System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a request input from a user; means for acquiring attribute information of the user based on the request; means for generating a prompt using the acquired attribute information; means for transmitting the generated prompt to a generative artificial intelligence model; and means for providing a suggestion returned from the generative artificial intelligence model to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Many current services face the challenge of making optimal suggestions to meet user requests. This is because user attribute information and interest information are not properly utilized. As a result, the accuracy of suggestions to users is low, leading to a decline in user satisfaction. The objective of this invention is to utilize user attribute information to realize highly accurate suggestions using a generative artificial intelligence model, thereby improving user satisfaction. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides the following means.

[0006] A system is constructed that includes means for receiving a request input from a user, means for acquiring user attribute information based on the request, means for generating a prompt using the acquired attribute information, means for sending the generated prompt to a generative AI model, and means for providing the user with a proposal returned from the generative AI model. This system generates highly accurate proposals that reflect the user's attribute information and interests, thereby improving user satisfaction.

[0007] "User" refers to an individual user of the system.

[0008] A "request" refers to a request or question a user makes to the system.

[0009] "Attribute information" refers to personal information related to a user, such as the user's age, gender, interests, and purchasing history.

[0010] A "prompt" is data input to a generative AI model, and is information that includes instructions or requests for obtaining a specific generation result.

[0011] A "generative AI model" is an AI model that has the ability to generate data based on input prompts. For example, models that generate sentences or images fall into this category.

[0012] "Suggestions" refer to answers or recommendations created by a generative AI model that provide optimal results in response to a user's requests.

[0013] "Server" refers to a computer system that communicates with users, processes their requests, and provides an interface to generative artificial intelligence models.

[0014] A "terminal" is a device that a user directly operates and that communicates with a server, and includes smartphones, tablets, personal computers, etc.

[0015] A "database" refers to a collection of information that stores user attribute information and history information and is managed so that it can be searched and retrieved quickly. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is a system that utilizes a generative artificial intelligence model based on user attribute information to complement prompts and provide highly accurate information and suggestions to users. Specific embodiments of this system are described below.

[0038] Overall system configuration

[0039] The system mainly consists of the following elements:

[0040] Terminal: The device on which the user operates. This includes smartphones, tablets, personal computers, etc.

[0041] Server: Processes user requests and interacts with the generative AI model. It is also connected to a database that manages user attribute information.

[0042] Database: Stores user attribute information and history information.

[0043] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0044] Program processing flow

[0045] The operation of this system is mainly as follows.

[0046] 1. User request input:

[0047] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[0048] 2. Sending a request to the server:

[0049] The terminal sends the user's input to the server. The sent data includes the user ID.

[0050] 3. Obtaining user attribute information:

[0051] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[0052] 4. Prompt generation and completion:

[0053] The server complements the prompt based on the user's request and attribute information. This allows for more detailed and specific prompts to be generated. For example, a prompt might be generated such as, "Please recommend a yoga brand T-shirt for around 5,000 yen for a woman in her 30s who is raising children."

[0054] 5. Send to the generative AI model:

[0055] The server sends the generated prompt to the generative artificial intelligence model.

[0056] 6. Proposal generation using generative artificial intelligence model:

[0057] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "Yogaworks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0058] 7. Returning suggestions and displaying them to the user:

[0059] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[0060] The device displays suggestions to the user, for example, "Recommended T-shirts are: YogaWorks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0061] Specific examples

[0062] For example, a female user in her 30s raising a child might input a request such as, "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and the clothes she usually buys cost 5,000 yen." Based on this, the server complements the prompt with, "Please recommend a yoga brand T-shirt that costs around 5,000 yen for a woman in her 30s raising a child," and sends it to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works T-shirt A, Lululemon T-shirt B, Nike T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[0063] This system allows users to receive highly accurate suggestions customized based on their attributes and interests, making product selection easier and increasing satisfaction.

[0064] The processing flow will be explained below.

[0065] Program processing flow

[0066] Step 1:

[0067] The user opens the application on the device and enters a request such as, "Tell me what T-shirts you recommend!" The device receives this request and sends it to the server as JSON format data.

[0068] Example: { "request": "What T-shirt do you recommend?", "userID": "12345"}

[0069] Step 2:

[0070] The server analyzes the request received from the terminal and accesses the database based on the user ID. The server then uses an SQL query to retrieve user attribute information from the database.

[0071] Example of information to retrieve: { "age": "30s", "gender": "female", "interests": ["yoga"], "purchaseHistory": { "average_spend": 5000}, "status": "parent"}

[0072] Step 3:

[0073] The server uses the user's attribute information acquired to complete a prompt appropriate to the request. Specifically, it generates a detailed prompt based on the user's request and attribute information.

[0074] Example of a completed prompt: { "prompt": "Please recommend a yoga brand T-shirt for a woman in her 30s who is raising children, priced around 5,000 yen."}

[0075] Step 4:

[0076] The server sends the completed prompts to the generative artificial intelligence model using an HTTP POST request.

[0077] Example API request: POST / generate-recommendation { "prompt": "Please recommend a yoga brand T-shirt for a woman in her 30s raising children, priced at around 5,000 yen."}

[0078] Step 5:

[0079] The generative AI model receives the prompt and uses its internal inference algorithm to generate the best possible suggestion. The generative AI model then compiles the suggestion results into JSON format data and sends it back to the server.

[0080] Example of inference result: { "recommendations": ["Yogaworks T-shirt A", "Lululemon T-shirt B", "Nike T-shirt C"]}

[0081] Step 6:

[0082] The server analyzes the proposal results received from the generative AI model and converts them into an appropriate format. The server then transfers this data to the device.

[0083] Step 7:

[0084] The terminal displays the recommendation results received from the server on the user interface, allowing the user to check the recommended product information on the terminal and select the next action to purchase or check the details.

[0085] Example: "Recommended t-shirts are: Yoga Works t-shirt A, Lululemon t-shirt B, Nike t-shirt C."

[0086] Through the above processing steps, highly accurate proposals can be generated using the user's attribute information based on the request input by the user, and provided to the user.

[0087] Example 1

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

[0089] Conventional systems have difficulty generating detailed prompts necessary to make accurate proposals in response to user requests, and have been unable to effectively utilize user attribute information. This has resulted in the inability to adequately propose products and services that meet user needs, making it difficult to increase user satisfaction.

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

[0091] In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information from a database based on the request, means for generating and completing detailed and specific prompts using the acquired attribute information, means for transmitting the generated prompts to a generative AI model, and means for providing the user with product or service suggestions returned from the generative AI model, thereby enabling highly accurate suggestions customized based on the user's attribute information.

[0092] "Requests input by a user" refers to information or requests provided by a user to the system via a terminal.

[0093] "User attribute information" refers to personal information and historical information about a user, including data such as age, gender, interests, and purchasing history.

[0094] "Database" refers to a system or device that has a data structure that stores user attribute information and other information and allows it to be searched and retrieved.

[0095] The "means for generating and completing prompts" refers to a means having a function for automatically creating more detailed and specific request content based on the user's attribute information and requests.

[0096] A "generative artificial intelligence model" is an artificial intelligence that has the ability to generate product and service suggestions based on prompts it receives.

[0097] "Product or service suggestions" refers to recommended products or services provided to a user by a generative artificial intelligence model based on prompts.

[0098] A "server" is a computer system that receives and processes user requests and communicates with the generative artificial intelligence model.

[0099] This invention is a system that utilizes a generative artificial intelligence model to complement prompts based on user attribute information and provides the user with highly accurate information and suggestions. Specifically, the user inputs a request from a terminal, the system obtains the user's attribute information from a database based on the request, and generates and complements detailed and specific prompts using the obtained attribute information. The system then sends the generated prompts to the generative artificial intelligence model, and provides the user with suggestions returned from the generative artificial intelligence model.

[0100] Overall system configuration

[0101] The system mainly consists of the following elements:

[0102] Terminal: The device on which the user operates. This includes smartphones, tablets, personal computers, etc.

[0103] Server: Processes user requests and interacts with the generative AI model. It is also connected to a database that manages user attribute information.

[0104] Database: Stores user attribute information and history information.

[0105] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0106] Program processing

[0107] 1. User request input

[0108] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[0109] 2. Sending a request to the server

[0110] The terminal sends the user's input to the server. The sent data includes the user ID.

[0111] 3. Obtaining user attribute information

[0112] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[0113] 4. Prompt generation and completion

[0114] The server complements the prompt based on the user's request and attribute information. This allows for more detailed and specific prompts to be generated. For example, a prompt might be generated such as, "Please recommend a yoga brand T-shirt for around 5,000 yen for a woman in her 30s who is raising children."

[0115] 5. Sending to the generative AI model

[0116] The server sends the generated prompt to the generative artificial intelligence model.

[0117] 6. Proposal generation using a generative artificial intelligence model

[0118] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "Yogaworks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0119] 7. Returning suggestions and displaying them to the user

[0120] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[0121] The device displays suggestions to the user, for example, "Recommended T-shirts are: YogaWorks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0122] Specific examples

[0123] For example, a female user in her 30s raising a child inputs a request such as "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and the clothes she usually buys cost 5,000 yen." Based on this, the server complements the prompt with "Please recommend a yoga brand T-shirt that costs around 5,000 yen for a woman in her 30s raising a child," and sends it to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works T-shirt A, Lululemon T-shirt B, Nike T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] A user opens an application on their device and enters a request such as "Tell me what T-shirts you recommend!" This request is sent to the application on their device. The input is text data that describes the user's needs, and the output is an HTTP request that is sent to the server.

[0127] Step 2:

[0128] The terminal sends the user's input data (request and user ID) to the server. Specifically, it uses an HTTP POST request to send the request content and user ID to the server. The input is the user's request and user ID, and the output is the request to the server.

[0129] Step 3:

[0130] The server analyzes the received request and sends a query to the database based on the user ID. Specifically, it accesses the database using an SQL query in the format "SELECT FROM user_attributes WHERE user_id = ?". The input is the user ID, and the output is the user's attribute information.

[0131] Step 4:

[0132] The server generates detailed and specific prompts based on the user's attribute information (e.g., age, gender, interests, purchasing history) retrieved from the database. This prompt is created by combining the user's request and attribute information. The input is the user's request and attribute information, and the output is the generated prompt.

[0133] Step 5:

[0134] The server sends the generated prompt to the generative AI model. Specifically, it sends an HTTP POST request to the API endpoint of the generative AI model. The input is the generated prompt, and the output is a request to the generative AI model.

[0135] Step 6:

[0136] A generative AI model generates optimal product suggestions based on the prompts received. It uses an internal algorithm to analyze the prompts and generate a product list. The input is the received prompt, and the output is the generated suggestions (product list).

[0137] Step 7:

[0138] The generative AI model returns the generated proposal to the server, which then sends the received proposal to the user's device. The input is the proposal from the generative AI model, and the output is a request sent to the user's device.

[0139] Step 8:

[0140] The terminal displays the suggestions received from the server to the user. Specifically, the suggestions are displayed as text in the application's user interface. The input is the suggestion data from the server, and the output is the display on the user interface.

[0141] (Application example 1)

[0142] 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."

[0143] Conventional mail-order sites and online shopping platforms can only make general suggestions in response to user requests, making it difficult to make customized suggestions that take into account the attributes and history information of individual users. For this reason, there has been a demand for a system that can quickly and accurately recommend products and services that are suitable for each user.

[0144] 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.

[0145] In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information and history information based on the request, means for generating and completing a prompt using the acquired attribute information and history information, means for transmitting the generated prompt to a generative AI model, and means for providing suggestions returned from the generative AI model to the user's terminal, thereby enabling highly accurate product and service suggestions based on the user's attribute information and history information.

[0146] "User" refers to the general consumer or client who uses the system.

[0147] "Request" refers to a request or inquiry entered by a user.

[0148] "Attribute information" refers to information that indicates personal characteristics such as a user's age, gender, interests, purchasing history, etc.

[0149] "History information" refers to data that indicates a user's past behavior, purchase history, and the like.

[0150] A "prompt" refers to a command statement that instructs a generative artificial intelligence model to perform specific processing or generation.

[0151] A "generative artificial intelligence model" refers to an algorithm or machine learning model that generates appropriate suggestions or answers based on input prompts.

[0152] A "terminal" is a device operated by a user, such as a smartphone, tablet, or personal computer.

[0153] "Suggestion" refers to the optimal product or service recommendation for the user returned from the generative artificial intelligence model.

[0154] The present invention provides a system for making highly accurate suggestions using a generative artificial intelligence model by utilizing user attribute information and history information. A specific embodiment of this system will be described below.

[0155] System configuration

[0156] The system consists of the following main components:

[0157] 1. Device:

[0158] A device operated by a user, including a smartphone, tablet, personal computer, etc. This terminal functions as an interface for the user to input requests.

[0159] 2. Server:

[0160] This is the central system for processing user requests and linking with the generative AI model. The server is connected to a database that manages user attribute information and history information.

[0161] 3. Database:

[0162] It stores attribute information and history information such as the user's age, gender, interests, and purchasing history.

[0163] 4. Generative AI Models:

[0164] It is an algorithm or machine learning model that generates optimal suggestions based on prompts sent from the server.

[0165] Program processing flow

[0166] The processing of the program in the system is as follows.

[0167] 1. User request input:

[0168] The user inputs a request through the terminal. For example, the user inputs a request such as "Tell me what shoes you recommend!"

[0169] 2. Send a request to the server and get user attribute information:

[0170] When a request sent from a device reaches the server, the server retrieves attribute and history information from a database based on the user ID, including age, gender, interests, and purchasing history.

[0171] 3. Prompt generation and completion:

[0172] The server generates prompts based on the acquired attribute information and history information, and fills in the details. For example, a prompt may be generated that recommends "running shoes for men in their 20s that cost less than 7,000 yen."

[0173] 4. Proposal generation using generative artificial intelligence model:

[0174] The generated prompts are then sent to a generative artificial intelligence model, which then generates optimal recommendations, such as specific product recommendations like "Nike running shoes A, Adidas running shoes B, Puma running shoes C."

[0175] 5. Return suggestions and display them to the user:

[0176] The server returns the suggested products to the terminal, which displays them to the user, who can then review the details of the suggested products and make a selection.

[0177] Specific examples

[0178] For example, consider the case where a male user in his 20s types "Tell me what shoes you recommend!" into a shopping app on his smartphone. At this time, the server retrieves the attribute information "male, 20s, interested in running, purchase price range under 7,000 yen" from the database. Based on this, the server complements the prompt with "running shoes for men in their 20s under 7,000 yen" and sends it to the generative AI model. The generative AI model generates suggestions such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C," which are sent to the user's device via the server. The user can view these suggestions on their smartphone screen and select the most suitable product.

[0179] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0180] Step 1:

[0181] The user inputs a request through the device. Specifically, the user opens a shopping app on their smartphone and inputs a request such as, "Tell me what shoes you recommend!" The input (request) is received by the device and sent to the next step.

[0182] Step 2:

[0183] The terminal sends the received request to the server. The server accesses the database based on the user ID included in the received request. From the database, it obtains attribute information and history information such as the user's age, gender, interests, and purchasing history. Through this process, the user's attribute information and history information are obtained by the server.

[0184] Step 3:

[0185] Based on the user's attribute information and history information acquired by the server, the server generates and completes a detailed prompt. Specifically, the server generates a detailed prompt such as "Running shoes for men in their 20s, under 7,000 yen." This prompt is customized to match specific user attributes. The input request and acquired attribute information are processed and output as a detailed prompt.

[0186] Step 4:

[0187] The server sends the generated prompt to the generative AI model. Specifically, the generated prompt text is sent to the generative AI model (for example, an API endpoint on the cloud). An example of a prompt text is "Running shoes for men in their 20s, priced under 7,000 yen."

[0188] Step 5:

[0189] The generative AI model generates optimal suggestions based on the received prompt. The model analyzes the information contained in the prompt and makes specific product suggestions, such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C." The generated suggestions are sent back from the generative AI model to the server, where the input prompt is processed and output as appropriate suggestions.

[0190] Step 6:

[0191] The server returns the suggestions received from the generative AI model to the user's device. The server then reformats the returned suggestion data and sends it to the user's device. This results in the device displaying suggestions such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C." The suggestion data is reformatted and output in a format suitable for display to the user.

[0192] This allows users to use their devices to receive highly accurate and customized product suggestions and select the most suitable products.

[0193] 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.

[0194] This invention is a system that combines a user's attribute information with an emotion engine that recognizes the user's emotion information, utilizes a generative AI model to complement prompts, and provides the user with highly accurate information and suggestions. Specific embodiments of this system are described below.

[0195] Overall system configuration

[0196] The system mainly consists of the following elements:

[0197] Terminal: A device that a user operates, including smartphones, tablets, and personal computers.

[0198] Server: Processes user requests, works with the generative AI model, and is connected to a database that manages user attribute information and emotional information.

[0199] Database: Stores user attribute information, history information, and emotional information.

[0200] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0201] Emotion Engine: An engine that uses technology to recognize emotions from the user's voice, text, and facial expressions.

[0202] Program processing flow

[0203] The operation of this system is mainly as follows.

[0204] 1. User request input:

[0205] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[0206] 2. Sending a request to the server:

[0207] The terminal sends the user's input to the server. The sent data includes the user ID.

[0208] 3. Obtaining user attribute information:

[0209] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[0210] 4. Acquiring emotional information:

[0211] The server uses an emotion engine to obtain emotional information from the user's voice, text, and facial expressions, such as stress level, satisfaction, and motivation.

[0212] 5. Prompt generation and completion:

[0213] The server complements the prompt based on the user's request, attribute information, and emotional information. This allows for the generation of more detailed and specific prompts. For example, a prompt might be generated such as, "For a woman in her 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[0214] 6. Send to the generative AI model:

[0215] The server generates and sends the completed prompt to the generative artificial intelligence model.

[0216] 7. Proposal generation using generative artificial intelligence model:

[0217] Based on the prompts received, the generative AI model generates optimal product recommendations, such as "YogaWorks Relaxing T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[0218] 8. Returning suggestions and displaying them to the user:

[0219] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[0220] The device displays suggestions to the user, such as "Recommended T-shirts: Yoga Works Relaxing T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[0221] Specific examples

[0222] For example, a female user in her 30s raising a child might input a request such as, "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and usually spends 5,000 yen on clothes." At the same time, the emotion engine analyzes the user's facial expressions and recognizes that her current stress level is high. Based on this, the server complements the prompt with, "For a female user in her 30s raising a child who is currently feeling stressed, please recommend a relaxing T-shirt from a yoga brand that costs around 5,000 yen," and sends this to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works Relaxing T-shirt A, Lululemon Comfortable T-shirt B, and Nike Stress Relief T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[0223] This system allows users to receive highly accurate suggestions that reflect their own attribute information, interests, and real-time emotional information, further improving satisfaction.

[0224] The processing flow will be explained below.

[0225] Program processing flow

[0226] Step 1:

[0227] The user opens the application on the device and enters a request such as, "Tell me what T-shirts you recommend!" The device receives this request and sends it to the server as JSON format data.

[0228] Example of data to send: { "request": "What T-shirts do you recommend?", "userID": "12345"}

[0229] Step 2:

[0230] The server analyzes the request received from the terminal and accesses the database based on the user ID. The server then uses an SQL query to retrieve user attribute information from the database.

[0231] Example of information to be acquired: { "age": "30s", "gender": "female", "interests": ["yoga"], "purchaseHistory": { "average_spend": 5000}, "status": "parent"}

[0232] Step 3:

[0233] The server activates the emotion engine, which collects voice, text, and facial expression data from the user's device. The emotion engine analyzes this data and recognizes the user's emotional information.

[0234] Emotion information example: { "stress_level": "high", "satisfaction": "neutral", "motivation": "low"}

[0235] Step 4:

[0236] The server complements the prompts appropriate for the request based on the user's attribute information and emotional information. Specifically, it generates detailed prompts based on the user's request, attribute information, and emotional information.

[0237] Example of a completed prompt: { "prompt": "For a user in their 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."}

[0238] Step 5:

[0239] The server sends the completed prompts to the generative artificial intelligence model using an HTTP POST request.

[0240] Example API request: POST / generate-recommendation { "prompt": "Recommend a relaxing yoga brand T-shirt for around 5,000 yen to a user who is a woman in her 30s raising children and currently feeling stressed."}

[0241] Step 6:

[0242] The generative AI model receives the prompt and uses its internal inference algorithm to generate the best possible suggestion. The generative AI model then compiles the suggestion results into JSON format data and sends it back to the server.

[0243] Example of inference result: { "recommendations": ["YogaWorks Relaxing T-shirt A", "Lululemon Comfort T-shirt B", "Nike Stress Relief T-shirt C"]}

[0244] Step 7:

[0245] The server analyzes the proposal result data received from the generative AI model and converts it into an appropriate format. The server then transfers this data to the device.

[0246] Step 8:

[0247] The terminal displays the recommendation results received from the server on the user interface, allowing the user to check the recommended product information on the terminal and select the next action to purchase or check the details.

[0248] Example: "Recommended t-shirts are: Yoga Works Relax T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[0249] Through the above processing steps, the user can receive highly accurate suggestions that utilize attribute information and emotion information based on the input request.

[0250] Example 2

[0251] 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."

[0252] In conventional systems, prompts were generated and suggestions were made based only on individual attribute information in response to user requests, making it difficult to provide highly accurate suggestions that reflected the user's mental state and emotional information in real time.In addition, to improve user satisfaction, individual responses based on the user's situation and emotions are required, and in this respect conventional systems were insufficient.

[0253] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information based on the request, means for generating and complementing a prompt using the acquired attribute information and user emotional information, means for transmitting the generated prompt to a generative AI model, and means for providing the user with a proposal returned from the generative AI model. This makes it possible to make highly accurate proposals that include the user's real-time emotional state.

[0254] A "user" is an individual or organization that uses the system and is the entity that inputs requests.

[0255] A "request" is a request or question that a user inputs to the system, and is information that the system must process.

[0256] "User attribute information" refers to information about the user, such as age, gender, interests, and purchasing history, and is referenced when generating prompts.

[0257] "Emotional information" refers to the emotional state of the user as recognized by their voice, text, and facial expressions, and is acquired in real time.

[0258] A "prompt" is a basic instruction that allows a generative artificial intelligence model to generate suggestions for a user.

[0259] A "generative artificial intelligence model" is an artificial intelligence algorithm that takes a user's requests or prompts as input and generates appropriate suggestions.

[0260] A "proposal" is a specific product or service that a generative artificial intelligence model generates based on a prompt and provides to a user.

[0261] This invention is a system that combines a user's attribute information with an emotion engine that recognizes the user's emotion information, utilizes a generative artificial intelligence model to complement prompts, and provides the user with highly accurate information and suggestions. Specific embodiments of this system are described below.

[0262] The system mainly consists of the following elements:

[0263] Terminal: A device that a user operates, including smartphones, tablets, and personal computers.

[0264] Server: Processes user requests, works with the generative AI model, and is connected to a database that manages user attribute information and emotional information.

[0265] Database: Stores user attribute information, history information, and emotional information.

[0266] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0267] Emotion Engine: An engine that uses technology to recognize emotions from the user's voice, text, and facial expressions.

[0268] The specific operational flow when implementing this is as follows:

[0269] 1. User request input:

[0270] The user opens the application on their device and enters a request, for example, "Tell me what T-shirts you recommend!"

[0271] 2. Sending a request to the server:

[0272] The terminal sends the user's input to the server. The sent data includes the user ID.

[0273] 3. Obtaining user attribute information:

[0274] The server accesses the database based on the user ID and obtains the user's attribute information (age, gender, interests, purchasing history, etc.) For example, if the user is a woman in her 30s raising a child and is interested in yoga brands, the direction of suggestions can be narrowed down based on this information.

[0275] 4. Acquiring emotional information:

[0276] The server uses an emotion engine to obtain emotional information from the user's voice, text, and facial expressions, for example, to analyze whether the user is currently feeling stressed.

[0277] 5. Prompt generation and completion:

[0278] The server complements the prompt based on the user's request, attribute information, and emotional information. This allows for the generation of more detailed and specific prompts. For example, a prompt might be generated such as, "For a woman in her 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[0279] 6. Send to the generative AI model:

[0280] The server generates and sends the completed prompt to the generative artificial intelligence model.

[0281] 7. Proposal generation using generative artificial intelligence model:

[0282] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "relaxing T-shirt A from a yoga brand, comfortable T-shirt B from a sports brand, and stress-reducing T-shirt C from an outdoor brand."

[0283] 8. Returning suggestions and displaying them to the user:

[0284] The server receives suggestions from the generative AI model and sends them back to the user's device. The device then displays the suggestions to the user. For example, the suggestions might look like this: "Recommended T-shirts are: Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, and Stress-reducing T-shirt C from an outdoor brand."

[0285] This specific form allows users to receive highly accurate suggestions that reflect their own attribute information, interests, and real-time emotional information, further improving their satisfaction.

[0286] The above is an embodiment of the invention, and this system is capable of making highly accurate suggestions that take into account the user's real-time emotional state.

[0287] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0288] Step 1:

[0289] The user opens the application on the terminal and enters a request.

[0290] Specific actions

[0291] - A user uses a smartphone or computer to type "Tell me your recommended T-shirt!" and presses the send button.

[0292] input

[0293] - Request: "What T-shirts do you recommend?"

[0294] output

[0295] - Request data: User ID and entered request details.

[0296] Step 2:

[0297] The device sends the request to the server.

[0298] Specific actions

[0299] - The device assembles the user ID and the input request content into a packet and sends an HTTP POST request to the server.

[0300] input

[0301] - A data packet containing the user ID and the request content.

[0302] output

[0303] - The request data received by the server.

[0304] Step 3:

[0305] The server retrieves user attribute information from the database based on the user ID.

[0306] Specific actions

[0307] - The server sends an SQL query to the database to retrieve attribute information using "SELECT FROM user_attributes WHERE user_id = user ID".

[0308] input

[0309] - User ID.

[0310] output

[0311] - User demographic information: Data such as age, gender, interests, and purchasing history.

[0312] Step 4:

[0313] The server acquires the user's emotion information using an emotion engine.

[0314] Specific actions

[0315] - The server sends voice input and facial expression data acquired by the camera to the emotion engine API to acquire emotion information.

[0316] input

[0317] - User voice, text and facial expression data.

[0318] output

[0319] - Emotional information: data such as stress levels, satisfaction, and motivation.

[0320] Step 5:

[0321] The server generates and completes prompts based on the user's request, attribute information, and emotional information.

[0322] Specific actions

[0323] - The server combines the request content, user attribute information, and emotional information to generate a detailed prompt. Example: "For a user in their 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[0324] input

[0325] - User requests, attribute information, and emotional information.

[0326] output

[0327] - Completed prompt sentence.

[0328] Step 6:

[0329] The server sends the generated prompt to the generative artificial intelligence model.

[0330] Specific actions

[0331] - The server sends the prompt sentence to the generative AI model as an API request.

[0332] input

[0333] - Completed prompt sentence.

[0334] output

[0335] - Prompt data sent to generative artificial intelligence models.

[0336] Step 7:

[0337] A generative artificial intelligence model generates optimal suggestions based on prompts.

[0338] Specific actions

[0339] - A generative AI model analyzes the prompts received and generates appropriate product suggestions, e.g., "Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, Stress-reducing T-shirt C from an outdoor brand."

[0340] input

[0341] - Completed prompt sentence.

[0342] output

[0343] - Proposal data: Multiple product proposal lists.

[0344] Step 8:

[0345] The server receives suggestions from the generative artificial intelligence model and returns them to the user's device.

[0346] Specific actions

[0347] - The server receives the suggestion data and sends it to the user's device. The device displays the suggestion to the user. For example, "The recommended T-shirts are: Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, and Stress-reducing T-shirt C from an outdoor brand."

[0348] input

[0349] - Proposal data.

[0350] output

[0351] - A list of suggestions displayed on the user's device.

[0352] This concludes the detailed explanation of each processing step. This detailed flow enables users to quickly receive highly accurate suggestions that reflect their own attribute information and emotional state.

[0353] (Application example 2)

[0354] 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."

[0355] Conventional user suggestion systems generate suggestions based only on the user's attribute information, making it difficult to reflect the user's emotional state. Therefore, there is a need for a method that takes into account the user's real-time emotional information and provides more personalized and accurate suggestions. Furthermore, there is a lack of technology that can timely recommend content appropriate to the user's emotional state, especially in content distribution services such as video and movie streaming.

[0356] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a request input from a user, means for acquiring attribute information and emotional information of the user, means for generating and complementing a prompt using the acquired attribute information and emotional information, means for sending the generated prompt to a generative AI model, and means for providing the user with a suggestion returned from the generative AI model. This enables highly accurate content suggestions that take into account the user's real-time emotional state.

[0357] The "means for receiving a request input by a user" refers to a device or program having a function for receiving a request when the user inputs the request into the system via an input device.

[0358] "Means for acquiring user attribute information and emotional information" refers to a device or program for detecting, extracting, and collecting a user's basic attributes (age, gender, interests, purchasing history, etc.) and emotional state (stress level, satisfaction, etc.).

[0359] A "means for generating and complementing prompts" is a device or program that creates instructions suitable for a generative artificial intelligence model based on a user's request and acquired attribute information and emotional information, and complements the instructions with additional information to make them more specific and effective.

[0360] The "means for transmitting to the generative artificial intelligence model" is a device or program for transmitting the generated and completed prompt to the generative artificial intelligence model via a network.

[0361] "Means for providing a user with suggestions returned from a generative artificial intelligence model" refers to a device or program for receiving suggestions generated by a generative artificial intelligence model based on a prompt and displaying or notifying the user of the suggestions.

[0362] This invention is a system that utilizes a generative artificial intelligence model to make highly accurate suggestions based on user attribute information and emotion information. The system configuration for implementing this includes a user terminal, a server, a database, a generative artificial intelligence model, and an emotion engine.

[0363] Overall system configuration

[0364] The system mainly consists of the following components:

[0365] User terminal: A device that a user operates and inputs requests and emotional data (facial images, voice data). Specific examples include smartphones, tablets, and personal computers.

[0366] Server: Receives user requests, acquires and processes various data, and interacts with the generative AI model.

[0367] Database: Stores user attribute information, history information, and emotional information.

[0368] Generative AI model: An AI model that generates optimal suggestions based on prompts sent from the server.

[0369] Emotion engine: An engine that recognizes emotions from the user's voice, text, and facial expressions and provides that information.

[0370] Devices and Software

[0371] Frontend: React Native (smartphone app)

[0372] Backend: Django (Python), Flask

[0373] Database: PostgreSQL

[0374] Emotion engine: OpenCV (face recognition), Google Cloud Speech-to-Text (voice recognition)

[0375] Generative AI model: OpenAI GPT-4

[0376] Operating Procedure

[0377] 1. Input of a request: The user inputs a request into the terminal. For example, "Tell me some recommended movies."

[0378] 2. Data Acquisition: The server receives the request entered by the user and acquires the user's attribute information (age, gender, interests, etc.) from the database. At the same time, it uses the emotion engine to analyze the user's emotional information (current stress level, satisfaction level, etc.).

[0379] 3. Prompt generation and completion: The server generates and completes detailed and specific prompts based on the acquired user attribute information and emotional information.

[0380] 4. Generate suggestions: The generated prompts are sent to a generative artificial intelligence model (GPT-4) to generate optimal suggestions.

[0381] 5. Providing suggestions: Receive suggestions from the generative AI model and display them on the user's device.

[0382] Examples of prompt statements

[0383] "Please recommend some movies to a user who is a man in his 30s, currently feeling stressed, and interested in science fiction and action movies."

[0384] "Please recommend some dramas to a female user in her 20s who wants to relax and is interested in comedy dramas."

[0385] Example scenario

[0386] For example, if a male user in his 30s inputs a request such as "Please recommend some movies," the server retrieves attribute information from the database, such as "Age: 30s, Gender: Male, Interests: Sci-Fi, Action." At the same time, the emotion engine recognizes a high stress level from the user's facial image and voice. Based on this, the server generates a prompt and sends it to a generative artificial intelligence model (GPT-4). The generative artificial intelligence model suggests movies such as "Inception," "The Matrix," and "Transformers," which are sent to the user's device via the server. The user can review these suggestions and select the best movie for their condition.

[0387] In this way, the system allows users to receive highly accurate suggestions that reflect their own attribute information and emotional state, improving their satisfaction with content selection.

[0388] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0389] Step 1:

[0390] A user inputs a request to the system through a terminal. For example, a user can input "Tell me some recommended movies." This input is sent to the server by the terminal. The input data is text information and includes the user's request.

[0391] Step 2:

[0392] The server receives the user's request sent from the terminal. The received request data includes the user ID, which is used to query the database and obtain the user's attribute information. The obtained attribute information includes age, gender, interests, purchasing history, etc. This process prepares the user's basic information.

[0393] Step 3:

[0394] The server uses an emotion engine based on the user's attribute information to obtain emotional information. Specifically, it recognizes the user's current emotional state (stress level, satisfaction, etc.) by analyzing the facial image and voice data provided by the user during input. OpenCV and Google Cloud Speech-to-Text are used to obtain this emotional information. The input data are images and voice, and the output data are numerical values ​​and category information of the emotional state.

[0395] Step 4:

[0396] The server combines the acquired attribute information and emotional information to generate and complement prompts suitable for the generative AI model. These prompts include attribute information such as the user's age, gender, and interests, as well as emotional information such as stress level. The generated prompts are detailed and specific instructions. For example, they could be in the form of "Please recommend movies to a user who is a man in his 30s, currently feeling stressed, and interested in science fiction and action movies."

[0397] Step 5:

[0398] The server sends the generated and completed prompts to a generative AI model (e.g., GPT-4), which receives the sent prompts and generates optimal suggestions based on them. In this case, the input data is the prompts, and the output data is a list of suggestions.

[0399] Step 6:

[0400] The generative AI model sends back the proposed results to the server. The server receives the proposed results and sends them to the user's device. The proposed results are, for example, a list of movies such as "Inception," "The Matrix," and "Transformers."

[0401] Step 7:

[0402] The user's device displays the suggestions received from the server, and the user can review these suggestions and choose the movie that best suits their emotional state and interests. The information displayed includes specific titles and synopses, allowing the user to make a decision based on them.

[0403] At each step, the input data is processed appropriately, and the final output is the optimal proposal provided to the user, which also improves user satisfaction.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] [Second embodiment]

[0408] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0419] 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."

[0420] This invention is a system that utilizes a generative artificial intelligence model based on user attribute information to complement prompts and provide highly accurate information and suggestions to users. Specific embodiments of this system are described below.

[0421] Overall system configuration

[0422] The system mainly consists of the following elements:

[0423] Terminal: The device on which the user operates. This includes smartphones, tablets, personal computers, etc.

[0424] Server: Processes user requests and interacts with the generative AI model. It is also connected to a database that manages user attribute information.

[0425] Database: Stores user attribute information and history information.

[0426] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0427] Program processing flow

[0428] The operation of this system is mainly as follows.

[0429] 1. User request input:

[0430] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[0431] 2. Sending a request to the server:

[0432] The terminal sends the user's input to the server. The sent data includes the user ID.

[0433] 3. Obtaining user attribute information:

[0434] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[0435] 4. Prompt generation and completion:

[0436] The server complements the prompt based on the user's request and attribute information. This allows for more detailed and specific prompts to be generated. For example, a prompt might be generated such as, "Please recommend a yoga brand T-shirt for around 5,000 yen for a woman in her 30s who is raising children."

[0437] 5. Send to the generative AI model:

[0438] The server sends the generated prompt to the generative artificial intelligence model.

[0439] 6. Proposal generation using generative artificial intelligence model:

[0440] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "Yogaworks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0441] 7. Returning suggestions and displaying them to the user:

[0442] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[0443] The device displays suggestions to the user, for example, "Recommended T-shirts are: YogaWorks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0444] Specific examples

[0445] For example, a female user in her 30s raising a child might input a request such as, "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and the clothes she usually buys cost 5,000 yen." Based on this, the server complements the prompt with, "Please recommend a yoga brand T-shirt that costs around 5,000 yen for a woman in her 30s raising a child," and sends it to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works T-shirt A, Lululemon T-shirt B, Nike T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[0446] This system allows users to receive highly accurate suggestions customized based on their attributes and interests, making product selection easier and increasing satisfaction.

[0447] The processing flow will be explained below.

[0448] Program processing flow

[0449] Step 1:

[0450] The user opens the application on the device and enters a request such as, "Tell me what T-shirts you recommend!" The device receives this request and sends it to the server as JSON format data.

[0451] Example: { "request": "What T-shirt do you recommend?", "userID": "12345"}

[0452] Step 2:

[0453] The server analyzes the request received from the terminal and accesses the database based on the user ID. The server then uses an SQL query to retrieve user attribute information from the database.

[0454] Example of information to retrieve: { "age": "30s", "gender": "female", "interests": ["yoga"], "purchaseHistory": { "average_spend": 5000}, "status": "parent"}

[0455] Step 3:

[0456] The server uses the user's attribute information acquired to complete a prompt appropriate to the request. Specifically, it generates a detailed prompt based on the user's request and attribute information.

[0457] Example of a completed prompt: { "prompt": "Please recommend a yoga brand T-shirt for a woman in her 30s who is raising children, priced around 5,000 yen."}

[0458] Step 4:

[0459] The server sends the completed prompts to the generative artificial intelligence model using an HTTP POST request.

[0460] Example API request: POST / generate-recommendation { "prompt": "Please recommend a yoga brand T-shirt for a woman in her 30s raising children, priced at around 5,000 yen."}

[0461] Step 5:

[0462] The generative AI model receives the prompt and uses its internal inference algorithm to generate the best possible suggestion. The generative AI model then compiles the suggestion results into JSON format data and sends it back to the server.

[0463] Example of inference result: { "recommendations": ["Yogaworks T-shirt A", "Lululemon T-shirt B", "Nike T-shirt C"]}

[0464] Step 6:

[0465] The server analyzes the proposal results received from the generative AI model and converts them into an appropriate format. The server then transfers this data to the device.

[0466] Step 7:

[0467] The terminal displays the recommendation results received from the server on the user interface, allowing the user to check the recommended product information on the terminal and select the next action to purchase or check the details.

[0468] Example: "Recommended t-shirts are: Yoga Works t-shirt A, Lululemon t-shirt B, Nike t-shirt C."

[0469] Through the above processing steps, highly accurate proposals can be generated using the user's attribute information based on the request input by the user, and provided to the user.

[0470] Example 1

[0471] 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."

[0472] Conventional systems have difficulty generating detailed prompts necessary to make accurate proposals in response to user requests, and have been unable to effectively utilize user attribute information. This has resulted in the inability to adequately propose products and services that meet user needs, making it difficult to increase user satisfaction.

[0473] 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.

[0474] In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information from a database based on the request, means for generating and completing detailed and specific prompts using the acquired attribute information, means for transmitting the generated prompts to a generative AI model, and means for providing the user with product or service suggestions returned from the generative AI model, thereby enabling highly accurate suggestions customized based on the user's attribute information.

[0475] "Requests input by a user" refers to information or requests provided by a user to the system via a terminal.

[0476] "User attribute information" refers to personal information and historical information about a user, including data such as age, gender, interests, and purchasing history.

[0477] "Database" refers to a system or device that has a data structure that stores user attribute information and other information and allows it to be searched and retrieved.

[0478] The "means for generating and completing prompts" refers to a means having a function for automatically creating more detailed and specific request content based on the user's attribute information and requests.

[0479] A "generative artificial intelligence model" is an artificial intelligence that has the ability to generate product and service suggestions based on prompts it receives.

[0480] "Product or service suggestions" refers to recommended products or services provided to a user by a generative artificial intelligence model based on prompts.

[0481] A "server" is a computer system that receives and processes user requests and communicates with the generative artificial intelligence model.

[0482] This invention is a system that utilizes a generative artificial intelligence model to complement prompts based on user attribute information and provides the user with highly accurate information and suggestions. Specifically, the user inputs a request from a terminal, the system obtains the user's attribute information from a database based on the request, and generates and complements detailed and specific prompts using the obtained attribute information. The system then sends the generated prompts to the generative artificial intelligence model, and provides the user with suggestions returned from the generative artificial intelligence model.

[0483] Overall system configuration

[0484] The system mainly consists of the following elements:

[0485] Terminal: The device on which the user operates. This includes smartphones, tablets, personal computers, etc.

[0486] Server: Processes user requests and interacts with the generative AI model. It is also connected to a database that manages user attribute information.

[0487] Database: Stores user attribute information and history information.

[0488] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0489] Program processing

[0490] 1. User request input

[0491] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[0492] 2. Sending a request to the server

[0493] The terminal sends the user's input to the server. The sent data includes the user ID.

[0494] 3. Obtaining user attribute information

[0495] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[0496] 4. Prompt generation and completion

[0497] The server complements the prompt based on the user's request and attribute information. This allows for more detailed and specific prompts to be generated. For example, a prompt might be generated such as, "Please recommend a yoga brand T-shirt for around 5,000 yen for a woman in her 30s who is raising children."

[0498] 5. Sending to the generative AI model

[0499] The server sends the generated prompt to the generative artificial intelligence model.

[0500] 6. Proposal generation using a generative artificial intelligence model

[0501] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "Yogaworks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0502] 7. Returning suggestions and displaying them to the user

[0503] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[0504] The device displays suggestions to the user, for example, "Recommended T-shirts are: YogaWorks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0505] Specific examples

[0506] For example, a female user in her 30s raising a child inputs a request such as "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and the clothes she usually buys cost 5,000 yen." Based on this, the server complements the prompt with "Please recommend a yoga brand T-shirt that costs around 5,000 yen for a woman in her 30s raising a child," and sends it to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works T-shirt A, Lululemon T-shirt B, Nike T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[0507] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0508] Step 1:

[0509] A user opens an application on their device and enters a request such as "Tell me what T-shirts you recommend!" This request is sent to the application on their device. The input is text data that describes the user's needs, and the output is an HTTP request that is sent to the server.

[0510] Step 2:

[0511] The terminal sends the user's input data (request and user ID) to the server. Specifically, it uses an HTTP POST request to send the request content and user ID to the server. The input is the user's request and user ID, and the output is the request to the server.

[0512] Step 3:

[0513] The server analyzes the received request and sends a query to the database based on the user ID. Specifically, it accesses the database using an SQL query in the format "SELECT FROM user_attributes WHERE user_id = ?". The input is the user ID, and the output is the user's attribute information.

[0514] Step 4:

[0515] The server generates detailed and specific prompts based on the user's attribute information (e.g., age, gender, interests, purchasing history) retrieved from the database. This prompt is created by combining the user's request and attribute information. The input is the user's request and attribute information, and the output is the generated prompt.

[0516] Step 5:

[0517] The server sends the generated prompt to the generative AI model. Specifically, it sends an HTTP POST request to the API endpoint of the generative AI model. The input is the generated prompt, and the output is a request to the generative AI model.

[0518] Step 6:

[0519] A generative AI model generates optimal product suggestions based on the prompts received. It uses an internal algorithm to analyze the prompts and generate a product list. The input is the received prompt, and the output is the generated suggestions (product list).

[0520] Step 7:

[0521] The generative AI model returns the generated proposal to the server, which then sends the received proposal to the user's device. The input is the proposal from the generative AI model, and the output is a request sent to the user's device.

[0522] Step 8:

[0523] The terminal displays the suggestions received from the server to the user. Specifically, the suggestions are displayed as text in the application's user interface. The input is the suggestion data from the server, and the output is the display on the user interface.

[0524] (Application example 1)

[0525] 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."

[0526] Conventional mail-order sites and online shopping platforms can only make general suggestions in response to user requests, making it difficult to make customized suggestions that take into account the attributes and history information of individual users. For this reason, there has been a demand for a system that can quickly and accurately recommend products and services that are suitable for each user.

[0527] 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.

[0528] In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information and history information based on the request, means for generating and completing a prompt using the acquired attribute information and history information, means for transmitting the generated prompt to a generative AI model, and means for providing suggestions returned from the generative AI model to the user's terminal, thereby enabling highly accurate product and service suggestions based on the user's attribute information and history information.

[0529] "User" refers to the general consumer or client who uses the system.

[0530] "Request" refers to a request or inquiry entered by a user.

[0531] "Attribute information" refers to information that indicates personal characteristics such as a user's age, gender, interests, purchasing history, etc.

[0532] "History information" refers to data that indicates a user's past behavior, purchase history, and the like.

[0533] A "prompt" refers to a command statement that instructs a generative artificial intelligence model to perform specific processing or generation.

[0534] A "generative artificial intelligence model" refers to an algorithm or machine learning model that generates appropriate suggestions or answers based on input prompts.

[0535] A "terminal" is a device operated by a user, such as a smartphone, tablet, or personal computer.

[0536] "Suggestion" refers to the optimal product or service recommendation for the user returned from the generative artificial intelligence model.

[0537] The present invention provides a system for making highly accurate suggestions using a generative artificial intelligence model by utilizing user attribute information and history information. A specific embodiment of this system will be described below.

[0538] System configuration

[0539] The system consists of the following main components:

[0540] 1. Device:

[0541] A device operated by a user, including a smartphone, tablet, personal computer, etc. This terminal functions as an interface for the user to input requests.

[0542] 2. Server:

[0543] This is the central system for processing user requests and linking with the generative AI model. The server is connected to a database that manages user attribute information and history information.

[0544] 3. Database:

[0545] It stores attribute information and history information such as the user's age, gender, interests, and purchasing history.

[0546] 4. Generative AI Models:

[0547] It is an algorithm or machine learning model that generates optimal suggestions based on prompts sent from the server.

[0548] Program processing flow

[0549] The processing of the program in the system is as follows.

[0550] 1. User request input:

[0551] The user inputs a request through the terminal. For example, the user inputs a request such as "Tell me what shoes you recommend!"

[0552] 2. Send a request to the server and get user attribute information:

[0553] When a request sent from a device reaches the server, the server retrieves attribute and history information from a database based on the user ID, including age, gender, interests, and purchasing history.

[0554] 3. Prompt generation and completion:

[0555] The server generates prompts based on the acquired attribute information and history information, and fills in the details. For example, a prompt may be generated that recommends "running shoes for men in their 20s that cost less than 7,000 yen."

[0556] 4. Proposal generation using generative artificial intelligence model:

[0557] The generated prompts are then sent to a generative artificial intelligence model, which then generates optimal recommendations, such as specific product recommendations like "Nike running shoes A, Adidas running shoes B, Puma running shoes C."

[0558] 5. Return suggestions and display them to the user:

[0559] The server returns the suggested products to the terminal, which displays them to the user, who can then review the details of the suggested products and make a selection.

[0560] Specific examples

[0561] For example, consider the case where a male user in his 20s types "Tell me what shoes you recommend!" into a shopping app on his smartphone. At this time, the server retrieves the attribute information "male, 20s, interested in running, purchase price range under 7,000 yen" from the database. Based on this, the server complements the prompt with "running shoes for men in their 20s under 7,000 yen" and sends it to the generative AI model. The generative AI model generates suggestions such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C," which are sent to the user's device via the server. The user can view these suggestions on their smartphone screen and select the most suitable product.

[0562] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0563] Step 1:

[0564] The user inputs a request through the device. Specifically, the user opens a shopping app on their smartphone and inputs a request such as, "Tell me what shoes you recommend!" The input (request) is received by the device and sent to the next step.

[0565] Step 2:

[0566] The terminal sends the received request to the server. The server accesses the database based on the user ID included in the received request. From the database, it obtains attribute information and history information such as the user's age, gender, interests, and purchasing history. Through this process, the user's attribute information and history information are obtained by the server.

[0567] Step 3:

[0568] Based on the user's attribute information and history information acquired by the server, the server generates and completes a detailed prompt. Specifically, the server generates a detailed prompt such as "Running shoes for men in their 20s, under 7,000 yen." This prompt is customized to match specific user attributes. The input request and acquired attribute information are processed and output as a detailed prompt.

[0569] Step 4:

[0570] The server sends the generated prompt to the generative AI model. Specifically, the generated prompt text is sent to the generative AI model (for example, an API endpoint on the cloud). An example of a prompt text is "Running shoes for men in their 20s, priced under 7,000 yen."

[0571] Step 5:

[0572] The generative AI model generates optimal suggestions based on the received prompt. The model analyzes the information contained in the prompt and makes specific product suggestions, such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C." The generated suggestions are sent back from the generative AI model to the server, where the input prompt is processed and output as appropriate suggestions.

[0573] Step 6:

[0574] The server returns the suggestions received from the generative AI model to the user's device. The server then reformats the returned suggestion data and sends it to the user's device. This results in the device displaying suggestions such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C." The suggestion data is reformatted and output in a format suitable for display to the user.

[0575] This allows users to use their devices to receive highly accurate and customized product suggestions and select the most suitable products.

[0576] 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.

[0577] This invention is a system that combines a user's attribute information with an emotion engine that recognizes the user's emotion information, utilizes a generative AI model to complement prompts, and provides the user with highly accurate information and suggestions. Specific embodiments of this system are described below.

[0578] Overall system configuration

[0579] The system mainly consists of the following elements:

[0580] Terminal: A device that a user operates, including smartphones, tablets, and personal computers.

[0581] Server: Processes user requests, works with the generative AI model, and is connected to a database that manages user attribute information and emotional information.

[0582] Database: Stores user attribute information, history information, and emotional information.

[0583] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0584] Emotion Engine: An engine that uses technology to recognize emotions from the user's voice, text, and facial expressions.

[0585] Program processing flow

[0586] The operation of this system is mainly as follows.

[0587] 1. User request input:

[0588] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[0589] 2. Sending a request to the server:

[0590] The terminal sends the user's input to the server. The sent data includes the user ID.

[0591] 3. Obtaining user attribute information:

[0592] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[0593] 4. Acquiring emotional information:

[0594] The server uses an emotion engine to obtain emotional information from the user's voice, text, and facial expressions, such as stress level, satisfaction, and motivation.

[0595] 5. Prompt generation and completion:

[0596] The server complements the prompt based on the user's request, attribute information, and emotional information. This allows for the generation of more detailed and specific prompts. For example, a prompt might be generated such as, "For a woman in her 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[0597] 6. Send to the generative AI model:

[0598] The server generates and sends the completed prompt to the generative artificial intelligence model.

[0599] 7. Proposal generation using generative artificial intelligence model:

[0600] Based on the prompts received, the generative AI model generates optimal product recommendations, such as "YogaWorks Relaxing T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[0601] 8. Returning suggestions and displaying them to the user:

[0602] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[0603] The device displays suggestions to the user, such as "Recommended T-shirts: Yoga Works Relaxing T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[0604] Specific examples

[0605] For example, a female user in her 30s raising a child might input a request such as, "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and usually spends 5,000 yen on clothes." At the same time, the emotion engine analyzes the user's facial expressions and recognizes that her current stress level is high. Based on this, the server complements the prompt with, "For a female user in her 30s raising a child who is currently feeling stressed, please recommend a relaxing T-shirt from a yoga brand that costs around 5,000 yen," and sends this to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works Relaxing T-shirt A, Lululemon Comfortable T-shirt B, and Nike Stress Relief T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[0606] This system allows users to receive highly accurate suggestions that reflect their own attribute information, interests, and real-time emotional information, further improving satisfaction.

[0607] The processing flow will be explained below.

[0608] Program processing flow

[0609] Step 1:

[0610] The user opens the application on the device and enters a request such as, "Tell me what T-shirts you recommend!" The device receives this request and sends it to the server as JSON format data.

[0611] Example of data to send: { "request": "What T-shirts do you recommend?", "userID": "12345"}

[0612] Step 2:

[0613] The server analyzes the request received from the terminal and accesses the database based on the user ID. The server then uses an SQL query to retrieve user attribute information from the database.

[0614] Example of information to be acquired: { "age": "30s", "gender": "female", "interests": ["yoga"], "purchaseHistory": { "average_spend": 5000}, "status": "parent"}

[0615] Step 3:

[0616] The server activates the emotion engine, which collects voice, text, and facial expression data from the user's device. The emotion engine analyzes this data and recognizes the user's emotional information.

[0617] Emotion information example: { "stress_level": "high", "satisfaction": "neutral", "motivation": "low"}

[0618] Step 4:

[0619] The server complements the prompts appropriate for the request based on the user's attribute information and emotional information. Specifically, it generates detailed prompts based on the user's request, attribute information, and emotional information.

[0620] Example of a completed prompt: { "prompt": "For a user in their 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."}

[0621] Step 5:

[0622] The server sends the completed prompts to the generative artificial intelligence model using an HTTP POST request.

[0623] Example API request: POST / generate-recommendation { "prompt": "Recommend a relaxing yoga brand T-shirt for around 5,000 yen to a user who is a woman in her 30s raising children and currently feeling stressed."}

[0624] Step 6:

[0625] The generative AI model receives the prompt and uses its internal inference algorithm to generate the best possible suggestion. The generative AI model then compiles the suggestion results into JSON format data and sends it back to the server.

[0626] Example of inference result: { "recommendations": ["YogaWorks Relaxing T-shirt A", "Lululemon Comfort T-shirt B", "Nike Stress Relief T-shirt C"]}

[0627] Step 7:

[0628] The server analyzes the proposal result data received from the generative AI model and converts it into an appropriate format. The server then transfers this data to the device.

[0629] Step 8:

[0630] The terminal displays the recommendation results received from the server on the user interface, allowing the user to check the recommended product information on the terminal and select the next action to purchase or check the details.

[0631] Example: "Recommended t-shirts are: Yoga Works Relax T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[0632] Through the above processing steps, the user can receive highly accurate suggestions that utilize attribute information and emotion information based on the input request.

[0633] Example 2

[0634] 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."

[0635] In conventional systems, prompts were generated and suggestions were made based only on individual attribute information in response to user requests, making it difficult to provide highly accurate suggestions that reflected the user's mental state and emotional information in real time.In addition, to improve user satisfaction, individual responses based on the user's situation and emotions are required, and in this respect conventional systems were insufficient.

[0636] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information based on the request, means for generating and complementing a prompt using the acquired attribute information and user emotional information, means for transmitting the generated prompt to a generative AI model, and means for providing the user with a proposal returned from the generative AI model. This makes it possible to make highly accurate proposals that include the user's real-time emotional state.

[0637] A "user" is an individual or organization that uses the system and is the entity that inputs requests.

[0638] A "request" is a request or question that a user inputs to the system, and is information that the system must process.

[0639] "User attribute information" refers to information about the user, such as age, gender, interests, and purchasing history, and is referenced when generating prompts.

[0640] "Emotional information" refers to the emotional state of the user as recognized by their voice, text, and facial expressions, and is acquired in real time.

[0641] A "prompt" is a basic instruction that allows a generative artificial intelligence model to generate suggestions for a user.

[0642] A "generative artificial intelligence model" is an artificial intelligence algorithm that takes a user's requests or prompts as input and generates appropriate suggestions.

[0643] A "proposal" is a specific product or service that a generative artificial intelligence model generates based on a prompt and provides to a user.

[0644] This invention is a system that combines a user's attribute information with an emotion engine that recognizes the user's emotion information, utilizes a generative artificial intelligence model to complement prompts, and provides the user with highly accurate information and suggestions. Specific embodiments of this system are described below.

[0645] The system mainly consists of the following elements:

[0646] Terminal: A device that a user operates, including smartphones, tablets, and personal computers.

[0647] Server: Processes user requests, works with the generative AI model, and is connected to a database that manages user attribute information and emotional information.

[0648] Database: Stores user attribute information, history information, and emotional information.

[0649] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0650] Emotion Engine: An engine that uses technology to recognize emotions from the user's voice, text, and facial expressions.

[0651] The specific operational flow when implementing this is as follows:

[0652] 1. User request input:

[0653] The user opens the application on their device and enters a request, for example, "Tell me what T-shirts you recommend!"

[0654] 2. Sending a request to the server:

[0655] The terminal sends the user's input to the server. The sent data includes the user ID.

[0656] 3. Obtaining user attribute information:

[0657] The server accesses the database based on the user ID and obtains the user's attribute information (age, gender, interests, purchasing history, etc.) For example, if the user is a woman in her 30s raising a child and is interested in yoga brands, the direction of suggestions can be narrowed down based on this information.

[0658] 4. Acquiring emotional information:

[0659] The server uses an emotion engine to obtain emotional information from the user's voice, text, and facial expressions, for example, to analyze whether the user is currently feeling stressed.

[0660] 5. Prompt generation and completion:

[0661] The server complements the prompt based on the user's request, attribute information, and emotional information. This allows for the generation of more detailed and specific prompts. For example, a prompt might be generated such as, "For a woman in her 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[0662] 6. Send to the generative AI model:

[0663] The server generates and sends the completed prompt to the generative artificial intelligence model.

[0664] 7. Proposal generation using generative artificial intelligence model:

[0665] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "relaxing T-shirt A from a yoga brand, comfortable T-shirt B from a sports brand, and stress-reducing T-shirt C from an outdoor brand."

[0666] 8. Returning suggestions and displaying them to the user:

[0667] The server receives suggestions from the generative AI model and sends them back to the user's device. The device then displays the suggestions to the user. For example, the suggestions might look like this: "Recommended T-shirts are: Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, and Stress-reducing T-shirt C from an outdoor brand."

[0668] This specific form allows users to receive highly accurate suggestions that reflect their own attribute information, interests, and real-time emotional information, further improving their satisfaction.

[0669] The above is an embodiment of the invention, and this system is capable of making highly accurate suggestions that take into account the user's real-time emotional state.

[0670] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0671] Step 1:

[0672] The user opens the application on the terminal and enters a request.

[0673] Specific actions

[0674] - A user uses a smartphone or computer to type "Tell me your recommended T-shirt!" and presses the send button.

[0675] input

[0676] - Request: "What T-shirts do you recommend?"

[0677] output

[0678] - Request data: User ID and entered request details.

[0679] Step 2:

[0680] The device sends the request to the server.

[0681] Specific actions

[0682] - The device assembles the user ID and the input request content into a packet and sends an HTTP POST request to the server.

[0683] input

[0684] - A data packet containing the user ID and the request content.

[0685] output

[0686] - The request data received by the server.

[0687] Step 3:

[0688] The server retrieves user attribute information from the database based on the user ID.

[0689] Specific actions

[0690] - The server sends an SQL query to the database to retrieve attribute information using "SELECT FROM user_attributes WHERE user_id = user ID".

[0691] input

[0692] - User ID.

[0693] output

[0694] - User demographic information: Data such as age, gender, interests, and purchasing history.

[0695] Step 4:

[0696] The server acquires the user's emotion information using an emotion engine.

[0697] Specific actions

[0698] - The server sends voice input and facial expression data acquired by the camera to the emotion engine API to acquire emotion information.

[0699] input

[0700] - User voice, text and facial expression data.

[0701] output

[0702] - Emotional information: data such as stress levels, satisfaction, and motivation.

[0703] Step 5:

[0704] The server generates and completes prompts based on the user's request, attribute information, and emotional information.

[0705] Specific actions

[0706] - The server combines the request content, user attribute information, and emotional information to generate a detailed prompt. Example: "For a user in their 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[0707] input

[0708] - User requests, attribute information, and emotional information.

[0709] output

[0710] - Completed prompt sentence.

[0711] Step 6:

[0712] The server sends the generated prompt to the generative artificial intelligence model.

[0713] Specific actions

[0714] - The server sends the prompt sentence to the generative AI model as an API request.

[0715] input

[0716] - Completed prompt sentence.

[0717] output

[0718] - Prompt data sent to generative artificial intelligence models.

[0719] Step 7:

[0720] A generative artificial intelligence model generates optimal suggestions based on prompts.

[0721] Specific actions

[0722] - A generative AI model analyzes the prompts received and generates appropriate product suggestions, e.g., "Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, Stress-reducing T-shirt C from an outdoor brand."

[0723] input

[0724] - Completed prompt sentence.

[0725] output

[0726] - Proposal data: Multiple product proposal lists.

[0727] Step 8:

[0728] The server receives suggestions from the generative artificial intelligence model and returns them to the user's device.

[0729] Specific actions

[0730] - The server receives the suggestion data and sends it to the user's device. The device displays the suggestion to the user. For example, "The recommended T-shirts are: Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, and Stress-reducing T-shirt C from an outdoor brand."

[0731] input

[0732] - Proposal data.

[0733] output

[0734] - A list of suggestions displayed on the user's device.

[0735] This concludes the detailed explanation of each processing step. This detailed flow enables users to quickly receive highly accurate suggestions that reflect their own attribute information and emotional state.

[0736] (Application example 2)

[0737] 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."

[0738] Conventional user suggestion systems generate suggestions based only on the user's attribute information, making it difficult to reflect the user's emotional state. Therefore, there is a need for a method that takes into account the user's real-time emotional information and provides more personalized and accurate suggestions. Furthermore, there is a lack of technology that can timely recommend content appropriate to the user's emotional state, especially in content distribution services such as video and movie streaming.

[0739] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a request input from a user, means for acquiring attribute information and emotional information of the user, means for generating and complementing a prompt using the acquired attribute information and emotional information, means for sending the generated prompt to a generative AI model, and means for providing the user with a suggestion returned from the generative AI model. This enables highly accurate content suggestions that take into account the user's real-time emotional state.

[0740] The "means for receiving a request input by a user" refers to a device or program having a function for receiving a request when the user inputs the request into the system via an input device.

[0741] "Means for acquiring user attribute information and emotional information" refers to a device or program for detecting, extracting, and collecting a user's basic attributes (age, gender, interests, purchasing history, etc.) and emotional state (stress level, satisfaction, etc.).

[0742] A "means for generating and complementing prompts" is a device or program that creates instructions suitable for a generative artificial intelligence model based on a user's request and acquired attribute information and emotional information, and complements the instructions with additional information to make them more specific and effective.

[0743] The "means for transmitting to the generative artificial intelligence model" is a device or program for transmitting the generated and completed prompt to the generative artificial intelligence model via a network.

[0744] "Means for providing a user with suggestions returned from a generative artificial intelligence model" refers to a device or program for receiving suggestions generated by a generative artificial intelligence model based on a prompt and displaying or notifying the user of the suggestions.

[0745] This invention is a system that utilizes a generative artificial intelligence model to make highly accurate suggestions based on user attribute information and emotion information. The system configuration for implementing this includes a user terminal, a server, a database, a generative artificial intelligence model, and an emotion engine.

[0746] Overall system configuration

[0747] The system mainly consists of the following components:

[0748] User terminal: A device that a user operates and inputs requests and emotional data (facial images, voice data). Specific examples include smartphones, tablets, and personal computers.

[0749] Server: Receives user requests, acquires and processes various data, and interacts with the generative AI model.

[0750] Database: Stores user attribute information, history information, and emotional information.

[0751] Generative AI model: An AI model that generates optimal suggestions based on prompts sent from the server.

[0752] Emotion engine: An engine that recognizes emotions from the user's voice, text, and facial expressions and provides that information.

[0753] Devices and Software

[0754] Frontend: React Native (smartphone app)

[0755] Backend: Django (Python), Flask

[0756] Database: PostgreSQL

[0757] Emotion engine: OpenCV (face recognition), Google Cloud Speech-to-Text (voice recognition)

[0758] Generative AI model: OpenAI GPT-4

[0759] Operating Procedure

[0760] 1. Input of a request: The user inputs a request into the terminal. For example, "Tell me some recommended movies."

[0761] 2. Data Acquisition: The server receives the request entered by the user and acquires the user's attribute information (age, gender, interests, etc.) from the database. At the same time, it uses the emotion engine to analyze the user's emotional information (current stress level, satisfaction level, etc.).

[0762] 3. Prompt generation and completion: The server generates and completes detailed and specific prompts based on the acquired user attribute information and emotional information.

[0763] 4. Generate suggestions: The generated prompts are sent to a generative artificial intelligence model (GPT-4) to generate optimal suggestions.

[0764] 5. Providing suggestions: Receive suggestions from the generative AI model and display them on the user's device.

[0765] Examples of prompt statements

[0766] "Please recommend some movies to a user who is a man in his 30s, currently feeling stressed, and interested in science fiction and action movies."

[0767] "Please recommend some dramas to a female user in her 20s who wants to relax and is interested in comedy dramas."

[0768] Example scenario

[0769] For example, if a male user in his 30s inputs a request such as "Please recommend some movies," the server retrieves attribute information from the database, such as "Age: 30s, Gender: Male, Interests: Sci-Fi, Action." At the same time, the emotion engine recognizes a high stress level from the user's facial image and voice. Based on this, the server generates a prompt and sends it to a generative artificial intelligence model (GPT-4). The generative artificial intelligence model suggests movies such as "Inception," "The Matrix," and "Transformers," which are sent to the user's device via the server. The user can review these suggestions and select the best movie for their condition.

[0770] In this way, the system allows users to receive highly accurate suggestions that reflect their own attribute information and emotional state, improving their satisfaction with content selection.

[0771] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0772] Step 1:

[0773] A user inputs a request to the system through a terminal. For example, a user can input "Tell me some recommended movies." This input is sent to the server by the terminal. The input data is text information and includes the user's request.

[0774] Step 2:

[0775] The server receives the user's request sent from the terminal. The received request data includes the user ID, which is used to query the database and obtain the user's attribute information. The obtained attribute information includes age, gender, interests, purchasing history, etc. This process prepares the user's basic information.

[0776] Step 3:

[0777] The server uses an emotion engine based on the user's attribute information to obtain emotional information. Specifically, it recognizes the user's current emotional state (stress level, satisfaction, etc.) by analyzing the facial image and voice data provided by the user during input. OpenCV and Google Cloud Speech-to-Text are used to obtain this emotional information. The input data are images and voice, and the output data are numerical values ​​and category information of the emotional state.

[0778] Step 4:

[0779] The server combines the acquired attribute information and emotional information to generate and complement prompts suitable for the generative AI model. These prompts include attribute information such as the user's age, gender, and interests, as well as emotional information such as stress level. The generated prompts are detailed and specific instructions. For example, they could be in the form of "Please recommend movies to a user who is a man in his 30s, currently feeling stressed, and interested in science fiction and action movies."

[0780] Step 5:

[0781] The server sends the generated and completed prompts to a generative AI model (e.g., GPT-4), which receives the sent prompts and generates optimal suggestions based on them. In this case, the input data is the prompts, and the output data is a list of suggestions.

[0782] Step 6:

[0783] The generative AI model sends back the proposed results to the server. The server receives the proposed results and sends them to the user's device. The proposed results are, for example, a list of movies such as "Inception," "The Matrix," and "Transformers."

[0784] Step 7:

[0785] The user's device displays the suggestions received from the server, and the user can review these suggestions and choose the movie that best suits their emotional state and interests. The information displayed includes specific titles and synopses, allowing the user to make a decision based on them.

[0786] At each step, the input data is processed appropriately, and the final output is the optimal proposal provided to the user, which also improves user satisfaction.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] [Third embodiment]

[0791] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0792] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0793] 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).

[0794] 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.

[0795] 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.

[0796] 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).

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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."

[0803] This invention is a system that utilizes a generative artificial intelligence model based on user attribute information to complement prompts and provide highly accurate information and suggestions to users. Specific embodiments of this system are described below.

[0804] Overall system configuration

[0805] The system mainly consists of the following elements:

[0806] Terminal: The device on which the user operates. This includes smartphones, tablets, personal computers, etc.

[0807] Server: Processes user requests and interacts with the generative AI model. It is also connected to a database that manages user attribute information.

[0808] Database: Stores user attribute information and history information.

[0809] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0810] Program processing flow

[0811] The operation of this system is mainly as follows.

[0812] 1. User request input:

[0813] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[0814] 2. Sending a request to the server:

[0815] The terminal sends the user's input to the server. The sent data includes the user ID.

[0816] 3. Obtaining user attribute information:

[0817] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[0818] 4. Prompt generation and completion:

[0819] The server complements the prompt based on the user's request and attribute information. This allows for more detailed and specific prompts to be generated. For example, a prompt might be generated such as, "Please recommend a yoga brand T-shirt for around 5,000 yen for a woman in her 30s who is raising children."

[0820] 5. Send to the generative AI model:

[0821] The server sends the generated prompt to the generative artificial intelligence model.

[0822] 6. Proposal generation using generative artificial intelligence model:

[0823] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "Yogaworks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0824] 7. Returning suggestions and displaying them to the user:

[0825] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[0826] The device displays suggestions to the user, for example, "Recommended T-shirts are: YogaWorks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0827] Specific examples

[0828] For example, a female user in her 30s raising a child might input a request such as, "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and the clothes she usually buys cost 5,000 yen." Based on this, the server complements the prompt with, "Please recommend a yoga brand T-shirt that costs around 5,000 yen for a woman in her 30s raising a child," and sends it to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works T-shirt A, Lululemon T-shirt B, Nike T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[0829] This system allows users to receive highly accurate suggestions customized based on their attributes and interests, making product selection easier and increasing satisfaction.

[0830] The processing flow will be explained below.

[0831] Program processing flow

[0832] Step 1:

[0833] The user opens the application on the device and enters a request such as, "Tell me what T-shirts you recommend!" The device receives this request and sends it to the server as JSON format data.

[0834] Example: { "request": "What T-shirt do you recommend?", "userID": "12345"}

[0835] Step 2:

[0836] The server analyzes the request received from the terminal and accesses the database based on the user ID. The server then uses an SQL query to retrieve user attribute information from the database.

[0837] Example of information to retrieve: { "age": "30s", "gender": "female", "interests": ["yoga"], "purchaseHistory": { "average_spend": 5000}, "status": "parent"}

[0838] Step 3:

[0839] The server uses the user's attribute information acquired to complete a prompt appropriate to the request. Specifically, it generates a detailed prompt based on the user's request and attribute information.

[0840] Example of a completed prompt: { "prompt": "Please recommend a yoga brand T-shirt for a woman in her 30s who is raising children, priced around 5,000 yen."}

[0841] Step 4:

[0842] The server sends the completed prompts to the generative artificial intelligence model using an HTTP POST request.

[0843] Example API request: POST / generate-recommendation { "prompt": "Please recommend a yoga brand T-shirt for a woman in her 30s raising children, priced at around 5,000 yen."}

[0844] Step 5:

[0845] The generative AI model receives the prompt and uses its internal inference algorithm to generate the best possible suggestion. The generative AI model then compiles the suggestion results into JSON format data and sends it back to the server.

[0846] Example of inference result: { "recommendations": ["Yogaworks T-shirt A", "Lululemon T-shirt B", "Nike T-shirt C"]}

[0847] Step 6:

[0848] The server analyzes the proposal results received from the generative AI model and converts them into an appropriate format. The server then transfers this data to the device.

[0849] Step 7:

[0850] The terminal displays the recommendation results received from the server on the user interface, allowing the user to check the recommended product information on the terminal and select the next action to purchase or check the details.

[0851] Example: "Recommended t-shirts are: Yoga Works t-shirt A, Lululemon t-shirt B, Nike t-shirt C."

[0852] Through the above processing steps, highly accurate proposals can be generated using the user's attribute information based on the request input by the user, and provided to the user.

[0853] Example 1

[0854] 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."

[0855] Conventional systems have difficulty generating detailed prompts necessary to make accurate proposals in response to user requests, and have been unable to effectively utilize user attribute information. This has resulted in the inability to adequately propose products and services that meet user needs, making it difficult to increase user satisfaction.

[0856] 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.

[0857] In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information from a database based on the request, means for generating and completing detailed and specific prompts using the acquired attribute information, means for transmitting the generated prompts to a generative AI model, and means for providing the user with product or service suggestions returned from the generative AI model, thereby enabling highly accurate suggestions customized based on the user's attribute information.

[0858] "Requests input by a user" refers to information or requests provided by a user to the system via a terminal.

[0859] "User attribute information" refers to personal information and historical information about a user, including data such as age, gender, interests, and purchasing history.

[0860] "Database" refers to a system or device that has a data structure that stores user attribute information and other information and allows it to be searched and retrieved.

[0861] The "means for generating and completing prompts" refers to a means having a function for automatically creating more detailed and specific request content based on the user's attribute information and requests.

[0862] A "generative artificial intelligence model" is an artificial intelligence that has the ability to generate product and service suggestions based on prompts it receives.

[0863] "Product or service suggestions" refers to recommended products or services provided to a user by a generative artificial intelligence model based on prompts.

[0864] A "server" is a computer system that receives and processes user requests and communicates with the generative artificial intelligence model.

[0865] This invention is a system that utilizes a generative artificial intelligence model to complement prompts based on user attribute information and provides the user with highly accurate information and suggestions. Specifically, the user inputs a request from a terminal, the system obtains the user's attribute information from a database based on the request, and generates and complements detailed and specific prompts using the obtained attribute information. The system then sends the generated prompts to the generative artificial intelligence model, and provides the user with suggestions returned from the generative artificial intelligence model.

[0866] Overall system configuration

[0867] The system mainly consists of the following elements:

[0868] Terminal: The device on which the user operates. This includes smartphones, tablets, personal computers, etc.

[0869] Server: Processes user requests and interacts with the generative AI model. It is also connected to a database that manages user attribute information.

[0870] Database: Stores user attribute information and history information.

[0871] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0872] Program processing

[0873] 1. User request input

[0874] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[0875] 2. Sending a request to the server

[0876] The terminal sends the user's input to the server. The sent data includes the user ID.

[0877] 3. Obtaining user attribute information

[0878] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[0879] 4. Prompt generation and completion

[0880] The server complements the prompt based on the user's request and attribute information. This allows for more detailed and specific prompts to be generated. For example, a prompt might be generated such as, "Please recommend a yoga brand T-shirt for around 5,000 yen for a woman in her 30s who is raising children."

[0881] 5. Sending to the generative AI model

[0882] The server sends the generated prompt to the generative artificial intelligence model.

[0883] 6. Proposal generation using a generative artificial intelligence model

[0884] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "Yogaworks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0885] 7. Returning suggestions and displaying them to the user

[0886] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[0887] The device displays suggestions to the user, for example, "Recommended T-shirts are: YogaWorks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[0888] Specific examples

[0889] For example, a female user in her 30s raising a child inputs a request such as "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and the clothes she usually buys cost 5,000 yen." Based on this, the server complements the prompt with "Please recommend a yoga brand T-shirt that costs around 5,000 yen for a woman in her 30s raising a child," and sends it to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works T-shirt A, Lululemon T-shirt B, Nike T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[0890] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0891] Step 1:

[0892] A user opens an application on their device and enters a request such as "Tell me what T-shirts you recommend!" This request is sent to the application on their device. The input is text data that describes the user's needs, and the output is an HTTP request that is sent to the server.

[0893] Step 2:

[0894] The terminal sends the user's input data (request and user ID) to the server. Specifically, it uses an HTTP POST request to send the request content and user ID to the server. The input is the user's request and user ID, and the output is the request to the server.

[0895] Step 3:

[0896] The server analyzes the received request and sends a query to the database based on the user ID. Specifically, it accesses the database using an SQL query in the format "SELECT FROM user_attributes WHERE user_id = ?". The input is the user ID, and the output is the user's attribute information.

[0897] Step 4:

[0898] The server generates detailed and specific prompts based on the user's attribute information (e.g., age, gender, interests, purchasing history) retrieved from the database. This prompt is created by combining the user's request and attribute information. The input is the user's request and attribute information, and the output is the generated prompt.

[0899] Step 5:

[0900] The server sends the generated prompt to the generative AI model. Specifically, it sends an HTTP POST request to the API endpoint of the generative AI model. The input is the generated prompt, and the output is a request to the generative AI model.

[0901] Step 6:

[0902] A generative AI model generates optimal product suggestions based on the prompts received. It uses an internal algorithm to analyze the prompts and generate a product list. The input is the received prompt, and the output is the generated suggestions (product list).

[0903] Step 7:

[0904] The generative AI model returns the generated proposal to the server, which then sends the received proposal to the user's device. The input is the proposal from the generative AI model, and the output is a request sent to the user's device.

[0905] Step 8:

[0906] The terminal displays the suggestions received from the server to the user. Specifically, the suggestions are displayed as text in the application's user interface. The input is the suggestion data from the server, and the output is the display on the user interface.

[0907] (Application example 1)

[0908] 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."

[0909] Conventional mail-order sites and online shopping platforms can only make general suggestions in response to user requests, making it difficult to make customized suggestions that take into account the attributes and history information of individual users. For this reason, there has been a demand for a system that can quickly and accurately recommend products and services that are suitable for each user.

[0910] 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.

[0911] In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information and history information based on the request, means for generating and completing a prompt using the acquired attribute information and history information, means for transmitting the generated prompt to a generative AI model, and means for providing suggestions returned from the generative AI model to the user's terminal, thereby enabling highly accurate product and service suggestions based on the user's attribute information and history information.

[0912] "User" refers to the general consumer or client who uses the system.

[0913] "Request" refers to a request or inquiry entered by a user.

[0914] "Attribute information" refers to information that indicates personal characteristics such as a user's age, gender, interests, purchasing history, etc.

[0915] "History information" refers to data that indicates a user's past behavior, purchase history, and the like.

[0916] A "prompt" refers to a command statement that instructs a generative artificial intelligence model to perform specific processing or generation.

[0917] A "generative artificial intelligence model" refers to an algorithm or machine learning model that generates appropriate suggestions or answers based on input prompts.

[0918] A "terminal" is a device operated by a user, such as a smartphone, tablet, or personal computer.

[0919] "Suggestion" refers to the optimal product or service recommendation for the user returned from the generative artificial intelligence model.

[0920] The present invention provides a system for making highly accurate suggestions using a generative artificial intelligence model by utilizing user attribute information and history information. A specific embodiment of this system will be described below.

[0921] System configuration

[0922] The system consists of the following main components:

[0923] 1. Device:

[0924] A device operated by a user, including a smartphone, tablet, personal computer, etc. This terminal functions as an interface for the user to input requests.

[0925] 2. Server:

[0926] This is the central system for processing user requests and linking with the generative AI model. The server is connected to a database that manages user attribute information and history information.

[0927] 3. Database:

[0928] It stores attribute information and history information such as the user's age, gender, interests, and purchasing history.

[0929] 4. Generative AI Models:

[0930] It is an algorithm or machine learning model that generates optimal suggestions based on prompts sent from the server.

[0931] Program processing flow

[0932] The processing of the program in the system is as follows.

[0933] 1. User request input:

[0934] The user inputs a request through the terminal. For example, the user inputs a request such as "Tell me what shoes you recommend!"

[0935] 2. Send a request to the server and get user attribute information:

[0936] When a request sent from a device reaches the server, the server retrieves attribute and history information from a database based on the user ID, including age, gender, interests, and purchasing history.

[0937] 3. Prompt generation and completion:

[0938] The server generates prompts based on the acquired attribute information and history information, and fills in the details. For example, a prompt may be generated that recommends "running shoes for men in their 20s that cost less than 7,000 yen."

[0939] 4. Proposal generation using generative artificial intelligence model:

[0940] The generated prompts are then sent to a generative artificial intelligence model, which then generates optimal recommendations, such as specific product recommendations like "Nike running shoes A, Adidas running shoes B, Puma running shoes C."

[0941] 5. Return suggestions and display them to the user:

[0942] The server returns the suggested products to the terminal, which displays them to the user, who can then review the details of the suggested products and make a selection.

[0943] Specific examples

[0944] For example, consider the case where a male user in his 20s types "Tell me what shoes you recommend!" into a shopping app on his smartphone. At this time, the server retrieves the attribute information "male, 20s, interested in running, purchase price range under 7,000 yen" from the database. Based on this, the server complements the prompt with "running shoes for men in their 20s under 7,000 yen" and sends it to the generative AI model. The generative AI model generates suggestions such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C," which are sent to the user's device via the server. The user can view these suggestions on their smartphone screen and select the most suitable product.

[0945] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0946] Step 1:

[0947] The user inputs a request through the device. Specifically, the user opens a shopping app on their smartphone and inputs a request such as, "Tell me what shoes you recommend!" The input (request) is received by the device and sent to the next step.

[0948] Step 2:

[0949] The terminal sends the received request to the server. The server accesses the database based on the user ID included in the received request. From the database, it obtains attribute information and history information such as the user's age, gender, interests, and purchasing history. Through this process, the user's attribute information and history information are obtained by the server.

[0950] Step 3:

[0951] Based on the user's attribute information and history information acquired by the server, the server generates and completes a detailed prompt. Specifically, the server generates a detailed prompt such as "Running shoes for men in their 20s, under 7,000 yen." This prompt is customized to match specific user attributes. The input request and acquired attribute information are processed and output as a detailed prompt.

[0952] Step 4:

[0953] The server sends the generated prompt to the generative AI model. Specifically, the generated prompt text is sent to the generative AI model (for example, an API endpoint on the cloud). An example of a prompt text is "Running shoes for men in their 20s, priced under 7,000 yen."

[0954] Step 5:

[0955] The generative AI model generates optimal suggestions based on the received prompt. The model analyzes the information contained in the prompt and makes specific product suggestions, such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C." The generated suggestions are sent back from the generative AI model to the server, where the input prompt is processed and output as appropriate suggestions.

[0956] Step 6:

[0957] The server returns the suggestions received from the generative AI model to the user's device. The server then reformats the returned suggestion data and sends it to the user's device. This results in the device displaying suggestions such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C." The suggestion data is reformatted and output in a format suitable for display to the user.

[0958] This allows users to use their devices to receive highly accurate and customized product suggestions and select the most suitable products.

[0959] 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.

[0960] This invention is a system that combines a user's attribute information with an emotion engine that recognizes the user's emotion information, utilizes a generative AI model to complement prompts, and provides the user with highly accurate information and suggestions. Specific embodiments of this system are described below.

[0961] Overall system configuration

[0962] The system mainly consists of the following elements:

[0963] Terminal: A device that a user operates, including smartphones, tablets, and personal computers.

[0964] Server: Processes user requests, works with the generative AI model, and is connected to a database that manages user attribute information and emotional information.

[0965] Database: Stores user attribute information, history information, and emotional information.

[0966] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[0967] Emotion Engine: An engine that uses technology to recognize emotions from the user's voice, text, and facial expressions.

[0968] Program processing flow

[0969] The operation of this system is mainly as follows.

[0970] 1. User request input:

[0971] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[0972] 2. Sending a request to the server:

[0973] The terminal sends the user's input to the server. The sent data includes the user ID.

[0974] 3. Obtaining user attribute information:

[0975] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[0976] 4. Acquiring emotional information:

[0977] The server uses an emotion engine to obtain emotional information from the user's voice, text, and facial expressions, such as stress level, satisfaction, and motivation.

[0978] 5. Prompt generation and completion:

[0979] The server complements the prompt based on the user's request, attribute information, and emotional information. This allows for the generation of more detailed and specific prompts. For example, a prompt might be generated such as, "For a woman in her 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[0980] 6. Send to the generative AI model:

[0981] The server generates and sends the completed prompt to the generative artificial intelligence model.

[0982] 7. Proposal generation using generative artificial intelligence model:

[0983] Based on the prompts received, the generative AI model generates optimal product recommendations, such as "YogaWorks Relaxing T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[0984] 8. Returning suggestions and displaying them to the user:

[0985] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[0986] The device displays suggestions to the user, such as "Recommended T-shirts: Yoga Works Relaxing T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[0987] Specific examples

[0988] For example, a female user in her 30s raising a child might input a request such as, "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and usually spends 5,000 yen on clothes." At the same time, the emotion engine analyzes the user's facial expressions and recognizes that her current stress level is high. Based on this, the server complements the prompt with, "For a female user in her 30s raising a child who is currently feeling stressed, please recommend a relaxing T-shirt from a yoga brand that costs around 5,000 yen," and sends this to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works Relaxing T-shirt A, Lululemon Comfortable T-shirt B, and Nike Stress Relief T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[0989] This system allows users to receive highly accurate suggestions that reflect their own attribute information, interests, and real-time emotional information, further improving satisfaction.

[0990] The processing flow will be explained below.

[0991] Program processing flow

[0992] Step 1:

[0993] The user opens the application on the device and enters a request such as, "Tell me what T-shirts you recommend!" The device receives this request and sends it to the server as JSON format data.

[0994] Example of data to send: { "request": "What T-shirts do you recommend?", "userID": "12345"}

[0995] Step 2:

[0996] The server analyzes the request received from the terminal and accesses the database based on the user ID. The server then uses an SQL query to retrieve user attribute information from the database.

[0997] Example of information to be acquired: { "age": "30s", "gender": "female", "interests": ["yoga"], "purchaseHistory": { "average_spend": 5000}, "status": "parent"}

[0998] Step 3:

[0999] The server activates the emotion engine, which collects voice, text, and facial expression data from the user's device. The emotion engine analyzes this data and recognizes the user's emotional information.

[1000] Emotion information example: { "stress_level": "high", "satisfaction": "neutral", "motivation": "low"}

[1001] Step 4:

[1002] The server complements the prompts appropriate for the request based on the user's attribute information and emotional information. Specifically, it generates detailed prompts based on the user's request, attribute information, and emotional information.

[1003] Example of a completed prompt: { "prompt": "For a user in their 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."}

[1004] Step 5:

[1005] The server sends the completed prompts to the generative artificial intelligence model using an HTTP POST request.

[1006] Example API request: POST / generate-recommendation { "prompt": "Recommend a relaxing yoga brand T-shirt for around 5,000 yen to a user who is a woman in her 30s raising children and currently feeling stressed."}

[1007] Step 6:

[1008] The generative AI model receives the prompt and uses its internal inference algorithm to generate the best possible suggestion. The generative AI model then compiles the suggestion results into JSON format data and sends it back to the server.

[1009] Example of inference result: { "recommendations": ["YogaWorks Relaxing T-shirt A", "Lululemon Comfort T-shirt B", "Nike Stress Relief T-shirt C"]}

[1010] Step 7:

[1011] The server analyzes the proposal result data received from the generative AI model and converts it into an appropriate format. The server then transfers this data to the device.

[1012] Step 8:

[1013] The terminal displays the recommendation results received from the server on the user interface, allowing the user to check the recommended product information on the terminal and select the next action to purchase or check the details.

[1014] Example: "Recommended t-shirts are: Yoga Works Relax T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[1015] Through the above processing steps, the user can receive highly accurate suggestions that utilize attribute information and emotion information based on the input request.

[1016] Example 2

[1017] 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."

[1018] In conventional systems, prompts were generated and suggestions were made based only on individual attribute information in response to user requests, making it difficult to provide highly accurate suggestions that reflected the user's mental state and emotional information in real time.In addition, to improve user satisfaction, individual responses based on the user's situation and emotions are required, and in this respect conventional systems were insufficient.

[1019] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information based on the request, means for generating and complementing a prompt using the acquired attribute information and user emotional information, means for transmitting the generated prompt to a generative AI model, and means for providing the user with a proposal returned from the generative AI model. This makes it possible to make highly accurate proposals that include the user's real-time emotional state.

[1020] A "user" is an individual or organization that uses the system and is the entity that inputs requests.

[1021] A "request" is a request or question that a user inputs to the system, and is information that the system must process.

[1022] "User attribute information" refers to information about the user, such as age, gender, interests, and purchasing history, and is referenced when generating prompts.

[1023] "Emotional information" refers to the emotional state of the user as recognized by their voice, text, and facial expressions, and is acquired in real time.

[1024] A "prompt" is a basic instruction that allows a generative artificial intelligence model to generate suggestions for a user.

[1025] A "generative artificial intelligence model" is an artificial intelligence algorithm that takes a user's requests or prompts as input and generates appropriate suggestions.

[1026] A "proposal" is a specific product or service that a generative artificial intelligence model generates based on a prompt and provides to a user.

[1027] This invention is a system that combines a user's attribute information with an emotion engine that recognizes the user's emotion information, utilizes a generative artificial intelligence model to complement prompts, and provides the user with highly accurate information and suggestions. Specific embodiments of this system are described below.

[1028] The system mainly consists of the following elements:

[1029] Terminal: A device that a user operates, including smartphones, tablets, and personal computers.

[1030] Server: Processes user requests, works with the generative AI model, and is connected to a database that manages user attribute information and emotional information.

[1031] Database: Stores user attribute information, history information, and emotional information.

[1032] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[1033] Emotion Engine: An engine that uses technology to recognize emotions from the user's voice, text, and facial expressions.

[1034] The specific operational flow when implementing this is as follows:

[1035] 1. User request input:

[1036] The user opens the application on their device and enters a request, for example, "Tell me what T-shirts you recommend!"

[1037] 2. Sending a request to the server:

[1038] The terminal sends the user's input to the server. The sent data includes the user ID.

[1039] 3. Obtaining user attribute information:

[1040] The server accesses the database based on the user ID and obtains the user's attribute information (age, gender, interests, purchasing history, etc.) For example, if the user is a woman in her 30s raising a child and is interested in yoga brands, the direction of suggestions can be narrowed down based on this information.

[1041] 4. Acquiring emotional information:

[1042] The server uses an emotion engine to obtain emotional information from the user's voice, text, and facial expressions, for example, to analyze whether the user is currently feeling stressed.

[1043] 5. Prompt generation and completion:

[1044] The server complements the prompt based on the user's request, attribute information, and emotional information. This allows for the generation of more detailed and specific prompts. For example, a prompt might be generated such as, "For a woman in her 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[1045] 6. Send to the generative AI model:

[1046] The server generates and sends the completed prompt to the generative artificial intelligence model.

[1047] 7. Proposal generation using generative artificial intelligence model:

[1048] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "relaxing T-shirt A from a yoga brand, comfortable T-shirt B from a sports brand, and stress-reducing T-shirt C from an outdoor brand."

[1049] 8. Returning suggestions and displaying them to the user:

[1050] The server receives suggestions from the generative AI model and sends them back to the user's device. The device then displays the suggestions to the user. For example, the suggestions might look like this: "Recommended T-shirts are: Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, and Stress-reducing T-shirt C from an outdoor brand."

[1051] This specific form allows users to receive highly accurate suggestions that reflect their own attribute information, interests, and real-time emotional information, further improving their satisfaction.

[1052] The above is an embodiment of the invention, and this system is capable of making highly accurate suggestions that take into account the user's real-time emotional state.

[1053] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1054] Step 1:

[1055] The user opens the application on the terminal and enters a request.

[1056] Specific actions

[1057] - A user uses a smartphone or computer to type "Tell me your recommended T-shirt!" and presses the send button.

[1058] input

[1059] - Request: "What T-shirts do you recommend?"

[1060] output

[1061] - Request data: User ID and entered request details.

[1062] Step 2:

[1063] The device sends the request to the server.

[1064] Specific actions

[1065] - The device assembles the user ID and the input request content into a packet and sends an HTTP POST request to the server.

[1066] input

[1067] - A data packet containing the user ID and the request content.

[1068] output

[1069] - The request data received by the server.

[1070] Step 3:

[1071] The server retrieves user attribute information from the database based on the user ID.

[1072] Specific actions

[1073] - The server sends an SQL query to the database to retrieve attribute information using "SELECT FROM user_attributes WHERE user_id = user ID".

[1074] input

[1075] - User ID.

[1076] output

[1077] - User demographic information: Data such as age, gender, interests, and purchasing history.

[1078] Step 4:

[1079] The server acquires the user's emotion information using an emotion engine.

[1080] Specific actions

[1081] - The server sends voice input and facial expression data acquired by the camera to the emotion engine API to acquire emotion information.

[1082] input

[1083] - User voice, text and facial expression data.

[1084] output

[1085] - Emotional information: data such as stress levels, satisfaction, and motivation.

[1086] Step 5:

[1087] The server generates and completes prompts based on the user's request, attribute information, and emotional information.

[1088] Specific actions

[1089] - The server combines the request content, user attribute information, and emotional information to generate a detailed prompt. Example: "For a user in their 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[1090] input

[1091] - User requests, attribute information, and emotional information.

[1092] output

[1093] - Completed prompt sentence.

[1094] Step 6:

[1095] The server sends the generated prompt to the generative artificial intelligence model.

[1096] Specific actions

[1097] - The server sends the prompt sentence to the generative AI model as an API request.

[1098] input

[1099] - Completed prompt sentence.

[1100] output

[1101] - Prompt data sent to generative artificial intelligence models.

[1102] Step 7:

[1103] A generative artificial intelligence model generates optimal suggestions based on prompts.

[1104] Specific actions

[1105] - A generative AI model analyzes the prompts received and generates appropriate product suggestions, e.g., "Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, Stress-reducing T-shirt C from an outdoor brand."

[1106] input

[1107] - Completed prompt sentence.

[1108] output

[1109] - Proposal data: Multiple product proposal lists.

[1110] Step 8:

[1111] The server receives suggestions from the generative artificial intelligence model and returns them to the user's device.

[1112] Specific actions

[1113] - The server receives the suggestion data and sends it to the user's device. The device displays the suggestion to the user. For example, "The recommended T-shirts are: Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, and Stress-reducing T-shirt C from an outdoor brand."

[1114] input

[1115] - Proposal data.

[1116] output

[1117] - A list of suggestions displayed on the user's device.

[1118] This concludes the detailed explanation of each processing step. This detailed flow enables users to quickly receive highly accurate suggestions that reflect their own attribute information and emotional state.

[1119] (Application example 2)

[1120] 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."

[1121] Conventional user suggestion systems generate suggestions based only on the user's attribute information, making it difficult to reflect the user's emotional state. Therefore, there is a need for a method that takes into account the user's real-time emotional information and provides more personalized and accurate suggestions. Furthermore, there is a lack of technology that can timely recommend content appropriate to the user's emotional state, especially in content distribution services such as video and movie streaming.

[1122] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a request input from a user, means for acquiring attribute information and emotional information of the user, means for generating and complementing a prompt using the acquired attribute information and emotional information, means for sending the generated prompt to a generative AI model, and means for providing the user with a suggestion returned from the generative AI model. This enables highly accurate content suggestions that take into account the user's real-time emotional state.

[1123] The "means for receiving a request input by a user" refers to a device or program having a function for receiving a request when the user inputs the request into the system via an input device.

[1124] "Means for acquiring user attribute information and emotional information" refers to a device or program for detecting, extracting, and collecting a user's basic attributes (age, gender, interests, purchasing history, etc.) and emotional state (stress level, satisfaction, etc.).

[1125] A "means for generating and complementing prompts" is a device or program that creates instructions suitable for a generative artificial intelligence model based on a user's request and acquired attribute information and emotional information, and complements the instructions with additional information to make them more specific and effective.

[1126] The "means for transmitting to the generative artificial intelligence model" is a device or program for transmitting the generated and completed prompt to the generative artificial intelligence model via a network.

[1127] "Means for providing a user with suggestions returned from a generative artificial intelligence model" refers to a device or program for receiving suggestions generated by a generative artificial intelligence model based on a prompt and displaying or notifying the user of the suggestions.

[1128] This invention is a system that utilizes a generative artificial intelligence model to make highly accurate suggestions based on user attribute information and emotion information. The system configuration for implementing this includes a user terminal, a server, a database, a generative artificial intelligence model, and an emotion engine.

[1129] Overall system configuration

[1130] The system mainly consists of the following components:

[1131] User terminal: A device that a user operates and inputs requests and emotional data (facial images, voice data). Specific examples include smartphones, tablets, and personal computers.

[1132] Server: Receives user requests, acquires and processes various data, and interacts with the generative AI model.

[1133] Database: Stores user attribute information, history information, and emotional information.

[1134] Generative AI model: An AI model that generates optimal suggestions based on prompts sent from the server.

[1135] Emotion engine: An engine that recognizes emotions from the user's voice, text, and facial expressions and provides that information.

[1136] Devices and Software

[1137] Frontend: React Native (smartphone app)

[1138] Backend: Django (Python), Flask

[1139] Database: PostgreSQL

[1140] Emotion engine: OpenCV (face recognition), Google Cloud Speech-to-Text (voice recognition)

[1141] Generative AI model: OpenAI GPT-4

[1142] Operating Procedure

[1143] 1. Input of a request: The user inputs a request into the terminal. For example, "Tell me some recommended movies."

[1144] 2. Data Acquisition: The server receives the request entered by the user and acquires the user's attribute information (age, gender, interests, etc.) from the database. At the same time, it uses the emotion engine to analyze the user's emotional information (current stress level, satisfaction level, etc.).

[1145] 3. Prompt generation and completion: The server generates and completes detailed and specific prompts based on the acquired user attribute information and emotional information.

[1146] 4. Generate suggestions: The generated prompts are sent to a generative artificial intelligence model (GPT-4) to generate optimal suggestions.

[1147] 5. Providing suggestions: Receive suggestions from the generative AI model and display them on the user's device.

[1148] Examples of prompt statements

[1149] "Please recommend some movies to a user who is a man in his 30s, currently feeling stressed, and interested in science fiction and action movies."

[1150] "Please recommend some dramas to a female user in her 20s who wants to relax and is interested in comedy dramas."

[1151] Example scenario

[1152] For example, if a male user in his 30s inputs a request such as "Please recommend some movies," the server retrieves attribute information from the database, such as "Age: 30s, Gender: Male, Interests: Sci-Fi, Action." At the same time, the emotion engine recognizes a high stress level from the user's facial image and voice. Based on this, the server generates a prompt and sends it to a generative artificial intelligence model (GPT-4). The generative artificial intelligence model suggests movies such as "Inception," "The Matrix," and "Transformers," which are sent to the user's device via the server. The user can review these suggestions and select the best movie for their condition.

[1153] In this way, the system allows users to receive highly accurate suggestions that reflect their own attribute information and emotional state, improving their satisfaction with content selection.

[1154] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1155] Step 1:

[1156] A user inputs a request to the system through a terminal. For example, a user can input "Tell me some recommended movies." This input is sent to the server by the terminal. The input data is text information and includes the user's request.

[1157] Step 2:

[1158] The server receives the user's request sent from the terminal. The received request data includes the user ID, which is used to query the database and obtain the user's attribute information. The obtained attribute information includes age, gender, interests, purchasing history, etc. This process prepares the user's basic information.

[1159] Step 3:

[1160] The server uses an emotion engine based on the user's attribute information to obtain emotional information. Specifically, it recognizes the user's current emotional state (stress level, satisfaction, etc.) by analyzing the facial image and voice data provided by the user during input. OpenCV and Google Cloud Speech-to-Text are used to obtain this emotional information. The input data are images and voice, and the output data are numerical values ​​and category information of the emotional state.

[1161] Step 4:

[1162] The server combines the acquired attribute information and emotional information to generate and complement prompts suitable for the generative AI model. These prompts include attribute information such as the user's age, gender, and interests, as well as emotional information such as stress level. The generated prompts are detailed and specific instructions. For example, they could be in the form of "Please recommend movies to a user who is a man in his 30s, currently feeling stressed, and interested in science fiction and action movies."

[1163] Step 5:

[1164] The server sends the generated and completed prompts to a generative AI model (e.g., GPT-4), which receives the sent prompts and generates optimal suggestions based on them. In this case, the input data is the prompts, and the output data is a list of suggestions.

[1165] Step 6:

[1166] The generative AI model sends back the proposed results to the server. The server receives the proposed results and sends them to the user's device. The proposed results are, for example, a list of movies such as "Inception," "The Matrix," and "Transformers."

[1167] Step 7:

[1168] The user's device displays the suggestions received from the server, and the user can review these suggestions and choose the movie that best suits their emotional state and interests. The information displayed includes specific titles and synopses, allowing the user to make a decision based on them.

[1169] At each step, the input data is processed appropriately, and the final output is the optimal proposal provided to the user, which also improves user satisfaction.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] [Fourth embodiment]

[1174] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1175] 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.

[1176] 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).

[1177] 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.

[1178] 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.

[1179] 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).

[1180] 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.

[1181] 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.

[1182] 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.

[1183] 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.

[1184] 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.

[1185] 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.

[1186] 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."

[1187] This invention is a system that utilizes a generative artificial intelligence model based on user attribute information to complement prompts and provide highly accurate information and suggestions to users. Specific embodiments of this system are described below.

[1188] Overall system configuration

[1189] The system mainly consists of the following elements:

[1190] Terminal: The device on which the user operates. This includes smartphones, tablets, personal computers, etc.

[1191] Server: Processes user requests and interacts with the generative AI model. It is also connected to a database that manages user attribute information.

[1192] Database: Stores user attribute information and history information.

[1193] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[1194] Program processing flow

[1195] The operation of this system is mainly as follows.

[1196] 1. User request input:

[1197] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[1198] 2. Sending a request to the server:

[1199] The terminal sends the user's input to the server. The sent data includes the user ID.

[1200] 3. Obtaining user attribute information:

[1201] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[1202] 4. Prompt generation and completion:

[1203] The server complements the prompt based on the user's request and attribute information. This allows for more detailed and specific prompts to be generated. For example, a prompt might be generated such as, "Please recommend a yoga brand T-shirt for around 5,000 yen for a woman in her 30s who is raising children."

[1204] 5. Send to the generative AI model:

[1205] The server sends the generated prompt to the generative artificial intelligence model.

[1206] 6. Proposal generation using generative artificial intelligence model:

[1207] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "Yogaworks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[1208] 7. Returning suggestions and displaying them to the user:

[1209] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[1210] The device displays suggestions to the user, for example, "Recommended T-shirts are: YogaWorks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[1211] Specific examples

[1212] For example, a female user in her 30s raising a child might input a request such as, "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and the clothes she usually buys cost 5,000 yen." Based on this, the server complements the prompt with, "Please recommend a yoga brand T-shirt that costs around 5,000 yen for a woman in her 30s raising a child," and sends it to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works T-shirt A, Lululemon T-shirt B, Nike T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[1213] This system allows users to receive highly accurate suggestions customized based on their attributes and interests, making product selection easier and increasing satisfaction.

[1214] The processing flow will be explained below.

[1215] Program processing flow

[1216] Step 1:

[1217] The user opens the application on the device and enters a request such as, "Tell me what T-shirts you recommend!" The device receives this request and sends it to the server as JSON format data.

[1218] Example: { "request": "What T-shirt do you recommend?", "userID": "12345"}

[1219] Step 2:

[1220] The server analyzes the request received from the terminal and accesses the database based on the user ID. The server then uses an SQL query to retrieve user attribute information from the database.

[1221] Example of information to retrieve: { "age": "30s", "gender": "female", "interests": ["yoga"], "purchaseHistory": { "average_spend": 5000}, "status": "parent"}

[1222] Step 3:

[1223] The server uses the user's attribute information acquired to complete a prompt appropriate to the request. Specifically, it generates a detailed prompt based on the user's request and attribute information.

[1224] Example of a completed prompt: { "prompt": "Please recommend a yoga brand T-shirt for a woman in her 30s who is raising children, priced around 5,000 yen."}

[1225] Step 4:

[1226] The server sends the completed prompts to the generative artificial intelligence model using an HTTP POST request.

[1227] Example API request: POST / generate-recommendation { "prompt": "Please recommend a yoga brand T-shirt for a woman in her 30s raising children, priced at around 5,000 yen."}

[1228] Step 5:

[1229] The generative AI model receives the prompt and uses its internal inference algorithm to generate the best possible suggestion. The generative AI model then compiles the suggestion results into JSON format data and sends it back to the server.

[1230] Example of inference result: { "recommendations": ["Yogaworks T-shirt A", "Lululemon T-shirt B", "Nike T-shirt C"]}

[1231] Step 6:

[1232] The server analyzes the proposal results received from the generative AI model and converts them into an appropriate format. The server then transfers this data to the device.

[1233] Step 7:

[1234] The terminal displays the recommendation results received from the server on the user interface, allowing the user to check the recommended product information on the terminal and select the next action to purchase or check the details.

[1235] Example: "Recommended t-shirts are: Yoga Works t-shirt A, Lululemon t-shirt B, Nike t-shirt C."

[1236] Through the above processing steps, highly accurate proposals can be generated using the user's attribute information based on the request input by the user, and provided to the user.

[1237] Example 1

[1238] 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."

[1239] Conventional systems have difficulty generating detailed prompts necessary to make accurate proposals in response to user requests, and have been unable to effectively utilize user attribute information. This has resulted in the inability to adequately propose products and services that meet user needs, making it difficult to increase user satisfaction.

[1240] 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.

[1241] In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information from a database based on the request, means for generating and completing detailed and specific prompts using the acquired attribute information, means for transmitting the generated prompts to a generative AI model, and means for providing the user with product or service suggestions returned from the generative AI model, thereby enabling highly accurate suggestions customized based on the user's attribute information.

[1242] "Requests input by a user" refers to information or requests provided by a user to the system via a terminal.

[1243] "User attribute information" refers to personal information and historical information about a user, including data such as age, gender, interests, and purchasing history.

[1244] "Database" refers to a system or device that has a data structure that stores user attribute information and other information and allows it to be searched and retrieved.

[1245] The "means for generating and completing prompts" refers to a means having a function for automatically creating more detailed and specific request content based on the user's attribute information and requests.

[1246] A "generative artificial intelligence model" is an artificial intelligence that has the ability to generate product and service suggestions based on prompts it receives.

[1247] "Product or service suggestions" refers to recommended products or services provided to a user by a generative artificial intelligence model based on prompts.

[1248] A "server" is a computer system that receives and processes user requests and communicates with the generative artificial intelligence model.

[1249] This invention is a system that utilizes a generative artificial intelligence model to complement prompts based on user attribute information and provides the user with highly accurate information and suggestions. Specifically, the user inputs a request from a terminal, the system obtains the user's attribute information from a database based on the request, and generates and complements detailed and specific prompts using the obtained attribute information. The system then sends the generated prompts to the generative artificial intelligence model, and provides the user with suggestions returned from the generative artificial intelligence model.

[1250] Overall system configuration

[1251] The system mainly consists of the following elements:

[1252] Terminal: The device on which the user operates. This includes smartphones, tablets, personal computers, etc.

[1253] Server: Processes user requests and interacts with the generative AI model. It is also connected to a database that manages user attribute information.

[1254] Database: Stores user attribute information and history information.

[1255] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[1256] Program processing

[1257] 1. User request input

[1258] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[1259] 2. Sending a request to the server

[1260] The terminal sends the user's input to the server. The sent data includes the user ID.

[1261] 3. Obtaining user attribute information

[1262] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[1263] 4. Prompt generation and completion

[1264] The server complements the prompt based on the user's request and attribute information. This allows for more detailed and specific prompts to be generated. For example, a prompt might be generated such as, "Please recommend a yoga brand T-shirt for around 5,000 yen for a woman in her 30s who is raising children."

[1265] 5. Sending to the generative AI model

[1266] The server sends the generated prompt to the generative artificial intelligence model.

[1267] 6. Proposal generation using a generative artificial intelligence model

[1268] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "Yogaworks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[1269] 7. Returning suggestions and displaying them to the user

[1270] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[1271] The device displays suggestions to the user, for example, "Recommended T-shirts are: YogaWorks T-shirt A, Lululemon T-shirt B, Nike T-shirt C."

[1272] Specific examples

[1273] For example, a female user in her 30s raising a child inputs a request such as "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and the clothes she usually buys cost 5,000 yen." Based on this, the server complements the prompt with "Please recommend a yoga brand T-shirt that costs around 5,000 yen for a woman in her 30s raising a child," and sends it to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works T-shirt A, Lululemon T-shirt B, Nike T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[1274] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1275] Step 1:

[1276] A user opens an application on their device and enters a request such as "Tell me what T-shirts you recommend!" This request is sent to the application on their device. The input is text data that describes the user's needs, and the output is an HTTP request that is sent to the server.

[1277] Step 2:

[1278] The terminal sends the user's input data (request and user ID) to the server. Specifically, it uses an HTTP POST request to send the request content and user ID to the server. The input is the user's request and user ID, and the output is the request to the server.

[1279] Step 3:

[1280] The server analyzes the received request and sends a query to the database based on the user ID. Specifically, it accesses the database using an SQL query in the format "SELECT FROM user_attributes WHERE user_id = ?". The input is the user ID, and the output is the user's attribute information.

[1281] Step 4:

[1282] The server generates detailed and specific prompts based on the user's attribute information (e.g., age, gender, interests, purchasing history) retrieved from the database. This prompt is created by combining the user's request and attribute information. The input is the user's request and attribute information, and the output is the generated prompt.

[1283] Step 5:

[1284] The server sends the generated prompt to the generative AI model. Specifically, it sends an HTTP POST request to the API endpoint of the generative AI model. The input is the generated prompt, and the output is a request to the generative AI model.

[1285] Step 6:

[1286] A generative AI model generates optimal product suggestions based on the prompts received. It uses an internal algorithm to analyze the prompts and generate a product list. The input is the received prompt, and the output is the generated suggestions (product list).

[1287] Step 7:

[1288] The generative AI model returns the generated proposal to the server, which then sends the received proposal to the user's device. The input is the proposal from the generative AI model, and the output is a request sent to the user's device.

[1289] Step 8:

[1290] The terminal displays the suggestions received from the server to the user. Specifically, the suggestions are displayed as text in the application's user interface. The input is the suggestion data from the server, and the output is the display on the user interface.

[1291] (Application example 1)

[1292] 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."

[1293] Conventional mail-order sites and online shopping platforms can only make general suggestions in response to user requests, making it difficult to make customized suggestions that take into account the attributes and history information of individual users. For this reason, there has been a demand for a system that can quickly and accurately recommend products and services that are suitable for each user.

[1294] 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.

[1295] In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information and history information based on the request, means for generating and completing a prompt using the acquired attribute information and history information, means for transmitting the generated prompt to a generative AI model, and means for providing suggestions returned from the generative AI model to the user's terminal, thereby enabling highly accurate product and service suggestions based on the user's attribute information and history information.

[1296] "User" refers to the general consumer or client who uses the system.

[1297] "Request" refers to a request or inquiry entered by a user.

[1298] "Attribute information" refers to information that indicates personal characteristics such as a user's age, gender, interests, purchasing history, etc.

[1299] "History information" refers to data that indicates a user's past behavior, purchase history, and the like.

[1300] A "prompt" refers to a command statement that instructs a generative artificial intelligence model to perform specific processing or generation.

[1301] A "generative artificial intelligence model" refers to an algorithm or machine learning model that generates appropriate suggestions or answers based on input prompts.

[1302] A "terminal" is a device operated by a user, such as a smartphone, tablet, or personal computer.

[1303] "Suggestion" refers to the optimal product or service recommendation for the user returned from the generative artificial intelligence model.

[1304] The present invention provides a system for making highly accurate suggestions using a generative artificial intelligence model by utilizing user attribute information and history information. A specific embodiment of this system will be described below.

[1305] System configuration

[1306] The system consists of the following main components:

[1307] 1. Device:

[1308] A device operated by a user, including a smartphone, tablet, personal computer, etc. This terminal functions as an interface for the user to input requests.

[1309] 2. Server:

[1310] This is the central system for processing user requests and linking with the generative AI model. The server is connected to a database that manages user attribute information and history information.

[1311] 3. Database:

[1312] It stores attribute information and history information such as the user's age, gender, interests, and purchasing history.

[1313] 4. Generative AI Models:

[1314] It is an algorithm or machine learning model that generates optimal suggestions based on prompts sent from the server.

[1315] Program processing flow

[1316] The processing of the program in the system is as follows.

[1317] 1. User request input:

[1318] The user inputs a request through the terminal. For example, the user inputs a request such as "Tell me what shoes you recommend!"

[1319] 2. Send a request to the server and get user attribute information:

[1320] When a request sent from a device reaches the server, the server retrieves attribute and history information from a database based on the user ID, including age, gender, interests, and purchasing history.

[1321] 3. Prompt generation and completion:

[1322] The server generates prompts based on the acquired attribute information and history information, and fills in the details. For example, a prompt may be generated that recommends "running shoes for men in their 20s that cost less than 7,000 yen."

[1323] 4. Proposal generation using generative artificial intelligence model:

[1324] The generated prompts are then sent to a generative artificial intelligence model, which then generates optimal recommendations, such as specific product recommendations like "Nike running shoes A, Adidas running shoes B, Puma running shoes C."

[1325] 5. Return suggestions and display them to the user:

[1326] The server returns the suggested products to the terminal, which displays them to the user, who can then review the details of the suggested products and make a selection.

[1327] Specific examples

[1328] For example, consider the case where a male user in his 20s types "Tell me what shoes you recommend!" into a shopping app on his smartphone. At this time, the server retrieves the attribute information "male, 20s, interested in running, purchase price range under 7,000 yen" from the database. Based on this, the server complements the prompt with "running shoes for men in their 20s under 7,000 yen" and sends it to the generative AI model. The generative AI model generates suggestions such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C," which are sent to the user's device via the server. The user can view these suggestions on their smartphone screen and select the most suitable product.

[1329] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1330] Step 1:

[1331] The user inputs a request through the device. Specifically, the user opens a shopping app on their smartphone and inputs a request such as, "Tell me what shoes you recommend!" The input (request) is received by the device and sent to the next step.

[1332] Step 2:

[1333] The terminal sends the received request to the server. The server accesses the database based on the user ID included in the received request. From the database, it obtains attribute information and history information such as the user's age, gender, interests, and purchasing history. Through this process, the user's attribute information and history information are obtained by the server.

[1334] Step 3:

[1335] Based on the user's attribute information and history information acquired by the server, the server generates and completes a detailed prompt. Specifically, the server generates a detailed prompt such as "Running shoes for men in their 20s, under 7,000 yen." This prompt is customized to match specific user attributes. The input request and acquired attribute information are processed and output as a detailed prompt.

[1336] Step 4:

[1337] The server sends the generated prompt to the generative AI model. Specifically, the generated prompt text is sent to the generative AI model (for example, an API endpoint on the cloud). An example of a prompt text is "Running shoes for men in their 20s, priced under 7,000 yen."

[1338] Step 5:

[1339] The generative AI model generates optimal suggestions based on the received prompt. The model analyzes the information contained in the prompt and makes specific product suggestions, such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C." The generated suggestions are sent back from the generative AI model to the server, where the input prompt is processed and output as appropriate suggestions.

[1340] Step 6:

[1341] The server returns the suggestions received from the generative AI model to the user's device. The server then reformats the returned suggestion data and sends it to the user's device. This results in the device displaying suggestions such as "Nike running shoes A, Adidas running shoes B, Puma running shoes C." The suggestion data is reformatted and output in a format suitable for display to the user.

[1342] This allows users to use their devices to receive highly accurate and customized product suggestions and select the most suitable products.

[1343] 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.

[1344] This invention is a system that combines a user's attribute information with an emotion engine that recognizes the user's emotion information, utilizes a generative AI model to complement prompts, and provides the user with highly accurate information and suggestions. Specific embodiments of this system are described below.

[1345] Overall system configuration

[1346] The system mainly consists of the following elements:

[1347] Terminal: A device that a user operates, including smartphones, tablets, and personal computers.

[1348] Server: Processes user requests, works with the generative AI model, and is connected to a database that manages user attribute information and emotional information.

[1349] Database: Stores user attribute information, history information, and emotional information.

[1350] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[1351] Emotion Engine: An engine that uses technology to recognize emotions from the user's voice, text, and facial expressions.

[1352] Program processing flow

[1353] The operation of this system is mainly as follows.

[1354] 1. User request input:

[1355] The user opens the application on the device and inputs a request, for example, "Tell me what T-shirts you recommend!"

[1356] 2. Sending a request to the server:

[1357] The terminal sends the user's input to the server. The sent data includes the user ID.

[1358] 3. Obtaining user attribute information:

[1359] The server accesses the database based on the user ID and obtains user attribute information, such as age, gender, interests, and purchasing history.

[1360] 4. Acquiring emotional information:

[1361] The server uses an emotion engine to obtain emotional information from the user's voice, text, and facial expressions, such as stress level, satisfaction, and motivation.

[1362] 5. Prompt generation and completion:

[1363] The server complements the prompt based on the user's request, attribute information, and emotional information. This allows for the generation of more detailed and specific prompts. For example, a prompt might be generated such as, "For a woman in her 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[1364] 6. Send to the generative AI model:

[1365] The server generates and sends the completed prompt to the generative artificial intelligence model.

[1366] 7. Proposal generation using generative artificial intelligence model:

[1367] Based on the prompts received, the generative AI model generates optimal product recommendations, such as "YogaWorks Relaxing T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[1368] 8. Returning suggestions and displaying them to the user:

[1369] The server receives suggestions from the generative artificial intelligence model and sends them back to the user's device.

[1370] The device displays suggestions to the user, such as "Recommended T-shirts: Yoga Works Relaxing T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[1371] Specific examples

[1372] For example, a female user in her 30s raising a child might input a request such as, "Tell me what T-shirts you recommend!" The server retrieves attribute information from the database, such as "female, 30s, raising a child, interested in yoga brands, and usually spends 5,000 yen on clothes." At the same time, the emotion engine analyzes the user's facial expressions and recognizes that her current stress level is high. Based on this, the server complements the prompt with, "For a female user in her 30s raising a child who is currently feeling stressed, please recommend a relaxing T-shirt from a yoga brand that costs around 5,000 yen," and sends this to the generative AI model. The generative AI model then generates suggestions such as "Yoga Works Relaxing T-shirt A, Lululemon Comfortable T-shirt B, and Nike Stress Relief T-shirt C," which are sent to the user's device via the server. The user can then review these suggestions on their device and select the T-shirt that best suits them.

[1373] This system allows users to receive highly accurate suggestions that reflect their own attribute information, interests, and real-time emotional information, further improving satisfaction.

[1374] The processing flow will be explained below.

[1375] Program processing flow

[1376] Step 1:

[1377] The user opens the application on the device and enters a request such as, "Tell me what T-shirts you recommend!" The device receives this request and sends it to the server as JSON format data.

[1378] Example of data to send: { "request": "What T-shirts do you recommend?", "userID": "12345"}

[1379] Step 2:

[1380] The server analyzes the request received from the terminal and accesses the database based on the user ID. The server then uses an SQL query to retrieve user attribute information from the database.

[1381] Example of information to be acquired: { "age": "30s", "gender": "female", "interests": ["yoga"], "purchaseHistory": { "average_spend": 5000}, "status": "parent"}

[1382] Step 3:

[1383] The server activates the emotion engine, which collects voice, text, and facial expression data from the user's device. The emotion engine analyzes this data and recognizes the user's emotional information.

[1384] Emotion information example: { "stress_level": "high", "satisfaction": "neutral", "motivation": "low"}

[1385] Step 4:

[1386] The server complements the prompts appropriate for the request based on the user's attribute information and emotional information. Specifically, it generates detailed prompts based on the user's request, attribute information, and emotional information.

[1387] Example of a completed prompt: { "prompt": "For a user in their 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."}

[1388] Step 5:

[1389] The server sends the completed prompts to the generative artificial intelligence model using an HTTP POST request.

[1390] Example API request: POST / generate-recommendation { "prompt": "Recommend a relaxing yoga brand T-shirt for around 5,000 yen to a user who is a woman in her 30s raising children and currently feeling stressed."}

[1391] Step 6:

[1392] The generative AI model receives the prompt and uses its internal inference algorithm to generate the best possible suggestion. The generative AI model then compiles the suggestion results into JSON format data and sends it back to the server.

[1393] Example of inference result: { "recommendations": ["YogaWorks Relaxing T-shirt A", "Lululemon Comfort T-shirt B", "Nike Stress Relief T-shirt C"]}

[1394] Step 7:

[1395] The server analyzes the proposal result data received from the generative AI model and converts it into an appropriate format. The server then transfers this data to the device.

[1396] Step 8:

[1397] The terminal displays the recommendation results received from the server on the user interface, allowing the user to check the recommended product information on the terminal and select the next action to purchase or check the details.

[1398] Example: "Recommended t-shirts are: Yoga Works Relax T-shirt A, Lululemon Comfort T-shirt B, Nike Stress Relief T-shirt C."

[1399] Through the above processing steps, the user can receive highly accurate suggestions that utilize attribute information and emotion information based on the input request.

[1400] Example 2

[1401] 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."

[1402] In conventional systems, prompts were generated and suggestions were made based only on individual attribute information in response to user requests, making it difficult to provide highly accurate suggestions that reflected the user's mental state and emotional information in real time.In addition, to improve user satisfaction, individual responses based on the user's situation and emotions are required, and in this respect conventional systems were insufficient.

[1403] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving a request input from a user, means for acquiring user attribute information based on the request, means for generating and complementing a prompt using the acquired attribute information and user emotional information, means for transmitting the generated prompt to a generative AI model, and means for providing the user with a proposal returned from the generative AI model. This makes it possible to make highly accurate proposals that include the user's real-time emotional state.

[1404] A "user" is an individual or organization that uses the system and is the entity that inputs requests.

[1405] A "request" is a request or question that a user inputs to the system, and is information that the system must process.

[1406] "User attribute information" refers to information about the user, such as age, gender, interests, and purchasing history, and is referenced when generating prompts.

[1407] "Emotional information" refers to the emotional state of the user as recognized by their voice, text, and facial expressions, and is acquired in real time.

[1408] A "prompt" is a basic instruction that allows a generative artificial intelligence model to generate suggestions for a user.

[1409] A "generative artificial intelligence model" is an artificial intelligence algorithm that takes a user's requests or prompts as input and generates appropriate suggestions.

[1410] A "proposal" is a specific product or service that a generative artificial intelligence model generates based on a prompt and provides to a user.

[1411] This invention is a system that combines a user's attribute information with an emotion engine that recognizes the user's emotion information, utilizes a generative artificial intelligence model to complement prompts, and provides the user with highly accurate information and suggestions. Specific embodiments of this system are described below.

[1412] The system mainly consists of the following elements:

[1413] Terminal: A device that a user operates, including smartphones, tablets, and personal computers.

[1414] Server: Processes user requests, works with the generative AI model, and is connected to a database that manages user attribute information and emotional information.

[1415] Database: Stores user attribute information, history information, and emotional information.

[1416] Generative AI model: An AI model that receives prompts from the server and generates appropriate suggestions for the user.

[1417] Emotion Engine: An engine that uses technology to recognize emotions from the user's voice, text, and facial expressions.

[1418] The specific operational flow when implementing this is as follows:

[1419] 1. User request input:

[1420] The user opens the application on their device and enters a request, for example, "Tell me what T-shirts you recommend!"

[1421] 2. Sending a request to the server:

[1422] The terminal sends the user's input to the server. The sent data includes the user ID.

[1423] 3. Obtaining user attribute information:

[1424] The server accesses the database based on the user ID and obtains the user's attribute information (age, gender, interests, purchasing history, etc.) For example, if the user is a woman in her 30s raising a child and is interested in yoga brands, the direction of suggestions can be narrowed down based on this information.

[1425] 4. Acquiring emotional information:

[1426] The server uses an emotion engine to obtain emotional information from the user's voice, text, and facial expressions, for example, to analyze whether the user is currently feeling stressed.

[1427] 5. Prompt generation and completion:

[1428] The server complements the prompt based on the user's request, attribute information, and emotional information. This allows for the generation of more detailed and specific prompts. For example, a prompt might be generated such as, "For a woman in her 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[1429] 6. Send to the generative AI model:

[1430] The server generates and sends the completed prompt to the generative artificial intelligence model.

[1431] 7. Proposal generation using generative artificial intelligence model:

[1432] Based on the prompts received, the generative AI model generates optimal product suggestions, such as "relaxing T-shirt A from a yoga brand, comfortable T-shirt B from a sports brand, and stress-reducing T-shirt C from an outdoor brand."

[1433] 8. Returning suggestions and displaying them to the user:

[1434] The server receives suggestions from the generative AI model and sends them back to the user's device. The device then displays the suggestions to the user. For example, the suggestions might look like this: "Recommended T-shirts are: Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, and Stress-reducing T-shirt C from an outdoor brand."

[1435] This specific form allows users to receive highly accurate suggestions that reflect their own attribute information, interests, and real-time emotional information, further improving their satisfaction.

[1436] The above is an embodiment of the invention, and this system is capable of making highly accurate suggestions that take into account the user's real-time emotional state.

[1437] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1438] Step 1:

[1439] The user opens the application on the terminal and enters a request.

[1440] Specific actions

[1441] - A user uses a smartphone or computer to type "Tell me your recommended T-shirt!" and presses the send button.

[1442] input

[1443] - Request: "What T-shirts do you recommend?"

[1444] output

[1445] - Request data: User ID and entered request details.

[1446] Step 2:

[1447] The device sends the request to the server.

[1448] Specific actions

[1449] - The device assembles the user ID and the input request content into a packet and sends an HTTP POST request to the server.

[1450] input

[1451] - A data packet containing the user ID and the request content.

[1452] output

[1453] - The request data received by the server.

[1454] Step 3:

[1455] The server retrieves user attribute information from the database based on the user ID.

[1456] Specific actions

[1457] - The server sends an SQL query to the database to retrieve attribute information using "SELECT FROM user_attributes WHERE user_id = user ID".

[1458] input

[1459] - User ID.

[1460] output

[1461] - User demographic information: Data such as age, gender, interests, and purchasing history.

[1462] Step 4:

[1463] The server acquires the user's emotion information using an emotion engine.

[1464] Specific actions

[1465] - The server sends voice input and facial expression data acquired by the camera to the emotion engine API to acquire emotion information.

[1466] input

[1467] - User voice, text and facial expression data.

[1468] output

[1469] - Emotional information: data such as stress levels, satisfaction, and motivation.

[1470] Step 5:

[1471] The server generates and completes prompts based on the user's request, attribute information, and emotional information.

[1472] Specific actions

[1473] - The server combines the request content, user attribute information, and emotional information to generate a detailed prompt. Example: "For a user in their 30s raising children who is currently feeling stressed, please recommend a relaxing yoga brand T-shirt for around 5,000 yen."

[1474] input

[1475] - User requests, attribute information, and emotional information.

[1476] output

[1477] - Completed prompt sentence.

[1478] Step 6:

[1479] The server sends the generated prompt to the generative artificial intelligence model.

[1480] Specific actions

[1481] - The server sends the prompt sentence to the generative AI model as an API request.

[1482] input

[1483] - Completed prompt sentence.

[1484] output

[1485] - Prompt data sent to generative artificial intelligence models.

[1486] Step 7:

[1487] A generative artificial intelligence model generates optimal suggestions based on prompts.

[1488] Specific actions

[1489] - A generative AI model analyzes the prompts received and generates appropriate product suggestions, e.g., "Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, Stress-reducing T-shirt C from an outdoor brand."

[1490] input

[1491] - Completed prompt sentence.

[1492] output

[1493] - Proposal data: Multiple product proposal lists.

[1494] Step 8:

[1495] The server receives suggestions from the generative artificial intelligence model and returns them to the user's device.

[1496] Specific actions

[1497] - The server receives the suggestion data and sends it to the user's device. The device displays the suggestion to the user. For example, "The recommended T-shirts are: Relaxing T-shirt A from a yoga brand, Comfortable T-shirt B from a sports brand, and Stress-reducing T-shirt C from an outdoor brand."

[1498] input

[1499] - Proposal data.

[1500] output

[1501] - A list of suggestions displayed on the user's device.

[1502] This concludes the detailed explanation of each processing step. This detailed flow enables users to quickly receive highly accurate suggestions that reflect their own attribute information and emotional state.

[1503] (Application example 2)

[1504] 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."

[1505] Conventional user suggestion systems generate suggestions based only on the user's attribute information, making it difficult to reflect the user's emotional state. Therefore, there is a need for a method that takes into account the user's real-time emotional information and provides more personalized and accurate suggestions. Furthermore, there is a lack of technology that can timely recommend content appropriate to the user's emotional state, especially in content distribution services such as video and movie streaming.

[1506] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a request input from a user, means for acquiring attribute information and emotional information of the user, means for generating and complementing a prompt using the acquired attribute information and emotional information, means for sending the generated prompt to a generative AI model, and means for providing the user with a suggestion returned from the generative AI model. This enables highly accurate content suggestions that take into account the user's real-time emotional state.

[1507] The "means for receiving a request input by a user" refers to a device or program having a function for receiving a request when the user inputs the request into the system via an input device.

[1508] "Means for acquiring user attribute information and emotional information" refers to a device or program for detecting, extracting, and collecting a user's basic attributes (age, gender, interests, purchasing history, etc.) and emotional state (stress level, satisfaction, etc.).

[1509] A "means for generating and complementing prompts" is a device or program that creates instructions suitable for a generative artificial intelligence model based on a user's request and acquired attribute information and emotional information, and complements the instructions with additional information to make them more specific and effective.

[1510] The "means for transmitting to the generative artificial intelligence model" is a device or program for transmitting the generated and completed prompt to the generative artificial intelligence model via a network.

[1511] "Means for providing a user with suggestions returned from a generative artificial intelligence model" refers to a device or program for receiving suggestions generated by a generative artificial intelligence model based on a prompt and displaying or notifying the user of the suggestions.

[1512] This invention is a system that utilizes a generative artificial intelligence model to make highly accurate suggestions based on user attribute information and emotion information. The system configuration for implementing this includes a user terminal, a server, a database, a generative artificial intelligence model, and an emotion engine.

[1513] Overall system configuration

[1514] The system mainly consists of the following components:

[1515] User terminal: A device that a user operates and inputs requests and emotional data (facial images, voice data). Specific examples include smartphones, tablets, and personal computers.

[1516] Server: Receives user requests, acquires and processes various data, and interacts with the generative AI model.

[1517] Database: Stores user attribute information, history information, and emotional information.

[1518] Generative AI model: An AI model that generates optimal suggestions based on prompts sent from the server.

[1519] Emotion engine: An engine that recognizes emotions from the user's voice, text, and facial expressions and provides that information.

[1520] Devices and Software

[1521] Frontend: React Native (smartphone app)

[1522] Backend: Django (Python), Flask

[1523] Database: PostgreSQL

[1524] Emotion engine: OpenCV (face recognition), Google Cloud Speech-to-Text (voice recognition)

[1525] Generative AI model: OpenAI GPT-4

[1526] Operating Procedure

[1527] 1. Input of a request: The user inputs a request into the terminal. For example, "Tell me some recommended movies."

[1528] 2. Data Acquisition: The server receives the request entered by the user and acquires the user's attribute information (age, gender, interests, etc.) from the database. At the same time, it uses the emotion engine to analyze the user's emotional information (current stress level, satisfaction level, etc.).

[1529] 3. Prompt generation and completion: The server generates and completes detailed and specific prompts based on the acquired user attribute information and emotional information.

[1530] 4. Generate suggestions: The generated prompts are sent to a generative artificial intelligence model (GPT-4) to generate optimal suggestions.

[1531] 5. Providing suggestions: Receive suggestions from the generative AI model and display them on the user's device.

[1532] Examples of prompt statements

[1533] "Please recommend some movies to a user who is a man in his 30s, currently feeling stressed, and interested in science fiction and action movies."

[1534] "Please recommend some dramas to a female user in her 20s who wants to relax and is interested in comedy dramas."

[1535] Example scenario

[1536] For example, if a male user in his 30s inputs a request such as "Please recommend some movies," the server retrieves attribute information from the database, such as "Age: 30s, Gender: Male, Interests: Sci-Fi, Action." At the same time, the emotion engine recognizes a high stress level from the user's facial image and voice. Based on this, the server generates a prompt and sends it to a generative artificial intelligence model (GPT-4). The generative artificial intelligence model suggests movies such as "Inception," "The Matrix," and "Transformers," which are sent to the user's device via the server. The user can review these suggestions and select the best movie for their condition.

[1537] In this way, the system allows users to receive highly accurate suggestions that reflect their own attribute information and emotional state, improving their satisfaction with content selection.

[1538] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1539] Step 1:

[1540] A user inputs a request to the system through a terminal. For example, a user can input "Tell me some recommended movies." This input is sent to the server by the terminal. The input data is text information and includes the user's request.

[1541] Step 2:

[1542] The server receives the user's request sent from the terminal. The received request data includes the user ID, which is used to query the database and obtain the user's attribute information. The obtained attribute information includes age, gender, interests, purchasing history, etc. This process prepares the user's basic information.

[1543] Step 3:

[1544] The server uses an emotion engine based on the user's attribute information to obtain emotional information. Specifically, it recognizes the user's current emotional state (stress level, satisfaction, etc.) by analyzing the facial image and voice data provided by the user during input. OpenCV and Google Cloud Speech-to-Text are used to obtain this emotional information. The input data are images and voice, and the output data are numerical values ​​and category information of the emotional state.

[1545] Step 4:

[1546] The server combines the acquired attribute information and emotional information to generate and complement prompts suitable for the generative AI model. These prompts include attribute information such as the user's age, gender, and interests, as well as emotional information such as stress level. The generated prompts are detailed and specific instructions. For example, they could be in the form of "Please recommend movies to a user who is a man in his 30s, currently feeling stressed, and interested in science fiction and action movies."

[1547] Step 5:

[1548] The server sends the generated and completed prompts to a generative AI model (e.g., GPT-4), which receives the sent prompts and generates optimal suggestions based on them. In this case, the input data is the prompts, and the output data is a list of suggestions.

[1549] Step 6:

[1550] The generative AI model sends back the proposed results to the server. The server receives the proposed results and sends them to the user's device. The proposed results are, for example, a list of movies such as "Inception," "The Matrix," and "Transformers."

[1551] Step 7:

[1552] The user's device displays the suggestions received from the server, and the user can review these suggestions and choose the movie that best suits their emotional state and interests. The information displayed includes specific titles and synopses, allowing the user to make a decision based on them.

[1553] At each step, the input data is processed appropriately, and the final output is the optimal proposal provided to the user, which also improves user satisfaction.

[1554] 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.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] 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).

[1561] 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.

[1562] 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."

[1563] 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.

[1564] 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).

[1565] 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.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] 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.

[1574] 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.

[1575] The following is further disclosed regarding the above embodiment.

[1576] (Claim 1)

[1577] means for receiving a request input from a user;

[1578] means for acquiring user attribute information based on the request;

[1579] means for generating a prompt using the acquired attribute information;

[1580] means for transmitting the generated prompt to a generative artificial intelligence model;

[1581] means for providing a user with suggestions returned from the generative artificial intelligence model;

[1582] A system including:

[1583] (Claim 2)

[1584] The system according to claim 1, wherein the user attribute information includes at least one of age, gender, interests, and purchasing history.

[1585] (Claim 3)

[1586] 10. The system of claim 1, wherein the generative artificial intelligence model generates product or service suggestions responsive to user requests.

[1587] "Example 1"

[1588] (Claim 1)

[1589] means for receiving a request input from a user;

[1590] means for acquiring user attribute information from a database based on the request;

[1591] A means for generating and completing detailed and specific prompts using the acquired attribute information;

[1592] means for transmitting the generated prompt to a generative artificial intelligence model;

[1593] means for providing a user with product or service suggestions returned from the generative artificial intelligence model;

[1594] A system including:

[1595] (Claim 2)

[1596] The system according to claim 1, wherein the user attribute information includes at least one of age, gender, interests, and purchasing history.

[1597] (Claim 3)

[1598] 10. The system of claim 1, wherein the generative artificial intelligence model generates product or service suggestions responsive to user requests.

[1599] "Application Example 1"

[1600] (Claim 1)

[1601] means for receiving a request input from a user;

[1602] means for acquiring user attribute information and history information based on the request;

[1603] means for generating and completing prompts using the acquired attribute information and history information;

[1604] means for transmitting the generated prompt to a generative artificial intelligence model;

[1605] means for providing the proposals returned from the generative artificial intelligence model to a user terminal;

[1606] A system including:

[1607] (Claim 2)

[1608] 2. The system according to claim 1, wherein the user's attribute information and history information includes at least one of age, gender, interests, and purchasing history.

[1609] (Claim 3)

[1610] 10. The system of claim 1, wherein the generative artificial intelligence model generates optimal product or service recommendations that address user requirements.

[1611] "Example 2: Combining Emotion Engines"

[1612] (Claim 1)

[1613] means for receiving a request input from a user;

[1614] means for acquiring user attribute information based on the request;

[1615] a means for generating and completing prompts using the acquired attribute information and user emotion information;

[1616] means for transmitting the generated prompt to a generative artificial intelligence model;

[1617] means for providing a user with suggestions returned from the generative artificial intelligence model;

[1618] A system including:

[1619] (Claim 2)

[1620] The system according to claim 1, wherein the user attribute information includes at least one of age, gender, interests, and purchasing history.

[1621] (Claim 3)

[1622] 10. The system of claim 1, wherein the generative artificial intelligence model generates product or service suggestions responsive to user requests.

[1623] "Application example 2 when combining emotion engines"

[1624] (Claim 1)

[1625] means for receiving a request input from a user;

[1626] means for acquiring attribute information and emotion information of the user based on the request;

[1627] means for generating and completing prompts using the acquired attribute information and emotion information;

[1628] means for transmitting the generated prompt to a generative artificial intelligence model;

[1629] means for providing a user with suggestions returned from the generative artificial intelligence model;

[1630] A system including:

[1631] (Claim 2)

[1632] 2. The system according to claim 1, wherein the user attribute information includes at least one of age, gender, interests, and purchasing history.

[1633] (Claim 3)

[1634] 10. The system of claim 1, wherein the generative artificial intelligence model generates content suggestions responsive to user requests. [Explanation of symbols]

[1635] 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. means for receiving a request input from a user; means for acquiring user attribute information based on the request; means for generating a prompt using the acquired attribute information; means for transmitting the generated prompt to a generative artificial intelligence model; means for providing a user with suggestions returned from the generative artificial intelligence model; A system including:

2. The system according to claim 1 , wherein the user attribute information includes at least one of age, gender, interests, and purchasing history.

3. The system of claim 1 , wherein the generative artificial intelligence model generates product or service suggestions responsive to user requests.

Images