System

Abstract

A system is provided.SOLUTION: A system, comprising: means for obtaining private information registered by a user; means for collecting usage history information from terminals of the user; means for receiving a question input by the user; means for generating an auxiliary prompt based on the private information and the usage history; means for sending the auxiliary prompt to a generation AI and obtaining an answer; and means for displaying the answer 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] Setting up prompts, which is necessary when using generative AI, is cumbersome, time-consuming, and difficult to understand. For these reasons, many users are unable to fully utilize the convenience of generative AI. The objective of this invention is to solve this problem and enable users to easily obtain optimized information. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a means for acquiring personal information registered by a user, a means for collecting usage history information from the user's device, a means for accepting questions entered by the user, a means for generating assistance prompts based on the personal information and usage history, a means for sending the assistance prompts to a generation AI and acquiring answers, and a means for displaying the answers to the user. This allows users to obtain information optimized to their preferences in one go, without the need for tedious prompt settings.

[0006] "Personal information" refers to information registered by users, such as hobbies, date of birth, and location.

[0007] "Usage history information" refers to historical data such as web access history and location information of the device used by the user.

[0008] "Question" refers to the text of a question entered by a user through the system.

[0009] "Assistive prompt" refers to input data that is automatically generated based on the user's personal information and usage history information and sent to the generation AI.

[0010] "Generative AI" refers to a system that uses artificial intelligence to generate appropriate answers to input prompts.

[0011] "Answer" refers to the information or result that the generative AI generates based on the auxiliary prompts and provides to the user.

[0012] The term "means" refers to a component in a specific embodiment for achieving the function aimed at by the present invention. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention provides a system that uses a generation AI to enable users to intuitively obtain optimized answers. This system includes a means for automatically generating an assistance prompt corresponding to a question entered by a user based on personal information and usage history information registered by the user, sending the assistance prompt to the generation AI to obtain the optimal answer, and displaying it to the user.

[0035] The entire system consists of three main components: the user's device, the server, and the generating AI.

[0036] When a user first accesses the app, the server displays a personal information registration screen, which contains fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0037] Next, after the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0038] When a user launches the app and enters a question, the device sends the question to the server. The server retrieves the user's personal information and usage history information from a database and generates a support prompt based on this information. This support prompt combines the user's personal information, usage history information, and the user's question, and is sent to the generation AI.

[0039] The AI ​​then receives the prompts and generates the best answer based on them. This answer is then sent back to the server and then to the user's device. Finally, the user can view the answer in the app.

[0040] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Has a Netflix subscription." The server generates a supplementary prompt based on this information and sends it to the generation AI in the form of "User location: Tokyo, Subscription service: Netflix, Question: What are some good movies?" Based on this supplementary prompt, the generation AI uses information about movies available on Netflix and the latest movies showing in Tokyo to generate the most appropriate answer, such as "Among the movies currently available on Netflix, we recommend the latest movie, 'Tenet,' which is showing at a local movie theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most appropriate information.

[0041] In this way, the present invention enables the user to obtain information optimized to his / her preferences in one go, without having to go through the hassle of setting up prompts.

[0042] The processing flow will be explained below.

[0043] Step 1:

[0044] Users register personal information when they first access the site

[0045] When a user accesses the app for the first time, the server displays a screen for registering personal information.

[0046] Users enter information such as hobbies, date of birth, and location, and press the send button.

[0047] The entered information is sent from the terminal to the server and stored in the server's database.

[0048] Step 2:

[0049] Collecting usage history information with the user's consent

[0050] When a user agrees to use the app, the device will collect usage history information such as web access history and location information.

[0051] The collected usage history information is sent from the terminal to the server and stored in the server's database.

[0052] Step 3:

[0053] The user enters a question

[0054] The user enters a question in the question input field of the app and presses the send button.

[0055] The question is sent from the terminal to the server.

[0056] Step 4:

[0057] The server collects personal information and usage history information

[0058] The server retrieves the personal information and usage history information registered by the user from the database.

[0059] Step 5:

[0060] The server generates a helper prompt

[0061] The server generates a prompt to answer the question entered by the user based on the acquired personal information and usage history information.

[0062] For example, create a follow-up prompt like this: "User location: Tokyo, Subscription service: Netflix, Question: What are some good movies?"

[0063] Step 6:

[0064] The server sends the generated help prompt to the generating AI.

[0065] Assistance prompts are sent to the generating AI.

[0066] Generative AI generates optimal answers based on auxiliary prompts.

[0067] Step 7:

[0068] Get answers from generative AI

[0069] The server receives the answer generated by the generation AI.

[0070] Step 8:

[0071] The server sends the answer to the user

[0072] The server sends the answer obtained from the generation AI to the terminal.

[0073] Step 9:

[0074] User checks the answer

[0075] The device displays the response received from the server on the app.

[0076] The user checks the displayed answers.

[0077] As a concrete example, if a user asks, "What are some good movies?", through the above processing steps, the answer displayed to the user will be, "Among the movies currently available on Netflix, we recommend the latest movie, 'TENET,' which is currently showing at a local movie theater in Tokyo!"

[0078] Example 1

[0079] 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."

[0080] Conventional systems have faced the problem of making it difficult for users to easily obtain information optimized for their preferences. In particular, there were few ways to efficiently utilize generative AI models to provide optimal answers to users. Furthermore, there was a lack of a way for users to effectively utilize personal information and usage history information to easily obtain information.

[0081] 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.

[0082] In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating assistance prompts based on the personal information and the usage history, means for transmitting the assistance prompts to a generative AI model that automatically generates the assistance prompts and obtaining answers, and means for transmitting and displaying the answers on the user's terminal, thereby enabling the user to obtain information optimized to their preferences in one go.

[0083] "User" refers to any individual or organization that uses this system.

[0084] "Personal Information" refers to information specific to you, such as your interests, date of birth, address, etc.

[0085] "Usage history" refers to a user's behavioral history, such as their internet access history and location information.

[0086] "Question" refers to a request for information that a user enters into the system.

[0087] "Assistive prompts" refer to inputs to a generative AI model that are generated based on a user's personal information and usage history.

[0088] "Generative AI model" refers to an artificial intelligence algorithm that receives auxiliary prompts and generates optimal answers.

[0089] "Answer" refers to the information generated by the generative AI model based on the auxiliary prompt and provided to the user.

[0090] "Terminal" refers to the electronic device (e.g., smartphone or personal computer) used by a User to access the System.

[0091] "Server" refers to a computer system that processes and stores data received from user terminals and provides necessary services.

[0092] This invention relates to a system that allows users to obtain intuitively optimized answers. The system generates assistance prompts for a generative AI model based on the user's personal information and usage history, and provides the user with the answers obtained from the generative AI model. The entire system consists of three main components: the user's terminal, a server, and a generative AI.

[0093] When a user first accesses the application, the server displays a personal information registration screen, which contains fields for entering information such as the user's interests, date of birth, address, etc. Once the user enters and submits this information, it is sent to the server and stored in a database.

[0094] Next, once the user agrees to use the app, usage history information is collected from the device. The device automatically collects internet access history and location information generated when the user browses the web or uses the app. The collected information is sent to a server and stored in a database along with personal information.

[0095] When a user launches an application and enters a question, the device sends the question to the server, which retrieves the user's personal information and usage history from a database and generates a prompt based on this information. This prompt is then sent to the generative AI model.

[0096] The generative AI model receives the prompts and generates the optimal answer based on them. The generated answer is then sent back to the user's device via the server. Finally, the user can view the answer in the application.

[0097] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is my hobby" and "My address is in City A," and their usage history includes information such as "I have a video streaming service contract." The server generates a supplementary prompt based on this information and sends it to the generative AI model in the form of, for example, "User's address: City A, Subscription service: Video streaming service, Question: What are some good movies?" Based on this supplementary prompt, the generative AI model uses information about movies offered by the video streaming service and the latest movies showing in City A to generate the optimal answer, such as "Among the movies currently available on video streaming services, we recommend the latest movie, 'Tenet,' currently showing at a theater near City A!" This answer is displayed to the user, who can immediately access the most appropriate information.

[0098] In this way, the system allows users to quickly obtain information optimized to their preferences without the need for tedious prompt settings.

[0099] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0100] Step 1:

[0101] The user accesses the app for the first time and registers their personal information.

[0102] Input: The first time the user opens the application

[0103] Processing: The server displays a personal information registration screen, which contains fields for entering information such as the user's interests, birthday, and address.

[0104] Output: The user enters personal information and clicks the "Submit" button to submit.

[0105] Step 2:

[0106] The server stores personal information

[0107] Input: Personal information submitted by the user

[0108] Processing: The server stores the received personal information in a database, using the user ID as a key.

[0109] Output: Personal information is saved in a database.

[0110] Step 3:

[0111] The user agrees to the collection of usage history information

[0112] Input: Screen after registering personal information

[0113] Processing: The server displays a consent screen for the collection of usage history information. When the user presses the "Agree" button, the consent information is sent to the server.

[0114] Output: Collection of usage history information is permitted.

[0115] Step 4:

[0116] The device collects usage history information and sends it to the server.

[0117] Input: User consent information

[0118] Processing: The device automatically collects usage history information (Internet access history, location information) generated when the user browses the web or uses apps. This information is periodically sent to the server.

[0119] Output: Usage history information is sent to the server.

[0120] Step 5:

[0121] The server stores usage history information

[0122] Input: Usage history information sent from the device

[0123] Processing: The server stores the received usage history information in a database, associating it with the user ID as a key.

[0124] Output: Usage history information is saved in a database.

[0125] Step 6:

[0126] The user types in a question and sends it to the server

[0127] Input: The question the user types into the app (e.g., "What are some good movies?")

[0128] Processing: The terminal sends the question entered by the user to the server.

[0129] Output: The question is sent to the server.

[0130] Step 7:

[0131] The server collects personal information and usage history information and generates a prompt.

[0132] Input: User questions, personal information from the database, and usage history information

[0133] Processing: The server retrieves relevant personal information and usage history information from the database. Based on this information, it generates a support prompt.

[0134] Output: Generated auxiliary prompt (e.g., "User's address: City A, Subscription service: Video streaming service, Question: What are some good movies?")

[0135] Step 8:

[0136] The server sends a help prompt to the generating AI

[0137] Input: Generated auxiliary prompt

[0138] Processing: The server sends the generated assistance prompt as an API request to the generating AI.

[0139] Output: A helper prompt is sent to the generating AI.

[0140] Step 9:

[0141] The generative AI generates the optimal answer and sends it to the server.

[0142] Input: Auxiliary prompt received by the generation AI

[0143] Processing: The generation AI analyzes the prompts and generates the optimal answer, which is then sent to the server as an API response.

[0144] Output: The generated answer is sent to the server.

[0145] Step 10:

[0146] The server sends the answer to the user's device

[0147] Input: Answer sent from the generation AI

[0148] Processing: The server sends the received response to the user's device using in-app notifications and data communication.

[0149] Output: The answer is sent to the user's device.

[0150] Step 11:

[0151] Users check their answers on the app

[0152] Input: Answer sent to the terminal

[0153] Processing: In the application, the user reviews the submitted answers and can decide what to do next based on the information presented.

[0154] Output: The user can see the most relevant information on the app.

[0155] (Application example 1)

[0156] 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."

[0157] In video streaming services, it is not easy for users to find the best content for them from a wide variety of content, and the process of selecting content can be time-consuming and laborious. Furthermore, there is a need to provide more personalized recommendations by effectively utilizing users' personal information and usage history. Given this background, it is necessary to improve the accuracy of recommendation systems in video streaming services and enhance the user experience.

[0158] 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.

[0159] In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating a help prompt based on the personal information and the usage history, means for transmitting the help prompt to a generation AI and acquiring an answer, means for displaying the answer to the user, and means for the answer to include recommended content for the viewing service. This allows the user to quickly receive content recommendations optimized based on their hobbies and usage history.

[0160] "User" refers to an individual or corporation that uses this system and provides personal information and usage history.

[0161] "Personal Information" is data provided by a user, including identifying information such as hobbies, date of birth, and location.

[0162] "Usage history" refers to data related to the use of this system, such as the user's web access history and location information.

[0163] "Question" refers to the inquiry or information a user enters through the system.

[0164] An "assistance prompt" is an input text to the generation AI that is automatically generated based on the user's personal information and usage history.

[0165] "Generative AI" is an artificial intelligence system that generates optimal answers based on user questions and supporting prompts.

[0166] "Answer" refers to the information or recommended content that the generative AI generates based on the auxiliary prompts and provides to the user.

[0167] "Viewing services" refer to online platforms and applications that distribute content such as video and music.

[0168] "Recommended content" refers to viewable content such as movies and dramas recommended by AI based on the user's personal information and usage history.

[0169] The system in this invention consists of three main components: a user, a server, and a generating AI. First, a user accesses a specific application using a device such as a smartphone or tablet. When the user uses the application for the first time, a personal information registration screen is displayed. This screen has fields for entering information such as the user's hobbies, date of birth, and location. Once the user enters and submits this information, the information is sent to the server and stored in a database.

[0170] Next, when a user starts using the application, the device automatically collects the user's usage history, including viewing history and location information. This information is also sent to the server and stored in a database, just like personal information.

[0171] When a user launches the application and enters a question, such as "What anime do you recommend?", the question is sent to the server. The server retrieves the user's personal information and usage history from the database and generates a prompt based on this information. This prompt is then sent to the generative AI model.

[0172] The generative AI model generates the best answer for the user based on the prompts, and the answer is sent back to the server and then to the user's device, where the user can finally view the answer in the application.

[0173] Hardware and Software Configuration

[0174] Hardware: smartphones, tablets, servers

[0175] Software: Python, Flask, SQLite, generative AI API

[0176] Data processing and calculation

[0177] The server first receives the question entered by the user and retrieves personal information and usage history information from the database. Based on this information, it generates a prompt and sends it to the generative AI model. The generative AI model then performs data calculations based on the prompt and generates the optimal answer. The generated answer is sent to the user's device via the server and displayed to the user.

[0178] Specific examples

[0179] Consider the case where a user enters the question "What anime do you recommend?" into an application. The user's personal information includes information such as "Watching anime is a hobby" and "Located in Tokyo," and their usage history includes information such as "A lot of action anime is viewed in their viewing history." The server generates a support prompt based on this information and sends it to the generative AI model in the form "User's location: Tokyo, Subscription service: Streaming service, Question: What anime do you recommend?" Based on this support prompt, the generative AI model generates the optimal answer, such as "Among the anime currently available on streaming services, we recommend the action anime 'Title'!" This answer is displayed to the user, allowing them to immediately obtain the most appropriate information.

[0180] Prompt Sentence Examples

[0181] User location: Tokyo, Subscription service: Streaming service, Question: What anime do you recommend?

[0182] In this way, the present invention helps the user intuitively find the most suitable content, and can significantly reduce the time and effort required for content selection.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Step 1:

[0185] When a user accesses the application using a device, the first time the user accesses it, a personal information registration screen is displayed, where the user enters information such as hobbies, date of birth, and location, and submits it.

[0186] Input: Personal information entered by the user.

[0187] Output: Personal information sent to the server and stored in a database.

[0188] Step 2:

[0189] Once a user agrees to use the application, usage history such as viewing history and location information is automatically collected from the device.

[0190] Input: User's viewing history, location information.

[0191] Output: Usage history information sent to the server and stored in a database.

[0192] Step 3:

[0193] The user launches the app and enters a question, such as "What anime do you recommend?" The question is sent from the device to the server.

[0194] Input: The question entered by the user.

[0195] Output: The question sent to the server.

[0196] Step 4:

[0197] The server retrieves the user's personal information and usage history information from a database and generates a prompt based on this information.

[0198] Input: Question, personal information, usage history information.

[0199] Data calculations: Combine personal information and usage history to generate assistive prompts.

[0200] Output: The generated auxiliary prompt.

[0201] Step 5:

[0202] The server sends the generated assistance prompts to the generative AI model to obtain the optimal answer.

[0203] Input: Auxiliary prompt.

[0204] Output: The optimal answer generated by the generative AI model.

[0205] Step 6:

[0206] The server then sends the obtained answer back to the user's terminal and displays it to the user.

[0207] Input: The answer from the generative AI model.

[0208] Output: The answer displayed on the user's terminal.

[0209] Step 7:

[0210] Users can view recommendations for the most suitable content through the application and watch content based on that information.

[0211] Input: The answer sent by the server.

[0212] Output: Recommended content that the user can see.

[0213] Through these steps, users can quickly receive optimized recommendations based on their personal information and usage history. Specific operations include collecting and registering information, generating assistance prompts, sending them to the generative AI model, and retrieving and displaying answers.

[0214] 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.

[0215] The present invention provides a system that uses a generation AI to enable users to intuitively obtain optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more personalized information provision. This system includes a means for automatically generating an assistance prompt that takes into account the question and emotion entered by the user based on personal information and usage history information registered by the user, sending it to the generation AI to obtain the optimal answer, and displaying it to the user.

[0216] The entire system consists of four main components: the user's device, the server, the generative AI, and the emotion engine.

[0217] When a user first accesses the app, the server displays a personal information registration screen, which contains fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0218] Next, once the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0219] When a user launches the app and enters a question, the device sends the question to the server, where the emotion engine simultaneously recognizes emotions from the user's facial expressions, voice, and text input. The recognized emotion information is also sent to the server.

[0220] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the user's personal information, usage history information, and emotional information with the user's question, and is sent to the generation AI.

[0221] The AI ​​then receives the prompts and generates the best answer based on them. This answer is then sent back to the server and sent to the user's device. Finally, the user can view the answer in the app.

[0222] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is my hobby" and "I live in Tokyo," and their usage history includes information such as "I have a Netflix subscription." Furthermore, suppose the emotion engine recognizes the user's emotion as "excited." The server generates a follow-up prompt based on this information and sends it to the generation AI in the form of "User's location: Tokyo, Subscription service: Netflix, Question: What are some good movies?, Emotion: Excited." Based on this follow-up prompt, the generation AI takes into account movies offered on Netflix and action movies currently showing in Tokyo, and generates the optimal answer, such as "Among the movies currently available on Netflix, I recommend the latest action movie, 'Tenet,' which is currently showing at a local theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[0223] In this way, the present invention enables a user to instantly obtain information optimized to his or her preferences, taking into account his or her emotional state, without having to go through the hassle of setting up prompts.

[0224] The processing flow will be explained below.

[0225] Step 1:

[0226] The server displays the personal information registration screen.

[0227] When a user accesses the app for the first time, the server displays a registration screen where the user can enter their personal information.

[0228] The registration screen includes fields for entering the user's hobbies, date of birth, location, etc.

[0229] Step 2:

[0230] The user enters and submits personal information

[0231] Users enter personal information such as hobbies, date of birth, and location, and press the send button.

[0232] The terminal sends the entered personal information to a server, which stores the information in a database.

[0233] Step 3:

[0234] The server collects usage history information

[0235] Once a user agrees to use the app, the server collects usage history information such as web access history and location information from the device.

[0236] The collected usage history information is stored in a database on the server.

[0237] Step 4:

[0238] User enters and submits a question

[0239] The user enters a question in the question input field of the app and presses the send button.

[0240] The terminal sends the user's question to the server.

[0241] Step 5:

[0242] The device recognizes and transmits emotional information

[0243] The emotion engine recognizes emotions from the user's facial expressions, voice, and text input.

[0244] The recognized emotion information is transmitted from the device to a server.

[0245] Step 6:

[0246] The server collects personal and historical information

[0247] The server retrieves the user's personal information and usage history information from the database.

[0248] Step 7:

[0249] The server generates a helper prompt

[0250] The server generates an auxiliary prompt in response to the user's question based on the acquired personal information, usage history information, and emotional information.

[0251] Support prompts include the user's location, the services they subscribe to, the question they have, and their current emotional state.

[0252] Step 8:

[0253] The server sends a help prompt to the generated AI.

[0254] The server sends the generated prompt to the AI ​​generator, requesting the best answer.

[0255] Step 9:

[0256] Generative AI generates optimized answers

[0257] Generative AI generates the best answer for the user based on auxiliary prompts.

[0258] Step 10:

[0259] The server gets the answer from the generation AI

[0260] The server receives the answer from the generation AI.

[0261] Step 11:

[0262] The server sends the answer to the user's device

[0263] The server sends the answer received from the generation AI to the user's device.

[0264] Step 12:

[0265] User checks the answer

[0266] The device displays the response received from the server on the app.

[0267] Users can view optimized answers through the app.

[0268] For example, if a user inputs the question "What are some good movies?" into the app and the emotion engine recognizes the user's emotion as "excited," the server will send the following auxiliary prompt to the generation AI: "User location: Tokyo, subscription service: Netflix, question: What are some good movies?, emotion: excited." Based on this auxiliary prompt, the generation AI will generate the optimal answer, such as "Among the movies currently available on Netflix, we recommend the latest action movie 'Tenet,' which is currently showing at a local movie theater in Tokyo!", allowing the user to immediately obtain this information.

[0269] Example 2

[0270] 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."

[0271] When users input questions and receive answers, it is difficult for the answers to be tailored to the user's specific situation and emotions. Furthermore, providing personalized information requires users to manually input a large amount of information, which is a burden for users. Therefore, there is a growing need for systems that can provide more intuitive and personalized information.

[0272] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for acquiring user emotion information, means for generating an assistance prompt based on the personal information, the usage history, and the emotion information, means for sending the assistance prompt to a generative AI model and acquiring an answer, and means for displaying the answer to the user. This makes it possible to provide personalized information in a form that best suits the user's specific situation and emotions.

[0273] "User" means any individual or entity that uses the System.

[0274] "Personal information" refers to data about users, such as hobbies, date of birth, and location.

[0275] "Terminal" means a device (e.g., smartphone, tablet, PC, etc.) used by a user to access the system.

[0276] "Usage history information" refers to behavioral data such as a user's web access history and location information.

[0277] A "question" is a query that a user enters into the system.

[0278] "Emotion information" is data about emotions recognized from a user's facial expressions, voice, and text input.

[0279] "Assistive prompts" are input data generated based on a user's personal information, usage history information, and emotional information, which the generative AI model uses to generate answers.

[0280] A "generative AI model" is an AI technology that receives auxiliary prompts and generates optimal answers.

[0281] An "answer" is information that a generative AI model generates based on a supplemental prompt.

[0282] A "server" is a computer that controls the entire system and collects, stores, analyzes, and transmits information to users.

[0283] The present invention provides a system that uses a generative AI model to enable users to intuitively obtain optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more personalized information provision. This system includes a means for automatically generating an assistance prompt that takes into account the user's input question and emotion based on personal information and usage history information registered by the user, sending it to the generative AI model to obtain the optimal answer, and displaying it to the user.

[0284] System Configuration

[0285] The entire system consists of four main components:

[0286] User's device

[0287] server

[0288] Generative AI Models

[0289] Emotion Engine

[0290] Hardware and software used

[0291] User's device: a device such as a smartphone, tablet, or computer

[0292] Server: The computer that collects, stores, analyzes, and transmits information to the user.

[0293] Generative AI models: AI technologies for natural language processing (e.g., GPT-3, BERT, etc.)

[0294] Emotion engine: software for analyzing a user's facial expressions, voice, and text input

[0295] When a user accesses the app for the first time, the server displays a personal information registration screen, which includes fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0296] Next, once the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0297] Questioning and emotional information processing

[0298] When a user launches the app and enters a question, the device sends the question to the server, where the emotion engine simultaneously recognizes emotions from the user's facial expressions, voice, and text input. The recognized emotion information is also sent to the server.

[0299] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the user's personal information, usage history information, and emotional information with the user's question, and is sent to the generative AI model.

[0300] Answer generation and display using generative AI models

[0301] The generative AI model receives the prompts and generates the optimal answer based on them. This answer is then sent back to the server and then to the user's device. Finally, the user can view the answer in the app.

[0302] Specific examples

[0303] Consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Currently subscribed to a video streaming service." Furthermore, let's say the emotion engine recognizes the user's emotion as "Excited." The server generates a follow-up prompt based on this information and sends it to the generative AI model in the form of "User's location: Tokyo, Subscription service: Video streaming service, Question: What are some good movies?, Emotion: Excited." Based on this follow-up prompt, the generative AI model generates the optimal answer, such as "Among the movies currently available on video streaming services, we recommend the latest action movie 'Action Movie Title', which is showing at a local movie theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[0304] In this way, the present invention enables a user to instantly obtain information optimized to his or her preferences, taking into account his or her emotional state, without having to go through the hassle of setting up prompts.

[0305] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0306] Step 1: Register your user information

[0307] Input: A user uses a device to enter personal information (such as interests, date of birth, or location).

[0308] When a user accesses the app for the first time, the server displays a personal information registration screen. When the user clicks the "Submit" button to submit the personal information they entered, the server receives the information and stores it in a database.

[0309] Output: User's personal information stored in a database.

[0310] What happens: The user fills out the form and clicks the "Submit" button. The server writes the received information to the database.

[0311] Step 2: Collecting usage history information

[0312] Input: The user consents to use the app on their device.

[0313] Once the user agrees to use the app, the device will collect the user's web access history and location information and send it to the server, which then receives this information and stores it in a database.

[0314] Output: User usage history information stored in a database.

[0315] Specific operation: The user presses the consent button. The device collects usage history and sends the information to the server. The server writes the information to the database.

[0316] Step 3: Sending questions and emotional information

[0317] Input: The user uses the device to type and submit a question, and the emotion engine analyzes the user's emotions.

[0318] The server receives the question entered by the user and also receives the emotion information obtained from the emotion engine. The emotion engine recognizes emotions from the user's facial expressions, voice, and text input, and sends the information to the server.

[0319] Output: User's question and sentiment information received by the server.

[0320] Specific operation: The user enters a question and clicks the "Send" button. The emotion engine analyzes emotions using the camera and microphone, and the server receives the question and emotion information.

[0321] Step 4: Generate supporting prompts

[0322] Input: The server obtains the user's personal information and usage history information from the database, and emotion information obtained from the emotion engine.

[0323] The server retrieves the user's personal information and usage history information from the database, integrates the emotional information received from the emotion engine, and generates a prompt to answer the user's question.

[0324] Output: The generated auxiliary prompt.

[0325] Specific operation: The server retrieves information from the database, integrates the emotional information, and generates a support prompt.

[0326] Step 5: Generating answers using a generative AI model

[0327] Input: Server-generated auxiliary prompt.

[0328] The generative AI model receives auxiliary prompts sent from the server and generates optimal answers based on them.

[0329] Output: The generated answer.

[0330] Specific operation: The generative AI model generates an answer based on the auxiliary prompt and sends it to the server.

[0331] Step 6: Display the answer to the user

[0332] Input: The answer sent by the generative AI model.

[0333] The server sends the answer obtained from the generative AI model to the user's device, where the user can view the answer on the app.

[0334] Output: The answer displayed on the user's device.

[0335] Specific operation: The server sends the answer to the user's device, and the user checks the answer on the app.

[0336] (Application example 2)

[0337] 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."

[0338] Conventional systems use generative AI to obtain answers to questions entered by users, but do not take the user's emotional state into consideration, making it difficult to provide personalized and optimal answers. Furthermore, personalization based solely on the user's personal information and usage history information was problematic in that it was not possible to recommend optimal content based on the user's current interests and emotions.

[0339] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating an assistance prompt based on the personal information and the usage history, means for sending the assistance prompt to a generation AI and acquiring an answer, means for displaying the answer to the user, means for recognizing the user's emotion, and means for generating an assistance prompt taking the emotion information into consideration. This makes it possible to generate personalized answers that reflect the user's emotional state, thereby providing more accurate information.

[0340] "Means for obtaining personal information registered by the user" refers to a function that sends personal information entered by the user, such as hobbies, date of birth, and location, to a server and stores it in a database.

[0341] "Means for collecting usage history information from the user's device" refers to a function that collects usage history information such as the user's web access history and location information, sends this to a server, and stores it in a database.

[0342] The "means for accepting questions entered by the user" is a function that sends questions entered by the user via a smartphone or other device to a server.

[0343] The "means for generating an auxiliary prompt based on the personal information and usage history" is a function that automatically generates an auxiliary prompt to be sent to the generation AI based on the user's personal information and usage history stored in a database.

[0344] The "means for sending the auxiliary prompt to the generation AI and obtaining an answer" is a function for sending an auxiliary prompt to the generation AI and obtaining the optimal answer based on the prompt.

[0345] "Means for displaying the answer to the user" refers to a function that displays the answer obtained from the generation AI on the user's device.

[0346] "Means for recognizing user emotions" refers to a function that recognizes emotions from the user's facial expressions, voice, etc., and sends that information to a database.

[0347] The "means for generating a support prompt taking into consideration the emotional information" is a function for generating a more accurate support prompt based on the emotional information of the user.

[0348] This invention is a system that uses generative AI to enable users to obtain intuitively optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it provides more personalized information. This system consists of four main components: the user's device, a server, generative AI, and the emotion engine.

[0349] 1. How to obtain personal information registered by users

[0350] When a user first accesses the app, the server displays a personal information registration screen, which includes fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0351] 2. Means of collecting usage history information from users' devices

[0352] When a user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0353] 3. A means of accepting user-entered questions

[0354] When a user launches the app and enters a question, the device sends the question to the server.

[0355] 4. How to recognize user emotions

[0356] The emotion engine recognizes the user's emotions from their facial expressions and voice, and this information is also sent to the server and stored in a database.

[0357] 5. Means for generating a support prompt based on the personal information and the usage history.

[0358] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the personal information, usage history information, emotional information, and the user's question.

[0359] 6. Means for sending the auxiliary prompt to the generation AI and obtaining a response

[0360] The AI ​​then receives the prompts and generates the optimal answer based on them, which is then sent back to the user's device via the server.

[0361] 7. Means for displaying said answers to the user

[0362] Finally, users can view the answers in the app.

[0363] Specific examples

[0364] For example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Currently subscribed to a video streaming service." Furthermore, suppose the emotion engine recognizes the user's emotion as "Excited." The server generates a supplementary prompt based on this information and sends it to the generation AI in the form of "User's location: Tokyo, Subscription service: Video streaming service, Question: What are some good movies?, Emotion: Excited." Based on this supplementary prompt, the generation AI uses information such as movies offered on the streaming service and action movies currently showing in Tokyo to generate the optimal answer, such as "Among the movies currently available on video streaming services, I recommend the latest action movie, 'Action Movie,' currently showing at a local theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[0365] Example prompt sentence:

[0366] User Location: Tokyo,

[0367] Movies seen: Avatar, Inception,

[0368] Q: What movie do you recommend?

[0369] Emotion: Excited

[0370] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0371] Step 1:

[0372] The user accesses the app and enters personal information. The user enters personal information such as hobbies, date of birth, location, etc. into the app and submits it. The server receives this information and stores it in a database.

[0373] Input: Personal information entered by the user (hobbies, date of birth, location)

[0374] Data processing: Convert the entered personal information into JSON format

[0375] Output: Personal information stored in a database

[0376] Step 2:

[0377] The user agrees to use the app, and usage history information is collected. The device collects the user's web access history and location information and sends it to the server. The server receives this information and stores it in a database.

[0378] Input: User's web access history, location information

[0379] Data processing: Convert collected usage history information into JSON format

[0380] Output: Usage history information stored in a database

[0381] Step 3:

[0382] The user launches the app and enters a question. The user enters the question in a text box within the app and submits it. The device then sends the question to the server.

[0383] Input: The question entered by the user

[0384] Data processing: Converting question text into a format that can be sent to the server

[0385] Output: The question sent to the server

[0386] Step 4:

[0387] The emotion engine recognizes emotions from the user's facial expressions and voice. Using the device's camera and microphone, the emotion engine captures the user's facial expressions and voice, analyzes them, and sends the results to the server.

[0388] Input: User's facial expression data, voice data

[0389] Data processing: Emotion analysis from facial expression and voice data

[0390] Output: Emotion information sent to the server

[0391] Step 5:

[0392] The server integrates personal information, usage history information, and emotional information to generate a support prompt.The server obtains the user's personal information, usage history information, and emotional information from the database and generates a support prompt based on these.

[0393] Input: Personal information, usage history information, and emotional information obtained from the database

[0394] Data Calculation: Generate Auxiliary Prompts

[0395] Output: Generated auxiliary prompts

[0396] Step 6:

[0397] The generation AI generates the optimal answer based on the auxiliary prompt. The server sends the auxiliary prompt to the generation AI, which then generates the optimal answer. The generated answer is then sent to the device via the server.

[0398] Input: Auxiliary prompt

[0399] Data Computation: Generating Answers with Generative AI

[0400] Output: Answer sent to the terminal via the server

[0401] Step 7:

[0402] The user checks the generated answer on the app, and the device displays the answer received from the server on the app.

[0403] Input: The answer sent by the server

[0404] Data processing: Converting received responses into a format that can be displayed on the app

[0405] Output: Answer displayed on the app

[0406] 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.

[0407] 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.

[0408] 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.

[0409] [Second embodiment]

[0410] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0411] 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.

[0412] 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).

[0413] 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.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0421] 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."

[0422] The present invention provides a system that uses a generation AI to enable users to intuitively obtain optimized answers. This system includes a means for automatically generating an assistance prompt corresponding to a question entered by a user based on personal information and usage history information registered by the user, sending the assistance prompt to the generation AI to obtain the optimal answer, and displaying it to the user.

[0423] The entire system consists of three main components: the user's device, the server, and the generating AI.

[0424] When a user first accesses the app, the server displays a personal information registration screen, which contains fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0425] Next, after the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0426] When a user launches the app and enters a question, the device sends the question to the server. The server retrieves the user's personal information and usage history information from a database and generates a support prompt based on this information. This support prompt combines the user's personal information, usage history information, and the user's question, and is sent to the generation AI.

[0427] The AI ​​then receives the prompts and generates the best answer based on them. This answer is then sent back to the server and then to the user's device. Finally, the user can view the answer in the app.

[0428] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Has a Netflix subscription." The server generates a supplementary prompt based on this information and sends it to the generation AI in the form of "User location: Tokyo, Subscription service: Netflix, Question: What are some good movies?" Based on this supplementary prompt, the generation AI uses information about movies available on Netflix and the latest movies showing in Tokyo to generate the most appropriate answer, such as "Among the movies currently available on Netflix, we recommend the latest movie, 'Tenet,' which is showing at a local movie theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most appropriate information.

[0429] In this way, the present invention enables the user to obtain information optimized to his / her preferences in one go, without having to go through the hassle of setting up prompts.

[0430] The processing flow will be explained below.

[0431] Step 1:

[0432] Users register personal information when they first access the site

[0433] When a user accesses the app for the first time, the server displays a screen for registering personal information.

[0434] Users enter information such as hobbies, date of birth, and location, and press the send button.

[0435] The entered information is sent from the terminal to the server and stored in the server's database.

[0436] Step 2:

[0437] Collecting usage history information with the user's consent

[0438] When a user agrees to use the app, the device will collect usage history information such as web access history and location information.

[0439] The collected usage history information is sent from the terminal to the server and stored in the server's database.

[0440] Step 3:

[0441] The user enters a question

[0442] The user enters a question in the question input field of the app and presses the send button.

[0443] The question is sent from the terminal to the server.

[0444] Step 4:

[0445] The server collects personal information and usage history information

[0446] The server retrieves the personal information and usage history information registered by the user from the database.

[0447] Step 5:

[0448] The server generates a helper prompt

[0449] The server generates a prompt to answer the question entered by the user based on the acquired personal information and usage history information.

[0450] For example, create a follow-up prompt like this: "User location: Tokyo, Subscription service: Netflix, Question: What are some good movies?"

[0451] Step 6:

[0452] The server sends the generated help prompt to the generating AI.

[0453] Assistance prompts are sent to the generating AI.

[0454] Generative AI generates optimal answers based on auxiliary prompts.

[0455] Step 7:

[0456] Get answers from generative AI

[0457] The server receives the answer generated by the generation AI.

[0458] Step 8:

[0459] The server sends the answer to the user

[0460] The server sends the answer obtained from the generation AI to the terminal.

[0461] Step 9:

[0462] User checks the answer

[0463] The device displays the response received from the server on the app.

[0464] The user checks the displayed answers.

[0465] As a concrete example, if a user asks, "What are some good movies?", through the above processing steps, the answer displayed to the user will be, "Among the movies currently available on Netflix, we recommend the latest movie, 'TENET,' which is currently showing at a local movie theater in Tokyo!"

[0466] Example 1

[0467] 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."

[0468] Conventional systems have faced the problem of making it difficult for users to easily obtain information optimized for their preferences. In particular, there were few ways to efficiently utilize generative AI models to provide optimal answers to users. Furthermore, there was a lack of a way for users to effectively utilize personal information and usage history information to easily obtain information.

[0469] 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.

[0470] In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating assistance prompts based on the personal information and the usage history, means for transmitting the assistance prompts to a generative AI model that automatically generates the assistance prompts and obtaining answers, and means for transmitting and displaying the answers on the user's terminal, thereby enabling the user to obtain information optimized to their preferences in one go.

[0471] "User" refers to any individual or organization that uses this system.

[0472] "Personal Information" refers to information specific to you, such as your interests, date of birth, address, etc.

[0473] "Usage history" refers to a user's behavioral history, such as their internet access history and location information.

[0474] "Question" refers to a request for information that a user enters into the system.

[0475] "Assistive prompts" refer to inputs to a generative AI model that are generated based on a user's personal information and usage history.

[0476] "Generative AI model" refers to an artificial intelligence algorithm that receives auxiliary prompts and generates optimal answers.

[0477] "Answer" refers to the information generated by the generative AI model based on the auxiliary prompt and provided to the user.

[0478] "Terminal" refers to the electronic device (e.g., smartphone or personal computer) used by a User to access the System.

[0479] "Server" refers to a computer system that processes and stores data received from user terminals and provides necessary services.

[0480] This invention relates to a system that allows users to obtain intuitively optimized answers. The system generates assistance prompts for a generative AI model based on the user's personal information and usage history, and provides the user with the answers obtained from the generative AI model. The entire system consists of three main components: the user's terminal, a server, and a generative AI.

[0481] When a user first accesses the application, the server displays a personal information registration screen, which contains fields for entering information such as the user's interests, date of birth, address, etc. Once the user enters and submits this information, it is sent to the server and stored in a database.

[0482] Next, once the user agrees to use the app, usage history information is collected from the device. The device automatically collects internet access history and location information generated when the user browses the web or uses the app. The collected information is sent to a server and stored in a database along with personal information.

[0483] When a user launches an application and enters a question, the device sends the question to the server, which retrieves the user's personal information and usage history from a database and generates a prompt based on this information. This prompt is then sent to the generative AI model.

[0484] The generative AI model receives the prompts and generates the optimal answer based on them. The generated answer is then sent back to the user's device via the server. Finally, the user can view the answer in the application.

[0485] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is my hobby" and "My address is in City A," and their usage history includes information such as "I have a video streaming service contract." The server generates a supplementary prompt based on this information and sends it to the generative AI model in the form of, for example, "User's address: City A, Subscription service: Video streaming service, Question: What are some good movies?" Based on this supplementary prompt, the generative AI model uses information about movies offered by the video streaming service and the latest movies showing in City A to generate the optimal answer, such as "Among the movies currently available on video streaming services, we recommend the latest movie, 'Tenet,' currently showing at a theater near City A!" This answer is displayed to the user, who can immediately access the most appropriate information.

[0486] In this way, the system allows users to quickly obtain information optimized to their preferences without the need for tedious prompt settings.

[0487] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0488] Step 1:

[0489] The user accesses the app for the first time and registers their personal information.

[0490] Input: The first time the user opens the application

[0491] Processing: The server displays a personal information registration screen, which contains fields for entering information such as the user's interests, birthday, and address.

[0492] Output: The user enters personal information and clicks the "Submit" button to submit.

[0493] Step 2:

[0494] The server stores personal information

[0495] Input: Personal information submitted by the user

[0496] Processing: The server stores the received personal information in a database, using the user ID as a key.

[0497] Output: Personal information is saved in a database.

[0498] Step 3:

[0499] The user agrees to the collection of usage history information

[0500] Input: Screen after registering personal information

[0501] Processing: The server displays a consent screen for the collection of usage history information. When the user presses the "Agree" button, the consent information is sent to the server.

[0502] Output: Collection of usage history information is permitted.

[0503] Step 4:

[0504] The device collects usage history information and sends it to the server.

[0505] Input: User consent information

[0506] Processing: The device automatically collects usage history information (Internet access history, location information) generated when the user browses the web or uses apps. This information is periodically sent to the server.

[0507] Output: Usage history information is sent to the server.

[0508] Step 5:

[0509] The server stores usage history information

[0510] Input: Usage history information sent from the device

[0511] Processing: The server stores the received usage history information in a database, associating it with the user ID as a key.

[0512] Output: Usage history information is saved in a database.

[0513] Step 6:

[0514] The user types in a question and sends it to the server

[0515] Input: The question the user types into the app (e.g., "What are some good movies?")

[0516] Processing: The terminal sends the question entered by the user to the server.

[0517] Output: The question is sent to the server.

[0518] Step 7:

[0519] The server collects personal information and usage history information and generates a prompt.

[0520] Input: User questions, personal information from the database, and usage history information

[0521] Processing: The server retrieves relevant personal information and usage history information from the database. Based on this information, it generates a support prompt.

[0522] Output: Generated auxiliary prompt (e.g., "User's address: City A, Subscription service: Video streaming service, Question: What are some good movies?")

[0523] Step 8:

[0524] The server sends a help prompt to the generating AI

[0525] Input: Generated auxiliary prompt

[0526] Processing: The server sends the generated assistance prompt as an API request to the generating AI.

[0527] Output: A helper prompt is sent to the generating AI.

[0528] Step 9:

[0529] The generative AI generates the optimal answer and sends it to the server.

[0530] Input: Auxiliary prompt received by the generation AI

[0531] Processing: The generation AI analyzes the prompts and generates the optimal answer, which is then sent to the server as an API response.

[0532] Output: The generated answer is sent to the server.

[0533] Step 10:

[0534] The server sends the answer to the user's device

[0535] Input: Answer sent from the generation AI

[0536] Processing: The server sends the received response to the user's device using in-app notifications and data communication.

[0537] Output: The answer is sent to the user's device.

[0538] Step 11:

[0539] Users check their answers on the app

[0540] Input: Answer sent to the terminal

[0541] Processing: In the application, the user reviews the submitted answers and can decide what to do next based on the information presented.

[0542] Output: The user can see the most relevant information on the app.

[0543] (Application example 1)

[0544] 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."

[0545] In video streaming services, it is not easy for users to find the best content for them from a wide variety of content, and the process of selecting content can be time-consuming and laborious. Furthermore, there is a need to provide more personalized recommendations by effectively utilizing users' personal information and usage history. Given this background, it is necessary to improve the accuracy of recommendation systems in video streaming services and enhance the user experience.

[0546] 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.

[0547] In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating a help prompt based on the personal information and the usage history, means for transmitting the help prompt to a generation AI and acquiring an answer, means for displaying the answer to the user, and means for the answer to include recommended content for the viewing service. This allows the user to quickly receive content recommendations optimized based on their hobbies and usage history.

[0548] "User" refers to an individual or corporation that uses this system and provides personal information and usage history.

[0549] "Personal Information" is data provided by a user, including identifying information such as hobbies, date of birth, and location.

[0550] "Usage history" refers to data related to the use of this system, such as the user's web access history and location information.

[0551] "Question" refers to the inquiry or information a user enters through the system.

[0552] An "assistance prompt" is an input text to the generation AI that is automatically generated based on the user's personal information and usage history.

[0553] "Generative AI" is an artificial intelligence system that generates optimal answers based on user questions and supporting prompts.

[0554] "Answer" refers to the information or recommended content that the generative AI generates based on the auxiliary prompts and provides to the user.

[0555] "Viewing services" refer to online platforms and applications that distribute content such as video and music.

[0556] "Recommended content" refers to viewable content such as movies and dramas recommended by AI based on the user's personal information and usage history.

[0557] The system in this invention consists of three main components: a user, a server, and a generating AI. First, a user accesses a specific application using a device such as a smartphone or tablet. When the user uses the application for the first time, a personal information registration screen is displayed. This screen has fields for entering information such as the user's hobbies, date of birth, and location. Once the user enters and submits this information, the information is sent to the server and stored in a database.

[0558] Next, when a user starts using the application, the device automatically collects the user's usage history, including viewing history and location information. This information is also sent to the server and stored in a database, just like personal information.

[0559] When a user launches the application and enters a question, such as "What anime do you recommend?", the question is sent to the server. The server retrieves the user's personal information and usage history from the database and generates a prompt based on this information. This prompt is then sent to the generative AI model.

[0560] The generative AI model generates the best answer for the user based on the prompts, and the answer is sent back to the server and then to the user's device, where the user can finally view the answer in the application.

[0561] Hardware and Software Configuration

[0562] Hardware: smartphones, tablets, servers

[0563] Software: Python, Flask, SQLite, generative AI API

[0564] Data processing and calculation

[0565] The server first receives the question entered by the user and retrieves personal information and usage history information from the database. Based on this information, it generates a prompt and sends it to the generative AI model. The generative AI model then performs data calculations based on the prompt and generates the optimal answer. The generated answer is sent to the user's device via the server and displayed to the user.

[0566] Specific examples

[0567] Consider the case where a user enters the question "What anime do you recommend?" into an application. The user's personal information includes information such as "Watching anime is a hobby" and "Located in Tokyo," and their usage history includes information such as "A lot of action anime is viewed in their viewing history." The server generates a support prompt based on this information and sends it to the generative AI model in the form "User's location: Tokyo, Subscription service: Streaming service, Question: What anime do you recommend?" Based on this support prompt, the generative AI model generates the optimal answer, such as "Among the anime currently available on streaming services, we recommend the action anime 'Title'!" This answer is displayed to the user, allowing them to immediately obtain the most appropriate information.

[0568] Prompt Sentence Examples

[0569] User location: Tokyo, Subscription service: Streaming service, Question: What anime do you recommend?

[0570] In this way, the present invention helps the user intuitively find the most suitable content, and can significantly reduce the time and effort required for content selection.

[0571] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0572] Step 1:

[0573] When a user accesses the application using a device, the first time the user accesses it, a personal information registration screen is displayed, where the user enters information such as hobbies, date of birth, and location, and submits it.

[0574] Input: Personal information entered by the user.

[0575] Output: Personal information sent to the server and stored in a database.

[0576] Step 2:

[0577] Once a user agrees to use the application, usage history such as viewing history and location information is automatically collected from the device.

[0578] Input: User's viewing history, location information.

[0579] Output: Usage history information sent to the server and stored in a database.

[0580] Step 3:

[0581] The user launches the app and enters a question, such as "What anime do you recommend?" The question is sent from the device to the server.

[0582] Input: The question entered by the user.

[0583] Output: The question sent to the server.

[0584] Step 4:

[0585] The server retrieves the user's personal information and usage history information from a database and generates a prompt based on this information.

[0586] Input: Question, personal information, usage history information.

[0587] Data calculations: Combine personal information and usage history to generate assistive prompts.

[0588] Output: The generated auxiliary prompt.

[0589] Step 5:

[0590] The server sends the generated assistance prompts to the generative AI model to obtain the optimal answer.

[0591] Input: Auxiliary prompt.

[0592] Output: The optimal answer generated by the generative AI model.

[0593] Step 6:

[0594] The server then sends the obtained answer back to the user's terminal and displays it to the user.

[0595] Input: The answer from the generative AI model.

[0596] Output: The answer displayed on the user's terminal.

[0597] Step 7:

[0598] Users can view recommendations for the most suitable content through the application and watch content based on that information.

[0599] Input: The answer sent by the server.

[0600] Output: Recommended content that the user can see.

[0601] Through these steps, users can quickly receive optimized recommendations based on their personal information and usage history. Specific operations include collecting and registering information, generating assistance prompts, sending them to the generative AI model, and retrieving and displaying answers.

[0602] 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.

[0603] The present invention provides a system that uses a generation AI to enable users to intuitively obtain optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more personalized information provision. This system includes a means for automatically generating an assistance prompt that takes into account the question and emotion entered by the user based on personal information and usage history information registered by the user, sending it to the generation AI to obtain the optimal answer, and displaying it to the user.

[0604] The entire system consists of four main components: the user's device, the server, the generative AI, and the emotion engine.

[0605] When a user first accesses the app, the server displays a personal information registration screen, which contains fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0606] Next, once the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0607] When a user launches the app and enters a question, the device sends the question to the server, where the emotion engine simultaneously recognizes emotions from the user's facial expressions, voice, and text input. The recognized emotion information is also sent to the server.

[0608] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the user's personal information, usage history information, and emotional information with the user's question, and is sent to the generation AI.

[0609] The AI ​​then receives the prompts and generates the best answer based on them. This answer is then sent back to the server and sent to the user's device. Finally, the user can view the answer in the app.

[0610] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is my hobby" and "I live in Tokyo," and their usage history includes information such as "I have a Netflix subscription." Furthermore, suppose the emotion engine recognizes the user's emotion as "excited." The server generates a follow-up prompt based on this information and sends it to the generation AI in the form of "User's location: Tokyo, Subscription service: Netflix, Question: What are some good movies?, Emotion: Excited." Based on this follow-up prompt, the generation AI takes into account movies offered on Netflix and action movies currently showing in Tokyo, and generates the optimal answer, such as "Among the movies currently available on Netflix, I recommend the latest action movie, 'Tenet,' which is currently showing at a local theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[0611] In this way, the present invention enables a user to instantly obtain information optimized to his or her preferences, taking into account his or her emotional state, without having to go through the hassle of setting up prompts.

[0612] The processing flow will be explained below.

[0613] Step 1:

[0614] The server displays the personal information registration screen.

[0615] When a user accesses the app for the first time, the server displays a registration screen where the user can enter their personal information.

[0616] The registration screen includes fields for entering the user's hobbies, date of birth, location, etc.

[0617] Step 2:

[0618] The user enters and submits personal information

[0619] Users enter personal information such as hobbies, date of birth, and location, and press the send button.

[0620] The terminal sends the entered personal information to a server, which stores the information in a database.

[0621] Step 3:

[0622] The server collects usage history information

[0623] Once a user agrees to use the app, the server collects usage history information such as web access history and location information from the device.

[0624] The collected usage history information is stored in a database on the server.

[0625] Step 4:

[0626] User enters and submits a question

[0627] The user enters a question in the question input field of the app and presses the send button.

[0628] The terminal sends the user's question to the server.

[0629] Step 5:

[0630] The device recognizes and transmits emotional information

[0631] The emotion engine recognizes emotions from the user's facial expressions, voice, and text input.

[0632] The recognized emotion information is transmitted from the device to a server.

[0633] Step 6:

[0634] The server collects personal and historical information

[0635] The server retrieves the user's personal information and usage history information from the database.

[0636] Step 7:

[0637] The server generates a helper prompt

[0638] The server generates an auxiliary prompt in response to the user's question based on the acquired personal information, usage history information, and emotional information.

[0639] Support prompts include the user's location, the services they subscribe to, the question they have, and their current emotional state.

[0640] Step 8:

[0641] The server sends a help prompt to the generated AI.

[0642] The server sends the generated prompt to the AI ​​generator, requesting the best answer.

[0643] Step 9:

[0644] Generative AI generates optimized answers

[0645] Generative AI generates the best answer for the user based on auxiliary prompts.

[0646] Step 10:

[0647] The server gets the answer from the generation AI

[0648] The server receives the answer from the generation AI.

[0649] Step 11:

[0650] The server sends the answer to the user's device

[0651] The server sends the answer received from the generation AI to the user's device.

[0652] Step 12:

[0653] User checks the answer

[0654] The device displays the response received from the server on the app.

[0655] Users can view optimized answers through the app.

[0656] For example, if a user inputs the question "What are some good movies?" into the app and the emotion engine recognizes the user's emotion as "excited," the server will send the following auxiliary prompt to the generation AI: "User location: Tokyo, subscription service: Netflix, question: What are some good movies?, emotion: excited." Based on this auxiliary prompt, the generation AI will generate the optimal answer, such as "Among the movies currently available on Netflix, we recommend the latest action movie 'Tenet,' which is currently showing at a local movie theater in Tokyo!", allowing the user to immediately obtain this information.

[0657] Example 2

[0658] 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."

[0659] When users input questions and receive answers, it is difficult for the answers to be tailored to the user's specific situation and emotions. Furthermore, providing personalized information requires users to manually input a large amount of information, which is a burden for users. Therefore, there is a growing need for systems that can provide more intuitive and personalized information.

[0660] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for acquiring user emotion information, means for generating an assistance prompt based on the personal information, the usage history, and the emotion information, means for sending the assistance prompt to a generative AI model and acquiring an answer, and means for displaying the answer to the user. This makes it possible to provide personalized information in a form that best suits the user's specific situation and emotions.

[0661] "User" means any individual or entity that uses the System.

[0662] "Personal information" refers to data about users, such as hobbies, date of birth, and location.

[0663] "Terminal" means a device (e.g., smartphone, tablet, PC, etc.) used by a user to access the system.

[0664] "Usage history information" refers to behavioral data such as a user's web access history and location information.

[0665] A "question" is a query that a user enters into the system.

[0666] "Emotion information" is data about emotions recognized from a user's facial expressions, voice, and text input.

[0667] "Assistive prompts" are input data generated based on a user's personal information, usage history information, and emotional information, which the generative AI model uses to generate answers.

[0668] A "generative AI model" is an AI technology that receives auxiliary prompts and generates optimal answers.

[0669] An "answer" is information that a generative AI model generates based on a supplemental prompt.

[0670] A "server" is a computer that controls the entire system and collects, stores, analyzes, and transmits information to users.

[0671] The present invention provides a system that uses a generative AI model to enable users to intuitively obtain optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more personalized information provision. This system includes a means for automatically generating an assistance prompt that takes into account the user's input question and emotion based on personal information and usage history information registered by the user, sending it to the generative AI model to obtain the optimal answer, and displaying it to the user.

[0672] System Configuration

[0673] The entire system consists of four main components:

[0674] User's device

[0675] server

[0676] Generative AI Models

[0677] Emotion Engine

[0678] Hardware and software used

[0679] User's device: a device such as a smartphone, tablet, or computer

[0680] Server: The computer that collects, stores, analyzes, and transmits information to the user.

[0681] Generative AI models: AI technologies for natural language processing (e.g., GPT-3, BERT, etc.)

[0682] Emotion engine: software for analyzing a user's facial expressions, voice, and text input

[0683] When a user accesses the app for the first time, the server displays a personal information registration screen, which includes fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0684] Next, once the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0685] Questioning and emotional information processing

[0686] When a user launches the app and enters a question, the device sends the question to the server, where the emotion engine simultaneously recognizes emotions from the user's facial expressions, voice, and text input. The recognized emotion information is also sent to the server.

[0687] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the user's personal information, usage history information, and emotional information with the user's question, and is sent to the generative AI model.

[0688] Answer generation and display using generative AI models

[0689] The generative AI model receives the prompts and generates the optimal answer based on them. This answer is then sent back to the server and then to the user's device. Finally, the user can view the answer in the app.

[0690] Specific examples

[0691] Consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Currently subscribed to a video streaming service." Furthermore, let's say the emotion engine recognizes the user's emotion as "Excited." The server generates a follow-up prompt based on this information and sends it to the generative AI model in the form of "User's location: Tokyo, Subscription service: Video streaming service, Question: What are some good movies?, Emotion: Excited." Based on this follow-up prompt, the generative AI model generates the optimal answer, such as "Among the movies currently available on video streaming services, we recommend the latest action movie 'Action Movie Title', which is showing at a local movie theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[0692] In this way, the present invention enables a user to instantly obtain information optimized to his or her preferences, taking into account his or her emotional state, without having to go through the hassle of setting up prompts.

[0693] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0694] Step 1: Register your user information

[0695] Input: A user uses a device to enter personal information (such as interests, date of birth, or location).

[0696] When a user accesses the app for the first time, the server displays a personal information registration screen. When the user clicks the "Submit" button to submit the personal information they entered, the server receives the information and stores it in a database.

[0697] Output: User's personal information stored in a database.

[0698] What happens: The user fills out the form and clicks the "Submit" button. The server writes the received information to the database.

[0699] Step 2: Collecting usage history information

[0700] Input: The user consents to use the app on their device.

[0701] Once the user agrees to use the app, the device will collect the user's web access history and location information and send it to the server, which then receives this information and stores it in a database.

[0702] Output: User usage history information stored in a database.

[0703] Specific operation: The user presses the consent button. The device collects usage history and sends the information to the server. The server writes the information to the database.

[0704] Step 3: Sending questions and emotional information

[0705] Input: The user uses the device to type and submit a question, and the emotion engine analyzes the user's emotions.

[0706] The server receives the question entered by the user and also receives the emotion information obtained from the emotion engine. The emotion engine recognizes emotions from the user's facial expressions, voice, and text input, and sends the information to the server.

[0707] Output: User's question and sentiment information received by the server.

[0708] Specific operation: The user enters a question and clicks the "Send" button. The emotion engine analyzes emotions using the camera and microphone, and the server receives the question and emotion information.

[0709] Step 4: Generate supporting prompts

[0710] Input: The server obtains the user's personal information and usage history information from the database, and emotion information obtained from the emotion engine.

[0711] The server retrieves the user's personal information and usage history information from the database, integrates the emotional information received from the emotion engine, and generates a prompt to answer the user's question.

[0712] Output: The generated auxiliary prompt.

[0713] Specific operation: The server retrieves information from the database, integrates the emotional information, and generates a support prompt.

[0714] Step 5: Generating answers using a generative AI model

[0715] Input: Server-generated auxiliary prompt.

[0716] The generative AI model receives auxiliary prompts sent from the server and generates optimal answers based on them.

[0717] Output: The generated answer.

[0718] Specific operation: The generative AI model generates an answer based on the auxiliary prompt and sends it to the server.

[0719] Step 6: Display the answer to the user

[0720] Input: The answer sent by the generative AI model.

[0721] The server sends the answer obtained from the generative AI model to the user's device, where the user can view the answer on the app.

[0722] Output: The answer displayed on the user's device.

[0723] Specific operation: The server sends the answer to the user's device, and the user checks the answer on the app.

[0724] (Application example 2)

[0725] 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."

[0726] Conventional systems use generative AI to obtain answers to questions entered by users, but do not take the user's emotional state into consideration, making it difficult to provide personalized and optimal answers. Furthermore, personalization based solely on the user's personal information and usage history information was problematic in that it was not possible to recommend optimal content based on the user's current interests and emotions.

[0727] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating an assistance prompt based on the personal information and the usage history, means for sending the assistance prompt to a generation AI and acquiring an answer, means for displaying the answer to the user, means for recognizing the user's emotion, and means for generating an assistance prompt taking the emotion information into consideration. This makes it possible to generate personalized answers that reflect the user's emotional state, thereby providing more accurate information.

[0728] "Means for obtaining personal information registered by the user" refers to a function that sends personal information entered by the user, such as hobbies, date of birth, and location, to a server and stores it in a database.

[0729] "Means for collecting usage history information from the user's device" refers to a function that collects usage history information such as the user's web access history and location information, sends this to a server, and stores it in a database.

[0730] The "means for accepting questions entered by the user" is a function that sends questions entered by the user via a smartphone or other device to a server.

[0731] The "means for generating an auxiliary prompt based on the personal information and usage history" is a function that automatically generates an auxiliary prompt to be sent to the generation AI based on the user's personal information and usage history stored in a database.

[0732] The "means for sending the auxiliary prompt to the generation AI and obtaining an answer" is a function for sending an auxiliary prompt to the generation AI and obtaining the optimal answer based on the prompt.

[0733] "Means for displaying the answer to the user" refers to a function that displays the answer obtained from the generation AI on the user's device.

[0734] "Means for recognizing user emotions" refers to a function that recognizes emotions from the user's facial expressions, voice, etc., and sends that information to a database.

[0735] The "means for generating a support prompt taking into consideration the emotional information" is a function for generating a more accurate support prompt based on the emotional information of the user.

[0736] This invention is a system that uses generative AI to enable users to obtain intuitively optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it provides more personalized information. This system consists of four main components: the user's device, a server, generative AI, and the emotion engine.

[0737] 1. How to obtain personal information registered by users

[0738] When a user first accesses the app, the server displays a personal information registration screen, which includes fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0739] 2. Means of collecting usage history information from users' devices

[0740] When a user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0741] 3. A means of accepting user-entered questions

[0742] When a user launches the app and enters a question, the device sends the question to the server.

[0743] 4. How to recognize user emotions

[0744] The emotion engine recognizes the user's emotions from their facial expressions and voice, and this information is also sent to the server and stored in a database.

[0745] 5. Means for generating a support prompt based on the personal information and the usage history.

[0746] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the personal information, usage history information, emotional information, and the user's question.

[0747] 6. Means for sending the auxiliary prompt to the generation AI and obtaining a response

[0748] The AI ​​then receives the prompts and generates the optimal answer based on them, which is then sent back to the user's device via the server.

[0749] 7. Means for displaying said answers to the user

[0750] Finally, users can view the answers in the app.

[0751] Specific examples

[0752] For example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Currently subscribed to a video streaming service." Furthermore, suppose the emotion engine recognizes the user's emotion as "Excited." The server generates a supplementary prompt based on this information and sends it to the generation AI in the form of "User's location: Tokyo, Subscription service: Video streaming service, Question: What are some good movies?, Emotion: Excited." Based on this supplementary prompt, the generation AI uses information such as movies offered on the streaming service and action movies currently showing in Tokyo to generate the optimal answer, such as "Among the movies currently available on video streaming services, I recommend the latest action movie, 'Action Movie,' currently showing at a local theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[0753] Example prompt sentence:

[0754] User Location: Tokyo,

[0755] Movies seen: Avatar, Inception,

[0756] Q: What movie do you recommend?

[0757] Emotion: Excited

[0758] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0759] Step 1:

[0760] The user accesses the app and enters personal information. The user enters personal information such as hobbies, date of birth, location, etc. into the app and submits it. The server receives this information and stores it in a database.

[0761] Input: Personal information entered by the user (hobbies, date of birth, location)

[0762] Data processing: Convert the entered personal information into JSON format

[0763] Output: Personal information stored in a database

[0764] Step 2:

[0765] The user agrees to use the app, and usage history information is collected. The device collects the user's web access history and location information and sends it to the server. The server receives this information and stores it in a database.

[0766] Input: User's web access history, location information

[0767] Data processing: Convert collected usage history information into JSON format

[0768] Output: Usage history information stored in a database

[0769] Step 3:

[0770] The user launches the app and enters a question. The user enters the question in a text box within the app and submits it. The device then sends the question to the server.

[0771] Input: The question entered by the user

[0772] Data processing: Converting question text into a format that can be sent to the server

[0773] Output: The question sent to the server

[0774] Step 4:

[0775] The emotion engine recognizes emotions from the user's facial expressions and voice. Using the device's camera and microphone, the emotion engine captures the user's facial expressions and voice, analyzes them, and sends the results to the server.

[0776] Input: User's facial expression data, voice data

[0777] Data processing: Emotion analysis from facial expression and voice data

[0778] Output: Emotion information sent to the server

[0779] Step 5:

[0780] The server integrates personal information, usage history information, and emotional information to generate a support prompt.The server obtains the user's personal information, usage history information, and emotional information from the database and generates a support prompt based on these.

[0781] Input: Personal information, usage history information, and emotional information obtained from the database

[0782] Data Calculation: Generate Auxiliary Prompts

[0783] Output: Generated auxiliary prompts

[0784] Step 6:

[0785] The generation AI generates the optimal answer based on the auxiliary prompt. The server sends the auxiliary prompt to the generation AI, which then generates the optimal answer. The generated answer is then sent to the device via the server.

[0786] Input: Auxiliary prompt

[0787] Data Computation: Generating Answers with Generative AI

[0788] Output: Answer sent to the terminal via the server

[0789] Step 7:

[0790] The user checks the generated answer on the app, and the device displays the answer received from the server on the app.

[0791] Input: The answer sent by the server

[0792] Data processing: Converting received responses into a format that can be displayed on the app

[0793] Output: Answer displayed on the app

[0794] 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.

[0795] 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.

[0796] 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.

[0797] [Third embodiment]

[0798] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0799] 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.

[0800] 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).

[0801] 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.

[0802] 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.

[0803] 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).

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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."

[0810] The present invention provides a system that uses a generation AI to enable users to intuitively obtain optimized answers. This system includes a means for automatically generating an assistance prompt corresponding to a question entered by a user based on personal information and usage history information registered by the user, sending the assistance prompt to the generation AI to obtain the optimal answer, and displaying it to the user.

[0811] The entire system consists of three main components: the user's device, the server, and the generating AI.

[0812] When a user first accesses the app, the server displays a personal information registration screen, which contains fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0813] Next, after the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0814] When a user launches the app and enters a question, the device sends the question to the server. The server retrieves the user's personal information and usage history information from a database and generates a support prompt based on this information. This support prompt combines the user's personal information, usage history information, and the user's question, and is sent to the generation AI.

[0815] The AI ​​then receives the prompts and generates the best answer based on them. This answer is then sent back to the server and then to the user's device. Finally, the user can view the answer in the app.

[0816] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Has a Netflix subscription." The server generates a supplementary prompt based on this information and sends it to the generation AI in the form of "User location: Tokyo, Subscription service: Netflix, Question: What are some good movies?" Based on this supplementary prompt, the generation AI uses information about movies available on Netflix and the latest movies showing in Tokyo to generate the most appropriate answer, such as "Among the movies currently available on Netflix, we recommend the latest movie, 'Tenet,' which is showing at a local movie theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most appropriate information.

[0817] In this way, the present invention enables the user to obtain information optimized to his / her preferences in one go, without having to go through the hassle of setting up prompts.

[0818] The processing flow will be explained below.

[0819] Step 1:

[0820] Users register personal information when they first access the site

[0821] When a user accesses the app for the first time, the server displays a screen for registering personal information.

[0822] Users enter information such as hobbies, date of birth, and location, and press the send button.

[0823] The entered information is sent from the terminal to the server and stored in the server's database.

[0824] Step 2:

[0825] Collecting usage history information with the user's consent

[0826] When a user agrees to use the app, the device will collect usage history information such as web access history and location information.

[0827] The collected usage history information is sent from the terminal to the server and stored in the server's database.

[0828] Step 3:

[0829] The user enters a question

[0830] The user enters a question in the question input field of the app and presses the send button.

[0831] The question is sent from the terminal to the server.

[0832] Step 4:

[0833] The server collects personal information and usage history information

[0834] The server retrieves the personal information and usage history information registered by the user from the database.

[0835] Step 5:

[0836] The server generates a helper prompt

[0837] The server generates a prompt to answer the question entered by the user based on the acquired personal information and usage history information.

[0838] For example, create a follow-up prompt like this: "User location: Tokyo, Subscription service: Netflix, Question: What are some good movies?"

[0839] Step 6:

[0840] The server sends the generated help prompt to the generating AI.

[0841] Assistance prompts are sent to the generating AI.

[0842] Generative AI generates optimal answers based on auxiliary prompts.

[0843] Step 7:

[0844] Get answers from generative AI

[0845] The server receives the answer generated by the generation AI.

[0846] Step 8:

[0847] The server sends the answer to the user

[0848] The server sends the answer obtained from the generation AI to the terminal.

[0849] Step 9:

[0850] User checks the answer

[0851] The device displays the response received from the server on the app.

[0852] The user checks the displayed answers.

[0853] As a concrete example, if a user asks, "What are some good movies?", through the above processing steps, the answer displayed to the user will be, "Among the movies currently available on Netflix, we recommend the latest movie, 'TENET,' which is currently showing at a local movie theater in Tokyo!"

[0854] Example 1

[0855] 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."

[0856] Conventional systems have faced the problem of making it difficult for users to easily obtain information optimized for their preferences. In particular, there were few ways to efficiently utilize generative AI models to provide optimal answers to users. Furthermore, there was a lack of a way for users to effectively utilize personal information and usage history information to easily obtain information.

[0857] 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.

[0858] In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating assistance prompts based on the personal information and the usage history, means for transmitting the assistance prompts to a generative AI model that automatically generates the assistance prompts and obtaining answers, and means for transmitting and displaying the answers on the user's terminal, thereby enabling the user to obtain information optimized to their preferences in one go.

[0859] "User" refers to any individual or organization that uses this system.

[0860] "Personal Information" refers to information specific to you, such as your interests, date of birth, address, etc.

[0861] "Usage history" refers to a user's behavioral history, such as their internet access history and location information.

[0862] "Question" refers to a request for information that a user enters into the system.

[0863] "Assistive prompts" refer to inputs to a generative AI model that are generated based on a user's personal information and usage history.

[0864] "Generative AI model" refers to an artificial intelligence algorithm that receives auxiliary prompts and generates optimal answers.

[0865] "Answer" refers to the information generated by the generative AI model based on the auxiliary prompt and provided to the user.

[0866] "Terminal" refers to the electronic device (e.g., smartphone or personal computer) used by a User to access the System.

[0867] "Server" refers to a computer system that processes and stores data received from user terminals and provides necessary services.

[0868] This invention relates to a system that allows users to obtain intuitively optimized answers. The system generates assistance prompts for a generative AI model based on the user's personal information and usage history, and provides the user with the answers obtained from the generative AI model. The entire system consists of three main components: the user's terminal, a server, and a generative AI.

[0869] When a user first accesses the application, the server displays a personal information registration screen, which contains fields for entering information such as the user's interests, date of birth, address, etc. Once the user enters and submits this information, it is sent to the server and stored in a database.

[0870] Next, once the user agrees to use the app, usage history information is collected from the device. The device automatically collects internet access history and location information generated when the user browses the web or uses the app. The collected information is sent to a server and stored in a database along with personal information.

[0871] When a user launches an application and enters a question, the device sends the question to the server, which retrieves the user's personal information and usage history from a database and generates a prompt based on this information. This prompt is then sent to the generative AI model.

[0872] The generative AI model receives the prompts and generates the optimal answer based on them. The generated answer is then sent back to the user's device via the server. Finally, the user can view the answer in the application.

[0873] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is my hobby" and "My address is in City A," and their usage history includes information such as "I have a video streaming service contract." The server generates a supplementary prompt based on this information and sends it to the generative AI model in the form of, for example, "User's address: City A, Subscription service: Video streaming service, Question: What are some good movies?" Based on this supplementary prompt, the generative AI model uses information about movies offered by the video streaming service and the latest movies showing in City A to generate the optimal answer, such as "Among the movies currently available on video streaming services, we recommend the latest movie, 'Tenet,' currently showing at a theater near City A!" This answer is displayed to the user, who can immediately access the most appropriate information.

[0874] In this way, the system allows users to quickly obtain information optimized to their preferences without the need for tedious prompt settings.

[0875] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0876] Step 1:

[0877] The user accesses the app for the first time and registers their personal information.

[0878] Input: The first time the user opens the application

[0879] Processing: The server displays a personal information registration screen, which contains fields for entering information such as the user's interests, birthday, and address.

[0880] Output: The user enters personal information and clicks the "Submit" button to submit.

[0881] Step 2:

[0882] The server stores personal information

[0883] Input: Personal information submitted by the user

[0884] Processing: The server stores the received personal information in a database, using the user ID as a key.

[0885] Output: Personal information is saved in a database.

[0886] Step 3:

[0887] The user agrees to the collection of usage history information

[0888] Input: Screen after registering personal information

[0889] Processing: The server displays a consent screen for the collection of usage history information. When the user presses the "Agree" button, the consent information is sent to the server.

[0890] Output: Collection of usage history information is permitted.

[0891] Step 4:

[0892] The device collects usage history information and sends it to the server.

[0893] Input: User consent information

[0894] Processing: The device automatically collects usage history information (Internet access history, location information) generated when the user browses the web or uses apps. This information is periodically sent to the server.

[0895] Output: Usage history information is sent to the server.

[0896] Step 5:

[0897] The server stores usage history information

[0898] Input: Usage history information sent from the device

[0899] Processing: The server stores the received usage history information in a database, associating it with the user ID as a key.

[0900] Output: Usage history information is saved in a database.

[0901] Step 6:

[0902] The user types in a question and sends it to the server

[0903] Input: The question the user types into the app (e.g., "What are some good movies?")

[0904] Processing: The terminal sends the question entered by the user to the server.

[0905] Output: The question is sent to the server.

[0906] Step 7:

[0907] The server collects personal information and usage history information and generates a prompt.

[0908] Input: User questions, personal information from the database, and usage history information

[0909] Processing: The server retrieves relevant personal information and usage history information from the database. Based on this information, it generates a support prompt.

[0910] Output: Generated auxiliary prompt (e.g., "User's address: City A, Subscription service: Video streaming service, Question: What are some good movies?")

[0911] Step 8:

[0912] The server sends a help prompt to the generating AI

[0913] Input: Generated auxiliary prompt

[0914] Processing: The server sends the generated assistance prompt as an API request to the generating AI.

[0915] Output: A helper prompt is sent to the generating AI.

[0916] Step 9:

[0917] The generative AI generates the optimal answer and sends it to the server.

[0918] Input: Auxiliary prompt received by the generation AI

[0919] Processing: The generation AI analyzes the prompts and generates the optimal answer, which is then sent to the server as an API response.

[0920] Output: The generated answer is sent to the server.

[0921] Step 10:

[0922] The server sends the answer to the user's device

[0923] Input: Answer sent from the generation AI

[0924] Processing: The server sends the received response to the user's device using in-app notifications and data communication.

[0925] Output: The answer is sent to the user's device.

[0926] Step 11:

[0927] Users check their answers on the app

[0928] Input: Answer sent to the terminal

[0929] Processing: In the application, the user reviews the submitted answers and can decide what to do next based on the information presented.

[0930] Output: The user can see the most relevant information on the app.

[0931] (Application example 1)

[0932] 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."

[0933] In video streaming services, it is not easy for users to find the best content for them from a wide variety of content, and the process of selecting content can be time-consuming and laborious. Furthermore, there is a need to provide more personalized recommendations by effectively utilizing users' personal information and usage history. Given this background, it is necessary to improve the accuracy of recommendation systems in video streaming services and enhance the user experience.

[0934] 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.

[0935] In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating a help prompt based on the personal information and the usage history, means for transmitting the help prompt to a generation AI and acquiring an answer, means for displaying the answer to the user, and means for the answer to include recommended content for the viewing service. This allows the user to quickly receive content recommendations optimized based on their hobbies and usage history.

[0936] "User" refers to an individual or corporation that uses this system and provides personal information and usage history.

[0937] "Personal Information" is data provided by a user, including identifying information such as hobbies, date of birth, and location.

[0938] "Usage history" refers to data related to the use of this system, such as the user's web access history and location information.

[0939] "Question" refers to the inquiry or information a user enters through the system.

[0940] An "assistance prompt" is an input text to the generation AI that is automatically generated based on the user's personal information and usage history.

[0941] "Generative AI" is an artificial intelligence system that generates optimal answers based on user questions and supporting prompts.

[0942] "Answer" refers to the information or recommended content that the generative AI generates based on the auxiliary prompts and provides to the user.

[0943] "Viewing services" refer to online platforms and applications that distribute content such as video and music.

[0944] "Recommended content" refers to viewable content such as movies and dramas recommended by AI based on the user's personal information and usage history.

[0945] The system in this invention consists of three main components: a user, a server, and a generating AI. First, a user accesses a specific application using a device such as a smartphone or tablet. When the user uses the application for the first time, a personal information registration screen is displayed. This screen has fields for entering information such as the user's hobbies, date of birth, and location. Once the user enters and submits this information, the information is sent to the server and stored in a database.

[0946] Next, when a user starts using the application, the device automatically collects the user's usage history, including viewing history and location information. This information is also sent to the server and stored in a database, just like personal information.

[0947] When a user launches the application and enters a question, such as "What anime do you recommend?", the question is sent to the server. The server retrieves the user's personal information and usage history from the database and generates a prompt based on this information. This prompt is then sent to the generative AI model.

[0948] The generative AI model generates the best answer for the user based on the prompts, and the answer is sent back to the server and then to the user's device, where the user can finally view the answer in the application.

[0949] Hardware and Software Configuration

[0950] Hardware: smartphones, tablets, servers

[0951] Software: Python, Flask, SQLite, generative AI API

[0952] Data processing and calculation

[0953] The server first receives the question entered by the user and retrieves personal information and usage history information from the database. Based on this information, it generates a prompt and sends it to the generative AI model. The generative AI model then performs data calculations based on the prompt and generates the optimal answer. The generated answer is sent to the user's device via the server and displayed to the user.

[0954] Specific examples

[0955] Consider the case where a user enters the question "What anime do you recommend?" into an application. The user's personal information includes information such as "Watching anime is a hobby" and "Located in Tokyo," and their usage history includes information such as "A lot of action anime is viewed in their viewing history." The server generates a support prompt based on this information and sends it to the generative AI model in the form "User's location: Tokyo, Subscription service: Streaming service, Question: What anime do you recommend?" Based on this support prompt, the generative AI model generates the optimal answer, such as "Among the anime currently available on streaming services, we recommend the action anime 'Title'!" This answer is displayed to the user, allowing them to immediately obtain the most appropriate information.

[0956] Prompt Sentence Examples

[0957] User location: Tokyo, Subscription service: Streaming service, Question: What anime do you recommend?

[0958] In this way, the present invention helps the user intuitively find the most suitable content, and can significantly reduce the time and effort required for content selection.

[0959] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0960] Step 1:

[0961] When a user accesses the application using a device, the first time the user accesses it, a personal information registration screen is displayed, where the user enters information such as hobbies, date of birth, and location, and submits it.

[0962] Input: Personal information entered by the user.

[0963] Output: Personal information sent to the server and stored in a database.

[0964] Step 2:

[0965] Once a user agrees to use the application, usage history such as viewing history and location information is automatically collected from the device.

[0966] Input: User's viewing history, location information.

[0967] Output: Usage history information sent to the server and stored in a database.

[0968] Step 3:

[0969] The user launches the app and enters a question, such as "What anime do you recommend?" The question is sent from the device to the server.

[0970] Input: The question entered by the user.

[0971] Output: The question sent to the server.

[0972] Step 4:

[0973] The server retrieves the user's personal information and usage history information from a database and generates a prompt based on this information.

[0974] Input: Question, personal information, usage history information.

[0975] Data calculations: Combine personal information and usage history to generate assistive prompts.

[0976] Output: The generated auxiliary prompt.

[0977] Step 5:

[0978] The server sends the generated assistance prompts to the generative AI model to obtain the optimal answer.

[0979] Input: Auxiliary prompt.

[0980] Output: The optimal answer generated by the generative AI model.

[0981] Step 6:

[0982] The server then sends the obtained answer back to the user's terminal and displays it to the user.

[0983] Input: The answer from the generative AI model.

[0984] Output: The answer displayed on the user's terminal.

[0985] Step 7:

[0986] Users can view recommendations for the most suitable content through the application and watch content based on that information.

[0987] Input: The answer sent by the server.

[0988] Output: Recommended content that the user can see.

[0989] Through these steps, users can quickly receive optimized recommendations based on their personal information and usage history. Specific operations include collecting and registering information, generating assistance prompts, sending them to the generative AI model, and retrieving and displaying answers.

[0990] 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.

[0991] The present invention provides a system that uses a generation AI to enable users to intuitively obtain optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more personalized information provision. This system includes a means for automatically generating an assistance prompt that takes into account the question and emotion entered by the user based on personal information and usage history information registered by the user, sending it to the generation AI to obtain the optimal answer, and displaying it to the user.

[0992] The entire system consists of four main components: the user's device, the server, the generative AI, and the emotion engine.

[0993] When a user first accesses the app, the server displays a personal information registration screen, which contains fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[0994] Next, once the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[0995] When a user launches the app and enters a question, the device sends the question to the server, where the emotion engine simultaneously recognizes emotions from the user's facial expressions, voice, and text input. The recognized emotion information is also sent to the server.

[0996] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the user's personal information, usage history information, and emotional information with the user's question, and is sent to the generation AI.

[0997] The AI ​​then receives the prompts and generates the best answer based on them. This answer is then sent back to the server and sent to the user's device. Finally, the user can view the answer in the app.

[0998] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is my hobby" and "I live in Tokyo," and their usage history includes information such as "I have a Netflix subscription." Furthermore, suppose the emotion engine recognizes the user's emotion as "excited." The server generates a follow-up prompt based on this information and sends it to the generation AI in the form of "User's location: Tokyo, Subscription service: Netflix, Question: What are some good movies?, Emotion: Excited." Based on this follow-up prompt, the generation AI takes into account movies offered on Netflix and action movies currently showing in Tokyo, and generates the optimal answer, such as "Among the movies currently available on Netflix, I recommend the latest action movie, 'Tenet,' which is currently showing at a local theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[0999] In this way, the present invention enables a user to instantly obtain information optimized to his or her preferences, taking into account his or her emotional state, without having to go through the hassle of setting up prompts.

[1000] The processing flow will be explained below.

[1001] Step 1:

[1002] The server displays the personal information registration screen.

[1003] When a user accesses the app for the first time, the server displays a registration screen where the user can enter their personal information.

[1004] The registration screen includes fields for entering the user's hobbies, date of birth, location, etc.

[1005] Step 2:

[1006] The user enters and submits personal information

[1007] Users enter personal information such as hobbies, date of birth, and location, and press the send button.

[1008] The terminal sends the entered personal information to a server, which stores the information in a database.

[1009] Step 3:

[1010] The server collects usage history information

[1011] Once a user agrees to use the app, the server collects usage history information such as web access history and location information from the device.

[1012] The collected usage history information is stored in a database on the server.

[1013] Step 4:

[1014] User enters and submits a question

[1015] The user enters a question in the question input field of the app and presses the send button.

[1016] The terminal sends the user's question to the server.

[1017] Step 5:

[1018] The device recognizes and transmits emotional information

[1019] The emotion engine recognizes emotions from the user's facial expressions, voice, and text input.

[1020] The recognized emotion information is transmitted from the device to a server.

[1021] Step 6:

[1022] The server collects personal and historical information

[1023] The server retrieves the user's personal information and usage history information from the database.

[1024] Step 7:

[1025] The server generates a helper prompt

[1026] The server generates an auxiliary prompt in response to the user's question based on the acquired personal information, usage history information, and emotional information.

[1027] Support prompts include the user's location, the services they subscribe to, the question they have, and their current emotional state.

[1028] Step 8:

[1029] The server sends a help prompt to the generated AI.

[1030] The server sends the generated prompt to the AI ​​generator, requesting the best answer.

[1031] Step 9:

[1032] Generative AI generates optimized answers

[1033] Generative AI generates the best answer for the user based on auxiliary prompts.

[1034] Step 10:

[1035] The server gets the answer from the generation AI

[1036] The server receives the answer from the generation AI.

[1037] Step 11:

[1038] The server sends the answer to the user's device

[1039] The server sends the answer received from the generation AI to the user's device.

[1040] Step 12:

[1041] User checks the answer

[1042] The device displays the response received from the server on the app.

[1043] Users can view optimized answers through the app.

[1044] For example, if a user inputs the question "What are some good movies?" into the app and the emotion engine recognizes the user's emotion as "excited," the server will send the following auxiliary prompt to the generation AI: "User location: Tokyo, subscription service: Netflix, question: What are some good movies?, emotion: excited." Based on this auxiliary prompt, the generation AI will generate the optimal answer, such as "Among the movies currently available on Netflix, we recommend the latest action movie 'Tenet,' which is currently showing at a local movie theater in Tokyo!", allowing the user to immediately obtain this information.

[1045] Example 2

[1046] 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."

[1047] When users input questions and receive answers, it is difficult for the answers to be tailored to the user's specific situation and emotions. Furthermore, providing personalized information requires users to manually input a large amount of information, which is a burden for users. Therefore, there is a growing need for systems that can provide more intuitive and personalized information.

[1048] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for acquiring user emotion information, means for generating an assistance prompt based on the personal information, the usage history, and the emotion information, means for sending the assistance prompt to a generative AI model and acquiring an answer, and means for displaying the answer to the user. This makes it possible to provide personalized information in a form that best suits the user's specific situation and emotions.

[1049] "User" means any individual or entity that uses the System.

[1050] "Personal information" refers to data about users, such as hobbies, date of birth, and location.

[1051] "Terminal" means a device (e.g., smartphone, tablet, PC, etc.) used by a user to access the system.

[1052] "Usage history information" refers to behavioral data such as a user's web access history and location information.

[1053] A "question" is a query that a user enters into the system.

[1054] "Emotion information" is data about emotions recognized from a user's facial expressions, voice, and text input.

[1055] "Assistive prompts" are input data generated based on a user's personal information, usage history information, and emotional information, which the generative AI model uses to generate answers.

[1056] A "generative AI model" is an AI technology that receives auxiliary prompts and generates optimal answers.

[1057] An "answer" is information that a generative AI model generates based on a supplemental prompt.

[1058] A "server" is a computer that controls the entire system and collects, stores, analyzes, and transmits information to users.

[1059] The present invention provides a system that uses a generative AI model to enable users to intuitively obtain optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more personalized information provision. This system includes a means for automatically generating an assistance prompt that takes into account the user's input question and emotion based on personal information and usage history information registered by the user, sending it to the generative AI model to obtain the optimal answer, and displaying it to the user.

[1060] System Configuration

[1061] The entire system consists of four main components:

[1062] User's device

[1063] server

[1064] Generative AI Models

[1065] Emotion Engine

[1066] Hardware and software used

[1067] User's device: a device such as a smartphone, tablet, or computer

[1068] Server: The computer that collects, stores, analyzes, and transmits information to the user.

[1069] Generative AI models: AI technologies for natural language processing (e.g., GPT-3, BERT, etc.)

[1070] Emotion engine: software for analyzing a user's facial expressions, voice, and text input

[1071] When a user accesses the app for the first time, the server displays a personal information registration screen, which includes fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[1072] Next, once the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[1073] Questioning and emotional information processing

[1074] When a user launches the app and enters a question, the device sends the question to the server, where the emotion engine simultaneously recognizes emotions from the user's facial expressions, voice, and text input. The recognized emotion information is also sent to the server.

[1075] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the user's personal information, usage history information, and emotional information with the user's question, and is sent to the generative AI model.

[1076] Answer generation and display using generative AI models

[1077] The generative AI model receives the prompts and generates the optimal answer based on them. This answer is then sent back to the server and then to the user's device. Finally, the user can view the answer in the app.

[1078] Specific examples

[1079] Consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Currently subscribed to a video streaming service." Furthermore, let's say the emotion engine recognizes the user's emotion as "Excited." The server generates a follow-up prompt based on this information and sends it to the generative AI model in the form of "User's location: Tokyo, Subscription service: Video streaming service, Question: What are some good movies?, Emotion: Excited." Based on this follow-up prompt, the generative AI model generates the optimal answer, such as "Among the movies currently available on video streaming services, we recommend the latest action movie 'Action Movie Title', which is showing at a local movie theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[1080] In this way, the present invention enables a user to instantly obtain information optimized to his or her preferences, taking into account his or her emotional state, without having to go through the hassle of setting up prompts.

[1081] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1082] Step 1: Register your user information

[1083] Input: A user uses a device to enter personal information (such as interests, date of birth, or location).

[1084] When a user accesses the app for the first time, the server displays a personal information registration screen. When the user clicks the "Submit" button to submit the personal information they entered, the server receives the information and stores it in a database.

[1085] Output: User's personal information stored in a database.

[1086] What happens: The user fills out the form and clicks the "Submit" button. The server writes the received information to the database.

[1087] Step 2: Collecting usage history information

[1088] Input: The user consents to use the app on their device.

[1089] Once the user agrees to use the app, the device will collect the user's web access history and location information and send it to the server, which then receives this information and stores it in a database.

[1090] Output: User usage history information stored in a database.

[1091] Specific operation: The user presses the consent button. The device collects usage history and sends the information to the server. The server writes the information to the database.

[1092] Step 3: Sending questions and emotional information

[1093] Input: The user uses the device to type and submit a question, and the emotion engine analyzes the user's emotions.

[1094] The server receives the question entered by the user and also receives the emotion information obtained from the emotion engine. The emotion engine recognizes emotions from the user's facial expressions, voice, and text input, and sends the information to the server.

[1095] Output: User's question and sentiment information received by the server.

[1096] Specific operation: The user enters a question and clicks the "Send" button. The emotion engine analyzes emotions using the camera and microphone, and the server receives the question and emotion information.

[1097] Step 4: Generate supporting prompts

[1098] Input: The server obtains the user's personal information and usage history information from the database, and emotion information obtained from the emotion engine.

[1099] The server retrieves the user's personal information and usage history information from the database, integrates the emotional information received from the emotion engine, and generates a prompt to answer the user's question.

[1100] Output: The generated auxiliary prompt.

[1101] Specific operation: The server retrieves information from the database, integrates the emotional information, and generates a support prompt.

[1102] Step 5: Generating answers using a generative AI model

[1103] Input: Server-generated auxiliary prompt.

[1104] The generative AI model receives auxiliary prompts sent from the server and generates optimal answers based on them.

[1105] Output: The generated answer.

[1106] Specific operation: The generative AI model generates an answer based on the auxiliary prompt and sends it to the server.

[1107] Step 6: Display the answer to the user

[1108] Input: The answer sent by the generative AI model.

[1109] The server sends the answer obtained from the generative AI model to the user's device, where the user can view the answer on the app.

[1110] Output: The answer displayed on the user's device.

[1111] Specific operation: The server sends the answer to the user's device, and the user checks the answer on the app.

[1112] (Application example 2)

[1113] 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."

[1114] Conventional systems use generative AI to obtain answers to questions entered by users, but do not take the user's emotional state into consideration, making it difficult to provide personalized and optimal answers. Furthermore, personalization based solely on the user's personal information and usage history information was problematic in that it was not possible to recommend optimal content based on the user's current interests and emotions.

[1115] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating an assistance prompt based on the personal information and the usage history, means for sending the assistance prompt to a generation AI and acquiring an answer, means for displaying the answer to the user, means for recognizing the user's emotion, and means for generating an assistance prompt taking the emotion information into consideration. This makes it possible to generate personalized answers that reflect the user's emotional state, thereby providing more accurate information.

[1116] "Means for obtaining personal information registered by the user" refers to a function that sends personal information entered by the user, such as hobbies, date of birth, and location, to a server and stores it in a database.

[1117] "Means for collecting usage history information from the user's device" refers to a function that collects usage history information such as the user's web access history and location information, sends this to a server, and stores it in a database.

[1118] The "means for accepting questions entered by the user" is a function that sends questions entered by the user via a smartphone or other device to a server.

[1119] The "means for generating an auxiliary prompt based on the personal information and usage history" is a function that automatically generates an auxiliary prompt to be sent to the generation AI based on the user's personal information and usage history stored in a database.

[1120] The "means for sending the auxiliary prompt to the generation AI and obtaining an answer" is a function for sending an auxiliary prompt to the generation AI and obtaining the optimal answer based on the prompt.

[1121] "Means for displaying the answer to the user" refers to a function that displays the answer obtained from the generation AI on the user's device.

[1122] "Means for recognizing user emotions" refers to a function that recognizes emotions from the user's facial expressions, voice, etc., and sends that information to a database.

[1123] The "means for generating a support prompt taking into consideration the emotional information" is a function for generating a more accurate support prompt based on the emotional information of the user.

[1124] This invention is a system that uses generative AI to enable users to obtain intuitively optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it provides more personalized information. This system consists of four main components: the user's device, a server, generative AI, and the emotion engine.

[1125] 1. How to obtain personal information registered by users

[1126] When a user first accesses the app, the server displays a personal information registration screen, which includes fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[1127] 2. Means of collecting usage history information from users' devices

[1128] When a user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[1129] 3. A means of accepting user-entered questions

[1130] When a user launches the app and enters a question, the device sends the question to the server.

[1131] 4. How to recognize user emotions

[1132] The emotion engine recognizes the user's emotions from their facial expressions and voice, and this information is also sent to the server and stored in a database.

[1133] 5. Means for generating a support prompt based on the personal information and the usage history.

[1134] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the personal information, usage history information, emotional information, and the user's question.

[1135] 6. Means for sending the auxiliary prompt to the generation AI and obtaining a response

[1136] The AI ​​then receives the prompts and generates the optimal answer based on them, which is then sent back to the user's device via the server.

[1137] 7. Means for displaying said answers to the user

[1138] Finally, users can view the answers in the app.

[1139] Specific examples

[1140] For example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Currently subscribed to a video streaming service." Furthermore, suppose the emotion engine recognizes the user's emotion as "Excited." The server generates a supplementary prompt based on this information and sends it to the generation AI in the form of "User's location: Tokyo, Subscription service: Video streaming service, Question: What are some good movies?, Emotion: Excited." Based on this supplementary prompt, the generation AI uses information such as movies offered on the streaming service and action movies currently showing in Tokyo to generate the optimal answer, such as "Among the movies currently available on video streaming services, I recommend the latest action movie, 'Action Movie,' currently showing at a local theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[1141] Example prompt sentence:

[1142] User Location: Tokyo,

[1143] Movies seen: Avatar, Inception,

[1144] Q: What movie do you recommend?

[1145] Emotion: Excited

[1146] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1147] Step 1:

[1148] The user accesses the app and enters personal information. The user enters personal information such as hobbies, date of birth, location, etc. into the app and submits it. The server receives this information and stores it in a database.

[1149] Input: Personal information entered by the user (hobbies, date of birth, location)

[1150] Data processing: Convert the entered personal information into JSON format

[1151] Output: Personal information stored in a database

[1152] Step 2:

[1153] The user agrees to use the app, and usage history information is collected. The device collects the user's web access history and location information and sends it to the server. The server receives this information and stores it in a database.

[1154] Input: User's web access history, location information

[1155] Data processing: Convert collected usage history information into JSON format

[1156] Output: Usage history information stored in a database

[1157] Step 3:

[1158] The user launches the app and enters a question. The user enters the question in a text box within the app and submits it. The device then sends the question to the server.

[1159] Input: The question entered by the user

[1160] Data processing: Converting question text into a format that can be sent to the server

[1161] Output: The question sent to the server

[1162] Step 4:

[1163] The emotion engine recognizes emotions from the user's facial expressions and voice. Using the device's camera and microphone, the emotion engine captures the user's facial expressions and voice, analyzes them, and sends the results to the server.

[1164] Input: User's facial expression data, voice data

[1165] Data processing: Emotion analysis from facial expression and voice data

[1166] Output: Emotion information sent to the server

[1167] Step 5:

[1168] The server integrates personal information, usage history information, and emotional information to generate a support prompt.The server obtains the user's personal information, usage history information, and emotional information from the database and generates a support prompt based on these.

[1169] Input: Personal information, usage history information, and emotional information obtained from the database

[1170] Data Calculation: Generate Auxiliary Prompts

[1171] Output: Generated auxiliary prompts

[1172] Step 6:

[1173] The generation AI generates the optimal answer based on the auxiliary prompt. The server sends the auxiliary prompt to the generation AI, which then generates the optimal answer. The generated answer is then sent to the device via the server.

[1174] Input: Auxiliary prompt

[1175] Data Computation: Generating Answers with Generative AI

[1176] Output: Answer sent to the terminal via the server

[1177] Step 7:

[1178] The user checks the generated answer on the app, and the device displays the answer received from the server on the app.

[1179] Input: The answer sent by the server

[1180] Data processing: Converting received responses into a format that can be displayed on the app

[1181] Output: Answer displayed on the app

[1182] 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.

[1183] 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.

[1184] 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.

[1185] [Fourth embodiment]

[1186] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1187] 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.

[1188] 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).

[1189] 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.

[1190] 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.

[1191] 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).

[1192] 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.

[1193] 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.

[1194] 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.

[1195] 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.

[1196] 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.

[1197] 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.

[1198] 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."

[1199] The present invention provides a system that uses a generation AI to enable users to intuitively obtain optimized answers. This system includes a means for automatically generating an assistance prompt corresponding to a question entered by a user based on personal information and usage history information registered by the user, sending the assistance prompt to the generation AI to obtain the optimal answer, and displaying it to the user.

[1200] The entire system consists of three main components: the user's device, the server, and the generating AI.

[1201] When a user first accesses the app, the server displays a personal information registration screen, which contains fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[1202] Next, after the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[1203] When a user launches the app and enters a question, the device sends the question to the server. The server retrieves the user's personal information and usage history information from a database and generates a support prompt based on this information. This support prompt combines the user's personal information, usage history information, and the user's question, and is sent to the generation AI.

[1204] The AI ​​then receives the prompts and generates the best answer based on them. This answer is then sent back to the server and then to the user's device. Finally, the user can view the answer in the app.

[1205] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Has a Netflix subscription." The server generates a supplementary prompt based on this information and sends it to the generation AI in the form of "User location: Tokyo, Subscription service: Netflix, Question: What are some good movies?" Based on this supplementary prompt, the generation AI uses information about movies available on Netflix and the latest movies showing in Tokyo to generate the most appropriate answer, such as "Among the movies currently available on Netflix, we recommend the latest movie, 'Tenet,' which is showing at a local movie theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most appropriate information.

[1206] In this way, the present invention enables the user to obtain information optimized to his / her preferences in one go, without having to go through the hassle of setting up prompts.

[1207] The processing flow will be explained below.

[1208] Step 1:

[1209] Users register personal information when they first access the site

[1210] When a user accesses the app for the first time, the server displays a screen for registering personal information.

[1211] Users enter information such as hobbies, date of birth, and location, and press the send button.

[1212] The entered information is sent from the terminal to the server and stored in the server's database.

[1213] Step 2:

[1214] Collecting usage history information with the user's consent

[1215] When a user agrees to use the app, the device will collect usage history information such as web access history and location information.

[1216] The collected usage history information is sent from the terminal to the server and stored in the server's database.

[1217] Step 3:

[1218] The user enters a question

[1219] The user enters a question in the question input field of the app and presses the send button.

[1220] The question is sent from the terminal to the server.

[1221] Step 4:

[1222] The server collects personal information and usage history information

[1223] The server retrieves the personal information and usage history information registered by the user from the database.

[1224] Step 5:

[1225] The server generates a helper prompt

[1226] The server generates a prompt to answer the question entered by the user based on the acquired personal information and usage history information.

[1227] For example, create a follow-up prompt like this: "User location: Tokyo, Subscription service: Netflix, Question: What are some good movies?"

[1228] Step 6:

[1229] The server sends the generated help prompt to the generating AI.

[1230] Assistance prompts are sent to the generating AI.

[1231] Generative AI generates optimal answers based on auxiliary prompts.

[1232] Step 7:

[1233] Get answers from generative AI

[1234] The server receives the answer generated by the generation AI.

[1235] Step 8:

[1236] The server sends the answer to the user

[1237] The server sends the answer obtained from the generation AI to the terminal.

[1238] Step 9:

[1239] User checks the answer

[1240] The device displays the response received from the server on the app.

[1241] The user checks the displayed answers.

[1242] As a concrete example, if a user asks, "What are some good movies?", through the above processing steps, the answer displayed to the user will be, "Among the movies currently available on Netflix, we recommend the latest movie, 'TENET,' which is currently showing at a local movie theater in Tokyo!"

[1243] Example 1

[1244] 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."

[1245] Conventional systems have faced the problem of making it difficult for users to easily obtain information optimized for their preferences. In particular, there were few ways to efficiently utilize generative AI models to provide optimal answers to users. Furthermore, there was a lack of a way for users to effectively utilize personal information and usage history information to easily obtain information.

[1246] 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.

[1247] In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating assistance prompts based on the personal information and the usage history, means for transmitting the assistance prompts to a generative AI model that automatically generates the assistance prompts and obtaining answers, and means for transmitting and displaying the answers on the user's terminal, thereby enabling the user to obtain information optimized to their preferences in one go.

[1248] "User" refers to any individual or organization that uses this system.

[1249] "Personal Information" refers to information specific to you, such as your interests, date of birth, address, etc.

[1250] "Usage history" refers to a user's behavioral history, such as their internet access history and location information.

[1251] "Question" refers to a request for information that a user enters into the system.

[1252] "Assistive prompts" refer to inputs to a generative AI model that are generated based on a user's personal information and usage history.

[1253] "Generative AI model" refers to an artificial intelligence algorithm that receives auxiliary prompts and generates optimal answers.

[1254] "Answer" refers to the information generated by the generative AI model based on the auxiliary prompt and provided to the user.

[1255] "Terminal" refers to the electronic device (e.g., smartphone or personal computer) used by a User to access the System.

[1256] "Server" refers to a computer system that processes and stores data received from user terminals and provides necessary services.

[1257] This invention relates to a system that allows users to obtain intuitively optimized answers. The system generates assistance prompts for a generative AI model based on the user's personal information and usage history, and provides the user with the answers obtained from the generative AI model. The entire system consists of three main components: the user's terminal, a server, and a generative AI.

[1258] When a user first accesses the application, the server displays a personal information registration screen, which contains fields for entering information such as the user's interests, date of birth, address, etc. Once the user enters and submits this information, it is sent to the server and stored in a database.

[1259] Next, once the user agrees to use the app, usage history information is collected from the device. The device automatically collects internet access history and location information generated when the user browses the web or uses the app. The collected information is sent to a server and stored in a database along with personal information.

[1260] When a user launches an application and enters a question, the device sends the question to the server, which retrieves the user's personal information and usage history from a database and generates a prompt based on this information. This prompt is then sent to the generative AI model.

[1261] The generative AI model receives the prompts and generates the optimal answer based on them. The generated answer is then sent back to the user's device via the server. Finally, the user can view the answer in the application.

[1262] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is my hobby" and "My address is in City A," and their usage history includes information such as "I have a video streaming service contract." The server generates a supplementary prompt based on this information and sends it to the generative AI model in the form of, for example, "User's address: City A, Subscription service: Video streaming service, Question: What are some good movies?" Based on this supplementary prompt, the generative AI model uses information about movies offered by the video streaming service and the latest movies showing in City A to generate the optimal answer, such as "Among the movies currently available on video streaming services, we recommend the latest movie, 'Tenet,' currently showing at a theater near City A!" This answer is displayed to the user, who can immediately access the most appropriate information.

[1263] In this way, the system allows users to quickly obtain information optimized to their preferences without the need for tedious prompt settings.

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

[1265] Step 1:

[1266] The user accesses the app for the first time and registers their personal information.

[1267] Input: The first time the user opens the application

[1268] Processing: The server displays a personal information registration screen, which contains fields for entering information such as the user's interests, birthday, and address.

[1269] Output: The user enters personal information and clicks the "Submit" button to submit.

[1270] Step 2:

[1271] The server stores personal information

[1272] Input: Personal information submitted by the user

[1273] Processing: The server stores the received personal information in a database, using the user ID as a key.

[1274] Output: Personal information is saved in a database.

[1275] Step 3:

[1276] The user agrees to the collection of usage history information

[1277] Input: Screen after registering personal information

[1278] Processing: The server displays a consent screen for the collection of usage history information. When the user presses the "Agree" button, the consent information is sent to the server.

[1279] Output: Collection of usage history information is permitted.

[1280] Step 4:

[1281] The device collects usage history information and sends it to the server.

[1282] Input: User consent information

[1283] Processing: The device automatically collects usage history information (Internet access history, location information) generated when the user browses the web or uses apps. This information is periodically sent to the server.

[1284] Output: Usage history information is sent to the server.

[1285] Step 5:

[1286] The server stores usage history information

[1287] Input: Usage history information sent from the device

[1288] Processing: The server stores the received usage history information in a database, associating it with the user ID as a key.

[1289] Output: Usage history information is saved in a database.

[1290] Step 6:

[1291] The user types in a question and sends it to the server

[1292] Input: The question the user types into the app (e.g., "What are some good movies?")

[1293] Processing: The terminal sends the question entered by the user to the server.

[1294] Output: The question is sent to the server.

[1295] Step 7:

[1296] The server collects personal information and usage history information and generates a prompt.

[1297] Input: User questions, personal information from the database, and usage history information

[1298] Processing: The server retrieves relevant personal information and usage history information from the database. Based on this information, it generates a support prompt.

[1299] Output: Generated auxiliary prompt (e.g., "User's address: City A, Subscription service: Video streaming service, Question: What are some good movies?")

[1300] Step 8:

[1301] The server sends a help prompt to the generating AI

[1302] Input: Generated auxiliary prompt

[1303] Processing: The server sends the generated assistance prompt as an API request to the generating AI.

[1304] Output: A helper prompt is sent to the generating AI.

[1305] Step 9:

[1306] The generative AI generates the optimal answer and sends it to the server.

[1307] Input: Auxiliary prompt received by the generation AI

[1308] Processing: The generation AI analyzes the prompts and generates the optimal answer, which is then sent to the server as an API response.

[1309] Output: The generated answer is sent to the server.

[1310] Step 10:

[1311] The server sends the answer to the user's device

[1312] Input: Answer sent from the generation AI

[1313] Processing: The server sends the received response to the user's device using in-app notifications and data communication.

[1314] Output: The answer is sent to the user's device.

[1315] Step 11:

[1316] Users check their answers on the app

[1317] Input: Answer sent to the terminal

[1318] Processing: In the application, the user reviews the submitted answers and can decide what to do next based on the information presented.

[1319] Output: The user can see the most relevant information on the app.

[1320] (Application example 1)

[1321] 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."

[1322] In video streaming services, it is not easy for users to find the best content for them from a wide variety of content, and the process of selecting content can be time-consuming and laborious. Furthermore, there is a need to provide more personalized recommendations by effectively utilizing users' personal information and usage history. Given this background, it is necessary to improve the accuracy of recommendation systems in video streaming services and enhance the user experience.

[1323] 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.

[1324] In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating a help prompt based on the personal information and the usage history, means for transmitting the help prompt to a generation AI and acquiring an answer, means for displaying the answer to the user, and means for the answer to include recommended content for the viewing service. This allows the user to quickly receive content recommendations optimized based on their hobbies and usage history.

[1325] "User" refers to an individual or corporation that uses this system and provides personal information and usage history.

[1326] "Personal Information" is data provided by a user, including identifying information such as hobbies, date of birth, and location.

[1327] "Usage history" refers to data related to the use of this system, such as the user's web access history and location information.

[1328] "Question" refers to the inquiry or information a user enters through the system.

[1329] An "assistance prompt" is an input text to the generation AI that is automatically generated based on the user's personal information and usage history.

[1330] "Generative AI" is an artificial intelligence system that generates optimal answers based on user questions and supporting prompts.

[1331] "Answer" refers to the information or recommended content that the generative AI generates based on the auxiliary prompts and provides to the user.

[1332] "Viewing services" refer to online platforms and applications that distribute content such as video and music.

[1333] "Recommended content" refers to viewable content such as movies and dramas recommended by AI based on the user's personal information and usage history.

[1334] The system in this invention consists of three main components: a user, a server, and a generating AI. First, a user accesses a specific application using a device such as a smartphone or tablet. When the user uses the application for the first time, a personal information registration screen is displayed. This screen has fields for entering information such as the user's hobbies, date of birth, and location. Once the user enters and submits this information, the information is sent to the server and stored in a database.

[1335] Next, when a user starts using the application, the device automatically collects the user's usage history, including viewing history and location information. This information is also sent to the server and stored in a database, just like personal information.

[1336] When a user launches the application and enters a question, such as "What anime do you recommend?", the question is sent to the server. The server retrieves the user's personal information and usage history from the database and generates a prompt based on this information. This prompt is then sent to the generative AI model.

[1337] The generative AI model generates the best answer for the user based on the prompts, and the answer is sent back to the server and then to the user's device, where the user can finally view the answer in the application.

[1338] Hardware and Software Configuration

[1339] Hardware: smartphones, tablets, servers

[1340] Software: Python, Flask, SQLite, generative AI API

[1341] Data processing and calculation

[1342] The server first receives the question entered by the user and retrieves personal information and usage history information from the database. Based on this information, it generates a prompt and sends it to the generative AI model. The generative AI model then performs data calculations based on the prompt and generates the optimal answer. The generated answer is sent to the user's device via the server and displayed to the user.

[1343] Specific examples

[1344] Consider the case where a user enters the question "What anime do you recommend?" into an application. The user's personal information includes information such as "Watching anime is a hobby" and "Located in Tokyo," and their usage history includes information such as "A lot of action anime is viewed in their viewing history." The server generates a support prompt based on this information and sends it to the generative AI model in the form "User's location: Tokyo, Subscription service: Streaming service, Question: What anime do you recommend?" Based on this support prompt, the generative AI model generates the optimal answer, such as "Among the anime currently available on streaming services, we recommend the action anime 'Title'!" This answer is displayed to the user, allowing them to immediately obtain the most appropriate information.

[1345] Prompt Sentence Examples

[1346] User location: Tokyo, Subscription service: Streaming service, Question: What anime do you recommend?

[1347] In this way, the present invention helps the user intuitively find the most suitable content, and can significantly reduce the time and effort required for content selection.

[1348] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1349] Step 1:

[1350] When a user accesses the application using a device, the first time the user accesses it, a personal information registration screen is displayed, where the user enters information such as hobbies, date of birth, and location, and submits it.

[1351] Input: Personal information entered by the user.

[1352] Output: Personal information sent to the server and stored in a database.

[1353] Step 2:

[1354] Once a user agrees to use the application, usage history such as viewing history and location information is automatically collected from the device.

[1355] Input: User's viewing history, location information.

[1356] Output: Usage history information sent to the server and stored in a database.

[1357] Step 3:

[1358] The user launches the app and enters a question, such as "What anime do you recommend?" The question is sent from the device to the server.

[1359] Input: The question entered by the user.

[1360] Output: The question sent to the server.

[1361] Step 4:

[1362] The server retrieves the user's personal information and usage history information from a database and generates a prompt based on this information.

[1363] Input: Question, personal information, usage history information.

[1364] Data calculations: Combine personal information and usage history to generate assistive prompts.

[1365] Output: The generated auxiliary prompt.

[1366] Step 5:

[1367] The server sends the generated assistance prompts to the generative AI model to obtain the optimal answer.

[1368] Input: Auxiliary prompt.

[1369] Output: The optimal answer generated by the generative AI model.

[1370] Step 6:

[1371] The server then sends the obtained answer back to the user's terminal and displays it to the user.

[1372] Input: The answer from the generative AI model.

[1373] Output: The answer displayed on the user's terminal.

[1374] Step 7:

[1375] Users can view recommendations for the most suitable content through the application and watch content based on that information.

[1376] Input: The answer sent by the server.

[1377] Output: Recommended content that the user can see.

[1378] Through these steps, users can quickly receive optimized recommendations based on their personal information and usage history. Specific operations include collecting and registering information, generating assistance prompts, sending them to the generative AI model, and retrieving and displaying answers.

[1379] 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.

[1380] The present invention provides a system that uses a generation AI to enable users to intuitively obtain optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more personalized information provision. This system includes a means for automatically generating an assistance prompt that takes into account the question and emotion entered by the user based on personal information and usage history information registered by the user, sending it to the generation AI to obtain the optimal answer, and displaying it to the user.

[1381] The entire system consists of four main components: the user's device, the server, the generative AI, and the emotion engine.

[1382] When a user first accesses the app, the server displays a personal information registration screen, which contains fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[1383] Next, once the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[1384] When a user launches the app and enters a question, the device sends the question to the server, where the emotion engine simultaneously recognizes emotions from the user's facial expressions, voice, and text input. The recognized emotion information is also sent to the server.

[1385] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the user's personal information, usage history information, and emotional information with the user's question, and is sent to the generation AI.

[1386] The AI ​​then receives the prompts and generates the best answer based on them. This answer is then sent back to the server and sent to the user's device. Finally, the user can view the answer in the app.

[1387] As a concrete example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is my hobby" and "I live in Tokyo," and their usage history includes information such as "I have a Netflix subscription." Furthermore, suppose the emotion engine recognizes the user's emotion as "excited." The server generates a follow-up prompt based on this information and sends it to the generation AI in the form of "User's location: Tokyo, Subscription service: Netflix, Question: What are some good movies?, Emotion: Excited." Based on this follow-up prompt, the generation AI takes into account movies offered on Netflix and action movies currently showing in Tokyo, and generates the optimal answer, such as "Among the movies currently available on Netflix, I recommend the latest action movie, 'Tenet,' which is currently showing at a local theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[1388] In this way, the present invention enables a user to instantly obtain information optimized to his or her preferences, taking into account his or her emotional state, without having to go through the hassle of setting up prompts.

[1389] The processing flow will be explained below.

[1390] Step 1:

[1391] The server displays the personal information registration screen.

[1392] When a user accesses the app for the first time, the server displays a registration screen where the user can enter their personal information.

[1393] The registration screen includes fields for entering the user's hobbies, date of birth, location, etc.

[1394] Step 2:

[1395] The user enters and submits personal information

[1396] Users enter personal information such as hobbies, date of birth, and location, and press the send button.

[1397] The terminal sends the entered personal information to a server, which stores the information in a database.

[1398] Step 3:

[1399] The server collects usage history information

[1400] Once a user agrees to use the app, the server collects usage history information such as web access history and location information from the device.

[1401] The collected usage history information is stored in a database on the server.

[1402] Step 4:

[1403] User enters and submits a question

[1404] The user enters a question in the question input field of the app and presses the send button.

[1405] The terminal sends the user's question to the server.

[1406] Step 5:

[1407] The device recognizes and transmits emotional information

[1408] The emotion engine recognizes emotions from the user's facial expressions, voice, and text input.

[1409] The recognized emotion information is transmitted from the device to a server.

[1410] Step 6:

[1411] The server collects personal and historical information

[1412] The server retrieves the user's personal information and usage history information from the database.

[1413] Step 7:

[1414] The server generates a helper prompt

[1415] The server generates an auxiliary prompt in response to the user's question based on the acquired personal information, usage history information, and emotional information.

[1416] Support prompts include the user's location, the services they subscribe to, the question they have, and their current emotional state.

[1417] Step 8:

[1418] The server sends a help prompt to the generated AI.

[1419] The server sends the generated prompt to the AI ​​generator, requesting the best answer.

[1420] Step 9:

[1421] Generative AI generates optimized answers

[1422] Generative AI generates the best answer for the user based on auxiliary prompts.

[1423] Step 10:

[1424] The server gets the answer from the generation AI

[1425] The server receives the answer from the generation AI.

[1426] Step 11:

[1427] The server sends the answer to the user's device

[1428] The server sends the answer received from the generation AI to the user's device.

[1429] Step 12:

[1430] User checks the answer

[1431] The device displays the response received from the server on the app.

[1432] Users can view optimized answers through the app.

[1433] For example, if a user inputs the question "What are some good movies?" into the app and the emotion engine recognizes the user's emotion as "excited," the server will send the following auxiliary prompt to the generation AI: "User location: Tokyo, subscription service: Netflix, question: What are some good movies?, emotion: excited." Based on this auxiliary prompt, the generation AI will generate the optimal answer, such as "Among the movies currently available on Netflix, we recommend the latest action movie 'Tenet,' which is currently showing at a local movie theater in Tokyo!", allowing the user to immediately obtain this information.

[1434] Example 2

[1435] 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."

[1436] When users input questions and receive answers, it is difficult for the answers to be tailored to the user's specific situation and emotions. Furthermore, providing personalized information requires users to manually input a large amount of information, which is a burden for users. Therefore, there is a growing need for systems that can provide more intuitive and personalized information.

[1437] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for acquiring user emotion information, means for generating an assistance prompt based on the personal information, the usage history, and the emotion information, means for sending the assistance prompt to a generative AI model and acquiring an answer, and means for displaying the answer to the user. This makes it possible to provide personalized information in a form that best suits the user's specific situation and emotions.

[1438] "User" means any individual or entity that uses the System.

[1439] "Personal information" refers to data about users, such as hobbies, date of birth, and location.

[1440] "Terminal" means a device (e.g., smartphone, tablet, PC, etc.) used by a user to access the system.

[1441] "Usage history information" refers to behavioral data such as a user's web access history and location information.

[1442] A "question" is a query that a user enters into the system.

[1443] "Emotion information" is data about emotions recognized from a user's facial expressions, voice, and text input.

[1444] "Assistive prompts" are input data generated based on a user's personal information, usage history information, and emotional information, which the generative AI model uses to generate answers.

[1445] A "generative AI model" is an AI technology that receives auxiliary prompts and generates optimal answers.

[1446] An "answer" is information that a generative AI model generates based on a supplemental prompt.

[1447] A "server" is a computer that controls the entire system and collects, stores, analyzes, and transmits information to users.

[1448] The present invention provides a system that uses a generative AI model to enable users to intuitively obtain optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it achieves more personalized information provision. This system includes a means for automatically generating an assistance prompt that takes into account the user's input question and emotion based on personal information and usage history information registered by the user, sending it to the generative AI model to obtain the optimal answer, and displaying it to the user.

[1449] System Configuration

[1450] The entire system consists of four main components:

[1451] User's device

[1452] server

[1453] Generative AI Models

[1454] Emotion Engine

[1455] Hardware and software used

[1456] User's device: a device such as a smartphone, tablet, or computer

[1457] Server: The computer that collects, stores, analyzes, and transmits information to the user.

[1458] Generative AI models: AI technologies for natural language processing (e.g., GPT-3, BERT, etc.)

[1459] Emotion engine: software for analyzing a user's facial expressions, voice, and text input

[1460] When a user accesses the app for the first time, the server displays a personal information registration screen, which includes fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[1461] Next, once the user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[1462] Questioning and emotional information processing

[1463] When a user launches the app and enters a question, the device sends the question to the server, where the emotion engine simultaneously recognizes emotions from the user's facial expressions, voice, and text input. The recognized emotion information is also sent to the server.

[1464] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the user's personal information, usage history information, and emotional information with the user's question, and is sent to the generative AI model.

[1465] Answer generation and display using generative AI models

[1466] The generative AI model receives the prompts and generates the optimal answer based on them. This answer is then sent back to the server and then to the user's device. Finally, the user can view the answer in the app.

[1467] Specific examples

[1468] Consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Currently subscribed to a video streaming service." Furthermore, let's say the emotion engine recognizes the user's emotion as "Excited." The server generates a follow-up prompt based on this information and sends it to the generative AI model in the form of "User's location: Tokyo, Subscription service: Video streaming service, Question: What are some good movies?, Emotion: Excited." Based on this follow-up prompt, the generative AI model generates the optimal answer, such as "Among the movies currently available on video streaming services, we recommend the latest action movie 'Action Movie Title', which is showing at a local movie theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[1469] In this way, the present invention enables a user to instantly obtain information optimized to his or her preferences, taking into account his or her emotional state, without having to go through the hassle of setting up prompts.

[1470] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1471] Step 1: Register your user information

[1472] Input: A user uses a device to enter personal information (such as interests, date of birth, or location).

[1473] When a user accesses the app for the first time, the server displays a personal information registration screen. When the user clicks the "Submit" button to submit the personal information they entered, the server receives the information and stores it in a database.

[1474] Output: User's personal information stored in a database.

[1475] What happens: The user fills out the form and clicks the "Submit" button. The server writes the received information to the database.

[1476] Step 2: Collecting usage history information

[1477] Input: The user consents to use the app on their device.

[1478] Once the user agrees to use the app, the device will collect the user's web access history and location information and send it to the server, which then receives this information and stores it in a database.

[1479] Output: User usage history information stored in a database.

[1480] Specific operation: The user presses the consent button. The device collects usage history and sends the information to the server. The server writes the information to the database.

[1481] Step 3: Sending questions and emotional information

[1482] Input: The user uses the device to type and submit a question, and the emotion engine analyzes the user's emotions.

[1483] The server receives the question entered by the user and also receives the emotion information obtained from the emotion engine. The emotion engine recognizes emotions from the user's facial expressions, voice, and text input, and sends the information to the server.

[1484] Output: User's question and sentiment information received by the server.

[1485] Specific operation: The user enters a question and clicks the "Send" button. The emotion engine analyzes emotions using the camera and microphone, and the server receives the question and emotion information.

[1486] Step 4: Generate supporting prompts

[1487] Input: The server obtains the user's personal information and usage history information from the database, and emotion information obtained from the emotion engine.

[1488] The server retrieves the user's personal information and usage history information from the database, integrates the emotional information received from the emotion engine, and generates a prompt to answer the user's question.

[1489] Output: The generated auxiliary prompt.

[1490] Specific operation: The server retrieves information from the database, integrates the emotional information, and generates a support prompt.

[1491] Step 5: Generating answers using a generative AI model

[1492] Input: Server-generated auxiliary prompt.

[1493] The generative AI model receives auxiliary prompts sent from the server and generates optimal answers based on them.

[1494] Output: The generated answer.

[1495] Specific operation: The generative AI model generates an answer based on the auxiliary prompt and sends it to the server.

[1496] Step 6: Display the answer to the user

[1497] Input: The answer sent by the generative AI model.

[1498] The server sends the answer obtained from the generative AI model to the user's device, where the user can view the answer on the app.

[1499] Output: The answer displayed on the user's device.

[1500] Specific operation: The server sends the answer to the user's device, and the user checks the answer on the app.

[1501] (Application example 2)

[1502] 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."

[1503] Conventional systems use generative AI to obtain answers to questions entered by users, but do not take the user's emotional state into consideration, making it difficult to provide personalized and optimal answers. Furthermore, personalization based solely on the user's personal information and usage history information was problematic in that it was not possible to recommend optimal content based on the user's current interests and emotions.

[1504] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring personal information registered by the user, means for collecting usage history information from the user's terminal, means for accepting questions entered by the user, means for generating an assistance prompt based on the personal information and the usage history, means for sending the assistance prompt to a generation AI and acquiring an answer, means for displaying the answer to the user, means for recognizing the user's emotion, and means for generating an assistance prompt taking the emotion information into consideration. This makes it possible to generate personalized answers that reflect the user's emotional state, thereby providing more accurate information.

[1505] "Means for obtaining personal information registered by the user" refers to a function that sends personal information entered by the user, such as hobbies, date of birth, and location, to a server and stores it in a database.

[1506] "Means for collecting usage history information from the user's device" refers to a function that collects usage history information such as the user's web access history and location information, sends this to a server, and stores it in a database.

[1507] The "means for accepting questions entered by the user" is a function that sends questions entered by the user via a smartphone or other device to a server.

[1508] The "means for generating an auxiliary prompt based on the personal information and usage history" is a function that automatically generates an auxiliary prompt to be sent to the generation AI based on the user's personal information and usage history stored in a database.

[1509] The "means for sending the auxiliary prompt to the generation AI and obtaining an answer" is a function for sending an auxiliary prompt to the generation AI and obtaining the optimal answer based on the prompt.

[1510] "Means for displaying the answer to the user" refers to a function that displays the answer obtained from the generation AI on the user's device.

[1511] "Means for recognizing user emotions" refers to a function that recognizes emotions from the user's facial expressions, voice, etc., and sends that information to a database.

[1512] The "means for generating a support prompt taking into consideration the emotional information" is a function for generating a more accurate support prompt based on the emotional information of the user.

[1513] This invention is a system that uses generative AI to enable users to obtain intuitively optimized answers, and by combining it with an emotion engine that recognizes the user's emotions, it provides more personalized information. This system consists of four main components: the user's device, a server, generative AI, and the emotion engine.

[1514] 1. How to obtain personal information registered by users

[1515] When a user first accesses the app, the server displays a personal information registration screen, which includes fields for entering information such as the user's hobbies, date of birth, location, etc. Once the user enters and submits their personal information, the information is sent to the server and stored in a database.

[1516] 2. Means of collecting usage history information from users' devices

[1517] When a user agrees to use the app, usage history information is collected from the device. This information includes the user's web access history and location information. This information is also sent to the server and stored in a database along with personal information.

[1518] 3. A means of accepting user-entered questions

[1519] When a user launches the app and enters a question, the device sends the question to the server.

[1520] 4. How to recognize user emotions

[1521] The emotion engine recognizes the user's emotions from their facial expressions and voice, and this information is also sent to the server and stored in a database.

[1522] 5. Means for generating a support prompt based on the personal information and the usage history.

[1523] The server retrieves the user's personal information and usage history information from the database, and integrates the emotional information received from the emotion engine. Based on this, it generates a support prompt for the question entered by the user. This support prompt is an integration of the personal information, usage history information, emotional information, and the user's question.

[1524] 6. Means for sending the auxiliary prompt to the generation AI and obtaining a response

[1525] The AI ​​then receives the prompts and generates the optimal answer based on them, which is then sent back to the user's device via the server.

[1526] 7. Means for displaying said answers to the user

[1527] Finally, users can view the answers in the app.

[1528] Specific examples

[1529] For example, consider the case where a user enters the question "What are some good movies?" into an app. The user's personal information includes information such as "Watching movies is a hobby" and "Located in Tokyo," and their usage history includes information such as "Currently subscribed to a video streaming service." Furthermore, suppose the emotion engine recognizes the user's emotion as "Excited." The server generates a supplementary prompt based on this information and sends it to the generation AI in the form of "User's location: Tokyo, Subscription service: Video streaming service, Question: What are some good movies?, Emotion: Excited." Based on this supplementary prompt, the generation AI uses information such as movies offered on the streaming service and action movies currently showing in Tokyo to generate the optimal answer, such as "Among the movies currently available on video streaming services, I recommend the latest action movie, 'Action Movie,' currently showing at a local theater in Tokyo!" This answer is then displayed to the user, who can immediately access the most relevant information.

[1530] Example prompt sentence:

[1531] User Location: Tokyo,

[1532] Movies seen: Avatar, Inception,

[1533] Q: What movie do you recommend?

[1534] Emotion: Excited

[1535] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1536] Step 1:

[1537] The user accesses the app and enters personal information. The user enters personal information such as hobbies, date of birth, location, etc. into the app and submits it. The server receives this information and stores it in a database.

[1538] Input: Personal information entered by the user (hobbies, date of birth, location)

[1539] Data processing: Convert the entered personal information into JSON format

[1540] Output: Personal information stored in a database

[1541] Step 2:

[1542] The user agrees to use the app, and usage history information is collected. The device collects the user's web access history and location information and sends it to the server. The server receives this information and stores it in a database.

[1543] Input: User's web access history, location information

[1544] Data processing: Convert collected usage history information into JSON format

[1545] Output: Usage history information stored in a database

[1546] Step 3:

[1547] The user launches the app and enters a question. The user enters the question in a text box within the app and submits it. The device then sends the question to the server.

[1548] Input: The question entered by the user

[1549] Data processing: Converting question text into a format that can be sent to the server

[1550] Output: The question sent to the server

[1551] Step 4:

[1552] The emotion engine recognizes emotions from the user's facial expressions and voice. Using the device's camera and microphone, the emotion engine captures the user's facial expressions and voice, analyzes them, and sends the results to the server.

[1553] Input: User's facial expression data, voice data

[1554] Data processing: Emotion analysis from facial expression and voice data

[1555] Output: Emotion information sent to the server

[1556] Step 5:

[1557] The server integrates personal information, usage history information, and emotional information to generate a support prompt.The server obtains the user's personal information, usage history information, and emotional information from the database and generates a support prompt based on these.

[1558] Input: Personal information, usage history information, and emotional information obtained from the database

[1559] Data Calculation: Generate Auxiliary Prompts

[1560] Output: Generated auxiliary prompts

[1561] Step 6:

[1562] The generation AI generates the optimal answer based on the auxiliary prompt. The server sends the auxiliary prompt to the generation AI, which then generates the optimal answer. The generated answer is then sent to the device via the server.

[1563] Input: Auxiliary prompt

[1564] Data Computation: Generating Answers with Generative AI

[1565] Output: Answer sent to the terminal via the server

[1566] Step 7:

[1567] The user checks the generated answer on the app, and the device displays the answer received from the server on the app.

[1568] Input: The answer sent by the server

[1569] Data processing: Converting received responses into a format that can be displayed on the app

[1570] Output: Answer displayed on the app

[1571] 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.

[1572] 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.

[1573] 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.

[1574] 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.

[1575] 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.

[1576] 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.

[1577] 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).

[1578] 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.

[1579] 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."

[1580] 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.

[1581] 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).

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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.

[1591] 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.

[1592] The following is further disclosed regarding the above embodiment.

[1593] (Claim 1)

[1594] A means of obtaining personal information registered by users;

[1595] A means of collecting usage history information from the user's device;

[1596] a means for accepting user-entered questions;

[1597] means for generating an assistance prompt based on the personal information and the usage history;

[1598] means for sending the auxiliary prompt to a generation AI and obtaining a response;

[1599] means for displaying said answer to a user;

[1600] A system including:

[1601] (Claim 2)

[1602] 10. The system of claim 1, wherein the personal information includes the user's hobbies, date of birth, and location.

[1603] (Claim 3)

[1604] The system of claim 1 , wherein the usage history includes the user's web access history and location information.

[1605] "Example 1"

[1606] (Claim 1)

[1607] A means of obtaining personal information registered by users;

[1608] A means of collecting usage history information from the user's device;

[1609] a means for accepting user-entered questions;

[1610] means for generating an assistance prompt based on the personal information and the usage history;

[1611] means for sending the auxiliary prompt to a generative AI model that automatically generates the auxiliary prompt and obtaining an answer;

[1612] means for transmitting and displaying said answer on a user's terminal;

[1613] A system including:

[1614] (Claim 2)

[1615] 10. The system of claim 1, wherein the personal information includes the user's interests, date of birth, and address.

[1616] (Claim 3)

[1617] The system of claim 1 , wherein the usage history includes the user's internet access history and location information.

[1618] "Application Example 1"

[1619] (Claim 1)

[1620] A means of obtaining personal information registered by users;

[1621] A means of collecting usage history information from the user's device;

[1622] a means for accepting user-entered questions;

[1623] means for generating an assistance prompt based on the personal information and the usage history;

[1624] means for sending the auxiliary prompt to a generation AI and obtaining a response;

[1625] means for displaying said answer to a user;

[1626] A means for the response to include recommended content in a viewing service;

[1627] A system including:

[1628] (Claim 2)

[1629] 10. The system of claim 1, wherein the personal information includes the user's hobbies, date of birth, and location.

[1630] (Claim 3)

[1631] The system of claim 1 , wherein the usage history includes the user's web access history and location information.

[1632] "Example 2: Combining Emotion Engines"

[1633] (Claim 1)

[1634] A means of obtaining personal information registered by users;

[1635] A means of collecting usage history information from the user's device;

[1636] a means for accepting user-entered questions;

[1637] A means for acquiring user emotion information;

[1638] means for generating an assistance prompt based on the personal information, the usage history, and the emotion information;

[1639] means for sending the auxiliary prompt to a generative AI model and obtaining a response;

[1640] means for displaying said answer to a user;

[1641] A system including:

[1642] (Claim 2)

[1643] 10. The system of claim 1, wherein the personal information includes the user's hobbies, date of birth, and location.

[1644] (Claim 3)

[1645] The system of claim 1 , wherein the usage history includes the user's web access history and location information.

[1646] "Application example 2 when combining emotion engines"

[1647] (Claim 1)

[1648] A means of obtaining personal information registered by users;

[1649] A means of collecting usage history information from the user's device;

[1650] a means for accepting user-entered questions;

[1651] means for generating an assistance prompt based on the personal information and the usage history;

[1652] means for sending the auxiliary prompt to a generation AI and obtaining a response;

[1653] means for displaying said answer to a user;

[1654] a means of recognizing a user's emotions;

[1655] means for generating an auxiliary prompt taking into account the emotional information;

[1656] A system including:

[1657] (Claim 2)

[1658] 10. The system of claim 1, wherein the personal information includes the user's hobbies, date of birth, and location.

[1659] (Claim 3)

[1660] The system of claim 1 , wherein the usage history includes the user's web access history and location information. [Explanation of symbols]

[1661] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining personal information registered by users; A means of collecting usage history information from the user's device; a means for accepting user-entered questions; means for generating an assistance prompt based on the personal information and the usage history; means for sending the auxiliary prompt to a generation AI and obtaining a response; means for displaying said answer to a user; A system including:

2. The system of claim 1 , wherein the personal information includes the user's hobbies, date of birth, and location.

3. The system of claim 1 , wherein the usage history includes the user's web access history and location information.

Images