system

Abstract

A system is provided.SOLUTION: The system according to claim 1, further comprising: means for transmitting the analysis result to a user device and providing the analysis result to a user through an interface; and means having a GPS function for acquiring location information of the pet and displaying the location information to the user, wherein the means for transmitting the analysis result to the user device and providing the analysis result to the user through the interface comprises: means for receiving the biometric information of the pet from the pet device; and means for performing preprocessing on the biometric information of the pet. AI.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Understanding pets' health and emotions in real time and taking appropriate action is a difficult challenge, especially for dual-income households and owners who are often away from home. Furthermore, when people return from working from home to working in the office or hybrid working, they are once again separated from their pets, making their health management even more complicated. To solve this problem, a means of collecting and analyzing pet biometric data is needed, but currently no satisfactory solutions are available. [Means for solving the problem]

[0005] This invention provides a system connected to a pet device equipped with a biosensor that collects biometric data from a pet. The system includes means for receiving and preprocessing the pet's biometric data from the pet device, analyzing the preprocessed data, and using a generative AI model to estimate the pet's emotions and health status, and storing the analysis results in a database. The system also includes means for transmitting the analysis results to a user terminal and providing them to the user through an interface, as well as a GPS function for acquiring the pet's location information and displaying it to the user. Furthermore, the user terminal can register basic information about the pet, and the generative AI model can learn data patterns and trends based on that information, enabling more advanced emotional understanding. This system allows owners to monitor their pet's health status and emotions in real time, even when they're out, and respond appropriately.

[0006] A "biometric sensor" is a device used to detect and collect biometric data such as a pet's heart rate, activity, and sound.

[0007] A "pet device" is a device that is attached to a pet, has multiple built-in biometric sensors, and has the function of collecting biometric data from the pet and transmitting it to a server.

[0008] A "generative AI model" is a model that uses machine learning and artificial intelligence techniques to predict and analyze a pet's emotions and health status from its biometric data.

[0009] "Analysis means" means a part of the system that has the function of analyzing the collected biometric data using a generative AI model and storing the results in a database.

[0010] The "database" is a storage device within the system that stores analyzed pet biometric data and the results, allowing it to be searched and referenced as needed.

[0011] A "user terminal" is a device used by a user, such as a smartphone or tablet, that runs software to display a pet's biometric data and analysis results.

[0012] An "interface" is a user-specific operation screen, such as an application or web page, that allows the user to visually check the pet's biometric data and analysis results and perform the necessary operations.

[0013] The "GPS function" is a function for obtaining and tracking the location of pets, and is a technology used to prevent pets from getting lost and to confirm their location.

[0014] "Preprocessing" refers to processes such as cleaning the data, filling in missing values, and removing noise that are carried out before analyzing collected biological data.

[0015] "Basic pet information" refers to key attribute information such as the pet's type, age, and gender, and is important basic data for learning AI models and analyzing data. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] System configuration

[0038] The invention is a system that includes a sensor built into a smart collar for pets and a dedicated application. The entire system consists of three main parts:

[0039] 1. Terminal part (pet device): This terminal is equipped with biosensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as your pet's heart rate, activity level, and barks in real time.

[0040] 2. Server part: The server receives data sent from the terminal, performs preprocessing, and then analyzes the data using the generative AI model. The analysis results are stored in a database and sent to the user terminal as needed.

[0041] 3. User device: The user device (e.g., smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It can also obtain pet location information based on user operations.

[0042] Program processing flow

[0043] 1. Sensor data collection and transmission (terminal part)

[0044] The device uses biometric sensors to continuously collect your pet's biometric data, including heart rate, activity level, and vocalizations.

[0045] The collected data is temporarily stored in a buffer. At regular intervals, the data in the buffer is packetized and sent to a server using a secure communication protocol.

[0046] 2. Data reception and analysis (server part)

[0047] The server receives the data sent from the terminal and stores it in a secure storage.

[0048] The received data is pre-processed to clean and denoise it, and then fed into a generative AI model to analyze the pet's emotions and health.

[0049] The analysis results are stored in a database and provided upon request from the user terminal.

[0050] 3. Notification to the user and provision of interface (user terminal part)

[0051] The user terminal performs authentication and acquires the user's pet information.

[0052] The analysis results are requested from the server and displayed to the user through an interface, showing the pet's health status and emotional changes in real time.

[0053] If necessary, the GPS function is used to obtain the pet's location information and display it to the user.

[0054] Specific examples

[0055] For example, if an owner wants to check on their pet (dog) while at work, the process would be as follows:

[0056] 1. Terminal part: Collects the dog's movements, heart rate, and barks.

[0057] 2. Server part: Receives the collected data and performs pre-processing (such as noise removal). Analyzes the data with a generative AI model and determines whether the dog is likely experiencing stress.

[0058] 3. User device: The analysis results are sent to the user via the app. The owner can open the app while at work, check that the dog is experiencing stress, and take appropriate action (e.g., contact a family member at home, remotely control a toy, etc.).

[0059] This system allows owners to keep track of their pet's health and emotions at all times and take any necessary action quickly.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The device uses biometric sensors (heart rate sensor, accelerometer, microphone) to collect data such as your pet's heart rate, movements, and sounds in real time.

[0063] Step 2:

[0064] The device stores the collected biometric data in a buffer at regular intervals (e.g., 1-second intervals). By storing the data in the buffer, data continuity is maintained.

[0065] Step 3:

[0066] The terminal packetizes the data in the buffer at regular intervals (for example, every 10 minutes) and transmits the data to the server using a secure communication protocol (for example, HTTPS).

[0067] Step 4:

[0068] The server first stores the received data in a secure storage, which prevents data loss.

[0069] Step 5:

[0070] The server preprocesses the stored data, which includes cleaning the data, filling in missing values, and removing noise to improve the accuracy of the analysis.

[0071] Step 6:

[0072] The server then inputs the preprocessed data into a generative AI model, which analyzes the data and estimates the pet's emotions (e.g., stress levels) and health status (e.g., abnormal heart rates).

[0073] Step 7:

[0074] The server stores the analysis results in a database, which allows for statistical analysis and historical reference in conjunction with past data.

[0075] Step 8:

[0076] The user terminal (application) performs user authentication and obtains basic information about the pet (species, age, sex, etc.). After authentication, it requests the necessary data from the server.

[0077] Step 9:

[0078] The server receives requests from the user's device and transmits the analysis results, which include information about the pet's current health condition and emotions.

[0079] Step 10:

[0080] The user terminal displays the received analysis results to the user in a visually easy-to-understand format, such as graphs or notification messages.

[0081] Step 11:

[0082] The user device will send push notifications as needed, for example, notifying the user immediately if their pet is experiencing high stress levels.

[0083] Step 12:

[0084] The user device uses the GPS function to acquire the pet's location information, which allows the pet's current location to be displayed on a map.

[0085] Step 13:

[0086] Users can check the analysis results and pet location information through the application, allowing them to understand their pet's condition in real time and take appropriate action.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] The challenge is to understand changes in a pet's health and emotions in real time and respond quickly. Even when the owner is away from their pet, it is necessary to monitor the pet's condition at the appropriate time. There is also a need for a system that can obtain pet location information and take necessary action immediately.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes means connected to an animal device equipped with a biosensor that collects the animal's biometric data, means for receiving the animal's biometric data from the animal device and performing preprocessing, means for analyzing the preprocessed data and using a generative AI model to estimate the animal's emotions and health status, means for storing the analysis results in a database, means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and means with a GPS function for acquiring the animal's location information and displaying it to the user. This makes it possible to monitor and understand changes in the pet's health status and emotions in real time and take prompt and appropriate action.

[0092] An "animal device" is a device equipped with sensors for collecting biometric data from an animal.

[0093] A "biosensor" is a sensor that detects and collects biological information such as an animal's heart rate, activity level, and vocalizations.

[0094] "Data preprocessing" refers to the process of preparing data before analysis, such as cleaning collected biological data and removing noise.

[0095] A "generative AI model" is an artificial intelligence model that analyzes collected data and is used to estimate the health and emotions of animals.

[0096] "Analysis means" refers to a device or system that uses a generative AI model to analyze pre-processed data and infer the animal's health and emotions.

[0097] A "database" is a system that stores and manages analysis results and other related data.

[0098] A "user terminal" is a device that receives analysis results and the current status of animals from the server and displays them to the user, and includes smartphones, tablets, etc.

[0099] "Interface" refers to the user interface used to display analysis results and the status of animals on the user's terminal.

[0100] The "GPS function" is a function that uses a satellite positioning system to obtain animal location information and display it on the user's device.

[0101] "Animal location information" is data indicating the current location of an animal obtained by the GPS function.

[0102] System configuration

[0103] This invention is a biosensor built into a smart device for animals, and a system for analyzing and managing it. In particular, it aims to monitor the animal's health and emotions in real time and notify the user. The system consists of three main parts:

[0104] 1. Terminal part (animal device):

[0105] Hardware: Heart rate sensors, accelerometers, and microphones built into animal collars, etc.

[0106] Software: A program that temporarily stores collected data in a buffer and sends the data to a server using a secure communication protocol (such as SSL / TLS).

[0107] 2. Server part:

[0108] Hardware: High-performance servers (e.g. virtual servers from cloud computing services).

[0109] Software: Programs for preprocessing, analyzing, and storing data, such as storage (e.g., cloud storage services), generative AI models (e.g., machine learning models), and databases (e.g., relational databases).

[0110] 3. User terminal part:

[0111] Hardware: Smartphones, tablets, etc.

[0112] Software: A program that receives analysis results and displays them to the user through a dedicated application. It also includes a function to obtain animal location information using GPS functionality and provide it to the user.

[0113] Basic system operation

[0114] The device collects data from the heart rate sensor, accelerometer, and microphone built into the animal's collar, temporarily stores this data in a buffer, periodically packetizes it, and transmits it to the server using the SSL / TLS protocol.

[0115] The server securely stores the received data and performs preprocessing, which includes data cleaning and noise removal. The preprocessed data is then fed into a generative AI model to analyze the animal's emotions and health status. The analysis results are stored in a database and, if necessary, sent to the user's device.

[0116] The user device requests the analysis results from the server and displays the received results to the user in real time. It can also use the GPS function to obtain animal location information and provide it to the user.

[0117] Specific examples

[0118] For example, if an owner wants to check on their pet (dog) while at work, the process would look like this:

[0119] 1. Terminal part: Collects the dog's heart rate, activity level, and barks. The heart rate sensor detects 80 bpm, the acceleration sensor detects low activity, and the microphone detects high-frequency barks.

[0120] 2. Server: Receives the collected data and performs preprocessing (such as noise removal). Analyzes the data using a generative AI model and determines whether the dog is experiencing stress.

[0121] 3. User terminal: The analysis results are sent to the user via a dedicated application. The user receives a notification such as "your dog is stressed" and can take appropriate action (such as contacting family members at home or remotely controlling a toy).

[0122] Example prompts to be input to the generative AI model

[0123] For example, you could input the following prompts into a generative AI model:

[0124] Analyze your dog's emotional and health status based on the following data collected from your dog:

[0125] Heart rate: 80 bpm

[0126] Activity level: low

[0127] Call frequency: High

[0128] Please briefly explain your dog's current condition.

[0129] This prompt allows the generative AI model to determine that the dog is stressed based on its high heart rate and low activity level, and provide useful information to the user.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1:

[0132] Data collection (terminal part)

[0133] The device uses a heart rate sensor, accelerometer, and microphone attached to the animal's collar to collect data such as heart rate, activity, and vocalizations in real time. Specifically, the heart rate sensor measures the heart rate every second, the accelerometer measures the animal's activity on three axes, and the microphone analyzes the frequency and volume of the animal's vocalizations.

[0134] Input: Animal heart rate, activity level, and sounds

[0135] Output: Collected biological data (heart rate, activity level, vocalizations)

[0136] Step 2:

[0137] Data transmission (terminal part)

[0138] The terminal temporarily stores the collected data in a buffer and packets the data at regular intervals (for example, every minute). The packetized data is securely sent to the server using the SSL / TLS protocol. Specifically, the data is packetized and encrypted.

[0139] Input: Collected biometric data

[0140] Output: Packetized and encrypted data

[0141] Step 3:

[0142] Data reception and storage (server part)

[0143] The server securely receives data sent from the device using the SSL / TLS protocol. The received data is then temporarily stored in storage (e.g., a cloud storage service). Specifically, the data is deserialized and stored.

[0144] Input: Packetized and encrypted data

[0145] Output: Stored biometric data

[0146] Step 4:

[0147] Data preprocessing (server part)

[0148] The server performs preprocessing on the stored data, including cleaning and noise removal. Specific operations include imputing missing values ​​in heart rate data, removing spikes in activity data, and removing noise from bird sounds.

[0149] Input: Stored biometric data

[0150] Output: Preprocessed biometric data

[0151] Step 5:

[0152] Data analysis (server part)

[0153] The server inputs the preprocessed data into the generative AI model, which then analyzes the animal's health and emotions from the input data. Specifically, the AI ​​model analyzes the data and outputs a specific result, such as "the animal is feeling stressed." The analysis results are stored in a database.

[0154] Input: Preprocessed biometric data

[0155] Output: Analysis of the animal's health and emotions

[0156] Step 6:

[0157] Notification of analysis results (user terminal)

[0158] The user's device requests the analysis results from the server. Once the results are received, they are displayed to the user through a dedicated application. Specifically, the application sends a notification to the user, such as "The animal is feeling stressed," and also uses GPS to obtain the animal's location.

[0159] Input: Analysis results, animal location information

[0160] Output: Notification to the user, display of animal location information

[0161] Examples:

[0162] Example prompts to input to a generative AI model:

[0163] Analyze your pet's emotions and health using the following data collected from your pet:

[0164] Heart rate: 80 bpm

[0165] Activity level: low

[0166] Call frequency: High

[0167] Please provide a brief description of your pet's current condition.

[0168]

[0169] (Application example 1)

[0170] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0171] It is important to monitor the status of operating equipment used in factories and work sites in real time and manage its operation safely and efficiently. However, conventional monitoring systems are expensive and have low accuracy in detecting abnormal conditions. In addition, it is difficult to respond quickly when an abnormality occurs, resulting in reduced productivity and significant damage due to breakdowns. It is also difficult to obtain location information of operating equipment and manage it appropriately.

[0172] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0173] In this invention, the server includes means connected to an equipment device equipped with a sensor that collects status data of operating equipment, means for receiving the status data of the operating equipment from the equipment device and performing preprocessing, means for analyzing the preprocessed data and using a generative AI model to estimate anomalies in the operating equipment, means for saving the analysis results in a database, means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and means equipped with a GPS function for acquiring location information of the operating equipment and displaying it to the user. This enables real-time status monitoring of operating equipment, rapid anomaly detection, and location information management.

[0174] "Operating equipment" is equipment used in a factory or workplace that operates mechanically to accomplish a specific task.

[0175] "Status data" refers to information about the operating status and performance of equipment, including vibration, movement, temperature, etc.

[0176] An "equipment device" is a device that includes a sensor and a communication module that is attached to collect status data of an operating device.

[0177] "Preprocessing" refers to the process of performing initial processing such as cleaning the received data and removing noise.

[0178] A "generative AI model" is an artificial intelligence algorithm model used to infer equipment anomalies based on collected data.

[0179] An "analysis means" is a device or system that has the function of inputting preprocessed data into a generative AI model and obtaining analytical results.

[0180] A "database" is an information system that systematically stores data obtained through preprocessing and analysis, as well as analysis results, and facilitates search and reference.

[0181] A "user terminal" is a device that receives the analysis results and displays them to the user, and includes smartphones, tablets, and the like.

[0182] "Interface" refers to a display screen and input device designed to allow users to easily understand and operate analysis results.

[0183] "GPS function" is a function for obtaining geographical location information, and provides the user with the exact location of the operating device.

[0184] The embodiments of the present invention will be described in detail below.

[0185] System configuration

[0186] This invention is a system for monitoring the status of equipment operating in a factory. The entire system consists of three main parts:

[0187] 1. Terminal part (device for equipment)

[0188] Sensors attached to operating equipment are used to collect status data such as vibration, movement, and temperature in real time. The data collected from these sensors is temporarily stored in a buffer, packetized at regular intervals, and sent to a server using a secure communication protocol.

[0189] 2. Server part

[0190] The server receives data sent from the terminal and stores it in secure storage. The received data is preprocessed, including cleaning and noise removal. It is then input into a generative AI model to analyze abnormalities and status changes in the operating equipment. The analysis results are stored in a database and provided upon request from the user's terminal.

[0191] 3. User terminal part

[0192] The user device (e.g., a smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It is also possible to obtain the location information of operating devices based on user operations.

[0193] Hardware and software used

[0194] Hardware used:

[0195] Robot sensors (motion sensors, vibration sensors, temperature sensors)

[0196] Communication module (Wi-Fi / Bluetooth)

[0197] server

[0198] User devices (smartphones, tablets)

[0199] Software used:

[0200] Python (data collection and analysis)

[0201] TensorFlow (building and running generative AI models)

[0202] Django (Web server framework)

[0203] Firebase (database)

[0204] Pushbullet (send alerts)

[0205] System Operation

[0206] Data collection and transmission

[0207] At the terminal section, sensors attached to the equipment device collect status data of the operating equipment, which is then sent to the server via a secure communication protocol.

[0208] Data analysis

[0209] The server preprocesses the received data and removes noise. The data is then input into a generative AI model to estimate abnormalities in the operating equipment. The analysis results are stored in a database and sent to the user's device as needed.

[0210] User Notification

[0211] The analysis results are sent to the user's device via the application. The user can use the application to check the status of the equipment in operation and take appropriate action if an abnormality occurs. The GPS function can also be used to obtain the location information of the equipment in operation.

[0212] Specific examples

[0213] For example, if a critical piece of equipment in a factory exhibits abnormal vibrations, the following steps will take place:

[0214] 1. Terminal part: Sensors collect information on the device's movement, vibration, and temperature.

[0215] 2. Server part: Receives collected data and performs preprocessing (such as noise removal). The data is analyzed using a generative AI model to detect anomalies.

[0216] 3. User device: The analysis results are sent to the user via the application. The user can open the app, check the abnormality warning, and take prompt action.

[0217] Example prompt sentence:

[0218] The system applies sensors built into smart pet collars to factory robots, creating an application that monitors the robot's movements, vibrations, and temperature in real time and sends an alert if an abnormality is detected.

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] The terminal uses sensors attached to the operating equipment to collect status data such as vibration, movement, and temperature in real time. The collected data is temporarily stored in a buffer. Specifically, each sensor acquires data every second and stores it in memory. The input is raw data from the sensor, and the output is the temporary data in the buffer.

[0222] Step 2:

[0223] The device periodically converts the data in the buffer into packets and sends them to the server using a secure communication protocol (e.g., SSL / TLS). At this stage, the data is still raw and pure sensor data is being sent. The input is the buffered data, and the output is the data to be sent to the server. Specifically, each time a certain amount of data accumulates, it is converted into packets and sent to the server via the network.

[0224] Step 3:

[0225] The server receives data sent from the terminal and stores it in secure storage (e.g., a cloud storage system). This storage minimizes the risk of data loss. The input is the raw data sent from the terminal, and the output is the data stored in the storage. Specifically, the server receives data through the network interface and writes it to a database.

[0226] Step 4:

[0227] The server preprocesses the received data, cleaning and denoising it. At this stage, noise data and outliers are removed. The input is raw data stored in storage, and the output is preprocessed clean data. Specifically, a data filtering algorithm is used to extract only valid data.

[0228] Step 5:

[0229] The server inputs the preprocessed data into a generative AI model to analyze abnormalities and state changes in the operating equipment. The generative AI model (using TensorFlow, for example) infers abnormalities in the operating equipment and outputs the analysis results. The input is preprocessed clean data, and the output is the analysis results. Specifically, the server feeds data into the AI ​​model and generates inference results.

[0230] Step 6:

[0231] The server stores the analysis results in a database, which can then be used for future reference or as historical data. The input is the analysis results, and the output is the result data stored in the database. Specifically, the server writes the analysis results to the database as structured data.

[0232] Step 7:

[0233] The server sends the analysis results in response to a request from the user terminal. The user terminal receives these analysis results and displays them to the user through a GUI (graphical user interface). The input is the analysis results retrieved from the database, and the output is the display data on the user terminal. Specifically, the data is sent to the client via a REST API.

[0234] Step 8:

[0235] The user terminal obtains the location information of the pet device and displays it to the user when specified. This location information is obtained using the GPS function. The input is GPS data, and the output is the location information displayed to the user. Specifically, the terminal obtains the location information from the GPS module and updates the display on the user interface.

[0236] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0237] System configuration

[0238] This invention is a system that combines biosensors built into a smart collar for pets, a dedicated application, and an emotion engine. The whole system consists of four main parts:

[0239] 1. Terminal part (pet device): This terminal is equipped with biosensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as your pet's heart rate, activity level, and barks in real time.

[0240] 2. Server: The server receives data sent from the device, performs preprocessing, and then analyzes the data using a generative AI model. Furthermore, the server incorporates an emotion engine to recognize the user's emotions and analyze the user's reaction to the pet's state. The analysis results are stored in a database and sent to the user's device as needed.

[0241] 3. User device: The user device (e.g., smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It also analyzes the user's operations and reactions using an emotion engine and provides feedback to the system.

[0242] 4. Emotion engine: The emotion engine recognizes emotions from the user's facial expressions, voice, and input data, and reflects the analysis results throughout the system. This allows for dynamic interface and notifications to be provided according to the user's emotional patterns.

[0243] Program processing flow

[0244] 1. Sensor data collection and transmission (terminal part)

[0245] The device uses biometric sensors to continuously collect your pet's biological data, including heart rate, activity level, and vocalizations, in real time.

[0246] The collected data is stored in a buffer at regular intervals, packetized, and sent to a server using a secure communication protocol.

[0247] 2. Data reception and analysis (server part)

[0248] The server first stores the received data in secure storage and pre-processes it, which includes cleaning and denoising the data.

[0249] The pre-processed data is input into a generative AI model to analyze the pet's emotions and health status.

[0250] The analysis results are stored in a database and are ready to be provided to the user terminal.

[0251] 3. User Emotion Recognition and Response (Server and Emotion Engine)

[0252] The server uses an emotion engine to recognize the user's emotions and takes the user's reactions into account in the analysis results.

[0253] The system dynamically adjusts notifications and alerts depending on the user's perceived emotions, for example providing detailed health information about a pet if the user appears anxious.

[0254] 4. Notification to the user and provision of interface (user terminal part)

[0255] The user terminal performs authentication and acquires basic information about the pet.

[0256] The analysis results and the emotion engine's evaluation are received from the server and displayed to the user.

[0257] Send push notifications when needed and provide an interface that dynamically adjusts to specific situations.

[0258] Specific examples

[0259] Scenario: An owner wants to monitor the status of their pet (dog) while at work:

[0260] 1. Terminal part: Collects the dog's movements, heart rate, and barks. The collected data is periodically sent to the server.

[0261] 2. Server part: The server receives the data and performs preprocessing. It analyzes the data using a generative AI model and determines that the dog is stressed. The emotion engine analyzes the user's facial expressions from the camera and determines that the user is anxious.

[0262] 3. User terminal: The analysis results and the emotion engine's evaluation are notified to the user through the application. The user opens the application and checks whether the dog is stressed and the cause (e.g., lack of exercise or external stimuli). The system then provides detailed information and advice to ease the user's anxiety.

[0263] This system allows owners to understand their pet's health and emotions in real time, while also recognizing their own emotions, allowing for individually tailored responses.

[0264] The processing flow will be explained below.

[0265] Step 1:

[0266] The device uses biosensors (heart rate sensor, accelerometer, microphone) to collect data such as your pet's heart rate, activity level, and cries in real time.

[0267] Step 2:

[0268] The device stores the collected biometric data in a buffer at regular intervals (e.g., 1-second intervals). By storing the data in the buffer, data continuity is maintained.

[0269] Step 3:

[0270] The terminal packetizes the data in the buffer at regular intervals (for example, every 10 minutes) and transmits the data to the server using a secure communication protocol (for example, HTTPS).

[0271] Step 4:

[0272] The server first stores the received data in a secure storage, which prevents data loss.

[0273] Step 5:

[0274] The server preprocesses the stored data, which includes cleaning the data, filling in missing values, and removing noise to improve the accuracy of the analysis.

[0275] Step 6:

[0276] The server then inputs the preprocessed data into a generative AI model, which analyzes the data and estimates the pet's emotions (e.g., stress levels) and health status (e.g., abnormal heart rates).

[0277] Step 7:

[0278] The server stores the analysis results in a database, which can then be combined with past data for statistical analysis and historical reference.

[0279] Step 8:

[0280] The server uses an emotion engine to recognize the user's emotions, which uses the user's facial expressions, voice, and input data.

[0281] Step 9:

[0282] The server adjusts the analysis results based on the user's perceived emotions, for example, providing more detailed information and suggestions if the user appears anxious.

[0283] Step 10:

[0284] The user device performs user authentication and acquires basic information about the pet. Once authentication is complete, the device requests data from the server.

[0285] Step 11:

[0286] The server receives a request from the user terminal and transmits the analysis results and the emotion engine's evaluation.

[0287] Step 12:

[0288] The user device displays the received analysis results and the emotion engine's evaluation to the user. The results are presented visually in easy-to-understand graphs and messages.

[0289] Step 13:

[0290] The user device will send push notifications as needed, including warnings if the pet is exhibiting high stress levels.

[0291] Step 14:

[0292] The user device uses the GPS function to acquire the pet's location information, which allows the pet's current location to be displayed on a map.

[0293] Step 15:

[0294] Users can check the analysis results and their pet's location information through the application, and can understand their pet's health condition and emotions in real time and take necessary measures.

[0295] Example 2

[0296] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0297] In today's busy lifestyles, it is difficult for pet owners to monitor their pets' health and emotions in real time and respond promptly to appropriate needs. As a result, pet owners may not notice a deterioration in their pet's health early and may not be able to provide appropriate care. There is also a need for systems that can reflect the owner's own emotional state to enable more appropriate responses. However, current technology does not provide a system that can simultaneously monitor the status of both the pet and the owner and provide appropriate information.

[0298] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0299] In this invention, the server includes: means connected to a pet device equipped with a biosensor that collects biometric data from the pet; means for receiving the biometric data from the pet device and performing preprocessing; means for analyzing the preprocessed data and using a generative AI model to estimate the pet's emotions and health status; means for storing the analysis results in a database; means for transmitting the analysis results to a user terminal and providing them to the user through an interface; means including an emotion engine that receives the user's emotion data and dynamically adjusts system notifications and alerts based on the analysis results; and means for the terminal to perform authentication, acquire, and display basic information about the pet. This makes it possible to monitor the pet's health status and the owner's emotional state in real time and provide the owner with individually customized appropriate information and responses.

[0300] A "biometric sensor" is a device for collecting physiological data from pets (e.g., heart rate, activity level, vocalizations, etc.).

[0301] A "pet device" is a data collection device attached to a pet, including biosensors and communication means.

[0302] "Preprocessing" is the process of cleaning the acquired data, removing noise, and preparing it in a format suitable for analysis.

[0303] A "generative AI model" is a machine learning model that analyzes pets' emotions and health status based on collected data.

[0304] "Analysis" refers to using a generative AI model based on pre-processed data to estimate a pet's emotions and health status.

[0305] "Database" means an electronic repository for storing analytical results and other related information.

[0306] A "user terminal" is an electronic device such as a smartphone or tablet that is used by a user.

[0307] "Interface" refers to the display screen and operating means used to provide information to the user.

[0308] An "emotion engine" is a software component that analyzes a user's emotional state and dynamically adjusts system behavior and notifications based on that.

[0309] "Authentication" is the process of verifying a user's identity in order to access a system.

[0310] This invention is a system that combines a smart device for pets, a dedicated application, and an emotion engine. The system aims to collect and analyze biometric data from pets to understand their health condition and emotions, and to provide appropriate information to users based on that data.

[0311] System configuration

[0312] Terminal part (pet device)

[0313] The terminal part is a device attached to a pet's collar and is equipped with biometric sensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as the pet's heart rate, activity level, and vocalizations in real time. The collected data is stored in a buffer and sent to a server using a secure communication protocol.

[0314] Examples:

[0315] A device attached to the dog's collar measures the dog's heart rate every second and sends the data to a server every 10 seconds.

[0316] Server part

[0317] The server receives the data sent from the device and first stores it in secure storage. It then preprocesses the data and analyzes the pet's biometric data using a generative AI model. The analysis includes data cleaning and noise removal. The preprocessed data is then analyzed by the AI ​​model to estimate the pet's emotions and health status. The analysis results are stored in a database and are ready to be provided to the user's device.

[0318] Examples:

[0319] The server receives the dog's heart rate data, cleans it to remove noise, and then inputs it into an AI model to determine whether the dog is stressed and stores the results in a database.

[0320] User terminal part

[0321] The user device is a smartphone or tablet, and receives analysis results from the server through a dedicated application. The user device visually displays the pet's health condition and emotions in real time. It can also analyze the user's actions and reactions using an emotion engine and provide feedback to the system. Authentication is completed when the user logs in to the app, and the latest analysis results are provided from the server.

[0322] Examples:

[0323] The user opens the app and checks their dog's latest heart rate and activity level data in real time. If the dog is stressed, the app will provide the user with details and advise them on what to do.

[0324] Emotion Engine

[0325] The emotion engine analyzes the user's camera footage and audio data in real time to recognize their emotions. Based on this information, the system dynamically adjusts notifications and alerts. For example, if the user is feeling anxious, it will provide detailed information about the condition of their pet.

[0326] Examples:

[0327] If the emotion engine detects a user's impatience while checking on their pet's condition, it will provide the user with advice on how to relax, along with detailed information about their pet's health.

[0328] Example prompts to be input to the generative AI model

[0329] "Example prompt for a generative AI model analyzing smart pet collar data: 'Analyze the dog's heart rate, activity level, and bark data to determine the dog's emotional state.'"

[0330] The entire system allows owners to monitor their pets' condition in real time, providing appropriate information and prompt responses, and also reflects the user's emotional state, providing personalized responses.

[0331] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0332] Step 1:

[0333] Sensor initialization

[0334] The device will initialize the heart rate sensor, accelerometer, microphone, etc. The firmware in the device will perform basic settings to ensure the sensors operate correctly.

[0335] Input: Sensor start signal

[0336] Output: The state at which the sensor starts collecting data

[0337] Specific operation: The heart rate sensor is set to measure the heart rate every second, and the microphone is set to capture the pet's cries in real time.

[0338] Step 2:

[0339] Data collection

[0340] The device uses biometric sensors to collect data such as your pet's heart rate, activity level, and sounds in real time.

[0341] Input: Pet's biological activity data

[0342] Output: Biological data (heart rate, activity level, vocalizations)

[0343] How it works: The heart rate sensor measures your pet's heart rate every second, the acceleration sensor records its activity as digital data, and the microphone records its barks as audio data.

[0344] Step 3:

[0345] Saving to the data buffer

[0346] The collected data is stored in a buffer at regular intervals. For example, a sensor collects data every second and stores it in a buffer for 10 seconds.

[0347] Input: Collected biometric data

[0348] Output: Buffered data

[0349] Specific operation: Heart rate data and activity data are stored every second for a short period (temporary storage). After 10 seconds, the data is prepared to be passed to the next step.

[0350] Step 4:

[0351] Packetizing and transmitting data

[0352] The data stored in the buffer is packetized and sent to the server using a secure communication protocol (e.g., TLS).

[0353] Input: Data stored in the buffer

[0354] Output: Data packets sent to the server

[0355] Specific operation: The data in the buffer is packetized in a certain format (e.g., JSON format) and sent to the server over the Internet using the TLS protocol.

[0356] Step 5:

[0357] Receiving data

[0358] The server receives the data packets sent from the terminal.

[0359] Input: Data packets sent from the device

[0360] Output: Biometric data stored on the server

[0361] Specific operation: The server receives the data packet via the communication protocol and stores it in its internal secure storage.

[0362] Step 6:

[0363] Performing preprocessing

[0364] The server performs preprocessing on the received data, which includes cleaning the data (filling in missing values, removing invalid values) and removing noise (applying filtering techniques).

[0365] Input: Biometric data stored on the server

[0366] Output: Preprocessed and clean data

[0367] Specific operation: Detects and removes or complements incomplete data from the incoming data, removing noise and creating a clean dataset.

[0368] Step 7:

[0369] Analysis using generative AI models

[0370] The preprocessed data is fed into a generative AI model (e.g., a model trained with TensorFlow or PyTorch) to analyze the pet's emotions and health status.

[0371] Input: Preprocessed clean data

[0372] Output: Analysis results (estimated information on pet's emotions and health status)

[0373] How it works: Clean biometric data is input into a generative AI model, and an inference algorithm is run to analyze the pet's emotions (e.g., stress, peace of mind) and health status (e.g., healthy, abnormal).

[0374] Step 8:

[0375] Data storage

[0376] The analysis results are saved in a database.

[0377] Input: Analysis results

[0378] Output: Analysis results stored in a database

[0379] Specific operation: The analysis results from the generative AI model are stored in a database, ready for further processing or use when needed.

[0380] Step 9:

[0381] Sending and displaying analysis results

[0382] The analysis results from the server are sent to the user's terminal and provided to the user through an interface.

[0383] Input: Analysis results stored in the database

[0384] Output: Analysis results sent to the user's device

[0385] Specific operation: The analysis results are sent to the user's device, allowing the user to view the data in the application.

[0386] Step 10:

[0387] User Emotion Recognition

[0388] The emotion engine receives the user's camera footage and audio data and analyzes the user's emotions.

[0389] Input: User's camera video and audio data

[0390] Output: Parsed user emotion data

[0391] Specific operation: While the user is using the application, the emotion engine analyzes camera footage and audio data in real time to estimate the user's emotional state.

[0392] Step 11:

[0393] Dynamic adjustment of notifications and alerts

[0394] Dynamically adjust system notifications and alerts based on recognized user emotions.

[0395] Input: Parsed user emotion data

[0396] Output: Dynamically adjusted notifications and alerts

[0397] Specific behavior: If the user feels anxious, detailed information about the pet's condition and appropriate advice will be automatically provided to the user.

[0398] (Application example 2)

[0399] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0400] In the food delivery industry, there is no way to monitor the health and emotions of delivery workers in real time, which has led to problems such as accidents and a decline in service quality due to overwork and stress.In addition, there is also the issue of difficulty in designing efficient delivery routes and responding to emergencies due to a lack of proper management of delivery workers.

[0401] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means connected to a delivery person device equipped with a biometric sensor, a means for receiving the delivery person's biometric data from the delivery person device and performing preprocessing, an analysis means using a generative AI model to analyze the preprocessed data and estimate the delivery person's emotions and health condition, a means for saving the analysis results in a database, a means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and a means with a GPS function for acquiring the location information of the delivery person during delivery and displaying it to the manager. This enables real-time monitoring of the health condition and emotions of delivery people, improving service quality and efficient operation management.

[0402] A "biometric sensor" is a device for collecting biometric data such as heart rate, activity level, voice, and location information.

[0403] A "delivery person device" is a terminal equipped with a built-in biometric sensor that collects biometric data from delivery persons in real time.

[0404] "Data preprocessing" refers to the process of removing noise and cleaning data from collected biometric data.

[0405] A "generative AI model" is an artificial intelligence model that analyzes collected and preprocessed biometric data to estimate the health status and emotions of delivery personnel.

[0406] A "database" is an information management system that systematically stores analyzed results and makes them accessible as needed.

[0407] A "user terminal" is a device (e.g., a smartphone) that receives analysis results and notifications and provides information to the user through an interface.

[0408] The "GPS function" is a location information system that acquires the current location of the delivery person and displays that information on the user terminal or administrator.

[0409] An "interface" refers to the screen and operating means for providing analysis results and notifications to the user through the user terminal.

[0410] A "delivery route" is a route designed to allow delivery personnel to make deliveries efficiently.

[0411] System configuration

[0412] The invention is a system that combines biometric sensors built into the delivery driver's smart device, a dedicated application, and a generative AI model. The entire system consists of four main parts:

[0413] 1. Terminal part (delivery person device):

[0414] The device is equipped with built-in biometric sensors, including a heart rate sensor, accelerometer, microphone, and GPS, which collect real-time data on the delivery person's heart rate, activity, voice, location, and more.

[0415] 2. Server part:

[0416] The server receives data sent from the device, performs preprocessing, and then analyzes the data using the generative AI model. The analysis results are stored in a database and sent to the user device as needed.

[0417] 3. User terminal part:

[0418] The user device (e.g., a smartphone) receives the analysis results from the server through the application and provides them to the user in real time. Feedback from the user's operations is also recorded and reflected in the system.

[0419] 4. GPS function part:

[0420] The system is equipped with a GPS function that acquires the location information of delivery personnel during deliveries and displays it in real time on the manager's device, enabling efficient optimization of delivery routes.

[0421] Implementation details

[0422] Hardware and software used

[0423] Hardware:

[0424] Smartwatches or smart glasses (e.g., Apple Watch, Google Glass)

[0425] Smartphone

[0426] Cloud servers (e.g., Amazon Web Services, Google Cloud)

[0427] software:

[0428] Data cleaning tools (e.g., Python's Pandas library)

[0429] Generative AI models (e.g., custom models using TensorFlow or PyTorch)

[0430] Data flow

[0431] The server receives biometric data collected from the delivery driver's smart device and stores it in secure storage. It then performs preprocessing, such as data cleaning and noise removal, and sends the preprocessed data to a generative AI model to analyze the delivery driver's health status and emotions.

[0432] The analysis results are stored in a database and sent to the user's device as needed. The user's device receives the analysis results and displays them to the user through an interface. In addition, the GPS function displays the delivery person's current location to the manager, supporting efficient operation management.

[0433] Specific examples

[0434] One food delivery service introduced a "delivery worker health monitoring system" to improve the working environment for delivery workers and enhance the quality of their service. When delivery workers wear smartwatches, their heart rate and activity levels are monitored in real time, and a generative AI model uses this data to analyze the worker's health and emotions. For example, if a delivery worker is determined to be fatigued, a notification is sent immediately via a smartphone application urging them to take a break. Meanwhile, managers can use the GPS function to check the worker's current location and provide instructions for the optimal delivery route.

[0435] Example prompts for generative AI models

[0436] Analyze the following sensor data to determine the health and emotions of the delivery driver.

[0437] The data format is heart rate, activity level, and audio.

[0438] Heart rate: 85 bpm, Activity level: 6000 steps, Voice: "I'm feeling a bit tired..."

[0439] Result (example):

[0440] Health condition: Slight fatigue

[0441] Emotion: Stress

[0442] Heart rate: [Heart rate data], Activity: [Activity data], Audio: [Audio data]

[0443] This system allows delivery personnel's health and emotions to be monitored in real time, enabling efficient operation management and improved service quality.

[0444] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0445] Step 1:

[0446] Data collection (device):

[0447] The terminal (delivery worker device) uses biometric sensors to collect biometric data such as the delivery worker's heart rate, activity level, voice, and location information in real time. This collected data is stored in a buffer at regular intervals. The input is the biometric data acquired by the terminal's sensors, and the output is the sensor data stored in the buffer.

[0448] Step 2:

[0449] Sending data (terminal):

[0450] The device packetizes the biometric data stored in the buffer and sends it to the server using a secure communication protocol. The input is the sensor data stored in the buffer, and the output is the packet data sent via the communication protocol. A security protocol (e.g., SSL / TLS) is used for this operation.

[0451] Step 3:

[0452] Data reception and preprocessing (server):

[0453] The server receives data sent from the device and stores it in secure storage. Next, it performs preprocessing such as data cleaning and noise removal on the received data. The input is the transmitted packet data, and the output is the cleaned data. Specific operations include filling in missing values ​​and correcting outliers.

[0454] Step 4:

[0455] Data analysis (server):

[0456] The server inputs the preprocessed data into a generative AI model to analyze the delivery driver's health status and emotions. The input is the preprocessed data, and the output is the analysis results. Specific operations include feeding the data forward to the model, estimating the results, and classifying emotions and health status.

[0457] Step 5:

[0458] Result storage and notification (server):

[0459] The server stores the generated analysis results in a database and sends them to the user device as needed. The input is the analysis results, and the output is the information stored in the database and a notification to the user device. Specific operations include writing to the database and sending push notifications.

[0460] Step 6:

[0461] Interface updates (user terminals):

[0462] The user terminal receives the analysis results sent from the server and updates the interface to display them to the user. The input is the analysis results sent from the server, and the output is the updated interface. Specific operations include updating the display screen and displaying a notification pop-up.

[0463] Step 7:

[0464] Acquiring and displaying GPS information (device and server):

[0465] The terminal periodically collects the delivery person's location information and sends it to the server. The server receives this location information and displays the current location on the administrator's terminal. The input is the GPS data sent from the terminal, and the output is the location information displayed on the administrator's terminal. Specific operations include obtaining the GPS data and plotting the location on a map.

[0466] The above are the specific processing steps for carrying out the present invention.

[0467] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0468] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0469] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0470] [Second embodiment]

[0471] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0472] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0473] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0474] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0475] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0476] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0477] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0478] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0479] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0480] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0481] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0482] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0483] System configuration

[0484] The invention is a system that includes a sensor built into a smart collar for pets and a dedicated application. The entire system consists of three main parts:

[0485] 1. Terminal part (pet device): This terminal is equipped with biosensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as your pet's heart rate, activity level, and barks in real time.

[0486] 2. Server part: The server receives data sent from the terminal, performs preprocessing, and then analyzes the data using the generative AI model. The analysis results are stored in a database and sent to the user terminal as needed.

[0487] 3. User device: The user device (e.g., smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It can also obtain pet location information based on user operations.

[0488] Program processing flow

[0489] 1. Sensor data collection and transmission (terminal part)

[0490] The device uses biometric sensors to continuously collect your pet's biometric data, including heart rate, activity level, and vocalizations.

[0491] The collected data is temporarily stored in a buffer. At regular intervals, the data in the buffer is packetized and sent to a server using a secure communication protocol.

[0492] 2. Data reception and analysis (server part)

[0493] The server receives the data sent from the terminal and stores it in a secure storage.

[0494] The received data is pre-processed to clean and denoise it, and then fed into a generative AI model to analyze the pet's emotions and health.

[0495] The analysis results are stored in a database and provided upon request from the user terminal.

[0496] 3. Notification to the user and provision of interface (user terminal part)

[0497] The user terminal performs authentication and acquires the user's pet information.

[0498] The analysis results are requested from the server and displayed to the user through an interface, showing the pet's health status and emotional changes in real time.

[0499] If necessary, the GPS function is used to obtain the pet's location information and display it to the user.

[0500] Specific examples

[0501] For example, if an owner wants to check on their pet (dog) while at work, the process would be as follows:

[0502] 1. Terminal part: Collects the dog's movements, heart rate, and barks.

[0503] 2. Server part: Receives the collected data and performs pre-processing (such as noise removal). Analyzes the data with a generative AI model and determines whether the dog is likely experiencing stress.

[0504] 3. User device: The analysis results are sent to the user via the app. The owner can open the app while at work, check that the dog is experiencing stress, and take appropriate action (e.g., contact a family member at home, remotely control a toy, etc.).

[0505] This system allows owners to keep track of their pet's health and emotions at all times and take any necessary action quickly.

[0506] The processing flow will be explained below.

[0507] Step 1:

[0508] The device uses biometric sensors (heart rate sensor, accelerometer, microphone) to collect data such as your pet's heart rate, movements, and sounds in real time.

[0509] Step 2:

[0510] The device stores the collected biometric data in a buffer at regular intervals (e.g., 1-second intervals). By storing the data in the buffer, data continuity is maintained.

[0511] Step 3:

[0512] The terminal packetizes the data in the buffer at regular intervals (for example, every 10 minutes) and transmits the data to the server using a secure communication protocol (for example, HTTPS).

[0513] Step 4:

[0514] The server first stores the received data in a secure storage, which prevents data loss.

[0515] Step 5:

[0516] The server preprocesses the stored data, which includes cleaning the data, filling in missing values, and removing noise to improve the accuracy of the analysis.

[0517] Step 6:

[0518] The server then inputs the preprocessed data into a generative AI model, which analyzes the data and estimates the pet's emotions (e.g., stress levels) and health status (e.g., abnormal heart rates).

[0519] Step 7:

[0520] The server stores the analysis results in a database, which allows for statistical analysis and historical reference in conjunction with past data.

[0521] Step 8:

[0522] The user terminal (application) performs user authentication and obtains basic information about the pet (species, age, sex, etc.). After authentication, it requests the necessary data from the server.

[0523] Step 9:

[0524] The server receives requests from the user's device and transmits the analysis results, which include information about the pet's current health condition and emotions.

[0525] Step 10:

[0526] The user terminal displays the received analysis results to the user in a visually easy-to-understand format, such as graphs or notification messages.

[0527] Step 11:

[0528] The user device will send push notifications as needed, for example, notifying the user immediately if their pet is experiencing high stress levels.

[0529] Step 12:

[0530] The user device uses the GPS function to acquire the pet's location information, which allows the pet's current location to be displayed on a map.

[0531] Step 13:

[0532] Users can check the analysis results and pet location information through the application, allowing them to understand their pet's condition in real time and take appropriate action.

[0533] Example 1

[0534] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0535] The challenge is to understand changes in a pet's health and emotions in real time and respond quickly. Even when the owner is away from their pet, it is necessary to monitor the pet's condition at the appropriate time. There is also a need for a system that can obtain pet location information and take necessary action immediately.

[0536] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0537] In this invention, the server includes means connected to an animal device equipped with a biosensor that collects the animal's biometric data, means for receiving the animal's biometric data from the animal device and performing preprocessing, means for analyzing the preprocessed data and using a generative AI model to estimate the animal's emotions and health status, means for storing the analysis results in a database, means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and means with a GPS function for acquiring the animal's location information and displaying it to the user. This makes it possible to monitor and understand changes in the pet's health status and emotions in real time and take prompt and appropriate action.

[0538] An "animal device" is a device equipped with sensors for collecting biometric data from an animal.

[0539] A "biosensor" is a sensor that detects and collects biological information such as an animal's heart rate, activity level, and vocalizations.

[0540] "Data preprocessing" refers to the process of preparing data before analysis, such as cleaning collected biological data and removing noise.

[0541] A "generative AI model" is an artificial intelligence model that analyzes collected data and is used to estimate the health and emotions of animals.

[0542] "Analysis means" refers to a device or system that uses a generative AI model to analyze pre-processed data and infer the animal's health and emotions.

[0543] A "database" is a system that stores and manages analysis results and other related data.

[0544] A "user terminal" is a device that receives analysis results and the current status of animals from the server and displays them to the user, and includes smartphones, tablets, etc.

[0545] "Interface" refers to the user interface used to display analysis results and the status of animals on the user's terminal.

[0546] The "GPS function" is a function that uses a satellite positioning system to obtain animal location information and display it on the user's device.

[0547] "Animal location information" is data indicating the current location of an animal obtained by the GPS function.

[0548] System configuration

[0549] This invention is a biosensor built into a smart device for animals, and a system for analyzing and managing it. In particular, it aims to monitor the animal's health and emotions in real time and notify the user. The system consists of three main parts:

[0550] 1. Terminal part (animal device):

[0551] Hardware: Heart rate sensors, accelerometers, and microphones built into animal collars, etc.

[0552] Software: A program that temporarily stores collected data in a buffer and sends the data to a server using a secure communication protocol (such as SSL / TLS).

[0553] 2. Server part:

[0554] Hardware: High-performance servers (e.g. virtual servers from cloud computing services).

[0555] Software: Programs for preprocessing, analyzing, and storing data, such as storage (e.g., cloud storage services), generative AI models (e.g., machine learning models), and databases (e.g., relational databases).

[0556] 3. User terminal part:

[0557] Hardware: Smartphones, tablets, etc.

[0558] Software: A program that receives analysis results and displays them to the user through a dedicated application. It also includes a function to obtain animal location information using GPS functionality and provide it to the user.

[0559] Basic system operation

[0560] The device collects data from the heart rate sensor, accelerometer, and microphone built into the animal's collar, temporarily stores this data in a buffer, periodically packetizes it, and transmits it to the server using the SSL / TLS protocol.

[0561] The server securely stores the received data and performs preprocessing, which includes data cleaning and noise removal. The preprocessed data is then fed into a generative AI model to analyze the animal's emotions and health status. The analysis results are stored in a database and, if necessary, sent to the user's device.

[0562] The user device requests the analysis results from the server and displays the received results to the user in real time. It can also use the GPS function to obtain animal location information and provide it to the user.

[0563] Specific examples

[0564] For example, if an owner wants to check on their pet (dog) while at work, the process would look like this:

[0565] 1. Terminal part: Collects the dog's heart rate, activity level, and barks. The heart rate sensor detects 80 bpm, the acceleration sensor detects low activity, and the microphone detects high-frequency barks.

[0566] 2. Server: Receives the collected data and performs preprocessing (such as noise removal). Analyzes the data using a generative AI model and determines whether the dog is experiencing stress.

[0567] 3. User terminal: The analysis results are sent to the user via a dedicated application. The user receives a notification such as "your dog is stressed" and can take appropriate action (such as contacting family members at home or remotely controlling a toy).

[0568] Example prompts to be input to the generative AI model

[0569] For example, you could input the following prompts into a generative AI model:

[0570] Analyze your dog's emotional and health status based on the following data collected from your dog:

[0571] Heart rate: 80 bpm

[0572] Activity level: low

[0573] Call frequency: High

[0574] Please briefly explain your dog's current condition.

[0575] This prompt allows the generative AI model to determine that the dog is stressed based on its high heart rate and low activity level, and provide useful information to the user.

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

[0577] Step 1:

[0578] Data collection (terminal part)

[0579] The device uses a heart rate sensor, accelerometer, and microphone attached to the animal's collar to collect data such as heart rate, activity, and vocalizations in real time. Specifically, the heart rate sensor measures the heart rate every second, the accelerometer measures the animal's activity on three axes, and the microphone analyzes the frequency and volume of the animal's vocalizations.

[0580] Input: Animal heart rate, activity level, and sounds

[0581] Output: Collected biological data (heart rate, activity level, vocalizations)

[0582] Step 2:

[0583] Data transmission (terminal part)

[0584] The terminal temporarily stores the collected data in a buffer and then packetizes the data at regular intervals (for example, every minute). The packetized data is then securely sent to the server using the SSL / TLS protocol. Specifically, the data is packetized and encrypted.

[0585] Input: Collected biometric data

[0586] Output: Packetized and encrypted data

[0587] Step 3:

[0588] Data reception and storage (server part)

[0589] The server securely receives data sent from the device using the SSL / TLS protocol. The received data is then temporarily stored in storage (e.g., a cloud storage service). Specifically, the data is deserialized and stored.

[0590] Input: Packetized and encrypted data

[0591] Output: Stored biometric data

[0592] Step 4:

[0593] Data preprocessing (server part)

[0594] The server performs preprocessing on the stored data, including cleaning and noise removal. Specific operations include imputing missing values ​​in heart rate data, removing spikes in activity data, and removing noise from bird sounds.

[0595] Input: Stored biometric data

[0596] Output: Preprocessed biometric data

[0597] Step 5:

[0598] Data analysis (server part)

[0599] The server inputs the preprocessed data into the generative AI model, which then analyzes the animal's health and emotions from the input data. Specifically, the AI ​​model analyzes the data and outputs a specific result, such as "the animal is feeling stressed." The analysis results are stored in a database.

[0600] Input: Preprocessed biometric data

[0601] Output: Analysis of the animal's health and emotions

[0602] Step 6:

[0603] Notification of analysis results (user terminal)

[0604] The user's device requests the analysis results from the server. Once the results are received, they are displayed to the user through a dedicated application. Specifically, the application sends a notification to the user, such as "The animal is feeling stressed," and also uses GPS to obtain the animal's location.

[0605] Input: Analysis results, animal location information

[0606] Output: Notification to the user, display of animal location information

[0607] Examples:

[0608] Example prompts to input to a generative AI model:

[0609] Analyze your pet's emotions and health using the following data collected from your pet:

[0610] Heart rate: 80 bpm

[0611] Activity level: low

[0612] Call frequency: High

[0613] Please provide a brief description of your pet's current condition.

[0614]

[0615] (Application example 1)

[0616] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0617] It is important to monitor the status of operating equipment used in factories and work sites in real time and manage its operation safely and efficiently. However, conventional monitoring systems are expensive and have low accuracy in detecting abnormal conditions. In addition, it is difficult to respond quickly when an abnormality occurs, resulting in reduced productivity and significant damage due to breakdowns. It is also difficult to obtain location information of operating equipment and manage it appropriately.

[0618] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0619] In this invention, the server includes means connected to an equipment device equipped with a sensor that collects status data of operating equipment, means for receiving the status data of the operating equipment from the equipment device and performing preprocessing, means for analyzing the preprocessed data and using a generative AI model to estimate anomalies in the operating equipment, means for saving the analysis results in a database, means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and means equipped with a GPS function for acquiring location information of the operating equipment and displaying it to the user. This enables real-time status monitoring of operating equipment, rapid anomaly detection, and location information management.

[0620] "Operating equipment" is equipment used in a factory or workplace that operates mechanically to accomplish a specific task.

[0621] "Status data" refers to information about the operating status and performance of equipment, including vibration, movement, temperature, etc.

[0622] An "equipment device" is a device that includes a sensor and a communication module that is attached to collect status data of an operating device.

[0623] "Preprocessing" refers to the process of performing initial processing such as cleaning the received data and removing noise.

[0624] A "generative AI model" is an artificial intelligence algorithm model used to infer equipment anomalies based on collected data.

[0625] An "analysis means" is a device or system that has the function of inputting preprocessed data into a generative AI model and obtaining analytical results.

[0626] A "database" is an information system that systematically stores data obtained through preprocessing and analysis, as well as analysis results, and facilitates search and reference.

[0627] A "user terminal" is a device that receives the analysis results and displays them to the user, and includes smartphones, tablets, and the like.

[0628] "Interface" refers to a display screen and input device designed to allow users to easily understand and operate analysis results.

[0629] "GPS function" is a function for obtaining geographical location information, and provides the user with the exact location of the operating device.

[0630] The embodiments of the present invention will be described in detail below.

[0631] System configuration

[0632] This invention is a system for monitoring the status of equipment operating in a factory. The entire system consists of three main parts:

[0633] 1. Terminal part (device for equipment)

[0634] Sensors attached to operating equipment are used to collect status data such as vibration, movement, and temperature in real time. The data collected from these sensors is temporarily stored in a buffer, packetized at regular intervals, and sent to a server using a secure communication protocol.

[0635] 2. Server part

[0636] The server receives data sent from the terminal and stores it in secure storage. The received data is preprocessed, including cleaning and noise removal. It is then input into a generative AI model to analyze abnormalities and status changes in the operating equipment. The analysis results are stored in a database and provided upon request from the user's terminal.

[0637] 3. User terminal part

[0638] The user device (e.g., a smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It is also possible to obtain the location information of operating devices based on user operations.

[0639] Hardware and software used

[0640] Hardware used:

[0641] Robot sensors (motion sensors, vibration sensors, temperature sensors)

[0642] Communication module (Wi-Fi / Bluetooth)

[0643] server

[0644] User devices (smartphones, tablets)

[0645] Software used:

[0646] Python (data collection and analysis)

[0647] TensorFlow (building and running generative AI models)

[0648] Django (Web server framework)

[0649] Firebase (database)

[0650] Pushbullet (send alerts)

[0651] System Operation

[0652] Data collection and transmission

[0653] At the terminal section, sensors attached to the equipment device collect status data of the operating equipment, which is then sent to the server via a secure communication protocol.

[0654] Data analysis

[0655] The server preprocesses the received data and removes noise. The data is then input into a generative AI model to estimate abnormalities in the operating equipment. The analysis results are stored in a database and sent to the user's device as needed.

[0656] User Notification

[0657] The analysis results are sent to the user's device via the application. The user can use the application to check the status of the equipment in operation and take appropriate action if an abnormality occurs. The GPS function can also be used to obtain the location information of the equipment in operation.

[0658] Specific examples

[0659] For example, if a critical piece of equipment in a factory exhibits abnormal vibrations, the following steps will take place:

[0660] 1. Terminal part: Sensors collect information on the device's movement, vibration, and temperature.

[0661] 2. Server part: Receives collected data and performs preprocessing (such as noise removal). The data is analyzed using a generative AI model to detect anomalies.

[0662] 3. User device: The analysis results are sent to the user via the application. The user can open the app, check the abnormality warning, and take prompt action.

[0663] Example prompt sentence:

[0664] The system applies sensors built into smart pet collars to factory robots, creating an application that monitors the robot's movements, vibrations, and temperature in real time and sends an alert if an abnormality is detected.

[0665] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0666] Step 1:

[0667] The terminal uses sensors attached to the operating equipment to collect status data such as vibration, movement, and temperature in real time. The collected data is temporarily stored in a buffer. Specifically, each sensor acquires data every second and stores it in memory. The input is raw data from the sensor, and the output is the temporary data in the buffer.

[0668] Step 2:

[0669] The device periodically converts the data in the buffer into packets and sends them to the server using a secure communication protocol (e.g., SSL / TLS). At this stage, the data is still raw and pure sensor data is being sent. The input is the buffered data, and the output is the data to be sent to the server. Specifically, each time a certain amount of data accumulates, it is converted into packets and sent to the server via the network.

[0670] Step 3:

[0671] The server receives data sent from the terminal and stores it in secure storage (e.g., a cloud storage system). This storage minimizes the risk of data loss. The input is the raw data sent from the terminal, and the output is the data stored in the storage. Specifically, the server receives data through the network interface and writes it to a database.

[0672] Step 4:

[0673] The server preprocesses the received data, cleaning and denoising it. At this stage, noise data and outliers are removed. The input is raw data stored in storage, and the output is preprocessed clean data. Specifically, a data filtering algorithm is used to extract only valid data.

[0674] Step 5:

[0675] The server inputs the preprocessed data into a generative AI model to analyze abnormalities and state changes in the operating equipment. The generative AI model (using TensorFlow, for example) infers abnormalities in the operating equipment and outputs the analysis results. The input is preprocessed clean data, and the output is the analysis results. Specifically, the server feeds data into the AI ​​model and generates inference results.

[0676] Step 6:

[0677] The server stores the analysis results in a database, which can then be used for future reference or as historical data. The input is the analysis results, and the output is the result data stored in the database. Specifically, the analysis results are written to the database as structured data.

[0678] Step 7:

[0679] The server sends the analysis results in response to a request from the user terminal. The user terminal receives these analysis results and displays them to the user through a GUI (graphical user interface). The input is the analysis results retrieved from the database, and the output is the display data on the user terminal. Specifically, the data is sent to the client via a REST API.

[0680] Step 8:

[0681] The user terminal obtains the location information of the pet device and displays it to the user when specified. This location information is obtained using the GPS function. The input is GPS data, and the output is the location information displayed to the user. Specifically, the terminal obtains the location information from the GPS module and updates the display on the user interface.

[0682] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0683] System configuration

[0684] This invention is a system that combines biosensors built into a smart collar for pets, a dedicated application, and an emotion engine. The whole system consists of four main parts:

[0685] 1. Terminal part (pet device): This terminal is equipped with biosensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as your pet's heart rate, activity level, and barks in real time.

[0686] 2. Server: The server receives data sent from the device, performs preprocessing, and then analyzes the data using a generative AI model. Furthermore, the server incorporates an emotion engine to recognize the user's emotions and analyze the user's reaction to the pet's state. The analysis results are stored in a database and sent to the user's device as needed.

[0687] 3. User device: The user device (e.g., smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It also analyzes the user's operations and reactions using an emotion engine and provides feedback to the system.

[0688] 4. Emotion engine: The emotion engine recognizes emotions from the user's facial expressions, voice, and input data, and reflects the analysis results throughout the system. This allows for dynamic interface and notifications to be provided according to the user's emotional patterns.

[0689] Program processing flow

[0690] 1. Sensor data collection and transmission (terminal part)

[0691] The device uses biometric sensors to continuously collect your pet's biological data, including heart rate, activity level, and vocalizations, in real time.

[0692] The collected data is stored in a buffer at regular intervals, packetized, and sent to a server using a secure communication protocol.

[0693] 2. Data reception and analysis (server part)

[0694] The server first stores the received data in secure storage and pre-processes it, which includes cleaning and denoising the data.

[0695] The pre-processed data is input into a generative AI model to analyze the pet's emotions and health status.

[0696] The analysis results are stored in a database and are ready to be provided to the user terminal.

[0697] 3. User Emotion Recognition and Response (Server and Emotion Engine)

[0698] The server uses an emotion engine to recognize the user's emotions and takes the user's reactions into account in the analysis results.

[0699] The system dynamically adjusts notifications and alerts depending on the user's perceived emotions, for example providing detailed health information about a pet if the user appears anxious.

[0700] 4. Notification to the user and provision of interface (user terminal part)

[0701] The user terminal performs authentication and acquires basic information about the pet.

[0702] The analysis results and the emotion engine's evaluation are received from the server and displayed to the user.

[0703] Send push notifications when needed and provide an interface that dynamically adjusts to specific situations.

[0704] Specific examples

[0705] Scenario: An owner wants to monitor the status of their pet (dog) while at work:

[0706] 1. Terminal part: Collects the dog's movements, heart rate, and barks. The collected data is periodically sent to the server.

[0707] 2. Server part: The server receives the data and performs preprocessing. It analyzes the data using a generative AI model and determines that the dog is stressed. The emotion engine analyzes the user's facial expressions from the camera and determines that the user is anxious.

[0708] 3. User terminal: The analysis results and the emotion engine's evaluation are notified to the user through the application. The user opens the application and checks whether the dog is stressed and the cause (e.g., lack of exercise or external stimuli). The system then provides detailed information and advice to ease the user's anxiety.

[0709] This system allows owners to understand their pet's health and emotions in real time, while also recognizing their own emotions, allowing for individually tailored responses.

[0710] The processing flow will be explained below.

[0711] Step 1:

[0712] The device uses biosensors (heart rate sensor, accelerometer, microphone) to collect data such as your pet's heart rate, activity level, and cries in real time.

[0713] Step 2:

[0714] The device stores the collected biometric data in a buffer at regular intervals (e.g., 1-second intervals). By storing the data in the buffer, data continuity is maintained.

[0715] Step 3:

[0716] The terminal packetizes the data in the buffer at regular intervals (for example, every 10 minutes) and transmits the data to the server using a secure communication protocol (for example, HTTPS).

[0717] Step 4:

[0718] The server first stores the received data in a secure storage, which prevents data loss.

[0719] Step 5:

[0720] The server preprocesses the stored data, which includes cleaning the data, filling in missing values, and removing noise to improve the accuracy of the analysis.

[0721] Step 6:

[0722] The server then inputs the preprocessed data into a generative AI model, which analyzes the data and estimates the pet's emotions (e.g., stress levels) and health status (e.g., abnormal heart rates).

[0723] Step 7:

[0724] The server stores the analysis results in a database, which can then be combined with past data for statistical analysis and historical reference.

[0725] Step 8:

[0726] The server uses an emotion engine to recognize the user's emotions, which uses the user's facial expressions, voice, and input data.

[0727] Step 9:

[0728] The server adjusts the analysis results based on the user's perceived emotions, for example, providing more detailed information and suggestions if the user appears anxious.

[0729] Step 10:

[0730] The user device performs user authentication and acquires basic information about the pet. Once authentication is complete, the device requests data from the server.

[0731] Step 11:

[0732] The server receives a request from the user terminal and transmits the analysis results and the emotion engine's evaluation.

[0733] Step 12:

[0734] The user device displays the received analysis results and the emotion engine's evaluation to the user. The results are presented visually in easy-to-understand graphs and messages.

[0735] Step 13:

[0736] The user device will send push notifications as needed, including warnings if the pet is exhibiting high stress levels.

[0737] Step 14:

[0738] The user device uses the GPS function to acquire the pet's location information, which allows the pet's current location to be displayed on a map.

[0739] Step 15:

[0740] Users can check the analysis results and their pet's location information through the application, and can understand their pet's health condition and emotions in real time and take necessary measures.

[0741] Example 2

[0742] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0743] In today's busy lifestyles, it is difficult for pet owners to monitor their pets' health and emotions in real time and respond promptly to appropriate needs. As a result, pet owners may not notice a deterioration in their pet's health early and may not be able to provide appropriate care. There is also a need for systems that can reflect the owner's own emotional state to enable more appropriate responses. However, current technology does not provide a system that can simultaneously monitor the status of both the pet and the owner and provide appropriate information.

[0744] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0745] In this invention, the server includes: means connected to a pet device equipped with a biosensor that collects biometric data from the pet; means for receiving the biometric data from the pet device and performing preprocessing; means for analyzing the preprocessed data and using a generative AI model to estimate the pet's emotions and health status; means for storing the analysis results in a database; means for transmitting the analysis results to a user terminal and providing them to the user through an interface; means including an emotion engine that receives the user's emotion data and dynamically adjusts system notifications and alerts based on the analysis results; and means for the terminal to perform authentication, acquire, and display basic information about the pet. This makes it possible to monitor the pet's health status and the owner's emotional state in real time and provide the owner with individually customized appropriate information and responses.

[0746] A "biometric sensor" is a device for collecting physiological data from pets (e.g., heart rate, activity level, vocalizations, etc.).

[0747] A "pet device" is a data collection device attached to a pet, including biosensors and communication means.

[0748] "Preprocessing" is the process of cleaning the acquired data, removing noise, and preparing it in a format suitable for analysis.

[0749] A "generative AI model" is a machine learning model that analyzes pets' emotions and health status based on collected data.

[0750] "Analysis" refers to using a generative AI model based on pre-processed data to estimate a pet's emotions and health status.

[0751] "Database" means an electronic repository for storing analytical results and other related information.

[0752] A "user terminal" is an electronic device such as a smartphone or tablet that is used by a user.

[0753] "Interface" refers to the display screen and operating means used to provide information to the user.

[0754] An "emotion engine" is a software component that analyzes a user's emotional state and dynamically adjusts system behavior and notifications based on that.

[0755] "Authentication" is the process of verifying a user's identity in order to access a system.

[0756] This invention is a system that combines a smart device for pets, a dedicated application, and an emotion engine. The system aims to collect and analyze biometric data from pets to understand their health condition and emotions, and to provide appropriate information to users based on that data.

[0757] System configuration

[0758] Terminal part (pet device)

[0759] The terminal part is a device attached to a pet's collar and is equipped with biometric sensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as the pet's heart rate, activity level, and vocalizations in real time. The collected data is stored in a buffer and sent to a server using a secure communication protocol.

[0760] Examples:

[0761] A device attached to the dog's collar measures the dog's heart rate every second and sends the data to a server every 10 seconds.

[0762] Server part

[0763] The server receives the data sent from the device and first stores it in secure storage. It then preprocesses the data and analyzes the pet's biometric data using a generative AI model. The analysis includes data cleaning and noise removal. The preprocessed data is then analyzed by the AI ​​model to estimate the pet's emotions and health status. The analysis results are stored in a database and are ready to be provided to the user's device.

[0764] Examples:

[0765] The server receives the dog's heart rate data, cleans it to remove noise, and then inputs it into an AI model to determine whether the dog is stressed and stores the results in a database.

[0766] User terminal part

[0767] The user device is a smartphone or tablet, and receives analysis results from the server through a dedicated application. The user device visually displays the pet's health condition and emotions in real time. It can also analyze the user's actions and reactions using an emotion engine and provide feedback to the system. Authentication is completed when the user logs in to the app, and the latest analysis results are provided from the server.

[0768] Examples:

[0769] The user opens the app and checks their dog's latest heart rate and activity level data in real time. If the dog is stressed, the app will provide the user with details and advise them on what to do.

[0770] Emotion Engine

[0771] The emotion engine analyzes the user's camera footage and audio data in real time to recognize their emotions. Based on this information, the system dynamically adjusts notifications and alerts. For example, if the user is feeling anxious, it will provide detailed information about the condition of their pet.

[0772] Examples:

[0773] If the emotion engine detects a user's impatience while checking on their pet's condition, it will provide the user with advice on how to relax, along with detailed information about their pet's health.

[0774] Example prompts to be input to the generative AI model

[0775] "Example prompt for a generative AI model analyzing smart pet collar data: 'Analyze the dog's heart rate, activity level, and bark data to determine the dog's emotional state.'"

[0776] The entire system allows owners to monitor their pets' condition in real time, providing appropriate information and prompt responses, and also reflects the user's emotional state, providing personalized responses.

[0777] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0778] Step 1:

[0779] Sensor initialization

[0780] The device will initialize the heart rate sensor, accelerometer, microphone, etc. The firmware in the device will perform basic settings to ensure the sensors operate correctly.

[0781] Input: Sensor start signal

[0782] Output: The state at which the sensor starts collecting data

[0783] Specific operation: The heart rate sensor is set to measure the heart rate every second, and the microphone is set to capture the pet's cries in real time.

[0784] Step 2:

[0785] Data collection

[0786] The device uses biometric sensors to collect data such as your pet's heart rate, activity level, and sounds in real time.

[0787] Input: Pet's biological activity data

[0788] Output: Biological data (heart rate, activity level, vocalizations)

[0789] How it works: The heart rate sensor measures your pet's heart rate every second, the acceleration sensor records its activity as digital data, and the microphone records its barks as audio data.

[0790] Step 3:

[0791] Saving to the data buffer

[0792] The collected data is stored in a buffer at regular intervals. For example, a sensor collects data every second and stores it in a buffer for 10 seconds.

[0793] Input: Collected biometric data

[0794] Output: Buffered data

[0795] Specific operation: Heart rate data and activity data are stored every second for a short period (temporary storage). After 10 seconds, the data is prepared to be passed to the next step.

[0796] Step 4:

[0797] Packetizing and transmitting data

[0798] The data stored in the buffer is packetized and sent to the server using a secure communication protocol (e.g., TLS).

[0799] Input: Data stored in the buffer

[0800] Output: Data packets sent to the server

[0801] Specific operation: The data in the buffer is packetized in a certain format (e.g., JSON format) and sent to the server over the Internet using the TLS protocol.

[0802] Step 5:

[0803] Receiving data

[0804] The server receives the data packets sent from the terminal.

[0805] Input: Data packets sent from the device

[0806] Output: Biometric data stored on the server

[0807] Specific operation: The server receives the data packet via the communication protocol and stores it in its internal secure storage.

[0808] Step 6:

[0809] Performing preprocessing

[0810] The server performs preprocessing on the received data, which includes cleaning the data (filling in missing values, removing invalid values) and removing noise (applying filtering techniques).

[0811] Input: Biometric data stored on the server

[0812] Output: Preprocessed and clean data

[0813] Specific operation: Detects and removes or complements incomplete data from the incoming data, removing noise and creating a clean dataset.

[0814] Step 7:

[0815] Analysis using generative AI models

[0816] The preprocessed data is fed into a generative AI model (e.g., a model trained with TensorFlow or PyTorch) to analyze the pet's emotions and health status.

[0817] Input: Preprocessed clean data

[0818] Output: Analysis results (estimated information on pet's emotions and health status)

[0819] How it works: Clean biometric data is input into a generative AI model, and an inference algorithm is run to analyze the pet's emotions (e.g., stress, peace of mind) and health status (e.g., healthy, abnormal).

[0820] Step 8:

[0821] Data storage

[0822] The analysis results are saved in a database.

[0823] Input: Analysis results

[0824] Output: Analysis results stored in a database

[0825] Specific operation: The analysis results from the generative AI model are stored in a database, ready for further processing or use when needed.

[0826] Step 9:

[0827] Sending and displaying analysis results

[0828] The analysis results from the server are sent to the user's terminal and provided to the user through an interface.

[0829] Input: Analysis results stored in the database

[0830] Output: Analysis results sent to the user's device

[0831] Specific operation: The analysis results are sent to the user's device, allowing the user to view the data in the application.

[0832] Step 10:

[0833] User Emotion Recognition

[0834] The emotion engine receives the user's camera footage and audio data and analyzes the user's emotions.

[0835] Input: User's camera video and audio data

[0836] Output: Parsed user emotion data

[0837] Specific operation: While the user is using the application, the emotion engine analyzes camera footage and audio data in real time to estimate the user's emotional state.

[0838] Step 11:

[0839] Dynamic adjustment of notifications and alerts

[0840] Dynamically adjust system notifications and alerts based on recognized user emotions.

[0841] Input: Parsed user emotion data

[0842] Output: Dynamically adjusted notifications and alerts

[0843] Specific behavior: If the user feels anxious, detailed information about the pet's condition and appropriate advice will be automatically provided to the user.

[0844] (Application example 2)

[0845] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0846] In the food delivery industry, there is no way to monitor the health and emotions of delivery workers in real time, which has led to problems such as accidents and a decline in service quality due to overwork and stress.In addition, there is also the issue of difficulty in designing efficient delivery routes and responding to emergencies due to a lack of proper management of delivery workers.

[0847] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means connected to a delivery person device equipped with a biometric sensor, a means for receiving the delivery person's biometric data from the delivery person device and performing preprocessing, an analysis means using a generative AI model to analyze the preprocessed data and estimate the delivery person's emotions and health condition, a means for saving the analysis results in a database, a means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and a means with a GPS function for acquiring the location information of the delivery person during delivery and displaying it to the manager. This enables real-time monitoring of the health condition and emotions of delivery people, improving service quality and efficient operation management.

[0848] A "biometric sensor" is a device for collecting biometric data such as heart rate, activity level, voice, and location information.

[0849] A "delivery person device" is a terminal equipped with a built-in biometric sensor that collects biometric data from delivery persons in real time.

[0850] "Data preprocessing" refers to the process of removing noise and cleaning data from collected biometric data.

[0851] A "generative AI model" is an artificial intelligence model that analyzes collected and preprocessed biometric data to estimate the health status and emotions of delivery personnel.

[0852] A "database" is an information management system that systematically stores analyzed results and makes them accessible as needed.

[0853] A "user terminal" is a device (e.g., a smartphone) that receives analysis results and notifications and provides information to the user through an interface.

[0854] The "GPS function" is a location information system that acquires the current location of the delivery person and displays that information on the user terminal or administrator.

[0855] An "interface" refers to the screen and operating means for providing analysis results and notifications to the user through the user terminal.

[0856] A "delivery route" is a route designed to allow delivery personnel to make deliveries efficiently.

[0857] System configuration

[0858] The invention is a system that combines biometric sensors built into the delivery driver's smart device, a dedicated application, and a generative AI model. The entire system consists of four main parts:

[0859] 1. Terminal part (delivery person device):

[0860] The device is equipped with built-in biometric sensors, including a heart rate sensor, accelerometer, microphone, and GPS, which collect real-time data on the delivery person's heart rate, activity, voice, location, and more.

[0861] 2. Server part:

[0862] The server receives data sent from the device, performs preprocessing, and then analyzes the data using the generative AI model. The analysis results are stored in a database and sent to the user device as needed.

[0863] 3. User terminal part:

[0864] The user device (e.g., a smartphone) receives the analysis results from the server through the application and provides them to the user in real time. Feedback from the user's operations is also recorded and reflected in the system.

[0865] 4. GPS function part:

[0866] The system is equipped with a GPS function that acquires the location information of delivery personnel during deliveries and displays it in real time on the manager's device, enabling efficient optimization of delivery routes.

[0867] Implementation details

[0868] Hardware and software used

[0869] Hardware:

[0870] Smartwatches or smart glasses (e.g., Apple Watch, Google Glass)

[0871] Smartphone

[0872] Cloud servers (e.g., Amazon Web Services, Google Cloud)

[0873] software:

[0874] Data cleaning tools (e.g., Python's Pandas library)

[0875] Generative AI models (e.g., custom models using TensorFlow or PyTorch)

[0876] Data flow

[0877] The server receives biometric data collected from the delivery driver's smart device and stores it in secure storage. It then performs preprocessing, such as data cleaning and noise removal, and sends the preprocessed data to a generative AI model to analyze the delivery driver's health status and emotions.

[0878] The analysis results are stored in a database and sent to the user's device as needed. The user's device receives the analysis results and displays them to the user through an interface. In addition, the GPS function displays the delivery person's current location to the manager, supporting efficient operation management.

[0879] Specific examples

[0880] One food delivery service introduced a "delivery worker health monitoring system" to improve the working environment for delivery workers and enhance the quality of their service. When delivery workers wear smartwatches, their heart rate and activity levels are monitored in real time, and a generative AI model uses this data to analyze the worker's health and emotions. For example, if a delivery worker is determined to be fatigued, a notification is sent immediately via a smartphone application urging them to take a break. Meanwhile, managers can use the GPS function to check the worker's current location and provide instructions for the optimal delivery route.

[0881] Example prompts for generative AI models

[0882] Analyze the following sensor data to determine the health and emotions of the delivery driver.

[0883] The data format is heart rate, activity level, and audio.

[0884] Heart rate: 85 bpm, Activity level: 6000 steps, Voice: "I'm feeling a bit tired..."

[0885] Result (example):

[0886] Health condition: Slight fatigue

[0887] Emotion: Stress

[0888] Heart rate: [Heart rate data], Activity: [Activity data], Audio: [Audio data]

[0889] This system allows delivery personnel's health and emotions to be monitored in real time, enabling efficient operation management and improved service quality.

[0890] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0891] Step 1:

[0892] Data collection (device):

[0893] The terminal (delivery worker device) uses biometric sensors to collect biometric data such as the delivery worker's heart rate, activity level, voice, and location information in real time. This collected data is stored in a buffer at regular intervals. The input is the biometric data acquired by the terminal's sensors, and the output is the sensor data stored in the buffer.

[0894] Step 2:

[0895] Sending data (terminal):

[0896] The device packetizes the biometric data stored in the buffer and sends it to the server using a secure communication protocol. The input is the sensor data stored in the buffer, and the output is the packet data sent via the communication protocol. A security protocol (e.g., SSL / TLS) is used for this operation.

[0897] Step 3:

[0898] Data reception and preprocessing (server):

[0899] The server receives data sent from the device and stores it in secure storage. Next, it performs preprocessing such as data cleaning and noise removal on the received data. The input is the transmitted packet data, and the output is the cleaned data. Specific operations include filling in missing values ​​and correcting outliers.

[0900] Step 4:

[0901] Data analysis (server):

[0902] The server inputs the preprocessed data into a generative AI model to analyze the delivery driver's health status and emotions. The input is the preprocessed data, and the output is the analysis results. Specific operations include feeding the data forward to the model, estimating the results, and classifying emotions and health status.

[0903] Step 5:

[0904] Result storage and notification (server):

[0905] The server stores the generated analysis results in a database and sends them to the user device as needed. The input is the analysis results, and the output is the information stored in the database and a notification to the user device. Specific operations include writing to the database and sending push notifications.

[0906] Step 6:

[0907] Interface updates (user terminals):

[0908] The user terminal receives the analysis results sent from the server and updates the interface to display them to the user. The input is the analysis results sent from the server, and the output is the updated interface. Specific operations include updating the display screen and displaying a notification pop-up.

[0909] Step 7:

[0910] Acquiring and displaying GPS information (device and server):

[0911] The terminal periodically collects the delivery person's location information and sends it to the server. The server receives this location information and displays the current location on the administrator's terminal. The input is the GPS data sent from the terminal, and the output is the location information displayed on the administrator's terminal. Specific operations include obtaining the GPS data and plotting the location on a map.

[0912] The above are the specific processing steps for carrying out the present invention.

[0913] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0914] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0915] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0916] [Third embodiment]

[0917] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0918] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0919] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0920] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0921] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0922] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0923] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0924] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0925] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0926] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0927] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0928] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0929] System configuration

[0930] The invention is a system that includes a sensor built into a smart collar for pets and a dedicated application. The entire system consists of three main parts:

[0931] 1. Terminal part (pet device): This terminal is equipped with biosensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as your pet's heart rate, activity level, and barks in real time.

[0932] 2. Server part: The server receives data sent from the terminal, performs preprocessing, and then analyzes the data using the generative AI model. The analysis results are stored in a database and sent to the user terminal as needed.

[0933] 3. User device: The user device (e.g., smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It can also obtain pet location information based on user operations.

[0934] Program processing flow

[0935] 1. Sensor data collection and transmission (terminal part)

[0936] The device uses biometric sensors to continuously collect your pet's biometric data, including heart rate, activity level, and vocalizations.

[0937] The collected data is temporarily stored in a buffer. At regular intervals, the data in the buffer is packetized and sent to a server using a secure communication protocol.

[0938] 2. Data reception and analysis (server part)

[0939] The server receives the data sent from the terminal and stores it in a secure storage.

[0940] The received data is pre-processed to clean and denoise it, and then fed into a generative AI model to analyze the pet's emotions and health.

[0941] The analysis results are stored in a database and provided upon request from the user terminal.

[0942] 3. Notification to the user and provision of interface (user terminal part)

[0943] The user terminal performs authentication and acquires the user's pet information.

[0944] The analysis results are requested from the server and displayed to the user through an interface, showing the pet's health status and emotional changes in real time.

[0945] If necessary, the GPS function is used to obtain the pet's location information and display it to the user.

[0946] Specific examples

[0947] For example, if an owner wants to check on their pet (dog) while at work, the process would be as follows:

[0948] 1. Terminal part: Collects the dog's movements, heart rate, and barks.

[0949] 2. Server part: Receives the collected data and performs pre-processing (such as noise removal). Analyzes the data with a generative AI model and determines whether the dog is likely experiencing stress.

[0950] 3. User device: The analysis results are sent to the user via the app. The owner can open the app while at work, check that the dog is experiencing stress, and take appropriate action (e.g., contact a family member at home, remotely control a toy, etc.).

[0951] This system allows owners to keep track of their pet's health and emotions at all times and take any necessary action quickly.

[0952] The processing flow will be explained below.

[0953] Step 1:

[0954] The device uses biometric sensors (heart rate sensor, accelerometer, microphone) to collect data such as your pet's heart rate, movements, and sounds in real time.

[0955] Step 2:

[0956] The device stores the collected biometric data in a buffer at regular intervals (e.g., 1-second intervals). By storing the data in the buffer, data continuity is maintained.

[0957] Step 3:

[0958] The terminal packetizes the data in the buffer at regular intervals (for example, every 10 minutes) and transmits the data to the server using a secure communication protocol (for example, HTTPS).

[0959] Step 4:

[0960] The server first stores the received data in a secure storage, which prevents data loss.

[0961] Step 5:

[0962] The server preprocesses the stored data, which includes cleaning the data, filling in missing values, and removing noise to improve the accuracy of the analysis.

[0963] Step 6:

[0964] The server then inputs the preprocessed data into a generative AI model, which analyzes the data and estimates the pet's emotions (e.g., stress levels) and health status (e.g., abnormal heart rates).

[0965] Step 7:

[0966] The server stores the analysis results in a database, which allows for statistical analysis and historical reference in conjunction with past data.

[0967] Step 8:

[0968] The user terminal (application) performs user authentication and obtains basic information about the pet (species, age, sex, etc.). After authentication, it requests the necessary data from the server.

[0969] Step 9:

[0970] The server receives requests from the user's device and transmits the analysis results, which include information about the pet's current health condition and emotions.

[0971] Step 10:

[0972] The user terminal displays the received analysis results to the user in a visually easy-to-understand format, such as graphs or notification messages.

[0973] Step 11:

[0974] The user device will send push notifications as needed, for example, notifying the user immediately if their pet is experiencing high stress levels.

[0975] Step 12:

[0976] The user device uses the GPS function to acquire the pet's location information, which allows the pet's current location to be displayed on a map.

[0977] Step 13:

[0978] Users can check the analysis results and pet location information through the application, allowing them to understand their pet's condition in real time and take appropriate action.

[0979] Example 1

[0980] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0981] The challenge is to understand changes in a pet's health and emotions in real time and respond quickly. Even when the owner is away from their pet, it is necessary to monitor the pet's condition at the appropriate time. There is also a need for a system that can obtain pet location information and take necessary action immediately.

[0982] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0983] In this invention, the server includes means connected to an animal device equipped with a biosensor that collects the animal's biometric data, means for receiving the animal's biometric data from the animal device and performing preprocessing, means for analyzing the preprocessed data and using a generative AI model to estimate the animal's emotions and health status, means for storing the analysis results in a database, means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and means with a GPS function for acquiring the animal's location information and displaying it to the user. This makes it possible to monitor and understand changes in the pet's health status and emotions in real time and take prompt and appropriate action.

[0984] An "animal device" is a device equipped with sensors for collecting biometric data from an animal.

[0985] A "biosensor" is a sensor that detects and collects biological information such as an animal's heart rate, activity level, and vocalizations.

[0986] "Data preprocessing" refers to the process of preparing data before analysis, such as cleaning collected biological data and removing noise.

[0987] A "generative AI model" is an artificial intelligence model that analyzes collected data and is used to estimate the health and emotions of animals.

[0988] "Analysis means" refers to a device or system that uses a generative AI model to analyze pre-processed data and infer the animal's health and emotions.

[0989] A "database" is a system that stores and manages analysis results and other related data.

[0990] A "user terminal" is a device that receives analysis results and the current status of animals from the server and displays them to the user, and includes smartphones, tablets, etc.

[0991] "Interface" refers to the user interface used to display analysis results and the status of animals on the user's terminal.

[0992] The "GPS function" is a function that uses a satellite positioning system to obtain animal location information and display it on the user's device.

[0993] "Animal location information" is data indicating the current location of an animal obtained by the GPS function.

[0994] System configuration

[0995] This invention is a biosensor built into a smart device for animals, and a system for analyzing and managing it. In particular, it aims to monitor the animal's health and emotions in real time and notify the user. The system consists of three main parts:

[0996] 1. Terminal part (animal device):

[0997] Hardware: Heart rate sensors, accelerometers, and microphones built into animal collars, etc.

[0998] Software: A program that temporarily stores collected data in a buffer and sends the data to a server using a secure communication protocol (such as SSL / TLS).

[0999] 2. Server part:

[1000] Hardware: High-performance servers (e.g. virtual servers from cloud computing services).

[1001] Software: Programs for preprocessing, analyzing, and storing data, such as storage (e.g., cloud storage services), generative AI models (e.g., machine learning models), and databases (e.g., relational databases).

[1002] 3. User terminal part:

[1003] Hardware: Smartphones, tablets, etc.

[1004] Software: A program that receives analysis results and displays them to the user through a dedicated application. It also includes a function to obtain animal location information using GPS functionality and provide it to the user.

[1005] Basic system operation

[1006] The device collects data from the heart rate sensor, accelerometer, and microphone built into the animal's collar, temporarily stores this data in a buffer, periodically packetizes it, and transmits it to the server using the SSL / TLS protocol.

[1007] The server securely stores the received data and performs preprocessing, which includes data cleaning and noise removal. The preprocessed data is then fed into a generative AI model to analyze the animal's emotions and health status. The analysis results are stored in a database and, if necessary, sent to the user's device.

[1008] The user device requests the analysis results from the server and displays the received results to the user in real time. It can also use the GPS function to obtain animal location information and provide it to the user.

[1009] Specific examples

[1010] For example, if an owner wants to check on their pet (dog) while at work, the process would look like this:

[1011] 1. Terminal part: Collects the dog's heart rate, activity level, and barks. The heart rate sensor detects 80 bpm, the acceleration sensor detects low activity, and the microphone detects high-frequency barks.

[1012] 2. Server: Receives the collected data and performs preprocessing (such as noise removal). Analyzes the data using a generative AI model and determines whether the dog is experiencing stress.

[1013] 3. User terminal: The analysis results are sent to the user via a dedicated application. The user receives a notification such as "your dog is stressed" and can take appropriate action (such as contacting family members at home or remotely controlling a toy).

[1014] Example prompts to be input to the generative AI model

[1015] For example, you could input the following prompts into a generative AI model:

[1016] Analyze your dog's emotional and health status based on the following data collected from your dog:

[1017] Heart rate: 80 bpm

[1018] Activity level: low

[1019] Call frequency: High

[1020] Please briefly explain your dog's current condition.

[1021] This prompt allows the generative AI model to determine that the dog is stressed based on its high heart rate and low activity level, and provide useful information to the user.

[1022] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1023] Step 1:

[1024] Data collection (terminal part)

[1025] The device uses a heart rate sensor, accelerometer, and microphone attached to the animal's collar to collect data such as heart rate, activity, and vocalizations in real time. Specifically, the heart rate sensor measures the heart rate every second, the accelerometer measures the animal's activity on three axes, and the microphone analyzes the frequency and volume of the animal's vocalizations.

[1026] Input: Animal heart rate, activity level, and sounds

[1027] Output: Collected biological data (heart rate, activity level, vocalizations)

[1028] Step 2:

[1029] Data transmission (terminal part)

[1030] The terminal temporarily stores the collected data in a buffer and packets the data at regular intervals (for example, every minute). The packetized data is securely sent to the server using the SSL / TLS protocol. Specifically, the data is packetized and encrypted.

[1031] Input: Collected biometric data

[1032] Output: Packetized and encrypted data

[1033] Step 3:

[1034] Data reception and storage (server part)

[1035] The server securely receives data sent from the device using the SSL / TLS protocol. The received data is then temporarily stored in storage (e.g., a cloud storage service). Specifically, the data is deserialized and stored.

[1036] Input: Packetized and encrypted data

[1037] Output: Stored biometric data

[1038] Step 4:

[1039] Data preprocessing (server part)

[1040] The server performs preprocessing on the stored data, including cleaning and noise removal. Specific operations include imputing missing values ​​in heart rate data, removing spikes in activity data, and removing noise from bird sounds.

[1041] Input: Stored biometric data

[1042] Output: Preprocessed biometric data

[1043] Step 5:

[1044] Data analysis (server part)

[1045] The server inputs the preprocessed data into the generative AI model, which then analyzes the animal's health and emotions from the input data. Specifically, the AI ​​model analyzes the data and outputs a specific result, such as "the animal is feeling stressed." The analysis results are stored in a database.

[1046] Input: Preprocessed biometric data

[1047] Output: Analysis of the animal's health and emotions

[1048] Step 6:

[1049] Notification of analysis results (user terminal)

[1050] The user's device requests the analysis results from the server. Once the results are received, they are displayed to the user through a dedicated application. Specifically, the application sends a notification to the user, such as "The animal is feeling stressed," and also uses GPS to obtain the animal's location.

[1051] Input: Analysis results, animal location information

[1052] Output: Notification to the user, display of animal location information

[1053] Examples:

[1054] Example prompts to input to a generative AI model:

[1055] Analyze your pet's emotions and health using the following data collected from your pet:

[1056] Heart rate: 80 bpm

[1057] Activity level: low

[1058] Call frequency: High

[1059] Please provide a brief description of your pet's current condition.

[1060]

[1061] (Application example 1)

[1062] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1063] It is important to monitor the status of operating equipment used in factories and work sites in real time and manage its operation safely and efficiently. However, conventional monitoring systems are expensive and have low accuracy in detecting abnormal conditions. In addition, it is difficult to respond quickly when an abnormality occurs, resulting in reduced productivity and significant damage due to breakdowns. It is also difficult to obtain location information of operating equipment and manage it appropriately.

[1064] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1065] In this invention, the server includes means connected to an equipment device equipped with a sensor that collects status data of operating equipment, means for receiving the status data of the operating equipment from the equipment device and performing preprocessing, means for analyzing the preprocessed data and using a generative AI model to estimate anomalies in the operating equipment, means for saving the analysis results in a database, means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and means equipped with a GPS function for acquiring location information of the operating equipment and displaying it to the user. This enables real-time status monitoring of operating equipment, rapid anomaly detection, and location information management.

[1066] "Operating equipment" is equipment used in a factory or workplace that operates mechanically to accomplish a specific task.

[1067] "Status data" refers to information about the operating status and performance of equipment, including vibration, movement, temperature, etc.

[1068] An "equipment device" is a device that includes a sensor and a communication module that is attached to collect status data of an operating device.

[1069] "Preprocessing" refers to the process of performing initial processing such as cleaning the received data and removing noise.

[1070] A "generative AI model" is an artificial intelligence algorithm model used to infer equipment anomalies based on collected data.

[1071] An "analysis means" is a device or system that has the function of inputting preprocessed data into a generative AI model and obtaining analytical results.

[1072] A "database" is an information system that systematically stores data obtained through preprocessing and analysis, as well as analysis results, and facilitates search and reference.

[1073] A "user terminal" is a device that receives the analysis results and displays them to the user, and includes smartphones, tablets, and the like.

[1074] "Interface" refers to a display screen and input device designed to allow users to easily understand and operate analysis results.

[1075] "GPS function" is a function for obtaining geographical location information, and provides the user with the exact location of the operating device.

[1076] The embodiments of the present invention will be described in detail below.

[1077] System configuration

[1078] This invention is a system for monitoring the status of equipment operating in a factory. The entire system consists of three main parts:

[1079] 1. Terminal part (device for equipment)

[1080] Sensors attached to operating equipment are used to collect status data such as vibration, movement, and temperature in real time. The data collected from these sensors is temporarily stored in a buffer, packetized at regular intervals, and sent to a server using a secure communication protocol.

[1081] 2. Server part

[1082] The server receives data sent from the terminal and stores it in secure storage. The received data is preprocessed, including cleaning and noise removal. It is then input into a generative AI model to analyze abnormalities and status changes in the operating equipment. The analysis results are stored in a database and provided upon request from the user's terminal.

[1083] 3. User terminal part

[1084] The user device (e.g., a smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It is also possible to obtain the location information of operating devices based on user operations.

[1085] Hardware and software used

[1086] Hardware used:

[1087] Robot sensors (motion sensors, vibration sensors, temperature sensors)

[1088] Communication module (Wi-Fi / Bluetooth)

[1089] server

[1090] User devices (smartphones, tablets)

[1091] Software used:

[1092] Python (data collection and analysis)

[1093] TensorFlow (building and running generative AI models)

[1094] Django (Web server framework)

[1095] Firebase (database)

[1096] Pushbullet (send alerts)

[1097] System Operation

[1098] Data collection and transmission

[1099] At the terminal section, sensors attached to the equipment device collect status data of the operating equipment, which is then sent to the server via a secure communication protocol.

[1100] Data analysis

[1101] The server preprocesses the received data and removes noise. The data is then input into a generative AI model to estimate abnormalities in the operating equipment. The analysis results are stored in a database and sent to the user's device as needed.

[1102] User Notification

[1103] The analysis results are sent to the user's device via the application. The user can use the application to check the status of the equipment in operation and take appropriate action if an abnormality occurs. The GPS function can also be used to obtain the location information of the equipment in operation.

[1104] Specific examples

[1105] For example, if a critical piece of equipment in a factory exhibits abnormal vibrations, the following steps will take place:

[1106] 1. Terminal part: Sensors collect information on the device's movement, vibration, and temperature.

[1107] 2. Server part: Receives collected data and performs preprocessing (such as noise removal). The data is analyzed using a generative AI model to detect anomalies.

[1108] 3. User device: The analysis results are sent to the user via the application. The user can open the app, check the abnormality warning, and take prompt action.

[1109] Example prompt sentence:

[1110] The system applies sensors built into smart pet collars to factory robots, creating an application that monitors the robot's movements, vibrations, and temperature in real time and sends an alert if an abnormality is detected.

[1111] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1112] Step 1:

[1113] The terminal uses sensors attached to the operating equipment to collect status data such as vibration, movement, and temperature in real time. The collected data is temporarily stored in a buffer. Specifically, each sensor acquires data every second and stores it in memory. The input is raw data from the sensor, and the output is the temporary data in the buffer.

[1114] Step 2:

[1115] The device periodically converts the data in the buffer into packets and sends them to the server using a secure communication protocol (e.g., SSL / TLS). At this stage, the data is still raw and pure sensor data is being sent. The input is the buffered data, and the output is the data to be sent to the server. Specifically, each time a certain amount of data accumulates, it is converted into packets and sent to the server via the network.

[1116] Step 3:

[1117] The server receives data sent from the terminal and stores it in secure storage (e.g., a cloud storage system). This storage minimizes the risk of data loss. The input is the raw data sent from the terminal, and the output is the data stored in the storage. Specifically, the server receives data through the network interface and writes it to a database.

[1118] Step 4:

[1119] The server preprocesses the received data, cleaning and denoising it. At this stage, noise data and outliers are removed. The input is raw data stored in storage, and the output is preprocessed clean data. Specifically, a data filtering algorithm is used to extract only valid data.

[1120] Step 5:

[1121] The server inputs the preprocessed data into a generative AI model to analyze abnormalities and state changes in the operating equipment. The generative AI model (using TensorFlow, for example) infers abnormalities in the operating equipment and outputs the analysis results. The input is preprocessed clean data, and the output is the analysis results. Specifically, the server feeds data into the AI ​​model and generates inference results.

[1122] Step 6:

[1123] The server stores the analysis results in a database, which can then be used for future reference or as historical data. The input is the analysis results, and the output is the result data stored in the database. Specifically, the analysis results are written to the database as structured data.

[1124] Step 7:

[1125] The server sends the analysis results in response to a request from the user terminal. The user terminal receives these analysis results and displays them to the user through a GUI (graphical user interface). The input is the analysis results retrieved from the database, and the output is the display data on the user terminal. Specifically, the data is sent to the client via a REST API.

[1126] Step 8:

[1127] The user terminal obtains the location information of the pet device and displays it to the user when specified. This location information is obtained using the GPS function. The input is GPS data, and the output is the location information displayed to the user. Specifically, the terminal obtains the location information from the GPS module and updates the display on the user interface.

[1128] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1129] System configuration

[1130] This invention is a system that combines biosensors built into a smart collar for pets, a dedicated application, and an emotion engine. The whole system consists of four main parts:

[1131] 1. Terminal part (pet device): This terminal is equipped with biosensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as your pet's heart rate, activity level, and barks in real time.

[1132] 2. Server: The server receives data sent from the device, performs preprocessing, and then analyzes the data using a generative AI model. Furthermore, the server incorporates an emotion engine to recognize the user's emotions and analyze the user's reaction to the pet's state. The analysis results are stored in a database and sent to the user's device as needed.

[1133] 3. User device: The user device (e.g., smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It also analyzes the user's operations and reactions using an emotion engine and provides feedback to the system.

[1134] 4. Emotion engine: The emotion engine recognizes emotions from the user's facial expressions, voice, and input data, and reflects the analysis results throughout the system. This allows for dynamic interface and notifications to be provided according to the user's emotional patterns.

[1135] Program processing flow

[1136] 1. Sensor data collection and transmission (terminal part)

[1137] The device uses biometric sensors to continuously collect your pet's biological data, including heart rate, activity level, and vocalizations, in real time.

[1138] The collected data is stored in a buffer at regular intervals, packetized, and sent to a server using a secure communication protocol.

[1139] 2. Data reception and analysis (server part)

[1140] The server first stores the received data in secure storage and pre-processes it, which includes cleaning and denoising the data.

[1141] The pre-processed data is input into a generative AI model to analyze the pet's emotions and health status.

[1142] The analysis results are stored in a database and are ready to be provided to the user terminal.

[1143] 3. User Emotion Recognition and Response (Server and Emotion Engine)

[1144] The server uses an emotion engine to recognize the user's emotions and takes the user's reactions into account in the analysis results.

[1145] The system dynamically adjusts notifications and alerts depending on the user's perceived emotions, for example providing detailed health information about a pet if the user appears anxious.

[1146] 4. Notification to the user and provision of interface (user terminal part)

[1147] The user terminal performs authentication and acquires basic information about the pet.

[1148] The analysis results and the emotion engine's evaluation are received from the server and displayed to the user.

[1149] Send push notifications when needed and provide an interface that dynamically adjusts to specific situations.

[1150] Specific examples

[1151] Scenario: An owner wants to monitor the status of their pet (dog) while at work:

[1152] 1. Terminal part: Collects the dog's movements, heart rate, and barks. The collected data is periodically sent to the server.

[1153] 2. Server part: The server receives the data and performs preprocessing. It analyzes the data using a generative AI model and determines that the dog is stressed. The emotion engine analyzes the user's facial expressions from the camera and determines that the user is anxious.

[1154] 3. User terminal: The analysis results and the emotion engine's evaluation are notified to the user through the application. The user opens the application and checks whether the dog is stressed and the cause (e.g., lack of exercise or external stimuli). The system then provides detailed information and advice to ease the user's anxiety.

[1155] This system allows owners to understand their pet's health and emotions in real time, while also recognizing their own emotions, allowing for individually tailored responses.

[1156] The processing flow will be explained below.

[1157] Step 1:

[1158] The device uses biosensors (heart rate sensor, accelerometer, microphone) to collect data such as your pet's heart rate, activity level, and cries in real time.

[1159] Step 2:

[1160] The device stores the collected biometric data in a buffer at regular intervals (e.g., 1-second intervals). By storing the data in the buffer, data continuity is maintained.

[1161] Step 3:

[1162] The terminal packetizes the data in the buffer at regular intervals (for example, every 10 minutes) and transmits the data to the server using a secure communication protocol (for example, HTTPS).

[1163] Step 4:

[1164] The server first stores the received data in a secure storage, which prevents data loss.

[1165] Step 5:

[1166] The server preprocesses the stored data, which includes cleaning the data, filling in missing values, and removing noise to improve the accuracy of the analysis.

[1167] Step 6:

[1168] The server then inputs the preprocessed data into a generative AI model, which analyzes the data and estimates the pet's emotions (e.g., stress levels) and health status (e.g., abnormal heart rates).

[1169] Step 7:

[1170] The server stores the analysis results in a database, which can then be combined with past data for statistical analysis and historical reference.

[1171] Step 8:

[1172] The server uses an emotion engine to recognize the user's emotions, which uses the user's facial expressions, voice, and input data.

[1173] Step 9:

[1174] The server adjusts the analysis results based on the user's perceived emotions, for example, providing more detailed information and suggestions if the user appears anxious.

[1175] Step 10:

[1176] The user device performs user authentication and acquires basic information about the pet. Once authentication is complete, the device requests data from the server.

[1177] Step 11:

[1178] The server receives a request from the user terminal and transmits the analysis results and the emotion engine's evaluation.

[1179] Step 12:

[1180] The user device displays the received analysis results and the emotion engine's evaluation to the user. The results are presented visually in easy-to-understand graphs and messages.

[1181] Step 13:

[1182] The user device will send push notifications as needed, including warnings if the pet is exhibiting high stress levels.

[1183] Step 14:

[1184] The user device uses the GPS function to acquire the pet's location information, which allows the pet's current location to be displayed on a map.

[1185] Step 15:

[1186] Users can check the analysis results and their pet's location information through the application, and can understand their pet's health condition and emotions in real time and take necessary measures.

[1187] Example 2

[1188] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1189] In today's busy lifestyles, it is difficult for pet owners to monitor their pets' health and emotions in real time and respond promptly to appropriate needs. As a result, pet owners may not notice a deterioration in their pet's health early and may not be able to provide appropriate care. There is also a need for systems that can reflect the owner's own emotional state to enable more appropriate responses. However, current technology does not provide a system that can simultaneously monitor the status of both the pet and the owner and provide appropriate information.

[1190] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1191] In this invention, the server includes: means connected to a pet device equipped with a biosensor that collects biometric data from the pet; means for receiving the biometric data from the pet device and performing preprocessing; means for analyzing the preprocessed data and using a generative AI model to estimate the pet's emotions and health status; means for storing the analysis results in a database; means for transmitting the analysis results to a user terminal and providing them to the user through an interface; means including an emotion engine that receives the user's emotion data and dynamically adjusts system notifications and alerts based on the analysis results; and means for the terminal to perform authentication, acquire, and display basic information about the pet. This makes it possible to monitor the pet's health status and the owner's emotional state in real time and provide the owner with individually customized appropriate information and responses.

[1192] A "biometric sensor" is a device for collecting physiological data from pets (e.g., heart rate, activity level, vocalizations, etc.).

[1193] A "pet device" is a data collection device attached to a pet, including biosensors and communication means.

[1194] "Preprocessing" is the process of cleaning the acquired data, removing noise, and preparing it in a format suitable for analysis.

[1195] A "generative AI model" is a machine learning model that analyzes pets' emotions and health status based on collected data.

[1196] "Analysis" refers to using a generative AI model based on pre-processed data to estimate a pet's emotions and health status.

[1197] "Database" means an electronic repository for storing analytical results and other related information.

[1198] A "user terminal" is an electronic device such as a smartphone or tablet that is used by a user.

[1199] "Interface" refers to the display screen and operating means used to provide information to the user.

[1200] An "emotion engine" is a software component that analyzes a user's emotional state and dynamically adjusts system behavior and notifications based on that.

[1201] "Authentication" is the process of verifying a user's identity in order to access a system.

[1202] This invention is a system that combines a smart device for pets, a dedicated application, and an emotion engine. The system aims to collect and analyze biometric data from pets to understand their health condition and emotions, and to provide appropriate information to users based on that data.

[1203] System configuration

[1204] Terminal part (pet device)

[1205] The terminal part is a device attached to a pet's collar and is equipped with biometric sensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as the pet's heart rate, activity level, and vocalizations in real time. The collected data is stored in a buffer and sent to a server using a secure communication protocol.

[1206] Examples:

[1207] A device attached to the dog's collar measures the dog's heart rate every second and sends the data to a server every 10 seconds.

[1208] Server part

[1209] The server receives the data sent from the device and first stores it in secure storage. It then preprocesses the data and analyzes the pet's biometric data using a generative AI model. The analysis includes data cleaning and noise removal. The preprocessed data is then analyzed by the AI ​​model to estimate the pet's emotions and health status. The analysis results are stored in a database and are ready to be provided to the user's device.

[1210] Examples:

[1211] The server receives the dog's heart rate data, cleans it to remove noise, and then inputs it into an AI model to determine whether the dog is stressed and stores the results in a database.

[1212] User terminal part

[1213] The user device is a smartphone or tablet, and receives analysis results from the server through a dedicated application. The user device visually displays the pet's health condition and emotions in real time. It can also analyze the user's actions and reactions using an emotion engine and provide feedback to the system. Authentication is completed when the user logs in to the app, and the latest analysis results are provided from the server.

[1214] Examples:

[1215] The user opens the app and checks their dog's latest heart rate and activity level data in real time. If the dog is stressed, the app will provide the user with details and advise them on what to do.

[1216] Emotion Engine

[1217] The emotion engine analyzes the user's camera footage and audio data in real time to recognize their emotions. Based on this information, the system dynamically adjusts notifications and alerts. For example, if the user is feeling anxious, it will provide detailed information about the condition of their pet.

[1218] Examples:

[1219] If the emotion engine detects a user's impatience while checking on their pet's condition, it will provide the user with advice on how to relax, along with detailed information about their pet's health.

[1220] Example prompts to be input to the generative AI model

[1221] "Example prompt for a generative AI model analyzing smart pet collar data: 'Analyze the dog's heart rate, activity level, and bark data to determine the dog's emotional state.'"

[1222] The entire system allows owners to monitor their pets' condition in real time, providing appropriate information and prompt responses, and also reflects the user's emotional state, providing personalized responses.

[1223] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1224] Step 1:

[1225] Sensor initialization

[1226] The device will initialize the heart rate sensor, accelerometer, microphone, etc. The firmware in the device will perform basic settings to ensure the sensors operate correctly.

[1227] Input: Sensor start signal

[1228] Output: The state at which the sensor starts collecting data

[1229] Specific operation: The heart rate sensor is set to measure the heart rate every second, and the microphone is set to capture the pet's cries in real time.

[1230] Step 2:

[1231] Data collection

[1232] The device uses biometric sensors to collect data such as your pet's heart rate, activity level, and sounds in real time.

[1233] Input: Pet's biological activity data

[1234] Output: Biological data (heart rate, activity level, vocalizations)

[1235] How it works: The heart rate sensor measures your pet's heart rate every second, the acceleration sensor records its activity as digital data, and the microphone records its barks as audio data.

[1236] Step 3:

[1237] Saving to the data buffer

[1238] The collected data is stored in a buffer at regular intervals. For example, a sensor collects data every second and stores it in a buffer for 10 seconds.

[1239] Input: Collected biometric data

[1240] Output: Buffered data

[1241] Specific operation: Heart rate data and activity data are stored every second for a short period (temporary storage). After 10 seconds, the data is prepared to be passed to the next step.

[1242] Step 4:

[1243] Packetizing and transmitting data

[1244] The data stored in the buffer is packetized and sent to the server using a secure communication protocol (e.g., TLS).

[1245] Input: Data stored in the buffer

[1246] Output: Data packets sent to the server

[1247] Specific operation: The data in the buffer is packetized in a certain format (e.g., JSON format) and sent to the server over the Internet using the TLS protocol.

[1248] Step 5:

[1249] Receiving data

[1250] The server receives the data packets sent from the terminal.

[1251] Input: Data packets sent from the device

[1252] Output: Biometric data stored on the server

[1253] Specific operation: The server receives the data packet via the communication protocol and stores it in its internal secure storage.

[1254] Step 6:

[1255] Performing preprocessing

[1256] The server performs preprocessing on the received data, which includes cleaning the data (filling in missing values, removing invalid values) and removing noise (applying filtering techniques).

[1257] Input: Biometric data stored on the server

[1258] Output: Preprocessed and clean data

[1259] Specific operation: Detects and removes or complements incomplete data from the incoming data, removing noise and creating a clean dataset.

[1260] Step 7:

[1261] Analysis using generative AI models

[1262] The preprocessed data is fed into a generative AI model (e.g., a model trained with TensorFlow or PyTorch) to analyze the pet's emotions and health status.

[1263] Input: Preprocessed clean data

[1264] Output: Analysis results (estimated information on pet's emotions and health status)

[1265] How it works: Clean biometric data is input into a generative AI model, and an inference algorithm is run to analyze the pet's emotions (e.g., stress, peace of mind) and health status (e.g., healthy, abnormal).

[1266] Step 8:

[1267] Data storage

[1268] The analysis results are saved in a database.

[1269] Input: Analysis results

[1270] Output: Analysis results stored in a database

[1271] Specific operation: The analysis results from the generative AI model are stored in a database, ready for further processing or use when needed.

[1272] Step 9:

[1273] Sending and displaying analysis results

[1274] The analysis results from the server are sent to the user's terminal and provided to the user through an interface.

[1275] Input: Analysis results stored in the database

[1276] Output: Analysis results sent to the user's device

[1277] Specific operation: The analysis results are sent to the user's device, allowing the user to view the data in the application.

[1278] Step 10:

[1279] User Emotion Recognition

[1280] The emotion engine receives the user's camera footage and audio data and analyzes the user's emotions.

[1281] Input: User's camera video and audio data

[1282] Output: Parsed user emotion data

[1283] Specific operation: While the user is using the application, the emotion engine analyzes camera footage and audio data in real time to estimate the user's emotional state.

[1284] Step 11:

[1285] Dynamic adjustment of notifications and alerts

[1286] Dynamically adjust system notifications and alerts based on recognized user emotions.

[1287] Input: Parsed user emotion data

[1288] Output: Dynamically adjusted notifications and alerts

[1289] Specific behavior: If the user feels anxious, detailed information about the pet's condition and appropriate advice will be automatically provided to the user.

[1290] (Application example 2)

[1291] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1292] In the food delivery industry, there is no way to monitor the health and emotions of delivery workers in real time, which has led to problems such as accidents and a decline in service quality due to overwork and stress.In addition, there is also the issue of difficulty in designing efficient delivery routes and responding to emergencies due to a lack of proper management of delivery workers.

[1293] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means connected to a delivery person device equipped with a biometric sensor, a means for receiving the delivery person's biometric data from the delivery person device and performing preprocessing, an analysis means using a generative AI model to analyze the preprocessed data and estimate the delivery person's emotions and health condition, a means for saving the analysis results in a database, a means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and a means with a GPS function for acquiring the location information of the delivery person during delivery and displaying it to the manager. This enables real-time monitoring of the health condition and emotions of delivery people, improving service quality and efficient operation management.

[1294] A "biometric sensor" is a device for collecting biometric data such as heart rate, activity level, voice, and location information.

[1295] A "delivery person device" is a terminal equipped with a built-in biometric sensor that collects biometric data from delivery persons in real time.

[1296] "Data preprocessing" refers to the process of removing noise and cleaning data from collected biometric data.

[1297] A "generative AI model" is an artificial intelligence model that analyzes collected and preprocessed biometric data to estimate the health status and emotions of delivery personnel.

[1298] A "database" is an information management system that systematically stores analyzed results and makes them accessible as needed.

[1299] A "user terminal" is a device (e.g., a smartphone) that receives analysis results and notifications and provides information to the user through an interface.

[1300] The "GPS function" is a location information system that acquires the current location of the delivery person and displays that information on the user terminal or administrator.

[1301] An "interface" refers to the screen and operating means for providing analysis results and notifications to the user through the user terminal.

[1302] A "delivery route" is a route designed to allow delivery personnel to make deliveries efficiently.

[1303] System configuration

[1304] The invention is a system that combines biometric sensors built into the delivery driver's smart device, a dedicated application, and a generative AI model. The entire system consists of four main parts:

[1305] 1. Terminal part (delivery person device):

[1306] The device is equipped with built-in biometric sensors, including a heart rate sensor, accelerometer, microphone, and GPS, which collect real-time data on the delivery person's heart rate, activity, voice, location, and more.

[1307] 2. Server part:

[1308] The server receives data sent from the device, performs preprocessing, and then analyzes the data using the generative AI model. The analysis results are stored in a database and sent to the user device as needed.

[1309] 3. User terminal part:

[1310] The user device (e.g., a smartphone) receives the analysis results from the server through the application and provides them to the user in real time. Feedback from the user's operations is also recorded and reflected in the system.

[1311] 4. GPS function part:

[1312] The system is equipped with a GPS function that acquires the location information of delivery personnel during deliveries and displays it in real time on the manager's device, enabling efficient optimization of delivery routes.

[1313] Implementation details

[1314] Hardware and software used

[1315] Hardware:

[1316] Smartwatches or smart glasses (e.g., Apple Watch, Google Glass)

[1317] Smartphone

[1318] Cloud servers (e.g., Amazon Web Services, Google Cloud)

[1319] software:

[1320] Data cleaning tools (e.g., Python's Pandas library)

[1321] Generative AI models (e.g., custom models using TensorFlow or PyTorch)

[1322] Data flow

[1323] The server receives biometric data collected from the delivery driver's smart device and stores it in secure storage. It then performs preprocessing, such as data cleaning and noise removal, and sends the preprocessed data to a generative AI model to analyze the delivery driver's health status and emotions.

[1324] The analysis results are stored in a database and sent to the user's device as needed. The user's device receives the analysis results and displays them to the user through an interface. In addition, the GPS function displays the delivery person's current location to the manager, supporting efficient operation management.

[1325] Specific examples

[1326] One food delivery service introduced a "delivery worker health monitoring system" to improve the working environment for delivery workers and enhance the quality of their service. When delivery workers wear smartwatches, their heart rate and activity levels are monitored in real time, and a generative AI model uses this data to analyze the worker's health and emotions. For example, if a delivery worker is determined to be fatigued, a notification is sent immediately via a smartphone application urging them to take a break. Meanwhile, managers can use the GPS function to check the worker's current location and provide instructions for the optimal delivery route.

[1327] Example prompts for generative AI models

[1328] Analyze the following sensor data to determine the health and emotions of the delivery driver.

[1329] The data format is heart rate, activity level, and audio.

[1330] Heart rate: 85 bpm, Activity level: 6000 steps, Voice: "I'm feeling a bit tired..."

[1331] Result (example):

[1332] Health condition: Slight fatigue

[1333] Emotion: Stress

[1334] Heart rate: [Heart rate data], Activity: [Activity data], Audio: [Audio data]

[1335] This system allows delivery personnel's health and emotions to be monitored in real time, enabling efficient operation management and improved service quality.

[1336] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1337] Step 1:

[1338] Data collection (device):

[1339] The terminal (delivery worker device) uses biometric sensors to collect biometric data such as the delivery worker's heart rate, activity level, voice, and location information in real time. This collected data is stored in a buffer at regular intervals. The input is the biometric data acquired by the terminal's sensors, and the output is the sensor data stored in the buffer.

[1340] Step 2:

[1341] Sending data (terminal):

[1342] The device packetizes the biometric data stored in the buffer and sends it to the server using a secure communication protocol. The input is the sensor data stored in the buffer, and the output is the packet data sent via the communication protocol. A security protocol (e.g., SSL / TLS) is used for this operation.

[1343] Step 3:

[1344] Data reception and preprocessing (server):

[1345] The server receives data sent from the device and stores it in secure storage. Next, it performs preprocessing such as data cleaning and noise removal on the received data. The input is the transmitted packet data, and the output is the cleaned data. Specific operations include filling in missing values ​​and correcting outliers.

[1346] Step 4:

[1347] Data analysis (server):

[1348] The server inputs the preprocessed data into a generative AI model to analyze the delivery driver's health status and emotions. The input is the preprocessed data, and the output is the analysis results. Specific operations include feeding the data forward to the model, estimating the results, and classifying emotions and health status.

[1349] Step 5:

[1350] Result storage and notification (server):

[1351] The server stores the generated analysis results in a database and sends them to the user device as needed. The input is the analysis results, and the output is the information stored in the database and a notification to the user device. Specific operations include writing to the database and sending push notifications.

[1352] Step 6:

[1353] Interface updates (user terminals):

[1354] The user terminal receives the analysis results sent from the server and updates the interface to display them to the user. The input is the analysis results sent from the server, and the output is the updated interface. Specific operations include updating the display screen and displaying a notification pop-up.

[1355] Step 7:

[1356] Acquiring and displaying GPS information (device and server):

[1357] The terminal periodically collects the delivery person's location information and sends it to the server. The server receives this location information and displays the current location on the administrator's terminal. The input is the GPS data sent from the terminal, and the output is the location information displayed on the administrator's terminal. Specific operations include obtaining the GPS data and plotting the location on a map.

[1358] The above are the specific processing steps for carrying out the present invention.

[1359] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1360] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1361] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1362] [Fourth embodiment]

[1363] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1364] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1365] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1366] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1367] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1368] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1369] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1370] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1371] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1372] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1373] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1374] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1375] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1376] System configuration

[1377] The invention is a system that includes a sensor built into a smart collar for pets and a dedicated application. The entire system consists of three main parts:

[1378] 1. Terminal part (pet device): This terminal is equipped with biosensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as your pet's heart rate, activity level, and barks in real time.

[1379] 2. Server part: The server receives data sent from the terminal, performs preprocessing, and then analyzes the data using the generative AI model. The analysis results are stored in a database and sent to the user terminal as needed.

[1380] 3. User device: The user device (e.g., smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It can also obtain pet location information based on user operations.

[1381] Program processing flow

[1382] 1. Sensor data collection and transmission (terminal part)

[1383] The device uses biometric sensors to continuously collect your pet's biometric data, including heart rate, activity level, and vocalizations.

[1384] The collected data is temporarily stored in a buffer. At regular intervals, the data in the buffer is packetized and sent to a server using a secure communication protocol.

[1385] 2. Data reception and analysis (server part)

[1386] The server receives the data sent from the terminal and stores it in a secure storage.

[1387] The received data is pre-processed to clean and denoise it, and then fed into a generative AI model to analyze the pet's emotions and health.

[1388] The analysis results are stored in a database and provided upon request from the user terminal.

[1389] 3. Notification to the user and provision of interface (user terminal part)

[1390] The user terminal performs authentication and acquires the user's pet information.

[1391] The analysis results are requested from the server and displayed to the user through an interface, showing the pet's health status and emotional changes in real time.

[1392] If necessary, the GPS function is used to obtain the pet's location information and display it to the user.

[1393] Specific examples

[1394] For example, if an owner wants to check on their pet (dog) while at work, the process would be as follows:

[1395] 1. Terminal part: Collects the dog's movements, heart rate, and barks.

[1396] 2. Server part: Receives the collected data and performs pre-processing (such as noise removal). Analyzes the data with a generative AI model and determines whether the dog is likely experiencing stress.

[1397] 3. User device: The analysis results are sent to the user via the app. The owner can open the app while at work, check that the dog is experiencing stress, and take appropriate action (e.g., contact a family member at home, remotely control a toy, etc.).

[1398] This system allows owners to keep track of their pet's health and emotions at all times and take any necessary action quickly.

[1399] The processing flow will be explained below.

[1400] Step 1:

[1401] The device uses biometric sensors (heart rate sensor, accelerometer, microphone) to collect data such as your pet's heart rate, movements, and sounds in real time.

[1402] Step 2:

[1403] The device stores the collected biometric data in a buffer at regular intervals (e.g., 1-second intervals). By storing the data in the buffer, data continuity is maintained.

[1404] Step 3:

[1405] The terminal packetizes the data in the buffer at regular intervals (for example, every 10 minutes) and transmits the data to the server using a secure communication protocol (for example, HTTPS).

[1406] Step 4:

[1407] The server first stores the received data in a secure storage, which prevents data loss.

[1408] Step 5:

[1409] The server preprocesses the stored data, which includes cleaning the data, filling in missing values, and removing noise to improve the accuracy of the analysis.

[1410] Step 6:

[1411] The server then inputs the preprocessed data into a generative AI model, which analyzes the data and estimates the pet's emotions (e.g., stress levels) and health status (e.g., abnormal heart rates).

[1412] Step 7:

[1413] The server stores the analysis results in a database, which allows for statistical analysis and historical reference in conjunction with past data.

[1414] Step 8:

[1415] The user terminal (application) performs user authentication and obtains basic information about the pet (species, age, sex, etc.). After authentication, it requests the necessary data from the server.

[1416] Step 9:

[1417] The server receives requests from the user's device and transmits the analysis results, which include information about the pet's current health condition and emotions.

[1418] Step 10:

[1419] The user terminal displays the received analysis results to the user in a visually easy-to-understand format, such as graphs or notification messages.

[1420] Step 11:

[1421] The user device will send push notifications as needed, for example, notifying the user immediately if their pet is experiencing high stress levels.

[1422] Step 12:

[1423] The user device uses the GPS function to acquire the pet's location information, which allows the pet's current location to be displayed on a map.

[1424] Step 13:

[1425] Users can check the analysis results and pet location information through the application, allowing them to understand their pet's condition in real time and take appropriate action.

[1426] Example 1

[1427] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1428] The challenge is to understand changes in a pet's health and emotions in real time and respond quickly. Even when the owner is away from their pet, it is necessary to monitor the pet's condition at the appropriate time. There is also a need for a system that can obtain pet location information and take necessary action immediately.

[1429] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1430] In this invention, the server includes means connected to an animal device equipped with a biosensor that collects the animal's biometric data, means for receiving the animal's biometric data from the animal device and performing preprocessing, means for analyzing the preprocessed data and using a generative AI model to estimate the animal's emotions and health status, means for storing the analysis results in a database, means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and means with a GPS function for acquiring the animal's location information and displaying it to the user. This makes it possible to monitor and understand changes in the pet's health status and emotions in real time and take prompt and appropriate action.

[1431] An "animal device" is a device equipped with sensors for collecting biometric data from an animal.

[1432] A "biosensor" is a sensor that detects and collects biological information such as an animal's heart rate, activity level, and vocalizations.

[1433] "Data preprocessing" refers to the process of preparing data before analysis, such as cleaning collected biological data and removing noise.

[1434] A "generative AI model" is an artificial intelligence model that analyzes collected data and is used to estimate the health and emotions of animals.

[1435] "Analysis means" refers to a device or system that uses a generative AI model to analyze pre-processed data and infer the animal's health and emotions.

[1436] A "database" is a system that stores and manages analysis results and other related data.

[1437] A "user terminal" is a device that receives analysis results and the current status of animals from the server and displays them to the user, and includes smartphones, tablets, etc.

[1438] "Interface" refers to the user interface used to display analysis results and the status of animals on the user's terminal.

[1439] The "GPS function" is a function that uses a satellite positioning system to obtain animal location information and display it on the user's device.

[1440] "Animal location information" is data indicating the current location of an animal obtained by the GPS function.

[1441] System configuration

[1442] This invention is a biosensor built into a smart device for animals, and a system for analyzing and managing it. In particular, it aims to monitor the animal's health and emotions in real time and notify the user. The system consists of three main parts:

[1443] 1. Terminal part (animal device):

[1444] Hardware: Heart rate sensors, accelerometers, and microphones built into animal collars, etc.

[1445] Software: A program that temporarily stores collected data in a buffer and sends the data to a server using a secure communication protocol (such as SSL / TLS).

[1446] 2. Server part:

[1447] Hardware: High-performance servers (e.g. virtual servers from cloud computing services).

[1448] Software: Programs for preprocessing, analyzing, and storing data, such as storage (e.g., cloud storage services), generative AI models (e.g., machine learning models), and databases (e.g., relational databases).

[1449] 3. User terminal part:

[1450] Hardware: Smartphones, tablets, etc.

[1451] Software: A program that receives analysis results and displays them to the user through a dedicated application. It also includes a function to obtain animal location information using GPS functionality and provide it to the user.

[1452] Basic system operation

[1453] The device collects data from the heart rate sensor, accelerometer, and microphone built into the animal's collar, temporarily stores this data in a buffer, periodically packetizes it, and transmits it to the server using the SSL / TLS protocol.

[1454] The server securely stores the received data and performs preprocessing, which includes data cleaning and noise removal. The preprocessed data is then fed into a generative AI model to analyze the animal's emotions and health status. The analysis results are stored in a database and, if necessary, sent to the user's device.

[1455] The user device requests the analysis results from the server and displays the received results to the user in real time. It can also use the GPS function to obtain animal location information and provide it to the user.

[1456] Specific examples

[1457] For example, if an owner wants to check on their pet (dog) while at work, the process would look like this:

[1458] 1. Terminal part: Collects the dog's heart rate, activity level, and barks. The heart rate sensor detects 80 bpm, the acceleration sensor detects low activity, and the microphone detects high-frequency barks.

[1459] 2. Server: Receives the collected data and performs preprocessing (such as noise removal). Analyzes the data using a generative AI model and determines whether the dog is experiencing stress.

[1460] 3. User terminal: The analysis results are sent to the user via a dedicated application. The user receives a notification such as "your dog is stressed" and can take appropriate action (such as contacting family members at home or remotely controlling a toy).

[1461] Example prompts to be input to the generative AI model

[1462] For example, you could input the following prompts into a generative AI model:

[1463] Analyze your dog's emotional and health status based on the following data collected from your dog:

[1464] Heart rate: 80 bpm

[1465] Activity level: low

[1466] Call frequency: High

[1467] Please briefly explain your dog's current condition.

[1468] This prompt allows the generative AI model to determine that the dog is stressed based on its high heart rate and low activity level, and provide useful information to the user.

[1469] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1470] Step 1:

[1471] Data collection (terminal part)

[1472] The device uses a heart rate sensor, accelerometer, and microphone attached to the animal's collar to collect data such as heart rate, activity, and vocalizations in real time. Specifically, the heart rate sensor measures the heart rate every second, the accelerometer measures the animal's activity on three axes, and the microphone analyzes the frequency and volume of the animal's vocalizations.

[1473] Input: Animal heart rate, activity level, and sounds

[1474] Output: Collected biological data (heart rate, activity level, vocalizations)

[1475] Step 2:

[1476] Data transmission (terminal part)

[1477] The terminal temporarily stores the collected data in a buffer and packets the data at regular intervals (for example, every minute). The packetized data is securely sent to the server using the SSL / TLS protocol. Specifically, the data is packetized and encrypted.

[1478] Input: Collected biometric data

[1479] Output: Packetized and encrypted data

[1480] Step 3:

[1481] Data reception and storage (server part)

[1482] The server securely receives data sent from the device using the SSL / TLS protocol. The received data is then temporarily stored in storage (e.g., a cloud storage service). Specifically, the data is deserialized and stored.

[1483] Input: Packetized and encrypted data

[1484] Output: Stored biometric data

[1485] Step 4:

[1486] Data preprocessing (server part)

[1487] The server performs preprocessing on the stored data, including cleaning and noise removal. Specific operations include imputing missing values ​​in heart rate data, removing spikes in activity data, and removing noise from bird sounds.

[1488] Input: Stored biometric data

[1489] Output: Preprocessed biometric data

[1490] Step 5:

[1491] Data analysis (server part)

[1492] The server inputs the preprocessed data into the generative AI model, which then analyzes the animal's health and emotions from the input data. Specifically, the AI ​​model analyzes the data and outputs a specific result, such as "the animal is feeling stressed." The analysis results are stored in a database.

[1493] Input: Preprocessed biometric data

[1494] Output: Analysis of the animal's health and emotions

[1495] Step 6:

[1496] Notification of analysis results (user terminal)

[1497] The user's device requests the analysis results from the server. Once the results are received, they are displayed to the user through a dedicated application. Specifically, the application sends a notification to the user, such as "The animal is feeling stressed," and also uses GPS to obtain the animal's location.

[1498] Input: Analysis results, animal location information

[1499] Output: Notification to the user, display of animal location information

[1500] Examples:

[1501] Example prompts to input to a generative AI model:

[1502] Analyze your pet's emotions and health using the following data collected from your pet:

[1503] Heart rate: 80 bpm

[1504] Activity level: low

[1505] Call frequency: High

[1506] Please provide a brief description of your pet's current condition.

[1507]

[1508] (Application example 1)

[1509] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1510] It is important to monitor the status of operating equipment used in factories and work sites in real time and manage its operation safely and efficiently. However, conventional monitoring systems are expensive and have low accuracy in detecting abnormal conditions. In addition, it is difficult to respond quickly when an abnormality occurs, resulting in reduced productivity and significant damage due to breakdowns. It is also difficult to obtain location information of operating equipment and manage it appropriately.

[1511] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1512] In this invention, the server includes means connected to an equipment device equipped with a sensor that collects status data of operating equipment, means for receiving the status data of the operating equipment from the equipment device and performing preprocessing, means for analyzing the preprocessed data and using a generative AI model to estimate anomalies in the operating equipment, means for saving the analysis results in a database, means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and means equipped with a GPS function for acquiring location information of the operating equipment and displaying it to the user. This enables real-time status monitoring of operating equipment, rapid anomaly detection, and location information management.

[1513] "Operating equipment" is equipment used in a factory or workplace that operates mechanically to accomplish a specific task.

[1514] "Status data" refers to information about the operating status and performance of equipment, including vibration, movement, temperature, etc.

[1515] An "equipment device" is a device that includes a sensor and a communication module that is attached to collect status data of an operating device.

[1516] "Preprocessing" refers to the process of performing initial processing such as cleaning the received data and removing noise.

[1517] A "generative AI model" is an artificial intelligence algorithm model used to infer equipment anomalies based on collected data.

[1518] An "analysis means" is a device or system that has the function of inputting preprocessed data into a generative AI model and obtaining analytical results.

[1519] A "database" is an information system that systematically stores data obtained through preprocessing and analysis, as well as analysis results, and facilitates search and reference.

[1520] A "user terminal" is a device that receives the analysis results and displays them to the user, and includes smartphones, tablets, and the like.

[1521] "Interface" refers to a display screen and input device designed to allow users to easily understand and operate analysis results.

[1522] "GPS function" is a function for obtaining geographical location information, and provides the user with the exact location of the operating device.

[1523] The embodiments of the present invention will be described in detail below.

[1524] System configuration

[1525] This invention is a system for monitoring the status of equipment operating in a factory. The entire system consists of three main parts:

[1526] 1. Terminal part (device for equipment)

[1527] Sensors attached to operating equipment are used to collect status data such as vibration, movement, and temperature in real time. The data collected from these sensors is temporarily stored in a buffer, packetized at regular intervals, and sent to a server using a secure communication protocol.

[1528] 2. Server part

[1529] The server receives data sent from the terminal and stores it in secure storage. The received data is preprocessed, including cleaning and noise removal. It is then input into a generative AI model to analyze abnormalities and status changes in the operating equipment. The analysis results are stored in a database and provided upon request from the user's terminal.

[1530] 3. User terminal part

[1531] The user device (e.g., a smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It is also possible to obtain the location information of operating devices based on user operations.

[1532] Hardware and software used

[1533] Hardware used:

[1534] Robot sensors (motion sensors, vibration sensors, temperature sensors)

[1535] Communication module (Wi-Fi / Bluetooth)

[1536] server

[1537] User devices (smartphones, tablets)

[1538] Software used:

[1539] Python (data collection and analysis)

[1540] TensorFlow (building and running generative AI models)

[1541] Django (Web server framework)

[1542] Firebase (database)

[1543] Pushbullet (send alerts)

[1544] System Operation

[1545] Data collection and transmission

[1546] At the terminal section, sensors attached to the equipment device collect status data of the operating equipment, which is then sent to the server via a secure communication protocol.

[1547] Data analysis

[1548] The server preprocesses the received data and removes noise. The data is then input into a generative AI model to estimate abnormalities in the operating equipment. The analysis results are stored in a database and sent to the user's device as needed.

[1549] User Notification

[1550] The analysis results are sent to the user's device via the application. The user can use the application to check the status of the equipment in operation and take appropriate action if an abnormality occurs. The GPS function can also be used to obtain the location information of the equipment in operation.

[1551] Specific examples

[1552] For example, if a critical piece of equipment in a factory exhibits abnormal vibrations, the following steps will take place:

[1553] 1. Terminal part: Sensors collect information on the device's movement, vibration, and temperature.

[1554] 2. Server part: Receives collected data and performs preprocessing (such as noise removal). The data is analyzed using a generative AI model to detect anomalies.

[1555] 3. User device: The analysis results are sent to the user via the application. The user can open the app, check the abnormality warning, and take prompt action.

[1556] Example prompt sentence:

[1557] The system applies sensors built into smart pet collars to factory robots, creating an application that monitors the robot's movements, vibrations, and temperature in real time and sends an alert if an abnormality is detected.

[1558] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1559] Step 1:

[1560] The terminal uses sensors attached to the operating equipment to collect status data such as vibration, movement, and temperature in real time. The collected data is temporarily stored in a buffer. Specifically, each sensor acquires data every second and stores it in memory. The input is raw data from the sensor, and the output is the temporary data in the buffer.

[1561] Step 2:

[1562] The device periodically converts the data in the buffer into packets and sends them to the server using a secure communication protocol (e.g., SSL / TLS). At this stage, the data is still raw and pure sensor data is being sent. The input is the buffered data, and the output is the data to be sent to the server. Specifically, each time a certain amount of data accumulates, it is converted into packets and sent to the server via the network.

[1563] Step 3:

[1564] The server receives data sent from the terminal and stores it in secure storage (e.g., a cloud storage system). This storage minimizes the risk of data loss. The input is the raw data sent from the terminal, and the output is the data stored in the storage. Specifically, the server receives data through the network interface and writes it to a database.

[1565] Step 4:

[1566] The server preprocesses the received data, cleaning and denoising it. At this stage, noise data and outliers are removed. The input is raw data stored in storage, and the output is preprocessed clean data. Specifically, a data filtering algorithm is used to extract only valid data.

[1567] Step 5:

[1568] The server inputs the preprocessed data into a generative AI model to analyze abnormalities and state changes in the operating equipment. The generative AI model (using TensorFlow, for example) infers abnormalities in the operating equipment and outputs the analysis results. The input is preprocessed clean data, and the output is the analysis results. Specifically, the server feeds data into the AI ​​model and generates inference results.

[1569] Step 6:

[1570] The server stores the analysis results in a database, which can then be used for future reference or as historical data. The input is the analysis results, and the output is the result data stored in the database. Specifically, the analysis results are written to the database as structured data.

[1571] Step 7:

[1572] The server sends the analysis results in response to a request from the user terminal. The user terminal receives these analysis results and displays them to the user through a GUI (graphical user interface). The input is the analysis results retrieved from the database, and the output is the display data on the user terminal. Specifically, the data is sent to the client via a REST API.

[1573] Step 8:

[1574] The user terminal obtains the location information of the pet device and displays it to the user when specified. This location information is obtained using the GPS function. The input is GPS data, and the output is the location information displayed to the user. Specifically, the terminal obtains the location information from the GPS module and updates the display on the user interface.

[1575] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1576] System configuration

[1577] This invention is a system that combines biosensors built into a smart collar for pets, a dedicated application, and an emotion engine. The whole system consists of four main parts:

[1578] 1. Terminal part (pet device): This terminal is equipped with biosensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as your pet's heart rate, activity level, and barks in real time.

[1579] 2. Server: The server receives data sent from the device, performs preprocessing, and then analyzes the data using a generative AI model. Furthermore, the server incorporates an emotion engine to recognize the user's emotions and analyze the user's reaction to the pet's state. The analysis results are stored in a database and sent to the user's device as needed.

[1580] 3. User device: The user device (e.g., smartphone or tablet) receives the analysis results from the server through the application and provides them to the user in real time. It also analyzes the user's operations and reactions using an emotion engine and provides feedback to the system.

[1581] 4. Emotion engine: The emotion engine recognizes emotions from the user's facial expressions, voice, and input data, and reflects the analysis results throughout the system. This allows for dynamic interface and notifications to be provided according to the user's emotional patterns.

[1582] Program processing flow

[1583] 1. Sensor data collection and transmission (terminal part)

[1584] The device uses biometric sensors to continuously collect your pet's biological data, including heart rate, activity level, and vocalizations, in real time.

[1585] The collected data is stored in a buffer at regular intervals, packetized, and sent to a server using a secure communication protocol.

[1586] 2. Data reception and analysis (server part)

[1587] The server first stores the received data in secure storage and pre-processes it, which includes cleaning and denoising the data.

[1588] The pre-processed data is input into a generative AI model to analyze the pet's emotions and health status.

[1589] The analysis results are stored in a database and are ready to be provided to the user terminal.

[1590] 3. User Emotion Recognition and Response (Server and Emotion Engine)

[1591] The server uses an emotion engine to recognize the user's emotions and takes the user's reactions into account in the analysis results.

[1592] The system dynamically adjusts notifications and alerts depending on the user's perceived emotions, for example providing detailed health information about a pet if the user appears anxious.

[1593] 4. Notification to the user and provision of interface (user terminal part)

[1594] The user terminal performs authentication and acquires basic information about the pet.

[1595] The analysis results and the emotion engine's evaluation are received from the server and displayed to the user.

[1596] Send push notifications when needed and provide an interface that dynamically adjusts to specific situations.

[1597] Specific examples

[1598] Scenario: An owner wants to monitor the status of their pet (dog) while at work:

[1599] 1. Terminal part: Collects the dog's movements, heart rate, and barks. The collected data is periodically sent to the server.

[1600] 2. Server part: The server receives the data and performs preprocessing. It analyzes the data using a generative AI model and determines that the dog is stressed. The emotion engine analyzes the user's facial expressions from the camera and determines that the user is anxious.

[1601] 3. User terminal: The analysis results and the emotion engine's evaluation are notified to the user through the application. The user opens the application and checks whether the dog is stressed and the cause (e.g., lack of exercise or external stimuli). The system then provides detailed information and advice to ease the user's anxiety.

[1602] This system allows owners to understand their pet's health and emotions in real time, while also recognizing their own emotions, allowing for individually tailored responses.

[1603] The processing flow will be explained below.

[1604] Step 1:

[1605] The device uses biosensors (heart rate sensor, accelerometer, microphone) to collect data such as your pet's heart rate, activity level, and cries in real time.

[1606] Step 2:

[1607] The device stores the collected biometric data in a buffer at regular intervals (e.g., 1-second intervals). By storing the data in the buffer, data continuity is maintained.

[1608] Step 3:

[1609] The terminal packetizes the data in the buffer at regular intervals (for example, every 10 minutes) and transmits the data to the server using a secure communication protocol (for example, HTTPS).

[1610] Step 4:

[1611] The server first stores the received data in a secure storage, which prevents data loss.

[1612] Step 5:

[1613] The server preprocesses the stored data, which includes cleaning the data, filling in missing values, and removing noise to improve the accuracy of the analysis.

[1614] Step 6:

[1615] The server then inputs the preprocessed data into a generative AI model, which analyzes the data and estimates the pet's emotions (e.g., stress levels) and health status (e.g., abnormal heart rates).

[1616] Step 7:

[1617] The server stores the analysis results in a database, which can then be combined with past data for statistical analysis and historical reference.

[1618] Step 8:

[1619] The server uses an emotion engine to recognize the user's emotions, which uses the user's facial expressions, voice, and input data.

[1620] Step 9:

[1621] The server adjusts the analysis results based on the user's perceived emotions, for example, providing more detailed information and suggestions if the user appears anxious.

[1622] Step 10:

[1623] The user device performs user authentication and acquires basic information about the pet. Once authentication is complete, the device requests data from the server.

[1624] Step 11:

[1625] The server receives a request from the user terminal and transmits the analysis results and the emotion engine's evaluation.

[1626] Step 12:

[1627] The user device displays the received analysis results and the emotion engine's evaluation to the user. The results are presented visually in easy-to-understand graphs and messages.

[1628] Step 13:

[1629] The user device will send push notifications as needed, including warnings if the pet is exhibiting high stress levels.

[1630] Step 14:

[1631] The user device uses the GPS function to acquire the pet's location information, which allows the pet's current location to be displayed on a map.

[1632] Step 15:

[1633] Users can check the analysis results and their pet's location information through the application, and can understand their pet's health condition and emotions in real time and take necessary measures.

[1634] Example 2

[1635] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1636] In today's busy lifestyles, it is difficult for pet owners to monitor their pets' health and emotions in real time and respond promptly to appropriate needs. As a result, pet owners may not notice a deterioration in their pet's health early and may not be able to provide appropriate care. There is also a need for systems that can reflect the owner's own emotional state to enable more appropriate responses. However, current technology does not provide a system that can simultaneously monitor the status of both the pet and the owner and provide appropriate information.

[1637] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1638] In this invention, the server includes: means connected to a pet device equipped with a biosensor that collects biometric data from the pet; means for receiving the biometric data from the pet device and performing preprocessing; means for analyzing the preprocessed data and using a generative AI model to estimate the pet's emotions and health status; means for storing the analysis results in a database; means for transmitting the analysis results to a user terminal and providing them to the user through an interface; means including an emotion engine that receives the user's emotion data and dynamically adjusts system notifications and alerts based on the analysis results; and means for the terminal to perform authentication, acquire, and display basic information about the pet. This makes it possible to monitor the pet's health status and the owner's emotional state in real time and provide the owner with individually customized appropriate information and responses.

[1639] A "biometric sensor" is a device for collecting physiological data from pets (e.g., heart rate, activity level, vocalizations, etc.).

[1640] A "pet device" is a data collection device attached to a pet, including biosensors and communication means.

[1641] "Preprocessing" is the process of cleaning the acquired data, removing noise, and preparing it in a format suitable for analysis.

[1642] A "generative AI model" is a machine learning model that analyzes pets' emotions and health status based on collected data.

[1643] "Analysis" refers to using a generative AI model based on pre-processed data to estimate a pet's emotions and health status.

[1644] "Database" means an electronic repository for storing analytical results and other related information.

[1645] A "user terminal" is an electronic device such as a smartphone or tablet that is used by a user.

[1646] "Interface" refers to the display screen and operating means used to provide information to the user.

[1647] An "emotion engine" is a software component that analyzes a user's emotional state and dynamically adjusts system behavior and notifications based on that.

[1648] "Authentication" is the process of verifying a user's identity in order to access a system.

[1649] This invention is a system that combines a smart device for pets, a dedicated application, and an emotion engine. The system aims to collect and analyze biometric data from pets to understand their health condition and emotions, and to provide appropriate information to users based on that data.

[1650] System configuration

[1651] Terminal part (pet device)

[1652] The terminal part is a device attached to a pet's collar and is equipped with biometric sensors such as a heart rate sensor, accelerometer, and microphone. These sensors collect data such as the pet's heart rate, activity level, and vocalizations in real time. The collected data is stored in a buffer and sent to a server using a secure communication protocol.

[1653] Examples:

[1654] A device attached to the dog's collar measures the dog's heart rate every second and sends the data to a server every 10 seconds.

[1655] Server part

[1656] The server receives the data sent from the device and first stores it in secure storage. It then preprocesses the data and analyzes the pet's biometric data using a generative AI model. The analysis includes data cleaning and noise removal. The preprocessed data is then analyzed by the AI ​​model to estimate the pet's emotions and health status. The analysis results are stored in a database and are ready to be provided to the user's device.

[1657] Examples:

[1658] The server receives the dog's heart rate data, cleans it to remove noise, and then inputs it into an AI model to determine whether the dog is stressed and stores the results in a database.

[1659] User terminal part

[1660] The user device is a smartphone or tablet, and receives analysis results from the server through a dedicated application. The user device visually displays the pet's health condition and emotions in real time. It can also analyze the user's actions and reactions using an emotion engine and provide feedback to the system. Authentication is completed when the user logs in to the app, and the latest analysis results are provided from the server.

[1661] Examples:

[1662] The user opens the app and checks their dog's latest heart rate and activity level data in real time. If the dog is stressed, the app will provide the user with details and advise them on what to do.

[1663] Emotion Engine

[1664] The emotion engine analyzes the user's camera footage and audio data in real time to recognize their emotions. Based on this information, the system dynamically adjusts notifications and alerts. For example, if the user is feeling anxious, it will provide detailed information about the condition of their pet.

[1665] Examples:

[1666] If the emotion engine detects a user's impatience while checking on their pet's condition, it will provide the user with advice on how to relax, along with detailed information about their pet's health.

[1667] Example prompts to be input to the generative AI model

[1668] "Example prompt for a generative AI model analyzing smart pet collar data: 'Analyze the dog's heart rate, activity level, and bark data to determine the dog's emotional state.'"

[1669] The entire system allows owners to monitor their pets' condition in real time, providing appropriate information and prompt responses, and also reflects the user's emotional state, providing personalized responses.

[1670] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1671] Step 1:

[1672] Sensor initialization

[1673] The device will initialize the heart rate sensor, accelerometer, microphone, etc. The firmware in the device will perform basic settings to ensure the sensors operate correctly.

[1674] Input: Sensor start signal

[1675] Output: The state at which the sensor starts collecting data

[1676] Specific operation: The heart rate sensor is set to measure the heart rate every second, and the microphone is set to capture the pet's cries in real time.

[1677] Step 2:

[1678] Data collection

[1679] The device uses biometric sensors to collect data such as your pet's heart rate, activity level, and sounds in real time.

[1680] Input: Pet's biological activity data

[1681] Output: Biological data (heart rate, activity level, vocalizations)

[1682] How it works: The heart rate sensor measures your pet's heart rate every second, the acceleration sensor records its activity as digital data, and the microphone records its barks as audio data.

[1683] Step 3:

[1684] Saving to the data buffer

[1685] The collected data is stored in a buffer at regular intervals. For example, a sensor collects data every second and stores it in a buffer for 10 seconds.

[1686] Input: Collected biometric data

[1687] Output: Buffered data

[1688] Specific operation: Heart rate data and activity data are stored every second for a short period (temporary storage). After 10 seconds, the data is prepared to be passed to the next step.

[1689] Step 4:

[1690] Packetizing and transmitting data

[1691] The data stored in the buffer is packetized and sent to the server using a secure communication protocol (e.g., TLS).

[1692] Input: Data stored in the buffer

[1693] Output: Data packets sent to the server

[1694] Specific operation: The data in the buffer is packetized in a certain format (e.g., JSON format) and sent to the server over the Internet using the TLS protocol.

[1695] Step 5:

[1696] Receiving data

[1697] The server receives the data packets sent from the terminal.

[1698] Input: Data packets sent from the device

[1699] Output: Biometric data stored on the server

[1700] Specific operation: The server receives the data packet via the communication protocol and stores it in its internal secure storage.

[1701] Step 6:

[1702] Performing preprocessing

[1703] The server performs preprocessing on the received data, which includes cleaning the data (filling in missing values, removing invalid values) and removing noise (applying filtering techniques).

[1704] Input: Biometric data stored on the server

[1705] Output: Preprocessed and clean data

[1706] Specific operation: Detects and removes or complements incomplete data from the incoming data, removing noise and creating a clean dataset.

[1707] Step 7:

[1708] Analysis using generative AI models

[1709] The preprocessed data is fed into a generative AI model (e.g., a model trained with TensorFlow or PyTorch) to analyze the pet's emotions and health status.

[1710] Input: Preprocessed clean data

[1711] Output: Analysis results (estimated information on pet's emotions and health status)

[1712] How it works: Clean biometric data is input into a generative AI model, and an inference algorithm is run to analyze the pet's emotions (e.g., stress, peace of mind) and health status (e.g., healthy, abnormal).

[1713] Step 8:

[1714] Data storage

[1715] The analysis results are saved in a database.

[1716] Input: Analysis results

[1717] Output: Analysis results stored in a database

[1718] Specific operation: The analysis results from the generative AI model are stored in a database, ready for further processing or use when needed.

[1719] Step 9:

[1720] Sending and displaying analysis results

[1721] The analysis results from the server are sent to the user's terminal and provided to the user through an interface.

[1722] Input: Analysis results stored in the database

[1723] Output: Analysis results sent to the user's device

[1724] Specific operation: The analysis results are sent to the user's device, allowing the user to view the data in the application.

[1725] Step 10:

[1726] User Emotion Recognition

[1727] The emotion engine receives the user's camera footage and audio data and analyzes the user's emotions.

[1728] Input: User's camera video and audio data

[1729] Output: Parsed user emotion data

[1730] Specific operation: While the user is using the application, the emotion engine analyzes camera footage and audio data in real time to estimate the user's emotional state.

[1731] Step 11:

[1732] Dynamic adjustment of notifications and alerts

[1733] Dynamically adjust system notifications and alerts based on recognized user emotions.

[1734] Input: Parsed user emotion data

[1735] Output: Dynamically adjusted notifications and alerts

[1736] Specific behavior: If the user feels anxious, detailed information about the pet's condition and appropriate advice will be automatically provided to the user.

[1737] (Application example 2)

[1738] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1739] In the food delivery industry, there is no way to monitor the health and emotions of delivery workers in real time, which has led to problems such as accidents and a decline in service quality due to overwork and stress.In addition, there is also the issue of difficulty in designing efficient delivery routes and responding to emergencies due to a lack of proper management of delivery workers.

[1740] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means connected to a delivery person device equipped with a biometric sensor, a means for receiving the delivery person's biometric data from the delivery person device and performing preprocessing, an analysis means using a generative AI model to analyze the preprocessed data and estimate the delivery person's emotions and health condition, a means for saving the analysis results in a database, a means for transmitting the analysis results to a user terminal and providing them to the user through an interface, and a means with a GPS function for acquiring the location information of the delivery person during delivery and displaying it to the manager. This enables real-time monitoring of the health condition and emotions of delivery people, improving service quality and efficient operation management.

[1741] A "biometric sensor" is a device for collecting biometric data such as heart rate, activity level, voice, and location information.

[1742] A "delivery person device" is a terminal equipped with a built-in biometric sensor that collects biometric data from delivery persons in real time.

[1743] "Data preprocessing" refers to the process of removing noise and cleaning data from collected biometric data.

[1744] A "generative AI model" is an artificial intelligence model that analyzes collected and preprocessed biometric data to estimate the health status and emotions of delivery personnel.

[1745] A "database" is an information management system that systematically stores analyzed results and makes them accessible as needed.

[1746] A "user terminal" is a device (e.g., a smartphone) that receives analysis results and notifications and provides information to the user through an interface.

[1747] The "GPS function" is a location information system that acquires the current location of the delivery person and displays that information on the user terminal or administrator.

[1748] An "interface" refers to the screen and operating means for providing analysis results and notifications to the user through the user terminal.

[1749] A "delivery route" is a route designed to allow delivery personnel to make deliveries efficiently.

[1750] System configuration

[1751] The invention is a system that combines biometric sensors built into the delivery driver's smart device, a dedicated application, and a generative AI model. The entire system consists of four main parts:

[1752] 1. Terminal part (delivery person device):

[1753] The device is equipped with built-in biometric sensors, including a heart rate sensor, accelerometer, microphone, and GPS, which collect real-time data on the delivery person's heart rate, activity, voice, location, and more.

[1754] 2. Server part:

[1755] The server receives data sent from the device, performs preprocessing, and then analyzes the data using the generative AI model. The analysis results are stored in a database and sent to the user device as needed.

[1756] 3. User terminal part:

[1757] The user device (e.g., a smartphone) receives the analysis results from the server through the application and provides them to the user in real time. Feedback from the user's operations is also recorded and reflected in the system.

[1758] 4. GPS function part:

[1759] The system is equipped with a GPS function that acquires the location information of delivery personnel during deliveries and displays it in real time on the manager's device, enabling efficient optimization of delivery routes.

[1760] Implementation details

[1761] Hardware and software used

[1762] Hardware:

[1763] Smartwatches or smart glasses (e.g., Apple Watch, Google Glass)

[1764] Smartphone

[1765] Cloud servers (e.g., Amazon Web Services, Google Cloud)

[1766] software:

[1767] Data cleaning tools (e.g., Python's Pandas library)

[1768] Generative AI models (e.g., custom models using TensorFlow or PyTorch)

[1769] Data flow

[1770] The server receives biometric data collected from the delivery driver's smart device and stores it in secure storage. It then performs preprocessing, such as data cleaning and noise removal, and sends the preprocessed data to a generative AI model to analyze the delivery driver's health status and emotions.

[1771] The analysis results are stored in a database and sent to the user's device as needed. The user's device receives the analysis results and displays them to the user through an interface. In addition, the GPS function displays the delivery person's current location to the manager, supporting efficient operation management.

[1772] Specific examples

[1773] One food delivery service introduced a "delivery worker health monitoring system" to improve the working environment for delivery workers and enhance the quality of their service. When delivery workers wear smartwatches, their heart rate and activity levels are monitored in real time, and a generative AI model uses this data to analyze the worker's health and emotions. For example, if a delivery worker is determined to be fatigued, a notification is sent immediately via a smartphone application urging them to take a break. Meanwhile, managers can use the GPS function to check the worker's current location and provide instructions for the optimal delivery route.

[1774] Example prompts for generative AI models

[1775] Analyze the following sensor data to determine the health and emotions of the delivery driver.

[1776] The data format is heart rate, activity level, and audio.

[1777] Heart rate: 85 bpm, Activity level: 6000 steps, Voice: "I'm feeling a bit tired..."

[1778] Result (example):

[1779] Health condition: Slight fatigue

[1780] Emotion: Stress

[1781] Heart rate: [Heart rate data], Activity: [Activity data], Audio: [Audio data]

[1782] This system allows delivery personnel's health and emotions to be monitored in real time, enabling efficient operation management and improved service quality.

[1783] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1784] Step 1:

[1785] Data collection (device):

[1786] The terminal (delivery worker device) uses biometric sensors to collect biometric data such as the delivery worker's heart rate, activity level, voice, and location information in real time. This collected data is stored in a buffer at regular intervals. The input is the biometric data acquired by the terminal's sensors, and the output is the sensor data stored in the buffer.

[1787] Step 2:

[1788] Sending data (terminal):

[1789] The device packetizes the biometric data stored in the buffer and sends it to the server using a secure communication protocol. The input is the sensor data stored in the buffer, and the output is the packet data sent via the communication protocol. A security protocol (e.g., SSL / TLS) is used for this operation.

[1790] Step 3:

[1791] Data reception and preprocessing (server):

[1792] The server receives data sent from the device and stores it in secure storage. Next, it performs preprocessing such as data cleaning and noise removal on the received data. The input is the transmitted packet data, and the output is the cleaned data. Specific operations include filling in missing values ​​and correcting outliers.

[1793] Step 4:

[1794] Data analysis (server):

[1795] The server inputs the preprocessed data into a generative AI model to analyze the delivery driver's health status and emotions. The input is the preprocessed data, and the output is the analysis results. Specific operations include feeding the data forward to the model, estimating the results, and classifying emotions and health status.

[1796] Step 5:

[1797] Result storage and notification (server):

[1798] The server stores the generated analysis results in a database and sends them to the user device as needed. The input is the analysis results, and the output is the information stored in the database and a notification to the user device. Specific operations include writing to the database and sending push notifications.

[1799] Step 6:

[1800] Interface updates (user terminals):

[1801] The user terminal receives the analysis results sent from the server and updates the interface to display them to the user. The input is the analysis results sent from the server, and the output is the updated interface. Specific operations include updating the display screen and displaying a notification pop-up.

[1802] Step 7:

[1803] Acquiring and displaying GPS information (device and server):

[1804] The terminal periodically collects the delivery person's location information and sends it to the server. The server receives this location information and displays the current location on the administrator's terminal. The input is the GPS data sent from the terminal, and the output is the location information displayed on the administrator's terminal. Specific operations include obtaining the GPS data and plotting the location on a map.

[1805] The above are the specific processing steps for carrying out the present invention.

[1806] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1807] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1808] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1809] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1810] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1811] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1812] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1813] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1814] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1815] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1816] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1817] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1818] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1819] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1820] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1821] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1822] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1823] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1824] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1825] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1826] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1827] The following is further disclosed regarding the above embodiment.

[1828] (Claim 1)

[1829] a means connected to a pet device having a biometric sensor for collecting biometric data of the pet;

[1830] means for receiving and pre-processing pet biometric data from the pet device;

[1831] An analytical means using a generative AI model to analyze the preprocessed data and estimate the pet's emotions and health status, and a means to store the analytical results in a database.

[1832] means for transmitting the analysis results to a user terminal and providing the results to the user through an interface;

[1833] A system including a means with GPS functionality for obtaining and displaying pet location information to a user.

[1834] (Claim 2)

[1835] The system of claim 1, wherein the user terminal registers basic information about the pet and the AI ​​model learns patterns and trends in the data based on that information.

[1836] (Claim 3)

[1837] 10. The system of claim 1, further comprising sensors that detect changes in the pet's vocalizations, tail wagging, body movements, and heart rate.

[1838] "Example 1"

[1839] (Claim 1)

[1840] a means connected to an animal device having a biosensor for collecting biometric data of the animal;

[1841] means for receiving and pre-processing the animal's biometric data from the animal device;

[1842] An analytical means using a generative AI model to analyze the preprocessed data and estimate the animal's emotions and health status, and a means to store the analytical results in a database.

[1843] means for transmitting the analysis results to a user terminal and providing the results to the user through an interface;

[1844] A system including a means with GPS functionality for obtaining and displaying animal location information to a user.

[1845] (Claim 2)

[1846] The system of claim 1, in which the user terminal registers basic information about the animal and the AI ​​model learns patterns and trends in the data based on that information.

[1847] (Claim 3)

[1848] 10. The system of claim 1, further comprising sensors that detect animal vocalizations, tail wags, body movements, and changes in heart rate.

[1849] "Application Example 1"

[1850] (Claim 1)

[1851] a means connected to an equipment device having a sensor for collecting status data of the operating equipment;

[1852] means for receiving status data of the operating equipment from the equipment device and performing preprocessing;

[1853] An analysis means using a generative AI model that analyzes the preprocessed data and estimates abnormalities in operating equipment, and a means for storing the analysis results in a database;

[1854] means for transmitting the analysis results to a user terminal and providing the results to the user through an interface;

[1855] A system including a means with a GPS function that acquires location information of operating equipment and displays it to the user.

[1856] (Claim 2)

[1857] The system of claim 1, wherein a user terminal registers basic information about operating equipment and the AI ​​model learns data patterns and trends based on that information.

[1858] (Claim 3)

[1859] 10. The system of claim 1, further comprising sensors for detecting vibration, movement, and temperature changes of the operating equipment.

[1860] "Example 2: Combining Emotion Engines"

[1861] (Claim 1)

[1862] a means connected to a pet device having a biometric sensor for collecting biometric data of the pet;

[1863] means for receiving and pre-processing pet biometric data from the pet device;

[1864] An analytical means using a generative AI model to analyze the preprocessed data and estimate the pet's emotions and health status, and a means to store the analytical results in a database.

[1865] means for transmitting the analysis results to a user terminal and providing the results to the user through an interface;

[1866] means for receiving user emotion data and dynamically adjusting system notifications and alerts based on said analysis results; and

[1867] The system includes a means for the terminal to perform authentication, obtain basic information about the pet, and display it.

[1868] (Claim 2)

[1869] The system of claim 1, wherein the user terminal registers basic information about the pet and the AI ​​model learns patterns and trends in the data based on that information.

[1870] (Claim 3)

[1871] 10. The system of claim 1, further comprising sensors that detect the pet's vocalizations, body movements, and changes in heart rate.

[1872] "Application example 2 when combining emotion engines"

[1873] (Claim 1)

[1874] a means for connecting to a delivery person device having a biometric sensor;

[1875] a means for receiving biometric data of the delivery person from the delivery person device and performing preprocessing;

[1876] An analytical means using a generative AI model to analyze the preprocessed data and estimate the emotions and health status of the delivery person, and a means for storing the analytical results in a database.

[1877] means for transmitting the analysis results to a user terminal and providing the results to the user through an interface;

[1878] A system including a means with GPS functionality that acquires location information of delivery personnel during deliveries and displays it to an administrator.

[1879] (Claim 2)

[1880] The system of claim 1, wherein the user terminal registers basic information about the delivery person and the generative AI model learns data patterns and trends based on that information.

[1881] (Claim 3)

[1882] The system of claim 1, further comprising sensors that detect changes in the delivery person's heart rate, activity level, voice, and location information. [Explanation of symbols]

[1883] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means connected to a pet device having a biometric sensor for collecting biometric data of the pet; means for receiving and pre-processing pet biometric data from the pet device; An analytical means using a generative AI model to analyze the preprocessed data and estimate the pet's emotions and health status, and a means to store the analytical results in a database. means for transmitting the analysis results to a user terminal and providing the results to the user through an interface; A system including a means with GPS functionality for obtaining and displaying pet location information to a user.

2. The system of claim 1, wherein the user terminal registers basic information about the pet and the generating AI model learns data patterns and trends based on that information.

3. 10. The system of claim 1, further comprising sensors for detecting changes in the pet's vocalizations, tail wagging, body movements, and heart rate.

Images