor worn by a target animal that is active together with a human; inputting first person identification information that identifies a person that is active together with the target animal and the first biometric information; and estimating the emotion of the target animal.

[0091] (Appendix 16) A computer-readable recording medium having recorded thereon the program according to Appendix 15, which causes the computer to execute a learning process in a learning phase, by inputting learning data associated with pre-registered second person identification information of a person, animal identification information that identifies an animal, second biometric information of the animal, and emotion information that represents the emotion of the animal into a learning model for estimating the emotion of the target animal.

[0092] (Supplementary Note 17) A computer-readable recording medium having recorded thereon the program according to Supplementary Note 16, which causes the computer to execute a process of: in a re-learning phase, if the result of emotion estimation of the target animal differs from the emotion perceived by a person interacting with the target animal, re-learning is performed using corrected emotion information.

[0093] (Appendix 18) A computer-readable recording medium having recorded thereon the program described in Appendix 16, wherein the first biological information and the second biological information include any one or more of information representing brain waves, heart rate, body temperature, vocalizations, eating and drinking, tail movements, and whole-body movements.

[0094] (Supplementary Note 19) A computer-readable recording medium storing the program according to Supplementary Note 17, wherein the emotion information is a label representing at least joy, anger, sadness, or pleasure of the animal.

[0095] (Supplementary Note 20) A computer-readable recording medium storing the program according to Supplementary Note 17, wherein the emotion information is a label representing at least fear, stress, and confusion of the animal.

[0096] (Supplementary Note 21) A computer-readable recording medium having the program according to Supplementary Note 17 recorded thereon, the computer-readable recording medium outputting a result of emotion estimation of the target animal and having a user interface used for the relearning.

[0097] (Supplementary Note 22) A learning device having a learning means for inputting learning data in which pre-registered person identification information for identifying a person, animal identification information for identifying an animal, biometric information of the animal, and emotion information representing the emotion of the animal are associated, and learning a learning model for estimating the emotion of the animal.

[0098] (Supplementary Note 23) The learning device according to Supplementary Note 22, wherein the biological information includes one or more of information representing brain waves, heart rate, body temperature, vocalizations, eating and drinking, tail movements, and whole-body movements.

[0099] (Supplementary Note 24) The learning device according to Supplementary Note 22, wherein the emotion information is a label representing at least joy, anger, sadness, or pleasure of the animal.

[0100] (Supplementary Note 25) The learning device according to Supplementary Note 22, wherein the emotion information is a label representing at least fear, stress, and confusion of the animal.

[0101] (Supplementary Note 26) A learning method, in which a learning device inputs learning data having person identification information for identifying a person who has been registered in advance, animal identification information for identifying a pre-recorded animal, biometric information of the animal, and emotion information representing the emotion of the animal, and learns a learning model for estimating the emotion of the animal.

[0102] (Supplementary Note 27) The learning method according to Supplementary Note 26, wherein the biological information includes one or more of information representing brain waves, heart rate, body temperature, vocalizations, eating and drinking, tail movements, and whole-body movements.

[0103] (Supplementary Note 28) The learning method according to Supplementary Note 26, wherein the emotion information is a label representing at least joy, anger, sadness, or pleasure of the animal.

[0104] (Supplementary Note 29) The learning method according to Supplementary Note 26, wherein the emotion information is a label representing at least fear, stress, and confusion of the animal.

[0105] (Supplementary Note 30) A computer-readable recording medium having recorded thereon a program for causing a computer to execute a process of inputting learning data having person identification information for identifying a person who has been registered in advance, animal identification information for identifying a pre-recorded animal, biometric information of the animal, and emotion information representing the emotion of the animal, and learning a learning model for estimating the emotion of the animal.

[0106] (Supplementary Note 31) A computer-readable recording medium having recorded thereon the program according to Supplementary Note 30, wherein the biological information includes any one or more of information representing brain waves, heart rate, body temperature, vocalizations, eating and drinking, tail movements, and whole-body movements.

[0107] (Supplementary Note 32) A computer-readable recording medium storing the program according to Supplementary Note 30, wherein the emotion information is a label representing at least joy, anger, sadness, or pleasure of the animal.

[0108] (Supplementary Note 33) A computer-readable recording medium storing the program according to Supplementary Note 30, wherein the emotion information is a label representing at least fear, stress, and confusion of the animal.

[0109] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0110] This application claims priority based on Japanese Patent Application No. 2024-123574, filed on July 30, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0111] According to the above description, communication with animals that work alongside humans can be improved, and the present invention is useful in fields where communication with animals is required.

[0112] 10 Information processing device 11 Acquisition unit 12 Emotion estimation unit 13 Editing unit 14 Learning unit (learning device) 15 Imaging device 16 Sensor 17 Storage device 18 Input device 19 Output device 20 Sensor 100 System 110 Computer 111 CPU 112 Main memory 113 Storage device 114 Input interface 115 Display controller 116 Data reader / writer 117 Communication interface 118 Input device 119 Display device 120 Recording medium 121 Bus

Claims

1. An information processing device having: an acquisition means for acquiring first biometric information from a sensor worn by a target animal that interacts with humans; and an emotion estimation means for inputting first person identification information that identifies a person that interacts with the target animal and the first biometric information, and estimating the emotion of the target animal.

2. The information processing device according to claim 1, further comprising a learning means for inputting, into a learning model for estimating the emotion of the target animal, learning data in which pre-registered second person identification information of a person, animal identification information for identifying an animal, second biometric information of the animal, and emotion information representing the emotion of the animal are associated in a learning phase.

3. The information processing device according to claim 2, wherein, in the re-learning phase, if the result of emotion estimation of the target animal differs from the emotion perceived by a person interacting with the target animal, the learning means re-learns using corrected emotion information.

4. The information processing device according to claim 2, wherein the first biometric information and the second biometric information include one or more of information representing brain waves, heart rate, body temperature, vocalizations, eating and drinking, tail movements, and whole-body movements.

5. The information processing device according to claim 3, wherein the emotion information is a label representing at least joy, anger, sadness, or pleasure of the animal.

6. The information processing device according to claim 3, which outputs the emotion estimation result of the target animal and has a user interface used for the relearning.

7. An information processing method, comprising: an information processing device acquiring first biometric information from a sensor worn by a target animal that interacts with a human; inputting first person identification information that identifies a person interacting with the target animal and the first biometric information; and estimating the emotion of the target animal.

8. A computer-readable recording medium having recorded thereon a program for causing a computer to execute the following process: acquiring first biometric information from a sensor worn by a target animal that interacts with a human; inputting first person identification information that identifies a person interacting with the target animal and the first biometric information; and estimating the emotion of the target animal.

9. A learning device having a learning means for inputting learning data in which pre-registered person identification information for identifying a person, animal identification information for identifying an animal, biometric information of the animal, and emotional information representing the animal's emotion are associated, and learning a learning model for estimating the emotion of the animal.

10. The learning device according to claim 9, wherein the biological information includes one or more of information representing brain waves, heart rate, body temperature, vocalizations, eating and drinking, tail movements, and whole-body movements.

11. The learning device according to claim 9, wherein the emotional information is a label representing at least joy, anger, sadness, or happiness of the animal.

12. A learning method in which a learning device inputs learning data having person identification information that identifies a pre-registered person, animal identification information that identifies a pre-recorded animal, biometric information of the animal, and emotion information that represents the emotion of the animal, and learns a learning model for estimating the emotion of the animal.

13. A computer-readable recording medium having recorded thereon a program for causing a computer to execute a process of inputting learning data having person identification information for identifying a person who has been registered in advance, animal identification information for identifying a pre-recorded animal, biometric information of the animal, and emotion information representing the emotion of the animal, and learning a learning model for estimating the emotion of the animal.

Images