Information processing system

Abstract

The present invention provides an information processing system, comprising: means for collecting activity amount, sleep pattern, and food intake data from an information collection means worn on a dog body; means for transmitting the collected data to a resolution server; the device is used for inputting the collected data into the generative artificial intelligence model by the analysis server and analyzing the data; the device is used for sending an analysis result to the terminal and informing a user; the device is used for receiving input about questions and dog symptoms from a user and generating suggestions through a generative artificial intelligence model; means for transmitting the generated suggestion to the terminal and displaying the suggestion to the user; a device for providing veterinary online consultation appointment functionality.

Description

Technical Field

[0001] The technology disclosed herein relates to an information processing system. Background Technology

[0002] Japanese Patent Application Publication No. 2022-180282 discloses a method for controlling a role-based chatbot executed by at least one processor. The method includes the following steps: receiving a user's speech; adding the user's speech to a prompt word, the prompt word containing instruction statements associated with an explanation of the chatbot's role; encoding the prompt word; and inputting the encoded prompt word into a language model to generate a chatbot response to the user's speech.

[0003] Existing methods for canine health management often rely on manual observation, which not only easily misses key health signals but also suffers from incomplete data collection, untimely analysis, a lack of scientifically tailored personalized advice, and the inability of users to efficiently consult with veterinarians online. Therefore, there is an urgent need for a system that can automatically collect canine health data, intelligently analyze it, and efficiently provide users with health advice and consultation services to improve the scientific rigor and convenience of canine health management. Summary of the Invention

[0004] This invention provides an information processing system, comprising: a device for collecting data on activity levels, sleep patterns, and food intake from an information collection device worn on a dog; a device for sending the collected data to a parsing server; a device for the parsing server to input the data into a generative artificial intelligence model for analysis; a device for sending the analysis results to a terminal and notifying the user; a device for receiving user input regarding problems and canine symptoms and generating suggestions through the generative artificial intelligence model; a device for sending the generated suggestions to the terminal and displaying them to the user; and a device for scheduling online consultations with a veterinarian. This system enables automated collection, intelligent analysis, anomaly identification, and personalized online consultation of canine health data, effectively improving the intelligence and efficiency of canine health management.

[0005] "Information collection device" refers to a device that can be worn on a dog to automatically detect and record health-related data such as the dog's activity level, sleep patterns, and food intake.

[0006] A "parse server" refers to a server-side system that is responsible for receiving, storing, preprocessing, and analyzing health data sent by information collection devices, and calling artificial intelligence models to generate analysis results and suggestions.

[0007] "Generative artificial intelligence models" refer to artificial intelligence algorithms that can analyze input health data, predict trends, detect anomalies, and generate corresponding natural language suggestions or responses.

[0008] "Terminal" refers to user-operated devices including smartphones, tablets, or other devices that can communicate with the server and receive / display health analysis results and recommendations.

[0009] "User" refers to an individual who uses this system to manage the health of their dog, receive analysis reports and suggestions, and can seek online consultation.

[0010] "Activity level" refers to the intensity of a dog's exercise, number of steps, distance traveled, and other values ​​that objectively reflect the degree of its physical activity within a certain period of time.

[0011] "Sleep pattern" refers to data such as the dog's total daily sleep duration, sleep / wake time, and sleep cycles, which reflect its rest patterns and quality.

[0012] "Food intake" refers to data such as the quality, frequency, or nutritional composition of food actually consumed by a dog within a specific time period.

[0013] "Recommendations" refer to specific content generated by artificial intelligence models based on health data analysis results, used to guide users in adjusting dog care methods or to alert them to relevant health risks.

[0014] "Online consultation appointment" refers to the function of users scheduling remote communication or health consultation services with veterinarians through a terminal. Attached Figure Description

[0015] Figure 1 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the first embodiment.

[0016] Figure 2 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and smart device according to the first embodiment.

[0017] Figure 3 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the second embodiment.

[0018] Figure 4 This is a conceptual diagram illustrating an example of the main functions of the data processing device and smart glasses according to the second embodiment.

[0019] Figure 5 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the third embodiment.

[0020] Figure 6 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and head-mounted terminal according to the third embodiment.

[0021] Figure 7 This is a conceptual diagram illustrating an example of the configuration of the data processing system according to the fourth embodiment.

[0022] Figure 8 This is a conceptual diagram illustrating an example of the main functions of the data processing device and robot according to the fourth embodiment.

[0023] Figure 9 This represents an emotion map that maps multiple emotions.

[0024] Figure 10 This represents an emotion map that maps multiple emotions.

[0025] Figure 11 This is a sequence diagram illustrating the processing flow of the data processing system of the first embodiment.

[0026] Figure 12 This is a sequence diagram illustrating the processing flow of the data processing system in Application Example 1.

[0027] Figure 13 This is a sequence diagram illustrating the processing flow of the data processing system of the second embodiment.

[0028] Figure 14 This is a sequence diagram illustrating the processing flow of the data processing system in Application Example 2. Detailed Implementation

[0029] Hereinafter, an example of an implementation of the system according to the present disclosure will be described with reference to the accompanying drawings.

[0030] First, let me explain the terminology used in the following instructions.

[0031] In the following embodiments, the processor (hereinafter referred to as "processor") with reference numerals may be a single computing device or a combination of multiple computing devices. Furthermore, the processor may be a single computing device or a combination of multiple computing devices. Examples of computing devices include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0032] In the following embodiments, RAM (Random Access Memory), as indicated in the figures, is a memory that temporarily stores information and is used as working memory by the processor.

[0033] In the following embodiments, the memory, as indicated by the reference numerals, is one or more non-volatile storage devices that store various programs and parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), disks (e.g., hard disks), or magnetic tapes.

[0034] In the following embodiments, the communication I / F (Interface) with reference numerals is an interface that includes a communication processor and an antenna, etc. The communication I / F is responsible for communication between multiple computers. As an example of a communication specification applicable to the communication I / F, wireless communication specifications such as 5G (5th Generation Mobile Communication System), Wi-Fi (wireless fidelity) (registered trademark), or Bluetooth (registered trademark) can be listed.

[0035] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it can be only A, only B, or a combination of A and B. Furthermore, in this specification, when "and / or" connects to express more than three items, the same interpretation as "A and / or B" applies.

[0036] First Implementation Method

[0037] Figure 1 An example of the configuration of the data processing system 10 according to the first embodiment is shown.

[0038] like Figure 1 As shown, the data processing system 10 includes a data processing device 12 and an intelligent device 14. A server can be cited as an example of the data processing device 12.

[0039] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, 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).

[0040] The smart device 14 includes a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. In addition, the receiving device 38, output device 40, camera 42, and communication I / F 44 are also connected to the bus 52.

[0041] The receiving device 38 includes a touchscreen 38A and a microphone 38B, and receives user input. The touchscreen 38A receives user input via touch by detecting contact with an indicator (e.g., a pen or finger). The microphone 38B receives user input via sound by detecting the user's voice. The control unit 46A in the processor 46 sends data representing the user input received by the touchscreen 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data representing the user input.

[0042] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting data in a form perceptible to the user 20 (e.g., sound and / or text). The display 40A displays visual information such as text and images according to instructions from the processor 46. The speaker 40B outputs sound according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as 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.

[0043] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for sending and receiving various information between processor 46 and processor 28 via network 54.

[0044] Figure 2 The diagram shows an example of the main functions of the data processing device 12 and the smart device 14.

[0045] like Figure 2 As shown, in the data processing apparatus 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the memory 32. The specific processing program 56 is an example of a "program" as understood in this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0046] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. In the emotion inference function (emotion-specific function) using the emotion-specific model 59, various inferences and predictions related to the user's emotions are performed, including inferences and predictions of the user's emotions, but this is not limited to this example. Furthermore, emotion inference and prediction may also include, for example, emotion analysis (parsing).

[0047] In the smart device 14, the processor 46 performs the acceptance output processing. The memory 50 stores the acceptance output program 60. The acceptance output program 60 is used in conjunction with the data processing system 10 and the specific processing program 56. The processor 46 reads the acceptance output program 60 from the memory 50 and executes the read acceptance output program 60 on the RAM 48. The acceptance output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance output program 60 executed on the RAM 48. Furthermore, the smart device 14 has the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and these models can also be used to perform the same processing as the specific processing unit 290. The acceptance output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance output program 60 executed on the RAM 48.

[0048] Alternatively, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. Furthermore, the data processing device 12 may be a server device or a user-held terminal device (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of the processing of the data processing system 10 of the first embodiment will be described.

[0049] Example 1

[0050] The flow of a specific process in Example 1 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart device 14. Furthermore, the data processing device 12 is referred to as the "server," and the smart device 14 is referred to as the "terminal."

[0051] Existing animal health management systems are fragmented across multiple stages, including biological data collection, data preprocessing, anomaly detection, suggestion generation, and appointments with professionals. This lack of unified integration leads to cumbersome user operations, delayed information feedback, inaccurate data parsing, and an inability to intelligently generate personalized suggestions based on specific user input. Furthermore, traditional systems are inefficient at filtering outomas and filling in missing values, and are insufficient in providing health trend predictions and preventative recommendations, failing to meet the needs of comprehensive and scientific animal health management.

[0052] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Embodiment 1 is achieved by the following means.

[0053] In this invention, the server includes a preprocessing unit for filtering outliers and completing missing values ​​in the collected biological data; a unit for inputting the preprocessed data into a generative artificial intelligence model for intelligent analysis; a unit for generating suggestion information based on the model's output and pushing it to the user terminal; a unit for receiving user input information and generating personalized suggestions through the generative artificial intelligence model; and a functional module for providing online appointments with professionals. Furthermore, the system includes a unit for automatically generating intelligent model input prompts via the terminal and a unit for managing analysis and suggestion history. This achieves the integration of efficient biological data collection, reliable preprocessing, intelligent analysis, personalized suggestion push, and appointment functions, improving the scientific nature of animal health management and the user experience.

[0054] "Information collection device" refers to an electronic device worn on an animal to collect biological data such as the animal's activity level, sleep patterns, and food intake.

[0055] "Biological data" refers to various types of data that reflect the health status of animals, including but not limited to activity level, sleep duration, food intake, heart rate, and body temperature.

[0056] "Information processing device" refers to a computing device that can receive, store, process and analyze biological data, usually referring to a server or cloud platform.

[0057] "Terminal device" refers to a device used by a user to receive notifications, input information, and display suggested information, such as a smartphone, tablet, or personal computer.

[0058] "Outlier filtering" refers to the process of automatically detecting and removing obviously unreasonable data items from collected biological data.

[0059] "Missing value completion" refers to the process of supplementing or estimating missing parts in biological data based on historical data or statistical models.

[0060] "Generative artificial intelligence models" refer to intelligent systems built on deep learning algorithms that can automatically generate analytical results or suggestions based on input data.

[0061] "Prompt statements" refer to natural language input used to guide generative artificial intelligence models in data parsing or to suggest the generation of data.

[0062] "Suggested information" refers to health management suggestions that are automatically generated by the system and pushed to users based on biological data and user input.

[0063] "Professionals" refers to experts with qualifications related to animal medical care or health management, such as veterinarians.

[0064] The "appointment function" refers to the online appointment service provided by the system for users to schedule consultations with professionals.

[0065] "Push notification function" refers to the function of terminal devices to proactively and promptly convey analysis results or suggestions to users through message pop-ups and other means.

[0066] "Historical information management" refers to the system's function of recording and managing various operations and results, such as analysis, suggestions, user input, and appointments.

[0067] This invention relates to an animal health management system, which mainly includes an information collection device, a terminal device, an information processing device (server), a generative artificial intelligence model, and a reservation module. The following will describe in detail the embodiments of this invention based on the above structure, so that others can accurately implement and apply this invention according to this description.

[0068] The data collection device can use hardware such as a smart collar to be securely worn on the animal, monitoring and collecting biological data such as activity level, sleep patterns, and food intake in real time. The device has a built-in Bluetooth or WiFi communication module, enabling data exchange with external devices.

[0069] Terminal devices, such as smartphones and tablets, run dedicated health management applications. These devices connect to the data collection device via Bluetooth or Wi-Fi and acquire the animal's biological data according to a set collection cycle (e.g., every 30 minutes). The collected data is first stored locally on the terminal and then uploaded to a server via HTTPS when a network connection is available. The terminal application also includes push notification functionality and a user-friendly interface, allowing users to view suggestions, enter questions, set data collection intervals, and schedule consultations.

[0070] The server, as the core processing unit of the system, is equipped with high-performance computing resources and can run software environments such as Python and Flask. After receiving biological data uploaded by the terminal, the server first performs data quality checks through programming, including outlier filtering (e.g., detecting mutation activity data) and missing value completion (e.g., filling in missing values ​​by referring to historical averages). The preprocessed data is then fed as input to the generative artificial intelligence model.

[0071] In one specific embodiment, the generative artificial intelligence model can be a commonly used deep learning natural language processing model, such as the "GPT-4" model. This model can connect to a server via an open platform API. The server can input raw or preprocessed biological data along with prompts into the generative artificial intelligence model to generate text content including health trend assessments, explanations of abnormal indicators, and specific suggestions.

[0072] The server not only promptly pushes the model's output suggestions to the terminal device, but also generates personalized responses based on the user's input. For example, if a user inputs "My dog ​​coughs very badly at night" through the terminal, the terminal uploads this input to the server. The server then combines this with the latest biological data to automatically generate suggestions such as "If the cough lasts for more than 48 hours, it is recommended to schedule an online consultation with a professional" and pushes this to the terminal interface.

[0073] In addition, the terminal device is equipped with an automatic prompt generation module, which can automatically organize data analysis prompts suitable for generative artificial intelligence models based on user-defined concerns or the characteristics of collected data. For example, the system can automatically generate the following prompt and submit it to the model: "Please analyze the following health data: activity level 2580 steps, sleep 7.6 hours, food intake 45 grams, and indicate whether there are any health risks and subsequent care suggestions."

[0074] Users can schedule online consultations with professionals anytime via the terminal. The terminal can directly complete the booking process based on the server's deadline and available time slots. Users will receive a notification on the interface such as "Booking successful. Please contact us online at 10:00 AM tomorrow".

[0075] In this invention, the hardware is not limited to the above-mentioned components, and the software used can be Python, Flask, MySQL, or MongoDB databases. The artificial intelligence model platform can be any of the mainstream generative artificial intelligence APIs. This invention enables the automatic and scientific collection and processing of animal health data, and provides users with personalized, timely, and reliable health management and scientific advice based on generative artificial intelligence models.

[0076] Example of a prompt statement:

[0077] "Please analyze the following animal health data, identify any abnormalities, and provide care recommendations: activity level 2900 steps, sleep 7 hours, food intake 40 grams."

[0078] "If an animal continues to cough, what are the initial steps to take and determine if a professional appointment is necessary?"

[0079] "Based on the changes in the animal's activity level and sleep over the past three days, please provide a trend analysis and precautions."

[0080] Through the above methods, the present invention can achieve efficient, intelligent and comprehensive animal health monitoring and management, thereby improving user experience and animal welfare.

[0081] use Figure 11 The processing flow is explained.

[0082] Step 1:

[0083] The terminal connects to an information collection device worn by the animal via Bluetooth or WiFi, periodically reading the animal's biological data, such as activity level, sleep duration, and food intake. The input is the raw biological data output in real time from the information collection device, and the output is the collected data stored in the terminal's local database. In actual operation, the terminal automatically wakes up the communication module every 30 minutes to acquire data and update the App interface to display the latest information.

[0084] Step 2:

[0085] The terminal packages the locally collected biological data into a JSON structure and uploads it to the server via HTTPS. The input is a set of biological data stored in the terminal's local database, and the output is the data successfully received by the server. Specifically, when the terminal detects a normal network environment, it automatically sends the remaining data in batches to the specified API interface on the server.

[0086] Step 3:

[0087] After receiving the biological data uploaded by the terminal, the server first performs data validation, including outlier detection and missing value completion. The input is the raw biological data from the terminal; the data processing involves using statistical rules to identify and remove outliers, supplementing missing items based on historical records, and the output is the optimized biological data. The server records the removed outliers and the completed data in the data processing log to ensure data integrity.

[0088] Step 4:

[0089] The server takes preprocessed biological data as input, generates appropriate prompts, and guides a generative AI model for intelligent analysis. The input consists of optimized biological data and the generated prompts. Data processing involves assembling the data into a natural language description in a standard format, which is then sent as a request to the generative AI model. The output is the analysis results and health suggestions provided by the AI ​​model. Specifically, the server automatically generates prompts such as "Please analyze the following health data: activity level 2580 steps, sleep 7.6 hours, food intake 45 grams, and point out potential health risks and suggestions," and calls the API to obtain the AI ​​output.

[0090] Step 5:

[0091] The server processes the output of the generative AI model and constructs it into structured suggestion text, while simultaneously storing the analysis content and suggestions in the database. The input is the natural language analysis and suggestions from the AI ​​model; data processing involves adding timestamps and user IDs; the output is a finalized suggestion draft for the user. The server then pushes the suggestion content to the target terminal.

[0092] Step 6:

[0093] The terminal receives suggestions or analysis results pushed by the server and displays them instantly via push notifications from the app or the main interface. The input is the suggested text from the server, and the output is a health reminder that the user can directly access. In practice, the terminal displays a pop-up notification saying, "Suggestion: You've been sleeping less lately; please reduce your activity level and carefully observe your animal's condition," while the main interface refreshes to display details.

[0094] Step 7:

[0095] Based on suggestions received by the terminal or their own observations, users input specific questions or feedback through the app interface (e.g., "animal has a persistent cough"). The terminal then uploads this information to the server. The input consists of the text content entered by the user, and the output consists of the user's question and related data sent to the server API.

[0096] Step 8:

[0097] After receiving user input, the server combines the latest biological data with the user's question to generate a new prompt for the generative AI model. The input consists of the user's question and recent biological data; the data processing involves comprehensively describing the user's question and data into a new prompt; and the output is a personalized suggestion or solution for the user's question. The server saves the consultation record and returns the AI-generated answer to the terminal.

[0098] Step 9:

[0099] The terminal receives personalized suggestions from the server and proactively pops up an online appointment prompt, allowing users to select the desired professional and time slot. Input consists of the server-pushed suggestion text and appointment options; output includes user feedback (appointment confirmation) and the appointment request upload. In practice, when the user clicks "Book for 10 AM tomorrow" in the pop-up window, the terminal sends an appointment request to the server.

[0100] Step 10:

[0101] The server processes received appointment requests, automatically confirms appointments based on available time slots and resources, and notifies the terminal of the results. Input is the appointment request from the terminal, and output is appointment confirmation information and detailed process prompts returned to the terminal. The server records the appointment information in the database for subsequent synchronization between practitioners and users.

[0102] Application Example 1

[0103] The process flow corresponding to the specific processing in Use Case 1 will be described below. The various parts of the system described below are implemented by the data processing device 12 and the intelligent device 14. Furthermore, the data processing device 12 is referred to as the "server" and the intelligent device 14 is referred to as the "terminal".

[0104] Existing animal health management methods suffer from the following shortcomings: untimely data collection, lack of multi-dimensional comprehensive analysis, inability to accurately monitor animal health status, and difficulty for users to obtain personalized health advice and emotional support. Furthermore, the complex and asynchronous information processes for remote consultations and appointments at physical hospitals severely impact user experience. Therefore, there is an urgent need for an information processing system capable of efficiently and automatically collecting animal physiological data, intelligently analyzing and generating recommendations, adjusting the content of recommendations based on the user's emotional state, and simultaneously enabling remote medical appointments.

[0105] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is achieved by the following means.

[0106] In this invention, the server includes a data acquisition module for obtaining physiological activity data from a data acquisition device attached to the animal; a processing module for preprocessing the data by removing outliers and completing missing data; an analysis module for inputting the preprocessed data into a generative artificial intelligence model for health analysis and trend assessment; a suggestion generation module for automatically generating health management suggestions and emotional care content based on the analysis results; an emotion recognition and suggestion adjustment module for inferring the emotional state based on the user's voice or image information and adjusting the content; an appointment management module for receiving and processing user remote consultation and treatment appointment requests and synchronizing them to physical stores; and a report module for generating and displaying health reports. This enables real-time, multi-dimensional, and intelligent monitoring of animal health status and personalized suggestion pushes, improving user experience, simplifying remote and offline appointment processes, and improving overall management efficiency.

[0107] "Data information collection device" refers to an electronic device attached to an animal to continuously collect physiological parameters such as the animal's activity, sleep, and feeding.

[0108] "Physiological activity data" refers to data reflecting the physiological state of an animal during its life cycle, such as activity level, sleep duration, and food intake.

[0109] "Information processing device" refers to computer equipment or server that can receive, store, process physiological activity data, and perform data analysis and generation control.

[0110] "Preprocessing" refers to the process of cleaning raw physiological activity data by performing outlier filtering, missing data completion, and normalization.

[0111] "Generative artificial intelligence models" refer to artificial intelligence algorithms or models that can automatically generate analysis results, suggestions, or response information based on input data.

[0112] "Health status assessment" refers to the process of judging the current health status of an animal through data analysis.

[0113] "Abnormal trend analysis" refers to the analysis process that identifies potential health risks or abnormal trends based on historical and current data.

[0114] "Recommendation information" refers to specific recommendations based on health analysis output, used to guide animal health management and care.

[0115] A "communication terminal" refers to an electronic device that can communicate with an information processing device to receive and display data and suggestions and enable user interaction, such as a smartphone or tablet computer.

[0116] "Emotion recognition algorithm" refers to an artificial intelligence method that automatically infers a user's emotional state by analyzing the user's voice, image, text and other inputs.

[0117] "Emotional state" refers to the user's current emotions and psychological state inferred through emotion recognition algorithms.

[0118] "Remote consultation" refers to a service that allows users to communicate remotely with professionals without having to go to a physical location.

[0119] "Medical appointment" refers to the act of users selecting a time, place, and expert through the system to book offline or remote medical services in advance.

[0120] "Physical store information processing device" refers to a computer system or server installed in a medical institution or store to receive and manage appointment information.

[0121] A "health report" refers to a document or data content that is automatically generated based on physiological activity data over a certain period, and includes health analysis and trend summaries.

[0122] To illustrate the present invention in more detail, the following description combines the system structure, the use of each hardware and software component, the data processing method, the operation process, and practical examples.

[0123] The system of this invention includes: a server (information processing device), a terminal (such as a smartphone), and data collection devices (such as smart collars) worn by users and animals. The server performs comprehensive management functions such as data collection, preprocessing, intelligent analysis, suggestion generation, emotion recognition and suggestion feedback, and appointment scheduling through various functional modules. This invention can be implemented based on general-purpose hardware (such as server computers, mobile terminal devices, wearable devices, etc.) and common software tools (such as TensorFlow, PyTorch, Pandas, NumPy, OpenAI models, smartphone operating systems, etc.).

[0124] First, users need to fit their animals with a specific smart collar. This collar integrates components such as an accelerometer, heart rate sensor, and GPS module, enabling real-time collection of physiological data such as activity level, sleep duration, and feeding frequency. The terminal connects to the smart collar via Bluetooth or Wi-Fi, collects this data periodically, and temporarily stores the collected data locally. Users can view basic monitoring data at any time through the terminal application.

[0125] In a network environment, the terminal uploads the collected and processed physiological activity data to the server via encrypted communication (such as HTTPS). After receiving the data, the server first performs data preprocessing using Python data processing packages (such as pandas and numpy), including outlier removal, missing value completion (such as using mean interpolation, linear interpolation, and other algorithms), and data format standardization.

[0126] The preprocessed data from the server is then fed into a generative artificial intelligence model. This model, developed using open-source AI frameworks such as TensorFlow or PyTorch, is used to analyze animal activity, sleep, and feeding behaviors from multiple dimensions, detecting potential abnormalities and predicting trends in health. Based on the model's output, the server automatically generates diagnostic conclusions and provides health recommendations.

[0127] Users can submit descriptions of animal symptoms, health questions, or their own emotional states (such as anxiety or worry, input via voice or image) to the server through the terminal. The terminal application uses a speech recognition SDK, camera module, and other means to collect emotion-related data and upload it to the server. The server uses emotion recognition algorithms (such as BERT, proprietary emotion recognition models, etc.) to determine the user's emotional state and dynamically adjusts the language style of the suggested text accordingly. For example, when a user is anxious, the suggestion is adjusted to a gentler, more reassuring expression.

[0128] All results, suggestions, health reports, and analytical charts are pushed to and visually displayed to users through the terminal application, and support the generation of detailed health reports and trend visualizations on a daily / weekly basis for multiple periods. The server also supports users initiating remote consultation appointments through the terminal, and synchronizes appointment information with the physical hospital information system in real time via protocols such as WebSocket.

[0129] Specific examples are as follows:

[0130] For example, a user puts a smart collar on their dog, and the device periodically collects data showing that the dog is not getting enough rest at night and its activity level is significantly reduced. After the data is preprocessed by the server, it is input into a TensorFlow-based generative AI model. The model outputs that the dog has a health risk. The server automatically generates suggestions such as "Increase the dog's outdoor walk time, adjust its diet appropriately, and seek veterinary care promptly if symptoms persist" and pushes them to the device. If the user expresses anxiety or confusion through voice input, the server analyzes their emotional state and adds reassuring statements such as "Rest assured, we will continue to monitor your pet's health" when pushing suggestions.

[0131] Examples of input prompts for generative artificial intelligence models include:

[0132] "Please analyze the dog's current health status based on the following data and provide specific recommendations: Activity level = 1500 steps, Sleep duration = 10 hours, Food intake = 400 grams."

[0133] "The user stated: 'My dog ​​hasn't been moving much and has been eating less these past few days, and I'm a little worried.' Please provide the user with scientific and gentle care suggestions, and offer appropriate emotional support."

[0134] "Based on the dog's recent health data (activity level, sleep, diet) and the user's concerns, please use the model to analyze health risks and provide detailed care recommendations (such as increasing exercise, adjusting diet, and recommending veterinary care)."

[0135] Through this system, users can achieve 24 / 7 automated and multi-dimensional intelligent monitoring of animal health status, and obtain dynamic, personalized, and emotionally supportive health management advice. At the same time, services such as remote consultation and offline diagnosis and treatment can be completed in real time and conveniently.

[0136] use Figure 12 The processing flow is explained.

[0137] Step 1:

[0138] The terminal connects to the data collection device worn by the animal via Bluetooth or WiFi, and periodically collects physiological activity data such as the animal's activity level, sleep duration, and feeding frequency from sensors (such as accelerometer, heart rate sensor, and GPS module), and stores this data in a local database.

[0139] Input: Raw physiological activity data transmitted by the acquisition device.

[0140] Output: Physiological activity data packets stored locally on the terminal.

[0141] Specific actions: The terminal automatically initiates a data synchronization request every 5 minutes, reads sensor data via standard Bluetooth or WiFi protocol, and stores the data and timestamp together in a local SQLite database.

[0142] Step 2:

[0143] The timing of terminal monitoring data upload (such as scheduled, manually triggered by the user, or when an anomaly is detected) involves packaging locally stored physiological activity data and uploading it to the server via HTTPS encryption protocol.

[0144] Input: Terminal local physiological activity data packet.

[0145] Output: Physiological activity data file uploaded to the server.

[0146] Specific actions: After the terminal encapsulates, compresses, and anonymizes the data packet, it sends it to the server API interface via a POST request.

[0147] Step 3:

[0148] After receiving the data uploaded by the terminal, the server performs data preprocessing operations such as format parsing, validity checks, outlier screening, and missing value completion on the received physiological activity data.

[0149] Input: Raw physiological activity data uploaded by the terminal.

[0150] Output: Cleaned and normalized physiological activity data.

[0151] Specific actions: The server uses data processing libraries such as pandas and numpy to detect data anomalies, automatically fill in missing values ​​according to preset algorithms, and store the processing results in the database for archiving.

[0152] Step 4:

[0153] The server inputs the preprocessed physiological activity data into the generative artificial intelligence model to perform health risk assessment and abnormal behavior detection, generating preliminary health analysis results.

[0154] Input: Preprocessed physiological activity data.

[0155] Output: Animal health risk analysis conclusions and risk scores.

[0156] Specific actions: The server calls a deep learning model implemented in TensorFlow or PyTorch to extract features and recognize patterns from the input data, and outputs whether there is a health risk and quantifies the risk level.

[0157] Step 5:

[0158] Based on the health analysis results, the server automatically generates personalized health management suggestions and, combined with the emotional state data uploaded by the user, adjusts the content and style of the suggestion text (such as comforting and encouraging) using an emotion recognition algorithm.

[0159] Input: Health risk analysis conclusions, user emotional state data.

[0160] Output: Generated health advice information and analysis report.

[0161] Specific actions: The server uses NLP algorithms to automatically assemble health advice. If the user's emotion is anxiety, reassuring statements are automatically added. The analysis and advice are packaged into a report text.

[0162] Step 6:

[0163] The server sends the health analysis report and recommendations to the terminal via HTTPS. After receiving the data, the terminal displays the report, recommendations, and historical trend charts to the user through local push notifications and the application interface.

[0164] Input: Health analysis reports, recommendations, and visualizations sent by the server.

[0165] Output: New reports displayed on the terminal interface and real-time health advice pushed to users.

[0166] Specific actions: The terminal parses the report content, calls the visualization component to draw a trend chart, and prompts the user with new suggestions in a pop-up window or notification bar.

[0167] Step 7:

[0168] Users can input health questions or descriptions about the animal's condition (supporting text, voice, etc.) on the terminal application, and can also proactively upload their own emotional status. The terminal packages the input data and uploads it to the server.

[0169] Input: User's health problems, description of animal symptoms, and emotional expressions.

[0170] Output: Interactive data packets sent to the server.

[0171] Specific actions: The terminal calls upon functions such as voice recognition and text input to convert the content into data packets and upload them to the server via HTTPS.

[0172] Step 8:

[0173] The server receives user-input questions, symptoms, and emotional data, combines them with historical health data, and uses a generative artificial intelligence model to automatically generate targeted responses and further suggestions.

[0174] Inputs: Current user interaction data, historical physiological activity data, and user emotional state.

[0175] Output: Personalized response text and suggestions.

[0176] Specific actions: The server retrieves relevant historical health records, the model generates a response text, and the output is sent to the terminal.

[0177] Step 9:

[0178] After receiving the server's response, the terminal immediately pushes and displays it to the user in the form of a notification and a dialog box, and saves the interaction history for future reference.

[0179] Input: The personalized response text returned by the server.

[0180] Output: Intelligent question-and-answer records and suggestions displayed on the terminal page.

[0181] Specific actions: The terminal updates the interface, reminds the user that the question has been answered, and archives and manages the question and answer content.

[0182] Step 10:

[0183] Users can book in-person medical treatment or remote consultation services through the terminal. The terminal collects appointment information and synchronizes it to the server in real time. The server then synchronizes it with the physical store's information system in real time via WebSocket, and finally sends the appointment status back to the user.

[0184] Input: The user's appointment request (such as time, doctor, service type, etc.).

[0185] Output: Appointment confirmation information and status prompts.

[0186] Specific actions: The terminal synchronizes data with the server and physical store system, provides real-time feedback on the reservation results, and notifies the user whether the reservation was successful or failed.

[0187] Alternatively, an emotion engine for inferring user emotions can be combined. That is, the specific processing unit 290 can also use the emotion-specific model 59 to infer user emotions and perform specific processing using user emotions.

[0188] Example 2

[0189] The flow of a specific process in Example 2 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 as the "terminal."

[0190] Existing animal health management systems typically only collect and analyze animal behavioral data, physiological status, and dietary intake information, failing to consider the emotional state of the user (owner) for comprehensive judgment. This results in insufficient targeting and personalization of health advice. Furthermore, existing systems lack convenience and integration in areas such as online veterinary consultations and appointments, requiring users to switch between multiple platforms, reducing management efficiency and user experience. Therefore, there is an urgent need for a new animal health management system that can efficiently collect and integrate information, analyze it in real time considering the user's emotional state, and provide integrated health advice delivery and remote medical appointments.

[0191] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Embodiment 2 is achieved by the following means.

[0192] In this invention, the server includes a device for collecting action information, status information, and intake information from information acquisition devices installed on the organism, and a device for receiving user status information via a communication network. The server executes various modules, including data preprocessing (outlier removal and completion), anomaly detection and trend analysis based on a generative artificial intelligence model, user emotion recognition, and the generation and transmission of personalized health advice. This allows for the integration of animal health data and user emotional states, enabling intelligent adjustment of health advice, improving the personalization and effectiveness of recommendations. It also provides immediate feedback on user-inputted health questions and integrated remote consultation appointments, significantly enhancing the intelligence level of animal health management and user experience.

[0193] "Data information acquisition device" refers to an electronic device installed on a living organism to collect the organism's action information, status information, and intake information in real time.

[0194] "Motion information" refers to sensor data that reflects the amount of physical activity of an organism, including but not limited to steps, exercise intensity, and activity duration.

[0195] "Status information" refers to data related to the physiological or behavioral state of an organism, including but not limited to sleep patterns, rest duration, and body temperature changes.

[0196] "Intake information" refers to data on the food, water, and other nutrients ingested by an organism within a certain period of time.

[0197] "User status information" refers to data related to a user's emotional state, such as facial expressions, voice, and behavior, obtained through sensing devices (such as cameras and microphones).

[0198] "Information processing device" refers to a data processing device used to receive, process, analyze, and store all relevant information transmitted from terminals and data information acquisition devices.

[0199] "Data preprocessing" refers to the operations performed by information processing devices on raw data, such as cleaning, removing outliers, and filling in missing values, in order to facilitate subsequent analysis and processing.

[0200] "Generative artificial intelligence models" refer to intelligent algorithm modules that are based on machine learning or neural network algorithms and can automatically analyze input data, identify anomalies, predict trends, and generate text suggestions.

[0201] "Emotion recognition algorithm" refers to a data analysis algorithm that can automatically identify a user's emotional state (such as stress, anxiety, happiness, etc.) based on data such as facial expressions and voice features.

[0202] "Suggested information" refers to specific operational guidelines or behavioral suggestions generated by the system based on the organism's health status and the user's emotional state.

[0203] "Information terminal" refers to a user-side electronic device that can interact with information processing devices, display suggested information to users, and support health management and online appointment operations.

[0204] "Medical communication services" refers to digital communication platforms and services that provide users with opportunities to communicate, make appointments, and conduct remote consultations with medical professionals (such as veterinarians) via the internet for the purpose of remote health consultation.

[0205] This invention provides an animal health management system that can comprehensively acquire various physiological and behavioral data of animals and combine them with the emotional state of users (owners). Through generative artificial intelligence models, the system performs comprehensive analysis and generates suggestions, thereby achieving precise health management and remote medical services.

[0206] In an embodiment of the present invention, the system mainly includes a data information acquisition device, an information terminal, an information processing device, a generative artificial intelligence model, an emotion recognition algorithm, and a diagnosis and treatment communication service. Each part can be implemented by a separate hardware device or integrated into a mobile terminal and a server.

[0207] The server can utilize high-performance computing devices (such as general-purpose servers and high-performance GPU servers) and deploy a Python programming environment, using mainstream open-source tools such as Pandas, NumPy, TensorFlow, or PyTorch to perform data preprocessing and artificial intelligence model inference. Generative AI models can employ advanced neural network-based structures, such as Transformers, to support trend analysis and textual suggestion generation for large-scale time-series data. The information terminal can be a general-purpose smartphone or tablet, integrating Bluetooth, WiFi communication modules, a camera, a microphone, and an application (APP) for easy data collection, transmission, and display of suggested information.

[0208] Specifically, the terminal (such as a smartphone) synchronizes data with the sensing devices worn by the animal via Bluetooth or WiFi, periodically acquiring various raw data such as the animal's activity level, sleep, body temperature, and food intake. The terminal also uses a front-facing camera, microphone, or artificial intelligence recognition module to acquire and determine the user's emotional state, such as stress, anxiety, or happiness. All collected information is encrypted before being sent to the information processing device via the network.

[0209] After receiving the data uploaded by the terminal, the server first uses data preprocessing modules (such as Pandas and NumPy) to automatically filter outliers and complete missing data. The preprocessed data, along with the user's emotional state, is then input into a generative artificial intelligence model. Based on predefined rules and algorithms, the model can automatically identify anomalies and trend changes in animal health data, and, combined with the user's current emotions, automatically generate more realistic behavioral suggestions. For example, if the system detects that the animal's activity level is low and the user is under stress, it can suggest, "Appropriately increasing interaction and exercise with the animal can help regulate the psychological and health conditions of both parties."

[0210] The server also analyzes user status information using emotion recognition algorithms, automatically identifying the current emotional state and recording it in the user's health profile. All suggestions are sent through the server, and upon receiving them, the terminal displays them to the user in various ways, such as pop-ups, messages, and dedicated pages. Users can view the suggestions, health trends, and historical data changes on the app page and adjust their daily management behaviors based on the system's recommendations.

[0211] In addition, users can actively input problems or symptoms into the terminal, such as "animal coughing" or "reduced appetite," and send them to the server via the terminal. The server uses a generative artificial intelligence model to combine the animal's condition with the input information to generate targeted care suggestions and prompt whether a remote doctor appointment is needed. The terminal also supports online appointment booking, allowing users to choose a suitable time for a remote video consultation with a doctor based on system feedback. All relevant data will be verified and sent to the server before being fed back to the user.

[0212] Hardware examples include: information collection devices, such as wearable smart sensor collars and gaiters; information terminals, such as Android or Apple smartphones and tablets; and server-side computing facilities, such as cloud computing servers equipped with GPUs and enterprise-level data center servers.

[0213] Software examples include: data processing tools such as Python Pandas and NumPy; artificial intelligence frameworks such as TensorFlow and PyTorch; terminal applications such as health management apps (which can integrate acquisition modules such as cameras and microphones); emotion recognition modules such as OpenCV and third-party API services (such as general emotion recognition APIs); and secure communication modules such as SSL encrypted communication protocols.

[0214] Specific examples:

[0215] Suppose a user notices their dog's activity level has decreased. The terminal collects relevant behavioral and physiological data, along with the user's current facial expressions and voice. All data is uploaded to a server, where it undergoes preprocessing and AI model analysis to generate a suggestion to "increase exercise." If the server detects the user is anxious, it will also add information such as "spending time with animals and going out can help relieve stress." If the user actively inputs "the animal is coughing," the system automatically generates care suggestions such as "monitor the temperature; if symptoms persist, please schedule a remote appointment with a doctor," and guides the user through the online appointment process.

[0216] Here are some examples of prompts for generative artificial intelligence models:

[0217] Please analyze the following animal health data and provide health advice if any abnormalities are found.

[0218] When generating suggestions, please consider the user's current emotional state and adjust the suggestions to better reflect the user's psychology.

[0219] Please provide care suggestions for "animal cough" and prompt users to schedule a remote doctor appointment as needed.

[0220] Through the above-described embodiments, the system of the present invention can intelligently, comprehensively, and in real time manage animal health data, generate personalized suggestions based on the user's emotional state, and integrate proactive feedback and remote medical services, greatly improving the level of intelligence in health management and monitoring and the user experience.

[0221] use Figure 13 The processing flow is explained.

[0222] Step 1:

[0223] The terminal collects motion, status, and intake information from a data acquisition device worn by the animal via Bluetooth or WiFi, while simultaneously acquiring user facial expressions and voice data using a camera and microphone. Inputs include animal sensor data and user audio / video data; outputs include raw health data and preliminary emotional data. Specific terminal actions include periodically activating the sensor reading interface, starting the camera to capture facial images, and using the microphone to record audio, all of which are then packaged together.

[0224] Step 2:

[0225] The terminal locally encrypts the collected animal health data and user emotional data, and then uploads them to the server via WiFi or cellular network. The input is the packaged and encrypted health and emotional data, and the output is the data packet transmitted to the server. Specifically, the process involves invoking the information encryption algorithm, detecting the network communication status, performing the data upload operation, and recording the upload log.

[0226] Step 3:

[0227] After receiving data packets from the terminal, the server performs data preprocessing on the health and sentiment data. The inputs are raw health and sentiment data, and the output is cleaned, completed, and standardized data. Specific server actions include using tools such as Pandas to perform outlier removal, missing value imputation, and data normalization.

[0228] Step 4:

[0229] The server inputs preprocessed health data into a generative artificial intelligence model for anomaly detection, trend analysis, and health suggestion generation. The input is standardized health data, and the output is health status analysis results and preliminary suggestions. The server's specific actions include calling neural network algorithms for data feature extraction, trend modeling, and automatically generating natural language suggestion text.

[0230] Step 5:

[0231] The server uses emotion recognition algorithms to analyze user emotional input and identify the user's specific emotional state. The input consists of user facial expression images and voice data, and the output is a user emotion label. Specific actions include using a deep learning model to classify the voice and images for emotion and generate corresponding emotion tags.

[0232] Step 6:

[0233] The server personalizes health advice text based on health analysis results from a generative artificial intelligence model and user sentiment tags. The input consists of initial suggestions and sentiment tags; the output is customized advice information. Specifically, the process involves calling a natural language generation module to integrate the advice content with the emotional state, optimizing the wording of the advice.

[0234] Step 7:

[0235] The server will then push the final customized recommendations and health analysis results to the terminal device via a secure protocol. The input is the generated recommendations and analysis results, and the output is the recommendation information sent to the terminal. Specific actions include calling the push notification API and generating push logs to ensure secure data delivery to the terminal.

[0236] Step 8:

[0237] The terminal receives analysis and suggestions pushed by the server and notifies the user through app message pop-ups and data display interfaces. The input is the notification and suggestion content sent by the server, and the output is the information displayed in the app interface and notification bar. Terminal actions include popping up system notifications, refreshing the health report page, and rendering detailed suggestions within the application.

[0238] Step 9:

[0239] Users can adjust their animal management practices based on suggestions or submit questions and symptom descriptions (such as "animal coughing") via the app. Input consists of the user's symptom description or health problem text, and output is the consultation text to be analyzed. The user's action is to fill out a form and submit it on the app's consultation interface.

[0240] Step 10:

[0241] The terminal encrypts the user's input consultation text and uploads it to the server. The server uses a generative artificial intelligence model to analyze the user's questions and generate targeted care suggestions, as well as remote consultation suggestions if necessary. The input includes the user's consultation text and health history, and the output includes care suggestions and remote treatment prompts. Server actions include natural language parsing, AI text generation, and automatically determining whether to recommend scheduling a remote doctor.

[0242] Step 11:

[0243] After receiving nursing suggestions and remote consultation prompts, the terminal displays an appointment interface for the user to select a doctor and time, and uploads an appointment request. The user inputs the appointment request information, and the terminal outputs the appointment data submitted to the server. Terminal actions include invoking the calendar component, collecting user selections, and encrypting and uploading the appointment content.

[0244] Step 12:

[0245] The server processes appointment requests, confirms them based on doctor resources and schedules, and displays the appointment result to the terminal via message notification. The input is the user's appointment data, and the output is a confirmation appointment notification. Specifically, the server connects to the doctor's system, writes the data to the appointment database, and pushes the result to the terminal.

[0246] Application Example 2

[0247] The process flow corresponding to the specific processing in Use Case 2 will be described below. The various parts of the system described below are implemented by the data processing device 12 and the intelligent device 14. In addition, the data processing device 12 is referred to as the "server" and the intelligent device 14 is referred to as the "terminal".

[0248] The specific processing performed by the specific processing unit 290 of the data processing apparatus 12 in Application Example 2 is achieved by the following means.

[0249] In this invention, the server includes: a device for preprocessing animal physiological activity information and user input information; a device for automatically acquiring user audio or image information and inferring user emotional state through an emotion analysis device; a device for combining the preprocessed physiological data and emotional state information and inputting it into a generative artificial intelligence model to generate analysis conclusions and personalized suggestions; a device for outputting suggestions to the user terminal and adjusting the expression of suggestions according to the user's emotions; and a device for receiving user health consultation input and making remote appointments with medical professionals. This enables multi-dimensional fusion analysis of animal health data and user emotional state, improves the targeting and humanization of suggestions, simplifies the remote medical consultation process, and greatly improves user experience and the level of intelligence in animal health management.

[0250] "Physiological activity information" refers to animal physiological data obtained through information collection devices such as sensors, including but not limited to activity level, sleep status, and food intake.

[0251] "Information processing device" refers to computing equipment capable of processing, storing and analyzing collected data, including servers, cloud platforms or other devices with data analysis and processing capabilities.

[0252] "User input information" refers to proactive data input by users through a terminal, such as health inquiries, symptom descriptions, and feedback information.

[0253] "Preprocessing" refers to a series of data cleaning and correction operations performed on the raw data before analysis, such as outlier screening, missing data completion, and format standardization.

[0254] "Generative artificial intelligence models" refer to artificial intelligence algorithm systems that are built by learning from a large amount of data and can automatically generate text information or analytical conclusions based on input data.

[0255] "User emotional information" refers to data inferred from users' current emotional state through the collection of audio, images, and other means, including representations of psychological states such as pleasure, stress, and anxiety.

[0256] "Suggested information" refers to personalized suggestions, operation prompts, health reminders, and other content automatically generated by the system based on the animal's health status and the user's current emotional state.

[0257] "Medical professionals" refers to a group of doctors, nurses, and other personnel who possess animal medical-related professional qualifications and can provide users with medical advice and online consultations.

[0258] "Remote consultation and appointment" refers to the function of users submitting appointment requests online through this system and engaging in interactive services such as appointment dialogues and video consultations with medical professionals via the network.

[0259] "Prompt statements" refer to instructional texts that are automatically constructed by the system before input into the generative artificial intelligence model, integrating various data information and set requirements.

[0260] In this embodiment of the invention, the system mainly includes hardware devices such as an information collection device, a terminal, an information processing device (server), and a display device. The information collection device is typically a wearable device worn on the animal, capable of automatically collecting physiological activity information such as activity level, sleep status, and food intake. The terminal can be a smartphone, tablet, or other commonly used mobile computing device, capable of communicating with the information collection device and transmitting data with the server. The information processing device is a computing device with high-performance data processing and storage capabilities, generally a cloud server or a local server.

[0261] The terminal connects to the information collection device via Bluetooth or WiFi, periodically acquiring and locally recording animal health data. Simultaneously, the terminal utilizes its built-in microphone and camera to automatically or with user authorization collect audio and video data during user interaction. To ensure the accuracy of emotion recognition, the system can also integrate third-party emotion analysis APIs (such as general speech recognition and facial expression recognition modules). The terminal performs preliminary legality verification on the collected data and then encrypts and uploads it to a cloud server via the internet.

[0262] The server, as the core processing unit, first utilizes data analysis libraries such as Python and Pandas to preprocess the received animal physiological activity information and user input, including outlier identification, screening, missing data completion, data normalization, and structured storage. The server integrates generative artificial intelligence models (e.g., mainstream large-scale language model APIs) with contextual prompts to integrate health data with user emotional data for further personalized analysis and suggestion generation. The server also integrates sentiment analysis tools to run analysis algorithms on uploaded audio, video, and other data to determine the user's current emotional state; common components include general audio analysis services or image analysis platforms. After synthesizing various information, the server automatically generates personalized suggestions and next-step instructions based on preset logic.

[0263] After generating the suggested information, the server pushes it to the terminal display device. The terminal presents the suggested content to the user in real time in a user-friendly format, such as text and charts, through in-app notifications, message bar reminders, or a dedicated display area on the main interface. Users can also independently input animal health-related consultation content, symptom descriptions, etc., on the terminal. The terminal is responsible for collecting and uploading this input, and the server uses this information to call a generative artificial intelligence model to generate targeted response suggestions by combining existing health data, emotional data, and consultation content, and then displays them to the user through the terminal. If users have deeper needs, they can access the remote medical consultation appointment page with one click, where the system automatically assigns medical professionals and completes the appointment process.

[0264] As an application example, suppose the terminal detects a sharp decline in the animal's recent activity level, and the user's facial expression analysis indicates anxiety. The server, using a generative artificial intelligence model, integrates this information and automatically generates the following suggestion: "A significant decrease in the animal's activity level has been detected recently, and your emotional state indicates anxiety. It is recommended to spend more time with the animal and increase outdoor activities appropriately. If the situation persists, please consider remotely scheduling a consultation with a medical professional." If the user spontaneously enters "What should I do if my animal has a persistent cough?", the system automatically analyzes and replies: "If the cough persists for a long time, it is recommended to schedule a professional medical consultation promptly. If necessary, relevant video footage can be taken to assist in diagnosis."

[0265] A typical example of a prompt statement is as follows:

[0266] Please combine recently obtained animal health data with user sentiment data to provide personalized recommendations for animal health management.

[0267] Please analyze the owner's current emotional state based on audio and facial expression data, and generate pet care suggestions that match the owner's psychological state.

[0268] The animal's activity level and sleep data show significant abnormalities. Please analyze the cause and generate treatment suggestions for the owner.

[0269] User inquiry: Animals are showing signs of decreased appetite. Please generate professional health advice based on all available data.

[0270] Through the above methods, the present invention can achieve efficient fusion analysis of animal physiological data and user emotional state, improve the accuracy of animal health management and the level of service humanization, and effectively reduce the technical threshold for users to consult remotely.

[0271] use Figure 14 The processing flow is explained.

[0272] Step 1:

[0273] The terminal establishes a communication connection with the information collection device worn by the animal via Bluetooth or WiFi, automatically collecting the animal's physiological activity information at regular intervals, including activity level, sleep status, and food intake. The input is the raw physiological data stored in the information collection device, and the output is locally cached and formatted health data. The terminal detects the time point of data collection and the validity of each data point, marking invalid or missing items and preparing for uploading.

[0274] Step 2:

[0275] The terminal uses its built-in camera and microphone to simultaneously collect the user's audio and facial image data during application launch or user operation. The input is the user's current voice and image, and the output is locally cached audio and image files. The terminal performs preliminary validity checks on the audio and video files (such as image brightness, successful face detection, and appropriate audio length), saving the passed data to a designated directory for later uploading.

[0276] Step 3:

[0277] The terminal packages the aforementioned health data and emotion-related audio / video data into a standardized data packet, and uploads it to the server via HTTPS encryption. The input is locally cached health and emotion data, and the output is a successfully sent upload request. The terminal performs a data integrity check before uploading, records the upload log, and automatically retryes when encountering network errors.

[0278] Step 4:

[0279] After receiving data from the terminal, the server first uses data processing software (such as Python, Pandas, etc.) to perform preprocessing operations on the health data and user input information, including outlier filtering, missing data imputation, and data normalization. The input consists of the raw health data uploaded by the terminal and user input; the output is the preprocessed structured data. The server determines the data type to be processed based on data characteristics and uses appropriate algorithms to correct the data.

[0280] Step 5:

[0281] The server invokes a sentiment analysis tool to perform sentiment recognition on audio and image data, extracting the user's emotional characteristics, such as anxiety, stress, or pleasure. The input consists of the user's audio and image files, and the output is a structured label representing the user's emotional state. The server determines the validity of the sentiment analysis results and saves them in association with health data.

[0282] Step 6:

[0283] The server integrates preprocessed health data and sentiment status tags to generate prompts which are then input into a generative AI model (such as a large-scale language generation model). Based on the prompts and data, the server performs health trend analysis, anomaly detection, and automatically generates personalized suggestions. The input consists of health data, sentiment tags, and corresponding prompts; the output is suggested text. The server automatically adjusts the wording and style of the suggestions based on user characteristics and current sentiment.

[0284] Step 7:

[0285] The server will send the generated suggestions, health analysis reports, and personalized notifications to the user's device via push notifications. The input is the newly generated suggestion text, and the output is the message content pushed to the device. After receiving the push notification, the device will automatically remind the user through application notifications, pop-ups, etc., and display detailed suggestions on the app interface for the user to view and implement.

[0286] Step 8:

[0287] Based on the analysis results and suggestions displayed on the terminal, users actively input their consultation content or symptom descriptions, such as specific symptoms or questions. Input can be natural language text or supplementary materials such as images and audio; output is a complete consultation request. The terminal integrates the user input data and sends it to the server.

[0288] Step 9:

[0289] After receiving a user's inquiry, the server automatically constructs detailed prompts based on current health data and emotional state. The input is then used to generate a professional response suggestion from a generative AI model. The input includes the user's inquiry content and recent health and emotional data; the output is the automatically generated suggested answer text. The server can also guide the user to a remote medical consultation or appointment interface as needed.

[0290] Step 10:

[0291] Based on the professional advice and remote appointment information returned by the server, the terminal displays new suggestions and appointment details to the user, who can then click to confirm the appointment. The input is the server-pushed suggestions and appointment content, and the output is text information, buttons, and other interactive elements displayed on the terminal interface. After user confirmation, the terminal sends the confirmation result back to the server, completing the closed loop of the remote medical service process.

[0292] The specific processing unit 290 sends 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 sound representing user input regarding the result of the specific processing. The control unit 46A sends the sound data representing 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 sound data.

[0293] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be partially or entirely performed by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0294] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or external devices, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or external devices.

[0295] For example, the collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the smart device 14 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0296] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the smart device 14.

[0297] Second Implementation Method

[0298] Figure 3 An example of the configuration of the data processing system 210 according to the second embodiment is shown.

[0299] like Figure 3 As shown, the data processing system 210 includes a data processing device 12 and smart glasses 214. A server can be cited as an example of the data processing device 12.

[0300] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, 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).

[0301] 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, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and communication I / F 44 are also connected to the bus 52.

[0302] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0303] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, to capture images of the user 20's surroundings (e.g., the field of view defined by an angle equivalent to the field of vision of an average healthy person).

[0304] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0305] Figure 4 This illustrates an example of the main functions of the data processing device 12 and the smart glasses 214. For example... Figure 4 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0306] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0307] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. In the emotion inference function (emotion-specific function) using the emotion-specific model 59, various inferences and predictions related to the user's emotions are performed, including inferences and predictions of the user's emotions, but this is not limited to this example. Furthermore, emotion inference and prediction may also include, for example, emotion analysis (parsing).

[0308] In the smart glasses 214, the processor 46 performs reception and output processing. The memory 50 stores the reception and output program 60. The processor 46 reads the reception and output program 60 from the memory 50 and executes the read reception and output program 60 on the RAM 48. The reception and output processing is implemented by the processor 46 operating as a control unit 46A according to the reception and output program 60 executed on the RAM 48. Furthermore, the smart glasses 214 has the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and these models can also be used to perform the same processing as the specific processing unit 290.

[0309] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the smart glasses 214. 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".

[0310] Example 1

[0311] The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0312] Application Example 1

[0313] The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0314] Example 2

[0315] The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0316] Application Example 2

[0317] The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0318] The specific processing unit 290 sends the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A outputs the result of the specific processing to the speaker 240. The microphone 238 acquires sound input representing the user's input regarding the result of the specific processing. The control unit 46A sends the sound data representing the user's 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 sound data.

[0319] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be partially or entirely performed by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0320] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or external devices, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or external devices.

[0321] For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the smart glasses 214 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0322] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the smart glasses 214.

[0323] Third Implementation Method

[0324] Figure 5 An example of the configuration of the data processing system 310 according to the third embodiment is shown.

[0325] like Figure 5 As shown, the data processing system 310 includes a data processing device 12 and a head-mounted terminal 314. A server can be cited as an example of the data processing device 12.

[0326] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, 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).

[0327] The head-mounted 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, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, display 343, and communication I / F 44 are also connected to the bus 52.

[0328] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0329] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, to capture images of the user 20's surroundings (e.g., the field of view defined by an angle equivalent to the field of vision of an average healthy person).

[0330] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0331] Figure 6 This illustrates an example of the main functions of the data processing device 12 and the head-mounted terminal 314. For example... Figure 6 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0332] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0333] The memory 32 stores the data generation model 58 and the emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290.

[0334] In the head-mounted terminal 314, the processor 46 performs the acceptance / output processing. The memory 50 stores the acceptance / output program 60. The processor 46 reads the acceptance / output program 60 from the memory 50 and executes the read acceptance / output program 60 on the RAM 48. The acceptance / output processing is implemented by the processor 46 operating as a control unit 46A according to the acceptance / output program 60 executed on the RAM 48.

[0335] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the head-mounted terminal 314. In the following description, the data processing device 12 will be referred to as the "server" and the head-mounted terminal 314 will be referred to as the "terminal".

[0336] Example 1

[0337] The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0338] Application Example 1

[0339] The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0340] Example 2

[0341] The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0342] Application Example 2

[0343] The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0344] The specific processing unit 290 sends the result of the specific processing to the head-mounted terminal 314. In the head-mounted terminal 314, the control unit 46A outputs the result of the specific processing to the speaker 240 and the display 343. The microphone 238 acquires sound input representing the user's input regarding the result of the specific processing. The control unit 46A sends the sound data representing the user's 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 sound data.

[0345] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be partially or entirely performed by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0346] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the head-mounted terminal 314, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the head-mounted terminal 314. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the head-mounted terminal 314 or external devices, and the head-mounted terminal 314 acquires or collects information required for processing from the data processing device 12 or external devices.

[0347] For example, the collection unit is implemented by the control unit 46A of the head-mounted terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the head-mounted terminal 314 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 to analyze the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 to generate a menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the head-mounted terminal 314 or the specific processing unit 290 of the data processing device 12 to provide the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0348] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the head-mounted terminal 314.

[0349] Fourth Implementation Method

[0350] Figure 7 An example of the configuration of the data processing system 410 according to the fourth embodiment is shown.

[0351] like Figure 7 As shown, the data processing system 410 includes a data processing device 12 and a robot 414. A server can be cited as an example of the data processing device 12.

[0352] The data processing apparatus 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" as understood in this disclosure. The computer 22 includes a processor 28, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, 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).

[0353] Robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, controlled object 443, and communication I / F 44 are also connected to the bus 52.

[0354] Microphone 238 receives instructions from user 20 by receiving sounds emitted by user 20. Microphone 238 captures sounds emitted by user 20 and converts the captured sounds into sound data, which is then output to processor 46. Speaker 240 outputs sound according to instructions from processor 46.

[0355] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and imaging elements such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, to photograph the area around robot 414 (e.g., the field of view defined by a perspective equivalent to the field of vision of an average healthy person).

[0356] Communication I / F44 is connected to network 54. Communication I / F44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F44 and 26 is performed in a secure state.

[0357] The controlled object 443 includes a display device, LEDs (light-emitting diodes) for the eyes, and motors for driving the arms, hands, and feet. The posture or movement of the robot 414 is controlled by controlling the motors in the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. In addition, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0358] Figure 8 This illustrates an example of the main functions of the data processing device 12 and the robot 414. For example... Figure 8 As shown, in the data processing device 12, specific processing is performed by the processor 28. The specific processing program 56 is stored in the memory 32.

[0359] The specific processing program 56 is an example of a "program" involved in the technology of this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0360] The memory 32 stores the data generation model 58 and the emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290.

[0361] In robot 414, the processor 46 performs the acceptance and output processing. The memory 50 stores the acceptance and output program 60. The processor 46 reads the acceptance and output program 60 from the memory 50 and executes the read acceptance and output program 60 on RAM 48. The acceptance and output processing is implemented by the processor 46 acting as the control unit 46A according to the acceptance and output program 60 executed on RAM 48.

[0362] Next, the specific processing of the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 will be referred to as the "terminal".

[0363] Example 1

[0364] The process is the same as that of the specific process described in Embodiment 1 in the first embodiment above, so the description is omitted.

[0365] Application Example 1

[0366] The process is the same as that in the specific processing described in Application Example 1 of the first embodiment above, so the description is omitted.

[0367] Example 2

[0368] The process is the same as that of the specific process in Embodiment 2 described in the first embodiment above, so the description is omitted.

[0369] Application Example 2

[0370] The process is the same as that in the specific processing described in Application Example 2 of the first embodiment above, so the description is omitted.

[0371] The specific processing unit 290 sends the result of the specific processing to the robot 414. In the robot 414, the control unit 46A outputs the result of the specific processing to the speaker 240 and the controlled object 443. The microphone 238 acquires sound input representing the result of the specific processing. The control unit 46A sends the sound data representing 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 sound data.

[0372] Data generation model 58 is a so-called generative AI (Artificial Intelligence). Examples of data generation models 58 include ChatGPT (registered trademark) (accessible via the internet (URL: https: / / openai.com / blog / chatgpt)). Data generation model 58 is obtained through deep learning on a neural network. Input to data generation model 58 are prompt words containing instructions, and inference data such as sound data representing sound, text data representing text, and image data representing images (e.g., still image data or animation data). Data generation model 58 infers from the input inference data based on the instructions represented by the prompt words and outputs the inference result in one or more data forms, such as sound data, text data, and image data. Data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or induction. The specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. The data generation model 58 can also be a model finely tuned to output inference results from prompts that do not contain instructions. In this case, the data generation model 58 can output inference results based on prompts that do not contain instructions. The data processing apparatus 12, etc., includes various data generation models 58, including AI other than the generation AI. AI other than the generation AI can be, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or Naive Bayes, and can perform various processes, but is not limited to this example. Furthermore, the AI ​​can also be an AI agent. Furthermore, when the processing of the above-mentioned parts is performed by AI, the processing can be partially or entirely performed by AI, but is not limited to this example. Furthermore, the processing performed by the AI ​​including the generation AI can be replaced by processing in the rule base, and the processing in the rule base can also be replaced by processing performed by the AI ​​including the generation AI.

[0373] Furthermore, the processing of the aforementioned data processing system 10 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it can also be performed by both the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or external devices, and the robot 414 acquires or collects information required for processing from the data processing device 12 or external devices.

[0374] For example, the collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit uses the camera 42 or communication I / F 44 of the robot 414 to acquire step data, which is then processed by the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes the data from the collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12, which uses a generation AI to generate a menu. For example, the serving unit is implemented by the speaker 240 of the robot 414 and the control object 443 or the specific processing unit 290 of the data processing device 12, which provides the generated menu to the user. The correspondence between each unit and the device or control unit is not limited to the above examples and various changes can be made.

[0375] In the above embodiments, examples of specific processing by the data processing device 12 are given, but the technology disclosed herein is not limited to this, and specific processing may also be performed by the robot 414.

[0376] Furthermore, the emotion-specific model 59, acting as an emotion engine, can determine a user's emotion based on a specific mapping. Specifically, the emotion-specific model 59 can determine a user's emotion based on an emotion graph that serves as a specific mapping (see [reference]). Figure 9 The system determines the user's emotions. Furthermore, the emotion-specific model 59 can similarly determine the robot's emotions, and the specific processing unit 290 performs specific processing based on the robot's emotions.

[0377] Figure 9 This is a diagram representing an emotion map 400 that maps multiple emotions. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotion is. On the outer side of the concentric circles, emotions representing states or behaviors arising from mood are arranged. Emotions are concepts that include feelings and mental states. Emotions generated by reactions occurring in the brain are arranged roughly to the left of the concentric circles. Emotions derived from situational judgments are arranged roughly to the right of the concentric circles. Emotions generated by reactions occurring in the brain and derived from situational judgments are arranged roughly above and below the concentric circles. Furthermore, "pleasant" emotions are arranged above the concentric circles, and "unpleasant" emotions are arranged below them. Thus, in the emotion map 400, multiple emotions are mapped based on the structure that generates emotions, and emotions that are likely to occur simultaneously are mapped close to each other.

[0378] These emotions are distributed at the three o'clock position of the emotion map 400, typically fluctuating between peace and anxiety. In the right half of the emotion map 400, situational awareness dominates over internal sensation, thus resulting in an impression of calm.

[0379] The inner side of the emotion map 400 represents the inner state, while the outer side represents behavior. Therefore, the further outward you are from the emotion map 400, the more visible the emotion becomes (manifested in behavior).

[0380] Here, human emotions are based on various balances such as posture and blood sugar levels. When these balances deviate from an ideal state, it indicates an unpleasant state; when they approach the ideal state, it indicates a pleasant state. Emotions in robots, cars, motorcycles, etc., can also be created in the following way: based on various balances such as posture and remaining battery power, when these balances deviate from an ideal state, it indicates an unpleasant state; when they approach the ideal state, it indicates a pleasant state. Emotion maps can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a Brain Physiological Signal Analysis System for Voice Emotion Recognition and Emotion, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). In the left half of the emotion map, emotions belonging to the sensory-dominated region, called "response," are arranged. Furthermore, in the right half of the emotion map, emotions belonging to the situational cognition-dominated region, called "situation," are arranged.

[0381] In the emotion map, two types of emotions that promote learning are defined. One is a negative emotion on the situational side, in the middle or peripheral region of "repentance" or "reflection." This occurs when the robot experiences negative emotions such as "I don't want to experience this feeling again" or "I don't want to be blamed again." The other is a positive emotion on the response side, near the "desire" region. This occurs when there are positive feelings such as "wanting more" or "wanting to know more."

[0382] The emotion-specific model 59 inputs user input into a pre-trained neural network to obtain emotion values ​​representing each emotion shown in the emotion map 400, thereby determining the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network... Figure 10 As shown in the sentiment graph 900, it was trained in a way that sentiments that are configured close to each other have similar values. Figure 10 The text shows examples of emotions such as "peace of mind", "stability", and "reassurance" that have similar emotion values.

[0383] The above description focuses on the functions of the data processing device 12, but the system of this disclosure is not necessarily installed on a server. The system of this disclosure can also be installed as a general information processing system. This disclosure can also be installed, for example, as a software program running on a personal computer, an application running on a smartphone, etc. The method of this disclosure can also be provided to users in the form of SaaS (Software as a Service).

[0384] In the above embodiments, an example of a specific process being performed by a single computer 22 is given. However, the technology disclosed herein is not limited to this, and the specific process can also be distributed among multiple computers, including computer 22. For example, the data generation model 58 can be located on an external device of the data processing apparatus 12, where data is generated based on the input data.

[0385] In the above embodiments, examples of storing a specific processing program 56 in the memory 32 have been described, but the technology disclosed herein is not limited thereto. For example, the specific processing program 56 may also 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 into the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0386] Alternatively, a specific processing program 56 may be pre-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 according to the requirements of the data processing device 12.

[0387] In addition, it is not necessary to store all the specific processing program 56 in the storage device such as the server connected to the data processing device 12 via the network 54 or in the memory 32; a portion of the specific processing program 56 may be stored in advance.

[0388] As hardware resources for performing specific processes, various processors, as shown below, can be used. For example, a CPU can be listed as a processor, which functions as a general-purpose processor that performs specific processes by executing software, i.e., a program. Furthermore, processors can be listed as special-purpose circuits such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application-Specific Integrated Circuits), which are processors with circuitry specifically designed to perform specific processes. Each processor has built-in or connected memory, and each processor executes specific processes using that memory.

[0389] The hardware resources for performing a specific process can consist of one of these various processors, or a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resources for performing a specific process can be a single processor.

[0390] As an example of a single processor, there are two approaches: First, a processor is composed of a combination of one or more CPUs and software, which functions as a hardware resource to perform a specific process; second, as represented by a SoC (System-on-a-chip), a processor is used to implement the functionality of the entire system, which includes multiple hardware resources for performing a specific process, using a single IC (Integrated Circuit) chip. In this way, the specific process is implemented by using one or more of the aforementioned processors as hardware resources.

[0391] Furthermore, the hardware architecture of these various processors, more specifically, can utilize circuits that combine semiconductor elements and other circuit components. Moreover, the specific process described above is just one example. Therefore, without departing from the main point, unnecessary steps can certainly be deleted, new steps added, or the processing order changed.

[0392] The descriptions and illustrations above are detailed explanations of a portion of the technology disclosed herein, and are merely one example of the technology disclosed herein. For example, the above descriptions of the structure, function, effect, and results are just one example of the structure, function, effect, and results of a portion of the technology disclosed herein. Therefore, without departing from the spirit of the technology disclosed herein, unnecessary parts may be deleted, new elements added, or replacements may be made to the descriptions and illustrations above. Furthermore, to avoid confusion and facilitate understanding of a portion of the technology disclosed herein, explanations of common technical knowledge that do not require special explanation under the premise of being able to implement the technology disclosed herein have been omitted from the descriptions and illustrations above.

[0393] All documents, patent applications and technical specifications set forth in this specification are incorporated herein by reference to the same extent that each document, patent application and technical specification is specifically and individually described therein and referenced by reference.

[0394] In addition, the following notes are provided in response to the above explanation.

[0395] Example 1

[0396] (Note 1)

[0397] An information processing system includes: a device for acquiring biological data from an information acquisition device worn by an animal; a device for sending the acquired biological data to an information processing device; a device for enabling the information processing device to perform preprocessing on the biological data, such as outlier filtering and missing value completion; a device for inputting the preprocessed data into a generative artificial intelligence model and parsing it; a device for sending the parsing result to a terminal device and notifying a user; a device for receiving user input information and inputting the input information and biological data into the generative artificial intelligence model to generate suggestion information; a device for sending the generated suggestion information to the terminal device and prompting the user; a device for providing the user with a reservation function for scheduling communication with professionals; a device for automatically generating prompt statements as input to the generative artificial intelligence model by the terminal device; a device for the information processing device to manage historical information of parsing processing or suggestion generation processing based on data received from the terminal device or user input information; and a device for the terminal device to notify the user of the parsing result or suggestion information via push notification.

[0398] (Note 2)

[0399] According to the information processing system described in Note 1, the generative artificial intelligence model also includes the function of identifying trends in animal health status based on time-series data analysis and providing preventative advice to users based on the analysis results.

[0400] (Note 3)

[0401] According to the information processing system described in Appendix 1, the terminal device further includes the function of receiving condition settings such as changes in biological data collection intervals or reservation information through a user interface, and reflecting such information to the information processing device.

[0402] Application Example 1

[0403] (Note 1)

[0404] An information processing system includes: a device for acquiring physiological activity data from a data acquisition device attached to an animal; a device for sending the acquired physiological activity data to an information processing device; a device for preprocessing the physiological activity data by the information processing device, such as outlier removal and missing value completion; a device for the information processing device to input the preprocessed data into a generative artificial intelligence model and perform health status determination and abnormal trend analysis; a device for the information processing device to generate health management suggestions based on the analysis results and send them to a communication terminal; a device for the communication terminal to receive and notify and display the analysis results and suggestions to the user; a device for receiving user-inputted questions or physiological symptom information and generating response information using a generative artificial intelligence model; a device for collecting user emotion inference data through the communication terminal, and for the information processing device to infer the user's emotional state based on an emotion recognition algorithm and adjust the suggestions based on the emotional state; a device for providing users with an online appointment function for remote consultation or medical treatment, and synchronizing the appointment information with the physical store's information processing device in real time; and a device for the information processing device to generate health reports divided by time periods based on the physiological activity data and display them on the communication terminal.

[0405] (Note 2)

[0406] According to the information processing system described in Appendix 1, the information processing device infers the user's emotional state based on voice or image information obtained from the user, and adjusts the content or expression of the suggested information output by the generative artificial intelligence model based on the inference result.

[0407] (Note 3)

[0408] According to the information processing system described in Appendix 1, the information processing device combines user inquiries, physiological symptom information, physiological activity data, and inferred user emotional state received from the communication terminal to generate personalized response information using a generative artificial intelligence model.

[0409] Example 2

[0410] (Note 1)

[0411] An information processing system includes: a device for collecting action information, status information, and intake information from a data acquisition device installed on a living organism; a device for sending the collected information and user status information to an information processing device; a device for performing data preprocessing, including outlier removal and completion, on the collected information and user status information in the information processing device; a device for inputting the preprocessed information into a generative artificial intelligence model and performing analysis, anomaly judgment, and time-series trend analysis based on the action information, status information, and intake information; a device for analyzing user status information and determining user emotional state using an emotion recognition algorithm; a device for generating personalized suggestion information based on the analysis results of the generative artificial intelligence model and user emotional state; a device for sending the generated suggestion information to an information terminal for notification and display; a device for generating suggestion information using a generative artificial intelligence model based on user input information and symptom information; and a device for realizing remote consultation and appointment using a diagnostic communication service.

[0412] (Note 2)

[0413] According to the information processing system described in Appendix 1, the information processing device performs data preprocessing, including outlier removal and missing value completion.

[0414] (Note 3)

[0415] According to the information processing system described in Appendix 1, the information processing device uses a generative artificial intelligence model to perform anomaly determination and time series trend analysis on action information, state information, and intake information.

[0416] Application Example 2

[0417] (Note 1)

[0418] An information processing system includes: means for acquiring physiological activity information from a physiological information acquisition device worn on an animal; means for sending the physiological activity information to an information processing device; means for enabling the information processing device to preprocess the physiological activity information and user input information, including outlier screening and missing data completion; means for enabling the information processing device to input the preprocessed data and user status information into a generative artificial intelligence model to generate health status analysis and suggestion information; means for enabling the information processing device to collect and analyze user emotional information; means for adjusting the content and expression of suggestion information according to the user's emotional state; means for sending the generated suggestion information to a display device and presenting it to the user; means for receiving user queries or symptom information input regarding health status; means for generating suggestion information based on the query or symptom information using a generative artificial intelligence model; and means for providing remote consultation appointments with medical professionals.

[0419] (Note 2)

[0420] According to the information processing system described in Appendix 1, the information processing device infers the user's emotional state based on the user's audio or image information through an emotion analysis device and reflects it in the suggestion information generation process.

[0421] (Note 3)

[0422] According to the information processing system described in Appendix 1, the suggestion information generation process combines physiological activity information, user input information, and user emotional state information to automatically generate prompt statements and input them into the generative artificial intelligence model.

Claims

1. An information processing system, characterized in that, include: A device used to collect data on activity levels, sleep patterns, and food intake from an information collection device worn on a dog; A device for sending collected data to a parsing server; A device for parsing data collected by a server and inputting it into a generative artificial intelligence model; A device for sending the parsed results to a terminal and notifying the user; A device for receiving input from users about problems and canine symptoms and generating suggestions through a generative artificial intelligence model; A device for sending the generated suggestions to a terminal and displaying them to the user; and A device for providing online veterinary consultation and appointment services.

2. The information processing system according to claim 1, characterized in that, The parsing server further includes devices for preprocessing data, filtering outliers, and completing missing data.

3. The information processing system according to claim 1, characterized in that, The parsing server further includes a device for identifying outliers in activity levels, sleep patterns, and food intake data using a generative artificial intelligence model.

Images