System

Abstract

A system is provided.SOLUTION: A system comprising: sensor means for collecting behavioral and facial expression data of a pet; communication means for receiving data from the sensor means; analysis means for analyzing the received data and inferring a desire of the pet; generation means for generating a notification based on the inferred desire of the pet; and transmission means for transmitting the generated notification to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional pet care systems make it difficult to accurately grasp a pet's needs from its behavior and facial expressions, making it difficult for owners to understand their pet's condition and respond appropriately. Furthermore, there are insufficient platforms for communication and information exchange between pet owners, limiting opportunities for sharing knowledge and experience regarding pet care. The present invention aims to provide a system that supports pet care by analyzing a pet's behavior and facial expressions and clearly notifying the pet's needs based on the results, and also to provide a platform that promotes communication between pet owners. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including a sensor means for collecting pet behavioral data and facial expression data, a communication means for receiving data from the sensor means, an analysis means for analyzing the received data and estimating the pet's needs, a generation means for generating a notification based on the estimated pet needs, and a transmission means for transmitting the generated notification to a user. In this invention, the sensor means includes a wearable sensor attached to the pet's collar or body and an indoor camera for capturing the pet's movements and facial expressions. Furthermore, the analysis means is configured to use a machine learning algorithm to identify the pet's behavioral patterns and emotional state from the received data. This system accurately estimates the pet's needs and quickly provides that information to the owner, allowing the owner to take appropriate action. Furthermore, by providing a platform for information exchange between pet owners, the system also promotes the sharing of knowledge and experience regarding pet care.

[0006] "Sensor means" refers to the devices and technologies used to collect pet behavioral and facial expression data.

[0007] "Communication means" refers to the technology and devices for transmitting data collected from the sensor means to a server or another device.

[0008] "Analysis means" refers to devices and techniques for analyzing the received behavioral data and facial expression data and inferring the pet's desires.

[0009] The "generation means" refers to a device and technology for generating notification content based on the pet's desires estimated by the analysis means.

[0010] "Transmission means" refers to devices and techniques for sending notifications created by the generation means to users.

[0011] "Pets" refers to animals such as dogs, cats, and birds kept in the home.

[0012] "Behavioral Data" refers to information about your pet's physical behavior, such as its movements, activity, and physical movements.

[0013] "Facial expression data" refers to information about a pet's emotional and psychological state that can be read from its facial and bodily expressions.

[0014] A "wearable sensor" is a device that is attached to a pet's collar or body and collects data on the pet's behavior.

[0015] An "indoor camera" refers to a camera installed indoors to capture your pet's movements and expressions.

[0016] "Machine learning algorithms" refers to a type of artificial intelligence technology used to identify behavioral patterns and emotional states from received data.

[0017] "User" refers to the owner who uses this system to monitor the behavior and desires of their pet and take appropriate action. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention provides a system that analyzes behavioral data and facial expression data of a pet, accurately estimates the pet's desires, and notifies the pet owner of the desires. Specific embodiments for implementing this system will be described below.

[0040] System Configuration

[0041] 1. Sensor means

[0042] The wearable sensor terminal is attached to the pet's collar or torso and collects behavioral data such as the pet's acceleration data, heart rate, and activity level.

[0043] The indoor camera serves as a terminal that captures your pet's movements and expressions in real time and saves them as video data.

[0044] 2. Means of communication

[0045] The devices (wearable sensors and indoor cameras) transmit the collected data to a server using communication technologies such as Wi-Fi and Bluetooth. The transmitted data includes a timestamp, facilitating data synchronization.

[0046] 3. Analysis method

[0047] The server stores the received data in a database and checks the integrity of the data.

[0048] The server performs preprocessing on the received data, such as noise removal and outlier removal, to improve the accuracy of the analysis.

[0049] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data. Specifically, it classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[0050] 4. Generation means

[0051] The server uses the analysis results to estimate the pet's needs and generates a message (text or voice) based on that information, such as "Your dog wants to go for a walk" or "Momo is hungry."

[0052] 5. Transmission Method

[0053] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[0054] Specific examples

[0055] Data Collection Example

[0056] The device (wearable sensor) collects the cat's activity data (especially its behavior walking around the room at night) at regular intervals. The sensor measures the cat's acceleration and heart rate and sends the data to the server. At the same time, the device (indoor camera) captures the cat's movements as video and sends it to the server.

[0057] Data analysis example

[0058] The server first stores the received data in a database and performs preprocessing to remove noise and outliers. It then analyzes the data using machine learning algorithms. For example, it can identify a "restless" behavior pattern based on frequent nighttime movements and elevated heart rates, and detect "anxious facial expressions" using facial recognition.

[0059] Message Generation and Notification Example

[0060] Based on the analysis results of the behavioral pattern "restless" and the emotional state "anxious expression," the server generates a message saying, "Momo may be feeling stressed at night." The message is sent to the user's smartphone as a push notification. The user receives the notification on their smartphone app and checks the details.

[0061] User Interface Example

[0062] After checking the notification, the user can choose to use an aroma diffuser to relax their cat based on the information in the app that "Momo is feeling stressed at night." They can also use the in-app communication platform to discuss the issue with other pet owners and seek additional advice.

[0063] This system can accurately estimate a pet's needs from its behavior and facial expressions, and provide that information to the owner quickly and appropriately. This will support the health and happiness of pets and reduce the burden on owners. It also provides a platform that promotes communication between pet owners, allowing them to share knowledge and experiences about pet care.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] The device (wearable sensor) collects pet behavior data (e.g., acceleration, heart rate, activity level) at regular intervals. This data is recorded in real time and temporarily stored in the built-in memory.

[0067] Step 2:

[0068] The device (indoor camera) captures your pet's movements and expressions and stores them as video data. The camera takes high-resolution still images and videos, and uses facial recognition technology to identify your pet if necessary.

[0069] Step 3:

[0070] The devices transmit collected sensor and camera data over Wi-Fi or Bluetooth to a server, where each data set is time-stamped to ensure data synchronization and integrity.

[0071] Step 4:

[0072] The server stores the received data in a database, where behavioral and facial expression data for each pet is accumulated and used for subsequent analysis.

[0073] Step 5:

[0074] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[0075] Step 6:

[0076] The server then uses machine learning algorithms to analyze the preprocessed data, identifying behavioral patterns such as "exercise," "rest," and "excitement" from the behavioral data, and inferring emotional states such as "happiness," "anxiety," and "fatigue" from the facial expression data.

[0077] Step 7:

[0078] The server then uses the analysis results to estimate the pet's needs. For example, if the server detects that the pet frequently wanders around food and has an anxious expression, it will assume that the pet is hungry.

[0079] Step 8:

[0080] The server generates a message (text or voice) for the user based on the estimated desires. The generated message should be specific and easy to understand. For example, it could be in the form of "Mimi seems hungry."

[0081] Step 9:

[0082] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[0083] Step 10:

[0084] Users receive a notification on their smartphone app, open the app to check the details, and then understand their pet's current condition and needs and choose appropriate actions (e.g., feeding or taking them for a walk).

[0085] Step 11:

[0086] Users can use the in-app communication platform to share information with other pet owners, for example by posting questions such as, "Momo seems to be stressed at night. How do you deal with it?"

[0087] Step 12:

[0088] The server collects answers from other users in real time and displays them to the user who posted the question. The answers include specific advice and similar experiences that can improve the quality of pet care.

[0089] The above is a specific flow of processing steps in the system of the present invention. This system can analyze pet behavior and desires in detail and provide appropriate feedback to the user. The user can then take prompt and effective action based on the information obtained to support the health and happiness of their pet.

[0090] Example 1

[0091] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0092] Understanding pet behavior and emotions is important for maintaining pet health and happiness, but currently owners have to manually observe and judge, which is time-consuming and often inaccurate. It is also difficult to properly understand and respond to pet needs and stress, which can result in a risk of compromising pet health and happiness.

[0093] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0094] In this invention, the server includes a sensor means for collecting behavioral data and facial expression data of the pet, a communication means for receiving data from the sensor means, a preprocessing means for saving the received data and removing noise and outliers, an analysis means for analyzing the preprocessed data and estimating the behavioral patterns and emotional state of the pet, a generation means for generating a notification using natural language generation technology based on the estimated desires of the pet, and a transmission means for sending the generated notification to the user as a push notification. This makes it possible to more accurately and quickly analyze the behavioral and emotional state of the pet and to send notifications to the owner at appropriate times.

[0095] "Sensor means" refers to a device installed to collect data on the behavior and facial expressions of pets. Specifically, it includes wearable sensors and indoor cameras.

[0096] "Communication means" refers to the technical means for transmitting data collected from the sensor means to the server. Specifically, it includes wireless communication technologies such as Wi-Fi and Bluetooth.

[0097] "Pre-processing means" refers to technical means for storing received data and cleaning the data, such as removing noise and outliers. Specifically, this includes database management systems and data processing software.

[0098] "Analysis means" refers to technical means for analyzing the pre-processed data and inferring the pet's behavioral patterns and emotional state, including machine learning algorithms and data analysis software.

[0099] The "generation means" refers to a technical means for generating a notification about the pet's needs in natural language based on the analysis results. Specifically, it includes natural language generation technology.

[0100] "Transmission means" refers to the technical means for transmitting the generated notification to the user as a push notification. Specifically, it includes the API of the push notification service.

[0101] The present invention provides a system that analyzes behavioral data and facial expression data of a pet, accurately estimates the pet's desires, and notifies the pet's owner of the desires. Specific embodiments for implementing this system will be described below.

[0102] System Configuration

[0103] Sensor means

[0104] Wearable sensors as terminals are attached to pets' collars or bodies and collect behavioral data such as pet acceleration data, heart rate, and activity levels. Specifically, they are generally called wearable devices. Indoor cameras as terminals capture pets' movements and facial expressions in real time and save them as video data. Specifically, they are generally called surveillance cameras. This allows data on pets' behavior and facial expressions to be continuously obtained.

[0105] communication means

[0106] The terminals (wearable devices and surveillance cameras) transmit the collected data to a server using communication technologies such as Wi-Fi or Bluetooth. Specifically, a wireless communication module is used. The transmitted data includes a timestamp to ensure data synchronization.

[0107] Pretreatment means

[0108] The server stores the received data in a database and checks the data integrity. The specific database used here is generally called a relational database management system (RDBMS). Next, preprocessing such as noise removal and outlier removal is performed using the Python Pandas library. This processing improves the accuracy of the data analysis.

[0109] Analysis means

[0110] The server uses machine learning algorithms to analyze behavioral and facial expression data. Specifically, it uses a generic term for a machine learning platform, utilizing libraries such as TENSORFLOW (registered trademark). It classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[0111] generation means

[0112] The server estimates the pet's needs from the analysis results and generates a message (text or voice) based on the estimate. Specifically, it uses natural language generation technology and a generative AI model (e.g., GPT-3 (registered trademark)). For example, it generates specific messages such as "Your dog wants to go for a walk" or "Momo is hungry."

[0113] Transmission method

[0114] The server then sends the generated message to the user's smartphone or tablet as a push notification, using the API of a push notification service (e.g., Firebase Cloud Messaging). The notification contains the analysis results and suggested solutions.

[0115] Specific examples

[0116] Data Collection Example

[0117] The terminal (wearable device) collects the cat's activity data (especially its behavior walking around the room at night) at regular intervals. The sensor measures the cat's acceleration and heart rate and sends the data to the server. At the same time, the terminal (surveillance camera) captures the cat's movements as video and sends it to the server as well.

[0118] Data analysis example

[0119] The server stores the received data in a relational database management system (RDBMS) and preprocesses it using Python's Pandas library to remove noise and outliers. The data is then analyzed using machine learning algorithms powered by TensorFlow. For example, it identifies a "restless" behavior pattern based on frequent nighttime movements and elevated heart rates, and uses facial recognition to detect "anxious facial expressions."

[0120] Message Generation and Notification Example

[0121] Based on the analysis results of the behavioral pattern "restless" and the emotional state "anxious expression," the server uses natural language generation technology (generative AI model) to generate a message saying "Momo may be feeling stressed at night." The message is then sent as a push notification to the user's smartphone using a push notification service (Firebase Cloud Messaging). The user receives the notification in their smartphone app and checks the details.

[0122] Prompt Sentence Examples

[0123] "Infer a pet's needs from its behavioral and facial expression data and generate a message to notify the owner. For example, if a cat moves around frequently at night and its heart rate increases, explain what kind of message should be generated based on the analysis results."

[0124] This system can accurately predict pet needs from their behavior and facial expressions, and provide them to their owners quickly and appropriately. This supports the health and happiness of pets and reduces the burden on owners. It also provides a platform that promotes communication between pet owners, allowing them to share knowledge and experiences about pet care.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Program processing flow

[0127] Step 1: Data collection

[0128] The terminal uses a wearable device to acquire the pet's behavioral data (acceleration, heart rate, activity level) and uses a surveillance camera to collect the pet's movements and facial expressions as video data.

[0129] Input: Sensor values ​​from wearable devices (acceleration data, heart rate data), video data from surveillance cameras

[0130] Output: Collected behavioral and video data

[0131] Specific operation: The wearable device uses sensors to acquire data at regular intervals (e.g., every minute) and temporarily stores it in its internal memory. The surveillance camera captures video in real time and also temporarily stores it.

[0132] Step 2: Send data

[0133] The device sends the collected data to a server via Wi-Fi or Bluetooth.

[0134] Input: Collected behavioral and video data

[0135] Output: Data packets sent to the server

[0136] How it works: Pet behavior data and video data are sent to a server via Wi-Fi, where a timestamp is added to ensure data synchronization.

[0137] Step 3: Data storage and preprocessing

[0138] The server stores the received data in a database and performs preprocessing (noise removal and outlier removal).

[0139] Input: Behavioral data and video data sent from the device

[0140] Output: Preprocessed data

[0141] How it works: The data is stored in a database management system and a script is run to remove noise and outliers using the Python Pandas library.

[0142] Step 4: Data analysis

[0143] The server uses the preprocessed data to analyze it using machine learning algorithms to estimate the pet's behavioral patterns and emotional state.

[0144] Input: Preprocessed data

[0145] Output: Analysis results of behavioral patterns and emotional states

[0146] Specific behavior: The data to be analyzed is input into a machine learning platform, and algorithms such as TensorFlow are used to classify and estimate the pet's behavioral patterns (e.g., "exercising," "resting," "excited") and emotional state (e.g., "happy," "anxious").

[0147] Step 5: Message Generation

[0148] The server uses natural language generation technology (generative AI model) based on the analysis results to generate a notification message.

[0149] Input: Analysis results of behavioral patterns and emotional states

[0150] Output: The generated notification message

[0151] Specific operation: A prompt sentence is input to the generative AI model, and a notification message for the user is created based on the generated text.

[0152] Step 6: Send the message

[0153] The server sends the generated notification message to the user's smartphone via a push notification service.

[0154] Input: The generated notification message

[0155] Output: Notification sent to the user's smartphone

[0156] Specific operation: Calls the API of the push notification service and sends the generated notification message to the user's smartphone.

[0157] Step 7: User Interface Support

[0158] The user checks the notification received on their smartphone and selects the necessary action based on the pet's condition.

[0159] Input: Received notification message

[0160] Output: Selected action (e.g., activate aroma diffuser for stress relief)

[0161] Specific Action: The user taps the notification to open the app, checks the detailed information, and selects the appropriate action if necessary. In this case, the user presses a button within the app to perform a specific action.

[0162] (Application example 1)

[0163] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0164] Today's pet owners find it difficult to accurately understand their pets' behavior and emotional state and provide appropriate care and product selection. In particular, physical stores such as pet goods shops lack systems that can quickly recommend the right product for each pet's condition. This means pet owners spend a lot of time choosing the right product in the store, which can increase stress for their pets. To solve this problem, a system is needed that collects and analyzes pet behavior and facial expression data and notifies users in real time.

[0165] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0166] In this invention, the server includes a sensor means for collecting behavioral data and facial expression data of the pet, a communication means for receiving data from the sensor means, an analysis means for analyzing the received data and estimating the pet's desires, a generation means for generating a notification based on the estimated pet's desires, and a transmission means for transmitting the generated notification to the user's mobile information terminal and suggesting products in the store, thereby enabling optimal product selection based on the pet's behavior and emotional state in a physical store.

[0167] "Pet behavior data" is information about a pet's physical activity, movements, and behavior.

[0168] "Facial expression data" is information related to the movements of a pet's face and changes in facial expression.

[0169] The "sensor means" is a device for collecting behavioral data and facial expression data of a pet.

[0170] A "wearable sensor" is a device that can be attached to a pet's collar or torso and measures the pet's movements and biological data.

[0171] An "indoor camera" is a video camera installed to capture your pet's movements and expressions.

[0172] "Communication means" refers to the technology used to transmit data from the sensor means to the server, and includes Wi-Fi, Bluetooth, etc.

[0173] The "analysis means" is a system for processing the received data and analyzing the pet's desires and emotional state.

[0174] A "machine learning algorithm" is a computational method that learns patterns from incoming data and identifies pet behaviors and emotions.

[0175] A "generator" is a system that creates a notification message based on the analyzed data.

[0176] "Transmission means" refers to a technique for transmitting the generated notification to the user's mobile information terminal.

[0177] A "user's mobile information terminal" is a mobile information device such as a smartphone or tablet used by the owner.

[0178] "Making product suggestions in-store" means recommending appropriate products to pet owners based on the analyzed condition of their pets.

[0179] The present invention provides a system that analyzes behavioral data and facial expression data of pets in a physical store, estimates the pet's desires, and proposes optimal products to pet owners. Specific embodiments for implementing this system are described below.

[0180] System Configuration

[0181] 1. Sensor means

[0182] Wearable sensor: A device that is attached to a pet's collar or body and collects behavioral data such as acceleration data, heart rate, and activity level.

[0183] Indoor camera: A device installed inside the store that captures pets' movements and expressions in real time and obtains them as video data.

[0184] 2. Means of communication

[0185] Communication method: This technology uses Wi-Fi or Bluetooth to transmit data collected from wearable sensors and indoor cameras to a server. The transmitted data includes a timestamp, making data synchronization easy.

[0186] 3. Analysis method

[0187] Analysis method: The server stores the received data in a database and checks its integrity. First, it performs preprocessing such as noise removal and outlier removal, then uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data. Specifically, it classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[0188] 4. Generation means

[0189] Generation method: The server estimates the pet's needs from the analysis results and generates a message (text or voice) based on the estimate. For example, it generates a specific message such as "Your dog wants to go for a walk" or "Your pet is stressed."

[0190] 5. Transmission Method

[0191] Transmission method: The server sends the generated message to the user's mobile information device (smartphone or tablet) as a push notification. The notification contains the analysis results and suggested countermeasures.

[0192] Explanation of program processing

[0193] The server uses the following hardware and software to collect and analyze pet behavior and facial expression data: wearable sensors, indoor cameras, smartphones, and tablets; and the requests library for communication processing, SciPy, and TensorFlow for data analysis.

[0194] Data is collected in real time by wearable sensors and indoor cameras and transmitted to a server via communication means. The server stores the received data in a database and first performs preprocessing. This preprocessing includes noise removal and outlier elimination to improve data quality. Then, machine learning algorithms are used to analyze the pet's behavioral patterns and emotional state. Based on the results of this analysis, the pet's desires are estimated and a notification message is generated for the owner. This notification message is then sent to the user's mobile information terminal, and appropriate product recommendations are made to the owner in the store.

[0195] Specific examples

[0196] If a dog brought into a pet goods shop looks anxious, the system will analyze data collected through wearable sensors and indoor cameras and send a message to the owner's smartphone saying, "This dog is likely feeling anxious. We recommend a toy that will have a relaxing effect."

[0197] Prompt Sentence Examples

[0198] "Please create an application that analyzes pet behavior data (acceleration data, heart rate) and facial expression data (camera footage), estimates the pet's condition in real time, and suggests appropriate products to the owner."

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] The devices (wearable sensors and indoor cameras) collect pet behavior data (e.g., acceleration data, heart rate) and facial expression data (e.g., camera footage). Specifically, the devices acquire data in real time from sensors attached to the pet's collar or body and temporarily store the data.

[0202] Input: Acceleration data, heart rate data, and camera footage collected from your pet

[0203] Output: Collected behavioral and facial expression data

[0204] Step 2:

[0205] The terminal sends the collected data to the server using a communication method (e.g., Wi-Fi or Bluetooth). Specifically, a timestamp is added to the data, and the data is transferred to the server using a communication protocol.

[0206] Input: Behavioral data and facial expression data stored on the device

[0207] Output: Data sent to the server

[0208] Step 3:

[0209] The server stores the received data in a database, checks the data integrity, and performs preprocessing. Specifically, it checks the data integrity and removes noise and outliers. This preprocessing improves the quality of the data.

[0210] Input: Data sent to and received from the server

[0211] Output: Integrity checked and preprocessed data

[0212] Step 4:

[0213] The server analyzes the preprocessed data and uses machine learning algorithms to identify the pet's behavioral patterns and emotional state. Specifically, the machine learning model is used to classify behavioral data into categories such as "exercising," "resting," and "excited," and to estimate emotions such as "happy" and "anxious" from facial expression data.

[0214] Input: Preprocessed behavioral and facial expression data

[0215] Output: Classified behavioral and emotional states

[0216] Step 5:

[0217] The server estimates the pet's needs based on the analysis results, and generates a notification message (e.g., "Your dog wants to go for a walk" or "Your pet is stressed") to be sent to the owner based on the needs.

[0218] Input: Classified behavioral and emotional states

[0219] Output: The generated notification message

[0220] Step 6:

[0221] The server sends the generated notification message to the user's mobile information terminal (smartphone or tablet) using a communication means. Specifically, it uses push notification to send the user a message containing the analysis results and suggested countermeasures.

[0222] Input: The generated notification message

[0223] Output: The notification message sent to the user's mobile device.

[0224] Step 7:

[0225] The user checks the received message using a mobile information terminal. In the store, the appropriate product or service is selected based on the analysis of the pet's behavior and emotional state. Specifically, the user searches for the relevant product on the store's shelves according to the content of the notification message.

[0226] Input: Notification message sent to mobile device

[0227] Output: User behavior (product selection)

[0228] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0229] The present invention is a system that combines a system that analyzes pet behavior data and facial expression data to accurately estimate the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[0230] System Configuration

[0231] 1. Sensor means

[0232] The wearable sensor terminal is attached to the pet's collar or torso and collects behavioral data such as the pet's acceleration data, heart rate, and activity level.

[0233] The indoor camera serves as a terminal that captures your pet's movements and expressions in real time and saves them as video data.

[0234] 2. Means of communication

[0235] The devices (wearable sensors and indoor cameras) transmit the collected data to a server via Wi-Fi or Bluetooth, and each data set is time-stamped to ensure data synchronization and integrity.

[0236] 3. Analysis method

[0237] The server stores the received data in a database and checks the integrity of the data.

[0238] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[0239] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data.

[0240] 4. Generation means

[0241] The server estimates the pet's desires from the analysis results and generates a message (text or voice) based on them.

[0242] 5. Transmission Method

[0243] The server sends the generated message to the user's smartphone or tablet as a push notification.

[0244] 6. Emotion Engine

[0245] The system further comprises an emotion engine that recognizes the emotions of the user.

[0246] The emotion engine includes a camera and microphone for collecting facial and voice data from the user.

[0247] The server analyzes the user's facial expressions and voice to estimate the user's emotional state.

[0248] The server integrates the pet's desire estimation result obtained by the analysis means with the user's emotional state, and generates a more accurate notification based on the integration result.

[0249] Specific examples

[0250] Data Collection Example

[0251] The terminal (wearable sensor) collects the dog's activity data (e.g., acceleration, heart rate) at regular intervals. The sensor captures the dog's behavioral patterns and sends the data to a server. In parallel, the terminal (indoor camera) captures the dog's movements and facial expressions as video and sends the video to the server.

[0252] Data analysis example

[0253] The server stores the received data in a database and performs preprocessing to remove outliers and noise. It then uses machine learning algorithms to analyze the behavioral and facial expression data. For example, it can identify behavioral patterns such as "exercising," "resting," and "excited" from acceleration and heart rate data, and recognize facial expressions from video data to estimate emotions such as "happiness" and "anxiety."

[0254] Example of pet desire estimation and notification generation

[0255] The server analyzes the behavioral pattern "requesting a walk" and the emotional state "expectation" and generates a message estimating "your dog wants to go for a walk." This message is then sent to the user's smartphone as a push notification.

[0256] Emotion Engine Example

[0257] The system is equipped with a camera to capture the user's facial expressions and a microphone to collect audio. The server analyzes the facial and audio data when the user checks the notification and estimates the user's emotional state. For example, if the user shows a happy expression when checking the notification that their pet is "excited," the server determines that the owner is "very interested in playing with their pet."

[0258] Example of integrated notifications for users and pets

[0259] The server determines from the pet's behavioral data that the pet is in a "stressed state due to lack of exercise" and from the user's facial expression data that the pet is in an "excited state." By integrating this information, the server generates a message to the user saying, "Your dog is stressed due to lack of exercise, but you seem to be in a good mood. Why don't you take a walk together to refresh yourself?"

[0260] This system allows for detailed analysis of the condition of both the pet and the user, and provides more accurate and appropriate feedback based on that analysis, enabling owners to support the health and happiness of their pets and achieve better pet care.

[0261] The processing flow will be explained below.

[0262] Step 1:

[0263] The device (wearable sensor) collects pet behavior data (e.g., acceleration, heart rate, activity level) at regular intervals. This data is recorded in real time and temporarily stored in the built-in memory.

[0264] Step 2:

[0265] The device (indoor camera) captures the pet's movements and expressions and stores them as video data. The camera takes high-resolution still and video images and, if necessary, uses facial recognition technology to identify the pet.

[0266] Step 3:

[0267] The devices transmit collected sensor and camera data over Wi-Fi or Bluetooth to a server, where each data set is time-stamped to ensure data synchronization and integrity.

[0268] Step 4:

[0269] The server stores the received data in a database, where behavioral and facial expression data for each pet is accumulated and used for subsequent analysis.

[0270] Step 5:

[0271] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[0272] Step 6:

[0273] The server then uses machine learning algorithms to analyze the preprocessed data, identifying behavioral patterns such as "exercise," "rest," and "excitement" from the behavioral data, and inferring emotional states such as "happiness," "anxiety," and "fatigue" from the facial expression data.

[0274] Step 7:

[0275] The server then uses the analysis results to estimate the pet's needs. For example, if the server detects that the pet frequently wanders around food and has an anxious expression, it will assume that the pet is hungry.

[0276] Step 8:

[0277] The server generates a message (text or voice) for the user based on the estimated desires. The generated message should be specific and easy to understand. For example, it could be in the form of "Mimi seems hungry."

[0278] Step 9:

[0279] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[0280] Step 10:

[0281] Users receive a notification on their smartphone app, open the app to check the details, and then understand their pet's current condition and needs and choose appropriate actions (e.g., feeding or taking them for a walk).

[0282] Step 11:

[0283] The device (a camera and microphone that are part of the emotion engine) collects the user's facial expression data and voice data in real time. The camera captures the user's face and the microphone records the user's voice.

[0284] Step 12:

[0285] The server analyzes the collected user facial expression and voice data to estimate the user's emotional state. For example, if the user raises their arms and smiles, it will identify this as "joy."

[0286] Step 13:

[0287] The server then integrates the pet's desire estimation results with the user's emotional state and generates more accurate notifications based on the integration results, such as "If your dog is feeling stressed due to lack of exercise and you are feeling excited, we recommend that you take him for a walk together."

[0288] Step 14:

[0289] The server then sends a notification based on the integration results back to the user's smartphone, which includes measures based on the pet's estimated needs and the user's emotional state.

[0290] Step 15:

[0291] The user checks the notification again and takes the recommended action. For example, they select the action "go for a walk." This action relieves stress for the pet and refreshes the user.

[0292] The above is a specific flow of processing steps in the system of the present invention. This system can analyze pet behavior and desires in detail, provide appropriate feedback to the user, and realize more accurate notifications that take the user's emotional state into consideration. This can support the health and happiness of pets and reduce the burden on owners.

[0293] Example 2

[0294] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0295] It is difficult to efficiently analyze pet behavioral and facial expression data and accurately estimate pet needs. Furthermore, there is a need for a method to provide feedback that takes into account the user's emotional state, thereby enabling more appropriate pet care. Furthermore, it is also important to improve the accuracy of analysis by removing noise from the data and detecting outliers.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0297] In this invention, the server includes: a sensor means for collecting pet behavior data and facial expression data; a communication means for receiving data from the sensor means; a storage means for saving the received data; a preprocessing means for performing noise reduction and outlier detection / correction on the received data; an analysis means using a machine learning algorithm to identify the pet's behavior pattern and emotional state from the preprocessed data; a generation means for estimating the pet's desires using the analysis means and generating a notification based on the estimated pet desires; a transmission means for sending the generated notification to a user; an emotion engine including a means for collecting and analyzing user facial expression data and voice data; and a means for integrating the pet desire estimation result obtained by the analysis means with the user's emotional state and generating a notification based on the integration result. This enables detailed analysis of the interactive state between the pet and the user and provides appropriate and accurate feedback.

[0298] The "sensor means" is a device for collecting behavioral data and facial expression data of a pet.

[0299] The "communication means" is a device for transmitting data collected from the sensor means to the server.

[0300] The "storage means" is a device for storing received data in a database.

[0301] The "preprocessing means" is a device that removes noise from the received data and detects and corrects abnormal values.

[0302] An "analysis means" is a device that uses machine learning algorithms to identify the behavioral patterns and emotional states of the pet from the pre-processed data.

[0303] The "generation means" is a device that generates a notification based on the pet's desires estimated by the analysis means.

[0304] The "transmitting means" is a device for transmitting the generated notification to the user.

[0305] An "emotion engine" is a device that collects and analyzes a user's facial expression and voice data to estimate the user's emotional state.

[0306] The present invention is a system that combines a system that analyzes behavioral data and facial expression data of a pet and accurately estimates the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system will be described below.

[0307] Sensor means

[0308] The devices used are a wearable sensor and an indoor camera. The wearable sensor is attached to the pet's collar or torso and collects behavioral data such as acceleration data, heart rate, and activity level. In addition, the indoor camera captures the pet's movements and facial expressions in real time and saves them as video data.

[0309] Specific examples

[0310] For example, the system records acceleration data when a dog runs and changes in heart rate while the dog is eating. In addition, an indoor camera captures the dog's facial expressions in real time.

[0311] communication means

[0312] The devices (wearable sensors and indoor cameras) transmit the collected data via Wi-Fi or Bluetooth to a server, which timestamps each data set and keeps the data synchronized and consistent.

[0313] Specific examples

[0314] The data detected by the sensor is sent to a server in real time, allowing for centralized management of pet activity. For example, data on the moment a dog chases a ball is sent along with its heart rate data at that time.

[0315] Data storage

[0316] The server stores the received data in a database, which makes it possible to refer to all past data and perform comparative analysis.

[0317] Specific examples

[0318] Not only the data from this walk, but also data from past walks is saved, allowing you to track changes at each point in time.

[0319] Data Preprocessing

[0320] The server removes noise from the stored data and detects and corrects outliers to improve data accuracy, enabling highly reliable data analysis.

[0321] Specific examples

[0322] A process is performed to remove abnormal heart rate data caused by temporary malfunction of the sensor.

[0323] Data analysis

[0324] The server uses machine learning algorithms to analyze the behavioral and facial expression data, identify behavioral patterns, and estimate the pet's emotional state.

[0325] Specific examples

[0326] Data showing that the dog is still for a certain period of time is used to identify the dog as "resting," and data on the dog's facial expression is used to estimate its "sense of security."

[0327] Message Generation

[0328] Based on the analysis results, the server generates notifications that infer your pet's needs, such as "Your dog wants a walk" or "It's time for exercise!"

[0329] Send notifications

[0330] The server sends the generated notification to the user's smartphone or tablet as a push notification, allowing the user to keep track of their pet's status in real time.

[0331] Specific examples

[0332] A notification will appear on your smartphone saying, "Your dog needs more exercise. We recommend taking it for a walk."

[0333] Emotion Engine

[0334] The system includes an emotion engine that recognizes the user's emotions. It uses a camera and microphone to collect the user's facial expressions and voice, which are then analyzed by a server.

[0335] Specific examples

[0336] If the user has a surprised expression, the emotion is analyzed and recognized as "surprise."

[0337] Integrated analytics and advanced notification generation

[0338] The server integrates the pet's desire estimation results with the user's emotional state to generate more accurate notifications.

[0339] Specific examples

[0340] It integrates the fact that a pet is lacking exercise with the user's relaxation and generates a notification such as, "Your dog is lacking exercise, but you seem relaxed. Would you like to join us for some light exercise?"

[0341] Prompt Sentence Examples

[0342] Data collection:

[0343] "Use wearable sensors to collect acceleration and heart rate data from your dog."

[0344] "Use an indoor camera to capture facial expression data of a dog."

[0345] Data transmission:

[0346] "Send the collected data to the server via Wi-Fi."

[0347] Data Retention:

[0348] Save the received data in the database.

[0349] Data preprocessing:

[0350] "Denoise your data and detect outliers"

[0351] Data Analysis:

[0352] "Implement machine learning algorithms for behavioral pattern identification and emotional state estimation"

[0353] Message Generation:

[0354] "Generate a message that estimates your pet's desires based on the results of data analysis."

[0355] Notification sent:

[0356] "Send the generated message to the user's smartphone via push notification."

[0357] Emotion recognition:

[0358] "Recognize the user's facial expressions and voice and analyze their emotions"

[0359] Integrated analytics and advanced notification generation:

[0360] "Integrate pet needs and user emotions to generate accurate notifications"

[0361] This system allows detailed analysis of the pet and user's condition and provides appropriate and accurate feedback, leading to better pet care.

[0362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0363] Step 1: Data collection

[0364] The devices (wearable sensors and indoor cameras) collect the dog's acceleration, heart rate, activity level, movement, and facial expression data in real time. The wearable sensors measure these data, and the indoor cameras capture video data.

[0365] Input: Dog activity and facial expressions

[0366] Output: Acceleration data, heart rate data, video data

[0367] Specifically, the wearable sensor measures the dog's acceleration and heart rate every second, and the indoor camera captures video at 30 frames per second. For example, when the dog starts exercising, the acceleration and heart rate data change, and the dog's movements are recorded on video.

[0368] Step 2: Send data

[0369] The devices transmit the collected data to a server via Wi-Fi or Bluetooth, and each data set is time-stamped to ensure data synchronization and integrity.

[0370] Input: Collected acceleration data, heart rate data, video data

[0371] Output: The dataset sent to the server

[0372] Specifically, the device collects all the data collected every 10 seconds and sends it to the server via Wi-Fi. For example, data from 10 seconds during which a dog is eating is sent to the server.

[0373] Step 3: Save Data

[0374] The server stores the received data in a database, which makes it possible to refer to all past data.

[0375] Input: The dataset sent to the server

[0376] Output: Data stored in the database

[0377] Specifically, the server classifies the received data by timestamp and stores it in the appropriate table in the database. For example, heart rate data is stored in the "heart rate" table, and video data is stored in the "video" table.

[0378] Step 4: Data Preprocessing

[0379] The server removes noise from the stored data and detects and corrects outliers, thereby improving the accuracy of the data.

[0380] Input: Data stored in a database

[0381] Output: Preprocessed data

[0382] Specifically, the server applies outlier detection algorithms to detect and remove, for example, extremely high heart rates. It also applies noise reduction filters to smooth the acceleration data.

[0383] Step 5: Data analysis

[0384] The server uses machine learning algorithms to analyze the behavioral and facial expression data, identify behavioral patterns, and infer the pet's emotional state.

[0385] Input: Preprocessed data

[0386] Output: Behavioral patterns and emotional states

[0387] Specifically, the server uses the collected acceleration and heart rate data to identify behavioral patterns such as "exercising" or "resting," and infers emotions such as "happiness" or "anxiety" from the video data. For example, if a sudden change in acceleration data coincides with a rise in heart rate, it will identify this as "exercising."

[0388] Step 6: Message Generation

[0389] Based on the analysis results, the server estimates the pet's needs and generates a notification based on them.

[0390] Input: behavioral patterns and emotional states

[0391] Output: Notification message

[0392] Specifically, the server combines the behavioral pattern of "lack of exercise" with the emotional state of "discomfort" to generate a message that says, "Your dog needs exercise. Take it for a walk."

[0393] Step 7: Send notification

[0394] The server sends the generated notification to the user's smartphone or tablet as a push notification.

[0395] Input: Notification message

[0396] Output: Push notification to user device

[0397] Specifically, the server sends the generated notification message to the user interface API, and a notification such as "Your dog needs more exercise. Please take it for a walk" is displayed on the smartphone.

[0398] Step 8: Emotion Recognition

[0399] The system includes an emotion engine that recognizes the user's emotions. The camera and microphone collect the user's facial expressions and voice, which are then analyzed by the server.

[0400] Input: User's facial expression data and voice data

[0401] Output: User's emotional state

[0402] Specifically, when a user plays with a pet, a camera and microphone capture the scene, and the server analyzes the footage to recognize the user's "joy."

[0403] Step 9: Integrated analytics and advanced notification generation

[0404] The server integrates the pet's desire estimation results with the user's emotional state to generate more accurate notifications.

[0405] Input: Pet behavior patterns and emotional state, user emotional state

[0406] Output: Consolidated notification message

[0407] Specifically, the server integrates the fact that the pet is lacking exercise with the user's relaxation and generates a notification saying, "Your dog is lacking exercise. Let's go for a walk together to refresh yourself."

[0408] Through these processing steps, the conditions of the pet and the user can be analyzed in detail, and appropriate and accurate feedback can be provided.

[0409] (Application example 2)

[0410] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0411] Current pet care systems only estimate pet needs based on behavioral and emotional data, but are unable to provide feedback that takes into account the user's emotional state. As a result, they lack concrete support for deepening communication and relationships between pets and users. Furthermore, they are unable to order pet food at the appropriate time to meet a pet's appetite, creating issues in terms of pet health management and user convenience.

[0412] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes sensor means for collecting behavioral data and facial expression data of the pet, communication means for receiving data from the sensor means, analysis means for analyzing the received data and inferring the pet's desires, emotion engine means for collecting and analyzing user emotion data, generation means for generating a notification based on the inferred pet's desires and the analyzed user's emotional state, and transmission means for transmitting the generated notification to the user. This makes it possible to provide more appropriate and timely feedback based on the pet's desires and the user's emotional state, thereby improving the health management and quality of life of the pet and the user.

[0413] "Sensor means" refers to a device used to collect behavioral data or facial expression data of a pet or user, and includes wearable sensors, indoor cameras, cameras, and microphones.

[0414] The "communication means" is a device for transmitting data collected from the sensor means to the server, and includes wireless communication technology and wired communication technology.

[0415] An "analysis means" is a device or program that processes the received data and uses machine learning algorithms to identify the pet's behavioral patterns and needs, as well as the user's emotional state.

[0416] The "emotion engine means" is a device or program that collects and analyzes facial expression data and voice data of the user to estimate the user's emotional state.

[0417] The "generating means" is a device or program that generates a notification message based on the analyzed pet's desires and the user's emotional state.

[0418] The "transmission means" is a device or program for transmitting the generated notification to the user's mobile terminal or the like as a push notification.

[0419] A "wearable sensor" is a sensor device that is attached to a pet's collar or body and collects data such as the pet's acceleration, heart rate, and activity level.

[0420] An "indoor camera" is a camera device that captures pet movements and facial expressions in real time and collects them as video data.

[0421] A "camera" is a photographing device for capturing the user's facial expression.

[0422] A "microphone" is a recording device for collecting a user's voice data.

[0423] A "machine learning algorithm" is an algorithm that analyzes large amounts of data, learns patterns and features, and makes predictions and classifications about future data.

[0424] This invention is a system that combines a system that analyzes pet behavior data and facial expression data to accurately estimate the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[0425] System Configuration

[0426] 1. Sensor means

[0427] Wearable sensors: These are attached to a pet's collar or torso and collect behavioral data such as pet acceleration data, heart rate, and activity level.

[0428] Indoor camera: This captures your pet's movements and expressions in real time and saves them as video data.

[0429] Camera and microphone: This is for collecting facial and voice data from the user.

[0430] 2. Means of communication

[0431] Wi-Fi or Bluetooth: This is used to transmit collected data to a server, where each data set is time-stamped to keep the data synchronized and consistent.

[0432] 3. Analysis method

[0433] The server stores the received data in a database and checks the integrity of the data.

[0434] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[0435] The server uses machine learning algorithms to analyze the behavioral patterns and emotional state of the pet from the behavioral and facial expression data, as well as the emotional state of the user.

[0436] 4. Generation means

[0437] The server integrates the pet's desires and the user's emotional state from the analysis results and generates a message (e.g., text or voice) based on the integration.

[0438] 5. Transmission Method

[0439] The server sends the generated message to the user's smartphone or tablet as a push notification.

[0440] Example

[0441] Examples of data collection:

[0442] The terminal (wearable sensor) collects the dog's activity data (e.g., acceleration, heart rate) at regular intervals. The sensor captures the dog's behavioral patterns and sends the data to a server. In parallel, the terminal (indoor camera) captures the dog's movements and facial expressions as video and sends the video to the server.

[0443] An example of analysis:

[0444] The server stores the received data in a database and performs preprocessing to remove outliers and noise. It then uses machine learning algorithms to analyze the behavioral and facial expression data. For example, it can identify behavioral patterns such as "exercising," "resting," and "excited" from acceleration and heart rate data, and recognize facial expressions from video data to estimate emotions such as "happiness" and "anxiety."

[0445] An example of pet desire estimation and notification generation:

[0446] The server analyzes the behavioral pattern "requesting a walk" and the emotional state "expectation" and generates a message estimating "your dog wants to go for a walk." This message is then sent to the user's smartphone as a push notification.

[0447] An example of an emotion engine:

[0448] The system is equipped with a camera to capture the user's facial expressions and a microphone to collect audio. The server analyzes the facial and audio data when the user checks the notification and estimates the user's emotional state. For example, if the user shows a happy expression when checking the notification that their pet is "excited," the server determines that the owner is "very interested in playing with their pet."

[0449] An example of a unified notification for users and pets:

[0450] The server determines from the pet's behavioral data that the pet is in a "stressed state due to lack of exercise" and from the user's facial expression data that the pet is in an "excited state." By integrating this information, the server generates a message to the user saying, "Your dog is stressed due to lack of exercise, but you seem to be in a good mood. Why don't you take a walk together to refresh yourself?"

[0451] Examples and prompts:

[0452] Examples:

[0453] Sensor data: {"timestamp": "2023-10-01T10:00:00", "acceleration": 0.45, "heart_rate": 120}

[0454] Camera data: {"timestamp": "2023-10-01T10:00:00", "image": "base64_encoded_image_data"}

[0455] User data: {"timestamp": "2023-10-01T10:00:00", "expression": "smiling", "voice_tone": "neutral"}

[0456] Example prompt sentence:

[0457] Analyze the behavioral patterns of the user's pet based on sensor data and camera data, and infer whether the pet is hungry. Also, estimate the user's emotions based on the user's facial expression data. If the pet is hungry and the user is happy, generate a message suggesting the user to order pet food. The following is sample data: Pet-related sensor data: {"timestamp": "2023-10-01T10:00:00", "acceleration": 0.45, "heart_rate": 120}, Camera data: {"timestamp": "2023-10-01T10:00:00", "image": "base64_encoded_image_data"}, User data: {"timestamp": "2023-10-01T10:00:00", "expression": "smiling", "voice_tone": "neutral"}

[0458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0459] Step 1:

[0460] The devices (wearable sensors and indoor cameras) collect pet behavior data (e.g., acceleration, heart rate) and facial expression data at regular intervals. The inputs are raw data from the sensors (acceleration, heart rate, video). The output is collected data with timestamps.

[0461] Step 2:

[0462] The device sends the collected data to the server via Wi-Fi or Bluetooth. The input is the raw data collected by the device and a timestamp. The output is the data transferred to the server.

[0463] Step 3:

[0464] The server stores the received data in a database and checks the integrity of the data. The input is the time-stamped data sent from the device. The output is the data whose integrity has been checked and stored in the database.

[0465] Step 4:

[0466] The server performs preprocessing on the received data, such as noise removal and outlier detection. The input is the received data, and the output is the data with noise removed and outliers corrected.

[0467] Step 5:

[0468] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data, as well as the user's emotional state. The inputs are preprocessed behavioral data, facial expression data, and the user's facial expression data. The output is the pet's behavioral patterns (e.g., exercising, resting, excited) and emotional state (e.g., happy, anxious), as well as the user's emotional state.

[0469] Step 6:

[0470] The server integrates the pet's needs and the user's emotional state from the analysis results and generates a message based on them. The inputs are the analyzed pet's needs and the user's emotional state. The output is a generated message (e.g., "Your dog wants to go for a walk") based on the pet's needs and the user's emotional state.

[0471] Step 7:

[0472] The server generates the message and sends it to the user's smartphone or tablet as a push notification. The input is the generated notification message. The output is the push notification sent to the user's smartphone.

[0473] The above are the specific processing steps for implementing the invention. This system analyzes the behavioral and facial expression data of the pet, and is able to provide more appropriate feedback and notifications that take into account the pet's needs and the user's emotional state.

[0474] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0475] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0476] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0477] [Second embodiment]

[0478] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0479] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0480] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0481] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0482] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0483] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0484] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0485] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0486] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0487] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0488] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0489] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0490] The present invention provides a system that analyzes behavioral data and facial expression data of a pet, accurately estimates the pet's desires, and notifies the pet owner of the desires. Specific embodiments for implementing this system will be described below.

[0491] System Configuration

[0492] 1. Sensor means

[0493] The wearable sensor terminal is attached to the pet's collar or torso and collects behavioral data such as the pet's acceleration data, heart rate, and activity level.

[0494] The indoor camera serves as a terminal that captures your pet's movements and expressions in real time and saves them as video data.

[0495] 2. Means of communication

[0496] The devices (wearable sensors and indoor cameras) transmit the collected data to a server using communication technologies such as Wi-Fi and Bluetooth. The transmitted data includes a timestamp, facilitating data synchronization.

[0497] 3. Analysis method

[0498] The server stores the received data in a database and checks the integrity of the data.

[0499] The server performs preprocessing on the received data, such as noise removal and outlier removal, to improve the accuracy of the analysis.

[0500] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data. Specifically, it classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[0501] 4. Generation means

[0502] The server uses the analysis results to estimate the pet's needs and generates a message (text or voice) based on that information, such as "Your dog wants to go for a walk" or "Momo is hungry."

[0503] 5. Transmission Method

[0504] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[0505] Specific examples

[0506] Data Collection Example

[0507] The device (wearable sensor) collects the cat's activity data (especially its behavior walking around the room at night) at regular intervals. The sensor measures the cat's acceleration and heart rate and sends the data to the server. At the same time, the device (indoor camera) captures the cat's movements as video and sends it to the server.

[0508] Data analysis example

[0509] The server first stores the received data in a database and performs preprocessing to remove noise and outliers. It then analyzes the data using machine learning algorithms. For example, it can identify a "restless" behavior pattern based on frequent nighttime movements and elevated heart rates, and detect "anxious facial expressions" using facial recognition.

[0510] Message Generation and Notification Example

[0511] Based on the analysis results of the behavioral pattern "restless" and the emotional state "anxious expression," the server generates a message saying, "Momo may be feeling stressed at night." The message is sent to the user's smartphone as a push notification. The user receives the notification on their smartphone app and checks the details.

[0512] User Interface Example

[0513] After checking the notification, the user can choose to use an aroma diffuser to relax their cat based on the information in the app that "Momo is feeling stressed at night." They can also use the in-app communication platform to discuss the issue with other pet owners and seek additional advice.

[0514] This system can accurately estimate a pet's needs from its behavior and facial expressions, and provide that information to the owner quickly and appropriately. This will support the health and happiness of pets and reduce the burden on owners. It also provides a platform that promotes communication between pet owners, allowing them to share knowledge and experiences about pet care.

[0515] The processing flow will be explained below.

[0516] Step 1:

[0517] The device (wearable sensor) collects pet behavior data (e.g., acceleration, heart rate, activity level) at regular intervals. This data is recorded in real time and temporarily stored in the built-in memory.

[0518] Step 2:

[0519] The device (indoor camera) captures your pet's movements and expressions and stores them as video data. The camera takes high-resolution still images and videos, and uses facial recognition technology to identify your pet if necessary.

[0520] Step 3:

[0521] The devices transmit collected sensor and camera data over Wi-Fi or Bluetooth to a server, where each data set is time-stamped to ensure data synchronization and integrity.

[0522] Step 4:

[0523] The server stores the received data in a database, where behavioral and facial expression data for each pet is accumulated and used for subsequent analysis.

[0524] Step 5:

[0525] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[0526] Step 6:

[0527] The server then uses machine learning algorithms to analyze the preprocessed data, identifying behavioral patterns such as "exercise," "rest," and "excitement" from the behavioral data, and inferring emotional states such as "happiness," "anxiety," and "fatigue" from the facial expression data.

[0528] Step 7:

[0529] The server then uses the analysis results to estimate the pet's needs. For example, if the server detects that the pet frequently wanders around food and has an anxious expression, it will assume that the pet is hungry.

[0530] Step 8:

[0531] The server generates a message (text or voice) for the user based on the estimated desires. The generated message should be specific and easy to understand. For example, it could be in the form of "Mimi seems hungry."

[0532] Step 9:

[0533] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[0534] Step 10:

[0535] Users receive a notification on their smartphone app, open the app to check the details, and then understand their pet's current condition and needs and choose appropriate actions (e.g., feeding or taking them for a walk).

[0536] Step 11:

[0537] Users can use the in-app communication platform to share information with other pet owners, for example by posting questions such as, "Momo seems to be stressed at night. How do you deal with it?"

[0538] Step 12:

[0539] The server collects answers from other users in real time and displays them to the user who posted the question. The answers include specific advice and similar experiences that can improve the quality of pet care.

[0540] The above is a specific flow of processing steps in the system of the present invention. This system can analyze pet behavior and desires in detail and provide appropriate feedback to the user. The user can then take prompt and effective action based on the information obtained to support the health and happiness of their pet.

[0541] Example 1

[0542] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0543] Understanding pet behavior and emotions is important for maintaining pet health and happiness, but currently owners have to manually observe and judge, which is time-consuming and often inaccurate. It is also difficult to properly understand and respond to pet needs and stress, which can result in a risk of compromising pet health and happiness.

[0544] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0545] In this invention, the server includes a sensor means for collecting behavioral data and facial expression data of the pet, a communication means for receiving data from the sensor means, a preprocessing means for saving the received data and removing noise and outliers, an analysis means for analyzing the preprocessed data and estimating the behavioral patterns and emotional state of the pet, a generation means for generating a notification using natural language generation technology based on the estimated desires of the pet, and a transmission means for sending the generated notification to the user as a push notification. This makes it possible to more accurately and quickly analyze the behavioral and emotional state of the pet and to send notifications to the owner at appropriate times.

[0546] "Sensor means" refers to a device installed to collect data on the behavior and facial expressions of pets. Specifically, it includes wearable sensors and indoor cameras.

[0547] "Communication means" refers to the technical means for transmitting data collected from the sensor means to the server. Specifically, it includes wireless communication technologies such as Wi-Fi and Bluetooth.

[0548] "Pre-processing means" refers to technical means for storing received data and cleaning the data, such as removing noise and outliers. Specifically, this includes database management systems and data processing software.

[0549] "Analysis means" refers to technical means for analyzing the pre-processed data and inferring the pet's behavioral patterns and emotional state, including machine learning algorithms and data analysis software.

[0550] The "generation means" refers to a technical means for generating a notification about the pet's needs in natural language based on the analysis results. Specifically, it includes natural language generation technology.

[0551] "Transmission means" refers to the technical means for transmitting the generated notification to the user as a push notification. Specifically, it includes the API of the push notification service.

[0552] The present invention provides a system that analyzes behavioral data and facial expression data of a pet, accurately estimates the pet's desires, and notifies the pet's owner of the desires. Specific embodiments for implementing this system will be described below.

[0553] System Configuration

[0554] Sensor means

[0555] Wearable sensors as terminals are attached to pets' collars or bodies and collect behavioral data such as pet acceleration data, heart rate, and activity levels. Specifically, they are generally called wearable devices. Indoor cameras as terminals capture pets' movements and facial expressions in real time and save them as video data. Specifically, they are generally called surveillance cameras. This allows data on pets' behavior and facial expressions to be continuously obtained.

[0556] communication means

[0557] The terminals (wearable devices and surveillance cameras) transmit the collected data to a server using communication technologies such as Wi-Fi or Bluetooth. Specifically, a wireless communication module is used. The transmitted data includes a timestamp to ensure data synchronization.

[0558] Pretreatment means

[0559] The server stores the received data in a database and checks the data integrity. The specific database used here is generally called a relational database management system (RDBMS). Next, preprocessing such as noise removal and outlier removal is performed using the Python Pandas library. This processing improves the accuracy of the data analysis.

[0560] Analysis means

[0561] The server uses machine learning algorithms to analyze behavioral and facial expression data. Specifically, it uses libraries such as TensorFlow, and is generally referred to as a machine learning platform. It classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[0562] generation means

[0563] The server uses the analysis results to estimate the pet's needs and generates a message (text or voice) based on that information. Specifically, it uses natural language generation technology and a generative AI model (e.g., GPT-3). For example, it generates specific messages such as "Your dog wants to go for a walk" or "Momo is hungry."

[0564] Transmission method

[0565] The server then sends the generated message to the user's smartphone or tablet as a push notification, using the API of a push notification service (e.g., Firebase Cloud Messaging). The notification contains the analysis results and suggested solutions.

[0566] Specific examples

[0567] Data Collection Example

[0568] The terminal (wearable device) collects the cat's activity data (especially its behavior walking around the room at night) at regular intervals. The sensor measures the cat's acceleration and heart rate and sends the data to the server. At the same time, the terminal (surveillance camera) captures the cat's movements as video and sends it to the server as well.

[0569] Data analysis example

[0570] The server stores the received data in a relational database management system (RDBMS) and preprocesses it using Python's Pandas library to remove noise and outliers. The data is then analyzed using machine learning algorithms powered by TensorFlow. For example, it identifies a "restless" behavior pattern based on frequent nighttime movements and elevated heart rates, and uses facial recognition to detect "anxious facial expressions."

[0571] Message Generation and Notification Example

[0572] Based on the analysis results of the behavioral pattern "restless" and the emotional state "anxious expression," the server uses natural language generation technology (generative AI model) to generate a message saying "Momo may be feeling stressed at night." The message is then sent as a push notification to the user's smartphone using a push notification service (Firebase Cloud Messaging). The user receives the notification in their smartphone app and checks the details.

[0573] Prompt Sentence Examples

[0574] "Infer a pet's needs from its behavioral and facial expression data and generate a message to notify the owner. For example, if a cat moves around frequently at night and its heart rate increases, explain what kind of message should be generated based on the analysis results."

[0575] This system can accurately predict pet needs from their behavior and facial expressions, and provide them to their owners quickly and appropriately. This supports the health and happiness of pets and reduces the burden on owners. It also provides a platform that promotes communication between pet owners, allowing them to share knowledge and experiences about pet care.

[0576] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0577] Program processing flow

[0578] Step 1: Data collection

[0579] The terminal uses a wearable device to acquire the pet's behavioral data (acceleration, heart rate, activity level) and uses a surveillance camera to collect the pet's movements and facial expressions as video data.

[0580] Input: Sensor values ​​from wearable devices (acceleration data, heart rate data), video data from surveillance cameras

[0581] Output: Collected behavioral and video data

[0582] Specific operation: The wearable device uses sensors to acquire data at regular intervals (e.g., every minute) and temporarily stores it in its internal memory. The surveillance camera captures video in real time and also temporarily stores it.

[0583] Step 2: Send data

[0584] The device sends the collected data to a server via Wi-Fi or Bluetooth.

[0585] Input: Collected behavioral and video data

[0586] Output: Data packets sent to the server

[0587] How it works: Pet behavior data and video data are sent to a server via Wi-Fi, where a timestamp is added to ensure data synchronization.

[0588] Step 3: Data storage and preprocessing

[0589] The server stores the received data in a database and performs preprocessing (noise removal and outlier removal).

[0590] Input: Behavioral data and video data sent from the device

[0591] Output: Preprocessed data

[0592] How it works: The data is stored in a database management system and a script is run to remove noise and outliers using the Python Pandas library.

[0593] Step 4: Data analysis

[0594] The server uses the preprocessed data to analyze it using machine learning algorithms to estimate the pet's behavioral patterns and emotional state.

[0595] Input: Preprocessed data

[0596] Output: Analysis results of behavioral patterns and emotional states

[0597] Specific behavior: The data to be analyzed is input into a machine learning platform, and algorithms such as TensorFlow are used to classify and estimate the pet's behavioral patterns (e.g., "exercising," "resting," "excited") and emotional state (e.g., "happy," "anxious").

[0598] Step 5: Message Generation

[0599] The server uses natural language generation technology (generative AI model) based on the analysis results to generate a notification message.

[0600] Input: Analysis results of behavioral patterns and emotional states

[0601] Output: The generated notification message

[0602] Specific operation: A prompt sentence is input to the generative AI model, and a notification message for the user is created based on the generated text.

[0603] Step 6: Send the message

[0604] The server sends the generated notification message to the user's smartphone via a push notification service.

[0605] Input: The generated notification message

[0606] Output: Notification sent to the user's smartphone

[0607] Specific operation: Calls the API of the push notification service and sends the generated notification message to the user's smartphone.

[0608] Step 7: User Interface Support

[0609] The user checks the notification received on their smartphone and selects the necessary action based on the pet's condition.

[0610] Input: Received notification message

[0611] Output: Selected action (e.g., activate aroma diffuser for stress relief)

[0612] Specific Action: The user taps the notification to open the app, checks the detailed information, and selects the appropriate action if necessary. In this case, the user presses a button within the app to perform a specific action.

[0613] (Application example 1)

[0614] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0615] Today's pet owners find it difficult to accurately understand their pets' behavior and emotional state and provide appropriate care and product selection. In particular, physical stores such as pet goods shops lack systems that can quickly recommend the right product for each pet's condition. This means pet owners spend a lot of time choosing the right product in the store, which can increase stress for their pets. To solve this problem, a system is needed that collects and analyzes pet behavior and facial expression data and notifies users in real time.

[0616] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0617] In this invention, the server includes a sensor means for collecting behavioral data and facial expression data of the pet, a communication means for receiving data from the sensor means, an analysis means for analyzing the received data and estimating the pet's desires, a generation means for generating a notification based on the estimated pet's desires, and a transmission means for transmitting the generated notification to the user's mobile information terminal and suggesting products in the store, thereby enabling optimal product selection based on the pet's behavior and emotional state in a physical store.

[0618] "Pet behavior data" is information about a pet's physical activity, movements, and behavior.

[0619] "Facial expression data" is information related to the movements of a pet's face and changes in facial expression.

[0620] The "sensor means" is a device for collecting behavioral data and facial expression data of a pet.

[0621] A "wearable sensor" is a device that can be attached to a pet's collar or torso and measures the pet's movements and biological data.

[0622] An "indoor camera" is a video camera installed to capture your pet's movements and expressions.

[0623] "Communication means" refers to the technology used to transmit data from the sensor means to the server, and includes Wi-Fi, Bluetooth, etc.

[0624] The "analysis means" is a system for processing the received data and analyzing the pet's desires and emotional state.

[0625] A "machine learning algorithm" is a computational method that learns patterns from incoming data and identifies pet behaviors and emotions.

[0626] A "generator" is a system that creates a notification message based on the analyzed data.

[0627] "Transmission means" refers to a technique for transmitting the generated notification to the user's mobile information terminal.

[0628] A "user's mobile information terminal" is a mobile information device such as a smartphone or tablet used by the owner.

[0629] "Making product suggestions in-store" means recommending appropriate products to pet owners based on the analyzed condition of their pets.

[0630] The present invention provides a system that analyzes behavioral data and facial expression data of pets in a physical store, estimates the pet's desires, and proposes optimal products to pet owners. Specific embodiments for implementing this system are described below.

[0631] System Configuration

[0632] 1. Sensor means

[0633] Wearable sensor: A device that is attached to a pet's collar or body and collects behavioral data such as acceleration data, heart rate, and activity level.

[0634] Indoor camera: A device installed inside the store that captures pets' movements and expressions in real time and obtains them as video data.

[0635] 2. Means of communication

[0636] Communication method: This technology uses Wi-Fi or Bluetooth to transmit data collected from wearable sensors and indoor cameras to a server. The transmitted data includes a timestamp, making data synchronization easy.

[0637] 3. Analysis method

[0638] Analysis method: The server stores the received data in a database and checks its integrity. First, it performs preprocessing such as noise removal and outlier removal, then uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data. Specifically, it classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[0639] 4. Generation means

[0640] Generation method: The server estimates the pet's needs from the analysis results and generates a message (text or voice) based on the estimate. For example, it generates a specific message such as "Your dog wants to go for a walk" or "Your pet is stressed."

[0641] 5. Transmission Method

[0642] Transmission method: The server sends the generated message to the user's mobile information device (smartphone or tablet) as a push notification. The notification contains the analysis results and suggested countermeasures.

[0643] Explanation of program processing

[0644] The server uses the following hardware and software to collect and analyze pet behavior and facial expression data: wearable sensors, indoor cameras, smartphones, and tablets; and the requests library for communication processing, SciPy, and TensorFlow for data analysis.

[0645] Data is collected in real time by wearable sensors and indoor cameras and transmitted to a server via communication means. The server stores the received data in a database and first performs preprocessing. This preprocessing includes noise removal and outlier elimination to improve data quality. Then, machine learning algorithms are used to analyze the pet's behavioral patterns and emotional state. Based on the results of this analysis, the pet's desires are estimated and a notification message is generated for the owner. This notification message is then sent to the user's mobile information terminal, and appropriate product recommendations are made to the owner in the store.

[0646] Specific examples

[0647] If a dog brought into a pet goods shop looks anxious, the system will analyze data collected through wearable sensors and indoor cameras and send a message to the owner's smartphone saying, "This dog is likely feeling anxious. We recommend a toy that will have a relaxing effect."

[0648] Prompt Sentence Examples

[0649] "Please create an application that analyzes pet behavior data (acceleration data, heart rate) and facial expression data (camera footage), estimates the pet's condition in real time, and suggests appropriate products to the owner."

[0650] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0651] Step 1:

[0652] The devices (wearable sensors and indoor cameras) collect pet behavior data (e.g., acceleration data, heart rate) and facial expression data (e.g., camera footage). Specifically, the devices acquire data in real time from sensors attached to the pet's collar or body and temporarily store the data.

[0653] Input: Acceleration data, heart rate data, and camera footage collected from your pet

[0654] Output: Collected behavioral and facial expression data

[0655] Step 2:

[0656] The terminal sends the collected data to the server using a communication method (e.g., Wi-Fi or Bluetooth). Specifically, a timestamp is added to the data, and the data is transferred to the server using a communication protocol.

[0657] Input: Behavioral data and facial expression data stored on the device

[0658] Output: Data sent to the server

[0659] Step 3:

[0660] The server stores the received data in a database, checks the data integrity, and performs preprocessing. Specifically, it checks the data integrity and removes noise and outliers. This preprocessing improves the quality of the data.

[0661] Input: Data sent to and received from the server

[0662] Output: Integrity checked and preprocessed data

[0663] Step 4:

[0664] The server analyzes the preprocessed data and uses machine learning algorithms to identify the pet's behavioral patterns and emotional state. Specifically, the machine learning model is used to classify behavioral data into categories such as "exercising," "resting," and "excited," and to estimate emotions such as "happy" and "anxious" from facial expression data.

[0665] Input: Preprocessed behavioral and facial expression data

[0666] Output: Classified behavioral and emotional states

[0667] Step 5:

[0668] The server estimates the pet's needs based on the analysis results, and generates a notification message (e.g., "Your dog wants to go for a walk" or "Your pet is stressed") to be sent to the owner based on the needs.

[0669] Input: Classified behavioral and emotional states

[0670] Output: The generated notification message

[0671] Step 6:

[0672] The server sends the generated notification message to the user's mobile information terminal (smartphone or tablet) using a communication means. Specifically, it uses push notification to send the user a message containing the analysis results and suggested countermeasures.

[0673] Input: The generated notification message

[0674] Output: The notification message sent to the user's mobile device.

[0675] Step 7:

[0676] The user checks the received message using a mobile information terminal. In the store, the appropriate product or service is selected based on the analysis of the pet's behavior and emotional state. Specifically, the user searches for the relevant product on the store's shelves according to the content of the notification message.

[0677] Input: Notification message sent to mobile device

[0678] Output: User behavior (product selection)

[0679] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0680] The present invention is a system that combines a system that analyzes pet behavior data and facial expression data to accurately estimate the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[0681] System Configuration

[0682] 1. Sensor means

[0683] The wearable sensor terminal is attached to the pet's collar or torso and collects behavioral data such as the pet's acceleration data, heart rate, and activity level.

[0684] The indoor camera serves as a terminal that captures your pet's movements and expressions in real time and saves them as video data.

[0685] 2. Means of communication

[0686] The devices (wearable sensors and indoor cameras) transmit the collected data to a server via Wi-Fi or Bluetooth, and each data set is time-stamped to ensure data synchronization and integrity.

[0687] 3. Analysis method

[0688] The server stores the received data in a database and checks the integrity of the data.

[0689] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[0690] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data.

[0691] 4. Generation means

[0692] The server estimates the pet's desires from the analysis results and generates a message (text or voice) based on them.

[0693] 5. Transmission Method

[0694] The server sends the generated message to the user's smartphone or tablet as a push notification.

[0695] 6. Emotion Engine

[0696] The system further comprises an emotion engine that recognizes the emotions of the user.

[0697] The emotion engine includes a camera and microphone for collecting facial and voice data from the user.

[0698] The server analyzes the user's facial expressions and voice to estimate the user's emotional state.

[0699] The server integrates the pet's desire estimation result obtained by the analysis means with the user's emotional state, and generates a more accurate notification based on the integration result.

[0700] Specific examples

[0701] Data Collection Example

[0702] The terminal (wearable sensor) collects the dog's activity data (e.g., acceleration, heart rate) at regular intervals. The sensor captures the dog's behavioral patterns and sends the data to a server. In parallel, the terminal (indoor camera) captures the dog's movements and facial expressions as video and sends the video to the server.

[0703] Data analysis example

[0704] The server stores the received data in a database and performs preprocessing to remove outliers and noise. It then uses machine learning algorithms to analyze the behavioral and facial expression data. For example, it can identify behavioral patterns such as "exercising," "resting," and "excited" from acceleration and heart rate data, and recognize facial expressions from video data to estimate emotions such as "happiness" and "anxiety."

[0705] Example of pet desire estimation and notification generation

[0706] The server analyzes the behavioral pattern "requesting a walk" and the emotional state "expectation" and generates a message estimating "your dog wants to go for a walk." This message is then sent to the user's smartphone as a push notification.

[0707] Emotion Engine Example

[0708] The system is equipped with a camera to capture the user's facial expressions and a microphone to collect audio. The server analyzes the facial and audio data when the user checks the notification and estimates the user's emotional state. For example, if the user shows a happy expression when checking the notification that their pet is "excited," the server determines that the owner is "very interested in playing with their pet."

[0709] Example of integrated notifications for users and pets

[0710] The server determines from the pet's behavioral data that the pet is in a "stressed state due to lack of exercise" and from the user's facial expression data that the pet is in an "excited state." By integrating this information, the server generates a message to the user saying, "Your dog is stressed due to lack of exercise, but you seem to be in a good mood. Why don't you take a walk together to refresh yourself?"

[0711] This system allows for detailed analysis of the condition of both the pet and the user, and provides more accurate and appropriate feedback based on that analysis, enabling owners to support the health and happiness of their pets and achieve better pet care.

[0712] The processing flow will be explained below.

[0713] Step 1:

[0714] The device (wearable sensor) collects pet behavior data (e.g., acceleration, heart rate, activity level) at regular intervals. This data is recorded in real time and temporarily stored in the built-in memory.

[0715] Step 2:

[0716] The device (indoor camera) captures the pet's movements and expressions and stores them as video data. The camera takes high-resolution still and video images and, if necessary, uses facial recognition technology to identify the pet.

[0717] Step 3:

[0718] The devices transmit collected sensor and camera data over Wi-Fi or Bluetooth to a server, where each data set is time-stamped to ensure data synchronization and integrity.

[0719] Step 4:

[0720] The server stores the received data in a database, where behavioral and facial expression data for each pet is accumulated and used for subsequent analysis.

[0721] Step 5:

[0722] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[0723] Step 6:

[0724] The server then uses machine learning algorithms to analyze the preprocessed data, identifying behavioral patterns such as "exercise," "rest," and "excitement" from the behavioral data, and inferring emotional states such as "happiness," "anxiety," and "fatigue" from the facial expression data.

[0725] Step 7:

[0726] The server then uses the analysis results to estimate the pet's needs. For example, if the server detects that the pet frequently wanders around food and has an anxious expression, it will assume that the pet is hungry.

[0727] Step 8:

[0728] The server generates a message (text or voice) for the user based on the estimated desires. The generated message should be specific and easy to understand. For example, it could be in the form of "Mimi seems hungry."

[0729] Step 9:

[0730] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[0731] Step 10:

[0732] Users receive a notification on their smartphone app, open the app to check the details, and then understand their pet's current condition and needs and choose appropriate actions (e.g., feeding or taking them for a walk).

[0733] Step 11:

[0734] The device (a camera and microphone that are part of the emotion engine) collects the user's facial expression data and voice data in real time. The camera captures the user's face and the microphone records the user's voice.

[0735] Step 12:

[0736] The server analyzes the collected user facial expression and voice data to estimate the user's emotional state. For example, if the user raises their arms and smiles, it will identify this as "joy."

[0737] Step 13:

[0738] The server then integrates the pet's desire estimation results with the user's emotional state and generates more accurate notifications based on the integration results, such as "If your dog is feeling stressed due to lack of exercise and you are feeling excited, we recommend that you take him for a walk together."

[0739] Step 14:

[0740] The server then sends a notification based on the integration results back to the user's smartphone, which includes measures based on the pet's estimated needs and the user's emotional state.

[0741] Step 15:

[0742] The user checks the notification again and takes the recommended action. For example, they select the action "go for a walk." This action relieves stress for the pet and refreshes the user.

[0743] The above is a specific flow of processing steps in the system of the present invention. This system can analyze pet behavior and desires in detail, provide appropriate feedback to the user, and realize more accurate notifications that take the user's emotional state into consideration. This can support the health and happiness of pets and reduce the burden on owners.

[0744] Example 2

[0745] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0746] It is difficult to efficiently analyze pet behavioral and facial expression data and accurately estimate pet needs. Furthermore, there is a need for a method to provide feedback that takes into account the user's emotional state, thereby enabling more appropriate pet care. Furthermore, it is also important to improve the accuracy of analysis by removing noise from the data and detecting outliers.

[0747] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0748] In this invention, the server includes: a sensor means for collecting pet behavior data and facial expression data; a communication means for receiving data from the sensor means; a storage means for saving the received data; a preprocessing means for performing noise reduction and outlier detection / correction on the received data; an analysis means using a machine learning algorithm to identify the pet's behavior pattern and emotional state from the preprocessed data; a generation means for estimating the pet's desires using the analysis means and generating a notification based on the estimated pet desires; a transmission means for sending the generated notification to a user; an emotion engine including a means for collecting and analyzing user facial expression data and voice data; and a means for integrating the pet desire estimation result obtained by the analysis means with the user's emotional state and generating a notification based on the integration result. This enables detailed analysis of the interactive state between the pet and the user and provides appropriate and accurate feedback.

[0749] The "sensor means" is a device for collecting behavioral data and facial expression data of a pet.

[0750] The "communication means" is a device for transmitting data collected from the sensor means to the server.

[0751] The "storage means" is a device for storing received data in a database.

[0752] The "preprocessing means" is a device that removes noise from the received data and detects and corrects abnormal values.

[0753] An "analysis means" is a device that uses machine learning algorithms to identify the behavioral patterns and emotional states of the pet from the pre-processed data.

[0754] The "generation means" is a device that generates a notification based on the pet's desires estimated by the analysis means.

[0755] The "transmitting means" is a device for transmitting the generated notification to the user.

[0756] An "emotion engine" is a device that collects and analyzes a user's facial expression and voice data to estimate the user's emotional state.

[0757] The present invention is a system that combines a system that analyzes behavioral data and facial expression data of a pet and accurately estimates the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system will be described below.

[0758] Sensor means

[0759] The devices used are a wearable sensor and an indoor camera. The wearable sensor is attached to the pet's collar or torso and collects behavioral data such as acceleration data, heart rate, and activity level. In addition, the indoor camera captures the pet's movements and facial expressions in real time and saves them as video data.

[0760] Specific examples

[0761] For example, the system records acceleration data when a dog runs and changes in heart rate while the dog is eating. In addition, an indoor camera captures the dog's facial expressions in real time.

[0762] communication means

[0763] The devices (wearable sensors and indoor cameras) transmit the collected data via Wi-Fi or Bluetooth to a server, which timestamps each data set and keeps the data synchronized and consistent.

[0764] Specific examples

[0765] The data detected by the sensor is sent to a server in real time, allowing for centralized management of pet activity. For example, data on the moment a dog chases a ball is sent along with its heart rate data at that time.

[0766] Data storage

[0767] The server stores the received data in a database, which makes it possible to refer to all past data and perform comparative analysis.

[0768] Specific examples

[0769] Not only the data from this walk, but also data from past walks is saved, allowing you to track changes at each point in time.

[0770] Data Preprocessing

[0771] The server removes noise from the stored data and detects and corrects outliers to improve data accuracy, enabling highly reliable data analysis.

[0772] Specific examples

[0773] A process is performed to remove abnormal heart rate data caused by temporary malfunction of the sensor.

[0774] Data analysis

[0775] The server uses machine learning algorithms to analyze the behavioral and facial expression data, identify behavioral patterns, and estimate the pet's emotional state.

[0776] Specific examples

[0777] Data showing that the dog is still for a certain period of time is used to identify the dog as "resting," and data on the dog's facial expression is used to estimate its "sense of security."

[0778] Message Generation

[0779] Based on the analysis results, the server generates notifications that infer your pet's needs, such as "Your dog wants a walk" or "It's time for exercise!"

[0780] Send notifications

[0781] The server sends the generated notification to the user's smartphone or tablet as a push notification, allowing the user to keep track of their pet's status in real time.

[0782] Specific examples

[0783] A notification will appear on your smartphone saying, "Your dog needs more exercise. We recommend taking it for a walk."

[0784] Emotion Engine

[0785] The system includes an emotion engine that recognizes the user's emotions. It uses a camera and microphone to collect the user's facial expressions and voice, which are then analyzed by a server.

[0786] Specific examples

[0787] If the user has a surprised expression, the emotion is analyzed and recognized as "surprise."

[0788] Integrated analytics and advanced notification generation

[0789] The server integrates the pet's desire estimation results with the user's emotional state to generate more accurate notifications.

[0790] Specific examples

[0791] It integrates the fact that a pet is lacking exercise with the user's relaxation and generates a notification such as, "Your dog is lacking exercise, but you seem relaxed. Would you like to join us for some light exercise?"

[0792] Prompt Sentence Examples

[0793] Data collection:

[0794] "Use wearable sensors to collect acceleration and heart rate data from your dog."

[0795] "Use an indoor camera to capture facial expression data of a dog."

[0796] Data transmission:

[0797] "Send the collected data to the server via Wi-Fi."

[0798] Data Retention:

[0799] Save the received data in the database.

[0800] Data preprocessing:

[0801] "Denoise your data and detect outliers"

[0802] Data Analysis:

[0803] "Implement machine learning algorithms for behavioral pattern identification and emotional state estimation"

[0804] Message Generation:

[0805] "Generate a message that estimates your pet's desires based on the results of data analysis."

[0806] Notification sent:

[0807] "Send the generated message to the user's smartphone via push notification."

[0808] Emotion recognition:

[0809] "Recognize the user's facial expressions and voice and analyze their emotions"

[0810] Integrated analytics and advanced notification generation:

[0811] "Integrate pet needs and user emotions to generate accurate notifications"

[0812] This system allows detailed analysis of the pet and user's condition and provides appropriate and accurate feedback, leading to better pet care.

[0813] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0814] Step 1: Data collection

[0815] The devices (wearable sensors and indoor cameras) collect the dog's acceleration, heart rate, activity level, movement, and facial expression data in real time. The wearable sensors measure these data, and the indoor cameras capture video data.

[0816] Input: Dog activity and facial expressions

[0817] Output: Acceleration data, heart rate data, video data

[0818] Specifically, the wearable sensor measures the dog's acceleration and heart rate every second, and the indoor camera captures video at 30 frames per second. For example, when the dog starts exercising, the acceleration and heart rate data change, and the dog's movements are recorded on video.

[0819] Step 2: Send data

[0820] The devices transmit the collected data to a server via Wi-Fi or Bluetooth, and each data set is time-stamped to ensure data synchronization and integrity.

[0821] Input: Collected acceleration data, heart rate data, video data

[0822] Output: The dataset sent to the server

[0823] Specifically, the device collects all the data collected every 10 seconds and sends it to the server via Wi-Fi. For example, data from 10 seconds during which a dog is eating is sent to the server.

[0824] Step 3: Save Data

[0825] The server stores the received data in a database, which makes it possible to refer to all past data.

[0826] Input: The dataset sent to the server

[0827] Output: Data stored in the database

[0828] Specifically, the server classifies the received data by timestamp and stores it in the appropriate table in the database. For example, heart rate data is stored in the "heart rate" table, and video data is stored in the "video" table.

[0829] Step 4: Data Preprocessing

[0830] The server removes noise from the stored data and detects and corrects outliers, thereby improving the accuracy of the data.

[0831] Input: Data stored in a database

[0832] Output: Preprocessed data

[0833] Specifically, the server applies outlier detection algorithms to detect and remove, for example, extremely high heart rates. It also applies noise reduction filters to smooth the acceleration data.

[0834] Step 5: Data analysis

[0835] The server uses machine learning algorithms to analyze the behavioral and facial expression data, identify behavioral patterns, and infer the pet's emotional state.

[0836] Input: Preprocessed data

[0837] Output: Behavioral patterns and emotional states

[0838] Specifically, the server uses the collected acceleration and heart rate data to identify behavioral patterns such as "exercising" or "resting," and infers emotions such as "happiness" or "anxiety" from the video data. For example, if a sudden change in acceleration data coincides with a rise in heart rate, it will identify this as "exercising."

[0839] Step 6: Message Generation

[0840] Based on the analysis results, the server estimates the pet's needs and generates a notification based on them.

[0841] Input: behavioral patterns and emotional states

[0842] Output: Notification message

[0843] Specifically, the server combines the behavioral pattern of "lack of exercise" with the emotional state of "discomfort" to generate a message that says, "Your dog needs exercise. Take it for a walk."

[0844] Step 7: Send notification

[0845] The server sends the generated notification to the user's smartphone or tablet as a push notification.

[0846] Input: Notification message

[0847] Output: Push notification to user device

[0848] Specifically, the server sends the generated notification message to the user interface API, and a notification such as "Your dog needs more exercise. Please take it for a walk" is displayed on the smartphone.

[0849] Step 8: Emotion Recognition

[0850] The system includes an emotion engine that recognizes the user's emotions. The camera and microphone collect the user's facial expressions and voice, which are then analyzed by the server.

[0851] Input: User's facial expression data and voice data

[0852] Output: User's emotional state

[0853] Specifically, when a user plays with a pet, a camera and microphone capture the scene, and the server analyzes the footage to recognize the user's "joy."

[0854] Step 9: Integrated analytics and advanced notification generation

[0855] The server integrates the pet's desire estimation results with the user's emotional state to generate more accurate notifications.

[0856] Input: Pet behavior patterns and emotional state, user emotional state

[0857] Output: Consolidated notification message

[0858] Specifically, the server integrates the fact that the pet is lacking exercise with the user's relaxation and generates a notification saying, "Your dog is lacking exercise. Let's go for a walk together to refresh yourself."

[0859] Through these processing steps, the conditions of the pet and the user can be analyzed in detail, and appropriate and accurate feedback can be provided.

[0860] (Application example 2)

[0861] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0862] Current pet care systems only estimate pet needs based on behavioral and emotional data, but are unable to provide feedback that takes into account the user's emotional state. As a result, they lack concrete support for deepening communication and relationships between pets and users. Furthermore, they are unable to order pet food at the appropriate time to meet a pet's appetite, creating issues in terms of pet health management and user convenience.

[0863] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes sensor means for collecting behavioral data and facial expression data of the pet, communication means for receiving data from the sensor means, analysis means for analyzing the received data and inferring the pet's desires, emotion engine means for collecting and analyzing user emotion data, generation means for generating a notification based on the inferred pet's desires and the analyzed user's emotional state, and transmission means for transmitting the generated notification to the user. This makes it possible to provide more appropriate and timely feedback based on the pet's desires and the user's emotional state, thereby improving the health management and quality of life of the pet and the user.

[0864] "Sensor means" refers to a device used to collect behavioral data or facial expression data of a pet or user, and includes wearable sensors, indoor cameras, cameras, and microphones.

[0865] The "communication means" is a device for transmitting data collected from the sensor means to the server, and includes wireless communication technology and wired communication technology.

[0866] An "analysis means" is a device or program that processes the received data and uses machine learning algorithms to identify the pet's behavioral patterns and needs, as well as the user's emotional state.

[0867] The "emotion engine means" is a device or program that collects and analyzes facial expression data and voice data of the user to estimate the user's emotional state.

[0868] The "generating means" is a device or program that generates a notification message based on the analyzed pet's desires and the user's emotional state.

[0869] The "transmission means" is a device or program for transmitting the generated notification to the user's mobile terminal or the like as a push notification.

[0870] A "wearable sensor" is a sensor device that is attached to a pet's collar or body and collects data such as the pet's acceleration, heart rate, and activity level.

[0871] An "indoor camera" is a camera device that captures pet movements and facial expressions in real time and collects them as video data.

[0872] A "camera" is a photographing device for capturing the user's facial expression.

[0873] A "microphone" is a recording device for collecting a user's voice data.

[0874] A "machine learning algorithm" is an algorithm that analyzes large amounts of data, learns patterns and features, and makes predictions and classifications about future data.

[0875] This invention is a system that combines a system that analyzes pet behavior data and facial expression data to accurately estimate the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[0876] System Configuration

[0877] 1. Sensor means

[0878] Wearable sensors: These are attached to a pet's collar or torso and collect behavioral data such as pet acceleration data, heart rate, and activity level.

[0879] Indoor camera: This captures your pet's movements and expressions in real time and saves them as video data.

[0880] Camera and microphone: This is for collecting facial and voice data from the user.

[0881] 2. Means of communication

[0882] Wi-Fi or Bluetooth: This is used to transmit collected data to a server, where each data set is time-stamped to keep the data synchronized and consistent.

[0883] 3. Analysis method

[0884] The server stores the received data in a database and checks the integrity of the data.

[0885] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[0886] The server uses machine learning algorithms to analyze the behavioral patterns and emotional state of the pet from the behavioral and facial expression data, as well as the emotional state of the user.

[0887] 4. Generation means

[0888] The server integrates the pet's desires and the user's emotional state from the analysis results and generates a message (e.g., text or voice) based on the integration.

[0889] 5. Transmission Method

[0890] The server sends the generated message to the user's smartphone or tablet as a push notification.

[0891] Example

[0892] Examples of data collection:

[0893] The terminal (wearable sensor) collects the dog's activity data (e.g., acceleration, heart rate) at regular intervals. The sensor captures the dog's behavioral patterns and sends the data to a server. In parallel, the terminal (indoor camera) captures the dog's movements and facial expressions as video and sends the video to the server.

[0894] An example of analysis:

[0895] The server stores the received data in a database and performs preprocessing to remove outliers and noise. It then uses machine learning algorithms to analyze the behavioral and facial expression data. For example, it can identify behavioral patterns such as "exercising," "resting," and "excited" from acceleration and heart rate data, and recognize facial expressions from video data to estimate emotions such as "happiness" and "anxiety."

[0896] An example of pet desire estimation and notification generation:

[0897] The server analyzes the behavioral pattern "requesting a walk" and the emotional state "expectation" and generates a message estimating "your dog wants to go for a walk." This message is then sent to the user's smartphone as a push notification.

[0898] An example of an emotion engine:

[0899] The system is equipped with a camera to capture the user's facial expressions and a microphone to collect audio. The server analyzes the facial and audio data when the user checks the notification and estimates the user's emotional state. For example, if the user shows a happy expression when checking the notification that their pet is "excited," the server determines that the owner is "very interested in playing with their pet."

[0900] An example of a unified notification for users and pets:

[0901] The server determines from the pet's behavioral data that the pet is in a "stressed state due to lack of exercise" and from the user's facial expression data that the pet is in an "excited state." By integrating this information, the server generates a message to the user saying, "Your dog is stressed due to lack of exercise, but you seem to be in a good mood. Why don't you take a walk together to refresh yourself?"

[0902] Examples and prompts:

[0903] Examples:

[0904] Sensor data: {"timestamp": "2023-10-01T10:00:00", "acceleration": 0.45, "heart_rate": 120}

[0905] Camera data: {"timestamp": "2023-10-01T10:00:00", "image": "base64_encoded_image_data"}

[0906] User data: {"timestamp": "2023-10-01T10:00:00", "expression": "smiling", "voice_tone": "neutral"}

[0907] Example prompt sentence:

[0908] Analyze the behavioral patterns of the user's pet based on sensor data and camera data, and infer whether the pet is hungry. Also, estimate the user's emotions based on the user's facial expression data. If the pet is hungry and the user is happy, generate a message suggesting the user to order pet food. The following is sample data: Pet-related sensor data: {"timestamp": "2023-10-01T10:00:00", "acceleration": 0.45, "heart_rate": 120}, Camera data: {"timestamp": "2023-10-01T10:00:00", "image": "base64_encoded_image_data"}, User data: {"timestamp": "2023-10-01T10:00:00", "expression": "smiling", "voice_tone": "neutral"}

[0909] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0910] Step 1:

[0911] The devices (wearable sensors and indoor cameras) collect pet behavior data (e.g., acceleration, heart rate) and facial expression data at regular intervals. The inputs are raw data from the sensors (acceleration, heart rate, video). The output is collected data with timestamps.

[0912] Step 2:

[0913] The device sends the collected data to the server via Wi-Fi or Bluetooth. The input is the raw data collected by the device and a timestamp. The output is the data transferred to the server.

[0914] Step 3:

[0915] The server stores the received data in a database and checks the integrity of the data. The input is the time-stamped data sent from the device. The output is the data whose integrity has been checked and stored in the database.

[0916] Step 4:

[0917] The server performs preprocessing on the received data, such as noise removal and outlier detection. The input is the received data, and the output is the data with noise removed and outliers corrected.

[0918] Step 5:

[0919] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data, as well as the user's emotional state. The inputs are preprocessed behavioral data, facial expression data, and the user's facial expression data. The output is the pet's behavioral patterns (e.g., exercising, resting, excited) and emotional state (e.g., happy, anxious), as well as the user's emotional state.

[0920] Step 6:

[0921] The server integrates the pet's needs and the user's emotional state from the analysis results and generates a message based on them. The inputs are the analyzed pet's needs and the user's emotional state. The output is a generated message (e.g., "Your dog wants to go for a walk") based on the pet's needs and the user's emotional state.

[0922] Step 7:

[0923] The server generates the message and sends it to the user's smartphone or tablet as a push notification. The input is the generated notification message. The output is the push notification sent to the user's smartphone.

[0924] The above are the specific processing steps for implementing the invention. This system analyzes the behavioral and facial expression data of the pet, and is able to provide more appropriate feedback and notifications that take into account the pet's needs and the user's emotional state.

[0925] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0926] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0927] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0928] [Third embodiment]

[0929] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0930] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0931] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0932] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0933] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0934] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0935] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0936] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0937] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0938] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0939] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0940] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0941] The present invention provides a system that analyzes behavioral data and facial expression data of a pet, accurately estimates the pet's desires, and notifies the pet owner of the desires. Specific embodiments for implementing this system will be described below.

[0942] System Configuration

[0943] 1. Sensor means

[0944] The wearable sensor terminal is attached to the pet's collar or torso and collects behavioral data such as the pet's acceleration data, heart rate, and activity level.

[0945] The indoor camera serves as a terminal that captures your pet's movements and expressions in real time and saves them as video data.

[0946] 2. Means of communication

[0947] The devices (wearable sensors and indoor cameras) transmit the collected data to a server using communication technologies such as Wi-Fi and Bluetooth. The transmitted data includes a timestamp, facilitating data synchronization.

[0948] 3. Analysis method

[0949] The server stores the received data in a database and checks the integrity of the data.

[0950] The server performs preprocessing on the received data, such as noise removal and outlier removal, to improve the accuracy of the analysis.

[0951] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data. Specifically, it classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[0952] 4. Generation means

[0953] The server uses the analysis results to estimate the pet's needs and generates a message (text or voice) based on that information, such as "Your dog wants to go for a walk" or "Momo is hungry."

[0954] 5. Transmission Method

[0955] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[0956] Specific examples

[0957] Data Collection Example

[0958] The device (wearable sensor) collects the cat's activity data (especially its behavior walking around the room at night) at regular intervals. The sensor measures the cat's acceleration and heart rate and sends the data to the server. At the same time, the device (indoor camera) captures the cat's movements as video and sends it to the server.

[0959] Data analysis example

[0960] The server first stores the received data in a database and performs preprocessing to remove noise and outliers. It then analyzes the data using machine learning algorithms. For example, it can identify a "restless" behavior pattern based on frequent nighttime movements and elevated heart rates, and detect "anxious facial expressions" using facial recognition.

[0961] Message Generation and Notification Example

[0962] Based on the analysis results of the behavioral pattern "restless" and the emotional state "anxious expression," the server generates a message saying, "Momo may be feeling stressed at night." The message is sent to the user's smartphone as a push notification. The user receives the notification on their smartphone app and checks the details.

[0963] User Interface Example

[0964] After checking the notification, the user can choose to use an aroma diffuser to relax their cat based on the information in the app that "Momo is feeling stressed at night." They can also use the in-app communication platform to discuss the issue with other pet owners and seek additional advice.

[0965] This system can accurately estimate a pet's needs from its behavior and facial expressions, and provide that information to the owner quickly and appropriately. This will support the health and happiness of pets and reduce the burden on owners. It also provides a platform that promotes communication between pet owners, allowing them to share knowledge and experiences about pet care.

[0966] The processing flow will be explained below.

[0967] Step 1:

[0968] The device (wearable sensor) collects pet behavior data (e.g., acceleration, heart rate, activity level) at regular intervals. This data is recorded in real time and temporarily stored in the built-in memory.

[0969] Step 2:

[0970] The device (indoor camera) captures your pet's movements and expressions and stores them as video data. The camera takes high-resolution still images and videos, and uses facial recognition technology to identify your pet if necessary.

[0971] Step 3:

[0972] The devices transmit collected sensor and camera data over Wi-Fi or Bluetooth to a server, where each data set is time-stamped to ensure data synchronization and integrity.

[0973] Step 4:

[0974] The server stores the received data in a database, where behavioral and facial expression data for each pet is accumulated and used for subsequent analysis.

[0975] Step 5:

[0976] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[0977] Step 6:

[0978] The server then uses machine learning algorithms to analyze the preprocessed data, identifying behavioral patterns such as "exercise," "rest," and "excitement" from the behavioral data, and inferring emotional states such as "happiness," "anxiety," and "fatigue" from the facial expression data.

[0979] Step 7:

[0980] The server then uses the analysis results to estimate the pet's needs. For example, if the server detects that the pet frequently wanders around food and has an anxious expression, it will assume that the pet is hungry.

[0981] Step 8:

[0982] The server generates a message (text or voice) for the user based on the estimated desires. The generated message should be specific and easy to understand. For example, it could be in the form of "Mimi seems hungry."

[0983] Step 9:

[0984] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[0985] Step 10:

[0986] Users receive a notification on their smartphone app, open the app to check the details, and then understand their pet's current condition and needs and choose appropriate actions (e.g., feeding or taking them for a walk).

[0987] Step 11:

[0988] Users can use the in-app communication platform to share information with other pet owners, for example by posting questions such as, "Momo seems to be stressed at night. How do you deal with it?"

[0989] Step 12:

[0990] The server collects answers from other users in real time and displays them to the user who posted the question. The answers include specific advice and similar experiences that can improve the quality of pet care.

[0991] The above is a specific flow of processing steps in the system of the present invention. This system can analyze pet behavior and desires in detail and provide appropriate feedback to the user. The user can then take prompt and effective action based on the information obtained to support the health and happiness of their pet.

[0992] Example 1

[0993] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0994] Understanding pet behavior and emotions is important for maintaining pet health and happiness, but currently owners have to manually observe and judge, which is time-consuming and often inaccurate. It is also difficult to properly understand and respond to pet needs and stress, which can result in a risk of compromising pet health and happiness.

[0995] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0996] In this invention, the server includes a sensor means for collecting behavioral data and facial expression data of the pet, a communication means for receiving data from the sensor means, a preprocessing means for saving the received data and removing noise and outliers, an analysis means for analyzing the preprocessed data and estimating the behavioral patterns and emotional state of the pet, a generation means for generating a notification using natural language generation technology based on the estimated desires of the pet, and a transmission means for sending the generated notification to the user as a push notification. This makes it possible to more accurately and quickly analyze the behavioral and emotional state of the pet and to send notifications to the owner at appropriate times.

[0997] "Sensor means" refers to a device installed to collect data on the behavior and facial expressions of pets. Specifically, it includes wearable sensors and indoor cameras.

[0998] "Communication means" refers to the technical means for transmitting data collected from the sensor means to the server. Specifically, it includes wireless communication technologies such as Wi-Fi and Bluetooth.

[0999] "Pre-processing means" refers to technical means for storing received data and cleaning the data, such as removing noise and outliers. Specifically, this includes database management systems and data processing software.

[1000] "Analysis means" refers to technical means for analyzing the pre-processed data and inferring the pet's behavioral patterns and emotional state, including machine learning algorithms and data analysis software.

[1001] The "generation means" refers to a technical means for generating a notification about the pet's needs in natural language based on the analysis results. Specifically, it includes natural language generation technology.

[1002] "Transmission means" refers to the technical means for transmitting the generated notification to the user as a push notification. Specifically, it includes the API of the push notification service.

[1003] The present invention provides a system that analyzes behavioral data and facial expression data of a pet, accurately estimates the pet's desires, and notifies the pet's owner of the desires. Specific embodiments for implementing this system will be described below.

[1004] System Configuration

[1005] Sensor means

[1006] Wearable sensors as terminals are attached to pets' collars or bodies and collect behavioral data such as pet acceleration data, heart rate, and activity levels. Specifically, they are generally called wearable devices. Indoor cameras as terminals capture pets' movements and facial expressions in real time and save them as video data. Specifically, they are generally called surveillance cameras. This allows data on pets' behavior and facial expressions to be continuously obtained.

[1007] communication means

[1008] The terminals (wearable devices and surveillance cameras) transmit the collected data to a server using communication technologies such as Wi-Fi or Bluetooth. Specifically, a wireless communication module is used. The transmitted data includes a timestamp to ensure data synchronization.

[1009] Pretreatment means

[1010] The server stores the received data in a database and checks the data integrity. The specific database used here is generally called a relational database management system (RDBMS). Next, preprocessing such as noise removal and outlier removal is performed using the Python Pandas library. This processing improves the accuracy of the data analysis.

[1011] Analysis means

[1012] The server uses machine learning algorithms to analyze behavioral and facial expression data. Specifically, it uses libraries such as TensorFlow, and is generally referred to as a machine learning platform. It classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[1013] generation means

[1014] The server uses the analysis results to estimate the pet's needs and generates a message (text or voice) based on that information. Specifically, it uses natural language generation technology and a generative AI model (e.g., GPT-3). For example, it generates specific messages such as "Your dog wants to go for a walk" or "Momo is hungry."

[1015] Transmission method

[1016] The server then sends the generated message to the user's smartphone or tablet as a push notification, using the API of a push notification service (e.g., Firebase Cloud Messaging). The notification contains the analysis results and suggested solutions.

[1017] Specific examples

[1018] Data Collection Example

[1019] The terminal (wearable device) collects the cat's activity data (especially its behavior walking around the room at night) at regular intervals. The sensor measures the cat's acceleration and heart rate and sends the data to the server. At the same time, the terminal (surveillance camera) captures the cat's movements as video and sends it to the server as well.

[1020] Data analysis example

[1021] The server stores the received data in a relational database management system (RDBMS) and preprocesses it using Python's Pandas library to remove noise and outliers. The data is then analyzed using machine learning algorithms powered by TensorFlow. For example, it identifies a "restless" behavior pattern based on frequent nighttime movements and elevated heart rates, and uses facial recognition to detect "anxious facial expressions."

[1022] Message Generation and Notification Example

[1023] Based on the analysis results of the behavioral pattern "restless" and the emotional state "anxious expression," the server uses natural language generation technology (generative AI model) to generate a message saying "Momo may be feeling stressed at night." The message is then sent as a push notification to the user's smartphone using a push notification service (Firebase Cloud Messaging). The user receives the notification in their smartphone app and checks the details.

[1024] Prompt Sentence Examples

[1025] "Infer a pet's needs from its behavioral and facial expression data and generate a message to notify the owner. For example, if a cat moves around frequently at night and its heart rate increases, explain what kind of message should be generated based on the analysis results."

[1026] This system can accurately predict pet needs from their behavior and facial expressions, and provide them to their owners quickly and appropriately. This supports the health and happiness of pets and reduces the burden on owners. It also provides a platform that promotes communication between pet owners, allowing them to share knowledge and experiences about pet care.

[1027] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1028] Program processing flow

[1029] Step 1: Data collection

[1030] The terminal uses a wearable device to acquire the pet's behavioral data (acceleration, heart rate, activity level) and uses a surveillance camera to collect the pet's movements and facial expressions as video data.

[1031] Input: Sensor values ​​from wearable devices (acceleration data, heart rate data), video data from surveillance cameras

[1032] Output: Collected behavioral and video data

[1033] Specific operation: The wearable device uses sensors to acquire data at regular intervals (e.g., every minute) and temporarily stores it in its internal memory. The surveillance camera captures video in real time and also temporarily stores it.

[1034] Step 2: Send data

[1035] The device sends the collected data to a server via Wi-Fi or Bluetooth.

[1036] Input: Collected behavioral and video data

[1037] Output: Data packets sent to the server

[1038] How it works: Pet behavior data and video data are sent to a server via Wi-Fi, where a timestamp is added to ensure data synchronization.

[1039] Step 3: Data storage and preprocessing

[1040] The server stores the received data in a database and performs preprocessing (noise removal and outlier removal).

[1041] Input: Behavioral data and video data sent from the device

[1042] Output: Preprocessed data

[1043] How it works: The data is stored in a database management system and a script is run to remove noise and outliers using the Python Pandas library.

[1044] Step 4: Data analysis

[1045] The server uses the preprocessed data to analyze it using machine learning algorithms to estimate the pet's behavioral patterns and emotional state.

[1046] Input: Preprocessed data

[1047] Output: Analysis results of behavioral patterns and emotional states

[1048] Specific behavior: The data to be analyzed is input into a machine learning platform, and algorithms such as TensorFlow are used to classify and estimate the pet's behavioral patterns (e.g., "exercising," "resting," "excited") and emotional state (e.g., "happy," "anxious").

[1049] Step 5: Message Generation

[1050] The server uses natural language generation technology (generative AI model) based on the analysis results to generate a notification message.

[1051] Input: Analysis results of behavioral patterns and emotional states

[1052] Output: The generated notification message

[1053] Specific operation: A prompt sentence is input to the generative AI model, and a notification message for the user is created based on the generated text.

[1054] Step 6: Send the message

[1055] The server sends the generated notification message to the user's smartphone via a push notification service.

[1056] Input: The generated notification message

[1057] Output: Notification sent to the user's smartphone

[1058] Specific operation: Calls the API of the push notification service and sends the generated notification message to the user's smartphone.

[1059] Step 7: User Interface Support

[1060] The user checks the notification received on their smartphone and selects the necessary action based on the pet's condition.

[1061] Input: Received notification message

[1062] Output: Selected action (e.g., activate aroma diffuser for stress relief)

[1063] Specific Action: The user taps the notification to open the app, checks the detailed information, and selects the appropriate action if necessary. In this case, the user presses a button within the app to perform a specific action.

[1064] (Application example 1)

[1065] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1066] Today's pet owners find it difficult to accurately understand their pets' behavior and emotional state and provide appropriate care and product selection. In particular, physical stores such as pet goods shops lack systems that can quickly recommend the right product for each pet's condition. This means pet owners spend a lot of time choosing the right product in the store, which can increase stress for their pets. To solve this problem, a system is needed that collects and analyzes pet behavior and facial expression data and notifies users in real time.

[1067] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1068] In this invention, the server includes a sensor means for collecting behavioral data and facial expression data of the pet, a communication means for receiving data from the sensor means, an analysis means for analyzing the received data and estimating the pet's desires, a generation means for generating a notification based on the estimated pet's desires, and a transmission means for transmitting the generated notification to the user's mobile information terminal and suggesting products in the store, thereby enabling optimal product selection based on the pet's behavior and emotional state in a physical store.

[1069] "Pet behavior data" is information about a pet's physical activity, movements, and behavior.

[1070] "Facial expression data" is information related to the movements of a pet's face and changes in facial expression.

[1071] The "sensor means" is a device for collecting behavioral data and facial expression data of a pet.

[1072] A "wearable sensor" is a device that can be attached to a pet's collar or torso and measures the pet's movements and biological data.

[1073] An "indoor camera" is a video camera installed to capture your pet's movements and expressions.

[1074] "Communication means" refers to the technology used to transmit data from the sensor means to the server, and includes Wi-Fi, Bluetooth, etc.

[1075] The "analysis means" is a system for processing the received data and analyzing the pet's desires and emotional state.

[1076] A "machine learning algorithm" is a computational method that learns patterns from incoming data and identifies pet behaviors and emotions.

[1077] A "generator" is a system that creates a notification message based on the analyzed data.

[1078] "Transmission means" refers to a technique for transmitting the generated notification to the user's mobile information terminal.

[1079] A "user's mobile information terminal" is a mobile information device such as a smartphone or tablet used by the owner.

[1080] "Making product suggestions in-store" means recommending appropriate products to pet owners based on the analyzed condition of their pets.

[1081] The present invention provides a system that analyzes behavioral data and facial expression data of pets in a physical store, estimates the pet's desires, and proposes optimal products to pet owners. Specific embodiments for implementing this system are described below.

[1082] System Configuration

[1083] 1. Sensor means

[1084] Wearable sensor: A device that is attached to a pet's collar or body and collects behavioral data such as acceleration data, heart rate, and activity level.

[1085] Indoor camera: A device installed inside the store that captures pets' movements and expressions in real time and obtains them as video data.

[1086] 2. Means of communication

[1087] Communication method: This technology uses Wi-Fi or Bluetooth to transmit data collected from wearable sensors and indoor cameras to a server. The transmitted data includes a timestamp, making data synchronization easy.

[1088] 3. Analysis method

[1089] Analysis method: The server stores the received data in a database and checks its integrity. First, it performs preprocessing such as noise removal and outlier removal, then uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data. Specifically, it classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[1090] 4. Generation means

[1091] Generation method: The server estimates the pet's needs from the analysis results and generates a message (text or voice) based on the estimate. For example, it generates a specific message such as "Your dog wants to go for a walk" or "Your pet is stressed."

[1092] 5. Transmission Method

[1093] Transmission method: The server sends the generated message to the user's mobile information device (smartphone or tablet) as a push notification. The notification contains the analysis results and suggested countermeasures.

[1094] Explanation of program processing

[1095] The server uses the following hardware and software to collect and analyze pet behavior and facial expression data: wearable sensors, indoor cameras, smartphones, and tablets; and the requests library for communication processing, SciPy, and TensorFlow for data analysis.

[1096] Data is collected in real time by wearable sensors and indoor cameras and transmitted to a server via communication means. The server stores the received data in a database and first performs preprocessing. This preprocessing includes noise removal and outlier elimination to improve data quality. Then, machine learning algorithms are used to analyze the pet's behavioral patterns and emotional state. Based on the results of this analysis, the pet's desires are estimated and a notification message is generated for the owner. This notification message is then sent to the user's mobile information terminal, and appropriate product recommendations are made to the owner in the store.

[1097] Specific examples

[1098] If a dog brought into a pet goods shop looks anxious, the system will analyze data collected through wearable sensors and indoor cameras and send a message to the owner's smartphone saying, "This dog is likely feeling anxious. We recommend a toy that will have a relaxing effect."

[1099] Prompt Sentence Examples

[1100] "Please create an application that analyzes pet behavior data (acceleration data, heart rate) and facial expression data (camera footage), estimates the pet's condition in real time, and suggests appropriate products to the owner."

[1101] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1102] Step 1:

[1103] The devices (wearable sensors and indoor cameras) collect pet behavior data (e.g., acceleration data, heart rate) and facial expression data (e.g., camera footage). Specifically, the devices acquire data in real time from sensors attached to the pet's collar or body and temporarily store the data.

[1104] Input: Acceleration data, heart rate data, and camera footage collected from your pet

[1105] Output: Collected behavioral and facial expression data

[1106] Step 2:

[1107] The terminal sends the collected data to the server using a communication method (e.g., Wi-Fi or Bluetooth). Specifically, a timestamp is added to the data, and the data is transferred to the server using a communication protocol.

[1108] Input: Behavioral data and facial expression data stored on the device

[1109] Output: Data sent to the server

[1110] Step 3:

[1111] The server stores the received data in a database, checks the data integrity, and performs preprocessing. Specifically, it checks the data integrity and removes noise and outliers. This preprocessing improves the quality of the data.

[1112] Input: Data sent to and received from the server

[1113] Output: Integrity checked and preprocessed data

[1114] Step 4:

[1115] The server analyzes the preprocessed data and uses machine learning algorithms to identify the pet's behavioral patterns and emotional state. Specifically, the machine learning model is used to classify behavioral data into categories such as "exercising," "resting," and "excited," and to estimate emotions such as "happy" and "anxious" from facial expression data.

[1116] Input: Preprocessed behavioral and facial expression data

[1117] Output: Classified behavioral and emotional states

[1118] Step 5:

[1119] The server estimates the pet's needs based on the analysis results, and generates a notification message (e.g., "Your dog wants to go for a walk" or "Your pet is stressed") to be sent to the owner based on the needs.

[1120] Input: Classified behavioral and emotional states

[1121] Output: The generated notification message

[1122] Step 6:

[1123] The server sends the generated notification message to the user's mobile information terminal (smartphone or tablet) using a communication means. Specifically, it uses push notification to send the user a message containing the analysis results and suggested countermeasures.

[1124] Input: The generated notification message

[1125] Output: The notification message sent to the user's mobile device.

[1126] Step 7:

[1127] The user checks the received message using a mobile information terminal. In the store, the appropriate product or service is selected based on the analysis of the pet's behavior and emotional state. Specifically, the user searches for the relevant product on the store's shelves according to the content of the notification message.

[1128] Input: Notification message sent to mobile device

[1129] Output: User behavior (product selection)

[1130] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1131] The present invention is a system that combines a system that analyzes pet behavior data and facial expression data to accurately estimate the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[1132] System Configuration

[1133] 1. Sensor means

[1134] The wearable sensor terminal is attached to the pet's collar or torso and collects behavioral data such as the pet's acceleration data, heart rate, and activity level.

[1135] The indoor camera serves as a terminal that captures your pet's movements and expressions in real time and saves them as video data.

[1136] 2. Means of communication

[1137] The devices (wearable sensors and indoor cameras) transmit the collected data to a server via Wi-Fi or Bluetooth, and each data set is time-stamped to ensure data synchronization and integrity.

[1138] 3. Analysis method

[1139] The server stores the received data in a database and checks the integrity of the data.

[1140] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[1141] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data.

[1142] 4. Generation means

[1143] The server estimates the pet's desires from the analysis results and generates a message (text or voice) based on them.

[1144] 5. Transmission Method

[1145] The server sends the generated message to the user's smartphone or tablet as a push notification.

[1146] 6. Emotion Engine

[1147] The system further comprises an emotion engine that recognizes the emotions of the user.

[1148] The emotion engine includes a camera and microphone for collecting facial and voice data from the user.

[1149] The server analyzes the user's facial expressions and voice to estimate the user's emotional state.

[1150] The server integrates the pet's desire estimation result obtained by the analysis means with the user's emotional state, and generates a more accurate notification based on the integration result.

[1151] Specific examples

[1152] Data Collection Example

[1153] The terminal (wearable sensor) collects the dog's activity data (e.g., acceleration, heart rate) at regular intervals. The sensor captures the dog's behavioral patterns and sends the data to a server. In parallel, the terminal (indoor camera) captures the dog's movements and facial expressions as video and sends the video to the server.

[1154] Data analysis example

[1155] The server stores the received data in a database and performs preprocessing to remove outliers and noise. It then uses machine learning algorithms to analyze the behavioral and facial expression data. For example, it can identify behavioral patterns such as "exercising," "resting," and "excited" from acceleration and heart rate data, and recognize facial expressions from video data to estimate emotions such as "happiness" and "anxiety."

[1156] Example of pet desire estimation and notification generation

[1157] The server analyzes the behavioral pattern "requesting a walk" and the emotional state "expectation" and generates a message estimating "your dog wants to go for a walk." This message is then sent to the user's smartphone as a push notification.

[1158] Emotion Engine Example

[1159] The system is equipped with a camera to capture the user's facial expressions and a microphone to collect audio. The server analyzes the facial and audio data when the user checks the notification and estimates the user's emotional state. For example, if the user shows a happy expression when checking the notification that their pet is "excited," the server determines that the owner is "very interested in playing with their pet."

[1160] Example of integrated notifications for users and pets

[1161] The server determines from the pet's behavioral data that the pet is in a "stressed state due to lack of exercise" and from the user's facial expression data that the pet is in an "excited state." By integrating this information, the server generates a message to the user saying, "Your dog is stressed due to lack of exercise, but you seem to be in a good mood. Why don't you take a walk together to refresh yourself?"

[1162] This system allows for detailed analysis of the condition of both the pet and the user, and provides more accurate and appropriate feedback based on that analysis, enabling owners to support the health and happiness of their pets and achieve better pet care.

[1163] The processing flow will be explained below.

[1164] Step 1:

[1165] The device (wearable sensor) collects pet behavior data (e.g., acceleration, heart rate, activity level) at regular intervals. This data is recorded in real time and temporarily stored in the built-in memory.

[1166] Step 2:

[1167] The device (indoor camera) captures the pet's movements and expressions and stores them as video data. The camera takes high-resolution still and video images and, if necessary, uses facial recognition technology to identify the pet.

[1168] Step 3:

[1169] The devices transmit collected sensor and camera data over Wi-Fi or Bluetooth to a server, where each data set is time-stamped to ensure data synchronization and integrity.

[1170] Step 4:

[1171] The server stores the received data in a database, where behavioral and facial expression data for each pet is accumulated and used for subsequent analysis.

[1172] Step 5:

[1173] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[1174] Step 6:

[1175] The server then uses machine learning algorithms to analyze the preprocessed data, identifying behavioral patterns such as "exercise," "rest," and "excitement" from the behavioral data, and inferring emotional states such as "happiness," "anxiety," and "fatigue" from the facial expression data.

[1176] Step 7:

[1177] The server then uses the analysis results to estimate the pet's needs. For example, if the server detects that the pet frequently wanders around food and has an anxious expression, it will assume that the pet is hungry.

[1178] Step 8:

[1179] The server generates a message (text or voice) for the user based on the estimated desires. The generated message should be specific and easy to understand. For example, it could be in the form of "Mimi seems hungry."

[1180] Step 9:

[1181] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[1182] Step 10:

[1183] Users receive a notification on their smartphone app, open the app to check the details, and then understand their pet's current condition and needs and choose appropriate actions (e.g., feeding or taking them for a walk).

[1184] Step 11:

[1185] The device (a camera and microphone that are part of the emotion engine) collects the user's facial expression data and voice data in real time. The camera captures the user's face and the microphone records the user's voice.

[1186] Step 12:

[1187] The server analyzes the collected user facial expression and voice data to estimate the user's emotional state. For example, if the user raises their arms and smiles, it will identify this as "joy."

[1188] Step 13:

[1189] The server then integrates the pet's desire estimation results with the user's emotional state and generates more accurate notifications based on the integration results, such as "If your dog is feeling stressed due to lack of exercise and you are feeling excited, we recommend that you take him for a walk together."

[1190] Step 14:

[1191] The server then sends a notification based on the integration results back to the user's smartphone, which includes measures based on the pet's estimated needs and the user's emotional state.

[1192] Step 15:

[1193] The user checks the notification again and takes the recommended action. For example, they select the action "go for a walk." This action relieves stress for the pet and refreshes the user.

[1194] The above is a specific flow of processing steps in the system of the present invention. This system can analyze pet behavior and desires in detail, provide appropriate feedback to the user, and realize more accurate notifications that take the user's emotional state into consideration. This can support the health and happiness of pets and reduce the burden on owners.

[1195] Example 2

[1196] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1197] It is difficult to efficiently analyze pet behavioral and facial expression data and accurately estimate pet needs. Furthermore, there is a need for a method to provide feedback that takes into account the user's emotional state, thereby enabling more appropriate pet care. Furthermore, it is also important to improve the accuracy of analysis by removing noise from the data and detecting outliers.

[1198] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1199] In this invention, the server includes: a sensor means for collecting pet behavior data and facial expression data; a communication means for receiving data from the sensor means; a storage means for saving the received data; a preprocessing means for performing noise reduction and outlier detection / correction on the received data; an analysis means using a machine learning algorithm to identify the pet's behavior pattern and emotional state from the preprocessed data; a generation means for estimating the pet's desires using the analysis means and generating a notification based on the estimated pet desires; a transmission means for sending the generated notification to a user; an emotion engine including a means for collecting and analyzing user facial expression data and voice data; and a means for integrating the pet desire estimation result obtained by the analysis means with the user's emotional state and generating a notification based on the integration result. This enables detailed analysis of the interactive state between the pet and the user and provides appropriate and accurate feedback.

[1200] The "sensor means" is a device for collecting behavioral data and facial expression data of a pet.

[1201] The "communication means" is a device for transmitting data collected from the sensor means to the server.

[1202] The "storage means" is a device for storing received data in a database.

[1203] The "preprocessing means" is a device that removes noise from the received data and detects and corrects abnormal values.

[1204] An "analysis means" is a device that uses machine learning algorithms to identify the behavioral patterns and emotional states of the pet from the pre-processed data.

[1205] The "generation means" is a device that generates a notification based on the pet's desires estimated by the analysis means.

[1206] The "transmitting means" is a device for transmitting the generated notification to the user.

[1207] An "emotion engine" is a device that collects and analyzes a user's facial expression and voice data to estimate the user's emotional state.

[1208] The present invention is a system that combines a system that analyzes behavioral data and facial expression data of a pet and accurately estimates the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system will be described below.

[1209] Sensor means

[1210] The devices used are a wearable sensor and an indoor camera. The wearable sensor is attached to the pet's collar or torso and collects behavioral data such as acceleration data, heart rate, and activity level. In addition, the indoor camera captures the pet's movements and facial expressions in real time and saves them as video data.

[1211] Specific examples

[1212] For example, the system records acceleration data when a dog runs and changes in heart rate while the dog is eating. In addition, an indoor camera captures the dog's facial expressions in real time.

[1213] communication means

[1214] The devices (wearable sensors and indoor cameras) transmit the collected data via Wi-Fi or Bluetooth to a server, which timestamps each data set and keeps the data synchronized and consistent.

[1215] Specific examples

[1216] The data detected by the sensor is sent to a server in real time, allowing for centralized management of pet activity. For example, data on the moment a dog chases a ball is sent along with its heart rate data at that time.

[1217] Data storage

[1218] The server stores the received data in a database, which makes it possible to refer to all past data and perform comparative analysis.

[1219] Specific examples

[1220] Not only the data from this walk, but also data from past walks is saved, allowing you to track changes at each point in time.

[1221] Data Preprocessing

[1222] The server removes noise from the stored data and detects and corrects outliers to improve data accuracy, enabling highly reliable data analysis.

[1223] Specific examples

[1224] A process is performed to remove abnormal heart rate data caused by temporary malfunction of the sensor.

[1225] Data analysis

[1226] The server uses machine learning algorithms to analyze the behavioral and facial expression data, identify behavioral patterns, and estimate the pet's emotional state.

[1227] Specific examples

[1228] Data showing that the dog is still for a certain period of time is used to identify the dog as "resting," and data on the dog's facial expression is used to estimate its "sense of security."

[1229] Message Generation

[1230] Based on the analysis results, the server generates notifications that infer your pet's needs, such as "Your dog wants a walk" or "It's time for exercise!"

[1231] Send notifications

[1232] The server sends the generated notification to the user's smartphone or tablet as a push notification, allowing the user to keep track of their pet's status in real time.

[1233] Specific examples

[1234] A notification will appear on your smartphone saying, "Your dog needs more exercise. We recommend taking it for a walk."

[1235] Emotion Engine

[1236] The system includes an emotion engine that recognizes the user's emotions. It uses a camera and microphone to collect the user's facial expressions and voice, which are then analyzed by a server.

[1237] Specific examples

[1238] If the user has a surprised expression, the emotion is analyzed and recognized as "surprise."

[1239] Integrated analytics and advanced notification generation

[1240] The server integrates the pet's desire estimation results with the user's emotional state to generate more accurate notifications.

[1241] Specific examples

[1242] It integrates the fact that a pet is lacking exercise with the user's relaxation and generates a notification such as, "Your dog is lacking exercise, but you seem relaxed. Would you like to join us for some light exercise?"

[1243] Prompt Sentence Examples

[1244] Data collection:

[1245] "Use wearable sensors to collect acceleration and heart rate data from your dog."

[1246] "Use an indoor camera to capture facial expression data of a dog."

[1247] Data transmission:

[1248] "Send the collected data to the server via Wi-Fi."

[1249] Data Retention:

[1250] Save the received data in the database.

[1251] Data preprocessing:

[1252] "Denoise your data and detect outliers"

[1253] Data Analysis:

[1254] "Implement machine learning algorithms for behavioral pattern identification and emotional state estimation"

[1255] Message Generation:

[1256] "Generate a message that estimates your pet's desires based on the results of data analysis."

[1257] Notification sent:

[1258] "Send the generated message to the user's smartphone via push notification."

[1259] Emotion recognition:

[1260] "Recognize the user's facial expressions and voice and analyze their emotions"

[1261] Integrated analytics and advanced notification generation:

[1262] "Integrate pet needs and user emotions to generate accurate notifications"

[1263] This system allows detailed analysis of the pet and user's condition and provides appropriate and accurate feedback, leading to better pet care.

[1264] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1265] Step 1: Data collection

[1266] The devices (wearable sensors and indoor cameras) collect the dog's acceleration, heart rate, activity level, movement, and facial expression data in real time. The wearable sensors measure these data, and the indoor cameras capture video data.

[1267] Input: Dog activity and facial expressions

[1268] Output: Acceleration data, heart rate data, video data

[1269] Specifically, the wearable sensor measures the dog's acceleration and heart rate every second, and the indoor camera captures video at 30 frames per second. For example, when the dog starts exercising, the acceleration and heart rate data change, and the dog's movements are recorded on video.

[1270] Step 2: Send data

[1271] The devices transmit the collected data to a server via Wi-Fi or Bluetooth, and each data set is time-stamped to ensure data synchronization and integrity.

[1272] Input: Collected acceleration data, heart rate data, video data

[1273] Output: The dataset sent to the server

[1274] Specifically, the device collects all the data collected every 10 seconds and sends it to the server via Wi-Fi. For example, data from 10 seconds during which a dog is eating is sent to the server.

[1275] Step 3: Save Data

[1276] The server stores the received data in a database, which makes it possible to refer to all past data.

[1277] Input: The dataset sent to the server

[1278] Output: Data stored in the database

[1279] Specifically, the server classifies the received data by timestamp and stores it in the appropriate table in the database. For example, heart rate data is stored in the "heart rate" table, and video data is stored in the "video" table.

[1280] Step 4: Data Preprocessing

[1281] The server removes noise from the stored data and detects and corrects outliers, thereby improving the accuracy of the data.

[1282] Input: Data stored in a database

[1283] Output: Preprocessed data

[1284] Specifically, the server applies outlier detection algorithms to detect and remove, for example, extremely high heart rates. It also applies noise reduction filters to smooth the acceleration data.

[1285] Step 5: Data analysis

[1286] The server uses machine learning algorithms to analyze the behavioral and facial expression data, identify behavioral patterns, and infer the pet's emotional state.

[1287] Input: Preprocessed data

[1288] Output: Behavioral patterns and emotional states

[1289] Specifically, the server uses the collected acceleration and heart rate data to identify behavioral patterns such as "exercising" or "resting," and infers emotions such as "happiness" or "anxiety" from the video data. For example, if a sudden change in acceleration data coincides with a rise in heart rate, it will identify this as "exercising."

[1290] Step 6: Message Generation

[1291] Based on the analysis results, the server estimates the pet's needs and generates a notification based on them.

[1292] Input: behavioral patterns and emotional states

[1293] Output: Notification message

[1294] Specifically, the server combines the behavioral pattern of "lack of exercise" with the emotional state of "discomfort" to generate a message that says, "Your dog needs exercise. Take it for a walk."

[1295] Step 7: Send notification

[1296] The server sends the generated notification to the user's smartphone or tablet as a push notification.

[1297] Input: Notification message

[1298] Output: Push notification to user device

[1299] Specifically, the server sends the generated notification message to the user interface API, and a notification such as "Your dog needs more exercise. Please take it for a walk" is displayed on the smartphone.

[1300] Step 8: Emotion Recognition

[1301] The system includes an emotion engine that recognizes the user's emotions. The camera and microphone collect the user's facial expressions and voice, which are then analyzed by the server.

[1302] Input: User's facial expression data and voice data

[1303] Output: User's emotional state

[1304] Specifically, when a user plays with a pet, a camera and microphone capture the scene, and the server analyzes the footage to recognize the user's "joy."

[1305] Step 9: Integrated analytics and advanced notification generation

[1306] The server integrates the pet's desire estimation results with the user's emotional state to generate more accurate notifications.

[1307] Input: Pet behavior patterns and emotional state, user emotional state

[1308] Output: Consolidated notification message

[1309] Specifically, the server integrates the fact that the pet is lacking exercise with the user's relaxation and generates a notification saying, "Your dog is lacking exercise. Let's go for a walk together to refresh yourself."

[1310] Through these processing steps, the conditions of the pet and the user can be analyzed in detail, and appropriate and accurate feedback can be provided.

[1311] (Application example 2)

[1312] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1313] Current pet care systems only estimate pet needs based on behavioral and emotional data, but are unable to provide feedback that takes into account the user's emotional state. As a result, they lack concrete support for deepening communication and relationships between pets and users. Furthermore, they are unable to order pet food at the appropriate time to meet a pet's appetite, creating issues in terms of pet health management and user convenience.

[1314] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes sensor means for collecting behavioral data and facial expression data of the pet, communication means for receiving data from the sensor means, analysis means for analyzing the received data and inferring the pet's desires, emotion engine means for collecting and analyzing user emotion data, generation means for generating a notification based on the inferred pet's desires and the analyzed user's emotional state, and transmission means for transmitting the generated notification to the user. This makes it possible to provide more appropriate and timely feedback based on the pet's desires and the user's emotional state, thereby improving the health management and quality of life of the pet and the user.

[1315] "Sensor means" refers to a device used to collect behavioral data or facial expression data of a pet or user, and includes wearable sensors, indoor cameras, cameras, and microphones.

[1316] The "communication means" is a device for transmitting data collected from the sensor means to the server, and includes wireless communication technology and wired communication technology.

[1317] An "analysis means" is a device or program that processes the received data and uses machine learning algorithms to identify the pet's behavioral patterns and needs, as well as the user's emotional state.

[1318] The "emotion engine means" is a device or program that collects and analyzes facial expression data and voice data of the user to estimate the user's emotional state.

[1319] The "generating means" is a device or program that generates a notification message based on the analyzed pet's desires and the user's emotional state.

[1320] The "transmission means" is a device or program for transmitting the generated notification to the user's mobile terminal or the like as a push notification.

[1321] A "wearable sensor" is a sensor device that is attached to a pet's collar or body and collects data such as the pet's acceleration, heart rate, and activity level.

[1322] An "indoor camera" is a camera device that captures pet movements and facial expressions in real time and collects them as video data.

[1323] A "camera" is a photographing device for capturing the user's facial expression.

[1324] A "microphone" is a recording device for collecting a user's voice data.

[1325] A "machine learning algorithm" is an algorithm that analyzes large amounts of data, learns patterns and features, and makes predictions and classifications about future data.

[1326] This invention is a system that combines a system that analyzes pet behavior data and facial expression data to accurately estimate the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[1327] System Configuration

[1328] 1. Sensor means

[1329] Wearable sensors: These are attached to a pet's collar or torso and collect behavioral data such as pet acceleration data, heart rate, and activity level.

[1330] Indoor camera: This captures your pet's movements and expressions in real time and saves them as video data.

[1331] Camera and microphone: This is for collecting facial and voice data from the user.

[1332] 2. Means of communication

[1333] Wi-Fi or Bluetooth: This is used to transmit collected data to a server, where each data set is time-stamped to keep the data synchronized and consistent.

[1334] 3. Analysis method

[1335] The server stores the received data in a database and checks the integrity of the data.

[1336] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[1337] The server uses machine learning algorithms to analyze the behavioral patterns and emotional state of the pet from the behavioral and facial expression data, as well as the emotional state of the user.

[1338] 4. Generation means

[1339] The server integrates the pet's desires and the user's emotional state from the analysis results and generates a message (e.g., text or voice) based on the integration.

[1340] 5. Transmission Method

[1341] The server sends the generated message to the user's smartphone or tablet as a push notification.

[1342] Example

[1343] Examples of data collection:

[1344] The terminal (wearable sensor) collects the dog's activity data (e.g., acceleration, heart rate) at regular intervals. The sensor captures the dog's behavioral patterns and sends the data to a server. In parallel, the terminal (indoor camera) captures the dog's movements and facial expressions as video and sends the video to the server.

[1345] An example of analysis:

[1346] The server stores the received data in a database and performs preprocessing to remove outliers and noise. It then uses machine learning algorithms to analyze the behavioral and facial expression data. For example, it can identify behavioral patterns such as "exercising," "resting," and "excited" from acceleration and heart rate data, and recognize facial expressions from video data to estimate emotions such as "happiness" and "anxiety."

[1347] An example of pet desire estimation and notification generation:

[1348] The server analyzes the behavioral pattern "requesting a walk" and the emotional state "expectation" and generates a message estimating "your dog wants to go for a walk." This message is then sent to the user's smartphone as a push notification.

[1349] An example of an emotion engine:

[1350] The system is equipped with a camera to capture the user's facial expressions and a microphone to collect audio. The server analyzes the facial and audio data when the user checks the notification and estimates the user's emotional state. For example, if the user shows a happy expression when checking the notification that their pet is "excited," the server determines that the owner is "very interested in playing with their pet."

[1351] An example of a unified notification for users and pets:

[1352] The server determines from the pet's behavioral data that the pet is in a "stressed state due to lack of exercise" and from the user's facial expression data that the pet is in an "excited state." By integrating this information, the server generates a message to the user saying, "Your dog is stressed due to lack of exercise, but you seem to be in a good mood. Why don't you take a walk together to refresh yourself?"

[1353] Examples and prompts:

[1354] Examples:

[1355] Sensor data: {"timestamp": "2023-10-01T10:00:00", "acceleration": 0.45, "heart_rate": 120}

[1356] Camera data: {"timestamp": "2023-10-01T10:00:00", "image": "base64_encoded_image_data"}

[1357] User data: {"timestamp": "2023-10-01T10:00:00", "expression": "smiling", "voice_tone": "neutral"}

[1358] Example prompt sentence:

[1359] Analyze the behavioral patterns of the user's pet based on sensor data and camera data, and infer whether the pet is hungry. Also, estimate the user's emotions based on the user's facial expression data. If the pet is hungry and the user is happy, generate a message suggesting the user to order pet food. The following is sample data: Pet-related sensor data: {"timestamp": "2023-10-01T10:00:00", "acceleration": 0.45, "heart_rate": 120}, Camera data: {"timestamp": "2023-10-01T10:00:00", "image": "base64_encoded_image_data"}, User data: {"timestamp": "2023-10-01T10:00:00", "expression": "smiling", "voice_tone": "neutral"}

[1360] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1361] Step 1:

[1362] The devices (wearable sensors and indoor cameras) collect pet behavior data (e.g., acceleration, heart rate) and facial expression data at regular intervals. The inputs are raw data from the sensors (acceleration, heart rate, video). The output is collected data with timestamps.

[1363] Step 2:

[1364] The device sends the collected data to the server via Wi-Fi or Bluetooth. The input is the raw data collected by the device and a timestamp. The output is the data transferred to the server.

[1365] Step 3:

[1366] The server stores the received data in a database and checks the integrity of the data. The input is the time-stamped data sent from the device. The output is the data whose integrity has been checked and stored in the database.

[1367] Step 4:

[1368] The server performs preprocessing on the received data, such as noise removal and outlier detection. The input is the received data, and the output is the data with noise removed and outliers corrected.

[1369] Step 5:

[1370] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data, as well as the user's emotional state. The inputs are preprocessed behavioral data, facial expression data, and the user's facial expression data. The output is the pet's behavioral patterns (e.g., exercising, resting, excited) and emotional state (e.g., happy, anxious), as well as the user's emotional state.

[1371] Step 6:

[1372] The server integrates the pet's needs and the user's emotional state from the analysis results and generates a message based on them. The inputs are the analyzed pet's needs and the user's emotional state. The output is a generated message (e.g., "Your dog wants to go for a walk") based on the pet's needs and the user's emotional state.

[1373] Step 7:

[1374] The server generates the message and sends it to the user's smartphone or tablet as a push notification. The input is the generated notification message. The output is the push notification sent to the user's smartphone.

[1375] The above are the specific processing steps for implementing the invention. This system analyzes the behavioral and facial expression data of the pet, and is able to provide more appropriate feedback and notifications that take into account the pet's needs and the user's emotional state.

[1376] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1377] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1378] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1379] [Fourth embodiment]

[1380] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1381] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1382] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1383] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1384] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1385] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1386] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1387] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1388] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1389] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1390] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1391] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1392] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1393] The present invention provides a system that analyzes behavioral data and facial expression data of a pet, accurately estimates the pet's desires, and notifies the pet owner of the desires. Specific embodiments for implementing this system will be described below.

[1394] System Configuration

[1395] 1. Sensor means

[1396] The wearable sensor terminal is attached to the pet's collar or torso and collects behavioral data such as the pet's acceleration data, heart rate, and activity level.

[1397] The indoor camera serves as a terminal that captures your pet's movements and expressions in real time and saves them as video data.

[1398] 2. Means of communication

[1399] The devices (wearable sensors and indoor cameras) transmit the collected data to a server using communication technologies such as Wi-Fi and Bluetooth. The transmitted data includes a timestamp, facilitating data synchronization.

[1400] 3. Analysis method

[1401] The server stores the received data in a database and checks the integrity of the data.

[1402] The server performs preprocessing on the received data, such as noise removal and outlier removal, to improve the accuracy of the analysis.

[1403] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data. Specifically, it classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[1404] 4. Generation means

[1405] The server uses the analysis results to estimate the pet's needs and generates a message (text or voice) based on that information, such as "Your dog wants to go for a walk" or "Momo is hungry."

[1406] 5. Transmission Method

[1407] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[1408] Specific examples

[1409] Data Collection Example

[1410] The device (wearable sensor) collects the cat's activity data (especially its behavior walking around the room at night) at regular intervals. The sensor measures the cat's acceleration and heart rate and sends the data to the server. At the same time, the device (indoor camera) captures the cat's movements as video and sends it to the server.

[1411] Data analysis example

[1412] The server first stores the received data in a database and performs preprocessing to remove noise and outliers. It then analyzes the data using machine learning algorithms. For example, it can identify a "restless" behavior pattern based on frequent nighttime movements and elevated heart rates, and detect "anxious facial expressions" using facial recognition.

[1413] Message Generation and Notification Example

[1414] Based on the analysis results of the behavioral pattern "restless" and the emotional state "anxious expression," the server generates a message saying, "Momo may be feeling stressed at night." The message is sent to the user's smartphone as a push notification. The user receives the notification on their smartphone app and checks the details.

[1415] User Interface Example

[1416] After checking the notification, the user can choose to use an aroma diffuser to relax their cat based on the information in the app that "Momo is feeling stressed at night." They can also use the in-app communication platform to discuss the issue with other pet owners and seek additional advice.

[1417] This system can accurately estimate a pet's needs from its behavior and facial expressions, and provide that information to the owner quickly and appropriately. This will support the health and happiness of pets and reduce the burden on owners. It also provides a platform that promotes communication between pet owners, allowing them to share knowledge and experiences about pet care.

[1418] The processing flow will be explained below.

[1419] Step 1:

[1420] The device (wearable sensor) collects pet behavior data (e.g., acceleration, heart rate, activity level) at regular intervals. This data is recorded in real time and temporarily stored in the built-in memory.

[1421] Step 2:

[1422] The device (indoor camera) captures your pet's movements and expressions and stores them as video data. The camera takes high-resolution still images and videos, and uses facial recognition technology to identify your pet if necessary.

[1423] Step 3:

[1424] The devices transmit collected sensor and camera data over Wi-Fi or Bluetooth to a server, where each data set is time-stamped to ensure data synchronization and integrity.

[1425] Step 4:

[1426] The server stores the received data in a database, where behavioral and facial expression data for each pet is accumulated and used for subsequent analysis.

[1427] Step 5:

[1428] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[1429] Step 6:

[1430] The server then uses machine learning algorithms to analyze the preprocessed data, identifying behavioral patterns such as "exercise," "rest," and "excitement" from the behavioral data, and inferring emotional states such as "happiness," "anxiety," and "fatigue" from the facial expression data.

[1431] Step 7:

[1432] The server then uses the analysis results to estimate the pet's needs. For example, if the server detects that the pet frequently wanders around food and has an anxious expression, it will assume that the pet is hungry.

[1433] Step 8:

[1434] The server generates a message (text or voice) for the user based on the estimated desires. The generated message should be specific and easy to understand. For example, it could be in the form of "Mimi seems hungry."

[1435] Step 9:

[1436] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[1437] Step 10:

[1438] Users receive a notification on their smartphone app, open the app to check the details, and then understand their pet's current condition and needs and choose appropriate actions (e.g., feeding or taking them for a walk).

[1439] Step 11:

[1440] Users can use the in-app communication platform to share information with other pet owners, for example by posting questions such as, "Momo seems to be stressed at night. How do you deal with it?"

[1441] Step 12:

[1442] The server collects answers from other users in real time and displays them to the user who posted the question. The answers include specific advice and similar experiences that can improve the quality of pet care.

[1443] The above is a specific flow of processing steps in the system of the present invention. This system can analyze pet behavior and desires in detail and provide appropriate feedback to the user. The user can then take prompt and effective action based on the information obtained to support the health and happiness of their pet.

[1444] Example 1

[1445] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1446] Understanding pet behavior and emotions is important for maintaining pet health and happiness, but currently owners have to manually observe and judge, which is time-consuming and often inaccurate. It is also difficult to properly understand and respond to pet needs and stress, which can result in a risk of compromising pet health and happiness.

[1447] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1448] In this invention, the server includes a sensor means for collecting behavioral data and facial expression data of the pet, a communication means for receiving data from the sensor means, a preprocessing means for saving the received data and removing noise and outliers, an analysis means for analyzing the preprocessed data and estimating the behavioral patterns and emotional state of the pet, a generation means for generating a notification using natural language generation technology based on the estimated desires of the pet, and a transmission means for sending the generated notification to the user as a push notification. This makes it possible to more accurately and quickly analyze the behavioral and emotional state of the pet and to send notifications to the owner at appropriate times.

[1449] "Sensor means" refers to a device installed to collect data on the behavior and facial expressions of pets. Specifically, it includes wearable sensors and indoor cameras.

[1450] "Communication means" refers to the technical means for transmitting data collected from the sensor means to the server. Specifically, it includes wireless communication technologies such as Wi-Fi and Bluetooth.

[1451] "Pre-processing means" refers to technical means for storing received data and cleaning the data, such as removing noise and outliers. Specifically, this includes database management systems and data processing software.

[1452] "Analysis means" refers to technical means for analyzing the pre-processed data and inferring the pet's behavioral patterns and emotional state, including machine learning algorithms and data analysis software.

[1453] The "generation means" refers to a technical means for generating a notification about the pet's needs in natural language based on the analysis results. Specifically, it includes natural language generation technology.

[1454] "Transmission means" refers to the technical means for transmitting the generated notification to the user as a push notification. Specifically, it includes the API of the push notification service.

[1455] The present invention provides a system that analyzes behavioral data and facial expression data of a pet, accurately estimates the pet's desires, and notifies the pet's owner of the desires. Specific embodiments for implementing this system will be described below.

[1456] System Configuration

[1457] Sensor means

[1458] Wearable sensors as terminals are attached to pets' collars or bodies and collect behavioral data such as pet acceleration data, heart rate, and activity levels. Specifically, they are generally called wearable devices. Indoor cameras as terminals capture pets' movements and facial expressions in real time and save them as video data. Specifically, they are generally called surveillance cameras. This allows data on pets' behavior and facial expressions to be continuously obtained.

[1459] communication means

[1460] The terminals (wearable devices and surveillance cameras) transmit the collected data to a server using communication technologies such as Wi-Fi or Bluetooth. Specifically, a wireless communication module is used. The transmitted data includes a timestamp to ensure data synchronization.

[1461] Pretreatment means

[1462] The server stores the received data in a database and checks the data integrity. The specific database used here is generally called a relational database management system (RDBMS). Next, preprocessing such as noise removal and outlier removal is performed using the Python Pandas library. This processing improves the accuracy of the data analysis.

[1463] Analysis means

[1464] The server uses machine learning algorithms to analyze behavioral and facial expression data. Specifically, it uses libraries such as TensorFlow, and is generally referred to as a machine learning platform. It classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[1465] generation means

[1466] The server uses the analysis results to estimate the pet's needs and generates a message (text or voice) based on that information. Specifically, it uses natural language generation technology and a generative AI model (e.g., GPT-3). For example, it generates specific messages such as "Your dog wants to go for a walk" or "Momo is hungry."

[1467] Transmission method

[1468] The server then sends the generated message to the user's smartphone or tablet as a push notification, using the API of a push notification service (e.g., Firebase Cloud Messaging). The notification contains the analysis results and suggested solutions.

[1469] Specific examples

[1470] Data Collection Example

[1471] The terminal (wearable device) collects the cat's activity data (especially its behavior walking around the room at night) at regular intervals. The sensor measures the cat's acceleration and heart rate and sends the data to the server. At the same time, the terminal (surveillance camera) captures the cat's movements as video and sends it to the server as well.

[1472] Data analysis example

[1473] The server stores the received data in a relational database management system (RDBMS) and preprocesses it using Python's Pandas library to remove noise and outliers. The data is then analyzed using machine learning algorithms powered by TensorFlow. For example, it identifies a "restless" behavior pattern based on frequent nighttime movements and elevated heart rates, and uses facial recognition to detect "anxious facial expressions."

[1474] Message Generation and Notification Example

[1475] Based on the analysis results of the behavioral pattern "restless" and the emotional state "anxious expression," the server uses natural language generation technology (generative AI model) to generate a message saying "Momo may be feeling stressed at night." The message is then sent as a push notification to the user's smartphone using a push notification service (Firebase Cloud Messaging). The user receives the notification in their smartphone app and checks the details.

[1476] Prompt Sentence Examples

[1477] "Infer a pet's needs from its behavioral and facial expression data and generate a message to notify the owner. For example, if a cat moves around frequently at night and its heart rate increases, explain what kind of message should be generated based on the analysis results."

[1478] This system can accurately predict pet needs from their behavior and facial expressions, and provide them to their owners quickly and appropriately. This supports the health and happiness of pets and reduces the burden on owners. It also provides a platform that promotes communication between pet owners, allowing them to share knowledge and experiences about pet care.

[1479] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1480] Program processing flow

[1481] Step 1: Data collection

[1482] The terminal uses a wearable device to acquire the pet's behavioral data (acceleration, heart rate, activity level) and uses a surveillance camera to collect the pet's movements and facial expressions as video data.

[1483] Input: Sensor values ​​from wearable devices (acceleration data, heart rate data), video data from surveillance cameras

[1484] Output: Collected behavioral and video data

[1485] Specific operation: The wearable device uses sensors to acquire data at regular intervals (e.g., every minute) and temporarily stores it in its internal memory. The surveillance camera captures video in real time and also temporarily stores it.

[1486] Step 2: Send data

[1487] The device sends the collected data to a server via Wi-Fi or Bluetooth.

[1488] Input: Collected behavioral and video data

[1489] Output: Data packets sent to the server

[1490] How it works: Pet behavior data and video data are sent to a server via Wi-Fi, where a timestamp is added to ensure data synchronization.

[1491] Step 3: Data storage and preprocessing

[1492] The server stores the received data in a database and performs preprocessing (noise removal and outlier removal).

[1493] Input: Behavioral data and video data sent from the device

[1494] Output: Preprocessed data

[1495] How it works: The data is stored in a database management system and a script is run to remove noise and outliers using the Python Pandas library.

[1496] Step 4: Data analysis

[1497] The server uses the preprocessed data to analyze it using machine learning algorithms to estimate the pet's behavioral patterns and emotional state.

[1498] Input: Preprocessed data

[1499] Output: Analysis results of behavioral patterns and emotional states

[1500] Specific behavior: The data to be analyzed is input into a machine learning platform, and algorithms such as TensorFlow are used to classify and estimate the pet's behavioral patterns (e.g., "exercising," "resting," "excited") and emotional state (e.g., "happy," "anxious").

[1501] Step 5: Message Generation

[1502] The server uses natural language generation technology (generative AI model) based on the analysis results to generate a notification message.

[1503] Input: Analysis results of behavioral patterns and emotional states

[1504] Output: The generated notification message

[1505] Specific operation: A prompt sentence is input to the generative AI model, and a notification message for the user is created based on the generated text.

[1506] Step 6: Send the message

[1507] The server sends the generated notification message to the user's smartphone via a push notification service.

[1508] Input: The generated notification message

[1509] Output: Notification sent to the user's smartphone

[1510] Specific operation: Calls the API of the push notification service and sends the generated notification message to the user's smartphone.

[1511] Step 7: User Interface Support

[1512] The user checks the notification received on their smartphone and selects the necessary action based on the pet's condition.

[1513] Input: Received notification message

[1514] Output: Selected action (e.g., activate aroma diffuser for stress relief)

[1515] Specific Action: The user taps the notification to open the app, checks the detailed information, and selects the appropriate action if necessary. In this case, the user presses a button within the app to perform a specific action.

[1516] (Application example 1)

[1517] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1518] Today's pet owners find it difficult to accurately understand their pets' behavior and emotional state and provide appropriate care and product selection. In particular, physical stores such as pet goods shops lack systems that can quickly recommend the right product for each pet's condition. This means pet owners spend a lot of time choosing the right product in the store, which can increase stress for their pets. To solve this problem, a system is needed that collects and analyzes pet behavior and facial expression data and notifies users in real time.

[1519] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1520] In this invention, the server includes a sensor means for collecting behavioral data and facial expression data of the pet, a communication means for receiving data from the sensor means, an analysis means for analyzing the received data and estimating the pet's desires, a generation means for generating a notification based on the estimated pet's desires, and a transmission means for transmitting the generated notification to the user's mobile information terminal and suggesting products in the store, thereby enabling optimal product selection based on the pet's behavior and emotional state in a physical store.

[1521] "Pet behavior data" is information about a pet's physical activity, movements, and behavior.

[1522] "Facial expression data" is information related to the movements of a pet's face and changes in facial expression.

[1523] The "sensor means" is a device for collecting behavioral data and facial expression data of a pet.

[1524] A "wearable sensor" is a device that can be attached to a pet's collar or torso and measures the pet's movements and biological data.

[1525] An "indoor camera" is a video camera installed to capture your pet's movements and expressions.

[1526] "Communication means" refers to the technology used to transmit data from the sensor means to the server, and includes Wi-Fi, Bluetooth, etc.

[1527] The "analysis means" is a system for processing the received data and analyzing the pet's desires and emotional state.

[1528] A "machine learning algorithm" is a computational method that learns patterns from incoming data and identifies pet behaviors and emotions.

[1529] A "generator" is a system that creates a notification message based on the analyzed data.

[1530] "Transmission means" refers to a technique for transmitting the generated notification to the user's mobile information terminal.

[1531] A "user's mobile information terminal" is a mobile information device such as a smartphone or tablet used by the owner.

[1532] "Making product suggestions in-store" means recommending appropriate products to pet owners based on the analyzed condition of their pets.

[1533] The present invention provides a system that analyzes behavioral data and facial expression data of pets in a physical store, estimates the pet's desires, and proposes optimal products to pet owners. Specific embodiments for implementing this system are described below.

[1534] System Configuration

[1535] 1. Sensor means

[1536] Wearable sensor: A device that is attached to a pet's collar or body and collects behavioral data such as acceleration data, heart rate, and activity level.

[1537] Indoor camera: A device installed inside the store that captures pets' movements and expressions in real time and obtains them as video data.

[1538] 2. Means of communication

[1539] Communication method: This technology uses Wi-Fi or Bluetooth to transmit data collected from wearable sensors and indoor cameras to a server. The transmitted data includes a timestamp, making data synchronization easy.

[1540] 3. Analysis method

[1541] Analysis method: The server stores the received data in a database and checks its integrity. First, it performs preprocessing such as noise removal and outlier removal, then uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data. Specifically, it classifies behaviors such as "exercising," "resting," and "excited" based on acceleration and heart rate data, and recognizes facial expressions from video data to estimate emotions such as "happy" or "anxious."

[1542] 4. Generation means

[1543] Generation method: The server estimates the pet's needs from the analysis results and generates a message (text or voice) based on the estimate. For example, it generates a specific message such as "Your dog wants to go for a walk" or "Your pet is stressed."

[1544] 5. Transmission Method

[1545] Transmission method: The server sends the generated message to the user's mobile information device (smartphone or tablet) as a push notification. The notification contains the analysis results and suggested countermeasures.

[1546] Explanation of program processing

[1547] The server uses the following hardware and software to collect and analyze pet behavior and facial expression data: wearable sensors, indoor cameras, smartphones, and tablets; and the requests library for communication processing, SciPy, and TensorFlow for data analysis.

[1548] Data is collected in real time by wearable sensors and indoor cameras and transmitted to a server via communication means. The server stores the received data in a database and first performs preprocessing. This preprocessing includes noise removal and outlier elimination to improve data quality. Then, machine learning algorithms are used to analyze the pet's behavioral patterns and emotional state. Based on the results of this analysis, the pet's desires are estimated and a notification message is generated for the owner. This notification message is then sent to the user's mobile information terminal, and appropriate product recommendations are made to the owner in the store.

[1549] Specific examples

[1550] If a dog brought into a pet goods shop looks anxious, the system will analyze data collected through wearable sensors and indoor cameras and send a message to the owner's smartphone saying, "This dog is likely feeling anxious. We recommend a toy that will have a relaxing effect."

[1551] Prompt Sentence Examples

[1552] "Please create an application that analyzes pet behavior data (acceleration data, heart rate) and facial expression data (camera footage), estimates the pet's condition in real time, and suggests appropriate products to the owner."

[1553] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1554] Step 1:

[1555] The devices (wearable sensors and indoor cameras) collect pet behavior data (e.g., acceleration data, heart rate) and facial expression data (e.g., camera footage). Specifically, the devices acquire data in real time from sensors attached to the pet's collar or body and temporarily store the data.

[1556] Input: Acceleration data, heart rate data, and camera footage collected from your pet

[1557] Output: Collected behavioral and facial expression data

[1558] Step 2:

[1559] The terminal sends the collected data to the server using a communication method (e.g., Wi-Fi or Bluetooth). Specifically, a timestamp is added to the data, and the data is transferred to the server using a communication protocol.

[1560] Input: Behavioral data and facial expression data stored on the device

[1561] Output: Data sent to the server

[1562] Step 3:

[1563] The server stores the received data in a database, checks the data integrity, and performs preprocessing. Specifically, it checks the data integrity and removes noise and outliers. This preprocessing improves the quality of the data.

[1564] Input: Data sent to and received from the server

[1565] Output: Integrity checked and preprocessed data

[1566] Step 4:

[1567] The server analyzes the preprocessed data and uses machine learning algorithms to identify the pet's behavioral patterns and emotional state. Specifically, the machine learning model is used to classify behavioral data into categories such as "exercising," "resting," and "excited," and to estimate emotions such as "happy" and "anxious" from facial expression data.

[1568] Input: Preprocessed behavioral and facial expression data

[1569] Output: Classified behavioral and emotional states

[1570] Step 5:

[1571] The server estimates the pet's needs based on the analysis results, and generates a notification message (e.g., "Your dog wants to go for a walk" or "Your pet is stressed") to be sent to the owner based on the needs.

[1572] Input: Classified behavioral and emotional states

[1573] Output: The generated notification message

[1574] Step 6:

[1575] The server sends the generated notification message to the user's mobile information terminal (smartphone or tablet) using a communication means. Specifically, it uses push notification to send the user a message containing the analysis results and suggested countermeasures.

[1576] Input: The generated notification message

[1577] Output: The notification message sent to the user's mobile device.

[1578] Step 7:

[1579] The user checks the received message using a mobile information terminal. In the store, the appropriate product or service is selected based on the analysis of the pet's behavior and emotional state. Specifically, the user searches for the relevant product on the store's shelves according to the content of the notification message.

[1580] Input: Notification message sent to mobile device

[1581] Output: User behavior (product selection)

[1582] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1583] The present invention is a system that combines a system that analyzes pet behavior data and facial expression data to accurately estimate the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[1584] System Configuration

[1585] 1. Sensor means

[1586] The wearable sensor terminal is attached to the pet's collar or torso and collects behavioral data such as the pet's acceleration data, heart rate, and activity level.

[1587] The indoor camera serves as a terminal that captures your pet's movements and expressions in real time and saves them as video data.

[1588] 2. Means of communication

[1589] The devices (wearable sensors and indoor cameras) transmit the collected data to a server via Wi-Fi or Bluetooth, and each data set is time-stamped to ensure data synchronization and integrity.

[1590] 3. Analysis method

[1591] The server stores the received data in a database and checks the integrity of the data.

[1592] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[1593] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data.

[1594] 4. Generation means

[1595] The server estimates the pet's desires from the analysis results and generates a message (text or voice) based on them.

[1596] 5. Transmission Method

[1597] The server sends the generated message to the user's smartphone or tablet as a push notification.

[1598] 6. Emotion Engine

[1599] The system further comprises an emotion engine that recognizes the emotions of the user.

[1600] The emotion engine includes a camera and microphone for collecting facial and voice data from the user.

[1601] The server analyzes the user's facial expressions and voice to estimate the user's emotional state.

[1602] The server integrates the pet's desire estimation result obtained by the analysis means with the user's emotional state, and generates a more accurate notification based on the integration result.

[1603] Specific examples

[1604] Data Collection Example

[1605] The terminal (wearable sensor) collects the dog's activity data (e.g., acceleration, heart rate) at regular intervals. The sensor captures the dog's behavioral patterns and sends the data to a server. In parallel, the terminal (indoor camera) captures the dog's movements and facial expressions as video and sends the video to the server.

[1606] Data analysis example

[1607] The server stores the received data in a database and performs preprocessing to remove outliers and noise. It then uses machine learning algorithms to analyze the behavioral and facial expression data. For example, it can identify behavioral patterns such as "exercising," "resting," and "excited" from acceleration and heart rate data, and recognize facial expressions from video data to estimate emotions such as "happiness" and "anxiety."

[1608] Example of pet desire estimation and notification generation

[1609] The server analyzes the behavioral pattern "requesting a walk" and the emotional state "expectation" and generates a message estimating "your dog wants to go for a walk." This message is then sent to the user's smartphone as a push notification.

[1610] Emotion Engine Example

[1611] The system is equipped with a camera to capture the user's facial expressions and a microphone to collect audio. The server analyzes the facial and audio data when the user checks the notification and estimates the user's emotional state. For example, if the user shows a happy expression when checking the notification that their pet is "excited," the server determines that the owner is "very interested in playing with their pet."

[1612] Example of integrated notifications for users and pets

[1613] The server determines from the pet's behavioral data that the pet is in a "stressed state due to lack of exercise" and from the user's facial expression data that the pet is in an "excited state." By integrating this information, the server generates a message to the user saying, "Your dog is stressed due to lack of exercise, but you seem to be in a good mood. Why don't you take a walk together to refresh yourself?"

[1614] This system allows for detailed analysis of the condition of both the pet and the user, and provides more accurate and appropriate feedback based on that analysis, enabling owners to support the health and happiness of their pets and achieve better pet care.

[1615] The processing flow will be explained below.

[1616] Step 1:

[1617] The device (wearable sensor) collects pet behavior data (e.g., acceleration, heart rate, activity level) at regular intervals. This data is recorded in real time and temporarily stored in the built-in memory.

[1618] Step 2:

[1619] The device (indoor camera) captures the pet's movements and expressions and stores them as video data. The camera takes high-resolution still and video images and, if necessary, uses facial recognition technology to identify the pet.

[1620] Step 3:

[1621] The devices transmit collected sensor and camera data over Wi-Fi or Bluetooth to a server, where each data set is time-stamped to ensure data synchronization and integrity.

[1622] Step 4:

[1623] The server stores the received data in a database, where behavioral and facial expression data for each pet is accumulated and used for subsequent analysis.

[1624] Step 5:

[1625] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[1626] Step 6:

[1627] The server then uses machine learning algorithms to analyze the preprocessed data, identifying behavioral patterns such as "exercise," "rest," and "excitement" from the behavioral data, and inferring emotional states such as "happiness," "anxiety," and "fatigue" from the facial expression data.

[1628] Step 7:

[1629] The server then uses the analysis results to estimate the pet's needs. For example, if the server detects that the pet frequently wanders around food and has an anxious expression, it will assume that the pet is hungry.

[1630] Step 8:

[1631] The server generates a message (text or voice) for the user based on the estimated desires. The generated message should be specific and easy to understand. For example, it could be in the form of "Mimi seems hungry."

[1632] Step 9:

[1633] The server then sends the generated message as a push notification to the user's smartphone or tablet, which includes the analysis results and suggested countermeasures.

[1634] Step 10:

[1635] Users receive a notification on their smartphone app, open the app to check the details, and then understand their pet's current condition and needs and choose appropriate actions (e.g., feeding or taking them for a walk).

[1636] Step 11:

[1637] The device (a camera and microphone that are part of the emotion engine) collects the user's facial expression data and voice data in real time. The camera captures the user's face and the microphone records the user's voice.

[1638] Step 12:

[1639] The server analyzes the collected user facial expression and voice data to estimate the user's emotional state. For example, if the user raises their arms and smiles, it will identify this as "joy."

[1640] Step 13:

[1641] The server then integrates the pet's desire estimation results with the user's emotional state and generates more accurate notifications based on the integration results, such as "If your dog is feeling stressed due to lack of exercise and you are feeling excited, we recommend that you take him for a walk together."

[1642] Step 14:

[1643] The server then sends a notification based on the integration results back to the user's smartphone, which includes measures based on the pet's estimated needs and the user's emotional state.

[1644] Step 15:

[1645] The user checks the notification again and takes the recommended action. For example, they select the action "go for a walk." This action relieves stress for the pet and refreshes the user.

[1646] The above is a specific flow of processing steps in the system of the present invention. This system can analyze pet behavior and desires in detail, provide appropriate feedback to the user, and realize more accurate notifications that take the user's emotional state into consideration. This can support the health and happiness of pets and reduce the burden on owners.

[1647] Example 2

[1648] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1649] It is difficult to efficiently analyze pet behavioral and facial expression data and accurately estimate pet needs. Furthermore, there is a need for a method to provide feedback that takes into account the user's emotional state, thereby enabling more appropriate pet care. Furthermore, it is also important to improve the accuracy of analysis by removing noise from the data and detecting outliers.

[1650] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1651] In this invention, the server includes: a sensor means for collecting pet behavior data and facial expression data; a communication means for receiving data from the sensor means; a storage means for saving the received data; a preprocessing means for performing noise reduction and outlier detection / correction on the received data; an analysis means using a machine learning algorithm to identify the pet's behavior pattern and emotional state from the preprocessed data; a generation means for estimating the pet's desires using the analysis means and generating a notification based on the estimated pet desires; a transmission means for sending the generated notification to a user; an emotion engine including a means for collecting and analyzing user facial expression data and voice data; and a means for integrating the pet desire estimation result obtained by the analysis means with the user's emotional state and generating a notification based on the integration result. This enables detailed analysis of the interactive state between the pet and the user and provides appropriate and accurate feedback.

[1652] The "sensor means" is a device for collecting behavioral data and facial expression data of a pet.

[1653] The "communication means" is a device for transmitting data collected from the sensor means to the server.

[1654] The "storage means" is a device for storing received data in a database.

[1655] The "preprocessing means" is a device that removes noise from the received data and detects and corrects abnormal values.

[1656] An "analysis means" is a device that uses machine learning algorithms to identify the behavioral patterns and emotional states of the pet from the pre-processed data.

[1657] The "generation means" is a device that generates a notification based on the pet's desires estimated by the analysis means.

[1658] The "transmitting means" is a device for transmitting the generated notification to the user.

[1659] An "emotion engine" is a device that collects and analyzes a user's facial expression and voice data to estimate the user's emotional state.

[1660] The present invention is a system that combines a system that analyzes behavioral data and facial expression data of a pet and accurately estimates the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system will be described below.

[1661] Sensor means

[1662] The devices used are a wearable sensor and an indoor camera. The wearable sensor is attached to the pet's collar or torso and collects behavioral data such as acceleration data, heart rate, and activity level. In addition, the indoor camera captures the pet's movements and facial expressions in real time and saves them as video data.

[1663] Specific examples

[1664] For example, the system records acceleration data when a dog runs and changes in heart rate while the dog is eating. In addition, an indoor camera captures the dog's facial expressions in real time.

[1665] communication means

[1666] The devices (wearable sensors and indoor cameras) transmit the collected data via Wi-Fi or Bluetooth to a server, which timestamps each data set and keeps the data synchronized and consistent.

[1667] Specific examples

[1668] The data detected by the sensor is sent to a server in real time, allowing for centralized management of pet activity. For example, data on the moment a dog chases a ball is sent along with its heart rate data at that time.

[1669] Data storage

[1670] The server stores the received data in a database, which makes it possible to refer to all past data and perform comparative analysis.

[1671] Specific examples

[1672] Not only the data from this walk, but also data from past walks is saved, allowing you to track changes at each point in time.

[1673] Data Preprocessing

[1674] The server removes noise from the stored data and detects and corrects outliers to improve data accuracy, enabling highly reliable data analysis.

[1675] Specific examples

[1676] A process is performed to remove abnormal heart rate data caused by temporary malfunction of the sensor.

[1677] Data analysis

[1678] The server uses machine learning algorithms to analyze the behavioral and facial expression data, identify behavioral patterns, and estimate the pet's emotional state.

[1679] Specific examples

[1680] Data showing that the dog is still for a certain period of time is used to identify the dog as "resting," and data on the dog's facial expression is used to estimate its "sense of security."

[1681] Message Generation

[1682] Based on the analysis results, the server generates notifications that infer your pet's needs, such as "Your dog wants a walk" or "It's time for exercise!"

[1683] Send notifications

[1684] The server sends the generated notification to the user's smartphone or tablet as a push notification, allowing the user to keep track of their pet's status in real time.

[1685] Specific examples

[1686] A notification will appear on your smartphone saying, "Your dog needs more exercise. We recommend taking it for a walk."

[1687] Emotion Engine

[1688] The system includes an emotion engine that recognizes the user's emotions. It uses a camera and microphone to collect the user's facial expressions and voice, which are then analyzed by a server.

[1689] Specific examples

[1690] If the user has a surprised expression, the emotion is analyzed and recognized as "surprise."

[1691] Integrated analytics and advanced notification generation

[1692] The server integrates the pet's desire estimation results with the user's emotional state to generate more accurate notifications.

[1693] Specific examples

[1694] It integrates the fact that a pet is lacking exercise with the user's relaxation and generates a notification such as, "Your dog is lacking exercise, but you seem relaxed. Would you like to join us for some light exercise?"

[1695] Prompt Sentence Examples

[1696] Data collection:

[1697] "Use wearable sensors to collect acceleration and heart rate data from your dog."

[1698] "Use an indoor camera to capture facial expression data of a dog."

[1699] Data transmission:

[1700] "Send the collected data to the server via Wi-Fi."

[1701] Data Retention:

[1702] Save the received data in the database.

[1703] Data preprocessing:

[1704] "Denoise your data and detect outliers"

[1705] Data Analysis:

[1706] "Implement machine learning algorithms for behavioral pattern identification and emotional state estimation"

[1707] Message Generation:

[1708] "Generate a message that estimates your pet's desires based on the results of data analysis."

[1709] Notification sent:

[1710] "Send the generated message to the user's smartphone via push notification."

[1711] Emotion recognition:

[1712] "Recognize the user's facial expressions and voice and analyze their emotions"

[1713] Integrated analytics and advanced notification generation:

[1714] "Integrate pet needs and user emotions to generate accurate notifications"

[1715] This system allows detailed analysis of the pet and user's condition and provides appropriate and accurate feedback, leading to better pet care.

[1716] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1717] Step 1: Data collection

[1718] The devices (wearable sensors and indoor cameras) collect the dog's acceleration, heart rate, activity level, movement, and facial expression data in real time. The wearable sensors measure these data, and the indoor cameras capture video data.

[1719] Input: Dog activity and facial expressions

[1720] Output: Acceleration data, heart rate data, video data

[1721] Specifically, the wearable sensor measures the dog's acceleration and heart rate every second, and the indoor camera captures video at 30 frames per second. For example, when the dog starts exercising, the acceleration and heart rate data change, and the dog's movements are recorded on video.

[1722] Step 2: Send data

[1723] The devices transmit the collected data to a server via Wi-Fi or Bluetooth, and each data set is time-stamped to ensure data synchronization and integrity.

[1724] Input: Collected acceleration data, heart rate data, video data

[1725] Output: The dataset sent to the server

[1726] Specifically, the device collects all the data collected every 10 seconds and sends it to the server via Wi-Fi. For example, data from 10 seconds during which a dog is eating is sent to the server.

[1727] Step 3: Save Data

[1728] The server stores the received data in a database, which makes it possible to refer to all past data.

[1729] Input: The dataset sent to the server

[1730] Output: Data stored in the database

[1731] Specifically, the server classifies the received data by timestamp and stores it in the appropriate table in the database. For example, heart rate data is stored in the "heart rate" table, and video data is stored in the "video" table.

[1732] Step 4: Data Preprocessing

[1733] The server removes noise from the stored data and detects and corrects outliers, thereby improving the accuracy of the data.

[1734] Input: Data stored in a database

[1735] Output: Preprocessed data

[1736] Specifically, the server applies outlier detection algorithms to detect and remove, for example, extremely high heart rates. It also applies noise reduction filters to smooth the acceleration data.

[1737] Step 5: Data analysis

[1738] The server uses machine learning algorithms to analyze the behavioral and facial expression data, identify behavioral patterns, and infer the pet's emotional state.

[1739] Input: Preprocessed data

[1740] Output: Behavioral patterns and emotional states

[1741] Specifically, the server uses the collected acceleration and heart rate data to identify behavioral patterns such as "exercising" or "resting," and infers emotions such as "happiness" or "anxiety" from the video data. For example, if a sudden change in acceleration data coincides with a rise in heart rate, it will identify this as "exercising."

[1742] Step 6: Message Generation

[1743] Based on the analysis results, the server estimates the pet's needs and generates a notification based on them.

[1744] Input: behavioral patterns and emotional states

[1745] Output: Notification message

[1746] Specifically, the server combines the behavioral pattern of "lack of exercise" with the emotional state of "discomfort" to generate a message that says, "Your dog needs exercise. Take it for a walk."

[1747] Step 7: Send notification

[1748] The server sends the generated notification to the user's smartphone or tablet as a push notification.

[1749] Input: Notification message

[1750] Output: Push notification to user device

[1751] Specifically, the server sends the generated notification message to the user interface API, and a notification such as "Your dog needs more exercise. Please take it for a walk" is displayed on the smartphone.

[1752] Step 8: Emotion Recognition

[1753] The system includes an emotion engine that recognizes the user's emotions. The camera and microphone collect the user's facial expressions and voice, which are then analyzed by the server.

[1754] Input: User's facial expression data and voice data

[1755] Output: User's emotional state

[1756] Specifically, when a user plays with a pet, a camera and microphone capture the scene, and the server analyzes the footage to recognize the user's "joy."

[1757] Step 9: Integrated analytics and advanced notification generation

[1758] The server integrates the pet's desire estimation results with the user's emotional state to generate more accurate notifications.

[1759] Input: Pet behavior patterns and emotional state, user emotional state

[1760] Output: Consolidated notification message

[1761] Specifically, the server integrates the fact that the pet is lacking exercise with the user's relaxation and generates a notification saying, "Your dog is lacking exercise. Let's go for a walk together to refresh yourself."

[1762] Through these processing steps, the conditions of the pet and the user can be analyzed in detail, and appropriate and accurate feedback can be provided.

[1763] (Application example 2)

[1764] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1765] Current pet care systems only estimate pet needs based on behavioral and emotional data, but are unable to provide feedback that takes into account the user's emotional state. As a result, they lack concrete support for deepening communication and relationships between pets and users. Furthermore, they are unable to order pet food at the appropriate time to meet a pet's appetite, creating issues in terms of pet health management and user convenience.

[1766] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes sensor means for collecting behavioral data and facial expression data of the pet, communication means for receiving data from the sensor means, analysis means for analyzing the received data and inferring the pet's desires, emotion engine means for collecting and analyzing user emotion data, generation means for generating a notification based on the inferred pet's desires and the analyzed user's emotional state, and transmission means for transmitting the generated notification to the user. This makes it possible to provide more appropriate and timely feedback based on the pet's desires and the user's emotional state, thereby improving the health management and quality of life of the pet and the user.

[1767] "Sensor means" refers to a device used to collect behavioral data or facial expression data of a pet or user, and includes wearable sensors, indoor cameras, cameras, and microphones.

[1768] The "communication means" is a device for transmitting data collected from the sensor means to the server, and includes wireless communication technology and wired communication technology.

[1769] An "analysis means" is a device or program that processes the received data and uses machine learning algorithms to identify the pet's behavioral patterns and needs, as well as the user's emotional state.

[1770] The "emotion engine means" is a device or program that collects and analyzes facial expression data and voice data of the user to estimate the user's emotional state.

[1771] The "generating means" is a device or program that generates a notification message based on the analyzed pet's desires and the user's emotional state.

[1772] The "transmission means" is a device or program for transmitting the generated notification to the user's mobile terminal or the like as a push notification.

[1773] A "wearable sensor" is a sensor device that is attached to a pet's collar or body and collects data such as the pet's acceleration, heart rate, and activity level.

[1774] An "indoor camera" is a camera device that captures pet movements and facial expressions in real time and collects them as video data.

[1775] A "camera" is a photographing device for capturing the user's facial expression.

[1776] A "microphone" is a recording device for collecting a user's voice data.

[1777] A "machine learning algorithm" is an algorithm that analyzes large amounts of data, learns patterns and features, and makes predictions and classifications about future data.

[1778] This invention is a system that combines a system that analyzes pet behavior data and facial expression data to accurately estimate the pet's desires with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[1779] System Configuration

[1780] 1. Sensor means

[1781] Wearable sensors: These are attached to a pet's collar or torso and collect behavioral data such as pet acceleration data, heart rate, and activity level.

[1782] Indoor camera: This captures your pet's movements and expressions in real time and saves them as video data.

[1783] Camera and microphone: This is for collecting facial and voice data from the user.

[1784] 2. Means of communication

[1785] Wi-Fi or Bluetooth: This is used to transmit collected data to a server, where each data set is time-stamped to keep the data synchronized and consistent.

[1786] 3. Analysis method

[1787] The server stores the received data in a database and checks the integrity of the data.

[1788] The server performs preprocessing on the received data, such as noise removal and outlier detection, to correct unnatural fluctuations and measurement errors.

[1789] The server uses machine learning algorithms to analyze the behavioral patterns and emotional state of the pet from the behavioral and facial expression data, as well as the emotional state of the user.

[1790] 4. Generation means

[1791] The server integrates the pet's desires and the user's emotional state from the analysis results and generates a message (e.g., text or voice) based on the integration.

[1792] 5. Transmission Method

[1793] The server sends the generated message to the user's smartphone or tablet as a push notification.

[1794] Example

[1795] Examples of data collection:

[1796] The terminal (wearable sensor) collects the dog's activity data (e.g., acceleration, heart rate) at regular intervals. The sensor captures the dog's behavioral patterns and sends the data to a server. In parallel, the terminal (indoor camera) captures the dog's movements and facial expressions as video and sends the video to the server.

[1797] An example of analysis:

[1798] The server stores the received data in a database and performs preprocessing to remove outliers and noise. It then uses machine learning algorithms to analyze the behavioral and facial expression data. For example, it can identify behavioral patterns such as "exercising," "resting," and "excited" from acceleration and heart rate data, and recognize facial expressions from video data to estimate emotions such as "happiness" and "anxiety."

[1799] An example of pet desire estimation and notification generation:

[1800] The server analyzes the behavioral pattern "requesting a walk" and the emotional state "expectation" and generates a message estimating "your dog wants to go for a walk." This message is then sent to the user's smartphone as a push notification.

[1801] An example of an emotion engine:

[1802] The system is equipped with a camera to capture the user's facial expressions and a microphone to collect audio. The server analyzes the facial and audio data when the user checks the notification and estimates the user's emotional state. For example, if the user shows a happy expression when checking the notification that their pet is "excited," the server determines that the owner is "very interested in playing with their pet."

[1803] An example of a unified notification for users and pets:

[1804] The server determines from the pet's behavioral data that the pet is in a "stressed state due to lack of exercise" and from the user's facial expression data that the pet is in an "excited state." By integrating this information, the server generates a message to the user saying, "Your dog is stressed due to lack of exercise, but you seem to be in a good mood. Why don't you take a walk together to refresh yourself?"

[1805] Examples and prompts:

[1806] Examples:

[1807] Sensor data: {"timestamp": "2023-10-01T10:00:00", "acceleration": 0.45, "heart_rate": 120}

[1808] Camera data: {"timestamp": "2023-10-01T10:00:00", "image": "base64_encoded_image_data"}

[1809] User data: {"timestamp": "2023-10-01T10:00:00", "expression": "smiling", "voice_tone": "neutral"}

[1810] Example prompt sentence:

[1811] Analyze the behavioral patterns of the user's pet based on sensor data and camera data, and infer whether the pet is hungry. Also, estimate the user's emotions based on the user's facial expression data. If the pet is hungry and the user is happy, generate a message suggesting the user to order pet food. The following is sample data: Pet-related sensor data: {"timestamp": "2023-10-01T10:00:00", "acceleration": 0.45, "heart_rate": 120}, Camera data: {"timestamp": "2023-10-01T10:00:00", "image": "base64_encoded_image_data"}, User data: {"timestamp": "2023-10-01T10:00:00", "expression": "smiling", "voice_tone": "neutral"}

[1812] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1813] Step 1:

[1814] The devices (wearable sensors and indoor cameras) collect pet behavior data (e.g., acceleration, heart rate) and facial expression data at regular intervals. The inputs are raw data from the sensors (acceleration, heart rate, video). The output is collected data with timestamps.

[1815] Step 2:

[1816] The device sends the collected data to the server via Wi-Fi or Bluetooth. The input is the raw data collected by the device and a timestamp. The output is the data transferred to the server.

[1817] Step 3:

[1818] The server stores the received data in a database and checks the integrity of the data. The input is the time-stamped data sent from the device. The output is the data whose integrity has been checked and stored in the database.

[1819] Step 4:

[1820] The server performs preprocessing on the received data, such as noise removal and outlier detection. The input is the received data, and the output is the data with noise removed and outliers corrected.

[1821] Step 5:

[1822] The server uses machine learning algorithms to analyze the pet's behavioral patterns and emotional state from the behavioral and facial expression data, as well as the user's emotional state. The inputs are preprocessed behavioral data, facial expression data, and the user's facial expression data. The output is the pet's behavioral patterns (e.g., exercising, resting, excited) and emotional state (e.g., happy, anxious), as well as the user's emotional state.

[1823] Step 6:

[1824] The server integrates the pet's needs and the user's emotional state from the analysis results and generates a message based on them. The inputs are the analyzed pet's needs and the user's emotional state. The output is a generated message (e.g., "Your dog wants to go for a walk") based on the pet's needs and the user's emotional state.

[1825] Step 7:

[1826] The server generates the message and sends it to the user's smartphone or tablet as a push notification. The input is the generated notification message. The output is the push notification sent to the user's smartphone.

[1827] The above are the specific processing steps for implementing the invention. This system analyzes the behavioral and facial expression data of the pet, and is able to provide more appropriate feedback and notifications that take into account the pet's needs and the user's emotional state.

[1828] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1829] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1830] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1831] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1832] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1833] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1834] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1835] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1836] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1837] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1838] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1839] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1840] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1841] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1842] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1843] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1844] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1845] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1846] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1847] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1848] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1849] The following is further disclosed regarding the above embodiment.

[1850] (Claim 1)

[1851] a sensor means for collecting behavioral data and facial expression data of the pet;

[1852] communication means for receiving data from said sensor means;

[1853] an analysis means for analyzing the received data and estimating the desires of the pet;

[1854] a generating means for generating a notification based on the estimated pet's desire;

[1855] a transmitting means for transmitting the generated notification to a user;

[1856] A system including:

[1857] (Claim 2)

[1858] 2. The system of claim 1, wherein the sensor means includes a wearable sensor attached to the pet's collar or body, and an indoor camera that captures the pet's movements and facial expressions.

[1859] (Claim 3)

[1860] 2. The system of claim 1, wherein the analyzing means uses machine learning algorithms to identify the behavioral patterns and emotional states of the pet from t...

Claims

1. a sensor means for collecting behavioral data and facial expression data of the pet; communication means for receiving data from said sensor means; an analysis means for analyzing the received data and estimating the desires of the pet; a generating means for generating a notification based on the estimated pet's desire; a transmitting means for transmitting the generated notification to a user; A system including:

2. 2. The system of claim 1, wherein the sensor means includes a wearable sensor attached to the pet's collar or body, and an indoor camera that captures the pet's movements and facial expressions.

3. 2. The system of claim 1, wherein the analyzing means uses machine learning algorithms to identify behavioral patterns and emotional states of the pet from the received data.

Images