System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting behavior data and emotion data of a user from a plurality of devices in real time; means for transmitting the collected data to a cloud database; means for interpreting and visualizing the data accumulated in the cloud database using a generative model; means for sharing the interpreted and visualized data to a plurality of agents; and means for each agent to provide a personalized response to the user based on the shared data.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] In today's information processing environment, users use multiple devices and platforms, making it difficult to consistently provide personalized experiences based on their individual usage patterns, behaviors, and emotions. This can lead to the so-called "cold start problem" when users begin using a new service or device, resulting in low initial satisfaction. Another issue is the lack of consistency and differences in personalized experiences across platforms. A system is needed to resolve these issues and enable users to consistently receive natural, optimal personalized experiences across all platforms. [Means for solving the problem]

[0005] This invention provides a means for collecting user behavioral data and emotional data from multiple devices in real time and a means for transmitting the collected data to a cloud database. It also provides a means for interpreting and visualizing the data stored in the cloud database using a generative model. Furthermore, a system is constructed that includes a means for sharing the interpreted and visualized data with multiple agents and a means for each agent to provide a personalized response to the user based on the shared data, thereby providing a consistent personalized experience based on the user's latest situation, behavior, and emotions. This solves the cold start problem and enables the provision of a consistent personalized experience across different platforms.

[0006] "Device" refers to the electronic devices and sensors used to collect user behavioral and emotional data.

[0007] "Behavioral Data" refers to information about a user's physical movements or activities, including, for example, location and activity level.

[0008] "Emotional data" refers to information about a user's psychological state or emotions, including, for example, facial expression recognition and vital sign data.

[0009] "Real-time" refers to data processing and communication occurring immediately and without delay.

[0010] A "cloud database" refers to a database stored on an external server accessible via the Internet.

[0011] A "generative model" refers to an algorithm that learns patterns and relationships based on large amounts of data, such as the Generative Pre-trained Transformer (GPT) model.

[0012] "Interpretation" refers to analyzing collected data and understanding its meaning and intent.

[0013] "Visualization" refers to displaying interpreted data in a way that is easy for humans to understand.

[0014] "Agent" refers to a program or system that provides a particular service or response to a user.

[0015] "Sharing" refers to distributing information so that multiple agents can use the same data.

[0016] "Personalization" refers to tailoring information and services to a user's individual characteristics and preferences.

[0017] "Response" refers to the reply or action that the agent takes to the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0026] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0039] A specific system for implementing the present invention is configured as follows.

[0040] Data collection

[0041] The device collects user behavioral and emotional data in real time. To do this, it uses smartphones, wearable devices, and sensors. Examples include smartphone GPS sensors, acceleration sensors, and heart rate sensors. Data collected from these sensors includes the user's location, amount of exercise, and heart rate. This allows it to understand whether the user is commuting, exercising, or relaxing.

[0042] Data transmission

[0043] The device sends the collected data to the server using a proprietary protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0044] Data accumulation and interpretation

[0045] The server stores the received data in a cloud database. This cloud database uses a technology suitable for storing structured data, such as a NoSQL database. The received data is not only stored as is, but also interpreted using a generative model. Specifically, a GPT model (e.g., GPT-3) is used to interpret the stored data and convert it into context information, such as "the user is commuting to work and exercising by bicycle."

[0046] Sharing contextual information

[0047] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0048] Providing a personalized experience

[0049] The AI ​​agent uses the latest contextual information retrieved from the cloud to provide personalized responses to users. These responses are generated based on contextual information interpreted using a generative model. For example, if the agent detects that the user is commuting, it might provide a personalized message such as, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0050] Specific examples

[0051] User behavior data collection

[0052] The device (e.g., a smartphone) uses GPS and an accelerometer to detect that the user is riding a bicycle, indicating that the user is commuting and exercising.

[0053] Data transmission and cloud storage

[0054] The collected behavioral data is sent to a server and stored in a cloud database. The stored data is then converted into context information using a generative model, such as "the user is commuting to work and exercising by bicycle."

[0055] Context sharing and response

[0056] Contextual information is shared among multiple authorized agents, and each agent can use this information to respond to the user. For example, an agent could provide a personalized message to the user: "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0057] This process ensures that users have a consistent and personalized experience across multiple devices and platforms.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The device collects user behavioral and emotional data in real time using sensors in the smartphone or wearable device, such as a GPS sensor to obtain location information and an acceleration sensor to detect movement patterns, and a heart rate sensor to collect heart rate data and estimate the user's emotional state.

[0061] Step 2:

[0062] The device sends the collected data to the server using a proprietary protocol, using HTTP POST requests and packaging the data in JSON format, ensuring real-time transmission without delay.

[0063] Step 3:

[0064] The server stores the received data in a cloud database. A NoSQL database is used, and the received data is structured and stored. For example, user behavior data and emotional data are stored in separate fields.

[0065] Step 4:

[0066] The server interprets the accumulated data using a generative model. Specifically, it analyzes the accumulated data using a GPT model and interprets the meaning of the data. For example, it generates contextual information such as "The user is currently exercising by riding a bicycle."

[0067] Step 5:

[0068] The server shares the interpreted and visualized data with multiple authorized agents, sending the interpreted data to each agent's API endpoint using an HTTP POST request, allowing data to be shared consistently across different platforms and services.

[0069] Step 6:

[0070] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative model to generate appropriate responses based on the contextual information. For example, if it detects that the user is commuting by bicycle, it can provide a message like, "Hello, I see you're commuting by bicycle. Please be safe. And since you're exercising, don't forget to stay hydrated."

[0071] Step 7:

[0072] The user receives a personalized response from the AI ​​agent and can provide feedback as needed to improve the system's accuracy and user experience. For example, the user can evaluate whether the message provided was helpful and provide feedback to the agent to further refine the response next time.

[0073] Example 1

[0074] 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."

[0075] In today's world, there is a need to consistently collect and interpret user behavioral and emotional data in real time across multiple devices and platforms, and provide personalized responses. However, there is a lack of effective means to efficiently collect, analyze, and share this data. In addition, to provide a consistent user experience across different devices and platforms, issues such as data latency and inconsistency must be resolved.

[0076] 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.

[0077] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for formatting the collected data in a standard format and transmitting it to the server, means for storing the data received by the server in a cloud database, means for interpreting and converting the stored data into contextual information using a generative AI model, means for sharing the interpreted and visualized data with multiple system agents, and means for each system agent to provide a personalized response to the user based on the shared data, thereby enabling a consistent and personalized user experience in real time across multiple different devices and platforms.

[0078] "Device" is a general term for hardware and software that has specific functions such as collecting, transmitting, and displaying data.

[0079] "Behavioral data" refers to data related to a user's physical movements, such as the user's location, amount of exercise, and means of transportation.

[0080] "Emotional Data" is data related to a user's psychological and physiological state, such as a user's heart rate, stress level, or emotional state.

[0081] "Real-time" means that data is processed and used immediately after collection, with little or no delay.

[0082] A "standard format" is a structured representation of data based on a specific protocol or format that allows it to be compatible with other systems and devices. Examples include JSON and XML.

[0083] A "generative AI model" is an algorithm or system that uses machine learning and artificial intelligence techniques to generate new information and context from data. An example of this is the GPT model.

[0084] "Context information" is information that indicates the user's situation or state, generated based on collected data.

[0085] A "system agent" is software or hardware that provides specific functions or services and is responsible for direct interaction with the user.

[0086] "Personalized responses" refer to messages and information that are customized based on individual user data and context.

[0087] A "cloud database" is a remote database system accessible via the Internet that provides scalable data storage and processing capabilities.

[0088] A specific system for implementing this invention includes a series of processes for collecting user behavioral and emotional data in real time and providing personalized responses based on that data, as described in detail below.

[0089] Data collection

[0090] The device uses smartphones and wearable devices to collect user behavioral and emotional data. Specific sensors used for this purpose include GPS sensors, acceleration sensors, and heart rate sensors. This allows the device to collect information on the user's location, amount of exercise, heart rate, etc., and to understand whether the user is commuting, exercising, or relaxing.

[0091] Data transmission

[0092] The device sends the collected data to the server using a dedicated protocol (e.g., MQTT or HTTP). The data is sent in real time and guaranteed to be delivered without delay. The data is packaged in a standard format (e.g., JSON) and sent as an HTTP POST request.

[0093] Data accumulation and interpretation

[0094] The server stores the received data in a cloud database. This cloud database uses a NoSQL database (e.g., MongoDB) for scalable and efficient data storage. The stored data is interpreted using a generative AI model (e.g., GPT-3) and converted into context information, such as "the user is commuting to work and exercising by bicycle."

[0095] Sharing contextual information

[0096] The server shares the interpreted and visualized data with multiple system agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0097] Providing a personalized experience

[0098] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative AI model to generate messages tailored to the user's situation. For example, if it detects that the user is commuting, the agent might provide a message like, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0099] Specific examples

[0100] Data Collection Example

[0101] A device (e.g., a smartphone) uses its GPS sensor and accelerometer during your morning commute to collect the following data: "latitude: 35.6895, longitude: 139.6917, activity: cycling".

[0102] Data transmission example

[0103] The collected data is sent to a cloud server in real time using HTTP POST requests.

[0104] Examples of data accumulation and interpretation

[0105] The server stores the received data in a cloud database and uses a generative AI model (GPT-3) to convert it into contextual information such as "the user is commuting to work and exercising by bicycle."

[0106] Examples of sharing and responding to contextual information

[0107] The server sends the interpreted data to the AI ​​agent's API endpoint, and the AI ​​agent then sends a personalized push notification to the user's smartphone saying, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, don't forget to stay hydrated."

[0108] Prompt Sentence Examples

[0109] “What message do you provide if you detect that a user is cycling to work?”

[0110] In this way, users receive useful information and advice in real time.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1: Data collection

[0113] The device acquires sensor information. Specifically, it uses the GPS sensor, acceleration sensor, heart rate sensor, etc. of the smartphone or wearable device to collect data such as location information, exercise volume, and heart rate.

[0114] Input: The user's physical actions and physiological state.

[0115] Output: Data formatted in JSON (e.g. "latitude: 35.6895, longitude: 139.6917, heart_rate: 75, activity: cycling").

[0116] Step 2: Sending data

[0117] The device sends the collected data to the server using an HTTP POST request in real time without delay.

[0118] Input: Data formatted in JSON format.

[0119] Output: The data sent to the server.

[0120] Step 3: Data reception and verification

[0121] The server receives the data and validates the format and content.

[0122] Input: Data sent from the terminal.

[0123] Output: Validated data.

[0124] Step 4: Data accumulation

[0125] The server stores the validated data in a cloud database, which uses NoSQL database technology (e.g., MongoDB).

[0126] Input: Validated data.

[0127] Output: Data stored in the database.

[0128] Step 5: Data interpretation

[0129] The server uses a generative AI model (e.g., GPT-3) to interpret the stored data and convert it into contextual information. The generative AI model integrates multiple input data and generates context, such as "the user is commuting to work and exercising by bicycle."

[0130] Input: Raw data retrieved from the database.

[0131] Output: Interpreted context information.

[0132] Step 6: Share contextual information

[0133] The server shares the interpreted contextual information with multiple system agents, sending the information to the agents' API endpoints using HTTP POST requests.

[0134] Input: Interpreted context information.

[0135] Output: Data sent to the system agent.

[0136] Step 7: Generate a personalized message

[0137] Based on the contextual information received, the AI ​​agent uses a generative AI model to generate a personalized response for the user.

[0138] Input: Context information sent by the server.

[0139] Output: The generated personalized message (e.g., "Hey, I see you're cycling to work. Be safe, and remember to stay hydrated since you're exercising.").

[0140] Step 8: User Notification

[0141] The AI ​​agent generates a message and sends it to the user's device, using push notifications or in-app notifications.

[0142] Input: The generated personalized message.

[0143] Output: The message displayed on the user's terminal.

[0144] (Application example 1)

[0145] 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."

[0146] Conventional food delivery services have the problem that they can only make uniform suggestions to users, and lack personalized suggestions based on the user's individual behavior and status. In addition, there was no technology that could use user behavioral and emotional data to make optimal suggestions in real time. This resulted in a problem of not improving the quality of the user experience.

[0147] 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.

[0148] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for transmitting the collected data to a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative model, means for sharing the interpreted and visualized data with multiple agents, means for each agent to provide a personalized response to the user based on the shared data, and means for making personalized food delivery suggestions based on the user behavioral data, thereby enabling optimal food delivery suggestions to be made according to the user's behavior and status.

[0149] "Device" means an electronic device, such as a smartphone or sensor, used to collect user behavioral and emotional data.

[0150] "Behavioral data" refers to information about a user's movements, exercise, and device usage.

[0151] "Emotional data" is information that indicates the user's emotional state, such as the user's heart rate, facial expression changes, and voice tone.

[0152] A "cloud database" is a system for storing and managing data that is accessible via the Internet.

[0153] A "generative model" is an artificial intelligence model used to interpret and visualize collected data.

[0154] "Visualization" is the process of displaying data in a graphical format that allows users to intuitively understand it.

[0155] An "agent" is a software program or system that provides responses or suggestions to a user based on collected data.

[0156] "Personalized responses" refer to the provision of messages and services optimized for individual users based on their behavioral and emotional data.

[0157] "Food delivery suggestions" are suggestions to recommend appropriate meals and drinks based on the user's behavior and condition.

[0158] A specific system for implementing the present invention is configured as follows.

[0159] Data collection

[0160] The device collects user behavioral and emotional data in real time. To do this, it uses smartphones, wearable devices, and sensors. Examples include smartphone GPS sensors, acceleration sensors, and heart rate sensors. Data collected from these sensors includes the user's location, amount of exercise, and heart rate. This allows it to understand whether the user is commuting, exercising, or relaxing.

[0161] Specific examples

[0162] When a user is exercising by bicycle, the device uses the GPS sensor, accelerometer, and heart rate sensor to collect the user's location, exercise volume, and heart rate.

[0163] Data transmission

[0164] The device sends the collected data to the server using a proprietary protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0165] Data accumulation and interpretation

[0166] The server stores the received data in a cloud database. This cloud database uses a technology suitable for storing structured data, such as a NoSQL database. The received data is not only stored as is, but also interpreted using a generative model. Specifically, a GPT model (e.g., GPT-3) is used to interpret the stored data and convert it into context information, such as "the user is exercising by riding a bicycle."

[0167] Sharing contextual information

[0168] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0169] Providing a personalized experience

[0170] The agent provides personalized food delivery suggestions to the user based on the latest contextual information retrieved from the server, and the responses are generated based on the contextual information interpreted using the generative model.

[0171] Specific examples

[0172] If the user is exercising by bicycle, the agent will make a suggestion such as, "You're currently exercising by bicycle. Good job! If you want to have a high-protein meal after exercise, we recommend a protein shake."

[0173] An example of a prompt for the generative AI model is as follows:

[0174] Suggest a high-protein diet for cyclists.

[0175] In this way, users can receive optimal food delivery suggestions based on their behavior and status.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] The device collects user behavioral and emotional data. This data is acquired using GPS sensors, accelerometers, heart rate sensors, etc. Inputs include location information, exercise volume, and heart rate. The output here is the collected raw data.

[0179] Step 2:

[0180] The terminal packages the collected data into JSON format and sends it to the server using an HTTP POST request. The input is the raw data obtained in step 1, and the output is the packaged data sent to the server without delay.

[0181] Step 3:

[0182] The server stores the received data in a cloud database, which may be a NoSQL database or similar. The input is the data sent in step 2, and the output is the data securely stored in the cloud database.

[0183] Step 4:

[0184] The server interprets and visualizes the accumulated data using a generative model (e.g., GPT-3). The input is raw data stored in a cloud database, and the output is interpreted and visualized contextual information. Specifically, the server analyzes the data and generates contextual information such as "the user is exercising by riding a bicycle."

[0185] Step 5:

[0186] The server shares the interpreted and visualized contextual information with multiple agents by sending it via an HTTP POST request to the API endpoint of each agent. The input is the interpreted and visualized contextual information, and the output is the data shared with each agent.

[0187] Step 6:

[0188] The agent makes personalized food delivery suggestions based on contextual information retrieved from the server. These suggestions are generated based on contextual information interpreted using a generative AI model. The input is the shared contextual information, and the output is personalized messages and suggestions provided to the user.

[0189] Specifically, if the user is exercising by bicycle, the agent will suggest, "You're currently exercising by bicycle. Good work! If you want to have a high-protein meal after your exercise, we recommend a protein shake." An example of a prompt sentence for the generative AI model is as follows:

[0190] Suggest a high-protein diet for cyclists.

[0191] 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.

[0192] A specific system for implementing the present invention is configured as follows.

[0193] Data collection

[0194] The device uses various sensors installed in smartphones and wearable devices to collect user behavioral and emotional data. These include GPS sensors, acceleration sensors, and heart rate sensors. These sensors are used to collect user location information, movement patterns, and vital sign data. Furthermore, facial expression and voice recognition technologies are used to collect user emotional data in real time.

[0195] Using the Emotion Engine

[0196] The device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and vital sign data. Based on the analysis results, the emotion engine identifies the user's emotional state. The emotion engine uses high-performance image and voice recognition algorithms to infer the user's emotions in real time from the collected data.

[0197] Data transmission

[0198] The terminals send the collected and analyzed data to the server using a dedicated protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0199] Data accumulation and interpretation

[0200] The server stores the received data in a cloud database. Because the cloud database uses a NoSQL database, the received data is structured and stored efficiently. The GPT model is then used to analyze the stored data and interpret its meaning. Specifically, it generates contextual information such as "Currently exercising by bicycle" based on the user's behavioral patterns and emotional state.

[0201] Sharing contextual information

[0202] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information via HTTP POST requests to each agent's API endpoint, ensuring consistent data sharing across different platforms and agents.

[0203] Providing a personalized experience

[0204] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. This response is generated based on the contextual information interpreted using a generative model. For example, if the AI ​​agent detects that a user is cycling to work and feeling stressed, it will provide the user with a personalized message such as, "Hello, I see you are cycling to work. Please be careful and make sure you drink plenty of water while exercising."

[0205] Specific examples

[0206] User behavior and sentiment data collection

[0207] The device (e.g., a smartphone) uses GPS and an acceleration sensor to detect that the user is riding a bicycle. If the heart rate sensor detects an abnormally high heart rate, the emotion engine infers that the user is in a stressed state. This indicates that the user is feeling stressed during their commute.

[0208] Data transmission and cloud storage

[0209] The collected and analyzed data is sent to a server and stored in a cloud database. The accumulated data is then converted into context information using a generative model, such as "The user is commuting by bicycle and feeling stressed."

[0210] Context sharing and response

[0211] Contextual information is shared among authorized agents, and the AI ​​agent can use this information to respond to the user, for example, providing a personalized message such as, "I see you're cycling to work. Please be careful and remember to take a deep breath to relax."

[0212] This process delivers a consistent and personalized experience across multiple devices and platforms based on user behavior and sentiment.

[0213] The processing flow will be explained below.

[0214] Step 1:

[0215] The device collects user behavioral and emotional data in real time. Specifically, it uses the smartphone's built-in GPS sensor to determine location and an acceleration sensor to detect movement. It also uses a heart rate sensor to obtain the user's heart rate and estimates their emotional state. It also uses a camera to recognize facial expressions and analyze emotions from the user's face.

[0216] Step 2:

[0217] The device sends the collected data to the server using a dedicated protocol. To ensure the data is accurate, the data is converted to JSON format and sent via an HTTP POST request. The data sent includes location information, movement information, heart rate data, facial expression data, and more.

[0218] Step 3:

[0219] The server accumulates the received data in a cloud database. The received data is structured and can be efficiently stored in a NoSQL database. For example, user behavior data is stored in a "location information" field, and emotional data is stored in an "emotional state" field.

[0220] Step 4:

[0221] The server interprets the accumulated data using a generative model. Specifically, the GPT model analyzes the relationships in the data and generates meaningful context information that summarizes the user's situation and emotions. For example, it generates the context "The user is currently commuting by bicycle and feeling stressed."

[0222] Step 5:

[0223] The server shares the interpreted and visualized data with multiple authorized agents, sending the interpreted contextual information via HTTP POST requests to each agent's API endpoint. This process ensures consistent data sharing across different platforms and agents.

[0224] Step 6:

[0225] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative model to generate appropriate responses based on the contextual information. For example, if a user is commuting by bicycle and feeling stressed, it can provide a message like, "Hello, I see you're commuting by bicycle. Please be safe. And it might be a good idea to take a deep breath to relax."

[0226] Step 7:

[0227] The user receives a personalized response from the AI ​​agent, and can provide feedback as needed to improve the system's accuracy and user experience. For example, users can evaluate whether the message provided was helpful and provide feedback to the agent to refine future responses.

[0228] Example 2

[0229] 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."

[0230] There are few systems that can collect user behavioral and emotional data in real time, analyze it efficiently, and provide personalized responses. Furthermore, there are problems with properly analyzing this data, generating consistent contextual information, and sharing it with multiple agents. This creates the risk of delays and reduced quality in providing the optimal personalized experience to users.

[0231] 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.

[0232] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple terminals in real time, means for transmitting the collected data to the server, means for storing the data received by the server in a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative AI model, means for sharing the interpreted and visualized data with multiple agents, and means for each agent to provide a personalized response to the user based on the shared data. This makes it possible to efficiently collect and analyze user behavioral and emotional data and provide a personalized response in real time.

[0233] "Terminal" refers to equipment or devices used to collect user behavioral and emotional data.

[0234] "Behavioral data" refers to information about a user's physical activities, such as their location and movement patterns.

[0235] "Emotional data" refers to data that indicates the user's emotional state, and refers to information collected from facial expressions, voice, vital signs, etc.

[0236] "Server" refers to a computer system that has the function of receiving, storing, analyzing, and sharing collected data.

[0237] A "cloud database" is a database that can be accessed via the Internet and is a system that efficiently stores and manages data.

[0238] A "generative AI model" refers to an algorithm that uses machine learning techniques to analyze input data and generate meaning and context.

[0239] An "agent" refers to software or systems that use interpreted and visualized data to provide personalized responses to users.

[0240] "Personalized responses" refer to customized messages and interactions that are specific to a user's particular situation or state.

[0241] The present invention relates to a system that collects and analyzes user behavioral and emotional data in real time to provide users with personalized responses. The system is composed of multiple terminals, a server, and agents.

[0242] Data collection

[0243] Devices are used to collect user behavioral and emotional data. Specifically, GPS sensors, acceleration sensors, heart rate sensors, facial recognition, and voice recognition technologies are used in smartphones and wearable devices. These sensors collect location information, movement patterns, vital data such as heart rate, and emotional data from the user's facial expressions and voice.

[0244] Using the Emotion Engine

[0245] The device is equipped with an emotion engine that analyzes the collected data to identify the user's emotional state in real time. Using high-performance image and voice recognition algorithms, it is able to estimate the user's stress level, joy, anger, and other emotions.

[0246] Data transmission

[0247] The terminals send the collected and analyzed data to the server using a dedicated protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent to the server via an HTTP POST request.

[0248] Data accumulation and interpretation

[0249] The server stores the received data in a cloud database. This cloud database uses a NoSQL database, which allows for efficient data storage and management. The stored data is then analyzed using a generative AI model (e.g., GPT-3) to generate contextual information. This provides contextual information based on the user's behavioral patterns and emotional state (e.g., "The user is commuting by bicycle and feeling stressed").

[0250] Sharing contextual information

[0251] The server sends an HTTP POST request to each agent's API endpoint to share the interpreted and visualized contextual information with multiple agents, allowing data to be shared consistently across different platforms and agents.

[0252] Providing a personalized experience

[0253] The AI ​​agent uses the latest contextual information retrieved from the cloud to provide personalized responses to users. These responses are generated based on contextual information interpreted using a generative AI model. For example, if the AI ​​agent detects that a user is cycling to work and feeling stressed, it might provide a personalized message to the user such as, "Hello, I see you're cycling to work. Please be careful and make sure you drink plenty of water while exercising."

[0254] Specific examples

[0255] The device (e.g., a smartphone) uses GPS and an acceleration sensor to detect that the user is cycling. If the heart rate sensor detects an abnormally high heart rate, the emotion engine infers that the user is in a state of stress. This indicates that the user is feeling stressed while commuting. The collected and analyzed data is sent to a server and stored in a cloud database. The accumulated data is analyzed using a generative AI model and converted into context information, such as "The user is feeling stressed while commuting by bicycle." The context information is shared with multiple authorized agents, and the AI ​​agents respond to the user based on this information. For example, they might provide a personalized message such as, "You're currently cycling to work. Please be careful and remember to take deep breaths to relax."

[0256] Prompt Sentence Examples

[0257] "Generate a message to be sent when a user is cycling to work and is estimated to have a high heart rate and be in a stressed state."

[0258] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0259] Step 1: Data collection

[0260] Terminals (smartphones and wearable devices) use GPS sensors, acceleration sensors, heart rate sensors, facial recognition, and voice recognition technology to collect user behavioral and emotional data in real time. Specifically, the terminal uses a GPS sensor to obtain the user's location information (latitude and longitude), and an acceleration sensor to detect movement patterns. Furthermore, the heart rate sensor collects vital sign data, and facial recognition and voice recognition technology analyzes emotional data. The input data is this sensor information, and the output data is the collected comprehensive data. For example, data such as "latitude: 35.6581, longitude: 139.7514, heart rate: 85 bpm, emotion: stress" can be obtained.

[0261] Step 2: Analysis by the emotion engine

[0262] The emotion engine installed on the device analyzes the collected facial expression, voice, and vital sign data to identify the user's emotional state. The input here is the comprehensive data obtained in step 1. The emotion engine analyzes the data using image and voice recognition algorithms and estimates the emotional state (e.g., stress, joy, anger, etc.) in real time. The output data is the analysis result, specifically including information such as "the user is feeling stressed."

[0263] Step 3: Send data

[0264] The device sends the collected and analyzed data to the server using a dedicated protocol. The input data here is the data analyzed by the emotion engine. This data is packaged in a standard format such as JSON and sent to the server via an HTTP POST request. Specifically, the data is converted to JSON and sent in the format {"location":{"lat":35.6581,"lon":139.7514},"heart_rate":85,"emotion":"stress"}. The output data is the data received by the server.

[0265] Step 4: Data accumulation and interpretation

[0266] The server stores the data received from the device in a cloud database. The input data here is the data received in step 3. A NoSQL database is used for the cloud database, allowing data to be efficiently stored and managed. Next, the server analyzes the stored data using a generative AI model (e.g., GPT-3) to generate contextual information. For example, the AI ​​model may interpret this as "the user is commuting by bicycle and feeling stressed." The output data is the analyzed contextual information.

[0267] Step 5: Share contextual information

[0268] The server shares the interpreted and visualized contextual information with multiple agents. The input data here is the contextual information generated in step 4. The server sends an HTTP POST request to the API endpoint of each agent to share the contextual information. Specifically, it sends data such as {"context":"cycling to work with stress"} to each agent. The output data is the contextual information sent to each agent.

[0269] Step 6: Deliver a personalized experience

[0270] The AI ​​agent provides a personalized response to the user based on the latest contextual information retrieved from the cloud. The input data here is the contextual information shared in step 5. The AI ​​agent uses the generative AI model to generate a response and displays it on the user's device. For example, if the AI ​​agent detects that the user is cycling to work and feeling stressed, it generates a message such as, "You're currently commuting. Please be careful and remember to take a deep breath to relax." The output data is the personalized message provided to the user.

[0271] (Application example 2)

[0272] 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."

[0273] Conventional food delivery services provide uniform menu recommendations without considering the user's current situation or emotional state, resulting in limited user experience and low satisfaction. Furthermore, they lacked personalized services tailored to the user's specific circumstances, making it difficult to meet individual needs. This made it difficult to improve user engagement and retention.

[0274] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0275] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple information processing devices in real time, means for transmitting the collected data to a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative model, means for sharing the interpreted and visualized data with multiple knowledge agents, means for each knowledge agent to provide a personalized response to the user based on the shared data, and means for providing optimal menus and promotional information based on the user behavioral data and emotional data, thereby enabling the provision of a personalized food delivery service according to the user's current situation and emotional state.

[0276] An "information processing device" is a device that includes hardware and software for acquiring and processing user behavioral data and emotion data.

[0277] "Behavioral data" refers to data related to a user's physical behavior, such as location information and movement patterns.

[0278] "Emotional data" refers to data that indicates the user's physiological and psychological state, such as heart rate and facial expression analysis.

[0279] A "cloud database" is a database system for storing, managing, and analyzing data in a cloud computing environment.

[0280] A "generative model" refers to a machine learning algorithm that analyzes large amounts of data, recognizes patterns, and generates new information.

[0281] A "knowledge agent" is an artificial intelligence agent that is trained to perform specific tasks and provide information to the user.

[0282] A "personalized response" is a response that is individually optimized based on a user's behavioral and emotional data.

[0283] "Menu and promotion information" refers to information about food options and special offers offered through food delivery services.

[0284] "User context" refers to information about the user's current environment and situation.

[0285] A system required to implement this invention includes an information processing system operating as a smartphone application, which includes a smartphone that collects user behavioral and emotional data, a cloud database that processes and stores the data, a generative model that interprets and visualizes the data, and a knowledge agent that provides personalized responses to the user.

[0286] First, the smartphone uses a GPS sensor, an acceleration sensor, a heart rate sensor, and a facial expression analysis camera to collect user behavioral data (location information and movement patterns) and emotional data (emotional state estimated from heart rate and facial expressions) in real time. This information is structured and sent to a cloud database. The cloud database uses a fast-access NoSQL database, which stores data in real time and analyzes it using a generative model.

[0287] Next, a generative model running on the server analyzes the collected behavioral and emotional data to generate the user's current contextual information, which is expressed as detailed situational information such as "I am currently exercising by riding a bicycle" based on the user's behavioral patterns and emotional state.

[0288] The generated contextual information is shared with multiple knowledge agents via an API endpoint. Based on this contextual information, the knowledge agents generate optimal responses for the user. These responses are presented as optimal menus and promotional information offered by food delivery services. For example, if the system detects that the user is tired, it can recommend stamina-boosting dishes.

[0289] For example, the flow is as follows:

[0290] 1. If a user is cycling to work and their heart rate is high, the smartphone sensor will detect this and the emotion engine will determine that the user is tired.

[0291] 2. This data is sent to a cloud database, where a generative model generates contextual information such as "the user is tired from riding a bicycle."

[0292] 3. Contextual information is shared with knowledge agents via APIs to create personalized responses, such as suggesting menus that will energize a tired user.

[0293] 4. As a result, the user's smartphone application will display a message such as, "You look tired. Would you like some food to give you some energy?"

[0294] Examples of prompts include:

[0295] "Is your current heart rate normal?"

[0296] "How accurately do the sensors track your movements?"

[0297] "What are some specific examples of menu suggestions when your emotional state is fatigued?"

[0298] In this way, a system can be realized that provides a personalized experience based on the user's real-time state and emotions.

[0299] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0300] Step 1:

[0301] Smartphones (devices) use built-in GPS sensors, acceleration sensors, heart rate sensors, and facial expression analysis cameras to collect real-time data on the user's location, movement patterns, heart rate, and facial expression. This data is collected as user behavioral and emotional data. The input is data from the sensors, and the output is structured behavioral and emotional data.

[0302] Step 2:

[0303] The device structures the collected behavioral and emotional data and sends it to the cloud database. Specifically, it converts the collected data into JSON format and sends it to the cloud database using an HTTP POST request. The input is the data collected in step 1, and the output is storage in the cloud database.

[0304] Step 3:

[0305] The server analyzes the data stored in the cloud database using a generative model (e.g., GPT-3) to generate the user's current contextual information. The generative model learns behavioral and emotional data, recognizes patterns, and generates specific contextual information such as "I am currently exercising by riding a bicycle." The input is the data stored in the cloud database, and the output is interpreted contextual information.

[0306] Step 4:

[0307] The server shares the generated context information with multiple knowledge agents through an API endpoint. Specifically, it sends the interpreted context information to each knowledge agent's API using an HTTP POST request. The input is the interpreted context information, and the output is data sent to each knowledge agent.

[0308] Step 5:

[0309] The knowledge agent generates the optimal response for the user based on the shared contextual information. For example, if it determines that the user is tired, it generates recommendations for stamina-boosting dishes. The input is contextual information, and the output is a personalized response.

[0310] Step 6:

[0311] The terminal displays the personalized response received from the knowledge agent to the user. For example, it displays a message such as, "You seem tired. Would you like some food that will give you energy?" The input is the response from the knowledge agent, and the output is the message displayed to the user.

[0312] 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.

[0313] 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.

[0314] 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.

[0315] [Second embodiment]

[0316] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0317] 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.

[0318] 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).

[0319] 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.

[0320] 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.

[0321] 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).

[0322] 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.

[0323] 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.

[0324] 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.

[0325] 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.

[0326] In the smart glasses 214, the 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.

[0327] 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."

[0328] A specific system for implementing the present invention is configured as follows.

[0329] Data collection

[0330] The device collects user behavioral and emotional data in real time. To do this, it uses smartphones, wearable devices, and sensors. Examples include smartphone GPS sensors, acceleration sensors, and heart rate sensors. Data collected from these sensors includes the user's location, amount of exercise, and heart rate. This allows it to understand whether the user is commuting, exercising, or relaxing.

[0331] Data transmission

[0332] The device sends the collected data to the server using a proprietary protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0333] Data accumulation and interpretation

[0334] The server stores the received data in a cloud database. This cloud database uses a technology suitable for storing structured data, such as a NoSQL database. The received data is not only stored as is, but also interpreted using a generative model. Specifically, a GPT model (e.g., GPT-3) is used to interpret the stored data and convert it into context information, such as "the user is commuting to work and exercising by bicycle."

[0335] Sharing contextual information

[0336] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0337] Providing a personalized experience

[0338] The AI ​​agent uses the latest contextual information retrieved from the cloud to provide personalized responses to users. These responses are generated based on contextual information interpreted using a generative model. For example, if the agent detects that the user is commuting, it might provide a personalized message such as, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0339] Specific examples

[0340] User behavior data collection

[0341] The device (e.g., a smartphone) uses GPS and an accelerometer to detect that the user is riding a bicycle, indicating that the user is commuting and exercising.

[0342] Data transmission and cloud storage

[0343] The collected behavioral data is sent to a server and stored in a cloud database. The stored data is then converted into context information using a generative model, such as "the user is commuting to work and exercising by bicycle."

[0344] Context sharing and response

[0345] Contextual information is shared among multiple authorized agents, and each agent can use this information to respond to the user. For example, an agent could provide a personalized message to the user: "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0346] This process ensures that users have a consistent and personalized experience across multiple devices and platforms.

[0347] The processing flow will be explained below.

[0348] Step 1:

[0349] The device collects user behavioral and emotional data in real time using sensors in the smartphone or wearable device, such as a GPS sensor to obtain location information and an acceleration sensor to detect movement patterns, and a heart rate sensor to collect heart rate data and estimate the user's emotional state.

[0350] Step 2:

[0351] The device sends the collected data to the server using a proprietary protocol, using HTTP POST requests and packaging the data in JSON format, ensuring real-time transmission without delay.

[0352] Step 3:

[0353] The server stores the received data in a cloud database. A NoSQL database is used, and the received data is structured and stored. For example, user behavior data and emotional data are stored in separate fields.

[0354] Step 4:

[0355] The server interprets the accumulated data using a generative model. Specifically, it analyzes the accumulated data using a GPT model and interprets the meaning of the data. For example, it generates contextual information such as "The user is currently exercising by riding a bicycle."

[0356] Step 5:

[0357] The server shares the interpreted and visualized data with multiple authorized agents, sending the interpreted data to each agent's API endpoint using an HTTP POST request, allowing data to be shared consistently across different platforms and services.

[0358] Step 6:

[0359] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative model to generate appropriate responses based on the contextual information. For example, if it detects that the user is commuting by bicycle, it can provide a message like, "Hello, I see you're commuting by bicycle. Please be safe. And since you're exercising, don't forget to stay hydrated."

[0360] Step 7:

[0361] The user receives a personalized response from the AI ​​agent and can provide feedback as needed to improve the system's accuracy and user experience. For example, the user can evaluate whether the message provided was helpful and provide feedback to the agent to further refine the response next time.

[0362] Example 1

[0363] 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."

[0364] In today's world, there is a need to consistently collect and interpret user behavioral and emotional data in real time across multiple devices and platforms, and provide personalized responses. However, there is a lack of effective means to efficiently collect, analyze, and share this data. In addition, to provide a consistent user experience across different devices and platforms, issues such as data latency and inconsistency must be resolved.

[0365] 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.

[0366] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for formatting the collected data in a standard format and transmitting it to the server, means for storing the data received by the server in a cloud database, means for interpreting and converting the stored data into contextual information using a generative AI model, means for sharing the interpreted and visualized data with multiple system agents, and means for each system agent to provide a personalized response to the user based on the shared data, thereby enabling a consistent and personalized user experience in real time across multiple different devices and platforms.

[0367] "Device" is a general term for hardware and software that has specific functions such as collecting, transmitting, and displaying data.

[0368] "Behavioral data" refers to data related to a user's physical movements, such as the user's location, amount of exercise, and means of transportation.

[0369] "Emotional Data" is data related to a user's psychological and physiological state, such as a user's heart rate, stress level, or emotional state.

[0370] "Real-time" means that data is processed and used immediately after collection, with little or no delay.

[0371] A "standard format" is a structured representation of data based on a specific protocol or format that allows it to be compatible with other systems and devices. Examples include JSON and XML.

[0372] A "generative AI model" is an algorithm or system that uses machine learning and artificial intelligence techniques to generate new information and context from data. An example of this is the GPT model.

[0373] "Context information" is information that indicates the user's situation or state, generated based on collected data.

[0374] A "system agent" is software or hardware that provides specific functions or services and is responsible for direct interaction with the user.

[0375] "Personalized responses" refer to messages and information that are customized based on individual user data and context.

[0376] A "cloud database" is a remote database system accessible via the Internet that provides scalable data storage and processing capabilities.

[0377] A specific system for implementing this invention includes a series of processes for collecting user behavioral and emotional data in real time and providing personalized responses based on that data, as described in detail below.

[0378] Data collection

[0379] The device uses smartphones and wearable devices to collect user behavioral and emotional data. Specific sensors used for this purpose include GPS sensors, acceleration sensors, and heart rate sensors. This allows the device to collect information on the user's location, amount of exercise, heart rate, etc., and to understand whether the user is commuting, exercising, or relaxing.

[0380] Data transmission

[0381] The device sends the collected data to the server using a dedicated protocol (e.g., MQTT or HTTP). The data is sent in real time and guaranteed to be delivered without delay. The data is packaged in a standard format (e.g., JSON) and sent as an HTTP POST request.

[0382] Data accumulation and interpretation

[0383] The server stores the received data in a cloud database. This cloud database uses a NoSQL database (e.g., MongoDB) for scalable and efficient data storage. The stored data is interpreted using a generative AI model (e.g., GPT-3) and converted into context information, such as "the user is commuting to work and exercising by bicycle."

[0384] Sharing contextual information

[0385] The server shares the interpreted and visualized data with multiple system agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0386] Providing a personalized experience

[0387] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative AI model to generate messages tailored to the user's situation. For example, if it detects that the user is commuting, the agent might provide a message like, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0388] Specific examples

[0389] Data Collection Example

[0390] A device (e.g., a smartphone) uses its GPS sensor and accelerometer during your morning commute to collect the following data: "latitude: 35.6895, longitude: 139.6917, activity: cycling".

[0391] Data transmission example

[0392] The collected data is sent to a cloud server in real time using HTTP POST requests.

[0393] Examples of data accumulation and interpretation

[0394] The server stores the received data in a cloud database and uses a generative AI model (GPT-3) to convert it into contextual information such as "the user is commuting to work and exercising by bicycle."

[0395] Examples of sharing and responding to contextual information

[0396] The server sends the interpreted data to the AI ​​agent's API endpoint, and the AI ​​agent then sends a personalized push notification to the user's smartphone saying, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, don't forget to stay hydrated."

[0397] Prompt Sentence Examples

[0398] “What message do you provide if you detect that a user is cycling to work?”

[0399] In this way, users receive useful information and advice in real time.

[0400] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0401] Step 1: Data collection

[0402] The device acquires sensor information. Specifically, it uses the GPS sensor, acceleration sensor, heart rate sensor, etc. of the smartphone or wearable device to collect data such as location information, exercise volume, and heart rate.

[0403] Input: The user's physical actions and physiological state.

[0404] Output: Data formatted in JSON (e.g. "latitude: 35.6895, longitude: 139.6917, heart_rate: 75, activity: cycling").

[0405] Step 2: Sending data

[0406] The device sends the collected data to the server using an HTTP POST request in real time without delay.

[0407] Input: Data formatted in JSON format.

[0408] Output: The data sent to the server.

[0409] Step 3: Data reception and verification

[0410] The server receives the data and validates the format and content.

[0411] Input: Data sent from the terminal.

[0412] Output: Validated data.

[0413] Step 4: Data accumulation

[0414] The server stores the validated data in a cloud database, which uses NoSQL database technology (e.g., MongoDB).

[0415] Input: Validated data.

[0416] Output: Data stored in the database.

[0417] Step 5: Data interpretation

[0418] The server uses a generative AI model (e.g., GPT-3) to interpret the stored data and convert it into contextual information. The generative AI model integrates multiple input data and generates context, such as "the user is commuting to work and exercising by bicycle."

[0419] Input: Raw data retrieved from the database.

[0420] Output: Interpreted context information.

[0421] Step 6: Share contextual information

[0422] The server shares the interpreted contextual information with multiple system agents, sending the information to the agents' API endpoints using HTTP POST requests.

[0423] Input: Interpreted context information.

[0424] Output: Data sent to the system agent.

[0425] Step 7: Generate a personalized message

[0426] Based on the contextual information received, the AI ​​agent uses a generative AI model to generate a personalized response for the user.

[0427] Input: Context information sent by the server.

[0428] Output: The generated personalized message (e.g., "Hey, I see you're cycling to work. Be safe, and remember to stay hydrated since you're exercising.").

[0429] Step 8: User Notification

[0430] The AI ​​agent generates a message and sends it to the user's device, using push notifications or in-app notifications.

[0431] Input: The generated personalized message.

[0432] Output: The message displayed on the user's terminal.

[0433] (Application example 1)

[0434] 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."

[0435] Conventional food delivery services have the problem that they can only make uniform suggestions to users, and lack personalized suggestions based on the user's individual behavior and status. In addition, there was no technology that could use user behavioral and emotional data to make optimal suggestions in real time. This resulted in a problem of not improving the quality of the user experience.

[0436] 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.

[0437] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for transmitting the collected data to a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative model, means for sharing the interpreted and visualized data with multiple agents, means for each agent to provide a personalized response to the user based on the shared data, and means for making personalized food delivery suggestions based on the user behavioral data, thereby enabling optimal food delivery suggestions to be made according to the user's behavior and status.

[0438] "Device" means an electronic device, such as a smartphone or sensor, used to collect user behavioral and emotional data.

[0439] "Behavioral data" refers to information about a user's movements, exercise, and device usage.

[0440] "Emotional data" is information that indicates the user's emotional state, such as the user's heart rate, facial expression changes, and voice tone.

[0441] A "cloud database" is a system for storing and managing data that is accessible via the Internet.

[0442] A "generative model" is an artificial intelligence model used to interpret and visualize collected data.

[0443] "Visualization" is the process of displaying data in a graphical format that allows users to intuitively understand it.

[0444] An "agent" is a software program or system that provides responses or suggestions to a user based on collected data.

[0445] "Personalized responses" refer to the provision of messages and services optimized for individual users based on their behavioral and emotional data.

[0446] "Food delivery suggestions" are suggestions to recommend appropriate meals and drinks based on the user's behavior and condition.

[0447] A specific system for implementing the present invention is configured as follows.

[0448] Data collection

[0449] The device collects user behavioral and emotional data in real time. To do this, it uses smartphones, wearable devices, and sensors. Examples include smartphone GPS sensors, acceleration sensors, and heart rate sensors. Data collected from these sensors includes the user's location, amount of exercise, and heart rate. This allows it to understand whether the user is commuting, exercising, or relaxing.

[0450] Specific examples

[0451] When a user is exercising by bicycle, the device uses the GPS sensor, accelerometer, and heart rate sensor to collect the user's location, exercise volume, and heart rate.

[0452] Data transmission

[0453] The device sends the collected data to the server using a proprietary protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0454] Data accumulation and interpretation

[0455] The server stores the received data in a cloud database. This cloud database uses a technology suitable for storing structured data, such as a NoSQL database. The received data is not only stored as is, but also interpreted using a generative model. Specifically, a GPT model (e.g., GPT-3) is used to interpret the stored data and convert it into context information, such as "the user is exercising by riding a bicycle."

[0456] Sharing contextual information

[0457] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0458] Providing a personalized experience

[0459] The agent provides personalized food delivery suggestions to the user based on the latest contextual information retrieved from the server, and the responses are generated based on the contextual information interpreted using the generative model.

[0460] Specific examples

[0461] If the user is exercising by bicycle, the agent will make a suggestion such as, "You're currently exercising by bicycle. Good job! If you want to have a high-protein meal after exercise, we recommend a protein shake."

[0462] An example of a prompt for the generative AI model is as follows:

[0463] Suggest a high-protein diet for cyclists.

[0464] In this way, users can receive optimal food delivery suggestions based on their behavior and status.

[0465] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0466] Step 1:

[0467] The device collects user behavioral and emotional data. This data is acquired using GPS sensors, accelerometers, heart rate sensors, etc. Inputs include location information, exercise volume, and heart rate. The output here is the collected raw data.

[0468] Step 2:

[0469] The terminal packages the collected data into JSON format and sends it to the server using an HTTP POST request. The input is the raw data obtained in step 1, and the output is the packaged data sent to the server without delay.

[0470] Step 3:

[0471] The server stores the received data in a cloud database, which may be a NoSQL database or similar. The input is the data sent in step 2, and the output is the data securely stored in the cloud database.

[0472] Step 4:

[0473] The server interprets and visualizes the accumulated data using a generative model (e.g., GPT-3). The input is raw data stored in a cloud database, and the output is interpreted and visualized contextual information. Specifically, the server analyzes the data and generates contextual information such as "the user is exercising by riding a bicycle."

[0474] Step 5:

[0475] The server shares the interpreted and visualized contextual information with multiple agents by sending it via an HTTP POST request to the API endpoint of each agent. The input is the interpreted and visualized contextual information, and the output is the data shared with each agent.

[0476] Step 6:

[0477] The agent makes personalized food delivery suggestions based on contextual information retrieved from the server. These suggestions are generated based on contextual information interpreted using a generative AI model. The input is the shared contextual information, and the output is personalized messages and suggestions provided to the user.

[0478] Specifically, if the user is exercising by bicycle, the agent will suggest, "You're currently exercising by bicycle. Good work! If you want to have a high-protein meal after your exercise, we recommend a protein shake." An example of a prompt sentence for the generative AI model is as follows:

[0479] Suggest a high-protein diet for cyclists.

[0480] 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.

[0481] A specific system for implementing the present invention is configured as follows.

[0482] Data collection

[0483] The device uses various sensors installed in smartphones and wearable devices to collect user behavioral and emotional data. These include GPS sensors, acceleration sensors, and heart rate sensors. These sensors are used to collect user location information, movement patterns, and vital sign data. Furthermore, facial expression and voice recognition technologies are used to collect user emotional data in real time.

[0484] Using the Emotion Engine

[0485] The device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and vital sign data. Based on the analysis results, the emotion engine identifies the user's emotional state. The emotion engine uses high-performance image and voice recognition algorithms to infer the user's emotions in real time from the collected data.

[0486] Data transmission

[0487] The terminals send the collected and analyzed data to the server using a dedicated protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0488] Data accumulation and interpretation

[0489] The server stores the received data in a cloud database. Because the cloud database uses a NoSQL database, the received data is structured and stored efficiently. The GPT model is then used to analyze the stored data and interpret its meaning. Specifically, it generates contextual information such as "Currently exercising by bicycle" based on the user's behavioral patterns and emotional state.

[0490] Sharing contextual information

[0491] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information via HTTP POST requests to each agent's API endpoint, ensuring consistent data sharing across different platforms and agents.

[0492] Providing a personalized experience

[0493] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. This response is generated based on the contextual information interpreted using a generative model. For example, if the AI ​​agent detects that a user is cycling to work and feeling stressed, it will provide the user with a personalized message such as, "Hello, I see you are cycling to work. Please be careful and make sure you drink plenty of water while exercising."

[0494] Specific examples

[0495] User behavior and sentiment data collection

[0496] The device (e.g., a smartphone) uses GPS and an acceleration sensor to detect that the user is riding a bicycle. If the heart rate sensor detects an abnormally high heart rate, the emotion engine infers that the user is in a stressed state. This indicates that the user is feeling stressed during their commute.

[0497] Data transmission and cloud storage

[0498] The collected and analyzed data is sent to a server and stored in a cloud database. The accumulated data is then converted into context information using a generative model, such as "The user is commuting by bicycle and feeling stressed."

[0499] Context sharing and response

[0500] Contextual information is shared among authorized agents, and the AI ​​agent can use this information to respond to the user, for example, providing a personalized message such as, "I see you're cycling to work. Please be careful and remember to take a deep breath to relax."

[0501] This process delivers a consistent and personalized experience across multiple devices and platforms based on user behavior and sentiment.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] The device collects user behavioral and emotional data in real time. Specifically, it uses the smartphone's built-in GPS sensor to determine location and an acceleration sensor to detect movement. It also uses a heart rate sensor to obtain the user's heart rate and estimates their emotional state. It also uses a camera to recognize facial expressions and analyze emotions from the user's face.

[0505] Step 2:

[0506] The device sends the collected data to the server using a dedicated protocol. To ensure the data is accurate, the data is converted to JSON format and sent via an HTTP POST request. The data sent includes location information, movement information, heart rate data, facial expression data, and more.

[0507] Step 3:

[0508] The server accumulates the received data in a cloud database. The received data is structured and can be efficiently stored in a NoSQL database. For example, user behavior data is stored in a "location information" field, and emotional data is stored in an "emotional state" field.

[0509] Step 4:

[0510] The server interprets the accumulated data using a generative model. Specifically, the GPT model analyzes the relationships in the data and generates meaningful context information that summarizes the user's situation and emotions. For example, it generates the context "The user is currently commuting by bicycle and feeling stressed."

[0511] Step 5:

[0512] The server shares the interpreted and visualized data with multiple authorized agents, sending the interpreted contextual information via HTTP POST requests to each agent's API endpoint. This process ensures consistent data sharing across different platforms and agents.

[0513] Step 6:

[0514] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative model to generate appropriate responses based on the contextual information. For example, if a user is commuting by bicycle and feeling stressed, it can provide a message like, "Hello, I see you're commuting by bicycle. Please be safe. And it might be a good idea to take a deep breath to relax."

[0515] Step 7:

[0516] The user receives a personalized response from the AI ​​agent, and can provide feedback as needed to improve the system's accuracy and user experience. For example, users can evaluate whether the message provided was helpful and provide feedback to the agent to refine future responses.

[0517] Example 2

[0518] 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."

[0519] There are few systems that can collect user behavioral and emotional data in real time, analyze it efficiently, and provide personalized responses. Furthermore, there are problems with properly analyzing this data, generating consistent contextual information, and sharing it with multiple agents. This creates the risk of delays and reduced quality in providing the optimal personalized experience to users.

[0520] 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.

[0521] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for transmitting the collected data to the server, means for storing the data received by the server in a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative AI model, means for sharing the interpreted and visualized data with multiple agents, and means for each agent to provide a personalized response to the user based on the shared data. This makes it possible to efficiently collect and analyze user behavioral and emotional data and provide a personalized response in real time.

[0522] "Terminal" refers to equipment or devices used to collect user behavioral and emotional data.

[0523] "Behavioral data" refers to information about a user's physical activities, such as their location and movement patterns.

[0524] "Emotional data" refers to data that indicates the user's emotional state, and refers to information collected from facial expressions, voice, vital signs, etc.

[0525] "Server" refers to a computer system that has the function of receiving, storing, analyzing, and sharing collected data.

[0526] A "cloud database" is a database that can be accessed via the Internet and is a system that efficiently stores and manages data.

[0527] A "generative AI model" refers to an algorithm that uses machine learning techniques to analyze input data and generate meaning and context.

[0528] An "agent" is a software or system that uses interpreted and visualized data to provide a personalized response to the user.

[0529] "Personalized responses" refer to customized messages and interactions that are specific to a user's particular situation or state.

[0530] The present invention relates to a system that collects and analyzes user behavioral and emotional data in real time to provide users with personalized responses. The system is composed of multiple terminals, a server, and agents.

[0531] Data collection

[0532] Devices are used to collect user behavioral and emotional data. Specifically, GPS sensors, acceleration sensors, heart rate sensors, facial recognition, and voice recognition technologies are used in smartphones and wearable devices. These sensors collect location information, movement patterns, vital data such as heart rate, and emotional data from the user's facial expressions and voice.

[0533] Using the Emotion Engine

[0534] The device is equipped with an emotion engine that analyzes the collected data to identify the user's emotional state in real time. Using high-performance image and voice recognition algorithms, it is able to estimate the user's stress level, joy, anger, and other emotions.

[0535] Data transmission

[0536] The terminals send the collected and analyzed data to the server using a dedicated protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent to the server via an HTTP POST request.

[0537] Data accumulation and interpretation

[0538] The server stores the received data in a cloud database. This cloud database uses a NoSQL database, which allows for efficient data storage and management. The stored data is then analyzed using a generative AI model (e.g., GPT-3) to generate contextual information. This provides contextual information based on the user's behavioral patterns and emotional state (e.g., "The user is commuting by bicycle and feeling stressed").

[0539] Sharing contextual information

[0540] The server sends an HTTP POST request to each agent's API endpoint to share the interpreted and visualized contextual information with multiple agents, allowing data to be shared consistently across different platforms and agents.

[0541] Providing a personalized experience

[0542] The AI ​​agent uses the latest contextual information retrieved from the cloud to provide personalized responses to users. These responses are generated based on contextual information interpreted using a generative AI model. For example, if the AI ​​agent detects that a user is cycling to work and feeling stressed, it might provide a personalized message to the user such as, "Hello, I see you're cycling to work. Please be careful and make sure you drink plenty of water while exercising."

[0543] Specific examples

[0544] The device (e.g., a smartphone) uses GPS and an acceleration sensor to detect that the user is cycling. If the heart rate sensor detects an abnormally high heart rate, the emotion engine infers that the user is in a state of stress. This indicates that the user is feeling stressed while commuting. The collected and analyzed data is sent to a server and stored in a cloud database. The accumulated data is analyzed using a generative AI model and converted into context information, such as "The user is feeling stressed while commuting by bicycle." The context information is shared with multiple authorized agents, and the AI ​​agents respond to the user based on this information. For example, they might provide a personalized message such as, "You're currently cycling to work. Please be careful and remember to take deep breaths to relax."

[0545] Prompt Sentence Examples

[0546] "Generate a message to be sent when a user is cycling to work and is estimated to have a high heart rate and be in a stressed state."

[0547] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0548] Step 1: Data collection

[0549] Terminals (smartphones and wearable devices) use GPS sensors, acceleration sensors, heart rate sensors, facial recognition, and voice recognition technology to collect user behavioral and emotional data in real time. Specifically, the terminal uses a GPS sensor to obtain the user's location information (latitude and longitude), and an acceleration sensor to detect movement patterns. Furthermore, the heart rate sensor collects vital sign data, and facial recognition and voice recognition technology analyzes emotional data. The input data is this sensor information, and the output data is the collected comprehensive data. For example, data such as "latitude: 35.6581, longitude: 139.7514, heart rate: 85 bpm, emotion: stress" can be obtained.

[0550] Step 2: Analysis by the emotion engine

[0551] The emotion engine installed on the device analyzes the collected facial expression, voice, and vital sign data to identify the user's emotional state. The input here is the comprehensive data obtained in step 1. The emotion engine analyzes the data using image and voice recognition algorithms and estimates the emotional state (e.g., stress, joy, anger, etc.) in real time. The output data is the analysis result, specifically including information such as "the user is feeling stressed."

[0552] Step 3: Send data

[0553] The device sends the collected and analyzed data to the server using a dedicated protocol. The input data here is the data analyzed by the emotion engine. This data is packaged in a standard format such as JSON and sent to the server via an HTTP POST request. Specifically, the data is converted to JSON and sent in the format {"location":{"lat":35.6581,"lon":139.7514},"heart_rate":85,"emotion":"stress"}. The output data is the data received by the server.

[0554] Step 4: Data accumulation and interpretation

[0555] The server stores the data received from the device in a cloud database. The input data here is the data received in step 3. A NoSQL database is used for the cloud database, allowing data to be efficiently stored and managed. Next, the server analyzes the stored data using a generative AI model (e.g., GPT-3) to generate contextual information. For example, the AI ​​model may interpret this as "the user is commuting by bicycle and feeling stressed." The output data is the analyzed contextual information.

[0556] Step 5: Share contextual information

[0557] The server shares the interpreted and visualized contextual information with multiple agents. The input data here is the contextual information generated in step 4. The server sends an HTTP POST request to the API endpoint of each agent to share the contextual information. Specifically, it sends data such as {"context":"cycling to work with stress"} to each agent. The output data is the contextual information sent to each agent.

[0558] Step 6: Deliver a personalized experience

[0559] The AI ​​agent provides a personalized response to the user based on the latest contextual information retrieved from the cloud. The input data here is the contextual information shared in step 5. The AI ​​agent uses the generative AI model to generate a response and displays it on the user's device. For example, if the AI ​​agent detects that the user is cycling to work and feeling stressed, it generates a message such as, "You're currently commuting. Please be careful and remember to take a deep breath to relax." The output data is the personalized message provided to the user.

[0560] (Application example 2)

[0561] 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."

[0562] Conventional food delivery services provide uniform menu recommendations without considering the user's current situation or emotional state, resulting in limited user experience and low satisfaction. Furthermore, they lacked personalized services tailored to the user's specific circumstances, making it difficult to meet individual needs. This made it difficult to improve user engagement and retention.

[0563] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0564] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple information processing devices in real time, means for transmitting the collected data to a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative model, means for sharing the interpreted and visualized data with multiple knowledge agents, means for each knowledge agent to provide a personalized response to the user based on the shared data, and means for providing optimal menus and promotional information based on the user behavioral data and emotional data, thereby enabling the provision of a personalized food delivery service according to the user's current situation and emotional state.

[0565] An "information processing device" is a device that includes hardware and software for acquiring and processing user behavioral data and emotion data.

[0566] "Behavioral data" refers to data related to a user's physical behavior, such as location information and movement patterns.

[0567] "Emotional data" refers to data that indicates the user's physiological and psychological state, such as heart rate and facial expression analysis.

[0568] A "cloud database" is a database system for storing, managing, and analyzing data in a cloud computing environment.

[0569] A "generative model" refers to a machine learning algorithm that analyzes large amounts of data, recognizes patterns, and generates new information.

[0570] A "knowledge agent" is an artificial intelligence agent that is trained to perform specific tasks and provide information to the user.

[0571] A "personalized response" is a response that is individually optimized based on a user's behavioral and emotional data.

[0572] "Menu and promotion information" refers to information about food options and special offers offered through food delivery services.

[0573] "User context" refers to information about the user's current environment and situation.

[0574] A system required to implement this invention includes an information processing system operating as a smartphone application, which includes a smartphone that collects user behavioral and emotional data, a cloud database that processes and stores the data, a generative model that interprets and visualizes the data, and a knowledge agent that provides personalized responses to the user.

[0575] First, the smartphone uses a GPS sensor, an acceleration sensor, a heart rate sensor, and a facial expression analysis camera to collect user behavioral data (location information and movement patterns) and emotional data (emotional state estimated from heart rate and facial expressions) in real time. This information is structured and sent to a cloud database. The cloud database uses a fast-access NoSQL database, which stores data in real time and analyzes it using a generative model.

[0576] Next, a generative model running on the server analyzes the collected behavioral and emotional data to generate the user's current contextual information, which is expressed as detailed situational information such as "I am currently exercising by riding a bicycle" based on the user's behavioral patterns and emotional state.

[0577] The generated contextual information is shared with multiple knowledge agents via an API endpoint. Based on this contextual information, the knowledge agents generate optimal responses for the user. These responses are presented as optimal menus and promotional information offered by food delivery services. For example, if the system detects that the user is tired, it can recommend stamina-boosting dishes.

[0578] For example, the flow is as follows:

[0579] 1. If a user is cycling to work and their heart rate is high, the smartphone sensor will detect this and the emotion engine will determine that the user is tired.

[0580] 2. This data is sent to a cloud database, where a generative model generates contextual information such as "the user is tired from riding a bicycle."

[0581] 3. Contextual information is shared with knowledge agents via APIs to create personalized responses, such as suggesting menus that will energize a tired user.

[0582] 4. As a result, the user's smartphone application will display a message such as, "You look tired. Would you like some food to give you some energy?"

[0583] Examples of prompts include:

[0584] "Is your current heart rate normal?"

[0585] "How accurately do the sensors track your movements?"

[0586] "What are some specific examples of menu suggestions when your emotional state is fatigued?"

[0587] In this way, a system can be realized that provides a personalized experience based on the user's real-time state and emotions.

[0588] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0589] Step 1:

[0590] Smartphones (devices) use built-in GPS sensors, acceleration sensors, heart rate sensors, and facial expression analysis cameras to collect real-time data on the user's location, movement patterns, heart rate, and facial expression. This data is collected as user behavioral and emotional data. The input is data from the sensors, and the output is structured behavioral and emotional data.

[0591] Step 2:

[0592] The device structures the collected behavioral and emotional data and sends it to the cloud database. Specifically, it converts the collected data into JSON format and sends it to the cloud database using an HTTP POST request. The input is the data collected in step 1, and the output is storage in the cloud database.

[0593] Step 3:

[0594] The server analyzes the data stored in the cloud database using a generative model (e.g., GPT-3) to generate the user's current contextual information. The generative model learns behavioral and emotional data, recognizes patterns, and generates specific contextual information such as "I am currently exercising by riding a bicycle." The input is the data stored in the cloud database, and the output is interpreted contextual information.

[0595] Step 4:

[0596] The server shares the generated context information with multiple knowledge agents through an API endpoint. Specifically, it sends the interpreted context information to each knowledge agent's API using an HTTP POST request. The input is the interpreted context information, and the output is data sent to each knowledge agent.

[0597] Step 5:

[0598] The knowledge agent generates the optimal response for the user based on the shared contextual information. For example, if it determines that the user is tired, it generates recommendations for stamina-boosting dishes. The input is contextual information, and the output is a personalized response.

[0599] Step 6:

[0600] The terminal displays the personalized response received from the knowledge agent to the user. For example, it displays a message such as, "You seem tired. Would you like some food that will give you energy?" The input is the response from the knowledge agent, and the output is the message displayed to the user.

[0601] 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.

[0602] 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.

[0603] 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.

[0604] [Third embodiment]

[0605] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0606] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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).

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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."

[0617] A specific system for implementing the present invention is configured as follows.

[0618] Data collection

[0619] The device collects user behavioral and emotional data in real time. To do this, it uses smartphones, wearable devices, and sensors. Examples include smartphone GPS sensors, acceleration sensors, and heart rate sensors. Data collected from these sensors includes the user's location, amount of exercise, and heart rate. This allows it to understand whether the user is commuting, exercising, or relaxing.

[0620] Data transmission

[0621] The device sends the collected data to the server using a proprietary protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0622] Data accumulation and interpretation

[0623] The server stores the received data in a cloud database. This cloud database uses a technology suitable for storing structured data, such as a NoSQL database. The received data is not only stored as is, but also interpreted using a generative model. Specifically, a GPT model (e.g., GPT-3) is used to interpret the stored data and convert it into context information, such as "the user is commuting to work and exercising by bicycle."

[0624] Sharing contextual information

[0625] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0626] Providing a personalized experience

[0627] The AI ​​agent uses the latest contextual information retrieved from the cloud to provide personalized responses to users. These responses are generated based on contextual information interpreted using a generative model. For example, if the agent detects that the user is commuting, it might provide a personalized message such as, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0628] Specific examples

[0629] User behavior data collection

[0630] The device (e.g., a smartphone) uses GPS and an accelerometer to detect that the user is riding a bicycle, indicating that the user is commuting and exercising.

[0631] Data transmission and cloud storage

[0632] The collected behavioral data is sent to a server and stored in a cloud database. The stored data is then converted into context information using a generative model, such as "the user is commuting to work and exercising by bicycle."

[0633] Context sharing and response

[0634] Contextual information is shared among multiple authorized agents, and each agent can use this information to respond to the user. For example, an agent could provide a personalized message to the user: "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0635] This process ensures that users have a consistent and personalized experience across multiple devices and platforms.

[0636] The processing flow will be explained below.

[0637] Step 1:

[0638] The device collects user behavioral and emotional data in real time using sensors in the smartphone or wearable device, such as a GPS sensor to obtain location information and an acceleration sensor to detect movement patterns, and a heart rate sensor to collect heart rate data and estimate the user's emotional state.

[0639] Step 2:

[0640] The device sends the collected data to the server using a proprietary protocol, using HTTP POST requests and packaging the data in JSON format, ensuring real-time transmission without delay.

[0641] Step 3:

[0642] The server stores the received data in a cloud database. A NoSQL database is used, and the received data is structured and stored. For example, user behavior data and emotional data are stored in separate fields.

[0643] Step 4:

[0644] The server interprets the accumulated data using a generative model. Specifically, it analyzes the accumulated data using a GPT model and interprets the meaning of the data. For example, it generates contextual information such as "The user is currently exercising by riding a bicycle."

[0645] Step 5:

[0646] The server shares the interpreted and visualized data with multiple authorized agents, sending the interpreted data to each agent's API endpoint using an HTTP POST request, allowing data to be shared consistently across different platforms and services.

[0647] Step 6:

[0648] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative model to generate appropriate responses based on the contextual information. For example, if it detects that the user is commuting by bicycle, it can provide a message like, "Hello, I see you're commuting by bicycle. Please be safe. And since you're exercising, don't forget to stay hydrated."

[0649] Step 7:

[0650] The user receives a personalized response from the AI ​​agent and can provide feedback as needed to improve the system's accuracy and user experience. For example, the user can evaluate whether the message provided was helpful and provide feedback to the agent to further refine the response next time.

[0651] Example 1

[0652] 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."

[0653] In today's world, there is a need to consistently collect and interpret user behavioral and emotional data in real time across multiple devices and platforms, and provide personalized responses. However, there is a lack of effective means to efficiently collect, analyze, and share this data. In addition, to provide a consistent user experience across different devices and platforms, issues such as data latency and inconsistency must be resolved.

[0654] 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.

[0655] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for formatting the collected data in a standard format and transmitting it to the server, means for storing the data received by the server in a cloud database, means for interpreting and converting the stored data into contextual information using a generative AI model, means for sharing the interpreted and visualized data with multiple system agents, and means for each system agent to provide a personalized response to the user based on the shared data, thereby enabling a consistent and personalized user experience in real time across multiple different devices and platforms.

[0656] "Device" is a general term for hardware and software that has specific functions such as collecting, transmitting, and displaying data.

[0657] "Behavioral data" refers to data related to a user's physical movements, such as the user's location, amount of exercise, and means of transportation.

[0658] "Emotional Data" is data related to a user's psychological and physiological state, such as a user's heart rate, stress level, or emotional state.

[0659] "Real-time" means that data is processed and used immediately after collection, with little or no delay.

[0660] A "standard format" is a structured representation of data based on a specific protocol or format that allows it to be compatible with other systems and devices. Examples include JSON and XML.

[0661] A "generative AI model" is an algorithm or system that uses machine learning and artificial intelligence techniques to generate new information and context from data. An example of this is the GPT model.

[0662] "Context information" is information that indicates the user's situation or state, generated based on collected data.

[0663] A "system agent" is software or hardware that provides specific functions or services and is responsible for direct interaction with the user.

[0664] "Personalized responses" refer to messages and information that are customized based on individual user data and context.

[0665] A "cloud database" is a remote database system accessible via the Internet that provides scalable data storage and processing capabilities.

[0666] A specific system for implementing this invention includes a series of processes for collecting user behavioral and emotional data in real time and providing personalized responses based on that data, as described in detail below.

[0667] Data collection

[0668] The device uses smartphones and wearable devices to collect user behavioral and emotional data. Specific sensors used for this purpose include GPS sensors, acceleration sensors, and heart rate sensors. This allows the device to collect information on the user's location, amount of exercise, heart rate, etc., and to understand whether the user is commuting, exercising, or relaxing.

[0669] Data transmission

[0670] The device sends the collected data to the server using a dedicated protocol (e.g., MQTT or HTTP). The data is sent in real time and guaranteed to be delivered without delay. The data is packaged in a standard format (e.g., JSON) and sent as an HTTP POST request.

[0671] Data accumulation and interpretation

[0672] The server stores the received data in a cloud database. This cloud database uses a NoSQL database (e.g., MongoDB) for scalable and efficient data storage. The stored data is interpreted using a generative AI model (e.g., GPT-3) and converted into context information, such as "the user is commuting to work and exercising by bicycle."

[0673] Sharing contextual information

[0674] The server shares the interpreted and visualized data with multiple system agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0675] Providing a personalized experience

[0676] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative AI model to generate messages tailored to the user's situation. For example, if it detects that the user is commuting, the agent might provide a message like, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0677] Specific examples

[0678] Data Collection Example

[0679] A device (e.g., a smartphone) uses its GPS sensor and accelerometer during your morning commute to collect the following data: "latitude: 35.6895, longitude: 139.6917, activity: cycling".

[0680] Data transmission example

[0681] The collected data is sent to a cloud server in real time using HTTP POST requests.

[0682] Examples of data accumulation and interpretation

[0683] The server stores the received data in a cloud database and uses a generative AI model (GPT-3) to convert it into contextual information such as "the user is commuting to work and exercising by bicycle."

[0684] Examples of sharing and responding to contextual information

[0685] The server sends the interpreted data to the AI ​​agent's API endpoint, and the AI ​​agent then sends a personalized push notification to the user's smartphone saying, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, don't forget to stay hydrated."

[0686] Prompt Sentence Examples

[0687] “What message do you provide if you detect that a user is cycling to work?”

[0688] In this way, users receive useful information and advice in real time.

[0689] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0690] Step 1: Data collection

[0691] The device acquires sensor information. Specifically, it uses the GPS sensor, acceleration sensor, heart rate sensor, etc. of the smartphone or wearable device to collect data such as location information, exercise volume, and heart rate.

[0692] Input: The user's physical actions and physiological state.

[0693] Output: Data formatted in JSON (e.g. "latitude: 35.6895, longitude: 139.6917, heart_rate: 75, activity: cycling").

[0694] Step 2: Sending data

[0695] The device sends the collected data to the server using an HTTP POST request in real time without delay.

[0696] Input: Data formatted in JSON format.

[0697] Output: The data sent to the server.

[0698] Step 3: Data reception and verification

[0699] The server receives the data and validates the format and content.

[0700] Input: Data sent from the terminal.

[0701] Output: Validated data.

[0702] Step 4: Data accumulation

[0703] The server stores the validated data in a cloud database, which uses NoSQL database technology (e.g., MongoDB).

[0704] Input: Validated data.

[0705] Output: Data stored in the database.

[0706] Step 5: Data interpretation

[0707] The server uses a generative AI model (e.g., GPT-3) to interpret the stored data and convert it into contextual information. The generative AI model integrates multiple input data and generates context, such as "the user is commuting to work and exercising by bicycle."

[0708] Input: Raw data retrieved from the database.

[0709] Output: Interpreted context information.

[0710] Step 6: Share contextual information

[0711] The server shares the interpreted contextual information with multiple system agents, sending the information to the agents' API endpoints using HTTP POST requests.

[0712] Input: Interpreted context information.

[0713] Output: Data sent to the system agent.

[0714] Step 7: Generate a personalized message

[0715] Based on the contextual information received, the AI ​​agent uses a generative AI model to generate a personalized response for the user.

[0716] Input: Context information sent by the server.

[0717] Output: The generated personalized message (e.g., "Hey, I see you're cycling to work. Be safe, and remember to stay hydrated since you're exercising.").

[0718] Step 8: User Notification

[0719] The AI ​​agent generates a message and sends it to the user's device, using push notifications or in-app notifications.

[0720] Input: The generated personalized message.

[0721] Output: The message displayed on the user's terminal.

[0722] (Application example 1)

[0723] 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."

[0724] Conventional food delivery services have the problem that they can only make uniform suggestions to users, and lack personalized suggestions based on the user's individual behavior and status. In addition, there was no technology that could use user behavioral and emotional data to make optimal suggestions in real time. This resulted in a problem of not improving the quality of the user experience.

[0725] 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.

[0726] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for transmitting the collected data to a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative model, means for sharing the interpreted and visualized data with multiple agents, means for each agent to provide a personalized response to the user based on the shared data, and means for making personalized food delivery suggestions based on the user behavioral data, thereby enabling optimal food delivery suggestions to be made according to the user's behavior and status.

[0727] "Device" means an electronic device, such as a smartphone or sensor, used to collect user behavioral and emotional data.

[0728] "Behavioral data" refers to information about a user's movements, exercise, and device usage.

[0729] "Emotional data" is information that indicates the user's emotional state, such as the user's heart rate, facial expression changes, and voice tone.

[0730] A "cloud database" is a system for storing and managing data that is accessible via the Internet.

[0731] A "generative model" is an artificial intelligence model used to interpret and visualize collected data.

[0732] "Visualization" is the process of displaying data in a graphical format that allows users to intuitively understand it.

[0733] An "agent" is a software program or system that provides responses or suggestions to a user based on collected data.

[0734] "Personalized responses" refer to the provision of messages and services optimized for individual users based on their behavioral and emotional data.

[0735] "Food delivery suggestions" are suggestions to recommend appropriate meals and drinks based on the user's behavior and condition.

[0736] A specific system for implementing the present invention is configured as follows.

[0737] Data collection

[0738] The device collects user behavioral and emotional data in real time. To do this, it uses smartphones, wearable devices, and sensors. Examples include smartphone GPS sensors, acceleration sensors, and heart rate sensors. Data collected from these sensors includes the user's location, amount of exercise, and heart rate. This allows it to understand whether the user is commuting, exercising, or relaxing.

[0739] Specific examples

[0740] When a user is exercising by bicycle, the device uses the GPS sensor, accelerometer, and heart rate sensor to collect the user's location, exercise volume, and heart rate.

[0741] Data transmission

[0742] The device sends the collected data to the server using a proprietary protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0743] Data accumulation and interpretation

[0744] The server stores the received data in a cloud database. This cloud database uses a technology suitable for storing structured data, such as a NoSQL database. The received data is not only stored as is, but also interpreted using a generative model. Specifically, a GPT model (e.g., GPT-3) is used to interpret the stored data and convert it into context information, such as "the user is exercising by riding a bicycle."

[0745] Sharing contextual information

[0746] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0747] Providing a personalized experience

[0748] The agent provides personalized food delivery suggestions to the user based on the latest contextual information retrieved from the server, and the responses are generated based on the contextual information interpreted using the generative model.

[0749] Specific examples

[0750] If the user is exercising by bicycle, the agent will make a suggestion such as, "You're currently exercising by bicycle. Good job! If you want to have a high-protein meal after exercise, we recommend a protein shake."

[0751] An example of a prompt for the generative AI model is as follows:

[0752] Suggest a high-protein diet for cyclists.

[0753] In this way, users can receive optimal food delivery suggestions based on their behavior and status.

[0754] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0755] Step 1:

[0756] The device collects user behavioral and emotional data. This data is acquired using GPS sensors, accelerometers, heart rate sensors, etc. Inputs include location information, exercise volume, and heart rate. The output here is the collected raw data.

[0757] Step 2:

[0758] The terminal packages the collected data into JSON format and sends it to the server using an HTTP POST request. The input is the raw data obtained in step 1, and the output is the packaged data sent to the server without delay.

[0759] Step 3:

[0760] The server stores the received data in a cloud database, which may be a NoSQL database or similar. The input is the data sent in step 2, and the output is the data securely stored in the cloud database.

[0761] Step 4:

[0762] The server interprets and visualizes the accumulated data using a generative model (e.g., GPT-3). The input is raw data stored in a cloud database, and the output is interpreted and visualized contextual information. Specifically, the server analyzes the data and generates contextual information such as "the user is exercising by riding a bicycle."

[0763] Step 5:

[0764] The server shares the interpreted and visualized contextual information with multiple agents by sending it via an HTTP POST request to the API endpoint of each agent. The input is the interpreted and visualized contextual information, and the output is the data shared with each agent.

[0765] Step 6:

[0766] The agent makes personalized food delivery suggestions based on contextual information retrieved from the server. These suggestions are generated based on contextual information interpreted using a generative AI model. The input is the shared contextual information, and the output is personalized messages and suggestions provided to the user.

[0767] Specifically, if the user is exercising by bicycle, the agent will suggest, "You're currently exercising by bicycle. Good work! If you want to have a high-protein meal after your exercise, we recommend a protein shake." An example of a prompt sentence for the generative AI model is as follows:

[0768] Suggest a high-protein diet for cyclists.

[0769] 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.

[0770] A specific system for implementing the present invention is configured as follows.

[0771] Data collection

[0772] The device uses various sensors installed in smartphones and wearable devices to collect user behavioral and emotional data. These include GPS sensors, acceleration sensors, and heart rate sensors. These sensors are used to collect user location information, movement patterns, and vital sign data. Furthermore, facial expression and voice recognition technologies are used to collect user emotional data in real time.

[0773] Using the Emotion Engine

[0774] The device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and vital sign data. Based on the analysis results, the emotion engine identifies the user's emotional state. The emotion engine uses high-performance image and voice recognition algorithms to infer the user's emotions in real time from the collected data.

[0775] Data transmission

[0776] The terminals send the collected and analyzed data to the server using a dedicated protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0777] Data accumulation and interpretation

[0778] The server stores the received data in a cloud database. Because the cloud database uses a NoSQL database, the received data is structured and stored efficiently. The GPT model is then used to analyze the stored data and interpret its meaning. Specifically, it generates contextual information such as "Currently exercising by bicycle" based on the user's behavioral patterns and emotional state.

[0779] Sharing contextual information

[0780] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information via HTTP POST requests to each agent's API endpoint, ensuring consistent data sharing across different platforms and agents.

[0781] Providing a personalized experience

[0782] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. This response is generated based on the contextual information interpreted using a generative model. For example, if the AI ​​agent detects that a user is cycling to work and feeling stressed, it will provide the user with a personalized message such as, "Hello, I see you are cycling to work. Please be careful and make sure you drink plenty of water while exercising."

[0783] Specific examples

[0784] User behavior and sentiment data collection

[0785] The device (e.g., a smartphone) uses GPS and an acceleration sensor to detect that the user is riding a bicycle. If the heart rate sensor detects an abnormally high heart rate, the emotion engine infers that the user is in a stressed state. This indicates that the user is feeling stressed during their commute.

[0786] Data transmission and cloud storage

[0787] The collected and analyzed data is sent to a server and stored in a cloud database. The accumulated data is then converted into context information using a generative model, such as "The user is commuting by bicycle and feeling stressed."

[0788] Context sharing and response

[0789] Contextual information is shared among authorized agents, and the AI ​​agent can use this information to respond to the user, for example, providing a personalized message such as, "I see you're cycling to work. Please be careful and remember to take a deep breath to relax."

[0790] This process delivers a consistent and personalized experience across multiple devices and platforms based on user behavior and sentiment.

[0791] The processing flow will be explained below.

[0792] Step 1:

[0793] The device collects user behavioral and emotional data in real time. Specifically, it uses the smartphone's built-in GPS sensor to determine location and an acceleration sensor to detect movement. It also uses a heart rate sensor to obtain the user's heart rate and estimates their emotional state. It also uses a camera to recognize facial expressions and analyze emotions from the user's face.

[0794] Step 2:

[0795] The device sends the collected data to the server using a dedicated protocol. To ensure the data is accurate, the data is converted to JSON format and sent via an HTTP POST request. The data sent includes location information, movement information, heart rate data, facial expression data, and more.

[0796] Step 3:

[0797] The server accumulates the received data in a cloud database. The received data is structured and can be efficiently stored in a NoSQL database. For example, user behavior data is stored in a "location information" field, and emotional data is stored in an "emotional state" field.

[0798] Step 4:

[0799] The server interprets the accumulated data using a generative model. Specifically, the GPT model analyzes the relationships in the data and generates meaningful context information that summarizes the user's situation and emotions. For example, it generates the context "The user is currently commuting by bicycle and feeling stressed."

[0800] Step 5:

[0801] The server shares the interpreted and visualized data with multiple authorized agents, sending the interpreted contextual information via HTTP POST requests to each agent's API endpoint. This process ensures consistent data sharing across different platforms and agents.

[0802] Step 6:

[0803] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative model to generate appropriate responses based on the contextual information. For example, if a user is commuting by bicycle and feeling stressed, it can provide a message like, "Hello, I see you're commuting by bicycle. Please be safe. And it might be a good idea to take a deep breath to relax."

[0804] Step 7:

[0805] The user receives a personalized response from the AI ​​agent, and can provide feedback as needed to improve the system's accuracy and user experience. For example, users can evaluate whether the message provided was helpful and provide feedback to the agent to refine future responses.

[0806] Example 2

[0807] 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."

[0808] There are few systems that can collect user behavioral and emotional data in real time, analyze it efficiently, and provide personalized responses. Furthermore, there are problems with properly analyzing this data, generating consistent contextual information, and sharing it with multiple agents. This creates the risk of delays and reduced quality in providing the optimal personalized experience to users.

[0809] 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.

[0810] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for transmitting the collected data to the server, means for storing the data received by the server in a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative AI model, means for sharing the interpreted and visualized data with multiple agents, and means for each agent to provide a personalized response to the user based on the shared data. This makes it possible to efficiently collect and analyze user behavioral and emotional data and provide a personalized response in real time.

[0811] "Terminal" refers to equipment or devices used to collect user behavioral and emotional data.

[0812] "Behavioral data" refers to information about a user's physical activities, such as their location and movement patterns.

[0813] "Emotional data" refers to data that indicates the user's emotional state, and refers to information collected from facial expressions, voice, vital signs, etc.

[0814] "Server" refers to a computer system that has the function of receiving, storing, analyzing, and sharing collected data.

[0815] A "cloud database" is a database that can be accessed via the Internet and is a system that efficiently stores and manages data.

[0816] A "generative AI model" refers to an algorithm that uses machine learning techniques to analyze input data and generate meaning and context.

[0817] An "agent" is a software or system that uses interpreted and visualized data to provide a personalized response to the user.

[0818] "Personalized responses" refer to customized messages and interactions that are specific to a user's particular situation or state.

[0819] The present invention relates to a system that collects and analyzes user behavioral and emotional data in real time to provide users with personalized responses. The system is composed of multiple terminals, a server, and agents.

[0820] Data collection

[0821] Devices are used to collect user behavioral and emotional data. Specifically, GPS sensors, acceleration sensors, heart rate sensors, facial recognition, and voice recognition technologies are used in smartphones and wearable devices. These sensors collect location information, movement patterns, vital data such as heart rate, and emotional data from the user's facial expressions and voice.

[0822] Using the Emotion Engine

[0823] The device is equipped with an emotion engine that analyzes the collected data to identify the user's emotional state in real time. Using high-performance image and voice recognition algorithms, it is able to estimate the user's stress level, joy, anger, and other emotions.

[0824] Data transmission

[0825] The terminals send the collected and analyzed data to the server using a dedicated protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent to the server via an HTTP POST request.

[0826] Data accumulation and interpretation

[0827] The server stores the received data in a cloud database. This cloud database uses a NoSQL database, which allows for efficient data storage and management. The stored data is then analyzed using a generative AI model (e.g., GPT-3) to generate contextual information. This provides contextual information based on the user's behavioral patterns and emotional state (e.g., "The user is commuting by bicycle and feeling stressed").

[0828] Sharing contextual information

[0829] The server sends an HTTP POST request to each agent's API endpoint to share the interpreted and visualized contextual information with multiple agents, allowing data to be shared consistently across different platforms and agents.

[0830] Providing a personalized experience

[0831] The AI ​​agent uses the latest contextual information retrieved from the cloud to provide personalized responses to users. These responses are generated based on contextual information interpreted using a generative AI model. For example, if the AI ​​agent detects that a user is cycling to work and feeling stressed, it might provide a personalized message to the user such as, "Hello, I see you're cycling to work. Please be careful and make sure you drink plenty of water while exercising."

[0832] Specific examples

[0833] The device (e.g., a smartphone) uses GPS and an acceleration sensor to detect that the user is cycling. If the heart rate sensor detects an abnormally high heart rate, the emotion engine infers that the user is in a state of stress. This indicates that the user is feeling stressed while commuting. The collected and analyzed data is sent to a server and stored in a cloud database. The accumulated data is analyzed using a generative AI model and converted into context information, such as "The user is feeling stressed while commuting by bicycle." The context information is shared with multiple authorized agents, and the AI ​​agents respond to the user based on this information. For example, they might provide a personalized message such as, "You're currently cycling to work. Please be careful and remember to take deep breaths to relax."

[0834] Prompt Sentence Examples

[0835] "Generate a message to be sent when a user is cycling to work and is estimated to have a high heart rate and be in a stressed state."

[0836] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0837] Step 1: Data collection

[0838] Terminals (smartphones and wearable devices) use GPS sensors, acceleration sensors, heart rate sensors, facial recognition, and voice recognition technology to collect user behavioral and emotional data in real time. Specifically, the terminal uses a GPS sensor to obtain the user's location information (latitude and longitude), and an acceleration sensor to detect movement patterns. Furthermore, the heart rate sensor collects vital sign data, and facial recognition and voice recognition technology analyzes emotional data. The input data is this sensor information, and the output data is the collected comprehensive data. For example, data such as "latitude: 35.6581, longitude: 139.7514, heart rate: 85 bpm, emotion: stress" can be obtained.

[0839] Step 2: Analysis by the emotion engine

[0840] The emotion engine installed on the device analyzes the collected facial expression, voice, and vital sign data to identify the user's emotional state. The input here is the comprehensive data obtained in step 1. The emotion engine analyzes the data using image and voice recognition algorithms and estimates the emotional state (e.g., stress, joy, anger, etc.) in real time. The output data is the analysis result, specifically including information such as "the user is feeling stressed."

[0841] Step 3: Send data

[0842] The device sends the collected and analyzed data to the server using a dedicated protocol. The input data here is the data analyzed by the emotion engine. This data is packaged in a standard format such as JSON and sent to the server via an HTTP POST request. Specifically, the data is converted to JSON and sent in the format {"location":{"lat":35.6581,"lon":139.7514},"heart_rate":85,"emotion":"stress"}. The output data is the data received by the server.

[0843] Step 4: Data accumulation and interpretation

[0844] The server stores the data received from the device in a cloud database. The input data here is the data received in step 3. A NoSQL database is used for the cloud database, allowing data to be efficiently stored and managed. Next, the server analyzes the stored data using a generative AI model (e.g., GPT-3) to generate contextual information. For example, the AI ​​model may interpret this as "the user is commuting by bicycle and feeling stressed." The output data is the analyzed contextual information.

[0845] Step 5: Share contextual information

[0846] The server shares the interpreted and visualized contextual information with multiple agents. The input data here is the contextual information generated in step 4. The server sends an HTTP POST request to the API endpoint of each agent to share the contextual information. Specifically, it sends data such as {"context":"cycling to work with stress"} to each agent. The output data is the contextual information sent to each agent.

[0847] Step 6: Deliver a personalized experience

[0848] The AI ​​agent provides a personalized response to the user based on the latest contextual information retrieved from the cloud. The input data here is the contextual information shared in step 5. The AI ​​agent uses the generative AI model to generate a response and displays it on the user's device. For example, if the AI ​​agent detects that the user is cycling to work and feeling stressed, it generates a message such as, "You're currently commuting. Please be careful and remember to take a deep breath to relax." The output data is the personalized message provided to the user.

[0849] (Application example 2)

[0850] 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."

[0851] Conventional food delivery services provide uniform menu recommendations without considering the user's current situation or emotional state, resulting in limited user experience and low satisfaction. Furthermore, they lacked personalized services tailored to the user's specific circumstances, making it difficult to meet individual needs. This made it difficult to improve user engagement and retention.

[0852] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0853] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple information processing devices in real time, means for transmitting the collected data to a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative model, means for sharing the interpreted and visualized data with multiple knowledge agents, means for each knowledge agent to provide a personalized response to the user based on the shared data, and means for providing optimal menus and promotional information based on the user behavioral data and emotional data, thereby enabling the provision of a personalized food delivery service according to the user's current situation and emotional state.

[0854] An "information processing device" is a device that includes hardware and software for acquiring and processing user behavioral data and emotion data.

[0855] "Behavioral data" refers to data related to a user's physical behavior, such as location information and movement patterns.

[0856] "Emotional data" refers to data that indicates the user's physiological and psychological state, such as heart rate and facial expression analysis.

[0857] A "cloud database" is a database system for storing, managing, and analyzing data in a cloud computing environment.

[0858] A "generative model" refers to a machine learning algorithm that analyzes large amounts of data, recognizes patterns, and generates new information.

[0859] A "knowledge agent" is an artificial intelligence agent that is trained to perform specific tasks and provide information to the user.

[0860] A "personalized response" is a response that is individually optimized based on a user's behavioral and emotional data.

[0861] "Menu and promotion information" refers to information about food options and special offers offered through food delivery services.

[0862] "User context" refers to information about the user's current environment and situation.

[0863] A system required to implement this invention includes an information processing system operating as a smartphone application, which includes a smartphone that collects user behavioral and emotional data, a cloud database that processes and stores the data, a generative model that interprets and visualizes the data, and a knowledge agent that provides personalized responses to the user.

[0864] First, the smartphone uses a GPS sensor, an acceleration sensor, a heart rate sensor, and a facial expression analysis camera to collect user behavioral data (location information and movement patterns) and emotional data (emotional state estimated from heart rate and facial expressions) in real time. This information is structured and sent to a cloud database. The cloud database uses a fast-access NoSQL database, which stores data in real time and analyzes it using a generative model.

[0865] Next, a generative model running on the server analyzes the collected behavioral and emotional data to generate the user's current contextual information, which is expressed as detailed situational information such as "I am currently exercising by riding a bicycle" based on the user's behavioral patterns and emotional state.

[0866] The generated contextual information is shared with multiple knowledge agents via an API endpoint. Based on this contextual information, the knowledge agents generate optimal responses for the user. These responses are presented as optimal menus and promotional information offered by food delivery services. For example, if the system detects that the user is tired, it can recommend stamina-boosting dishes.

[0867] For example, the flow is as follows:

[0868] 1. If a user is cycling to work and their heart rate is high, the smartphone sensor will detect this and the emotion engine will determine that the user is tired.

[0869] 2. This data is sent to a cloud database, where a generative model generates contextual information such as "the user is tired from riding a bicycle."

[0870] 3. Contextual information is shared with knowledge agents via APIs to create personalized responses, such as suggesting menus that will energize a tired user.

[0871] 4. As a result, the user's smartphone application will display a message such as, "You look tired. Would you like some food to give you some energy?"

[0872] Examples of prompts include:

[0873] "Is your current heart rate normal?"

[0874] "How accurately do the sensors track your movements?"

[0875] "What are some specific examples of menu suggestions when your emotional state is fatigued?"

[0876] In this way, a system can be realized that provides a personalized experience based on the user's real-time state and emotions.

[0877] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0878] Step 1:

[0879] Smartphones (devices) use built-in GPS sensors, acceleration sensors, heart rate sensors, and facial expression analysis cameras to collect real-time data on the user's location, movement patterns, heart rate, and facial expression. This data is collected as user behavioral and emotional data. The input is data from the sensors, and the output is structured behavioral and emotional data.

[0880] Step 2:

[0881] The device structures the collected behavioral and emotional data and sends it to the cloud database. Specifically, it converts the collected data into JSON format and sends it to the cloud database using an HTTP POST request. The input is the data collected in step 1, and the output is storage in the cloud database.

[0882] Step 3:

[0883] The server analyzes the data stored in the cloud database using a generative model (e.g., GPT-3) to generate the user's current contextual information. The generative model learns behavioral and emotional data, recognizes patterns, and generates specific contextual information such as "I am currently exercising by riding a bicycle." The input is the data stored in the cloud database, and the output is interpreted contextual information.

[0884] Step 4:

[0885] The server shares the generated context information with multiple knowledge agents through an API endpoint. Specifically, it sends the interpreted context information to each knowledge agent's API using an HTTP POST request. The input is the interpreted context information, and the output is data sent to each knowledge agent.

[0886] Step 5:

[0887] The knowledge agent generates the optimal response for the user based on the shared contextual information. For example, if it determines that the user is tired, it generates recommendations for stamina-boosting dishes. The input is contextual information, and the output is a personalized response.

[0888] Step 6:

[0889] The terminal displays the personalized response received from the knowledge agent to the user. For example, it displays a message such as, "You seem tired. Would you like some food that will give you energy?" The input is the response from the knowledge agent, and the output is the message displayed to the user.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] [Fourth embodiment]

[0894] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0895] 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.

[0896] 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).

[0897] 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.

[0898] 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.

[0899] 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).

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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."

[0907] A specific system for implementing the present invention is configured as follows.

[0908] Data collection

[0909] The device collects user behavioral and emotional data in real time. To do this, it uses smartphones, wearable devices, and sensors. Examples include smartphone GPS sensors, acceleration sensors, and heart rate sensors. Data collected from these sensors includes the user's location, amount of exercise, and heart rate. This allows it to understand whether the user is commuting, exercising, or relaxing.

[0910] Data transmission

[0911] The device sends the collected data to the server using a proprietary protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[0912] Data accumulation and interpretation

[0913] The server stores the received data in a cloud database. This cloud database uses a technology suitable for storing structured data, such as a NoSQL database. The received data is not only stored as is, but also interpreted using a generative model. Specifically, a GPT model (e.g., GPT-3) is used to interpret the stored data and convert it into context information, such as "the user is commuting to work and exercising by bicycle."

[0914] Sharing contextual information

[0915] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0916] Providing a personalized experience

[0917] The AI ​​agent uses the latest contextual information retrieved from the cloud to provide personalized responses to users. These responses are generated based on contextual information interpreted using a generative model. For example, if the agent detects that the user is commuting, it might provide a personalized message such as, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0918] Specific examples

[0919] User behavior data collection

[0920] The device (e.g., a smartphone) uses GPS and an accelerometer to detect that the user is riding a bicycle, indicating that the user is commuting and exercising.

[0921] Data transmission and cloud storage

[0922] The collected behavioral data is sent to a server and stored in a cloud database. The stored data is then converted into context information using a generative model, such as "the user is commuting to work and exercising by bicycle."

[0923] Context sharing and response

[0924] Contextual information is shared among multiple authorized agents, and each agent can use this information to respond to the user. For example, an agent could provide a personalized message to the user: "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0925] This process ensures that users have a consistent and personalized experience across multiple devices and platforms.

[0926] The processing flow will be explained below.

[0927] Step 1:

[0928] The device collects user behavioral and emotional data in real time using sensors in the smartphone or wearable device, such as a GPS sensor to obtain location information and an acceleration sensor to detect movement patterns, and a heart rate sensor to collect heart rate data and estimate the user's emotional state.

[0929] Step 2:

[0930] The device sends the collected data to the server using a proprietary protocol, using HTTP POST requests and packaging the data in JSON format, ensuring real-time transmission without delay.

[0931] Step 3:

[0932] The server stores the received data in a cloud database. A NoSQL database is used, and the received data is structured and stored. For example, user behavior data and emotional data are stored in separate fields.

[0933] Step 4:

[0934] The server interprets the accumulated data using a generative model. Specifically, it analyzes the accumulated data using a GPT model and interprets the meaning of the data. For example, it generates contextual information such as "The user is currently exercising by riding a bicycle."

[0935] Step 5:

[0936] The server shares the interpreted and visualized data with multiple authorized agents, sending the interpreted data to each agent's API endpoint using an HTTP POST request, allowing data to be shared consistently across different platforms and services.

[0937] Step 6:

[0938] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative model to generate appropriate responses based on the contextual information. For example, if it detects that the user is commuting by bicycle, it can provide a message like, "Hello, I see you're commuting by bicycle. Please be safe. And since you're exercising, don't forget to stay hydrated."

[0939] Step 7:

[0940] The user receives a personalized response from the AI ​​agent and can provide feedback as needed to improve the system's accuracy and user experience. For example, the user can evaluate whether the message provided was helpful and provide feedback to the agent to further refine the response next time.

[0941] Example 1

[0942] 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."

[0943] In today's world, there is a need to consistently collect and interpret user behavioral and emotional data in real time across multiple devices and platforms, and provide personalized responses. However, there is a lack of effective means to efficiently collect, analyze, and share this data. In addition, to provide a consistent user experience across different devices and platforms, issues such as data latency and inconsistency must be resolved.

[0944] 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.

[0945] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for formatting the collected data in a standard format and transmitting it to the server, means for storing the data received by the server in a cloud database, means for interpreting and converting the stored data into contextual information using a generative AI model, means for sharing the interpreted and visualized data with multiple system agents, and means for each system agent to provide a personalized response to the user based on the shared data, thereby enabling a consistent and personalized user experience in real time across multiple different devices and platforms.

[0946] "Device" is a general term for hardware and software that has specific functions such as collecting, transmitting, and displaying data.

[0947] "Behavioral data" refers to data related to a user's physical movements, such as the user's location, amount of exercise, and means of transportation.

[0948] "Emotional Data" is data related to a user's psychological and physiological state, such as a user's heart rate, stress level, or emotional state.

[0949] "Real-time" means that data is processed and used immediately after collection, with little or no delay.

[0950] A "standard format" is a structured representation of data based on a specific protocol or format that allows it to be compatible with other systems and devices. Examples include JSON and XML.

[0951] A "generative AI model" is an algorithm or system that uses machine learning and artificial intelligence techniques to generate new information and context from data. An example of this is the GPT model.

[0952] "Context information" is information that indicates the user's situation or state, generated based on collected data.

[0953] A "system agent" is software or hardware that provides specific functions or services and is responsible for direct interaction with the user.

[0954] "Personalized responses" refer to messages and information that are customized based on individual user data and context.

[0955] A "cloud database" is a remote database system accessible via the Internet that provides scalable data storage and processing capabilities.

[0956] A specific system for implementing this invention includes a series of processes for collecting user behavioral and emotional data in real time and providing personalized responses based on that data, as described in detail below.

[0957] Data collection

[0958] The device uses smartphones and wearable devices to collect user behavioral and emotional data. Specific sensors used for this purpose include GPS sensors, acceleration sensors, and heart rate sensors. This allows the device to collect information on the user's location, amount of exercise, heart rate, etc., and to understand whether the user is commuting, exercising, or relaxing.

[0959] Data transmission

[0960] The device sends the collected data to the server using a dedicated protocol (e.g., MQTT or HTTP). The data is sent in real time and guaranteed to be delivered without delay. The data is packaged in a standard format (e.g., JSON) and sent as an HTTP POST request.

[0961] Data accumulation and interpretation

[0962] The server stores the received data in a cloud database. This cloud database uses a NoSQL database (e.g., MongoDB) for scalable and efficient data storage. The stored data is interpreted using a generative AI model (e.g., GPT-3) and converted into context information, such as "the user is commuting to work and exercising by bicycle."

[0963] Sharing contextual information

[0964] The server shares the interpreted and visualized data with multiple system agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[0965] Providing a personalized experience

[0966] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative AI model to generate messages tailored to the user's situation. For example, if it detects that the user is commuting, the agent might provide a message like, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, remember to stay hydrated."

[0967] Specific examples

[0968] Data Collection Example

[0969] A device (e.g., a smartphone) uses its GPS sensor and accelerometer during your morning commute to collect the following data: "latitude: 35.6895, longitude: 139.6917, activity: cycling".

[0970] Data transmission example

[0971] The collected data is sent to a cloud server in real time using HTTP POST requests.

[0972] Examples of data accumulation and interpretation

[0973] The server stores the received data in a cloud database and uses a generative AI model (GPT-3) to convert it into contextual information such as "the user is commuting to work and exercising by bicycle."

[0974] Examples of sharing and responding to contextual information

[0975] The server sends the interpreted data to the AI ​​agent's API endpoint, and the AI ​​agent then sends a personalized push notification to the user's smartphone saying, "Hello, I see you're cycling to work. Please be safe, and since you're exercising, don't forget to stay hydrated."

[0976] Prompt Sentence Examples

[0977] “What message do you provide if you detect that a user is cycling to work?”

[0978] In this way, users receive useful information and advice in real time.

[0979] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0980] Step 1: Data collection

[0981] The device acquires sensor information. Specifically, it uses the GPS sensor, acceleration sensor, heart rate sensor, etc. of the smartphone or wearable device to collect data such as location information, exercise volume, and heart rate.

[0982] Input: The user's physical actions and physiological state.

[0983] Output: Data formatted in JSON (e.g. "latitude: 35.6895, longitude: 139.6917, heart_rate: 75, activity: cycling").

[0984] Step 2: Sending data

[0985] The device sends the collected data to the server using an HTTP POST request in real time without delay.

[0986] Input: Data formatted in JSON format.

[0987] Output: The data sent to the server.

[0988] Step 3: Data reception and verification

[0989] The server receives the data and validates the format and content.

[0990] Input: Data sent from the terminal.

[0991] Output: Validated data.

[0992] Step 4: Data accumulation

[0993] The server stores the validated data in a cloud database, which uses NoSQL database technology (e.g., MongoDB).

[0994] Input: Validated data.

[0995] Output: Data stored in the database.

[0996] Step 5: Data interpretation

[0997] The server uses a generative AI model (e.g., GPT-3) to interpret the stored data and convert it into contextual information. The generative AI model integrates multiple input data and generates context, such as "the user is commuting to work and exercising by bicycle."

[0998] Input: Raw data retrieved from the database.

[0999] Output: Interpreted context information.

[1000] Step 6: Share contextual information

[1001] The server shares the interpreted contextual information with multiple system agents, sending the information to the agents' API endpoints using HTTP POST requests.

[1002] Input: Interpreted context information.

[1003] Output: Data sent to the system agent.

[1004] Step 7: Generate a personalized message

[1005] Based on the contextual information received, the AI ​​agent uses a generative AI model to generate a personalized response for the user.

[1006] Input: Context information sent by the server.

[1007] Output: The generated personalized message (e.g., "Hey, I see you're cycling to work. Be safe, and remember to stay hydrated since you're exercising.").

[1008] Step 8: User Notification

[1009] The AI ​​agent generates a message and sends it to the user's device, using push notifications or in-app notifications.

[1010] Input: The generated personalized message.

[1011] Output: The message displayed on the user's terminal.

[1012] (Application example 1)

[1013] 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."

[1014] Conventional food delivery services have the problem that they can only make uniform suggestions to users, and lack personalized suggestions based on the user's individual behavior and status. In addition, there was no technology that could use user behavioral and emotional data to make optimal suggestions in real time. This resulted in a problem of not improving the quality of the user experience.

[1015] 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.

[1016] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for transmitting the collected data to a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative model, means for sharing the interpreted and visualized data with multiple agents, means for each agent to provide a personalized response to the user based on the shared data, and means for making personalized food delivery suggestions based on the user behavioral data, thereby enabling optimal food delivery suggestions to be made according to the user's behavior and status.

[1017] "Device" means an electronic device, such as a smartphone or sensor, used to collect user behavioral and emotional data.

[1018] "Behavioral data" refers to information about a user's movements, exercise, and device usage.

[1019] "Emotional data" is information that indicates the user's emotional state, such as the user's heart rate, facial expression changes, and voice tone.

[1020] A "cloud database" is a system for storing and managing data that is accessible via the Internet.

[1021] A "generative model" is an artificial intelligence model used to interpret and visualize collected data.

[1022] "Visualization" is the process of displaying data in a graphical format that allows users to intuitively understand it.

[1023] An "agent" is a software program or system that provides responses or suggestions to a user based on collected data.

[1024] "Personalized responses" refer to the provision of messages and services optimized for individual users based on their behavioral and emotional data.

[1025] "Food delivery suggestions" are suggestions to recommend appropriate meals and drinks based on the user's behavior and condition.

[1026] A specific system for implementing the present invention is configured as follows.

[1027] Data collection

[1028] The device collects user behavioral and emotional data in real time. To do this, it uses smartphones, wearable devices, and sensors. Examples include smartphone GPS sensors, acceleration sensors, and heart rate sensors. Data collected from these sensors includes the user's location, amount of exercise, and heart rate. This allows it to understand whether the user is commuting, exercising, or relaxing.

[1029] Specific examples

[1030] When a user is exercising by bicycle, the device uses the GPS sensor, accelerometer, and heart rate sensor to collect the user's location, exercise volume, and heart rate.

[1031] Data transmission

[1032] The device sends the collected data to the server using a proprietary protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[1033] Data accumulation and interpretation

[1034] The server stores the received data in a cloud database. This cloud database uses a technology suitable for storing structured data, such as a NoSQL database. The received data is not only stored as is, but also interpreted using a generative model. Specifically, a GPT model (e.g., GPT-3) is used to interpret the stored data and convert it into context information, such as "the user is exercising by riding a bicycle."

[1035] Sharing contextual information

[1036] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information to each agent's API endpoint via HTTP POST requests, allowing consistent data sharing across different platforms and services.

[1037] Providing a personalized experience

[1038] The agent provides personalized food delivery suggestions to the user based on the latest contextual information retrieved from the server, and the responses are generated based on the contextual information interpreted using the generative model.

[1039] Specific examples

[1040] If the user is exercising by bicycle, the agent will make a suggestion such as, "You're currently exercising by bicycle. Good job! If you want to have a high-protein meal after exercise, we recommend a protein shake."

[1041] An example of a prompt for the generative AI model is as follows:

[1042] Suggest a high-protein diet for cyclists.

[1043] In this way, users can receive optimal food delivery suggestions based on their behavior and status.

[1044] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1045] Step 1:

[1046] The device collects user behavioral and emotional data. This data is acquired using GPS sensors, accelerometers, heart rate sensors, etc. Inputs include location information, exercise volume, and heart rate. The output here is the collected raw data.

[1047] Step 2:

[1048] The terminal packages the collected data into JSON format and sends it to the server using an HTTP POST request. The input is the raw data obtained in step 1, and the output is the packaged data sent to the server without delay.

[1049] Step 3:

[1050] The server stores the received data in a cloud database, which may be a NoSQL database or similar. The input is the data sent in step 2, and the output is the data securely stored in the cloud database.

[1051] Step 4:

[1052] The server interprets and visualizes the accumulated data using a generative model (e.g., GPT-3). The input is raw data stored in a cloud database, and the output is interpreted and visualized contextual information. Specifically, the server analyzes the data and generates contextual information such as "the user is exercising by riding a bicycle."

[1053] Step 5:

[1054] The server shares the interpreted and visualized contextual information with multiple agents by sending it via an HTTP POST request to the API endpoint of each agent. The input is the interpreted and visualized contextual information, and the output is the data shared with each agent.

[1055] Step 6:

[1056] The agent makes personalized food delivery suggestions based on contextual information retrieved from the server. These suggestions are generated based on contextual information interpreted using a generative AI model. The input is the shared contextual information, and the output is personalized messages and suggestions provided to the user.

[1057] Specifically, if the user is exercising by bicycle, the agent will suggest, "You're currently exercising by bicycle. Good work! If you want to have a high-protein meal after your exercise, we recommend a protein shake." An example of a prompt sentence for the generative AI model is as follows:

[1058] Suggest a high-protein diet for cyclists.

[1059] 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.

[1060] A specific system for implementing the present invention is configured as follows.

[1061] Data collection

[1062] The device uses various sensors installed in smartphones and wearable devices to collect user behavioral and emotional data. These include GPS sensors, acceleration sensors, and heart rate sensors. These sensors are used to collect user location information, movement patterns, and vital sign data. Furthermore, facial expression and voice recognition technologies are used to collect user emotional data in real time.

[1063] Using the Emotion Engine

[1064] The device is equipped with an emotion engine that analyzes the user's facial expressions, voice, and vital sign data. Based on the analysis results, the emotion engine identifies the user's emotional state. The emotion engine uses high-performance image and voice recognition algorithms to infer the user's emotions in real time from the collected data.

[1065] Data transmission

[1066] The terminals send the collected and analyzed data to the server using a dedicated protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent via an HTTP POST request.

[1067] Data accumulation and interpretation

[1068] The server stores the received data in a cloud database. Because the cloud database uses a NoSQL database, the received data is structured and stored efficiently. The GPT model is then used to analyze the stored data and interpret its meaning. Specifically, it generates contextual information such as "Currently exercising by bicycle" based on the user's behavioral patterns and emotional state.

[1069] Sharing contextual information

[1070] The server shares the interpreted and visualized data with multiple agents by sending the interpreted contextual information via HTTP POST requests to each agent's API endpoint, ensuring consistent data sharing across different platforms and agents.

[1071] Providing a personalized experience

[1072] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. This response is generated based on the contextual information interpreted using a generative model. For example, if the AI ​​agent detects that a user is cycling to work and feeling stressed, it will provide the user with a personalized message such as, "Hello, I see you are cycling to work. Please be careful and make sure you drink plenty of water while exercising."

[1073] Specific examples

[1074] User behavior and sentiment data collection

[1075] The device (e.g., a smartphone) uses GPS and an acceleration sensor to detect that the user is riding a bicycle. If the heart rate sensor detects an abnormally high heart rate, the emotion engine infers that the user is in a stressed state. This indicates that the user is feeling stressed during their commute.

[1076] Data transmission and cloud storage

[1077] The collected and analyzed data is sent to a server and stored in a cloud database. The accumulated data is then converted into context information using a generative model, such as "The user is commuting by bicycle and feeling stressed."

[1078] Context sharing and response

[1079] Contextual information is shared among authorized agents, and the AI ​​agent can use this information to respond to the user, for example, providing a personalized message such as, "I see you're cycling to work. Please be careful and remember to take a deep breath to relax."

[1080] This process delivers a consistent and personalized experience across multiple devices and platforms based on user behavior and sentiment.

[1081] The processing flow will be explained below.

[1082] Step 1:

[1083] The device collects user behavioral and emotional data in real time. Specifically, it uses the smartphone's built-in GPS sensor to determine location and an acceleration sensor to detect movement. It also uses a heart rate sensor to obtain the user's heart rate and estimates their emotional state. It also uses a camera to recognize facial expressions and analyze emotions from the user's face.

[1084] Step 2:

[1085] The device sends the collected data to the server using a dedicated protocol. To ensure the data is accurate, the data is converted to JSON format and sent via an HTTP POST request. The data sent includes location information, movement information, heart rate data, facial expression data, and more.

[1086] Step 3:

[1087] The server accumulates the received data in a cloud database. The received data is structured and can be efficiently stored in a NoSQL database. For example, user behavior data is stored in a "location information" field, and emotional data is stored in an "emotional state" field.

[1088] Step 4:

[1089] The server interprets the accumulated data using a generative model. Specifically, the GPT model analyzes the relationships in the data and generates meaningful context information that summarizes the user's situation and emotions. For example, it generates the context "The user is currently commuting by bicycle and feeling stressed."

[1090] Step 5:

[1091] The server shares the interpreted and visualized data with multiple authorized agents, sending the interpreted contextual information via HTTP POST requests to each agent's API endpoint. This process ensures consistent data sharing across different platforms and agents.

[1092] Step 6:

[1093] The AI ​​agent provides personalized responses to users based on the latest contextual information retrieved from the cloud. It uses a generative model to generate appropriate responses based on the contextual information. For example, if a user is commuting by bicycle and feeling stressed, it can provide a message like, "Hello, I see you're commuting by bicycle. Please be safe. And it might be a good idea to take a deep breath to relax."

[1094] Step 7:

[1095] The user receives a personalized response from the AI ​​agent, and can provide feedback as needed to improve the system's accuracy and user experience. For example, users can evaluate whether the message provided was helpful and provide feedback to the agent to refine future responses.

[1096] Example 2

[1097] 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."

[1098] There are few systems that can collect user behavioral and emotional data in real time, analyze it efficiently, and provide personalized responses. Furthermore, there are problems with properly analyzing this data, generating consistent contextual information, and sharing it with multiple agents. This creates the risk of delays and reduced quality in providing the optimal personalized experience to users.

[1099] 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.

[1100] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple devices in real time, means for transmitting the collected data to the server, means for storing the data received by the server in a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative AI model, means for sharing the interpreted and visualized data with multiple agents, and means for each agent to provide a personalized response to the user based on the shared data. This makes it possible to efficiently collect and analyze user behavioral and emotional data and provide a personalized response in real time.

[1101] "Terminal" refers to equipment or devices used to collect user behavioral and emotional data.

[1102] "Behavioral data" refers to information about a user's physical activities, such as their location and movement patterns.

[1103] "Emotional data" refers to data that indicates the user's emotional state, and refers to information collected from facial expressions, voice, vital signs, etc.

[1104] "Server" refers to a computer system that has the function of receiving, storing, analyzing, and sharing collected data.

[1105] A "cloud database" is a database that can be accessed via the Internet and is a system that efficiently stores and manages data.

[1106] A "generative AI model" refers to an algorithm that uses machine learning techniques to analyze input data and generate meaning and context.

[1107] An "agent" is a software or system that uses interpreted and visualized data to provide a personalized response to the user.

[1108] "Personalized responses" refer to customized messages and interactions that are specific to a user's particular situation or state.

[1109] The present invention relates to a system that collects and analyzes user behavioral and emotional data in real time to provide users with personalized responses. The system is composed of multiple terminals, a server, and agents.

[1110] Data collection

[1111] Devices are used to collect user behavioral and emotional data. Specifically, GPS sensors, acceleration sensors, heart rate sensors, facial recognition, and voice recognition technologies are used in smartphones and wearable devices. These sensors collect location information, movement patterns, vital data such as heart rate, and emotional data from the user's facial expressions and voice.

[1112] Using the Emotion Engine

[1113] The device is equipped with an emotion engine that analyzes the collected data to identify the user's emotional state in real time. Using high-performance image and voice recognition algorithms, it is able to estimate the user's stress level, joy, anger, and other emotions.

[1114] Data transmission

[1115] The terminals send the collected and analyzed data to the server using a dedicated protocol that ensures real-time transmission without delay. The data is packaged in a standard format, such as JSON, and sent to the server via an HTTP POST request.

[1116] Data accumulation and interpretation

[1117] The server stores the received data in a cloud database. This cloud database uses a NoSQL database, which allows for efficient data storage and management. The stored data is then analyzed using a generative AI model (e.g., GPT-3) to generate contextual information. This provides contextual information based on the user's behavioral patterns and emotional state (e.g., "The user is commuting by bicycle and feeling stressed").

[1118] Sharing contextual information

[1119] The server sends an HTTP POST request to each agent's API endpoint to share the interpreted and visualized contextual information with multiple agents, allowing data to be shared consistently across different platforms and agents.

[1120] Providing a personalized experience

[1121] The AI ​​agent uses the latest contextual information retrieved from the cloud to provide personalized responses to users. These responses are generated based on contextual information interpreted using a generative AI model. For example, if the AI ​​agent detects that a user is cycling to work and feeling stressed, it might provide a personalized message to the user such as, "Hello, I see you're cycling to work. Please be careful and make sure you drink plenty of water while exercising."

[1122] Specific examples

[1123] The device (e.g., a smartphone) uses GPS and an acceleration sensor to detect that the user is cycling. If the heart rate sensor detects an abnormally high heart rate, the emotion engine infers that the user is in a state of stress. This indicates that the user is feeling stressed while commuting. The collected and analyzed data is sent to a server and stored in a cloud database. The accumulated data is analyzed using a generative AI model and converted into context information, such as "The user is feeling stressed while commuting by bicycle." The context information is shared with multiple authorized agents, and the AI ​​agents respond to the user based on this information. For example, they might provide a personalized message such as, "You're currently cycling to work. Please be careful and remember to take deep breaths to relax."

[1124] Prompt Sentence Examples

[1125] "Generate a message to be sent when a user is cycling to work and is estimated to have a high heart rate and be in a stressed state."

[1126] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1127] Step 1: Data collection

[1128] Terminals (smartphones and wearable devices) use GPS sensors, acceleration sensors, heart rate sensors, facial recognition, and voice recognition technology to collect user behavioral and emotional data in real time. Specifically, the terminal uses a GPS sensor to obtain the user's location information (latitude and longitude), and an acceleration sensor to detect movement patterns. Furthermore, the heart rate sensor collects vital sign data, and facial recognition and voice recognition technology analyzes emotional data. The input data is this sensor information, and the output data is the collected comprehensive data. For example, data such as "latitude: 35.6581, longitude: 139.7514, heart rate: 85 bpm, emotion: stress" can be obtained.

[1129] Step 2: Analysis by the emotion engine

[1130] The emotion engine installed on the device analyzes the collected facial expression, voice, and vital sign data to identify the user's emotional state. The input here is the comprehensive data obtained in step 1. The emotion engine analyzes the data using image and voice recognition algorithms and estimates the emotional state (e.g., stress, joy, anger, etc.) in real time. The output data is the analysis result, specifically including information such as "the user is feeling stressed."

[1131] Step 3: Send data

[1132] The device sends the collected and analyzed data to the server using a dedicated protocol. The input data here is the data analyzed by the emotion engine. This data is packaged in a standard format such as JSON and sent to the server via an HTTP POST request. Specifically, the data is converted to JSON and sent in the format {"location":{"lat":35.6581,"lon":139.7514},"heart_rate":85,"emotion":"stress"}. The output data is the data received by the server.

[1133] Step 4: Data accumulation and interpretation

[1134] The server stores the data received from the device in a cloud database. The input data here is the data received in step 3. A NoSQL database is used for the cloud database, allowing data to be efficiently stored and managed. Next, the server analyzes the stored data using a generative AI model (e.g., GPT-3) to generate contextual information. For example, the AI ​​model may interpret this as "the user is commuting by bicycle and feeling stressed." The output data is the analyzed contextual information.

[1135] Step 5: Share contextual information

[1136] The server shares the interpreted and visualized contextual information with multiple agents. The input data here is the contextual information generated in step 4. The server sends an HTTP POST request to the API endpoint of each agent to share the contextual information. Specifically, it sends data such as {"context":"cycling to work with stress"} to each agent. The output data is the contextual information sent to each agent.

[1137] Step 6: Deliver a personalized experience

[1138] The AI ​​agent provides a personalized response to the user based on the latest contextual information retrieved from the cloud. The input data here is the contextual information shared in step 5. The AI ​​agent uses the generative AI model to generate a response and displays it on the user's device. For example, if the AI ​​agent detects that the user is cycling to work and feeling stressed, it generates a message such as, "You're currently commuting. Please be careful and remember to take a deep breath to relax." The output data is the personalized message provided to the user.

[1139] (Application example 2)

[1140] 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."

[1141] Conventional food delivery services provide uniform menu recommendations without considering the user's current situation or emotional state, resulting in limited user experience and low satisfaction. Furthermore, they lacked personalized services tailored to the user's specific circumstances, making it difficult to meet individual needs. This made it difficult to improve user engagement and retention.

[1142] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1143] In this invention, the server includes means for collecting user behavioral data and emotional data from multiple information processing devices in real time, means for transmitting the collected data to a cloud database, means for interpreting and visualizing the data stored in the cloud database using a generative model, means for sharing the interpreted and visualized data with multiple knowledge agents, means for each knowledge agent to provide a personalized response to the user based on the shared data, and means for providing optimal menus and promotional information based on the user behavioral data and emotional data, thereby enabling the provision of a personalized food delivery service according to the user's current situation and emotional state.

[1144] An "information processing device" is a device that includes hardware and software for acquiring and processing user behavioral data and emotion data.

[1145] "Behavioral data" refers to data related to a user's physical behavior, such as location information and movement patterns.

[1146] "Emotional data" refers to data that indicates the user's physiological and psychological state, such as heart rate and facial expression analysis.

[1147] A "cloud database" is a database system for storing, managing, and analyzing data in a cloud computing environment.

[1148] A "generative model" refers to a machine learning algorithm that analyzes large amounts of data, recognizes patterns, and generates new information.

[1149] A "knowledge agent" is an artificial intelligence agent that is trained to perform specific tasks and provide information to the user.

[1150] A "personalized response" is a response that is individually optimized based on a user's behavioral and emotional data.

[1151] "Menu and promotion information" refers to information about food options and special offers offered through food delivery services.

[1152] "User context" refers to information about the user's current environment and situation.

[1153] A system required to implement this invention includes an information processing system operating as a smartphone application, which includes a smartphone that collects user behavioral and emotional data, a cloud database that processes and stores the data, a generative model that interprets and visualizes the data, and a knowledge agent that provides personalized responses to the user.

[1154] First, the smartphone uses a GPS sensor, an acceleration sensor, a heart rate sensor, and a facial expression analysis camera to collect user behavioral data (location information and movement patterns) and emotional data (emotional state estimated from heart rate and facial expressions) in real time. This information is structured and sent to a cloud database. The cloud database uses a fast-access NoSQL database, which stores data in real time and analyzes it using a generative model.

[1155] Next, a generative model running on the server analyzes the collected behavioral and emotional data to generate the user's current contextual information, which is expressed as detailed situational information such as "I am currently exercising by riding a bicycle" based on the user's behavioral patterns and emotional state.

[1156] The generated contextual information is shared with multiple knowledge agents via an API endpoint. Based on this contextual information, the knowledge agents generate optimal responses for the user. These responses are presented as optimal menus and promotional information offered by food delivery services. For example, if the system detects that the user is tired, it can recommend stamina-boosting dishes.

[1157] For example, the flow is as follows:

[1158] 1. If a user is cycling to work and their heart rate is high, the smartphone sensor will detect this and the emotion engine will determine that the user is tired.

[1159] 2. This data is sent to a cloud database, where a generative model generates contextual information such as "the user is tired from riding a bicycle."

[1160] 3. Contextual information is shared with knowledge agents via APIs to create personalized responses, such as suggesting menus that will energize a tired user.

[1161] 4. As a result, the user's smartphone application will display a message such as, "You look tired. Would you like some food to give you some energy?"

[1162] Examples of prompts include:

[1163] "Is your current heart rate normal?"

[1164] "How accurately do the sensors track your movements?"

[1165] "What are some specific examples of menu suggestions when your emotional state is fatigued?"

[1166] In this way, a system can be realized that provides a personalized experience based on the user's real-time state and emotions.

[1167] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1168] Step 1:

[1169] Smartphones (devices) use built-in GPS sensors, acceleration sensors, heart rate sensors, and facial expression analysis cameras to collect real-time data on the user's location, movement patterns, heart rate, and facial expression. This data is collected as user behavioral and emotional data. The input is data from the sensors, and the output is structured behavioral and emotional data.

[1170] Step 2:

[1171] The device structures the collected behavioral and emotional data and sends it to the cloud database. Specifically, it converts the collected data into JSON format and sends it to the cloud database using an HTTP POST request. The input is the data collected in step 1, and the output is storage in the cloud database.

[1172] Step 3:

[1173] The server analyzes the data stored in the cloud database using a generative model (e.g., GPT-3) to generate the user's current contextual information. The generative model learns behavioral and emotional data, recognizes patterns, and generates specific contextual information such as "I am currently exercising by riding a bicycle." The input is the data stored in the cloud database, and the output is interpreted contextual information.

[1174] Step 4:

[1175] The server shares the generated context information with multiple knowledge agents through an API endpoint. Specifically, it sends the interpreted context information to each knowledge agent's API using an HTTP POST request. The input is the interpreted context information, and the output is data sent to each knowledge agent.

[1176] Step 5:

[1177] The knowledge agent generates the optimal response for the user based on the shared contextual information. For example, if it determines that the user is tired, it generates recommendations for stamina-boosting dishes. The input is contextual information, and the output is a personalized response.

[1178] Step 6:

[1179] The terminal displays the personalized response received from the knowledge agent to the user. For example, it displays a message such as, "You seem tired. Would you like some food that will give you energy?" The input is the response from the knowledge agent, and the output is the message displayed to the user.

[1180] 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.

[1181] 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.

[1182] 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.

[1183] 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.

[1184] 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.

[1185] 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.

[1186] 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).

[1187] 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.

[1188] 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."

[1189] 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.

[1190] 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).

[1191] 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.

[1192] 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.

[1193] 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.

[1194] 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.

[1195] 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.

[1196] 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.

[1197] 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.

[1198] 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.

[1199] 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.

[1200] 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.

[1201] The following is further disclosed regarding the above embodiment.

[1202] (Claim 1)

[1203] a means for collecting user behavioral and emotional data from multiple devices in real time;

[1204] means for transmitting the collected data to a cloud database;

[1205] A means for interpreting and visualizing data stored in a cloud database using a generative model;

[1206] a means of sharing the interpreted and visualized data with multiple agents;

[1207] A means for each agent to provide personalized responses to the user based on the shared data; and

[1208] A system including:

[1209] (Claim 2)

[1210] 10. The system of claim 1, wherein the collection of user behavioral data and emotional data is performed using sensors.

[1211] (Claim 3)

[1212] 10. The system of claim 1, wherein the interpretation and visualization of the user's contextual information is performed using a generative model.

[1213] "Example 1"

[1214] (Claim 1)

[1215] means for collecting user behavioral and emotional data in real time from multiple devices;

[1216] means for formatting the collected data in a standard format and transmitting it to a server;

[1217] means for storing the data received by the server in a cloud database;

[1218] A means of transforming the accumulated data into interpretation and contextual information using a generative AI model; and

[1219] a means for sharing the interpreted and visualized data with multiple system agents;

[1220] a means for each system agent to provide a personalized response to the user based on the shared data; and

[1221] A system including:

[1222] (Claim 2)

[1223] 2. The system according to claim 1, wherein the collection of user behavioral data and emotional data is performed using a sensor device.

[1224] (Claim 3)

[1225] 10. The system of claim 1, wherein the interpretation and visualization of the user's contextual information is performed using a generative AI model.

[1226] "Application Example 1"

[1227] (Claim 1)

[1228] a means for collecting user behavioral and emotional data from multiple devices in real time;

[1229] means for transmitting the collected data to a cloud database;

[1230] A means for interpreting and visualizing data stored in a cloud database using a generative model;

[1231] a means of sharing the interpreted and visualized data with multiple agents;

[1232] A means for each agent to provide personalized responses to the user based on the shared data; and

[1233] A means to provide personalized food delivery suggestions based on user behavior data;

[1234] A system including:

[1235] (Claim 2)

[1236] 10. The system of claim 1, wherein the collection of user behavioral data and emotional data is performed using sensors.

[1237] (Claim 3)

[1238] 10. The system of claim 1, wherein the interpretation and visualization of the user's contextual information is performed using a generative model.

[1239] "Example 2: Combining Emotion Engines"

[1240] (Claim 1)

[1241] A means for collecting user behavioral and emotional data in real time from multiple devices;

[1242] means for transmitting the collected data to a server;

[1243] A means for storing the data received by the server in a cloud database;

[1244] A means of interpreting and visualizing data stored in a cloud database using a generative AI model; and

[1245] a means of sharing the interpreted and visualized data with multiple agents;

[1246] A means for each agent to provide personalized responses to the user based on the shared data; and

[1247] A system including:

[1248] (Claim 2)

[1249] The system of claim 1, wherein the collection of user behavioral data and emotional data is performed using sensors installed in the smart device.

[1250] (Claim 3)

[1251] 10. The system of claim 1, wherein the interpretation and visualization of the user's contextual information is performed using a generative AI model.

[1252] "Application example 2 when combining emotion engines"

[1253] (Claim 1)

[1254] means for collecting user behavior data and emotion data in real time from a plurality of information processing devices;

[1255] means for transmitting the collected data to a cloud database;

[1256] A means for interpreting and visualizing data stored in a cloud database using a generative model;

[1257] a means of sharing the interpreted and visualized data with multiple knowledge agents;

[1258] a means for each knowledge agent to provide a personalized response to the user based on the shared data;

[1259] A means of providing optimal menus and promotional information based on user behavioral and emotional data;

[1260] A system including:

[1261] (Claim 2)

[1262] 10. The system of claim 1, wherein the collection of user behavioral data and emotional data is performed using sensors.

[1263] (Claim 3)

[1264] 10. The system of claim 1, wherein the interpretation and visualization of the user's contextual information is performed using a generative model. [Explanation of symbols]

[1265] 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 for collecting user behavioral and emotional data from multiple devices in real time; means for transmitting the collected data to a cloud database; A means for interpreting and visualizing data stored in a cloud database using a generative model; a means of sharing the interpreted and visualized data with multiple agents; A means for each agent to provide personalized responses to the user based on the shared data; and A system including:

2. The system of claim 1 , wherein the collection of user behavioral data and emotion data is performed using sensors.

3. The system of claim 1 , wherein the interpretation and visualization of the user's contextual information is performed using a generative model.

Images