system

Abstract

We provide the system. [Solution] A means for registering the user's search preferences, A means of converting user input into prompts based on search preferences, A generation means for generating a response using a converted prompt, A system including a display means for listing and displaying the generated responses.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional conversational AI systems have the problem of low user satisfaction because they generate uniform responses without considering the individual search preferences of users. Also, appropriate prompts are not generated for the information desired by users, and the intended responses are often not obtained. Furthermore, since the generated responses are not appropriately listed and presented, there is also a problem that information cannot be provided in a form that is easy for users to see and understand.

Means for Solving the Problems

[0005] This invention provides a means for registering a user's search preferences and converting user input into prompts based on those preferences. Furthermore, it provides a system that includes a generation means for generating responses using these prompts, and a display means for listing and displaying the generated responses. In this way, it is possible to provide customized responses for each user, improving the accuracy of responses and user satisfaction. In addition, by listing the responses, it becomes possible to provide information to the user in a format that is easy to view and understand.

[0006] A "user search preference registration method" is a method that has the function of registering a user's search preferences in a database.

[0007] "User input" refers to instructions or questions, such as text or voice input, that a user provides to a conversational system.

[0008] A "prompt" refers to input data generated based on user input to derive a response.

[0009] A "prompt conversion means" is a means that has the function of generating an appropriate prompt based on the user's search preferences and input.

[0010] A "response generation means" is a means that has the function of generating a response using an artificial intelligence model based on a prompt.

[0011] An "artificial intelligence model" refers to an algorithm or program that learns from input data and generates an appropriate response.

[0012] "Response" refers to the text or audio response that the system provides in response to a user's question or instruction.

[0013] A "response display means" is a means that has the function of visually displaying the generated response to the user.

[0014] "Listing" refers to organizing and displaying multiple responses in a user-friendly format.

Brief Description of the Drawings

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a signed storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the 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.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0029] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated by a backend server.

[0037] User search preference registration

[0038] First, the user accesses the front-end conversation server via their device and registers their search preferences. For example, a user can specify preferences such as "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in its internal database.

[0039] User input reception and prompt generation

[0040] Next, the user enters a question or request (e.g., "I want to know about recent sunspot activity") into the front-end conversation server. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information.

[0041] Generate response on backend server

[0042] The generated prompt is sent to the backend conversational generation AI server. The backend conversational generation AI server receives this prompt and uses its internal artificial intelligence model to generate a response. For example, a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," might be generated.

[0043] Listing and presentation of responses

[0044] The generated responses are sent back to the front-end conversation server. The front-end conversation server lists these responses and presents them visually to the user. This allows the user to see the necessary information at a glance.

[0045] Specific example

[0046] For example, if a user types "I want to know about recent technological advancements," and their search preference is "Technology News Details," the front-end conversation server generates the prompt "Technology News Details: I want to know about recent technological advancements." This is sent to the back-end server, where the AI ​​model generates a response such as "Recent technological advancements are amazing. We've seen a lot of innovation, especially in the fields of artificial intelligence and machine learning." This response is then listed by the front-end server and displayed to the user.

[0047] This invention makes it possible to provide customized responses for each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide information to users in a format that is easy to view and understand.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] The user accesses the front-end conversation server using their device and registers their search preferences. For example, the user might input preferences such as "I like science news and prefer information with an optimistic tone" and send them to the front-end conversation server.

[0051] Step 2:

[0052] The front-end conversation server stores the preference information received from the user in an internal database. This allows each user's preferences to be managed individually.

[0053] Step 3:

[0054] The user uses their device to input and send questions or requests (e.g., "I want to know about recent sunspot activity") to the front-end conversation server.

[0055] Step 4:

[0056] The front-end conversation server receives user input and retrieves pre-registered preference information. Based on this, it converts the entered questions and requests into appropriate prompts (e.g., "Science News Optimistic: I want to know about recent sunspot activity").

[0057] Step 5:

[0058] The front-end conversation server sends the generated prompt to the back-end conversational AI server. The prompt reflects the user's preferences.

[0059] Step 6:

[0060] The backend conversational generation AI server receives a prompt and uses an artificial intelligence model to generate a response. For example, it might generate a response like, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0061] Step 7:

[0062] The backend conversational AI server generates responses, which are then sent to the frontend conversation server.

[0063] Step 8:

[0064] The front-end conversation server lists the responses received from the back-end conversational AI server. For example, if there are multiple responses, they are organized for easier viewing.

[0065] Step 9:

[0066] The front-end conversation server displays a list of responses on the user's terminal. The user can view the information in a visually organized and easy-to-understand format.

[0067] (Example 1)

[0068] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0069] Conventional systems fail to adequately provide information based on user search preferences, making it difficult to improve the quality of the user experience. Furthermore, the lack of a mechanism for properly listing and displaying generated responses means users cannot quickly obtain the information they need.

[0070] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0071] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses from the prompts using a generative AI model, and means for listing and displaying the generated responses. This enables the provision of highly accurate, customized information to the user, allowing the user to quickly obtain the information they need.

[0072] A "means for registering user search preferences" refers to an element that has the function of allowing users to input specific preference information based on their interests and concerns, and then save that information in a database.

[0073] A "means for converting user input into prompts based on search preferences" refers to an element that has the function of converting questions or requests entered by the user into an appropriate prompt format based on pre-registered preference information.

[0074] A "generative AI model" is an artificial intelligence model used to generate responses from prompts, and a concrete example is a general conversational generative model.

[0075] "Generating means for generating a response using a converted prompt" refers to an element that has the function of generating an appropriate response from a converted prompt using a generation AI model.

[0076] A "display means for listing and displaying generated responses" refers to an element that has the function of visually organizing the generated responses and presenting them in a format that is easy for the user to understand.

[0077] A "terminal" is a device used by a user to access a system and input data, and specific examples include personal computers and smartphones.

[0078] A "front-end conversation server" is a server that processes user input information and preference information and generates appropriate prompts.

[0079] A "backend conversational generation AI server" is a server that receives prompts sent from a frontend conversation server and generates responses using a generation AI model.

[0080] A "frontend framework" is a software tool used to visually list and display the generated responses to the user; specific examples include React and Vue.js.

[0081] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated using a generative AI model. The following describes in detail how this system can be specifically implemented.

[0082] User search preference registration

[0083] First, the user accesses the front-end conversation server using their device. The user accesses the system's registration page via a browser or mobile app and enters their search preferences. For example, a user might specify that they "like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in a relational database (e.g., MySQL® or PostgreSQL).

[0084] User input reception and prompt generation

[0085] Next, the user enters a question or request through the terminal (e.g., "I want to know about recent sunspot activity"). The front-end conversation server receives this input and generates an appropriate prompt based on pre-registered preference information. Specifically, if the user has registered "Optimistic Science News" as a preference, the prompt "Optimistic Science News: I want to know about recent sunspot activity" will be generated.

[0086] Generate response on backend server

[0087] The generated prompt is sent from the front-end conversation server to the back-end conversational generative AI server. The back-end conversational generative AI server receives this prompt and generates a response using a generative AI model (e.g., OpenAI®'s GPT-3®). For example, it might generate a response such as, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0088] Listing and presentation of responses

[0089] The generated responses are sent again from the backend conversational AI server to the frontend conversation server. The frontend conversation server lists these responses and displays them visually to the user using a frontend framework such as React or Vue.js. This allows the user to see the necessary information at a glance.

[0090] Specific example

[0091] For example, consider a scenario where a user types "I want to know about recent technological advancements." If the user's search preference is set to "Technology news details," the front-end conversational server generates the prompt "Technology news details: I want to know about recent technological advancements." This prompt is sent to the back-end conversational generative AI server, where the generative AI model generates the response "Recent technological advancements are astonishing. There have been many innovations, especially in the fields of artificial intelligence and machine learning." This response is listed by the front-end conversational server, and the user reviews this information on their device screen.

[0092] This invention makes it possible to provide customized responses for each user, which is expected to improve response accuracy and user satisfaction. Furthermore, by listing responses, users can easily obtain information.

[0093] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0094] Step 1:

[0095] The user accesses the frontend conversation server from their device. The input is an HTTP request sent from the device, and a login screen is displayed. Upon the user logging in, user identification information is output.

[0096] Step 2:

[0097] The user enters their search preferences on their terminal and sends them to the front-end conversation server. The input includes preference information (e.g., "Science news, optimistic"). The front-end conversation server receives this and saves it to a database such as MySQL or PostgreSQL. Specifically, the preference information is saved to the database using the query INSERT INTO user_preferences (user_id, preference) VALUES (1, 'Science news, optimistic'). The output is the preference information saved in the database.

[0098] Step 3:

[0099] The user enters a question or request into the frontend conversation server. The user's question (e.g., "I want to know about recent sunspot activity") is sent from the terminal to the server as input. The frontend conversation server receives this input and generates a prompt based on the user's preferences. Specifically, it retrieves preference information using the query SELECT preference FROM user_preferences WHERE user_id=1 and generates the prompt "Science News Optimistic: I want to know about recent sunspot activity". The output is the generated prompt.

[0100] Step 4:

[0101] The frontend conversation server sends the generated prompt to the backend conversational AI server. The input includes the prompt "Science News Optimistic: I want to know about recent sunspot activity". The frontend conversation server sends the prompt using an HTTP POST request. Specifically, it sends the request `curl -X POST http: / / backend-ai.server / generate -d '{"prompt":"Science News Optimistic: I want to know about recent sunspot activity"}'`. The output is the prompt sent to the backend conversational AI server.

[0102] Step 5:

[0103] A backend conversational generative AI server receives a prompt and generates a response using a generative AI model. The input to the backend server is the prompt "Science News Optimistic: I want to know about recent sunspot activity." The generative AI model (e.g., GPT-3) analyzes the prompt and generates the response, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries." In concrete terms, the generative AI model processes the prompt, and the text generation engine creates the response. The output is the generated response.

[0104] Step 6:

[0105] The generated response is sent from the backend conversational generation AI server to the frontend conversation server. The input includes the generated response, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries." Specifically, the backend server sends the response as an HTTP response. The output is the generated response that arrived at the frontend conversation server.

[0106] Step 7:

[0107] The frontend conversation server lists the responses it receives and presents them to the user. The input includes the generated responses. The frontend conversation server uses a frontend framework such as React or Vue.js to list the responses and display them visually to the user. Specifically, the response list is rendered in HTML or JavaScript and displayed on the user's screen. The output is a list of responses that the user can visually review.

[0108] (Application Example 1)

[0109] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0110] In conventional autonomous vehicles, passengers had limited means of receiving up-to-date information based on their interests and preferences in real time while traveling. This resulted in decreased passenger satisfaction and reduced efficiency in information acquisition. The present invention aims to solve these problems and provide a means for passengers to acquire highly personalized information in real time, even while traveling.

[0111] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0112] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses using the converted prompts, means for displaying a list of the generated responses, and means for transmitting the prompts generated based on the search preferences and user input to a backend server, and displaying the responses received from the backend server in a visual representation on the vehicle's infotainment system. This makes it possible for passengers to obtain and visually confirm personalized information in real time, even while on the move.

[0113] "User search preferences" refer to the topics, information sources, and tone of voice that users are interested in.

[0114] A "prompt" is a set of instructions generated based on user input, containing the information necessary for the server to generate a response.

[0115] "Generation means" refers to a system that has the function of generating a response using an artificial intelligence model based on a prompt.

[0116] "Display means" refers to a system that has the function of listing the generated responses and presenting them visually to the user.

[0117] A "backend server" refers to a system that receives prompts sent from a frontend server and generates responses using an artificial intelligence model.

[0118] An "infotainment system" refers to a system that provides information and entertainment for use inside a vehicle.

[0119] This invention is a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated by a backend server. The system for carrying out this invention uses the following hardware and software.

[0120] hardware

[0121] 1. Infotainment system for autonomous vehicles: A device that receives and displays user input.

[0122] 2. Frontend conversation server: A server that receives user search preferences and generates prompts.

[0123] 3. Backend conversational generation AI server: A server that receives generated prompts and generates responses.

[0124] software

[0125] 1. Flask: A framework for providing Web APIs.

[0126] 2. requests: A library for efficient communication between servers.

[0127] 3. Generative AI Model: An artificial intelligence model for generating responses based on prompts.

[0128] Program processing

[0129] The program processes the information as follows: First, the user accesses the front-end conversation server via the infotainment system and registers their search preferences. For example, the user can specify preferences such as "I like technology news and prefer detailed information." The front-end conversation server receives this preference information and stores it in its internal database.

[0130] Next, the user enters a question or request (e.g., "Tell me about the latest autonomous driving technology") via the infotainment system. The front-end conversational server receives this input and generates an appropriate prompt (e.g., "Technology News Details: Tell me about the latest autonomous driving technology") based on pre-registered preference information. The generated prompt is then sent to the back-end conversational generation AI server.

[0131] The backend conversational generative AI server receives this prompt and uses its internal generative AI model to generate a response. For example, it might generate a response such as, "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented." This generated response is then sent back to the frontend conversational server. The frontend conversational server lists these responses and displays them visualized on the infotainment system. This allows the user to see the necessary information at a glance.

[0132] Specific example

[0133] For example, if a passenger types "Tell me about the latest autonomous driving technology," the prompt will generate "Technology News Details: Tell me about the latest autonomous driving technology." The AI ​​model will then generate a response such as "The latest autonomous driving technology is advancing and new sensor technologies are being implemented," which will be displayed in the vehicle's infotainment system.

[0134] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0135] Step 1:

[0136] Users register their search preferences using the infotainment system of the autonomous vehicle. In this step, the user first enters their interests and information filtering criteria (e.g., "I like technology news and prefer detailed information"). This input data is sent to the front-end conversation server via the infotainment system. The front-end conversation server stores the received preference data in its internal database and associates it with the user ID.

[0137] Input: User's search preferences (e.g., "I like technology news and prefer detailed information")

[0138] Output: Preference information stored in the frontend conversation server's database.

[0139] Step 2:

[0140] The user enters a request for information they want to know (e.g., "Tell me about the latest autonomous driving technology") into the infotainment system. The infotainment system sends this to the front-end conversation server. The front-end conversation server retrieves pre-registered user preference information and combines it with the entered request to generate a new prompt. For example, it might become, "Technology News Details: Tell me about the latest autonomous driving technology."

[0141] Input: User request (e.g., "Please tell me about the latest autonomous driving technology")

[0142] Output: Generated prompt (Example: "Technical News Details: Tell me about the latest autonomous driving technologies")

[0143] Step 3:

[0144] The generated prompt is sent from the front-end conversational server to the back-end conversational generation AI server. The back-end conversational generation AI server receives this prompt and uses its internal generation AI model to generate a response based on the prompt. For example, a response such as "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented." might be generated.

[0145] Input: Generated prompt (Example: "Technical News Details: Tell me about the latest autonomous driving technology")

[0146] Output: Generated response (Example: "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented.")

[0147] Step 4:

[0148] The generated responses are sent from the backend conversational AI server to the frontend conversational server. The frontend conversational server converts the received responses into a visualized format and sends them to the infotainment system. The infotainment system lists these generated responses and displays them visually to the user, allowing the user to quickly see the information they need.

[0149] Input: Generated response (Example: "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented.")

[0150] Output: List of responses displayed on the infotainment system

[0151] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0152] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, further recognizes the user's emotions using an emotion engine, and lists and displays the responses generated by the backend server.

[0153] User search preference registration

[0154] First, the user accesses the front-end conversation server via their device and registers their search preferences. For example, a user can specify preferences such as "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in its internal database.

[0155] User input reception and prompt generation

[0156] Next, the user enters a question or request (e.g., "I want to know about recent sunspot activity") into the front-end conversation server and sends it. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information.

[0157] Emotion recognition by an emotion engine

[0158] Furthermore, the front-end conversation server uses an emotion engine to recognize the user's emotions from their input and past conversation data. For example, when a user types "I want to know about recent sunspot activity," the emotion engine analyzes the user's text and extracts emotions such as "excited" or "interested."

[0159] Prompt adjustment

[0160] The recognized emotional information is reflected in the prompts to generate more personalized prompts. For example, "Science News Optimistic Excited: I want to know about recent sunspot activity."

[0161] Generate response on backend server

[0162] The generated prompt is sent to the backend conversational generation AI server. The backend conversational generation AI server receives this prompt and uses its internal artificial intelligence model to generate a response. For example, it might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0163] Emotion-based response regulation

[0164] The front-end conversation server then uses the emotion engine to refine the generated response. For example, if the response is "Recent sunspot activity has been very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[0165] Listing and presentation of responses

[0166] The generated responses are sent back to the front-end conversation server, where they are listed and visually presented to the user. This allows the user to quickly see the information they need.

[0167] Specific example

[0168] For example, if a user types "I want to know about recent technological advancements," and their search preference is "Technology news details," and the emotion engine recognizes "Expectation," the front-end conversation server generates a prompt that reads "Technology news details Expectation: I want to know about recent technological advancements." This is sent to the back-end server, where the AI ​​model generates a response that reads, "Recent technological advancements are amazing. We're seeing a lot of innovation, especially in the fields of artificial intelligence and machine learning." This response is then adjusted to reflect the emotion of "Expectation," becoming something like, "It's like the future is taking shape now! We're seeing amazing advancements, especially in the fields of artificial intelligence and machine learning," and is then listed and displayed to the user.

[0169] This invention provides customized responses that reflect the emotions of each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide information to users in a format that is easy to view and understand.

[0170] The following describes the processing flow.

[0171] Step 1:

[0172] The user accesses the front-end conversation server using their device and registers their search preferences. For example, the user might input preferences such as "I like science news and prefer information with an optimistic tone" and send them to the front-end conversation server.

[0173] Step 2:

[0174] The front-end conversation server stores the preference information received from the user in an internal database. This allows each user's preferences to be managed individually.

[0175] Step 3:

[0176] The user uses their device to input and send questions or requests (e.g., "I want to know about recent sunspot activity") to the front-end conversation server.

[0177] Step 4:

[0178] The front-end conversation server receives user input and generates appropriate prompts based on pre-registered preference information. For example, it might generate a prompt such as "Science News Optimistic: I want to know about recent sunspot activity."

[0179] Step 5:

[0180] The front-end conversation server uses an emotion engine to recognize the user's emotions from their input and past conversation data. For example, when a user inputs "I want to know about recent sunspot activity," the emotion engine extracts emotions such as "excitement" and "interest."

[0181] Step 6:

[0182] The front-end conversation server incorporates recognized sentiment information into prompts to generate more personalized prompts. For example, "Science News, Optimistic, Excited: I want to know about recent sunspot activity."

[0183] Step 7:

[0184] The front-end conversation server sends the generated prompt to the back-end conversational AI server. The prompt reflects the user's preferences and emotions.

[0185] Step 8:

[0186] The backend conversational generation AI server receives a prompt and uses an artificial intelligence model to generate a response. For example, it might generate a response like, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0187] Step 9:

[0188] The backend conversational AI server generates responses, which are then sent to the frontend conversation server.

[0189] Step 10:

[0190] The front-end conversation server then uses the emotion engine to further refine the generated response. For example, if the response is "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[0191] Step 11:

[0192] The front-end conversation server lists the coordinated responses. For example, if there are multiple responses, they are organized for easier viewing.

[0193] Step 12:

[0194] The front-end conversation server displays a list of responses on the user's terminal. The user can view the information in a visually organized and easy-to-understand format.

[0195] (Example 2)

[0196] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 will be referred to as the "terminal".

[0197] Conventional information retrieval systems have difficulty providing responses that reflect users' search preferences, and have been unable to quickly deliver appropriate content for the information users are seeking. Furthermore, the lack of response generation that takes user emotions into account results in low satisfaction with the responses.

[0198] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0199] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses using artificial intelligence with the converted prompts, means for recognizing the user's emotions during the response generation process and generating prompts that reflect those emotions, means for adjusting the responses generated using prompts that include emotion reflection, and display means for listing and displaying the generated responses. This makes it possible to generate personalized responses that reflect the user's preferences and emotions.

[0200] A "user" refers to a person who uses this system to search for information and obtain a response.

[0201] "Search preferences" refer to data that shows users' preferences and tendencies regarding the types of information, sources, and presentation methods they like.

[0202] A "prompt" refers to a set of instructions given to an artificial intelligence model, generated based on user input and search preferences.

[0203] "Artificial intelligence" refers to the technology that enables computers to mimic human intelligence, performing tasks such as learning, reasoning, and perception.

[0204] "Generation means" refers to the part that executes functions or processes for generating responses using user input and prompts.

[0205] "Emotion recognition" refers to technologies and methods that identify a user's emotions based on their input and past conversation data.

[0206] "Adjustment mechanisms" refer to the parts or processes that perform functions to adjust responses based on emotion recognition and make them more appropriate for the user.

[0207] "Display means" refers to functions or devices that visually provide the generated response to the user.

[0208] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, recognizes the user's emotions using an emotion engine, and displays the generated responses in a list. An embodiment for implementing this system is described below.

[0209] User search preference registration

[0210] Users access the front-end conversation server via their device and register their search preferences. Through a browser or application, users access a search preference settings page and input data on specific topics, sources, and tone. This data can be entered as, for example, "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in an internal database (e.g., MySQL or PostgreSQL).

[0211] User input reception and prompt generation

[0212] The user enters a question or request into the front-end conversation server and sends it. For example, the user might enter "I want to know about recent sunspot activity" and click the send button. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information. Program logic is used to generate this prompt.

[0213] Emotion recognition by an emotion engine

[0214] The front-end conversation server uses an emotion engine to recognize the user's emotions from user input and past conversation data. The emotion engine utilizes natural language processing libraries (e.g., NLTK and Spacy) to extract emotion labels such as "excited" or "interested" from the text.

[0215] Prompt adjustment

[0216] The system incorporates recognized emotional information into prompts to generate more personalized prompts. For example, it might adjust prompts to something like, "Science News, Optimistic, Excited: I want to know about recent sunspot activity." This adjustment is done by updating the prompt template.

[0217] Generate response on backend server

[0218] The front-end conversational server sends the generated prompt to the back-end conversational generative AI server. The back-end conversational generative AI server receives this prompt and uses its internal artificial intelligence model (e.g., generative AI model) to generate a response. For example, it might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0219] Emotion-based response regulation

[0220] The front-end conversation server then uses the emotion engine to refine the generated response. For example, if the response is "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[0221] Listing and presentation of responses

[0222] The generated responses are sent back to the front-end conversation server, where they are listed and visually presented to the user. The response list is reflected in an HTML template and displayed on the screen in a formatted manner. For example, if a user enters "I want to know about recent technological advancements," and the search preference is "Technology news details," and the sentiment engine recognizes "Expectations," the following prompt is generated: "Technology news details Expectations: I want to know about recent technological advancements." The back-end server then generates the response "Recent technological advancements are amazing. We're seeing a lot of innovation, especially in the fields of artificial intelligence and machine learning," which, after final adjustments, is displayed to the user as "It's like the future is taking shape now! We're seeing amazing advancements, especially in the fields of artificial intelligence and machine learning."

[0223] This invention provides customized responses that reflect the emotions of each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide users with the information they need in an easy-to-view and easy-to-understand format.

[0224] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0225] Step 1:

[0226] User search preference input

[0227] The user accesses the front-end conversation server via their device and enters their search preferences. For example, a user might access a search preference settings page using a browser or app and enter preferences such as "I like science news and prefer information with an optimistic tone" into a text box. The entered preferences are then sent from the device to the server in string format.

[0228] Input: User's search preferences (e.g., "I like science news and prefer information with an optimistic tone")

[0229] Output: Preference data sent to the front-end conversation server

[0230] Step 2:

[0231] Receiving and saving search preferences

[0232] The front-end conversation server receives preference information sent from the terminal and stores it in an internal database. Specifically, the front-end conversation server uses INSERT queries to save the received preference data to a database such as MySQL or PostgreSQL.

[0233] Input: Preference data received from the device

[0234] Output: Preference data stored in the database

[0235] Step 3:

[0236] User input reception

[0237] The user enters and sends questions or requests to the front-end conversation server. For example, the user might type "I want to know about recent sunspot activity" into the chat box and click the send button. This sends the user's request data from the device to the front-end conversation server.

[0238] Input: User request (e.g., "I want to know about recent sunspot activity")

[0239] Output: Request data sent to the frontend conversation server

[0240] Step 4:

[0241] Generate a view

[0242] The front-end conversation server receives user request data and retrieves pre-registered search preference data from the database. Then, it generates a prompt based on the retrieved preference data and the user request data. Specifically, it retrieves preference data from the database using a SELECT query and combines it with the request data to create a prompt such as "Science News Optimistic: I want to know about recent sunspot activity."

[0243] Input: User request data, search preference data

[0244] Output: Generated prompt (Example: "Science News Optimistic: I want to know about recent sunspot activity")

[0245] Step 5:

[0246] Recognition of emotions

[0247] The front-end conversation server sends the generated prompts to the emotion engine to recognize the user's emotions. Specifically, it uses natural language processing libraries (e.g., NLTK or Spacy) to extract emotion labels such as "excited" or "interested."

[0248] Input: Generated prompt

[0249] Output: Recognized emotion information (e.g., "excitement")

[0250] Step 6:

[0251] Prompt adjustment

[0252] The front-end conversation server incorporates recognized sentiment information into prompts, generating personalized prompts. Based on the sentiment information, it updates prompt templates, adjusting them to something like "Science News Optimistic Excited: I want to know about recent sunspot activity."

[0253] Input: Recognized emotion information, generated prompt

[0254] Output: Adjusted prompt (e.g., "Science News Optimistic Exciting: I want to know about recent sunspot activity")

[0255] Step 7:

[0256] Send a prompt

[0257] The front-end conversation server sends the prepared prompt to the back-end conversational generation AI server. Specifically, the prompt is sent via an HTTP POST request.

[0258] Input: Adjusted prompt

[0259] Output: Prompt sent to the backend conversational generation AI server

[0260] Step 8:

[0261] Response generation

[0262] The backend conversational generative AI server receives a prompt and generates a response using its internal artificial intelligence model (e.g., a generative AI model). For example, the model might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0263] Input: Sent prompt

[0264] Output: Generated response (Example: "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries.")

[0265] Step 9:

[0266] Emotional regulation of responses

[0267] The front-end conversation server analyzes the generated response again with the emotion engine and adjusts the response to reflect the user's emotions. For example, if the generated response is "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the emotion "excitement" to "It's an exciting time, it feels like we're making new discoveries every day!"

[0268] Input: Generated response, recognized emotion information

[0269] Output: Adjusted response (e.g., "This is an exciting time, it feels like we're making new discoveries every day!")

[0270] Step 10:

[0271] Listing and presentation of responses

[0272] The front-end conversation server lists the prepared responses and presents them visually to the user. The response list is reflected in an HTML template and displayed on the screen in a formatted manner.

[0273] Input: Adjusted response

[0274] Output: List of responses displayed to the user

[0275] Through the steps described above, the system of the present invention provides responses that reflect emotions customized for each user, improving response accuracy and user satisfaction. Furthermore, by listing the responses, it provides users with the information they need in an easy-to-view and easy-to-understand format.

[0276] (Application Example 2)

[0277] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0278] In conventional virtual stores, there is a problem that it is difficult to provide personalized product recommendations that fully reflect the individual preferences and emotions of users, and it is difficult to improve user satisfaction. In addition, product information displayed without considering the emotions of users is difficult to arouse the desire to purchase at an appropriate timing. As a result, the user's purchase experience is monotonous and it is difficult to maintain interest.

[0279] 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.

[0280] In this invention, the server includes means for registering the search preferences of a user, means for converting a user input into a prompt based on the search preferences, means for recognizing the emotions of the user, means for generating a prompt adjusted by reflecting the recognized emotion information in the prompt, generation means for generating a response using the generated prompt, means for adjusting the generated response based on the emotion information, and display means for listing and displaying the adjusted response. Thereby, it becomes possible to provide personalized product recommendations that reflect the preferences and emotions of the user, and it becomes possible to improve user satisfaction and the purchase experience.

[0281] "Search preference" refers to data indicating the preferences and interests of a user for specific information or products.

[0282] "Prompt" refers to an instruction sentence generated based on user input and preference information, and serves as an input for generating a response by an artificial intelligence model.

[0283] "User input" refers to text data including questions and requests made by a user to the system.

[0284] "Emotion information" refers to data of emotions extracted from a user's text input and past dialogue data.

[0285] "Generation means" refers to means having a function of generating a response by an artificial intelligence model based on input data such as a prompt and emotion information.

[0286] The "display means" refers to means having a function for visually presenting the generated response to the user.

[0287] The present invention is a system that registers a user's search preference, generates a prompt based on it, recognizes the user's emotion using an emotion engine, and displays a list of responses generated by a backend server. This system is realized as an application of a personalized virtual shop.

[0288] System Configuration

[0289] The server includes the following means.

[0290] 1. Means for registering the user's search preference

[0291] 2. Means for converting the user input into a prompt based on the search preference

[0292] 3. Means for recognizing the user's emotion

[0293] 4. Means for generating an adjusted prompt by reflecting the recognized emotion information in the prompt

[0294] 5. Generation means for generating a response using the generated prompt

[0295] 6. Means for adjusting the generated response based on the emotion information

[0296] 7. Display means for listing and displaying the adjusted response

[0297] Generation of Program

[0298] The server implements these means using a Python program. The details of each means are shown below.

[0299] Means for registering the user's search preference

[0300] The user registers their search preferences through a smartphone app. Specifically, they select their favorite product categories, preferred styles, and information sources, and this data is saved in a database. Databases such as MySQL or Firebase are used.

[0301] Means for converting user input into a prompt based on search preferences

[0302] When the user enters a question or request (e.g., "I want to know the recommended fashion items for this month") into the smartphone app, the input is converted into a prompt. This prompt is generated based on search preferences and constructed according to a specific format.

[0303] Means for recognizing the user's emotions

[0304] Using an Emotion Engine, analyze the emotion from the user's input text. This emotion information (e.g., "expectation") is used in prompt generation.

[0305] Means for generating a prompt adjusted by reflecting the recognized emotion information in the prompt

[0306] Add the recognized emotion information to the prompt to generate a more personalized prompt sentence. For example, a prompt like "Fashion trend expectation: I want to know the recommended fashion items for this month" is generated.

[0307] Generating means for generating a response using the generated prompt

[0308] The generated prompt is sent to an artificial intelligence model (e.g., GPT-3) in the backend, and an appropriate response is generated. The response generation means sends the prompt to the artificial intelligence model through an API and receives the response.

[0309] A means of adjusting the generated response based on emotional information.

[0310] The generated responses are then refined using the emotion engine to reflect the user's emotions. For example, a response like "This month's fashion is full of new trends!" might be adjusted to something like, "It's like being at a fashion show! The new fall collection is especially stylish and exceeds expectations!"

[0311] Display means for listing and displaying the adjusted responses.

[0312] The adjusted responses are displayed in a list format on the smartphone app's user interface. This allows users to see the necessary information at a glance.

[0313] Specific example

[0314] For example, if a user enters "I want to know this month's recommended fashion items," their search preference will be recognized as "fashion trends" and their emotion as "expectation." In this case,

[0315] Prompt: "Fashion Trend Expectations: I want to know this month's recommended fashion items."

[0316] Generated response: "This month's fashion is full of new trends!"

[0317] Adjusted response: "It's like being at a fashion show! The new fall collection is especially stylish and exceeds expectations!"

[0318] In this way, responses that reflect the user's preferences and emotions are provided.

[0319] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0320] Step 1: Register the user's search preferences.

[0321] Users input their search preferences (e.g., "fashion trends" or "technology news") via their smartphone. The device sends this information to a front-end server (conversation server), which stores the preference information in a database. The input data consists of the user ID and preference information, while the output data is the preference data stored in the database.

[0322] Step 2: Accept user input and generate prompts

[0323] The user sends a question or request from their device (e.g., "I want to know this month's recommended fashion items"). The device sends this to the front-end server, which generates a prompt based on the user's preference information. The input data consists of the user's question or request and pre-registered preference information, while the output data is the generated prompt text.

[0324] Step 3: Recognize the user's emotions

[0325] The emotion engine on the server recognizes emotions (e.g., "expectation" or "excitement") from the user's input text. The input data is the user's input text, and the output data is the recognized emotion information. Specifically, the emotion engine performs text analysis and extracts specific emotions.

[0326] Step 4: Adjust prompts using emotional information

[0327] The server incorporates the recognized emotion information into the prompt text to generate an adjusted prompt text. The input data consists of the generated prompt text and the recognized emotion information, while the output data is the adjusted prompt text. Specifically, the server performs processing such as adding emotion keywords to the prompt text.

[0328] Step 5: Send a prompt to the backend server and generate a response.

[0329] The server sends a pre-tuned prompt to a backend generation AI model (e.g., GPT-3) to generate an appropriate response. The input data is the pre-tuned prompt, and the output data is the generated response. Specifically, the prompt is sent to the AI ​​model via an API, and the response is retrieved.

[0330] Step 6: Adjust the generated response based on emotional information.

[0331] The server refurbishes the responses generated by reusing the emotion engine, modifying them to reflect the user's emotions. The input data consists of the generated response and recognized emotion information, while the output data is the refined response. Specifically, emotion keywords and expressions are added to the response.

[0332] Step 7: List and display the adjusted responses.

[0333] The server displays the adjusted responses in a list format on the user's smartphone. The input data is the adjusted response text, and the output data is the list of responses displayed on the device. Specifically, the response text is displayed in a visually easy-to-understand format with a rich user interface.

[0334] By following these steps, it becomes possible to provide personalized product suggestions that reflect the user's preferences and emotions.

[0335] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0336] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0337] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0338] [Second Embodiment]

[0339] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0340] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0341] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0342] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0343] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0344] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0345] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0346] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0347] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0348] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0349] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0350] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0351] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated by a backend server.

[0352] User search preference registration

[0353] First, the user accesses the front-end conversation server via their device and registers their search preferences. For example, a user can specify preferences such as "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in its internal database.

[0354] User input reception and prompt generation

[0355] Next, the user enters a question or request (e.g., "I want to know about recent sunspot activity") into the front-end conversation server. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information.

[0356] Generate response on backend server

[0357] The generated prompt is sent to the backend conversational generation AI server. The backend conversational generation AI server receives this prompt and uses its internal artificial intelligence model to generate a response. For example, a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," might be generated.

[0358] Listing and presentation of responses

[0359] The generated responses are sent back to the front-end conversation server. The front-end conversation server lists these responses and presents them visually to the user. This allows the user to see the necessary information at a glance.

[0360] Specific example

[0361] For example, if a user types "I want to know about recent technological advancements," and their search preference is "Technology News Details," the front-end conversation server generates the prompt "Technology News Details: I want to know about recent technological advancements." This is sent to the back-end server, where the AI ​​model generates a response such as "Recent technological advancements are amazing. We've seen a lot of innovation, especially in the fields of artificial intelligence and machine learning." This response is then listed by the front-end server and displayed to the user.

[0362] This invention makes it possible to provide customized responses for each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide information to users in a format that is easy to view and understand.

[0363] The following describes the processing flow.

[0364] Step 1:

[0365] The user accesses the front-end conversation server using their device and registers their search preferences. For example, the user might input preferences such as "I like science news and prefer information with an optimistic tone" and send them to the front-end conversation server.

[0366] Step 2:

[0367] The front-end conversation server stores the preference information received from the user in an internal database. This allows each user's preferences to be managed individually.

[0368] Step 3:

[0369] The user uses their device to input and send questions or requests (e.g., "I want to know about recent sunspot activity") to the front-end conversation server.

[0370] Step 4:

[0371] The front-end conversation server receives user input and retrieves pre-registered preference information. Based on this, it converts the entered questions and requests into appropriate prompts (e.g., "Science News Optimistic: I want to know about recent sunspot activity").

[0372] Step 5:

[0373] The front-end conversation server sends the generated prompt to the back-end conversational AI server. The prompt reflects the user's preferences.

[0374] Step 6:

[0375] The backend conversational generation AI server receives a prompt and uses an artificial intelligence model to generate a response. For example, it might generate a response like, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0376] Step 7:

[0377] The backend conversational AI server generates responses, which are then sent to the frontend conversation server.

[0378] Step 8:

[0379] The front-end conversation server lists the responses received from the back-end conversational AI server. For example, if there are multiple responses, they are organized for easier viewing.

[0380] Step 9:

[0381] The front-end conversation server displays a list of responses on the user's terminal. The user can view the information in a visually organized and easy-to-understand format.

[0382] (Example 1)

[0383] Next, we will describe Example 1. 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."

[0384] Conventional systems fail to adequately provide information based on user search preferences, making it difficult to improve the quality of the user experience. Furthermore, the lack of a mechanism for properly listing and displaying generated responses means users cannot quickly obtain the information they need.

[0385] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0386] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses from the prompts using a generative AI model, and means for listing and displaying the generated responses. This enables the provision of highly accurate, customized information to the user, allowing the user to quickly obtain the information they need.

[0387] A "means for registering user search preferences" refers to an element that has the function of allowing users to input specific preference information based on their interests and concerns, and then save that information in a database.

[0388] A "means for converting user input into prompts based on search preferences" refers to an element that has the function of converting questions or requests entered by the user into an appropriate prompt format based on pre-registered preference information.

[0389] A "generative AI model" is an artificial intelligence model used to generate responses from prompts, and a concrete example is a general conversational generative model.

[0390] "Generating means for generating a response using a converted prompt" refers to an element that has the function of generating an appropriate response from a converted prompt using a generation AI model.

[0391] A "display means for listing and displaying generated responses" refers to an element that has the function of visually organizing the generated responses and presenting them in a format that is easy for the user to understand.

[0392] A "terminal" is a device used by a user to access a system and input data, and specific examples include personal computers and smartphones.

[0393] A "front-end conversation server" is a server that processes user input information and preference information and generates appropriate prompts.

[0394] A "backend conversational generation AI server" is a server that receives prompts sent from a frontend conversation server and generates responses using a generation AI model.

[0395] A "frontend framework" is a software tool used to visually list and display the generated responses to the user; specific examples include React and Vue.js.

[0396] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated using a generative AI model. The following describes in detail how this system can be specifically implemented.

[0397] User search preference registration

[0398] First, the user accesses the front-end conversation server using their device. The user accesses the system's registration page via a browser or mobile app and enters their search preferences. For example, a user might specify that they "like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in a relational database (e.g., MySQL or PostgreSQL).

[0399] User input reception and prompt generation

[0400] Next, the user enters a question or request through the terminal (e.g., "I want to know about recent sunspot activity"). The front-end conversation server receives this input and generates an appropriate prompt based on pre-registered preference information. Specifically, if the user has registered "Optimistic Science News" as a preference, the prompt "Optimistic Science News: I want to know about recent sunspot activity" will be generated.

[0401] Generate response on backend server

[0402] The generated prompt is sent from the front-end conversation server to the back-end conversational generative AI server. The back-end conversational generative AI server receives this prompt and generates a response using a generative AI model (e.g., OpenAI's GPT-3). For example, it might generate a response such as, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0403] Listing and presentation of responses

[0404] The generated responses are sent again from the backend conversational AI server to the frontend conversation server. The frontend conversation server lists these responses and displays them visually to the user using a frontend framework such as React or Vue.js. This allows the user to see the necessary information at a glance.

[0405] Specific example

[0406] For example, consider a scenario where a user types "I want to know about recent technological advancements." If the user's search preference is set to "Technology news details," the front-end conversational server generates the prompt "Technology news details: I want to know about recent technological advancements." This prompt is sent to the back-end conversational generative AI server, where the generative AI model generates the response "Recent technological advancements are astonishing. There have been many innovations, especially in the fields of artificial intelligence and machine learning." This response is listed by the front-end conversational server, and the user reviews this information on their device screen.

[0407] This invention makes it possible to provide customized responses for each user, which is expected to improve response accuracy and user satisfaction. Furthermore, by listing responses, users can easily obtain information.

[0408] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0409] Step 1:

[0410] The user accesses the frontend conversation server from their device. The input is an HTTP request sent from the device, and a login screen is displayed. Upon the user logging in, user identification information is output.

[0411] Step 2:

[0412] The user enters their search preferences on their terminal and sends them to the front-end conversation server. The input includes preference information (e.g., "Science news, optimistic"). The front-end conversation server receives this and saves it to a database such as MySQL or PostgreSQL. Specifically, the preference information is saved to the database using the query INSERT INTO user_preferences (user_id, preference) VALUES (1, 'Science news, optimistic'). The output is the preference information saved in the database.

[0413] Step 3:

[0414] The user enters a question or request into the frontend conversation server. The user's question (e.g., "I want to know about recent sunspot activity") is sent from the terminal to the server as input. The frontend conversation server receives this input and generates a prompt based on the user's preferences. Specifically, it retrieves preference information using the query SELECT preference FROM user_preferences WHERE user_id=1 and generates the prompt "Science News Optimistic: I want to know about recent sunspot activity". The output is the generated prompt.

[0415] Step 4:

[0416] The frontend conversation server sends the generated prompt to the backend conversational AI server. The input includes the prompt "Science News Optimistic: I want to know about recent sunspot activity". The frontend conversation server sends the prompt using an HTTP POST request. Specifically, it sends the request `curl -X POST http: / / backend-ai.server / generate -d '{"prompt":"Science News Optimistic: I want to know about recent sunspot activity"}'`. The output is the prompt sent to the backend conversational AI server.

[0417] Step 5:

[0418] A backend conversational generative AI server receives a prompt and generates a response using a generative AI model. The input to the backend server is the prompt "Science News Optimistic: I want to know about recent sunspot activity." The generative AI model (e.g., GPT-3) analyzes the prompt and generates the response, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries." In concrete terms, the generative AI model processes the prompt, and the text generation engine creates the response. The output is the generated response.

[0419] Step 6:

[0420] The generated response is sent from the backend conversational generation AI server to the frontend conversation server. The input includes the generated response, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries." Specifically, the backend server sends the response as an HTTP response. The output is the generated response that arrived at the frontend conversation server.

[0421] Step 7:

[0422] The frontend conversation server lists the responses it receives and presents them to the user. The input includes the generated responses. The frontend conversation server uses a frontend framework such as React or Vue.js to list the responses and display them visually to the user. Specifically, the response list is rendered using HTML or JavaScript and displayed on the user's screen. The output is a list of responses that the user can visually review.

[0423] (Application Example 1)

[0424] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0425] In conventional autonomous vehicles, passengers had limited means of receiving up-to-date information based on their interests and preferences in real time while traveling. This resulted in decreased passenger satisfaction and reduced efficiency in information acquisition. The present invention aims to solve these problems and provide a means for passengers to acquire highly personalized information in real time, even while traveling.

[0426] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0427] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses using the converted prompts, means for displaying a list of the generated responses, and means for transmitting the prompts generated based on the search preferences and user input to a backend server, and displaying the responses received from the backend server in a visual representation on the vehicle's infotainment system. This makes it possible for passengers to obtain and visually confirm personalized information in real time, even while on the move.

[0428] "User search preferences" refer to the topics, information sources, and tone of voice that users are interested in.

[0429] A "prompt" is a set of instructions generated based on user input, containing the information necessary for the server to generate a response.

[0430] "Generation means" refers to a system that has the function of generating a response using an artificial intelligence model based on a prompt.

[0431] "Display means" refers to a system that has the function of listing the generated responses and presenting them visually to the user.

[0432] A "backend server" refers to a system that receives prompts sent from a frontend server and generates responses using an artificial intelligence model.

[0433] An "infotainment system" refers to a system that provides information and entertainment for use inside a vehicle.

[0434] This invention is a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated by a backend server. The system for carrying out this invention uses the following hardware and software.

[0435] hardware

[0436] 1. Infotainment system for autonomous vehicles: A device that receives and displays user input.

[0437] 2. Frontend conversation server: A server that receives user search preferences and generates prompts.

[0438] 3. Backend conversational generation AI server: A server that receives generated prompts and generates responses.

[0439] software

[0440] 1. Flask: A framework for providing Web APIs.

[0441] 2. requests: A library for efficient communication between servers.

[0442] 3. Generative AI Model: An artificial intelligence model for generating responses based on prompts.

[0443] Program processing

[0444] The program processes the information as follows: First, the user accesses the front-end conversation server via the infotainment system and registers their search preferences. For example, the user can specify preferences such as "I like technology news and prefer detailed information." The front-end conversation server receives this preference information and stores it in its internal database.

[0445] Next, the user enters a question or request (e.g., "Tell me about the latest autonomous driving technology") via the infotainment system. The front-end conversational server receives this input and generates an appropriate prompt (e.g., "Technology News Details: Tell me about the latest autonomous driving technology") based on pre-registered preference information. The generated prompt is then sent to the back-end conversational generation AI server.

[0446] The backend conversational generative AI server receives this prompt and uses its internal generative AI model to generate a response. For example, it might generate a response such as, "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented." This generated response is then sent back to the frontend conversational server. The frontend conversational server lists these responses and displays them visualized on the infotainment system. This allows the user to see the necessary information at a glance.

[0447] Specific example

[0448] For example, if a passenger types "Tell me about the latest autonomous driving technology," the prompt will generate "Technology News Details: Tell me about the latest autonomous driving technology." The AI ​​model will then generate a response such as "The latest autonomous driving technology is advancing and new sensor technologies are being implemented," which will be displayed in the vehicle's infotainment system.

[0449] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0450] Step 1:

[0451] Users register their search preferences using the infotainment system of the autonomous vehicle. In this step, the user first enters their interests and information filtering criteria (e.g., "I like technology news and prefer detailed information"). This input data is sent to the front-end conversation server via the infotainment system. The front-end conversation server stores the received preference data in its internal database and associates it with the user ID.

[0452] Input: User's search preferences (e.g., "I like technology news and prefer detailed information")

[0453] Output: Preference information stored in the frontend conversation server's database.

[0454] Step 2:

[0455] The user enters a request for information they want to know (e.g., "Tell me about the latest autonomous driving technology") into the infotainment system. The infotainment system sends this to the front-end conversation server. The front-end conversation server retrieves pre-registered user preference information and combines it with the entered request to generate a new prompt. For example, it might become, "Technology News Details: Tell me about the latest autonomous driving technology."

[0456] Input: User request (e.g., "Please tell me about the latest autonomous driving technology")

[0457] Output: Generated prompt (Example: "Technical News Details: Tell me about the latest autonomous driving technologies")

[0458] Step 3:

[0459] The generated prompt is sent from the front-end conversational server to the back-end conversational generation AI server. The back-end conversational generation AI server receives this prompt and uses its internal generation AI model to generate a response based on the prompt. For example, a response such as "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented." might be generated.

[0460] Input: Generated prompt (Example: "Technical News Details: Tell me about the latest autonomous driving technology")

[0461] Output: Generated response (Example: "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented.")

[0462] Step 4:

[0463] The generated responses are sent from the backend conversational AI server to the frontend conversational server. The frontend conversational server converts the received responses into a visualized format and sends them to the infotainment system. The infotainment system lists these generated responses and displays them visually to the user, allowing the user to quickly see the information they need.

[0464] Input: Generated response (Example: "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented.")

[0465] Output: List of responses displayed on the infotainment system

[0466] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0467] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, further recognizes the user's emotions using an emotion engine, and lists and displays the responses generated by the backend server.

[0468] User search preference registration

[0469] First, the user accesses the front-end conversation server via their device and registers their search preferences. For example, a user can specify preferences such as "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in its internal database.

[0470] User input reception and prompt generation

[0471] Next, the user enters a question or request (e.g., "I want to know about recent sunspot activity") into the front-end conversation server and sends it. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information.

[0472] Emotion recognition by an emotion engine

[0473] Furthermore, the front-end conversation server uses an emotion engine to recognize the user's emotions from their input and past conversation data. For example, when a user types "I want to know about recent sunspot activity," the emotion engine analyzes the user's text and extracts emotions such as "excited" or "interested."

[0474] Prompt adjustment

[0475] The recognized emotional information is reflected in the prompts to generate more personalized prompts. For example, "Science News Optimistic Excited: I want to know about recent sunspot activity."

[0476] Generate response on backend server

[0477] The generated prompt is sent to the backend conversational generation AI server. The backend conversational generation AI server receives this prompt and uses its internal artificial intelligence model to generate a response. For example, it might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0478] Emotion-based response regulation

[0479] The front-end conversation server then uses the emotion engine to refine the generated response. For example, if the response is "Recent sunspot activity has been very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[0480] Listing and presentation of responses

[0481] The generated responses are sent back to the front-end conversation server, where they are listed and visually presented to the user. This allows the user to quickly see the information they need.

[0482] Specific example

[0483] For example, if a user types "I want to know about recent technological advancements," and their search preference is "Technology news details," and the emotion engine recognizes "Expectation," the front-end conversation server generates a prompt that reads "Technology news details Expectation: I want to know about recent technological advancements." This is sent to the back-end server, where the AI ​​model generates a response that reads, "Recent technological advancements are amazing. We're seeing a lot of innovation, especially in the fields of artificial intelligence and machine learning." This response is then adjusted to reflect the emotion of "Expectation," becoming something like, "It's like the future is taking shape now! We're seeing amazing advancements, especially in the fields of artificial intelligence and machine learning," and is then listed and displayed to the user.

[0484] This invention provides customized responses that reflect the emotions of each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide information to users in a format that is easy to view and understand.

[0485] The following describes the processing flow.

[0486] Step 1:

[0487] The user accesses the front-end conversation server using their device and registers their search preferences. For example, the user might input preferences such as "I like science news and prefer information with an optimistic tone" and send them to the front-end conversation server.

[0488] Step 2:

[0489] The front-end conversation server stores the preference information received from the user in an internal database. This allows each user's preferences to be managed individually.

[0490] Step 3:

[0491] The user uses their device to input and send questions or requests (e.g., "I want to know about recent sunspot activity") to the front-end conversation server.

[0492] Step 4:

[0493] The front-end conversation server receives user input and generates appropriate prompts based on pre-registered preference information. For example, it might generate a prompt such as "Science News Optimistic: I want to know about recent sunspot activity."

[0494] Step 5:

[0495] The front-end conversation server uses an emotion engine to recognize the user's emotions from their input and past conversation data. For example, when a user inputs "I want to know about recent sunspot activity," the emotion engine extracts emotions such as "excitement" and "interest."

[0496] Step 6:

[0497] The front-end conversation server incorporates recognized sentiment information into prompts to generate more personalized prompts. For example, "Science News, Optimistic, Excited: I want to know about recent sunspot activity."

[0498] Step 7:

[0499] The front-end conversation server sends the generated prompt to the back-end conversational AI server. The prompt reflects the user's preferences and emotions.

[0500] Step 8:

[0501] The backend conversational generation AI server receives a prompt and uses an artificial intelligence model to generate a response. For example, it might generate a response like, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0502] Step 9:

[0503] The backend conversational AI server generates responses, which are then sent to the frontend conversation server.

[0504] Step 10:

[0505] The front-end conversation server then uses the emotion engine to further refine the generated response. For example, if the response is "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[0506] Step 11:

[0507] The front-end conversation server lists the coordinated responses. For example, if there are multiple responses, they are organized for easier viewing.

[0508] Step 12:

[0509] The front-end conversation server displays a list of responses on the user's terminal. The user can view the information in a visually organized and easy-to-understand format.

[0510] (Example 2)

[0511] Next, we will describe Example 2. 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".

[0512] Conventional information retrieval systems have difficulty providing responses that reflect users' search preferences, and have been unable to quickly deliver appropriate content for the information users are seeking. Furthermore, the lack of response generation that takes user emotions into account results in low satisfaction with the responses.

[0513] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0514] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses using artificial intelligence with the converted prompts, means for recognizing the user's emotions during the response generation process and generating prompts that reflect those emotions, means for adjusting the responses generated using prompts that include emotion reflection, and display means for listing and displaying the generated responses. This makes it possible to generate personalized responses that reflect the user's preferences and emotions.

[0515] A "user" refers to a person who uses this system to search for information and obtain a response.

[0516] "Search preferences" refer to data that shows users' preferences and tendencies regarding the types of information, sources, and presentation methods they like.

[0517] A "prompt" refers to a set of instructions given to an artificial intelligence model, generated based on user input and search preferences.

[0518] "Artificial intelligence" refers to the technology that enables computers to mimic human intelligence, performing tasks such as learning, reasoning, and perception.

[0519] "Generation means" refers to the part that executes functions or processes for generating responses using user input and prompts.

[0520] "Emotion recognition" refers to technologies and methods that identify a user's emotions based on their input and past conversation data.

[0521] "Adjustment mechanisms" refer to the parts or processes that perform functions to adjust responses based on emotion recognition and make them more appropriate for the user.

[0522] "Display means" refers to functions or devices that visually provide the generated response to the user.

[0523] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, recognizes the user's emotions using an emotion engine, and displays the generated responses in a list. An embodiment for implementing this system is described below.

[0524] User search preference registration

[0525] Users access the front-end conversation server via their device and register their search preferences. Through a browser or application, users access a search preference settings page and input data on specific topics, sources, and tone. This data can be entered as, for example, "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in an internal database (e.g., MySQL or PostgreSQL).

[0526] User input reception and prompt generation

[0527] The user enters a question or request into the front-end conversation server and sends it. For example, the user might enter "I want to know about recent sunspot activity" and click the send button. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information. Program logic is used to generate this prompt.

[0528] Emotion recognition by an emotion engine

[0529] The front-end conversation server uses an emotion engine to recognize the user's emotions from user input and past conversation data. The emotion engine utilizes natural language processing libraries (e.g., NLTK and Spacy) to extract emotion labels such as "excited" or "interested" from the text.

[0530] Prompt adjustment

[0531] The system incorporates recognized emotional information into prompts to generate more personalized prompts. For example, it might adjust prompts to something like, "Science News, Optimistic, Excited: I want to know about recent sunspot activity." This adjustment is done by updating the prompt template.

[0532] Generate response on backend server

[0533] The front-end conversational server sends the generated prompt to the back-end conversational generative AI server. The back-end conversational generative AI server receives this prompt and uses its internal artificial intelligence model (e.g., generative AI model) to generate a response. For example, it might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0534] Emotion-based response regulation

[0535] The front-end conversation server then uses the emotion engine to refine the generated response. For example, if the response is "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[0536] Listing and presentation of responses

[0537] The generated responses are sent back to the front-end conversation server, where they are listed and visually presented to the user. The response list is reflected in an HTML template and displayed on the screen in a formatted manner. For example, if a user enters "I want to know about recent technological advancements," and the search preference is "Technology news details," and the sentiment engine recognizes "Expectations," the following prompt is generated: "Technology news details Expectations: I want to know about recent technological advancements." The back-end server then generates the response "Recent technological advancements are amazing. We're seeing a lot of innovation, especially in the fields of artificial intelligence and machine learning," which, after final adjustments, is displayed to the user as "It's like the future is taking shape now! We're seeing amazing advancements, especially in the fields of artificial intelligence and machine learning."

[0538] This invention provides customized responses that reflect the emotions of each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide users with the information they need in an easy-to-view and easy-to-understand format.

[0539] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0540] Step 1:

[0541] User search preference input

[0542] The user accesses the front-end conversation server via their device and enters their search preferences. For example, a user might access a search preference settings page using a browser or app and enter preferences such as "I like science news and prefer information with an optimistic tone" into a text box. The entered preferences are then sent from the device to the server in string format.

[0543] Input: User's search preferences (e.g., "I like science news and prefer information with an optimistic tone")

[0544] Output: Preference data sent to the front-end conversation server

[0545] Step 2:

[0546] Receiving and saving search preferences

[0547] The front-end conversation server receives preference information sent from the terminal and stores it in an internal database. Specifically, the front-end conversation server uses INSERT queries to save the received preference data to a database such as MySQL or PostgreSQL.

[0548] Input: Preference data received from the device

[0549] Output: Preference data stored in the database

[0550] Step 3:

[0551] User input reception

[0552] The user enters and sends questions or requests to the front-end conversation server. For example, the user might type "I want to know about recent sunspot activity" into the chat box and click the send button. This sends the user's request data from the device to the front-end conversation server.

[0553] Input: User request (e.g., "I want to know about recent sunspot activity")

[0554] Output: Request data sent to the frontend conversation server

[0555] Step 4:

[0556] Generate a view

[0557] The front-end conversation server receives user request data and retrieves pre-registered search preference data from the database. Then, it generates a prompt based on the retrieved preference data and the user request data. Specifically, it retrieves preference data from the database using a SELECT query and combines it with the request data to create a prompt such as "Science News Optimistic: I want to know about recent sunspot activity."

[0558] Input: User request data, search preference data

[0559] Output: Generated prompt (Example: "Science News Optimistic: I want to know about recent sunspot activity")

[0560] Step 5:

[0561] Recognition of emotions

[0562] The front-end conversation server sends the generated prompts to the emotion engine to recognize the user's emotions. Specifically, it uses natural language processing libraries (e.g., NLTK or Spacy) to extract emotion labels such as "excited" or "interested."

[0563] Input: Generated prompt

[0564] Output: Recognized emotion information (e.g., "excitement")

[0565] Step 6:

[0566] Prompt adjustment

[0567] The front-end conversation server incorporates recognized sentiment information into prompts, generating personalized prompts. Based on the sentiment information, it updates prompt templates, adjusting them to something like "Science News Optimistic Excited: I want to know about recent sunspot activity."

[0568] Input: Recognized emotion information, generated prompt

[0569] Output: Adjusted prompt (e.g., "Science News Optimistic Exciting: I want to know about recent sunspot activity")

[0570] Step 7:

[0571] Send a prompt

[0572] The front-end conversation server sends the prepared prompt to the back-end conversational generation AI server. Specifically, the prompt is sent via an HTTP POST request.

[0573] Input: Adjusted prompt

[0574] Output: Prompt sent to the backend conversational generation AI server

[0575] Step 8:

[0576] Response generation

[0577] The backend conversational generative AI server receives a prompt and generates a response using its internal artificial intelligence model (e.g., a generative AI model). For example, the model might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0578] Input: Sent prompt

[0579] Output: Generated response (Example: "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries.")

[0580] Step 9:

[0581] Emotional regulation of responses

[0582] The front-end conversation server analyzes the generated response again with the emotion engine and adjusts the response to reflect the user's emotions. For example, if the generated response is "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the emotion "excitement" to "It's an exciting time, it feels like we're making new discoveries every day!"

[0583] Input: Generated response, recognized emotion information

[0584] Output: Adjusted response (e.g., "This is an exciting time, it feels like we're making new discoveries every day!")

[0585] Step 10:

[0586] Listing and presentation of responses

[0587] The front-end conversation server lists the prepared responses and presents them visually to the user. The response list is reflected in an HTML template and displayed on the screen in a formatted manner.

[0588] Input: Adjusted response

[0589] Output: List of responses displayed to the user

[0590] Through the steps described above, the system of the present invention provides responses that reflect emotions customized for each user, improving response accuracy and user satisfaction. Furthermore, by listing the responses, it provides users with the information they need in an easy-to-view and easy-to-understand format.

[0591] (Application Example 2)

[0592] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0593] Traditional virtual stores face the challenge of not being able to provide personalized product suggestions that fully reflect individual user preferences and emotions, making it difficult to improve user satisfaction. Furthermore, product information displayed without considering user emotions makes it difficult to stimulate purchasing intent at the appropriate time. As a result, the user's purchasing experience becomes monotonous, making it difficult to maintain their interest.

[0594] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0595] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for recognizing the user's emotions, means for generating prompts adjusted by reflecting the recognized emotional information in the prompts, means for generating responses using the generated prompts, means for adjusting the generated responses based on the emotional information, and means for displaying a list of the adjusted responses. This enables personalized product suggestions that reflect the user's preferences and emotions, thereby improving user satisfaction and the purchasing experience.

[0596] "Search preferences" refer to data that shows a user's preferences and interests regarding specific information or products.

[0597] A "prompt" is a set of instructions generated based on user input and preference information, and serves as input for generating a response in an artificial intelligence model.

[0598] "User input" refers to text data that includes questions and requests made by the user to the system.

[0599] "Emotional information" refers to emotional data extracted from user text input and past conversation data.

[0600] A "generation method" refers to a means that allows an artificial intelligence model to generate a response based on input data such as prompts and emotional information.

[0601] A "display means" refers to a means that has the function of visually presenting the generated response to the user.

[0602] This invention relates to a system that registers a user's search preferences, generates prompts based on those preferences, recognizes the user's emotions using an emotion engine, and displays a list of responses generated by a backend server. This system is implemented as a personalized virtual shop application.

[0603] System Configuration

[0604] The server includes the following measures:

[0605] 1. Means for registering user search preferences

[0606] 2. Means for converting user input into prompts based on search preferences

[0607] 3. Means of recognizing user emotions

[0608] 4. Means for generating adjusted prompts by reflecting recognized emotional information in the prompts.

[0609] 5. Generation means for generating a response using the generated prompt.

[0610] 6. Means for adjusting the generated response based on emotional information

[0611] 7. Display means for listing and displaying the adjusted responses.

[0612] Program generation

[0613] The server implements these measures using Python programs. Details of each measure are shown below.

[0614] A method for registering user search preferences

[0615] Users register their search preferences via a smartphone app. Specifically, they select their favorite product categories, preferred styles, and information sources, and this data is stored in a database. The database uses services such as MySQL or Firebase.

[0616] A means of converting user input into prompts based on search preferences.

[0617] When a user enters a question or request (e.g., "I want to know this month's recommended fashion items") into the smartphone app, that input is converted into a prompt. This prompt is generated based on the user's search preferences and constructed according to a specific format.

[0618] Means of recognizing user emotions

[0619] The EmotionEngine is used to analyze the emotions expressed in the user's input text. This emotional information (e.g., "expectation") is then used to generate prompts.

[0620] A means of generating adjusted prompts by reflecting recognized emotional information in the prompts.

[0621] Recognized emotion information is added to the prompt to generate more personalized prompt messages. For example, a prompt such as "Fashion Trend Expectation: I want to know this month's recommended fashion items" might be generated.

[0622] Generation means for generating a response using the generated prompt.

[0623] The generated prompt is sent to an artificial intelligence model (e.g., GPT-3) in the backend, and an appropriate response is generated. The response generation means sends prompts to the artificial intelligence model via an API and receives responses.

[0624] A means of adjusting the generated response based on emotional information.

[0625] The generated responses are then refined using the emotion engine to reflect the user's emotions. For example, a response like "This month's fashion is full of new trends!" might be adjusted to something like, "It's like being at a fashion show! The new fall collection is especially stylish and exceeds expectations!"

[0626] Display means for listing and displaying the adjusted responses.

[0627] The adjusted responses are displayed in a list format on the smartphone app's user interface. This allows users to see the necessary information at a glance.

[0628] Specific example

[0629] For example, if a user enters "I want to know this month's recommended fashion items," their search preference will be recognized as "fashion trends" and their emotion as "expectation." In this case,

[0630] Prompt: "Fashion Trend Expectations: I want to know this month's recommended fashion items."

[0631] Generated response: "This month's fashion is full of new trends!"

[0632] Adjusted response: "It's like being at a fashion show! The new fall collection is especially stylish and exceeds expectations!"

[0633] In this way, responses that reflect the user's preferences and emotions are provided.

[0634] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0635] Step 1: Register the user's search preferences.

[0636] Users input their search preferences (e.g., "fashion trends" or "technology news") via their smartphone. The device sends this information to a front-end server (conversation server), which stores the preference information in a database. The input data consists of the user ID and preference information, while the output data is the preference data stored in the database.

[0637] Step 2: Accept user input and generate prompts

[0638] The user sends a question or request from their device (e.g., "I want to know this month's recommended fashion items"). The device sends this to the front-end server, which generates a prompt based on the user's preference information. The input data consists of the user's question or request and pre-registered preference information, while the output data is the generated prompt text.

[0639] Step 3: Recognize the user's emotions

[0640] The emotion engine on the server recognizes emotions (e.g., "expectation" or "excitement") from the user's input text. The input data is the user's input text, and the output data is the recognized emotion information. Specifically, the emotion engine performs text analysis and extracts specific emotions.

[0641] Step 4: Adjust prompts using emotional information

[0642] The server incorporates the recognized emotion information into the prompt text to generate an adjusted prompt text. The input data consists of the generated prompt text and the recognized emotion information, while the output data is the adjusted prompt text. Specifically, the server performs processing such as adding emotion keywords to the prompt text.

[0643] Step 5: Send a prompt to the backend server and generate a response.

[0644] The server sends a pre-tuned prompt to a backend generation AI model (e.g., GPT-3) to generate an appropriate response. The input data is the pre-tuned prompt, and the output data is the generated response. Specifically, the prompt is sent to the AI ​​model via an API, and the response is retrieved.

[0645] Step 6: Adjust the generated response based on emotional information.

[0646] The server refurbishes the responses generated by reusing the emotion engine, modifying them to reflect the user's emotions. The input data consists of the generated response and recognized emotion information, while the output data is the refined response. Specifically, emotion keywords and expressions are added to the response.

[0647] Step 7: List and display the adjusted responses.

[0648] The server displays the adjusted responses in a list format on the user's smartphone. The input data is the adjusted response text, and the output data is the list of responses displayed on the device. Specifically, the response text is displayed in a visually easy-to-understand format with a rich user interface.

[0649] By following these steps, it becomes possible to provide personalized product suggestions that reflect the user's preferences and emotions.

[0650] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0651] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0652] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0653] [Third Embodiment]

[0654] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0655] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0656] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0657] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0658] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0659] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0660] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0661] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0662] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0663] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0664] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0665] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0666] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated by a backend server.

[0667] User search preference registration

[0668] First, the user accesses the front-end conversation server via their device and registers their search preferences. For example, a user can specify preferences such as "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in its internal database.

[0669] User input reception and prompt generation

[0670] Next, the user enters a question or request (e.g., "I want to know about recent sunspot activity") into the front-end conversation server. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information.

[0671] Generate response on backend server

[0672] The generated prompt is sent to the backend conversational generation AI server. The backend conversational generation AI server receives this prompt and uses its internal artificial intelligence model to generate a response. For example, a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," might be generated.

[0673] Listing and presentation of responses

[0674] The generated responses are sent back to the front-end conversation server. The front-end conversation server lists these responses and presents them visually to the user. This allows the user to see the necessary information at a glance.

[0675] Specific example

[0676] For example, if a user types "I want to know about recent technological advancements," and their search preference is "Technology News Details," the front-end conversation server generates the prompt "Technology News Details: I want to know about recent technological advancements." This is sent to the back-end server, where the AI ​​model generates a response such as "Recent technological advancements are amazing. We've seen a lot of innovation, especially in the fields of artificial intelligence and machine learning." This response is then listed by the front-end server and displayed to the user.

[0677] This invention makes it possible to provide customized responses for each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide information to users in a format that is easy to view and understand.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] The user accesses the front-end conversation server using their device and registers their search preferences. For example, the user might input preferences such as "I like science news and prefer information with an optimistic tone" and send them to the front-end conversation server.

[0681] Step 2:

[0682] The front-end conversation server stores the preference information received from the user in an internal database. This allows each user's preferences to be managed individually.

[0683] Step 3:

[0684] The user uses their device to input and send questions or requests (e.g., "I want to know about recent sunspot activity") to the front-end conversation server.

[0685] Step 4:

[0686] The front-end conversation server receives user input and retrieves pre-registered preference information. Based on this, it converts the entered questions and requests into appropriate prompts (e.g., "Science News Optimistic: I want to know about recent sunspot activity").

[0687] Step 5:

[0688] The front-end conversation server sends the generated prompt to the back-end conversational AI server. The prompt reflects the user's preferences.

[0689] Step 6:

[0690] The backend conversational generation AI server receives a prompt and uses an artificial intelligence model to generate a response. For example, it might generate a response like, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0691] Step 7:

[0692] The backend conversational AI server generates responses, which are then sent to the frontend conversation server.

[0693] Step 8:

[0694] The front-end conversation server lists the responses received from the back-end conversational AI server. For example, if there are multiple responses, they are organized for easier viewing.

[0695] Step 9:

[0696] The front-end conversation server displays a list of responses on the user's terminal. The user can view the information in a visually organized and easy-to-understand format.

[0697] (Example 1)

[0698] Next, we will describe Example 1. 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."

[0699] Conventional systems fail to adequately provide information based on user search preferences, making it difficult to improve the quality of the user experience. Furthermore, the lack of a mechanism for properly listing and displaying generated responses means users cannot quickly obtain the information they need.

[0700] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0701] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses from the prompts using a generative AI model, and means for listing and displaying the generated responses. This enables the provision of highly accurate, customized information to the user, allowing the user to quickly obtain the information they need.

[0702] A "means for registering user search preferences" refers to an element that has the function of allowing users to input specific preference information based on their interests and concerns, and then save that information in a database.

[0703] A "means for converting user input into prompts based on search preferences" refers to an element that has the function of converting questions or requests entered by the user into an appropriate prompt format based on pre-registered preference information.

[0704] A "generative AI model" is an artificial intelligence model used to generate responses from prompts, and a concrete example is a general conversational generative model.

[0705] "Generating means for generating a response using a converted prompt" refers to an element that has the function of generating an appropriate response from a converted prompt using a generation AI model.

[0706] A "display means for listing and displaying generated responses" refers to an element that has the function of visually organizing the generated responses and presenting them in a format that is easy for the user to understand.

[0707] A "terminal" is a device used by a user to access a system and input data, and specific examples include personal computers and smartphones.

[0708] A "front-end conversation server" is a server that processes user input information and preference information and generates appropriate prompts.

[0709] A "backend conversational generation AI server" is a server that receives prompts sent from a frontend conversation server and generates responses using a generation AI model.

[0710] A "frontend framework" is a software tool used to visually list and display the generated responses to the user; specific examples include React and Vue.js.

[0711] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated using a generative AI model. The following describes in detail how this system can be specifically implemented.

[0712] User search preference registration

[0713] First, the user accesses the front-end conversation server using their device. The user accesses the system's registration page via a browser or mobile app and enters their search preferences. For example, a user might specify that they "like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in a relational database (e.g., MySQL or PostgreSQL).

[0714] User input reception and prompt generation

[0715] Next, the user enters a question or request through the terminal (e.g., "I want to know about recent sunspot activity"). The front-end conversation server receives this input and generates an appropriate prompt based on pre-registered preference information. Specifically, if the user has registered "Optimistic Science News" as a preference, the prompt "Optimistic Science News: I want to know about recent sunspot activity" will be generated.

[0716] Generate response on backend server

[0717] The generated prompt is sent from the front-end conversation server to the back-end conversational generative AI server. The back-end conversational generative AI server receives this prompt and generates a response using a generative AI model (e.g., OpenAI's GPT-3). For example, it might generate a response such as, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0718] Listing and presentation of responses

[0719] The generated responses are sent again from the backend conversational AI server to the frontend conversation server. The frontend conversation server lists these responses and displays them visually to the user using a frontend framework such as React or Vue.js. This allows the user to see the necessary information at a glance.

[0720] Specific example

[0721] For example, consider a scenario where a user types "I want to know about recent technological advancements." If the user's search preference is set to "Technology news details," the front-end conversational server generates the prompt "Technology news details: I want to know about recent technological advancements." This prompt is sent to the back-end conversational generative AI server, where the generative AI model generates the response "Recent technological advancements are astonishing. There have been many innovations, especially in the fields of artificial intelligence and machine learning." This response is listed by the front-end conversational server, and the user reviews this information on their device screen.

[0722] This invention makes it possible to provide customized responses for each user, which is expected to improve response accuracy and user satisfaction. Furthermore, by listing responses, users can easily obtain information.

[0723] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0724] Step 1:

[0725] The user accesses the frontend conversation server from their device. The input is an HTTP request sent from the device, and a login screen is displayed. Upon the user logging in, user identification information is output.

[0726] Step 2:

[0727] The user enters their search preferences on their terminal and sends them to the front-end conversation server. The input includes preference information (e.g., "Science news, optimistic"). The front-end conversation server receives this and saves it to a database such as MySQL or PostgreSQL. Specifically, the preference information is saved to the database using the query INSERT INTO user_preferences (user_id, preference) VALUES (1, 'Science news, optimistic'). The output is the preference information saved in the database.

[0728] Step 3:

[0729] The user enters a question or request into the frontend conversation server. The user's question (e.g., "I want to know about recent sunspot activity") is sent from the terminal to the server as input. The frontend conversation server receives this input and generates a prompt based on the user's preferences. Specifically, it retrieves preference information using the query SELECT preference FROM user_preferences WHERE user_id=1 and generates the prompt "Science News Optimistic: I want to know about recent sunspot activity". The output is the generated prompt.

[0730] Step 4:

[0731] The frontend conversation server sends the generated prompt to the backend conversational AI server. The input includes the prompt "Science News Optimistic: I want to know about recent sunspot activity". The frontend conversation server sends the prompt using an HTTP POST request. Specifically, it sends the request `curl -X POST http: / / backend-ai.server / generate -d '{"prompt":"Science News Optimistic: I want to know about recent sunspot activity"}'`. The output is the prompt sent to the backend conversational AI server.

[0732] Step 5:

[0733] A backend conversational generative AI server receives a prompt and generates a response using a generative AI model. The input to the backend server is the prompt "Science News Optimistic: I want to know about recent sunspot activity." The generative AI model (e.g., GPT-3) analyzes the prompt and generates the response, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries." In concrete terms, the generative AI model processes the prompt, and the text generation engine creates the response. The output is the generated response.

[0734] Step 6:

[0735] The generated response is sent from the backend conversational generation AI server to the frontend conversation server. The input includes the generated response, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries." Specifically, the backend server sends the response as an HTTP response. The output is the generated response that arrived at the frontend conversation server.

[0736] Step 7:

[0737] The frontend conversation server lists the responses it receives and presents them to the user. The input includes the generated responses. The frontend conversation server uses a frontend framework such as React or Vue.js to list the responses and display them visually to the user. Specifically, the response list is rendered using HTML or JavaScript and displayed on the user's screen. The output is a list of responses that the user can visually review.

[0738] (Application Example 1)

[0739] Next, we will explain Application Example 1. In the following explanation, 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."

[0740] In conventional autonomous vehicles, passengers had limited means of receiving up-to-date information based on their interests and preferences in real time while traveling. This resulted in decreased passenger satisfaction and reduced efficiency in information acquisition. The present invention aims to solve these problems and provide a means for passengers to acquire highly personalized information in real time, even while traveling.

[0741] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0742] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses using the converted prompts, means for displaying a list of the generated responses, and means for transmitting the prompts generated based on the search preferences and user input to a backend server, and displaying the responses received from the backend server in a visual representation on the vehicle's infotainment system. This makes it possible for passengers to obtain and visually confirm personalized information in real time, even while on the move.

[0743] "User search preferences" refer to the topics, information sources, and tone of voice that users are interested in.

[0744] A "prompt" is a set of instructions generated based on user input, containing the information necessary for the server to generate a response.

[0745] "Generation means" refers to a system that has the function of generating a response using an artificial intelligence model based on a prompt.

[0746] "Display means" refers to a system that has the function of listing the generated responses and presenting them visually to the user.

[0747] A "backend server" refers to a system that receives prompts sent from a frontend server and generates responses using an artificial intelligence model.

[0748] An "infotainment system" refers to a system that provides information and entertainment for use inside a vehicle.

[0749] This invention is a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated by a backend server. The system for carrying out this invention uses the following hardware and software.

[0750] hardware

[0751] 1. Infotainment system for autonomous vehicles: A device that receives and displays user input.

[0752] 2. Frontend conversation server: A server that receives user search preferences and generates prompts.

[0753] 3. Backend conversational generation AI server: A server that receives generated prompts and generates responses.

[0754] software

[0755] 1. Flask: A framework for providing Web APIs.

[0756] 2. requests: A library for efficient communication between servers.

[0757] 3. Generative AI Model: An artificial intelligence model for generating responses based on prompts.

[0758] Program processing

[0759] The program processes the information as follows: First, the user accesses the front-end conversation server via the infotainment system and registers their search preferences. For example, the user can specify preferences such as "I like technology news and prefer detailed information." The front-end conversation server receives this preference information and stores it in its internal database.

[0760] Next, the user enters a question or request (e.g., "Tell me about the latest autonomous driving technology") via the infotainment system. The front-end conversational server receives this input and generates an appropriate prompt (e.g., "Technology News Details: Tell me about the latest autonomous driving technology") based on pre-registered preference information. The generated prompt is then sent to the back-end conversational generation AI server.

[0761] The backend conversational generative AI server receives this prompt and uses its internal generative AI model to generate a response. For example, it might generate a response such as, "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented." This generated response is then sent back to the frontend conversational server. The frontend conversational server lists these responses and displays them visualized on the infotainment system. This allows the user to see the necessary information at a glance.

[0762] Specific example

[0763] For example, if a passenger types "Tell me about the latest autonomous driving technology," the prompt will generate "Technology News Details: Tell me about the latest autonomous driving technology." The AI ​​model will then generate a response such as "The latest autonomous driving technology is advancing and new sensor technologies are being implemented," which will be displayed in the vehicle's infotainment system.

[0764] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0765] Step 1:

[0766] Users register their search preferences using the infotainment system of the autonomous vehicle. In this step, the user first enters their interests and information filtering criteria (e.g., "I like technology news and prefer detailed information"). This input data is sent to the front-end conversation server via the infotainment system. The front-end conversation server stores the received preference data in its internal database and associates it with the user ID.

[0767] Input: User's search preferences (e.g., "I like technology news and prefer detailed information")

[0768] Output: Preference information stored in the frontend conversation server's database.

[0769] Step 2:

[0770] The user enters a request for information they want to know (e.g., "Tell me about the latest autonomous driving technology") into the infotainment system. The infotainment system sends this to the front-end conversation server. The front-end conversation server retrieves pre-registered user preference information and combines it with the entered request to generate a new prompt. For example, it might become, "Technology News Details: Tell me about the latest autonomous driving technology."

[0771] Input: User request (e.g., "Please tell me about the latest autonomous driving technology")

[0772] Output: Generated prompt (Example: "Technical News Details: Tell me about the latest autonomous driving technologies")

[0773] Step 3:

[0774] The generated prompt is sent from the front-end conversational server to the back-end conversational generation AI server. The back-end conversational generation AI server receives this prompt and uses its internal generation AI model to generate a response based on the prompt. For example, a response such as "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented." might be generated.

[0775] Input: Generated prompt (Example: "Technical News Details: Tell me about the latest autonomous driving technology")

[0776] Output: Generated response (Example: "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented.")

[0777] Step 4:

[0778] The generated responses are sent from the backend conversational AI server to the frontend conversational server. The frontend conversational server converts the received responses into a visualized format and sends them to the infotainment system. The infotainment system lists these generated responses and displays them visually to the user, allowing the user to quickly see the information they need.

[0779] Input: Generated response (Example: "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented.")

[0780] Output: List of responses displayed on the infotainment system

[0781] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0782] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, further recognizes the user's emotions using an emotion engine, and lists and displays the responses generated by the backend server.

[0783] User search preference registration

[0784] First, the user accesses the front-end conversation server via their device and registers their search preferences. For example, a user can specify preferences such as "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in its internal database.

[0785] User input reception and prompt generation

[0786] Next, the user enters a question or request (e.g., "I want to know about recent sunspot activity") into the front-end conversation server and sends it. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information.

[0787] Emotion recognition by an emotion engine

[0788] Furthermore, the front-end conversation server uses an emotion engine to recognize the user's emotions from their input and past conversation data. For example, when a user types "I want to know about recent sunspot activity," the emotion engine analyzes the user's text and extracts emotions such as "excited" or "interested."

[0789] Prompt adjustment

[0790] The recognized emotional information is reflected in the prompts to generate more personalized prompts. For example, "Science News Optimistic Excited: I want to know about recent sunspot activity."

[0791] Generate response on backend server

[0792] The generated prompt is sent to the backend conversational generation AI server. The backend conversational generation AI server receives this prompt and uses its internal artificial intelligence model to generate a response. For example, it might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0793] Emotion-based response regulation

[0794] The front-end conversation server then uses the emotion engine to refine the generated response. For example, if the response is "Recent sunspot activity has been very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[0795] Listing and presentation of responses

[0796] The generated responses are sent back to the front-end conversation server, where they are listed and visually presented to the user. This allows the user to quickly see the information they need.

[0797] Specific example

[0798] For example, if a user types "I want to know about recent technological advancements," and their search preference is "Technology news details," and the emotion engine recognizes "Expectation," the front-end conversation server generates a prompt that reads "Technology news details Expectation: I want to know about recent technological advancements." This is sent to the back-end server, where the AI ​​model generates a response that reads, "Recent technological advancements are amazing. We're seeing a lot of innovation, especially in the fields of artificial intelligence and machine learning." This response is then adjusted to reflect the emotion of "Expectation," becoming something like, "It's like the future is taking shape now! We're seeing amazing advancements, especially in the fields of artificial intelligence and machine learning," and is then listed and displayed to the user.

[0799] This invention provides customized responses that reflect the emotions of each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide information to users in a format that is easy to view and understand.

[0800] The following describes the processing flow.

[0801] Step 1:

[0802] The user accesses the front-end conversation server using their device and registers their search preferences. For example, the user might input preferences such as "I like science news and prefer information with an optimistic tone" and send them to the front-end conversation server.

[0803] Step 2:

[0804] The front-end conversation server stores the preference information received from the user in an internal database. This allows each user's preferences to be managed individually.

[0805] Step 3:

[0806] The user uses their device to input and send questions or requests (e.g., "I want to know about recent sunspot activity") to the front-end conversation server.

[0807] Step 4:

[0808] The front-end conversation server receives user input and generates appropriate prompts based on pre-registered preference information. For example, it might generate a prompt such as "Science News Optimistic: I want to know about recent sunspot activity."

[0809] Step 5:

[0810] The front-end conversation server uses an emotion engine to recognize the user's emotions from their input and past conversation data. For example, when a user inputs "I want to know about recent sunspot activity," the emotion engine extracts emotions such as "excitement" and "interest."

[0811] Step 6:

[0812] The front-end conversation server incorporates recognized sentiment information into prompts to generate more personalized prompts. For example, "Science News, Optimistic, Excited: I want to know about recent sunspot activity."

[0813] Step 7:

[0814] The front-end conversation server sends the generated prompt to the back-end conversational AI server. The prompt reflects the user's preferences and emotions.

[0815] Step 8:

[0816] The backend conversational generation AI server receives a prompt and uses an artificial intelligence model to generate a response. For example, it might generate a response like, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0817] Step 9:

[0818] The backend conversational AI server generates responses, which are then sent to the frontend conversation server.

[0819] Step 10:

[0820] The front-end conversation server then uses the emotion engine to further refine the generated response. For example, if the response is "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[0821] Step 11:

[0822] The front-end conversation server lists the coordinated responses. For example, if there are multiple responses, they are organized for easier viewing.

[0823] Step 12:

[0824] The front-end conversation server displays a list of responses on the user's terminal. The user can view the information in a visually organized and easy-to-understand format.

[0825] (Example 2)

[0826] Next, we will describe Example 2. 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."

[0827] Conventional information retrieval systems have difficulty providing responses that reflect users' search preferences, and have been unable to quickly deliver appropriate content for the information users are seeking. Furthermore, the lack of response generation that takes user emotions into account results in low satisfaction with the responses.

[0828] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0829] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses using artificial intelligence with the converted prompts, means for recognizing the user's emotions during the response generation process and generating prompts that reflect those emotions, means for adjusting the responses generated using prompts that include emotion reflection, and display means for listing and displaying the generated responses. This makes it possible to generate personalized responses that reflect the user's preferences and emotions.

[0830] A "user" refers to a person who uses this system to search for information and obtain a response.

[0831] "Search preferences" refer to data that shows users' preferences and tendencies regarding the types of information, sources, and presentation methods they like.

[0832] A "prompt" refers to a set of instructions given to an artificial intelligence model, generated based on user input and search preferences.

[0833] "Artificial intelligence" refers to the technology that enables computers to mimic human intelligence, performing tasks such as learning, reasoning, and perception.

[0834] "Generation means" refers to the part that executes functions or processes for generating responses using user input and prompts.

[0835] "Emotion recognition" refers to technologies and methods that identify a user's emotions based on their input and past conversation data.

[0836] "Adjustment mechanisms" refer to the parts or processes that perform functions to adjust responses based on emotion recognition and make them more appropriate for the user.

[0837] "Display means" refers to functions or devices that visually provide the generated response to the user.

[0838] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, recognizes the user's emotions using an emotion engine, and displays the generated responses in a list. An embodiment for implementing this system is described below.

[0839] User search preference registration

[0840] Users access the front-end conversation server via their device and register their search preferences. Through a browser or application, users access a search preference settings page and input data on specific topics, sources, and tone. This data can be entered as, for example, "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in an internal database (e.g., MySQL or PostgreSQL).

[0841] User input reception and prompt generation

[0842] The user enters a question or request into the front-end conversation server and sends it. For example, the user might enter "I want to know about recent sunspot activity" and click the send button. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information. Program logic is used to generate this prompt.

[0843] Emotion recognition by an emotion engine

[0844] The front-end conversation server uses an emotion engine to recognize the user's emotions from user input and past conversation data. The emotion engine utilizes natural language processing libraries (e.g., NLTK and Spacy) to extract emotion labels such as "excited" or "interested" from the text.

[0845] Prompt adjustment

[0846] The system incorporates recognized emotional information into prompts to generate more personalized prompts. For example, it might adjust prompts to something like, "Science News, Optimistic, Excited: I want to know about recent sunspot activity." This adjustment is done by updating the prompt template.

[0847] Generate response on backend server

[0848] The front-end conversational server sends the generated prompt to the back-end conversational generative AI server. The back-end conversational generative AI server receives this prompt and uses its internal artificial intelligence model (e.g., generative AI model) to generate a response. For example, it might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0849] Emotion-based response regulation

[0850] The front-end conversation server then uses the emotion engine to refine the generated response. For example, if the response is "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[0851] Listing and presentation of responses

[0852] The generated responses are sent back to the front-end conversation server, where they are listed and visually presented to the user. The response list is reflected in an HTML template and displayed on the screen in a formatted manner. For example, if a user enters "I want to know about recent technological advancements," and the search preference is "Technology news details," and the sentiment engine recognizes "Expectations," the following prompt is generated: "Technology news details Expectations: I want to know about recent technological advancements." The back-end server then generates the response "Recent technological advancements are amazing. We're seeing a lot of innovation, especially in the fields of artificial intelligence and machine learning," which, after final adjustments, is displayed to the user as "It's like the future is taking shape now! We're seeing amazing advancements, especially in the fields of artificial intelligence and machine learning."

[0853] This invention provides customized responses that reflect the emotions of each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide users with the information they need in an easy-to-view and easy-to-understand format.

[0854] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0855] Step 1:

[0856] User search preference input

[0857] The user accesses the front-end conversation server via their device and enters their search preferences. For example, a user might access a search preference settings page using a browser or app and enter preferences such as "I like science news and prefer information with an optimistic tone" into a text box. The entered preferences are then sent from the device to the server in string format.

[0858] Input: User's search preferences (e.g., "I like science news and prefer information with an optimistic tone")

[0859] Output: Preference data sent to the front-end conversation server

[0860] Step 2:

[0861] Receiving and saving search preferences

[0862] The front-end conversation server receives preference information sent from the terminal and stores it in an internal database. Specifically, the front-end conversation server uses INSERT queries to save the received preference data to a database such as MySQL or PostgreSQL.

[0863] Input: Preference data received from the device

[0864] Output: Preference data stored in the database

[0865] Step 3:

[0866] User input reception

[0867] The user enters and sends questions or requests to the front-end conversation server. For example, the user might type "I want to know about recent sunspot activity" into the chat box and click the send button. This sends the user's request data from the device to the front-end conversation server.

[0868] Input: User request (e.g., "I want to know about recent sunspot activity")

[0869] Output: Request data sent to the frontend conversation server

[0870] Step 4:

[0871] Generate a view

[0872] The front-end conversation server receives user request data and retrieves pre-registered search preference data from the database. Then, it generates a prompt based on the retrieved preference data and the user request data. Specifically, it retrieves preference data from the database using a SELECT query and combines it with the request data to create a prompt such as "Science News Optimistic: I want to know about recent sunspot activity."

[0873] Input: User request data, search preference data

[0874] Output: Generated prompt (Example: "Science News Optimistic: I want to know about recent sunspot activity")

[0875] Step 5:

[0876] Recognition of emotions

[0877] The front-end conversation server sends the generated prompts to the emotion engine to recognize the user's emotions. Specifically, it uses natural language processing libraries (e.g., NLTK or Spacy) to extract emotion labels such as "excited" or "interested."

[0878] Input: Generated prompt

[0879] Output: Recognized emotion information (e.g., "excitement")

[0880] Step 6:

[0881] Prompt adjustment

[0882] The front-end conversation server incorporates recognized sentiment information into prompts, generating personalized prompts. Based on the sentiment information, it updates prompt templates, adjusting them to something like "Science News Optimistic Excited: I want to know about recent sunspot activity."

[0883] Input: Recognized emotion information, generated prompt

[0884] Output: Adjusted prompt (e.g., "Science News Optimistic Exciting: I want to know about recent sunspot activity")

[0885] Step 7:

[0886] Send a prompt

[0887] The front-end conversation server sends the prepared prompt to the back-end conversational generation AI server. Specifically, the prompt is sent via an HTTP POST request.

[0888] Input: Adjusted prompt

[0889] Output: Prompt sent to the backend conversational generation AI server

[0890] Step 8:

[0891] Response generation

[0892] The backend conversational generative AI server receives a prompt and generates a response using its internal artificial intelligence model (e.g., a generative AI model). For example, the model might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[0893] Input: Sent prompt

[0894] Output: Generated response (Example: "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries.")

[0895] Step 9:

[0896] Emotional regulation of responses

[0897] The front-end conversation server analyzes the generated response again with the emotion engine and adjusts the response to reflect the user's emotions. For example, if the generated response is "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the emotion "excitement" to "It's an exciting time, it feels like we're making new discoveries every day!"

[0898] Input: Generated response, recognized emotion information

[0899] Output: Adjusted response (e.g., "This is an exciting time, it feels like we're making new discoveries every day!")

[0900] Step 10:

[0901] Listing and presentation of responses

[0902] The front-end conversation server lists the prepared responses and presents them visually to the user. The response list is reflected in an HTML template and displayed on the screen in a formatted manner.

[0903] Input: Adjusted response

[0904] Output: List of responses displayed to the user

[0905] Through the steps described above, the system of the present invention provides responses that reflect emotions customized for each user, improving response accuracy and user satisfaction. Furthermore, by listing the responses, it provides users with the information they need in an easy-to-view and easy-to-understand format.

[0906] (Application Example 2)

[0907] Next, we will explain application example 2. In the following explanation, 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."

[0908] Traditional virtual stores face the challenge of not being able to provide personalized product suggestions that fully reflect individual user preferences and emotions, making it difficult to improve user satisfaction. Furthermore, product information displayed without considering user emotions makes it difficult to stimulate purchasing intent at the appropriate time. As a result, the user's purchasing experience becomes monotonous, making it difficult to maintain their interest.

[0909] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0910] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for recognizing the user's emotions, means for generating prompts adjusted by reflecting the recognized emotional information in the prompts, means for generating responses using the generated prompts, means for adjusting the generated responses based on the emotional information, and means for displaying a list of the adjusted responses. This enables personalized product suggestions that reflect the user's preferences and emotions, thereby improving user satisfaction and the purchasing experience.

[0911] "Search preferences" refer to data that shows a user's preferences and interests regarding specific information or products.

[0912] A "prompt" is a set of instructions generated based on user input and preference information, and serves as input for generating a response in an artificial intelligence model.

[0913] "User input" refers to text data that includes questions and requests made by the user to the system.

[0914] "Emotional information" refers to emotional data extracted from user text input and past conversation data.

[0915] A "generation method" refers to a means that allows an artificial intelligence model to generate a response based on input data such as prompts and emotional information.

[0916] A "display means" refers to a means that has the function of visually presenting the generated response to the user.

[0917] This invention relates to a system that registers a user's search preferences, generates prompts based on those preferences, recognizes the user's emotions using an emotion engine, and displays a list of responses generated by a backend server. This system is implemented as a personalized virtual shop application.

[0918] System Configuration

[0919] The server includes the following measures:

[0920] 1. Means for registering user search preferences

[0921] 2. Means for converting user input into prompts based on search preferences

[0922] 3. Means of recognizing user emotions

[0923] 4. Means for generating adjusted prompts by reflecting recognized emotional information in the prompts.

[0924] 5. Generation means for generating a response using the generated prompt.

[0925] 6. Means for adjusting the generated response based on emotional information

[0926] 7. Display means for listing and displaying the adjusted responses.

[0927] Program generation

[0928] The server implements these measures using Python programs. Details of each measure are shown below.

[0929] A method for registering user search preferences

[0930] Users register their search preferences via a smartphone app. Specifically, they select their favorite product categories, preferred styles, and information sources, and this data is stored in a database. The database uses services such as MySQL or Firebase.

[0931] A means of converting user input into prompts based on search preferences.

[0932] When a user enters a question or request (e.g., "I want to know this month's recommended fashion items") into the smartphone app, that input is converted into a prompt. This prompt is generated based on the user's search preferences and constructed according to a specific format.

[0933] Means of recognizing user emotions

[0934] The EmotionEngine is used to analyze the emotions expressed in the user's input text. This emotional information (e.g., "expectation") is then used to generate prompts.

[0935] A means of generating adjusted prompts by reflecting recognized emotional information in the prompts.

[0936] Recognized emotion information is added to the prompt to generate more personalized prompt messages. For example, a prompt such as "Fashion Trend Expectation: I want to know this month's recommended fashion items" might be generated.

[0937] Generation means for generating a response using the generated prompt.

[0938] The generated prompt is sent to an artificial intelligence model (e.g., GPT-3) in the backend, and an appropriate response is generated. The response generation means sends prompts to the artificial intelligence model via an API and receives responses.

[0939] A means of adjusting the generated response based on emotional information.

[0940] The generated responses are then refined using the emotion engine to reflect the user's emotions. For example, a response like "This month's fashion is full of new trends!" might be adjusted to something like, "It's like being at a fashion show! The new fall collection is especially stylish and exceeds expectations!"

[0941] Display means for listing and displaying the adjusted responses.

[0942] The adjusted responses are displayed in a list format on the smartphone app's user interface. This allows users to see the necessary information at a glance.

[0943] Specific example

[0944] For example, if a user enters "I want to know this month's recommended fashion items," their search preference will be recognized as "fashion trends" and their emotion as "expectation." In this case,

[0945] Prompt: "Fashion Trend Expectations: I want to know this month's recommended fashion items."

[0946] Generated response: "This month's fashion is full of new trends!"

[0947] Adjusted response: "It's like being at a fashion show! The new fall collection is especially stylish and exceeds expectations!"

[0948] In this way, responses that reflect the user's preferences and emotions are provided.

[0949] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0950] Step 1: Register the user's search preferences.

[0951] Users input their search preferences (e.g., "fashion trends" or "technology news") via their smartphone. The device sends this information to a front-end server (conversation server), which stores the preference information in a database. The input data consists of the user ID and preference information, while the output data is the preference data stored in the database.

[0952] Step 2: Accept user input and generate prompts

[0953] The user sends a question or request from their device (e.g., "I want to know this month's recommended fashion items"). The device sends this to the front-end server, which generates a prompt based on the user's preference information. The input data consists of the user's question or request and pre-registered preference information, while the output data is the generated prompt text.

[0954] Step 3: Recognize the user's emotions

[0955] The emotion engine on the server recognizes emotions (e.g., "expectation" or "excitement") from the user's input text. The input data is the user's input text, and the output data is the recognized emotion information. Specifically, the emotion engine performs text analysis and extracts specific emotions.

[0956] Step 4: Adjust prompts using emotional information

[0957] The server incorporates the recognized emotion information into the prompt text to generate an adjusted prompt text. The input data consists of the generated prompt text and the recognized emotion information, while the output data is the adjusted prompt text. Specifically, the server performs processing such as adding emotion keywords to the prompt text.

[0958] Step 5: Send a prompt to the backend server and generate a response.

[0959] The server sends a pre-tuned prompt to a backend generation AI model (e.g., GPT-3) to generate an appropriate response. The input data is the pre-tuned prompt, and the output data is the generated response. Specifically, the prompt is sent to the AI ​​model via an API, and the response is retrieved.

[0960] Step 6: Adjust the generated response based on emotional information.

[0961] The server refurbishes the responses generated by reusing the emotion engine, modifying them to reflect the user's emotions. The input data consists of the generated response and recognized emotion information, while the output data is the refined response. Specifically, emotion keywords and expressions are added to the response.

[0962] Step 7: List and display the adjusted responses.

[0963] The server displays the adjusted responses in a list format on the user's smartphone. The input data is the adjusted response text, and the output data is the list of responses displayed on the device. Specifically, the response text is displayed in a visually easy-to-understand format with a rich user interface.

[0964] By following these steps, it becomes possible to provide personalized product suggestions that reflect the user's preferences and emotions.

[0965] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0966] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0967] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0968] [Fourth Embodiment]

[0969] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0970] As shown in Figure 7, the 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.

[0971] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0972] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0973] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0974] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0975] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0976] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0977] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0978] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0979] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0980] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0981] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0982] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated by a backend server.

[0983] User search preference registration

[0984] First, the user accesses the front-end conversation server via their device and registers their search preferences. For example, a user can specify preferences such as "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in its internal database.

[0985] User input reception and prompt generation

[0986] Next, the user enters a question or request (e.g., "I want to know about recent sunspot activity") into the front-end conversation server. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information.

[0987] Generate response on backend server

[0988] The generated prompt is sent to the backend conversational generation AI server. The backend conversational generation AI server receives this prompt and uses its internal artificial intelligence model to generate a response. For example, a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," might be generated.

[0989] Listing and presentation of responses

[0990] The generated responses are sent back to the front-end conversation server. The front-end conversation server lists these responses and presents them visually to the user. This allows the user to see the necessary information at a glance.

[0991] Specific example

[0992] For example, if a user types "I want to know about recent technological advancements," and their search preference is "Technology News Details," the front-end conversation server generates the prompt "Technology News Details: I want to know about recent technological advancements." This is sent to the back-end server, where the AI ​​model generates a response such as "Recent technological advancements are amazing. We've seen a lot of innovation, especially in the fields of artificial intelligence and machine learning." This response is then listed by the front-end server and displayed to the user.

[0993] This invention makes it possible to provide customized responses for each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide information to users in a format that is easy to view and understand.

[0994] The following describes the processing flow.

[0995] Step 1:

[0996] The user accesses the front-end conversation server using their device and registers their search preferences. For example, the user might input preferences such as "I like science news and prefer information with an optimistic tone" and send them to the front-end conversation server.

[0997] Step 2:

[0998] The front-end conversation server stores the preference information received from the user in an internal database. This allows each user's preferences to be managed individually.

[0999] Step 3:

[1000] The user uses their device to input and send questions or requests (e.g., "I want to know about recent sunspot activity") to the front-end conversation server.

[1001] Step 4:

[1002] The front-end conversation server receives user input and retrieves pre-registered preference information. Based on this, it converts the entered questions and requests into appropriate prompts (e.g., "Science News Optimistic: I want to know about recent sunspot activity").

[1003] Step 5:

[1004] The front-end conversation server sends the generated prompt to the back-end conversational AI server. The prompt reflects the user's preferences.

[1005] Step 6:

[1006] The backend conversational generation AI server receives a prompt and uses an artificial intelligence model to generate a response. For example, it might generate a response like, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[1007] Step 7:

[1008] The backend conversational AI server generates responses, which are then sent to the frontend conversation server.

[1009] Step 8:

[1010] The front-end conversation server lists the responses received from the back-end conversational AI server. For example, if there are multiple responses, they are organized for easier viewing.

[1011] Step 9:

[1012] The front-end conversation server displays a list of responses on the user's terminal. The user can view the information in a visually organized and easy-to-understand format.

[1013] (Example 1)

[1014] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1015] Conventional systems fail to adequately provide information based on user search preferences, making it difficult to improve the quality of the user experience. Furthermore, the lack of a mechanism for properly listing and displaying generated responses means users cannot quickly obtain the information they need.

[1016] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1017] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses from the prompts using a generative AI model, and means for listing and displaying the generated responses. This enables the provision of highly accurate, customized information to the user, allowing the user to quickly obtain the information they need.

[1018] A "means for registering user search preferences" refers to an element that has the function of allowing users to input specific preference information based on their interests and concerns, and then save that information in a database.

[1019] A "means for converting user input into prompts based on search preferences" refers to an element that has the function of converting questions or requests entered by the user into an appropriate prompt format based on pre-registered preference information.

[1020] A "generative AI model" is an artificial intelligence model used to generate responses from prompts, and a concrete example is a general conversational generative model.

[1021] "Generating means for generating a response using a converted prompt" refers to an element that has the function of generating an appropriate response from a converted prompt using a generation AI model.

[1022] A "display means for listing and displaying generated responses" refers to an element that has the function of visually organizing the generated responses and presenting them in a format that is easy for the user to understand.

[1023] A "terminal" is a device used by a user to access a system and input data, and specific examples include personal computers and smartphones.

[1024] A "front-end conversation server" is a server that processes user input information and preference information and generates appropriate prompts.

[1025] A "backend conversational generation AI server" is a server that receives prompts sent from a frontend conversation server and generates responses using a generation AI model.

[1026] A "frontend framework" is a software tool used to visually list and display the generated responses to the user; specific examples include React and Vue.js.

[1027] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated using a generative AI model. The following describes in detail how this system can be specifically implemented.

[1028] User search preference registration

[1029] First, the user accesses the front-end conversation server using their device. The user accesses the system's registration page via a browser or mobile app and enters their search preferences. For example, a user might specify that they "like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in a relational database (e.g., MySQL or PostgreSQL).

[1030] User input reception and prompt generation

[1031] Next, the user enters a question or request through the terminal (e.g., "I want to know about recent sunspot activity"). The front-end conversation server receives this input and generates an appropriate prompt based on pre-registered preference information. Specifically, if the user has registered "Optimistic Science News" as a preference, the prompt "Optimistic Science News: I want to know about recent sunspot activity" will be generated.

[1032] Generate response on backend server

[1033] The generated prompt is sent from the front-end conversation server to the back-end conversational generative AI server. The back-end conversational generative AI server receives this prompt and generates a response using a generative AI model (e.g., OpenAI's GPT-3). For example, it might generate a response such as, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[1034] Listing and presentation of responses

[1035] The generated responses are sent again from the backend conversational AI server to the frontend conversation server. The frontend conversation server lists these responses and displays them visually to the user using a frontend framework such as React or Vue.js. This allows the user to see the necessary information at a glance.

[1036] Specific example

[1037] For example, consider a scenario where a user types "I want to know about recent technological advancements." If the user's search preference is set to "Technology news details," the front-end conversational server generates the prompt "Technology news details: I want to know about recent technological advancements." This prompt is sent to the back-end conversational generative AI server, where the generative AI model generates the response "Recent technological advancements are astonishing. There have been many innovations, especially in the fields of artificial intelligence and machine learning." This response is listed by the front-end conversational server, and the user reviews this information on their device screen.

[1038] This invention makes it possible to provide customized responses for each user, which is expected to improve response accuracy and user satisfaction. Furthermore, by listing responses, users can easily obtain information.

[1039] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1040] Step 1:

[1041] The user accesses the frontend conversation server from their device. The input is an HTTP request sent from the device, and a login screen is displayed. Upon the user logging in, user identification information is output.

[1042] Step 2:

[1043] The user enters their search preferences on their terminal and sends them to the front-end conversation server. The input includes preference information (e.g., "Science news, optimistic"). The front-end conversation server receives this and saves it to a database such as MySQL or PostgreSQL. Specifically, the preference information is saved to the database using the query INSERT INTO user_preferences (user_id, preference) VALUES (1, 'Science news, optimistic'). The output is the preference information saved in the database.

[1044] Step 3:

[1045] The user enters a question or request into the frontend conversation server. The user's question (e.g., "I want to know about recent sunspot activity") is sent from the terminal to the server as input. The frontend conversation server receives this input and generates a prompt based on the user's preferences. Specifically, it retrieves preference information using the query SELECT preference FROM user_preferences WHERE user_id=1 and generates the prompt "Science News Optimistic: I want to know about recent sunspot activity". The output is the generated prompt.

[1046] Step 4:

[1047] The frontend conversation server sends the generated prompt to the backend conversational AI server. The input includes the prompt "Science News Optimistic: I want to know about recent sunspot activity". The frontend conversation server sends the prompt using an HTTP POST request. Specifically, it sends the request `curl -X POST http: / / backend-ai.server / generate -d '{"prompt":"Science News Optimistic: I want to know about recent sunspot activity"}'`. The output is the prompt sent to the backend conversational AI server.

[1048] Step 5:

[1049] A backend conversational generative AI server receives a prompt and generates a response using a generative AI model. The input to the backend server is the prompt "Science News Optimistic: I want to know about recent sunspot activity." The generative AI model (e.g., GPT-3) analyzes the prompt and generates the response, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries." In concrete terms, the generative AI model processes the prompt, and the text generation engine creates the response. The output is the generated response.

[1050] Step 6:

[1051] The generated response is sent from the backend conversational generation AI server to the frontend conversation server. The input includes the generated response, "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries." Specifically, the backend server sends the response as an HTTP response. The output is the generated response that arrived at the frontend conversation server.

[1052] Step 7:

[1053] The frontend conversation server lists the responses it receives and presents them to the user. The input includes the generated responses. The frontend conversation server uses a frontend framework such as React or Vue.js to list the responses and display them visually to the user. Specifically, the response list is rendered using HTML or JavaScript and displayed on the user's screen. The output is a list of responses that the user can visually review.

[1054] (Application Example 1)

[1055] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1056] In conventional autonomous vehicles, passengers had limited means of receiving up-to-date information based on their interests and preferences in real time while traveling. This resulted in decreased passenger satisfaction and reduced efficiency in information acquisition. The present invention aims to solve these problems and provide a means for passengers to acquire highly personalized information in real time, even while traveling.

[1057] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1058] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses using the converted prompts, means for displaying a list of the generated responses, and means for transmitting the prompts generated based on the search preferences and user input to a backend server, and displaying the responses received from the backend server in a visual representation on the vehicle's infotainment system. This makes it possible for passengers to obtain and visually confirm personalized information in real time, even while on the move.

[1059] "User search preferences" refer to the topics, information sources, and tone of voice that users are interested in.

[1060] A "prompt" is a set of instructions generated based on user input, containing the information necessary for the server to generate a response.

[1061] "Generation means" refers to a system that has the function of generating a response using an artificial intelligence model based on a prompt.

[1062] "Display means" refers to a system that has the function of listing the generated responses and presenting them visually to the user.

[1063] A "backend server" refers to a system that receives prompts sent from a frontend server and generates responses using an artificial intelligence model.

[1064] An "infotainment system" refers to a system that provides information and entertainment for use inside a vehicle.

[1065] This invention is a system that registers a user's search preferences, converts user input into prompts based on those preferences, and displays a list of responses generated by a backend server. The system for carrying out this invention uses the following hardware and software.

[1066] hardware

[1067] 1. Infotainment system for autonomous vehicles: A device that receives and displays user input.

[1068] 2. Frontend conversation server: A server that receives user search preferences and generates prompts.

[1069] 3. Backend conversational generation AI server: A server that receives generated prompts and generates responses.

[1070] software

[1071] 1. Flask: A framework for providing Web APIs.

[1072] 2. requests: A library for efficient communication between servers.

[1073] 3. Generative AI Model: An artificial intelligence model for generating responses based on prompts.

[1074] Program processing

[1075] The program processes the information as follows: First, the user accesses the front-end conversation server via the infotainment system and registers their search preferences. For example, the user can specify preferences such as "I like technology news and prefer detailed information." The front-end conversation server receives this preference information and stores it in its internal database.

[1076] Next, the user enters a question or request (e.g., "Tell me about the latest autonomous driving technology") via the infotainment system. The front-end conversational server receives this input and generates an appropriate prompt (e.g., "Technology News Details: Tell me about the latest autonomous driving technology") based on pre-registered preference information. The generated prompt is then sent to the back-end conversational generation AI server.

[1077] The backend conversational generative AI server receives this prompt and uses its internal generative AI model to generate a response. For example, it might generate a response such as, "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented." This generated response is then sent back to the frontend conversational server. The frontend conversational server lists these responses and displays them visualized on the infotainment system. This allows the user to see the necessary information at a glance.

[1078] Specific example

[1079] For example, if a passenger types "Tell me about the latest autonomous driving technology," the prompt will generate "Technology News Details: Tell me about the latest autonomous driving technology." The AI ​​model will then generate a response such as "The latest autonomous driving technology is advancing and new sensor technologies are being implemented," which will be displayed in the vehicle's infotainment system.

[1080] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1081] Step 1:

[1082] Users register their search preferences using the infotainment system of the autonomous vehicle. In this step, the user first enters their interests and information filtering criteria (e.g., "I like technology news and prefer detailed information"). This input data is sent to the front-end conversation server via the infotainment system. The front-end conversation server stores the received preference data in its internal database and associates it with the user ID.

[1083] Input: User's search preferences (e.g., "I like technology news and prefer detailed information")

[1084] Output: Preference information stored in the frontend conversation server's database.

[1085] Step 2:

[1086] The user enters a request for information they want to know (e.g., "Tell me about the latest autonomous driving technology") into the infotainment system. The infotainment system sends this to the front-end conversation server. The front-end conversation server retrieves pre-registered user preference information and combines it with the entered request to generate a new prompt. For example, it might become, "Technology News Details: Tell me about the latest autonomous driving technology."

[1087] Input: User request (e.g., "Please tell me about the latest autonomous driving technology")

[1088] Output: Generated prompt (Example: "Technical News Details: Tell me about the latest autonomous driving technologies")

[1089] Step 3:

[1090] The generated prompt is sent from the front-end conversational server to the back-end conversational generation AI server. The back-end conversational generation AI server receives this prompt and uses its internal generation AI model to generate a response based on the prompt. For example, a response such as "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented." might be generated.

[1091] Input: Generated prompt (Example: "Technical News Details: Tell me about the latest autonomous driving technology")

[1092] Output: Generated response (Example: "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented.")

[1093] Step 4:

[1094] The generated responses are sent from the backend conversational AI server to the frontend conversational server. The frontend conversational server converts the received responses into a visualized format and sends them to the infotainment system. The infotainment system lists these generated responses and displays them visually to the user, allowing the user to quickly see the information they need.

[1095] Input: Generated response (Example: "The latest autonomous driving technology is advancing, and new sensor technologies are being implemented.")

[1096] Output: List of responses displayed on the infotainment system

[1097] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1098] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, further recognizes the user's emotions using an emotion engine, and lists and displays the responses generated by the backend server.

[1099] User search preference registration

[1100] First, the user accesses the front-end conversation server via their device and registers their search preferences. For example, a user can specify preferences such as "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in its internal database.

[1101] User input reception and prompt generation

[1102] Next, the user enters a question or request (e.g., "I want to know about recent sunspot activity") into the front-end conversation server and sends it. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information.

[1103] Emotion recognition by an emotion engine

[1104] Furthermore, the front-end conversation server uses an emotion engine to recognize the user's emotions from their input and past conversation data. For example, when a user types "I want to know about recent sunspot activity," the emotion engine analyzes the user's text and extracts emotions such as "excited" or "interested."

[1105] Prompt adjustment

[1106] The recognized emotional information is reflected in the prompts to generate more personalized prompts. For example, "Science News Optimistic Excited: I want to know about recent sunspot activity."

[1107] Generate response on backend server

[1108] The generated prompt is sent to the backend conversational generation AI server. The backend conversational generation AI server receives this prompt and uses its internal artificial intelligence model to generate a response. For example, it might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[1109] Emotion-based response regulation

[1110] The front-end conversation server then uses the emotion engine to refine the generated response. For example, if the response is "Recent sunspot activity has been very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[1111] Listing and presentation of responses

[1112] The generated responses are sent back to the front-end conversation server, where they are listed and visually presented to the user. This allows the user to quickly see the information they need.

[1113] Specific example

[1114] For example, if a user types "I want to know about recent technological advancements," and their search preference is "Technology news details," and the emotion engine recognizes "Expectation," the front-end conversation server generates a prompt that reads "Technology news details Expectation: I want to know about recent technological advancements." This is sent to the back-end server, where the AI ​​model generates a response that reads, "Recent technological advancements are amazing. We're seeing a lot of innovation, especially in the fields of artificial intelligence and machine learning." This response is then adjusted to reflect the emotion of "Expectation," becoming something like, "It's like the future is taking shape now! We're seeing amazing advancements, especially in the fields of artificial intelligence and machine learning," and is then listed and displayed to the user.

[1115] This invention provides customized responses that reflect the emotions of each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide information to users in a format that is easy to view and understand.

[1116] The following describes the processing flow.

[1117] Step 1:

[1118] The user accesses the front-end conversation server using their device and registers their search preferences. For example, the user might input preferences such as "I like science news and prefer information with an optimistic tone" and send them to the front-end conversation server.

[1119] Step 2:

[1120] The front-end conversation server stores the preference information received from the user in an internal database. This allows each user's preferences to be managed individually.

[1121] Step 3:

[1122] The user uses their device to input and send questions or requests (e.g., "I want to know about recent sunspot activity") to the front-end conversation server.

[1123] Step 4:

[1124] The front-end conversation server receives user input and generates appropriate prompts based on pre-registered preference information. For example, it might generate a prompt such as "Science News Optimistic: I want to know about recent sunspot activity."

[1125] Step 5:

[1126] The front-end conversation server uses an emotion engine to recognize the user's emotions from their input and past conversation data. For example, when a user inputs "I want to know about recent sunspot activity," the emotion engine extracts emotions such as "excitement" and "interest."

[1127] Step 6:

[1128] The front-end conversation server incorporates recognized sentiment information into prompts to generate more personalized prompts. For example, "Science News, Optimistic, Excited: I want to know about recent sunspot activity."

[1129] Step 7:

[1130] The front-end conversation server sends the generated prompt to the back-end conversational AI server. The prompt reflects the user's preferences and emotions.

[1131] Step 8:

[1132] The backend conversational generation AI server receives a prompt and uses an artificial intelligence model to generate a response. For example, it might generate a response like, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[1133] Step 9:

[1134] The backend conversational AI server generates responses, which are then sent to the frontend conversation server.

[1135] Step 10:

[1136] The front-end conversation server then uses the emotion engine to further refine the generated response. For example, if the response is "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[1137] Step 11:

[1138] The front-end conversation server lists the coordinated responses. For example, if there are multiple responses, they are organized for easier viewing.

[1139] Step 12:

[1140] The front-end conversation server displays a list of responses on the user's terminal. The user can view the information in a visually organized and easy-to-understand format.

[1141] (Example 2)

[1142] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1143] Conventional information retrieval systems have difficulty providing responses that reflect users' search preferences, and have been unable to quickly deliver appropriate content for the information users are seeking. Furthermore, the lack of response generation that takes user emotions into account results in low satisfaction with the responses.

[1144] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1145] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for generating responses using artificial intelligence with the converted prompts, means for recognizing the user's emotions during the response generation process and generating prompts that reflect those emotions, means for adjusting the responses generated using prompts that include emotion reflection, and display means for listing and displaying the generated responses. This makes it possible to generate personalized responses that reflect the user's preferences and emotions.

[1146] A "user" refers to a person who uses this system to search for information and obtain a response.

[1147] "Search preferences" refer to data that shows users' preferences and tendencies regarding the types of information, sources, and presentation methods they like.

[1148] A "prompt" refers to a set of instructions given to an artificial intelligence model, generated based on user input and search preferences.

[1149] "Artificial intelligence" refers to the technology that enables computers to mimic human intelligence, performing tasks such as learning, reasoning, and perception.

[1150] "Generation means" refers to the part that executes functions or processes for generating responses using user input and prompts.

[1151] "Emotion recognition" refers to technologies and methods that identify a user's emotions based on their input and past conversation data.

[1152] "Adjustment mechanisms" refer to the parts or processes that perform functions to adjust responses based on emotion recognition and make them more appropriate for the user.

[1153] "Display means" refers to functions or devices that visually provide the generated response to the user.

[1154] This invention relates to a system that registers a user's search preferences, converts user input into prompts based on those preferences, recognizes the user's emotions using an emotion engine, and displays the generated responses in a list. An embodiment for implementing this system is described below.

[1155] User search preference registration

[1156] Users access the front-end conversation server via their device and register their search preferences. Through a browser or application, users access a search preference settings page and input data on specific topics, sources, and tone. This data can be entered as, for example, "I like science news and prefer information with an optimistic tone." The front-end conversation server receives this preference information and stores it in an internal database (e.g., MySQL or PostgreSQL).

[1157] User input reception and prompt generation

[1158] The user enters a question or request into the front-end conversation server and sends it. For example, the user might enter "I want to know about recent sunspot activity" and click the send button. The front-end conversation server receives this input and generates an appropriate prompt (e.g., "Science News Optimistic: I want to know about recent sunspot activity") based on pre-registered preference information. Program logic is used to generate this prompt.

[1159] Emotion recognition by an emotion engine

[1160] The front-end conversation server uses an emotion engine to recognize the user's emotions from user input and past conversation data. The emotion engine utilizes natural language processing libraries (e.g., NLTK and Spacy) to extract emotion labels such as "excited" or "interested" from the text.

[1161] Prompt adjustment

[1162] The system incorporates recognized emotional information into prompts to generate more personalized prompts. For example, it might adjust prompts to something like, "Science News, Optimistic, Excited: I want to know about recent sunspot activity." This adjustment is done by updating the prompt template.

[1163] Generate response on backend server

[1164] The front-end conversational server sends the generated prompt to the back-end conversational generative AI server. The back-end conversational generative AI server receives this prompt and uses its internal artificial intelligence model (e.g., generative AI model) to generate a response. For example, it might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[1165] Emotion-based response regulation

[1166] The front-end conversation server then uses the emotion engine to refine the generated response. For example, if the response is "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the user's emotion of "excitement" and become "It's such an exciting time, it feels like we're making new discoveries every day!"

[1167] Listing and presentation of responses

[1168] The generated responses are sent back to the front-end conversation server, where they are listed and visually presented to the user. The response list is reflected in an HTML template and displayed on the screen in a formatted manner. For example, if a user enters "I want to know about recent technological advancements," and the search preference is "Technology news details," and the sentiment engine recognizes "Expectations," the following prompt is generated: "Technology news details Expectations: I want to know about recent technological advancements." The back-end server then generates the response "Recent technological advancements are amazing. We're seeing a lot of innovation, especially in the fields of artificial intelligence and machine learning," which, after final adjustments, is displayed to the user as "It's like the future is taking shape now! We're seeing amazing advancements, especially in the fields of artificial intelligence and machine learning."

[1169] This invention provides customized responses that reflect the emotions of each user, thereby improving response accuracy and user satisfaction. Furthermore, by listing responses, it becomes possible to provide users with the information they need in an easy-to-view and easy-to-understand format.

[1170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1171] Step 1:

[1172] User search preference input

[1173] The user accesses the front-end conversation server via their device and enters their search preferences. For example, a user might access a search preference settings page using a browser or app and enter preferences such as "I like science news and prefer information with an optimistic tone" into a text box. The entered preferences are then sent from the device to the server in string format.

[1174] Input: User's search preferences (e.g., "I like science news and prefer information with an optimistic tone")

[1175] Output: Preference data sent to the front-end conversation server

[1176] Step 2:

[1177] Receiving and saving search preferences

[1178] The front-end conversation server receives preference information sent from the terminal and stores it in an internal database. Specifically, the front-end conversation server uses INSERT queries to save the received preference data to a database such as MySQL or PostgreSQL.

[1179] Input: Preference data received from the device

[1180] Output: Preference data stored in the database

[1181] Step 3:

[1182] User input reception

[1183] The user enters and sends questions or requests to the front-end conversation server. For example, the user might type "I want to know about recent sunspot activity" into the chat box and click the send button. This sends the user's request data from the device to the front-end conversation server.

[1184] Input: User request (e.g., "I want to know about recent sunspot activity")

[1185] Output: Request data sent to the frontend conversation server

[1186] Step 4:

[1187] Generate a view

[1188] The front-end conversation server receives user request data and retrieves pre-registered search preference data from the database. Then, it generates a prompt based on the retrieved preference data and the user request data. Specifically, it retrieves preference data from the database using a SELECT query and combines it with the request data to create a prompt such as "Science News Optimistic: I want to know about recent sunspot activity."

[1189] Input: User request data, search preference data

[1190] Output: Generated prompt (Example: "Science News Optimistic: I want to know about recent sunspot activity")

[1191] Step 5:

[1192] Recognition of emotions

[1193] The front-end conversation server sends the generated prompts to the emotion engine to recognize the user's emotions. Specifically, it uses natural language processing libraries (e.g., NLTK or Spacy) to extract emotion labels such as "excited" or "interested."

[1194] Input: Generated prompt

[1195] Output: Recognized emotion information (e.g., "excitement")

[1196] Step 6:

[1197] Prompt adjustment

[1198] The front-end conversation server incorporates recognized sentiment information into prompts, generating personalized prompts. Based on the sentiment information, it updates prompt templates, adjusting them to something like "Science News Optimistic Excited: I want to know about recent sunspot activity."

[1199] Input: Recognized emotion information, generated prompt

[1200] Output: Adjusted prompt (e.g., "Science News Optimistic Exciting: I want to know about recent sunspot activity")

[1201] Step 7:

[1202] Send a prompt

[1203] The front-end conversation server sends the prepared prompt to the back-end conversational generation AI server. Specifically, the prompt is sent via an HTTP POST request.

[1204] Input: Adjusted prompt

[1205] Output: Prompt sent to the backend conversational generation AI server

[1206] Step 8:

[1207] Response generation

[1208] The backend conversational generative AI server receives a prompt and generates a response using its internal artificial intelligence model (e.g., a generative AI model). For example, the model might generate a response such as, "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries."

[1209] Input: Sent prompt

[1210] Output: Generated response (Example: "Recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries.")

[1211] Step 9:

[1212] Emotional regulation of responses

[1213] The front-end conversation server analyzes the generated response again with the emotion engine and adjusts the response to reflect the user's emotions. For example, if the generated response is "The recent sunspot activity is very interesting! The sun is in an active phase, and we can expect new discoveries," it will be adjusted to reflect the emotion "excitement" to "It's an exciting time, it feels like we're making new discoveries every day!"

[1214] Input: Generated response, recognized emotion information

[1215] Output: Adjusted response (e.g., "This is an exciting time, it feels like we're making new discoveries every day!")

[1216] Step 10:

[1217] Listing and presentation of responses

[1218] The front-end conversation server lists the prepared responses and presents them visually to the user. The response list is reflected in an HTML template and displayed on the screen in a formatted manner.

[1219] Input: Adjusted response

[1220] Output: List of responses displayed to the user

[1221] Through the steps described above, the system of the present invention provides responses that reflect emotions customized for each user, improving response accuracy and user satisfaction. Furthermore, by listing the responses, it provides users with the information they need in an easy-to-view and easy-to-understand format.

[1222] (Application Example 2)

[1223] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1224] Traditional virtual stores face the challenge of not being able to provide personalized product suggestions that fully reflect individual user preferences and emotions, making it difficult to improve user satisfaction. Furthermore, product information displayed without considering user emotions makes it difficult to stimulate purchasing intent at the appropriate time. As a result, the user's purchasing experience becomes monotonous, making it difficult to maintain their interest.

[1225] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1226] In this invention, the server includes means for registering the user's search preferences, means for converting user input into prompts based on the search preferences, means for recognizing the user's emotions, means for generating prompts adjusted by reflecting the recognized emotional information in the prompts, means for generating responses using the generated prompts, means for adjusting the generated responses based on the emotional information, and means for displaying a list of the adjusted responses. This enables personalized product suggestions that reflect the user's preferences and emotions, thereby improving user satisfaction and the purchasing experience.

[1227] "Search preferences" refer to data that shows a user's preferences and interests regarding specific information or products.

[1228] A "prompt" is a set of instructions generated based on user input and preference information, and serves as input for generating a response in an artificial intelligence model.

[1229] "User input" refers to text data that includes questions and requests made by the user to the system.

[1230] "Emotional information" refers to emotional data extracted from user text input and past conversation data.

[1231] A "generation method" refers to a means that allows an artificial intelligence model to generate a response based on input data such as prompts and emotional information.

[1232] A "display means" refers to a means that has the function of visually presenting the generated response to the user.

[1233] This invention relates to a system that registers a user's search preferences, generates prompts based on those preferences, recognizes the user's emotions using an emotion engine, and displays a list of responses generated by a backend server. This system is implemented as a personalized virtual shop application.

[1234] System Configuration

[1235] The server includes the following measures:

[1236] 1. Means for registering user search preferences

[1237] 2. Means for converting user input into prompts based on search preferences

[1238] 3. Means of recognizing user emotions

[1239] 4. Means for generating adjusted prompts by reflecting recognized emotional information in the prompts.

[1240] 5. Generation means for generating a response using the generated prompt.

[1241] 6. Means for adjusting the generated response based on emotional information

[1242] 7. Display means for listing and displaying the adjusted responses.

[1243] Program generation

[1244] The server implements these measures using Python programs. Details of each measure are shown below.

[1245] A method for registering user search preferences

[1246] Users register their search preferences via a smartphone app. Specifically, they select their favorite product categories, preferred styles, and information sources, and this data is stored in a database. The database uses services such as MySQL or Firebase.

[1247] A means of converting user input into prompts based on search preferences.

[1248] When a user enters a question or request (e.g., "I want to know this month's recommended fashion items") into the smartphone app, that input is converted into a prompt. This prompt is generated based on the user's search preferences and constructed according to a specific format.

[1249] Means of recognizing user emotions

[1250] The EmotionEngine is used to analyze the emotions expressed in the user's input text. This emotional information (e.g., "expectation") is then used to generate prompts.

[1251] A means of generating adjusted prompts by reflecting recognized emotional information in the prompts.

[1252] Recognized emotion information is added to the prompt to generate more personalized prompt messages. For example, a prompt such as "Fashion Trend Expectation: I want to know this month's recommended fashion items" might be generated.

[1253] Generation means for generating a response using the generated prompt.

[1254] The generated prompt is sent to an artificial intelligence model (e.g., GPT-3) in the backend, and an appropriate response is generated. The response generation means sends prompts to the artificial intelligence model via an API and receives responses.

[1255] A means of adjusting the generated response based on emotional information.

[1256] The generated responses are then refined using the emotion engine to reflect the user's emotions. For example, a response like "This month's fashion is full of new trends!" might be adjusted to something like, "It's like being at a fashion show! The new fall collection is especially stylish and exceeds expectations!"

[1257] Display means for listing and displaying the adjusted responses.

[1258] The adjusted responses are displayed in a list format on the smartphone app's user interface. This allows users to see the necessary information at a glance.

[1259] Specific example

[1260] For example, if a user enters "I want to know this month's recommended fashion items," their search preference will be recognized as "fashion trends" and their emotion as "expectation." In this case,

[1261] Prompt: "Fashion Trend Expectations: I want to know this month's recommended fashion items."

[1262] Generated response: "This month's fashion is full of new trends!"

[1263] Adjusted response: "It's like being at a fashion show! The new fall collection is especially stylish and exceeds expectations!"

[1264] In this way, responses that reflect the user's preferences and emotions are provided.

[1265] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1266] Step 1: Register the user's search preferences.

[1267] Users input their search preferences (e.g., "fashion trends" or "technology news") via their smartphone. The device sends this information to a front-end server (conversation server), which stores the preference information in a database. The input data consists of the user ID and preference information, while the output data is the preference data stored in the database.

[1268] Step 2: Accept user input and generate prompts

[1269] The user sends a question or request from their device (e.g., "I want to know this month's recommended fashion items"). The device sends this to the front-end server, which generates a prompt based on the user's preference information. The input data consists of the user's question or request and pre-registered preference information, while the output data is the generated prompt text.

[1270] Step 3: Recognize the user's emotions

[1271] The emotion engine on the server recognizes emotions (e.g., "expectation" or "excitement") from the user's input text. The input data is the user's input text, and the output data is the recognized emotion information. Specifically, the emotion engine performs text analysis and extracts specific emotions.

[1272] Step 4: Adjust prompts using emotional information

[1273] The server incorporates the recognized emotion information into the prompt text to generate an adjusted prompt text. The input data consists of the generated prompt text and the recognized emotion information, while the output data is the adjusted prompt text. Specifically, the server performs processing such as adding emotion keywords to the prompt text.

[1274] Step 5: Send a prompt to the backend server and generate a response.

[1275] The server sends a pre-tuned prompt to a backend generation AI model (e.g., GPT-3) to generate an appropriate response. The input data is the pre-tuned prompt, and the output data is the generated response. Specifically, the prompt is sent to the AI ​​model via an API, and the response is retrieved.

[1276] Step 6: Adjust the generated response based on emotional information.

[1277] The server refurbishes the responses generated by reusing the emotion engine, modifying them to reflect the user's emotions. The input data consists of the generated response and recognized emotion information, while the output data is the refined response. Specifically, emotion keywords and expressions are added to the response.

[1278] Step 7: List and display the adjusted responses.

[1279] The server displays the adjusted responses in a list format on the user's smartphone. The input data is the adjusted response text, and the output data is the list of responses displayed on the device. Specifically, the response text is displayed in a visually easy-to-understand format with a rich user interface.

[1280] By following these steps, it becomes possible to provide personalized product suggestions that reflect the user's preferences and emotions.

[1281] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1282] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1283] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1284] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1285] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1286] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1287] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1288] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1289] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1290] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1291] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1292] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1293] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1294] 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.

[1295] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1296] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1297] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1298] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1299] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1300] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1301] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1302] The following is further disclosed regarding the embodiments described above.

[1303] (Claim 1)

[1304] A means of registering user search preferences,

[1305] A means of converting user input into prompts based on search preferences,

[1306] A generation means for generating a response using a converted prompt,

[1307] A system including a display means for listing and displaying the generated responses.

[1308] (Claim 2)

[1309] The system according to claim 1, wherein the response generation means is a generation means that generates a response using an artificial intelligence model with respect to a prompt.

[1310] (Claim 3)

[1311] The system according to claim 1, wherein the user search preference registration means is a means for registering preferences including data on specific topics, information sources, and tone of voice.

[1312] "Example 1"

[1313] (Claim 1)

[1314] A means of registering user search preferences,

[1315] A means of converting user input into prompts based on search preferences,

[1316] A generation means for generating a response using a converted prompt,

[1317] A system including a display means for listing and displaying the generated responses.

[1318] (Claim 2)

[1319] The system according to claim 1, wherein the response generation means is a generation means that generates a response using a generation AI model based on a prompt.

[1320] (Claim 3)

[1321] The system according to claim 1, wherein the user search preference registration means is a means for registering preferences including data on specific areas, information sources, and tone of voice.

[1322] (Claim 4)

[1323] A system including a terminal for receiving user input, a front-end conversational server for processing search preferences and user input, and a back-end conversational generative AI server that generates responses using a generative AI model.

[1324] (Claim 5)

[1325] The system according to claim 1, wherein the display means uses a front-end framework for visually listing responses and is a means for presenting responses to the user.

[1326] "Application Example 1"

[1327] (Claim 1)

[1328] A means of registering user search preferences,

[1329] A means of converting user input into prompts based on search preferences,

[1330] A generation means for generating a response using a converted prompt,

[1331] A display means for listing and displaying the generated responses,

[1332] A prompt generated based on the aforementioned search preferences and user input is sent to the backend server.

[1333] A system including a display means for visually displaying responses received from a backend server on an automobile's infotainment system.

[1334] (Claim 2)

[1335] The system according to claim 1, wherein the response generation means is a generation means that generates a response using an artificial intelligence model with respect to a prompt.

[1336] (Claim 3)

[1337] The user search preference registration means is a means for registering preferences that include data on specific topics, information sources, and tone of voice.

[1338] The system according to claim 1, comprising means for providing a display format optimized for the infotainment system.

[1339] "Example 2 of combining an emotion engine"

[1340] (Claim 1)

[1341] A means of registering user search preferences,

[1342] A means of converting user input into prompts based on search preferences,

[1343] A generation means that uses artificial intelligence to generate a response using a converted prompt,

[1344] A means for recognizing the user's emotions during the process of generating a response and generating a prompt that reflects those emotions,

[1345] A means of adjusting the response generated using prompts that include emotional reflection,

[1346] A system including a display means for listing and displaying the generated responses.

[1347] (Claim 2)

[1348] The system according to claim 1, wherein the response generation means is a generation means that generates a response using an artificial intelligence model with respect to a prompt.

[1349] (Claim 3)

[1350] The system according to claim 1, wherein the user search preference registration means is a means for registering preferences including data on specific topics, information sources, and tone of voice.

[1351] "Application example 2 when combining with an emotional engine"

[1352] (Claim 1)

[1353] A means of registering user search preferences,

[1354] A means of converting user input into prompts based on search preferences,

[1355] Means of recognizing user emotions,

[1356] A means for generating a prompt that has been adjusted by reflecting recognized emotional information in the prompt,

[1357] A generation means for generating a response using a generated prompt,

[1358] A means for adjusting the generated response based on emotional information,

[1359] A system including a display means for listing and displaying the adjusted responses.

[1360] (Claim 2)

[1361] The system according to claim 1, wherein the response generation means is a generation means that generates a response using an artificial intelligence model with respect to a prompt.

[1362] (Claim 3)

[1363] The system according to claim 1, wherein the user search preference registration means is a means for registering preferences that include data on specific topics, information sources, and styles of expression. [Explanation of Symbols]

[1364] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of registering user search preferences, A means of converting user input into prompts based on search preferences, A generation means for generating a response using a converted prompt, A system including a display means for listing and displaying the generated responses.

2. The system according to claim 1, wherein the response generation means is a generation means that generates a response using an artificial intelligence model with respect to a prompt.

3. The system according to claim 1, wherein the user search preference registration means is a means for registering preferences including data on specific topics, information sources, and tone of voice.

Images