system

Abstract

Provide a system. A terminal means for inputting a question; server means for receiving input questions and providing generated answers; a user means for scoring the generated answers; a database means for storing and managing scores; A means of extracting the highest scoring answers and querying them in external sources; A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, generative AI technology has evolved, improving its ability to provide a wealth of information. However, concerns remain about the accuracy and reliability of these answers. Users lack the means to evaluate the validity of answers and obtain reliable information. Therefore, there is a need for a method to efficiently extract and query reliable answers from a large amount of information and provide them to users. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including a terminal means for inputting a question, a server means for receiving the input question and providing a generated answer, a user means for scoring the generated answer, a database means for storing and managing the scores, and a means for extracting answers with high scores and querying external sources. This system allows users to evaluate the validity of answers provided by the generation AI and easily obtain reliable information.

[0006] A "question" is a text-based inquiry that a user enters into the generating AI about the information or problem they want to know.

[0007] A "terminal" is an electronic device, such as a computer or smartphone, that a user uses to enter questions and receive answers.

[0008] The "server" is a centralized processing unit that receives questions, sends them to the generating AI, receives answers, and sends them to the user's device.

[0009] "Generative AI" refers to an artificial intelligence technology program that automatically generates answers based on questions.

[0010] An "answer" is the information or response that the generation AI generates in response to an input question and provides to the user.

[0011] "User means" refers to an interface or function that allows a user to evaluate the validity of the displayed answers and input a score.

[0012] A "score" is a number entered by the user to evaluate the validity and reliability of an answer.

[0013] "Database means" refers to a database system for storing and managing data such as questions, answers, and scores.

[0014] "External sources" are external information sources or databases used to query and verify the reliability of the generative AI's answers.

[0015] "Querying" is the process of sending a question or query to a database or external source and receiving the results. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The present invention is a system in which a user inputs a question, obtains an answer from a generation AI, and evaluates and scores the validity of the answer. The system includes a server, a terminal, a user means, a database means, an external source, and a query means.

[0038] Enter your question

[0039] Terminal: The user uses the terminal to input a question. The terminal must have an input field and a submit button. When the user inputs a question and clicks the submit button, the question is sent to the server.

[0040] Receiving and processing questions

[0041] Server: Parses the received question and formats it as a request to the generation AI. An API request is made to send the question to the generation AI and get the answer.

[0042] Generate and display answers

[0043] Generative AI: Generates an appropriate answer to the input question and sends it back to the server. The server then sends the received answer back to the user's device and displays it on the device.

[0044] Terminal: The received answers are displayed on the screen. The interface for users to check the answers should be designed with ease of viewing and operation in mind.

[0045] Scoring

[0046] User: The user inputs an evaluation score for the displayed answer. The scoring interface can be, for example, a format where a user selects a number from 1 to 5. After inputting the score, the user clicks the submit button to send the score to the server.

[0047] Score storage and management

[0048] Server: Stores the received scores along with the corresponding questions and answers in a database. This database should employ an appropriate database management system (DBMS) to effectively manage the scoring information.

[0049] Extracting and querying high-scoring answers

[0050] Server: Regularly checks the database and extracts answers with high scores. For example, a system is built to extract answers with a score of 4 or higher.

[0051] External sources: The extracted answers are checked against external expert databases and reliable information sources. The data obtained from external sources is used to strengthen the reliability of the generated AI's answers.

[0052] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification to the user saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[0053] Manage your subscription

[0054] Server: Manages the user's subscription status, notifies them of expiration dates, and connects with the payment system to process periodic charges.

[0055] Specific examples

[0056] User: For example, a user types and submits a question: "Which is the largest planet in the solar system?"

[0057] Server: Receives the question and sends a request to the generation AI.

[0058] Generation AI: Generates the answer "It's Jupiter" and sends it back to the server.

[0059] Server: Receives the response and sends it to the device.

[0060] Terminal: Shows the answer, and the user enters a score of "5 / 5" and submits.

[0061] Server: Receives the scores and stores them in a database.

[0062] Server: Periodically extracts high-scoring answers and queries them against external specialized databases.

[0063] Server: Notifies the user that the authenticity has been confirmed based on the query results.

[0064] In this way, the present invention provides a system that allows users to evaluate the validity of answers generated by AI and obtain reliable information. This system is easy for users to use and can provide reliable information.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] User: Enters a question using a device and clicks the "Submit Question" button.

[0068] Step 2:

[0069] Terminal: Takes the entered question and sends it to the server as JSON format data. This data includes the format {"question": "Which is the largest planet in the solar system?"}.

[0070] Step 3:

[0071] Server: Receives question data, formats the question into an appropriate format, and prepares an API request to the generation AI.

[0072] Step 4:

[0073] Server: Sends a request containing question data to the generation AI.

[0074] Step 5:

[0075] Generative AI: Analyzes the question data received from the server and generates an answer to the question. For example, it generates an answer such as "It's Jupiter" and sends it back to the server.

[0076] Step 6:

[0077] Server: Receives the answer returned by the generation AI and sends it to the user's device.

[0078] Step 7:

[0079] Device: Displays the received answer on the screen, e.g., the text "Jupiter" is displayed in a visible form to the user.

[0080] Step 8:

[0081] User: Enter a rating score for the displayed answer. For example, rate it from 1 to 5 and give it a score of "5 / 5." Click the "Submit Score" button.

[0082] Step 9:

[0083] Device: The entered score is sent to the server as JSON format data, which includes the format "{"question_id": 123, "score": 5}", for example.

[0084] Step 10:

[0085] Server: Stores the received scores in a database along with the corresponding question and answer data.

[0086] Step 11:

[0087] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher.

[0088] Step 12:

[0089] Server: Query the extracted high-scoring answers using external sources (e.g., specialized databases or reliable information sources).

[0090] Step 13:

[0091] External Source: Provides query results in response to queries received from the server, e.g., returns data such as "Confirmed that Jupiter is the largest planet in the solar system."

[0092] Step 14:

[0093] Server: Stores the query results in a database and notifies the user of the results. The user is informed that the information is reliable.

[0094] Step 15:

[0095] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing appropriately. For example, if a user's subscription is due for renewal, the server initiates billing.

[0096] Example 1

[0097] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0098] Conventional question-answering systems do not guarantee the validity or reliability of the generated answers, and users have limited means to evaluate the information provided. Furthermore, for answers with high scores, there is no way to verify their reliability with an external, reliable information source, making it difficult to provide users with reliable information. These issues need to be addressed.

[0099] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0100] In this invention, the server includes a means for receiving questions and sending them to the generative AI model, a means for acquiring the generated answers and returning them to the user's terminal, and a means for storing the evaluated scores in a database, which allows high-scoring answers to be extracted and queried in an external reliable information source.

[0101] "Information processing device means" refers to the device used by the user to input a query, and typically includes a desktop computer, laptop, smartphone, tablet, etc.

[0102] "Data processing means" refers to a server that has the functionality to receive input questions and send requests to the generative AI model to obtain answers.

[0103] The "evaluation means" refers to an interface that allows a user to input a score for a generated answer and evaluate it.

[0104] "Storage means" refers to a database system for storing and managing users' scores and corresponding questions and answers.

[0105] "Generative AI model" refers to an artificial intelligence model used to generate appropriate answers to input questions.

[0106] "External sources" refers to reliable databases or sources used to verify the reliability of the generated answers, examples of which include specialist databases and recognized sources.

[0107] "Scoring" refers to the rating points that users give to generated answers, typically in the form of selecting a number between 1 and 5.

[0108] "Consulting" refers to the process of using external sources to verify the accuracy and reliability of the generated answers.

[0109] The present invention provides a system in which a user inputs a question, obtains an answer from a generative AI model, and the user evaluates the validity of the answer. The system includes an information processing device, a data processing device, an evaluation device, a storage device, and an external information source.

[0110] information processing device means

[0111] The user uses a data processing device to input the question, typically a desktop computer, laptop, smartphone, or tablet. The user uses the data processing device to enter the question into an input field and clicks a submit button.

[0112] Data Processing Means

[0113] The server, which is the data processing means, receives the question sent from the information processing means. The server analyzes the question and formats it as a request to the generative AI model. The server then sends an API request to the generative AI model to obtain the answer.

[0114] Generative AI Models

[0115] The generative AI model generates appropriate answers to questions received from the server. For example, if a user sends a question such as "Which is the largest planet in the solar system?", the generative AI model generates the answer "Jupiter" and sends it back to the server.

[0116] Returning and displaying answers

[0117] The server returns the answer received from the generative AI model to the information processing device means, which displays the answer on a screen so that the user can easily check it.

[0118] Evaluation methods

[0119] The user inputs an evaluation score for the displayed answer. This evaluation is done by selecting a number, for example, from 1 to 5. When the user inputs the score and clicks the submit button, the evaluation score is sent to the server.

[0120] storage means

[0121] The server stores the received scores together with the corresponding questions and answers in a storage means or database, which may employ a suitable database management system such as MySQL®.

[0122] Extracting and querying high-scoring answers

[0123] The server periodically checks the database and extracts high-scoring answers. For example, answers with a score of 4 or higher are automatically extracted. For the extracted answers, the server queries external sources to verify the accuracy and reliability of the generated AI model's answers. For example, it verifies that "Jupiter is the largest planet in the solar system" with specialized databases and authorized sources.

[0124] Manage your subscription

[0125] The server manages the user's subscription status, notifies them when the expiration date is approaching, and handles periodic billing, which is handled in cooperation with a payment system (e.g., Stripe, PayPal, etc.).

[0126] Specific examples

[0127] For example, a user inputs and submits the question "Which is the largest planet in the solar system?" The server receives this question and sends a request to the generative AI model. After receiving the answer "Jupiter" from the generative AI model, the server transmits this answer to the information processing means and displays it. The user inputs a rating of "5 / 5" for the displayed answer and transmits it. The server receives the score and stores it in the storage means. The server periodically checks the database, extracts answers with high scores, and queries external information sources. The user is notified of the confirmed, reliable answers.

[0128] In this way, the present invention provides a system that allows users to evaluate the validity of the answers of generative AI models and obtain reliable information.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1:

[0131] The user types a question into the terminal.

[0132] Specific Actions: Using the input field on the device, the user enters a question and clicks the submit button.

[0133] Input: Text entered by the user (e.g., "Which is the largest planet in the solar system?").

[0134] Output: The entered question data is sent to the server.

[0135] Step 2:

[0136] The server receives the query and parses it.

[0137] Specific operation: The server receives the query data from the terminal, analyzes the content, and converts it into an appropriate data format.

[0138] Input: Question data sent from the terminal.

[0139] Output: Data formatted for API requests to the generative AI model.

[0140] Step 3:

[0141] The server sends an API request to the generative AI model.

[0142] Specific operation: The server sends a formatted request to the API endpoint of the generative AI model.

[0143] Input: Question data in the form of an API request.

[0144] Output: The answer data generated by the generative AI model.

[0145] Step 4:

[0146] A generative AI model generates answers to questions.

[0147] How it works: The generative AI model analyzes the requested question and generates an appropriate answer.

[0148] Input: Question data in the form of an API request from the server.

[0149] Output: The generated answer data (e.g., "It's Jupiter").

[0150] Step 5:

[0151] The server receives the response and sends it to the terminal.

[0152] Specific operation: The server receives the response data from the generative AI model and sends it to the terminal.

[0153] Input: Answer data from the generative AI model.

[0154] Output: The response data sent to the device.

[0155] Step 6:

[0156] The device will display the answer.

[0157] Specific operation: The terminal displays the received response data on the screen in a format that is easy for the user to view.

[0158] Input: The response data sent from the server.

[0159] Output: The answer that appears on the screen (e.g., "Jupiter").

[0160] Step 7:

[0161] The user enters a score for the answer.

[0162] Specific operation: The user enters an evaluation score for the displayed answer and clicks the submit button.

[0163] Input: The score entered by the user (e.g., "5 / 5").

[0164] Output: The entered score data is sent to the server.

[0165] Step 8:

[0166] The server receives the scores and stores them in a database.

[0167] Specific Operation: The server stores the received score data in a database along with the associated question and answer data.

[0168] Input: Score data submitted by the user.

[0169] Output: Score, question and answer data stored in a database.

[0170] Step 9:

[0171] The server extracts the answers with the highest scores.

[0172] Specific operation: The server periodically checks the database and extracts answers with a score of 4 or higher.

[0173] Input: Score, question and answer data stored in the database.

[0174] Output: Extracted high-scoring answer data.

[0175] Step 10:

[0176] The server queries the external information source.

[0177] Specific operation: The server queries the extracted high-scoring answers using external information sources to verify their accuracy and reliability.

[0178] Input: Extracted high-scoring answer data.

[0179] Output: Query result data obtained from external sources.

[0180] Step 11:

[0181] The server stores the query results in a database and notifies the user.

[0182] Specific operation: The query results are saved in the database and the confirmed information is notified to the user.

[0183] Input: Query result data from external sources.

[0184] Output: A notification with the confirmed information (e.g., "Jupiter has been confirmed to be the largest planet in the solar system").

[0185] (Application example 1)

[0186] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0187] Modern electronic payment services require rapid and accurate responses to user information requests. However, many current systems rely on human intervention to meet these requests, resulting in problems of inefficiency and reliability. Furthermore, these systems lack a means to effectively evaluate user satisfaction and reflect that evaluation in service improvements. Therefore, there is a need for an efficient system that can provide rapid and accurate answers to user questions and reflect user evaluations of those answers in the system.

[0188] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0189] In this invention, the server includes a means for causing the generative AI model to generate answers in real time, a means for displaying the answers generated by the generative AI model and providing a dedicated interface for users to input their ratings, and a means for enhancing reliability based on the results of inquiries in external information sources, thereby enabling quick and accurate answers to users' questions and effective collection and management of ratings for the answers.

[0190] A "terminal means" is a device used by a user to input a question.

[0191] "Server means" refers to a central processing unit that receives input questions and transmits them to a generative AI model to provide answers.

[0192] "User means" refers to the interface and functionality that allows a user to score the generated answers.

[0193] "Database means" refers to a database system for storing and managing scores, questions and answers.

[0194] "External Source" means an external, reliable source of information used to query and augment the reliability of the answers provided by the generative AI model.

[0195] A "generative AI model" is an artificial intelligence model that generates answers to input questions.

[0196] The "dedicated interface" refers to a dedicated operation screen and function that allows users to check the answers of the generated AI model and enter evaluation scores.

[0197] "Real-time" means that processing occurs almost instantaneously, with immediate response to user input.

[0198] "Measures to enhance trustworthiness" refers to a function that verifies the accuracy of the answers of the generated AI model based on the results of inquiries from external information sources, thereby improving trustworthiness.

[0199] MODE FOR CARRYING OUT THE INVENTION

[0200] This invention provides a system that quickly and accurately answers user questions. The system includes a terminal, a server, a generative AI model, a database, an external information source, and a dedicated interface. The specific functions and operations of each element are described below.

[0201] Terminal means

[0202] Users enter questions using devices such as smartphones or computers. The devices have an input field and a submit button, and the questions entered by the user are sent to the server.

[0203] Server Means

[0204] The server receives questions sent by users and sends them to the generative AI model. This process involves a program running on the server. Specifically, a web server using Flask receives the questions and sends them to the generative AI model using the OpenAI (registered trademark) API. The server then receives the generated answers and sends them back to the user's device.

[0205] Generative AI Models

[0206] A generative AI model (e.g., OpenAI's GPT-3 (registered trademark)) generates an answer to a user's question. The generative AI model generates an answer based on the question sent from the server and sends the answer back to the server. An example of a prompt sentence used here is, "What should I do if I don't receive my electronic payment receipt?"

[0207] Dedicated Interface

[0208] The generated answers are displayed on the user's device, and the dedicated interface includes a scoring function for evaluating the answers, allowing the user to rate the appropriateness of the answers on a scale of 1 to 5. The entered score is then sent to the server.

[0209] Database Means

[0210] The server stores the received scores and the corresponding questions and answers in a database, using a database management system such as SQLite. The stored data is later used to extract and analyze high-scoring answers.

[0211] external information sources

[0212] The server periodically checks the database and extracts the highest-scoring answers, then queries and strengthens the reliability of these answers using external sources, such as trusted data sources and specialized databases.

[0213] Specific examples of programs

[0214] For example, a user enters a question such as, "What should I do if I don't receive my electronic payment receipt?" The question is immediately received by the server and sent to a generative AI model (GPT-3). The generated answer is returned as, "Contact your electronic payment company and provide them with the transaction ID to request confirmation." The user rates this answer as "5 / 5" and enters a score. The server stores this score in a database and later extracts it as a high-scoring answer, verifying its reliability with an external source.

[0215] The system allows users to receive fast and accurate answers, improving the efficiency and reliability of electronic payment services.

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] A user inputs a question using a terminal. The user generates question data by entering the question in an input field on the terminal and clicking the send button. The input data is the user's question text. This question text is sent to the server.

[0219] Step 2:

[0220] The server receives the question sent by the user. It analyzes the received question text and formats it into a request format to send to the generative AI model. This request data is JSON format data including the question text. The server sends this data to the API that provides the generative AI model.

[0221] Step 3:

[0222] The generative AI model receives the API request and generates an answer to the question. The generated answer is sent back to the server in the form of an API response. This response data contains the text of the answer. The generative AI model analyzes the input question text and uses its internal algorithm to create the optimal answer text.

[0223] Step 4:

[0224] The server receives the answer returned from the generative AI model and sends it back to the user's device. The received answer data is JSON format data containing the answer text and related metadata. The server sends this data to the user's device.

[0225] Step 5:

[0226] The user's device displays the received answer on the user interface. The user checks the displayed answer and inputs an evaluation score for the answer using the scoring interface. The input data based on the scoring is the score value. When the user inputs the score and clicks the submit button, the score data is sent to the server.

[0227] Step 6:

[0228] The server receives the score data sent by the user, associates it with the question and answer, and stores it in a database. This score data includes the score value and metadata such as question ID and answer ID. The server manages this data by inserting it into the database.

[0229] Step 7:

[0230] The server periodically checks the database and extracts the top-scoring answers by analyzing the scores in the database using queries, which are then used to query external sources.

[0231] Step 8:

[0232] The server uses external information sources to verify the reliability of high-scoring answers. The data obtained from the external information sources is matched with the answer text of the generative AI model. Answer data that is verified as reliable through this verification process is stored in a database and notified to the user.

[0233] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0234] The present invention combines a system in which a user inputs a question, obtains an answer from a generation AI, evaluates the validity of the answer, and scores it, with an emotion engine that recognizes the user's emotions. This system includes a server, a terminal, user means, database means, an external source, a query means, and an emotion engine.

[0235] Enter your question

[0236] Terminal: The user uses the terminal to input a question. The terminal has an input field and a send button, and when the user inputs a question and clicks the send button, the question is sent to the server.

[0237] Receiving and processing questions

[0238] Server: Parses the received question and formats it as a request to the generation AI. An API request is made to send the question to the generation AI and retrieve the answer.

[0239] Generate and display answers

[0240] Generative AI: Generates an appropriate answer to the input question and sends it back to the server. The server then sends the received answer back to the user's device and displays it on the device.

[0241] Device: The received answer is displayed on the screen. For example, the answer "Jupiter" is displayed.

[0242] Scoring

[0243] User: Checks the answers and enters an evaluation score. The scoring interface is a form where a user selects a number, for example, from 1 to 5. The user enters the score and clicks the submit button, which sends the score to the server.

[0244] Emotion recognition by emotion engine

[0245] Emotion engine: It has the ability to analyze and recognize emotions from user input and behavior (e.g., typing speed, response confirmation time, etc.). Emotion data is used to improve the quality of user responses and feedback.

[0246] Storing and managing score and emotion data

[0247] Server: Stores the received scores and sentiment data in a database along with the corresponding questions and answers.

[0248] Extracting and querying high-scoring answers

[0249] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher. The extracted answers are then compared with external specialized databases and reliable information sources.

[0250] Saving and notifying query results

[0251] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[0252] Manage your subscription

[0253] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[0254] Specific examples

[0255] User: For example, a user types and submits a question: "Which is the largest planet in the solar system?"

[0256] Server: Receives the question and sends a request to the generation AI.

[0257] Generation AI: Generates the answer "It's Jupiter" and sends it back to the server.

[0258] Server: Receives the response and sends it to the device.

[0259] Terminal: Shows the answer, and the user enters a score of "5 / 5" and submits.

[0260] Emotion engine: Recognizes emotions from the user's input speed and behavior patterns and records that data.

[0261] Server: Receives scores and emotion data and stores them in a database.

[0262] Server: Periodically extracts high-scoring answers and queries them against external specialized databases.

[0263] Server: Notifies the user that the authenticity has been confirmed based on the query results.

[0264] Server: Manages user subscription status, notifies expiration and processes billing.

[0265] In this way, the present invention provides a system that allows users to evaluate the validity of the answers of the AI ​​generator and obtain reliable information through feedback that includes emotions. This system is easy for users to use and can provide reliable information.

[0266] The processing flow will be explained below.

[0267] Step 1:

[0268] User: Enters a question using a device and clicks the "Submit Question" button.

[0269] Step 2:

[0270] Terminal: Takes the entered question and sends it to the server as JSON format data, for example, "{"question": "Which is the largest planet in the solar system?"}".

[0271] Step 3:

[0272] Server: Receives question data, formats the question appropriately, and creates an API request to the generation AI.

[0273] Step 4:

[0274] Server: Sends a request containing question data to the generation AI.

[0275] Step 5:

[0276] Generative AI: Analyzes the question data received from the server and generates an answer to the question. For example, it generates an answer such as "It's Jupiter" and sends it back to the server.

[0277] Step 6:

[0278] Server: Receives the answer returned by the generation AI and sends it to the user's device.

[0279] Step 7:

[0280] Terminal: Displays the received answer on the screen. For example, the answer "Jupiter" is displayed on the screen.

[0281] Step 8:

[0282] User: Enter a rating score for the displayed answer. For example, rate it from 1 to 5 and give it a score of "5 / 5." Click the "Submit Score" button.

[0283] Step 9:

[0284] Device: The entered score is sent to the server as JSON format data, for example, "{"question_id": 123, "score": 5}".

[0285] Step 10:

[0286] Server: Stores the received scores in a database along with the corresponding question and answer data.

[0287] Step 11:

[0288] Emotion engine: Recognizes the user's emotions by analyzing the user's input speed, typing patterns, and response confirmation time. For example, if the input speed is slow, it is recognized as "anxious," and if it is fast, it is recognized as "confident."

[0289] Step 12:

[0290] Server: Receives emotion data obtained from the emotion engine and stores it in a database along with the corresponding question and answer data.

[0291] Step 13:

[0292] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher.

[0293] Step 14:

[0294] Server: queries external sources (specialized databases and reliable information sources) for extracted high-scoring answers.

[0295] Step 15:

[0296] External Source: Provides data in response to a query from the server, e.g., sends back to the server information that "Jupiter has been confirmed to be the largest planet in the solar system."

[0297] Step 16:

[0298] Server: Stores the query results from external sources in a database and notifies the user of the results, for example, sending a notification that "Jupiter has been confirmed to be the largest planet in the solar system."

[0299] Step 17:

[0300] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[0301] Example 2

[0302] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0303] Conventional systems do not properly evaluate the validity of the answers received from the AI ​​generator and provide scoring and feedback to ensure reliable information. As a result, the reliability of the information received by the user is reduced, resulting in an unsatisfactory user experience. Furthermore, there is a lack of means to improve the quality of the feedback by utilizing user emotional data.

[0304] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means having a function of receiving an input question, analyzing it, formatting it for the generation AI, and obtaining an answer, means for displaying the generated answer on a terminal and allowing the user to score it, means having a function of analyzing the user's emotional data using an emotion engine, database means for saving and managing scores and related emotional data, and means for extracting answers with high scores and checking their reliability with an external information source. This allows the user to evaluate the validity of the answer from the generation AI and obtain reliable information, while also making it possible to improve the quality of the user experience based on the emotional data.

[0305] The "device means for inputting a question" refers to a terminal or device that allows a user to freely input a question and transmits the input question to a server for subsequent processing.

[0306] "Server means having the function of receiving, analyzing, formatting for the generation AI, and obtaining the answer" refers to the server function of receiving a question entered by a user, analyzing it, converting it into an appropriate format for the generation AI, and obtaining the answer.

[0307] "A means for the generated answers to be displayed on the device and scored by the user" refers to a function that displays the answers obtained from the generation AI on the user's device and provides an interface for the user to evaluate the answers.

[0308] "Means having a function for analyzing user emotional data using an emotion engine" refers to a function within the system for analyzing emotions from user input and behavioral patterns and collecting that data.

[0309] "Database means for saving and managing scores and related emotional data" refers to the function of a database for saving and managing scores entered by users and the emotional data associated with them.

[0310] "Means for extracting answers with high scores and checking their reliability with external information sources" refers to a system function that periodically extracts answers that have received particularly high scores from the stored scores and checks their reliability by checking with external, reliable databases or information sources.

[0311] The present invention relates to a system in which a user inputs a question, obtains an answer from a generation AI, and the user evaluates the validity of the answer and scores it. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the feedback can be improved. This system includes a server, a terminal, user means, database means, an external source, query means, and an emotion engine.

[0312] Enter your question

[0313] Terminal: The user uses the terminal to input a question. The terminal has an input field and a send button, and when the user inputs a question and clicks the send button, the question is sent to the server.

[0314] Receiving and processing questions

[0315] Server: Parses the received questions and formats them as requests for the generation AI. Protocols such as RESTful APIs and GraphQL can be used to enable API communication with other systems.

[0316] Generate and display answers

[0317] Generative AI: Generates an appropriate answer to the input question and returns the answer to the server. Generative AI can use, for example, a large-scale language model. Below is a specific example of a prompt sentence.

[0318] Examples:

[0319] User-supplied question: "Which is the largest planet in the solar system?"

[0320] The AI ​​responds: "Jupiter."

[0321] Server: Returns the received answer to the user's terminal and displays it on the terminal.

[0322] Terminal: Displays the received response on the screen.

[0323] Scoring

[0324] User: Checks the answers and enters an evaluation score. The scoring interface allows users to select a number from 1 to 5, for example. The user enters the score and clicks the submit button, which sends the score to the server.

[0325] Emotion recognition by emotion engine

[0326] Emotion engine: It has the ability to analyze and recognize emotions from user input and behavior (e.g., typing speed, response confirmation time, etc.). Emotion data is used to improve the quality of user responses and feedback.

[0327] Storing and managing score and emotion data

[0328] Server: Stores the received scores and emotion data along with the corresponding questions and answers in a database. The database can be, for example, a relational database or a NoSQL database.

[0329] Extracting and querying high-scoring answers

[0330] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher. The extracted answers are then compared with external specialized databases and reliable information sources.

[0331] Saving and notifying query results

[0332] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[0333] Manage your subscription

[0334] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[0335] In this way, by providing a system that comprehensively handles everything from question input to answer generation, scoring, emotion recognition, extraction and query of high-scoring answers, and even subscription management, it is possible to provide users with highly reliable information. Furthermore, the introduction of an emotion engine is expected to improve the user experience.

[0336] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0337] Step 1:

[0338] User: The user uses the terminal to input a question. Specifically, the user writes the question in the input field displayed on the terminal and clicks the send button. The input data is a text-based question. For example, the user might enter "Which is the largest planet in the solar system?" The output of this step is the input question sent to the server as a data packet.

[0339] Step 2:

[0340] Server: Receives the question sent from the device. The received data is a text-formatted question. The server analyzes the received question and formats it as a request for the generation AI. Specifically, it converts the question into an API request format such as JSON. The converted request data is sent to the generation AI, which is the output of this step.

[0341] Step 3:

[0342] Server: Sends an API request to the generation AI. The request includes the converted question. The server sends an HTTP POST request specifying the generation AI's endpoint URL and providing the necessary API key or token. The input to this step is the formatted API request data, and the output is the answer data returned by the generation AI.

[0343] Step 4:

[0344] Generative AI: Generates answers based on the received API request. Generative AI uses a large language model to create an answer to the input question. For example, the answer to the question "Which is the largest planet in the solar system?" is generated as "Jupiter." The generated answer data is sent back to the server as the output of this step.

[0345] Step 5:

[0346] Server: Sends the answer data received from the generation AI to the user's device. Analyzes the received answer data and converts it into a format that can be displayed on the device. Specifically, the answer from the generation AI is included in the HTTP response as a text message. The converted answer data is sent to the device and becomes the output of this step.

[0347] Step 6:

[0348] Terminal: The received answer is displayed on the screen. For example, the answer "Jupiter" is displayed on the user's terminal. The user confirms the displayed answer in this step.

[0349] Step 7:

[0350] User: The user evaluates the displayed answers and enters a score. The user follows the scoring interface to select a numerical score, for example, between 1 and 5. After entering the score, the user clicks the submit button, which sends the score to the server. The output of this step is the entered score data.

[0351] Step 8:

[0352] Emotion engine: Analyzes emotions from the user's input speed and behavioral patterns. Behavioral data such as input speed and response confirmation time are input. The emotion engine analyzes this data and determines the user's emotions. For example, if the typing speed is fast, it is analyzed as being excited. The analysis results are sent to the server and become the output of this step.

[0353] Step 9:

[0354] Server: Stores the received score and emotion data in the database. Creates a new record in the database to store the question, answer, and their corresponding score and emotion data. The input of this step is the score data and emotion data, and the output is a message confirming the stored data.

[0355] Step 10:

[0356] Server: Periodically checks the database and extracts answers with high scores. Specifically, it uses a query to extract records with a score of 4 or higher. It then queries external sources for verification of those records. It communicates with external databases to verify the accuracy and reliability of the answers. The output of this step is external data for verification of reliability.

[0357] Step 11:

[0358] Server: Stores the query results obtained from external sources in a database and notifies the user. Stores the query results as a new record and sends a message to the user device informing them of the results. For example, "Jupiter has been confirmed to be the largest planet in the solar system." The output of this step is the storage of the query results and a message to the user.

[0359] Step 12:

[0360] Server: Manages the user's subscription status and notifies them when the expiration date approaches. Specifically, it monitors the subscription expiration date and sends reminder notifications to the user when the expiration date approaches. It also handles billing as needed. The output of this step is a subscription renewal notification and a billing confirmation message.

[0361] (Application example 2)

[0362] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0363] Conventional question-answering systems using generative AI do not fully consider user emotions and feedback, and have limited means to guarantee the reliability of generated answers. This can result in low user satisfaction with the validity and reliability of answers. Furthermore, in the security field, the accuracy of the information provided is extremely important, and inquiries from reliable sources are essential. The present invention aims to solve these issues and provide a question-answering system that users can use with confidence.

[0364] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0365] In this invention, the server includes terminal means for inputting a question, server means for receiving the input question and providing a generated answer, user means for scoring the generated answer, database means for saving and managing the scores, means for extracting answers with high scores and querying external sources, emotion engine means for analyzing and recognizing emotions from the user's input and actions, and query means for confirming the reliability of answers to user questions with external expert information sources. This makes it possible to generate appropriate answers to user questions and guarantee their reliability, as well as to provide better services based on the user's emotions and feedback.

[0366] The "terminal means for inputting a question" refers to a device that allows a user to input and submit a question. This device includes an input field and a submit button.

[0367] "Server means for receiving input questions and providing generated answers" refers to a server that has the function of receiving questions from users, generating appropriate answers using generation AI, and sending them to the terminal.

[0368] "User means for scoring generated answers" refers to an interface for users to input rating scores for generated answers, thereby collecting user ratings.

[0369] "Database means for storing and managing scores" refers to a database system that stores scores entered by users and other related data and that can be accessed as needed.

[0370] "Means for extracting highly scored answers and querying external sources" refers to the functionality for selecting highly scored answers from the database and querying their reliability with external expert sources.

[0371] "Emotion engine means for analyzing and recognizing emotions from user input and behavior" refers to a system that reads and analyzes emotions from the user's input speed, behavioral patterns, etc. This data will be used to improve services.

[0372] "A means for checking the reliability of answers to user questions from external expert information sources" refers to a function for querying the accuracy and reliability of generated answers from external expert information sources and reflecting the results.

[0373] "Generative AI model" refers to an artificial intelligence model used to generate appropriate answers based on user questions.

[0374] A "prompt" is a text that describes a question or request to the generation AI, which then generates an answer based on the prompt.

[0375] This invention is a system in which a user inputs a question, a generative AI provides an answer to that question, and evaluates the validity of the answer. The system includes an emotion engine that analyzes the user's emotions and also includes a function to verify the reliability of the generated answer with an external expert information source. A method for implementing this system is described below.

[0376] Terminal means:

[0377] Users input questions using devices such as smartphones and personal computers. The devices have an input field for entering questions and a submit button.

[0378] Server means:

[0379] The server receives the question sent from the device, converts it into an appropriate format, and sends a request to the generative AI model. The generative AI model generates an answer to the question and sends it back to the server. The server receives the answer, sends it to the device, and displays it to the user. Specifically, a web server is built using, for example, the Python (registered trademark)-based Flask framework. A commonly used generative AI model such as GPT-3 can be used.

[0380] Emotion Engine means:

[0381] The server contains an emotion engine that analyzes and recognizes emotions from the user's input speed and behavioral patterns. The emotion engine is implemented using, for example, TextBlob, a natural language processing library. It analyzes the speed and timing of the user's input of questions and quantifies positive or negative emotions.

[0382] User means:

[0383] Once a user receives the generated answer, they can assign a rating to it. The user interface uses a scoring system ranging from 1 to 5. Once the user enters and submits the score, it is stored on the server.

[0384] Database Methods:

[0385] The server stores the scores and emotion data entered by the user in a database, which can be constructed using SQLite or MySQL, for example.

[0386] Inquiry methods:

[0387] The server periodically checks the database and extracts the top-scoring answers, then queries external sources, such as specialized information services or APIs, to verify the reliability of the generated answers.

[0388] Examples:

[0389] For example, a user enters a question such as, "How can I improve my home Wi-Fi security?" The server sends this question to a generative AI model, which responds, "We recommend using a strong password, using the latest encryption methods, and updating your router's firmware." The answer is then provided to the user via the server. The user rates this answer "5 / 5," and the server stores this score and sentiment data. The server periodically checks this answer against expert sources, and if its reliability is confirmed, records the information in a database and notifies the user.

[0390] As a result, this system allows users to evaluate the validity of the generated AI's answers and provide feedback that includes emotions, making it possible to provide users with more reliable information.

[0391] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0392] Step 1:

[0393] The terminal accepts questions from the user in an input field. When the user enters a question and presses the send button, the question is sent to the server.

[0394] Input: The question entered by the user

[0395] Output: The question sent to the server

[0396] Step 2:

[0397] The server parses the received question and formats it as a request to the generative AI model, which then sends the request to the generative AI model.

[0398] Input: Question received from the terminal

[0399] Output: The request sent to the generative AI model

[0400] Step 3:

[0401] The generative AI model receives the formatted request and generates an appropriate answer to the question, which is then sent back to the server.

[0402] Input: The request sent by the server

[0403] Output: The generated answer

[0404] Step 4:

[0405] The server sends the answer received from the generative AI model back to the device and displays it to the user.

[0406] Input: The answer received from the generative AI model

[0407] Output: Answer sent back to the terminal

[0408] Step 5:

[0409] The terminal displays the received answer to the user. The user checks the answer and enters an evaluation score. The evaluation score is entered and sent.

[0410] Input: The answer returned by the server

[0411] Output: User-entered rating score

[0412] Step 6:

[0413] The server receives the user-submitted rating score, stores the data in a database, and, if the rating score is high (e.g., 4 or higher), queries the answer to an external source.

[0414] Input: Rating score from device

[0415] Output: Scores stored in a database and query requests sent to external sources

[0416] Step 7:

[0417] The external source receives the query request from the server and verifies the authenticity of the generated answer, which is then sent back to the server.

[0418] Input: A query request from the server

[0419] Output: Reliability check result

[0420] Step 8:

[0421] The server receives the results of the trust verification from the external source, stores them in a database, and notifies the user of the results.

[0422] Input: Reliability check results from external sources

[0423] Output: Trust verification results stored in the database and notified to the user

[0424] Through these steps, the system generates appropriate answers to users' questions, guarantees their reliability, and collects feedback, including users' emotions.

[0425] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0426] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0427] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0428] [Second embodiment]

[0429] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0430] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0431] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0432] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0433] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0434] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0435] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0436] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0437] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0438] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0439] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0440] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0441] The present invention is a system in which a user inputs a question, obtains an answer from a generation AI, and evaluates and scores the validity of the answer. The system includes a server, a terminal, a user means, a database means, an external source, and a query means.

[0442] Enter your question

[0443] Terminal: The user uses the terminal to input a question. The terminal must have an input field and a submit button. When the user inputs a question and clicks the submit button, the question is sent to the server.

[0444] Receiving and processing questions

[0445] Server: Parses the received question and formats it as a request to the generation AI. An API request is made to send the question to the generation AI and get the answer.

[0446] Generate and display answers

[0447] Generative AI: Generates an appropriate answer to the input question and sends it back to the server. The server then sends the received answer back to the user's device and displays it on the device.

[0448] Terminal: The received answers are displayed on the screen. The interface for users to check the answers should be designed with ease of viewing and operation in mind.

[0449] Scoring

[0450] User: The user inputs an evaluation score for the displayed answer. The scoring interface can be, for example, a format where a user selects a number from 1 to 5. After inputting the score, the user clicks the submit button to send the score to the server.

[0451] Score storage and management

[0452] Server: Stores the received scores along with the corresponding questions and answers in a database. This database should employ an appropriate database management system (DBMS) to effectively manage the scoring information.

[0453] Extracting and querying high-scoring answers

[0454] Server: Regularly checks the database and extracts answers with high scores. For example, a system is built to extract answers with a score of 4 or higher.

[0455] External sources: The extracted answers are checked against external expert databases and reliable information sources. The data obtained from external sources is used to strengthen the reliability of the generated AI's answers.

[0456] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification to the user saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[0457] Manage your subscription

[0458] Server: Manages the user's subscription status, notifies them of expiration dates, and connects with the payment system to process periodic charges.

[0459] Specific examples

[0460] User: For example, a user types and submits a question: "Which is the largest planet in the solar system?"

[0461] Server: Receives the question and sends a request to the generation AI.

[0462] Generation AI: Generates the answer "It's Jupiter" and sends it back to the server.

[0463] Server: Receives the response and sends it to the device.

[0464] Terminal: Shows the answer, and the user enters a score of "5 / 5" and submits.

[0465] Server: Receives the scores and stores them in a database.

[0466] Server: Periodically extracts high-scoring answers and queries them against external specialized databases.

[0467] Server: Notifies the user that the authenticity has been confirmed based on the query results.

[0468] In this way, the present invention provides a system that allows users to evaluate the validity of answers generated by AI and obtain reliable information. This system is easy for users to use and can provide reliable information.

[0469] The processing flow will be explained below.

[0470] Step 1:

[0471] User: Enters a question using a device and clicks the "Submit Question" button.

[0472] Step 2:

[0473] Terminal: Takes the entered question and sends it to the server as JSON format data. This data includes the format {"question": "Which is the largest planet in the solar system?"}.

[0474] Step 3:

[0475] Server: Receives question data, formats the question into an appropriate format, and prepares an API request to the generation AI.

[0476] Step 4:

[0477] Server: Sends a request containing question data to the generation AI.

[0478] Step 5:

[0479] Generative AI: Analyzes the question data received from the server and generates an answer to the question. For example, it generates an answer such as "It's Jupiter" and sends it back to the server.

[0480] Step 6:

[0481] Server: Receives the answer returned by the generation AI and sends it to the user's device.

[0482] Step 7:

[0483] Device: Displays the received answer on the screen, e.g., the text "Jupiter" is displayed in a visible form to the user.

[0484] Step 8:

[0485] User: Enter a rating score for the displayed answer. For example, rate it from 1 to 5 and give it a score of "5 / 5." Click the "Submit Score" button.

[0486] Step 9:

[0487] Device: The entered score is sent to the server as JSON format data, which includes the format "{"question_id": 123, "score": 5}", for example.

[0488] Step 10:

[0489] Server: Stores the received scores in a database along with the corresponding question and answer data.

[0490] Step 11:

[0491] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher.

[0492] Step 12:

[0493] Server: Query the extracted high-scoring answers using external sources (e.g., specialized databases or reliable information sources).

[0494] Step 13:

[0495] External Source: Provides query results in response to queries received from the server, e.g., returns data such as "Confirmed that Jupiter is the largest planet in the solar system."

[0496] Step 14:

[0497] Server: Stores the query results in a database and notifies the user of the results. The user is informed that the information is reliable.

[0498] Step 15:

[0499] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing appropriately. For example, if a user's subscription is due for renewal, the server initiates billing.

[0500] Example 1

[0501] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0502] Conventional question-answering systems do not guarantee the validity or reliability of the generated answers, and users have limited means to evaluate the information provided. Furthermore, for answers with high scores, there is no way to verify their reliability with an external, reliable information source, making it difficult to provide users with reliable information. These issues need to be addressed.

[0503] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0504] In this invention, the server includes a means for receiving questions and sending them to the generative AI model, a means for acquiring the generated answers and returning them to the user's terminal, and a means for storing the evaluated scores in a database, which allows high-scoring answers to be extracted and queried in an external reliable information source.

[0505] "Information processing device means" refers to the device used by the user to input a query, and typically includes a desktop computer, laptop, smartphone, tablet, etc.

[0506] "Data processing means" refers to a server that has the functionality to receive input questions and send requests to the generative AI model to obtain answers.

[0507] The "evaluation means" refers to an interface that allows a user to input a score for a generated answer and evaluate it.

[0508] "Storage means" refers to a database system for storing and managing users' scores and corresponding questions and answers.

[0509] "Generative AI model" refers to an artificial intelligence model used to generate appropriate answers to input questions.

[0510] "External sources" refers to reliable databases or sources used to verify the reliability of the generated answers, examples of which include specialist databases and recognized sources.

[0511] "Scoring" refers to the rating points that users give to generated answers, typically in the form of selecting a number between 1 and 5.

[0512] "Consulting" refers to the process of using external sources to verify the accuracy and reliability of the generated answers.

[0513] The present invention provides a system in which a user inputs a question, obtains an answer from a generative AI model, and the user evaluates the validity of the answer. The system includes an information processing device, a data processing device, an evaluation device, a storage device, and an external information source.

[0514] information processing device means

[0515] The user uses a data processing device to input the question, typically a desktop computer, laptop, smartphone, or tablet. The user uses the data processing device to enter the question into an input field and clicks a submit button.

[0516] Data Processing Means

[0517] The server, which is the data processing means, receives the question sent from the information processing means. The server analyzes the question and formats it as a request to the generative AI model. The server then sends an API request to the generative AI model to obtain the answer.

[0518] Generative AI Models

[0519] The generative AI model generates appropriate answers to questions received from the server. For example, if a user sends a question such as "Which is the largest planet in the solar system?", the generative AI model generates the answer "Jupiter" and sends it back to the server.

[0520] Returning and displaying answers

[0521] The server returns the answer received from the generative AI model to the information processing device means, which displays the answer on a screen so that the user can easily check it.

[0522] Evaluation methods

[0523] The user inputs an evaluation score for the displayed answer. This evaluation is done by selecting a number, for example, from 1 to 5. When the user inputs the score and clicks the submit button, the evaluation score is sent to the server.

[0524] storage means

[0525] The server stores the received scores together with the corresponding questions and answers in a storage means or database, which may employ a suitable database management system such as MySQL.

[0526] Extracting and querying high-scoring answers

[0527] The server periodically checks the database and extracts high-scoring answers. For example, answers with a score of 4 or higher are automatically extracted. For the extracted answers, the server queries external sources to verify the accuracy and reliability of the generated AI model's answers. For example, it verifies that "Jupiter is the largest planet in the solar system" with specialized databases and authorized sources.

[0528] Manage your subscription

[0529] The server manages the user's subscription status, notifies them when the expiration date is approaching, and handles periodic billing, which is handled in cooperation with a payment system (e.g., Stripe, PayPal, etc.).

[0530] Specific examples

[0531] For example, a user inputs and submits the question "Which is the largest planet in the solar system?" The server receives this question and sends a request to the generative AI model. After receiving the answer "Jupiter" from the generative AI model, the server transmits this answer to the information processing means and displays it. The user inputs a rating of "5 / 5" for the displayed answer and transmits it. The server receives the score and stores it in the storage means. The server periodically checks the database, extracts answers with high scores, and queries external information sources. The user is notified of the confirmed, reliable answers.

[0532] In this way, the present invention provides a system that allows users to evaluate the validity of the answers of generative AI models and obtain reliable information.

[0533] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0534] Step 1:

[0535] The user types a question into the terminal.

[0536] Specific Actions: Using the input field on the device, the user enters a question and clicks the submit button.

[0537] Input: Text entered by the user (e.g., "Which is the largest planet in the solar system?").

[0538] Output: The entered question data is sent to the server.

[0539] Step 2:

[0540] The server receives the query and parses it.

[0541] Specific operation: The server receives the query data from the terminal, analyzes the content, and converts it into an appropriate data format.

[0542] Input: Question data sent from the terminal.

[0543] Output: Data formatted for API requests to the generative AI model.

[0544] Step 3:

[0545] The server sends an API request to the generative AI model.

[0546] Specific operation: The server sends a formatted request to the API endpoint of the generative AI model.

[0547] Input: Question data in the form of an API request.

[0548] Output: The answer data generated by the generative AI model.

[0549] Step 4:

[0550] A generative AI model generates answers to questions.

[0551] How it works: The generative AI model analyzes the requested question and generates an appropriate answer.

[0552] Input: Question data in the form of an API request from the server.

[0553] Output: The generated answer data (e.g., "It's Jupiter").

[0554] Step 5:

[0555] The server receives the response and sends it to the terminal.

[0556] Specific operation: The server receives the response data from the generative AI model and sends it to the terminal.

[0557] Input: Answer data from the generative AI model.

[0558] Output: The response data sent to the device.

[0559] Step 6:

[0560] The device will display the answer.

[0561] Specific operation: The terminal displays the received response data on the screen in a format that is easy for the user to view.

[0562] Input: The response data sent from the server.

[0563] Output: The answer that appears on the screen (e.g., "Jupiter").

[0564] Step 7:

[0565] The user enters a score for the answer.

[0566] Specific operation: The user enters an evaluation score for the displayed answer and clicks the submit button.

[0567] Input: The score entered by the user (e.g., "5 / 5").

[0568] Output: The entered score data is sent to the server.

[0569] Step 8:

[0570] The server receives the scores and stores them in a database.

[0571] Specific Operation: The server stores the received score data in a database along with the associated question and answer data.

[0572] Input: Score data submitted by the user.

[0573] Output: Score, question and answer data stored in a database.

[0574] Step 9:

[0575] The server extracts the answers with the highest scores.

[0576] Specific operation: The server periodically checks the database and extracts answers with a score of 4 or higher.

[0577] Input: Score, question and answer data stored in the database.

[0578] Output: Extracted high-scoring answer data.

[0579] Step 10:

[0580] The server queries the external information source.

[0581] Specific operation: The server queries the extracted high-scoring answers using external information sources to verify their accuracy and reliability.

[0582] Input: Extracted high-scoring answer data.

[0583] Output: Query result data obtained from external sources.

[0584] Step 11:

[0585] The server stores the query results in a database and notifies the user.

[0586] Specific operation: The query results are saved in the database and the confirmed information is notified to the user.

[0587] Input: Query result data from external sources.

[0588] Output: A notification with the confirmed information (e.g., "Jupiter has been confirmed to be the largest planet in the solar system").

[0589] (Application example 1)

[0590] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0591] Modern electronic payment services require rapid and accurate responses to user information requests. However, many current systems rely on human intervention to meet these requests, resulting in problems of inefficiency and reliability. Furthermore, these systems lack a means to effectively evaluate user satisfaction and reflect that evaluation in service improvements. Therefore, there is a need for an efficient system that can provide rapid and accurate answers to user questions and reflect user evaluations of those answers in the system.

[0592] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0593] In this invention, the server includes a means for causing the generative AI model to generate answers in real time, a means for displaying the answers generated by the generative AI model and providing a dedicated interface for users to input their ratings, and a means for enhancing reliability based on the results of inquiries in external information sources, thereby enabling quick and accurate answers to users' questions and effective collection and management of ratings for the answers.

[0594] A "terminal means" is a device used by a user to input a question.

[0595] "Server means" refers to a central processing unit that receives input questions and transmits them to a generative AI model to provide answers.

[0596] "User means" refers to the interface and functionality that allows a user to score the generated answers.

[0597] "Database means" refers to a database system for storing and managing scores, questions and answers.

[0598] "External Source" means an external, reliable source of information used to query and augment the reliability of the answers provided by the generative AI model.

[0599] A "generative AI model" is an artificial intelligence model that generates answers to input questions.

[0600] The "dedicated interface" refers to a dedicated operation screen and function that allows users to check the answers of the generated AI model and enter evaluation scores.

[0601] "Real-time" means that processing occurs almost instantaneously, with immediate response to user input.

[0602] "Measures to enhance trustworthiness" refers to a function that verifies the accuracy of the answers of the generated AI model based on the results of inquiries from external information sources, thereby improving trustworthiness.

[0603] MODE FOR CARRYING OUT THE INVENTION

[0604] This invention provides a system that quickly and accurately answers user questions. The system includes a terminal, a server, a generative AI model, a database, an external information source, and a dedicated interface. The specific functions and operations of each element are described below.

[0605] Terminal means

[0606] Users enter questions using devices such as smartphones or computers. The devices have an input field and a submit button, and the questions entered by the user are sent to the server.

[0607] Server Means

[0608] The server receives questions sent by users and sends them to the generative AI model. This process involves a program running on the server. Specifically, a web server using Flask receives the question and sends it to the generative AI model using OpenAI's API. The server then receives the generated answer and sends it back to the user's device.

[0609] Generative AI Models

[0610] A generative AI model (e.g., OpenAI's GPT-3) generates answers to user questions. The generative AI model generates answers based on questions sent from the server and sends the answers back to the server. An example of a prompt sentence used here is, "What should I do if I don't receive my electronic payment receipt?"

[0611] Dedicated Interface

[0612] The generated answers are displayed on the user's device, and the dedicated interface includes a scoring function for evaluating the answers, allowing the user to rate the appropriateness of the answers on a scale of 1 to 5. The entered score is then sent to the server.

[0613] Database Means

[0614] The server stores the received scores and the corresponding questions and answers in a database, using a database management system such as SQLite. The stored data is later used to extract and analyze high-scoring answers.

[0615] external information sources

[0616] The server periodically checks the database and extracts the highest-scoring answers, then queries and strengthens the reliability of these answers using external sources, such as trusted data sources and specialized databases.

[0617] Specific examples of programs

[0618] For example, a user enters a question such as, "What should I do if I don't receive my electronic payment receipt?" The question is immediately received by the server and sent to a generative AI model (GPT-3). The generated answer is returned as, "Contact your electronic payment company and provide them with the transaction ID to request confirmation." The user rates this answer as "5 / 5" and enters a score. The server stores this score in a database and later extracts it as a high-scoring answer, verifying its reliability with an external source.

[0619] The system allows users to receive fast and accurate answers, improving the efficiency and reliability of electronic payment services.

[0620] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0621] Step 1:

[0622] A user inputs a question using a terminal. The user generates question data by entering the question in an input field on the terminal and clicking the send button. The input data is the user's question text. This question text is sent to the server.

[0623] Step 2:

[0624] The server receives the question sent by the user. It analyzes the received question text and formats it into a request format to send to the generative AI model. This request data is JSON format data including the question text. The server sends this data to the API that provides the generative AI model.

[0625] Step 3:

[0626] The generative AI model receives the API request and generates an answer to the question. The generated answer is sent back to the server in the form of an API response. This response data contains the text of the answer. The generative AI model analyzes the input question text and uses its internal algorithm to create the optimal answer text.

[0627] Step 4:

[0628] The server receives the answer returned from the generative AI model and sends it back to the user's device. The received answer data is JSON format data containing the answer text and related metadata. The server sends this data to the user's device.

[0629] Step 5:

[0630] The user's device displays the received answer on the user interface. The user checks the displayed answer and inputs an evaluation score for the answer using the scoring interface. The input data based on the scoring is the score value. When the user inputs the score and clicks the submit button, the score data is sent to the server.

[0631] Step 6:

[0632] The server receives the score data sent by the user, associates it with the question and answer, and stores it in a database. This score data includes the score value and metadata such as question ID and answer ID. The server manages this data by inserting it into the database.

[0633] Step 7:

[0634] The server periodically checks the database and extracts the top-scoring answers by analyzing the scores in the database using queries, which are then used to query external sources.

[0635] Step 8:

[0636] The server uses external information sources to verify the reliability of high-scoring answers. The data obtained from the external information sources is matched with the answer text of the generative AI model. Answer data that is verified as reliable through this verification process is stored in a database and notified to the user.

[0637] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0638] The present invention combines a system in which a user inputs a question, obtains an answer from a generation AI, evaluates the validity of the answer, and scores it, with an emotion engine that recognizes the user's emotions. This system includes a server, a terminal, user means, database means, an external source, a query means, and an emotion engine.

[0639] Enter your question

[0640] Terminal: The user uses the terminal to input a question. The terminal has an input field and a send button, and when the user inputs a question and clicks the send button, the question is sent to the server.

[0641] Receiving and processing questions

[0642] Server: Parses the received question and formats it as a request to the generation AI. An API request is made to send the question to the generation AI and retrieve the answer.

[0643] Generate and display answers

[0644] Generative AI: Generates an appropriate answer to the input question and sends it back to the server. The server then sends the received answer back to the user's device and displays it on the device.

[0645] Device: The received answer is displayed on the screen. For example, the answer "Jupiter" is displayed.

[0646] Scoring

[0647] User: Checks the answers and enters an evaluation score. The scoring interface is a form where a user selects a number, for example, from 1 to 5. The user enters the score and clicks the submit button, which sends the score to the server.

[0648] Emotion recognition by emotion engine

[0649] Emotion engine: It has the ability to analyze and recognize emotions from user input and behavior (e.g., typing speed, response confirmation time, etc.). Emotion data is used to improve the quality of user responses and feedback.

[0650] Storing and managing score and emotion data

[0651] Server: Stores the received scores and sentiment data in a database along with the corresponding questions and answers.

[0652] Extracting and querying high-scoring answers

[0653] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher. The extracted answers are then compared with external specialized databases and reliable information sources.

[0654] Saving and notifying query results

[0655] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[0656] Manage your subscription

[0657] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[0658] Specific examples

[0659] User: For example, a user types and submits a question: "Which is the largest planet in the solar system?"

[0660] Server: Receives the question and sends a request to the generation AI.

[0661] Generation AI: Generates the answer "It's Jupiter" and sends it back to the server.

[0662] Server: Receives the response and sends it to the device.

[0663] Terminal: Shows the answer, and the user enters a score of "5 / 5" and submits.

[0664] Emotion engine: Recognizes emotions from the user's input speed and behavior patterns and records that data.

[0665] Server: Receives scores and emotion data and stores them in a database.

[0666] Server: Periodically extracts high-scoring answers and queries them against external specialized databases.

[0667] Server: Notifies the user that the authenticity has been confirmed based on the query results.

[0668] Server: Manages user subscription status, notifies expiration and processes billing.

[0669] In this way, the present invention provides a system that allows users to evaluate the validity of the answers of the AI ​​generator and obtain reliable information through feedback that includes emotions. This system is easy for users to use and can provide reliable information.

[0670] The processing flow will be explained below.

[0671] Step 1:

[0672] User: Enters a question using a device and clicks the "Submit Question" button.

[0673] Step 2:

[0674] Terminal: Takes the entered question and sends it to the server as JSON format data, for example, "{"question": "Which is the largest planet in the solar system?"}".

[0675] Step 3:

[0676] Server: Receives question data, formats the question appropriately, and creates an API request to the generation AI.

[0677] Step 4:

[0678] Server: Sends a request containing question data to the generation AI.

[0679] Step 5:

[0680] Generative AI: Analyzes the question data received from the server and generates an answer to the question. For example, it generates an answer such as "It's Jupiter" and sends it back to the server.

[0681] Step 6:

[0682] Server: Receives the answer returned by the generation AI and sends it to the user's device.

[0683] Step 7:

[0684] Terminal: Displays the received answer on the screen. For example, the answer "Jupiter" is displayed on the screen.

[0685] Step 8:

[0686] User: Enter a rating score for the displayed answer. For example, rate it from 1 to 5 and give it a score of "5 / 5." Click the "Submit Score" button.

[0687] Step 9:

[0688] Device: The entered score is sent to the server as JSON format data, for example, "{"question_id": 123, "score": 5}".

[0689] Step 10:

[0690] Server: Stores the received scores in a database along with the corresponding question and answer data.

[0691] Step 11:

[0692] Emotion engine: Recognizes the user's emotions by analyzing the user's input speed, typing patterns, and response confirmation time. For example, if the input speed is slow, it is recognized as "anxious," and if it is fast, it is recognized as "confident."

[0693] Step 12:

[0694] Server: Receives emotion data obtained from the emotion engine and stores it in a database along with the corresponding question and answer data.

[0695] Step 13:

[0696] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher.

[0697] Step 14:

[0698] Server: queries external sources (specialized databases and reliable information sources) for extracted high-scoring answers.

[0699] Step 15:

[0700] External Source: Provides data in response to a query from the server, e.g., sends back to the server information that "Jupiter has been confirmed to be the largest planet in the solar system."

[0701] Step 16:

[0702] Server: Stores the query results from external sources in a database and notifies the user of the results, for example, sending a notification that "Jupiter has been confirmed to be the largest planet in the solar system."

[0703] Step 17:

[0704] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[0705] Example 2

[0706] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0707] Conventional systems do not properly evaluate the validity of the answers received from the AI ​​generator and provide scoring and feedback to ensure reliable information. As a result, the reliability of the information received by the user is reduced, resulting in an unsatisfactory user experience. Furthermore, there is a lack of means to improve the quality of the feedback by utilizing user emotional data.

[0708] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means having a function of receiving an input question, analyzing it, formatting it for the generation AI, and obtaining an answer, means for displaying the generated answer on a terminal and allowing the user to score it, means having a function of analyzing the user's emotional data using an emotion engine, database means for saving and managing scores and related emotional data, and means for extracting answers with high scores and checking their reliability with an external information source. This allows the user to evaluate the validity of the answer from the generation AI and obtain reliable information, while also making it possible to improve the quality of the user experience based on the emotional data.

[0709] The "device means for inputting a question" refers to a terminal or device that allows a user to freely input a question and transmits the input question to a server for subsequent processing.

[0710] "Server means having the function of receiving, analyzing, formatting for the generation AI, and obtaining the answer" refers to the server function of receiving a question entered by a user, analyzing it, converting it into an appropriate format for the generation AI, and obtaining the answer.

[0711] "A means for the generated answers to be displayed on the device and scored by the user" refers to a function that displays the answers obtained from the generation AI on the user's device and provides an interface for the user to evaluate the answers.

[0712] "Means having a function for analyzing user emotional data using an emotion engine" refers to a function within the system for analyzing emotions from user input and behavioral patterns and collecting that data.

[0713] "Database means for saving and managing scores and related emotional data" refers to the function of a database for saving and managing scores entered by users and the emotional data associated with them.

[0714] "Means for extracting answers with high scores and checking their reliability with external information sources" refers to a system function that periodically extracts answers that have received particularly high scores from the stored scores and checks their reliability by checking with external, reliable databases or information sources.

[0715] The present invention relates to a system in which a user inputs a question, obtains an answer from a generation AI, and the user evaluates the validity of the answer and scores it. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the feedback can be improved. This system includes a server, a terminal, user means, database means, an external source, query means, and an emotion engine.

[0716] Enter your question

[0717] Terminal: The user uses the terminal to input a question. The terminal has an input field and a send button, and when the user inputs a question and clicks the send button, the question is sent to the server.

[0718] Receiving and processing questions

[0719] Server: Parses the received questions and formats them as requests for the generation AI. Protocols such as RESTful APIs and GraphQL can be used to enable API communication with other systems.

[0720] Generate and display answers

[0721] Generative AI: Generates an appropriate answer to the input question and returns the answer to the server. Generative AI can use, for example, a large-scale language model. Below is a specific example of a prompt sentence.

[0722] Examples:

[0723] User-supplied question: "Which is the largest planet in the solar system?"

[0724] The AI ​​responds: "Jupiter."

[0725] Server: Returns the received answer to the user's terminal and displays it on the terminal.

[0726] Terminal: Displays the received response on the screen.

[0727] Scoring

[0728] User: Checks the answers and enters an evaluation score. The scoring interface allows users to select a number from 1 to 5, for example. The user enters the score and clicks the submit button, which sends the score to the server.

[0729] Emotion recognition by emotion engine

[0730] Emotion engine: It has the ability to analyze and recognize emotions from user input and behavior (e.g., typing speed, response confirmation time, etc.). Emotion data is used to improve the quality of user responses and feedback.

[0731] Storing and managing score and emotion data

[0732] Server: Stores the received scores and emotion data along with the corresponding questions and answers in a database. The database can be, for example, a relational database or a NoSQL database.

[0733] Extracting and querying high-scoring answers

[0734] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher. The extracted answers are then compared with external specialized databases and reliable information sources.

[0735] Saving and notifying query results

[0736] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[0737] Manage your subscription

[0738] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[0739] In this way, by providing a system that comprehensively handles everything from question input to answer generation, scoring, emotion recognition, extraction and query of high-scoring answers, and even subscription management, it is possible to provide users with highly reliable information. Furthermore, the introduction of an emotion engine is expected to improve the user experience.

[0740] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0741] Step 1:

[0742] User: The user uses the terminal to input a question. Specifically, the user writes the question in the input field displayed on the terminal and clicks the send button. The input data is a text-based question. For example, the user might enter "Which is the largest planet in the solar system?" The output of this step is the input question sent to the server as a data packet.

[0743] Step 2:

[0744] Server: Receives the question sent from the device. The received data is a text-formatted question. The server analyzes the received question and formats it as a request for the generation AI. Specifically, it converts the question into an API request format such as JSON. The converted request data is sent to the generation AI, which is the output of this step.

[0745] Step 3:

[0746] Server: Sends an API request to the generation AI. The request includes the converted question. The server sends an HTTP POST request specifying the generation AI's endpoint URL and providing the necessary API key or token. The input to this step is the formatted API request data, and the output is the answer data returned by the generation AI.

[0747] Step 4:

[0748] Generative AI: Generates answers based on the received API request. Generative AI uses a large language model to create an answer to the input question. For example, the answer to the question "Which is the largest planet in the solar system?" is generated as "Jupiter." The generated answer data is sent back to the server as the output of this step.

[0749] Step 5:

[0750] Server: Sends the answer data received from the generation AI to the user's device. Analyzes the received answer data and converts it into a format that can be displayed on the device. Specifically, the answer from the generation AI is included in the HTTP response as a text message. The converted answer data is sent to the device and becomes the output of this step.

[0751] Step 6:

[0752] Terminal: The received answer is displayed on the screen. For example, the answer "Jupiter" is displayed on the user's terminal. The user confirms the displayed answer in this step.

[0753] Step 7:

[0754] User: The user evaluates the displayed answers and enters a score. The user follows the scoring interface to select a numerical score, for example, between 1 and 5. After entering the score, the user clicks the submit button, which sends the score to the server. The output of this step is the entered score data.

[0755] Step 8:

[0756] Emotion engine: Analyzes emotions from the user's input speed and behavioral patterns. Behavioral data such as input speed and response confirmation time are input. The emotion engine analyzes this data and determines the user's emotions. For example, if the typing speed is fast, it is analyzed as being excited. The analysis results are sent to the server and become the output of this step.

[0757] Step 9:

[0758] Server: Stores the received score and emotion data in the database. Creates a new record in the database to store the question, answer, and their corresponding score and emotion data. The input of this step is the score data and emotion data, and the output is a message confirming the stored data.

[0759] Step 10:

[0760] Server: Periodically checks the database and extracts answers with high scores. Specifically, it uses a query to extract records with a score of 4 or higher. It then queries external sources for verification of those records. It communicates with external databases to verify the accuracy and reliability of the answers. The output of this step is external data for verification of reliability.

[0761] Step 11:

[0762] Server: Stores the query results obtained from external sources in a database and notifies the user. Stores the query results as a new record and sends a message to the user device informing them of the results. For example, "Jupiter has been confirmed to be the largest planet in the solar system." The output of this step is the storage of the query results and a message to the user.

[0763] Step 12:

[0764] Server: Manages the user's subscription status and notifies them when the expiration date approaches. Specifically, it monitors the subscription expiration date and sends reminder notifications to the user when the expiration date approaches. It also handles billing as needed. The output of this step is a subscription renewal notification and a billing confirmation message.

[0765] (Application example 2)

[0766] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0767] Conventional question-answering systems using generative AI do not fully consider user emotions and feedback, and have limited means to guarantee the reliability of generated answers. This can result in low user satisfaction with the validity and reliability of answers. Furthermore, in the security field, the accuracy of the information provided is extremely important, and inquiries from reliable sources are essential. The present invention aims to solve these issues and provide a question-answering system that users can use with confidence.

[0768] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0769] In this invention, the server includes terminal means for inputting a question, server means for receiving the input question and providing a generated answer, user means for scoring the generated answer, database means for saving and managing the scores, means for extracting answers with high scores and querying external sources, emotion engine means for analyzing and recognizing emotions from the user's input and actions, and query means for confirming the reliability of answers to user questions with external expert information sources. This makes it possible to generate appropriate answers to user questions and guarantee their reliability, as well as to provide better services based on the user's emotions and feedback.

[0770] The "terminal means for inputting a question" refers to a device that allows a user to input and submit a question. This device includes an input field and a submit button.

[0771] "Server means for receiving input questions and providing generated answers" refers to a server that has the function of receiving questions from users, generating appropriate answers using generation AI, and sending them to the terminal.

[0772] "User means for scoring generated answers" refers to an interface for users to input rating scores for generated answers, thereby collecting user ratings.

[0773] "Database means for storing and managing scores" refers to a database system that stores scores entered by users and other related data and that can be accessed as needed.

[0774] "Means for extracting highly scored answers and querying external sources" refers to the functionality for selecting highly scored answers from the database and querying their reliability with external expert sources.

[0775] "Emotion engine means for analyzing and recognizing emotions from user input and behavior" refers to a system that reads and analyzes emotions from the user's input speed, behavioral patterns, etc. This data will be used to improve services.

[0776] "A means for checking the reliability of answers to user questions from external expert information sources" refers to a function for querying the accuracy and reliability of generated answers from external expert information sources and reflecting the results.

[0777] "Generative AI model" refers to an artificial intelligence model used to generate appropriate answers based on user questions.

[0778] A "prompt" is a text that describes a question or request to the generation AI, which then generates an answer based on the prompt.

[0779] This invention is a system in which a user inputs a question, a generative AI provides an answer to that question, and evaluates the validity of the answer. The system includes an emotion engine that analyzes the user's emotions and also includes a function to verify the reliability of the generated answer with an external expert information source. A method for implementing this system is described below.

[0780] Terminal means:

[0781] Users input questions using devices such as smartphones and personal computers. The devices have an input field for entering questions and a submit button.

[0782] Server means:

[0783] The server receives the question sent from the device, converts it into an appropriate format, and sends a request to the generative AI model. The generative AI model generates an answer to the question and sends it back to the server. The server receives the answer and sends it to the device to display it to the user. Specifically, a web server can be built using the Python-based Flask framework, for example. A commonly used generative AI model could be GPT-3.

[0784] Emotion Engine means:

[0785] The server contains an emotion engine that analyzes and recognizes emotions from the user's input speed and behavioral patterns. The emotion engine is implemented using, for example, TextBlob, a natural language processing library. It analyzes the speed and timing of the user's input of questions and quantifies positive or negative emotions.

[0786] User means:

[0787] Once a user receives the generated answer, they can assign a rating to it. The user interface uses a scoring system ranging from 1 to 5. Once the user enters and submits the score, it is stored on the server.

[0788] Database Methods:

[0789] The server stores the scores and emotion data entered by the user in a database, which can be constructed using SQLite or MySQL, for example.

[0790] Inquiry methods:

[0791] The server periodically checks the database and extracts the top-scoring answers, then queries external sources, such as specialized information services or APIs, to verify the reliability of the generated answers.

[0792] Examples:

[0793] For example, a user enters a question such as, "How can I improve my home Wi-Fi security?" The server sends this question to a generative AI model, which responds, "We recommend using a strong password, using the latest encryption methods, and updating your router's firmware." The answer is then provided to the user via the server. The user rates this answer "5 / 5," and the server stores this score and sentiment data. The server periodically checks this answer against expert sources, and if its reliability is confirmed, records the information in a database and notifies the user.

[0794] As a result, this system allows users to evaluate the validity of the generated AI's answers and provide feedback that includes emotions, making it possible to provide users with more reliable information.

[0795] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0796] Step 1:

[0797] The terminal accepts questions from the user in an input field. When the user enters a question and presses the send button, the question is sent to the server.

[0798] Input: The question entered by the user

[0799] Output: The question sent to the server

[0800] Step 2:

[0801] The server parses the received question and formats it as a request to the generative AI model, which then sends the request to the generative AI model.

[0802] Input: Question received from the terminal

[0803] Output: The request sent to the generative AI model

[0804] Step 3:

[0805] The generative AI model receives the formatted request and generates an appropriate answer to the question, which is then sent back to the server.

[0806] Input: The request sent by the server

[0807] Output: The generated answer

[0808] Step 4:

[0809] The server sends the answer received from the generative AI model back to the device and displays it to the user.

[0810] Input: The answer received from the generative AI model

[0811] Output: Answer sent back to the terminal

[0812] Step 5:

[0813] The terminal displays the received answer to the user. The user checks the answer and enters an evaluation score. The evaluation score is entered and sent.

[0814] Input: The answer returned by the server

[0815] Output: User-entered rating score

[0816] Step 6:

[0817] The server receives the user-submitted rating score, stores the data in a database, and, if the rating score is high (e.g., 4 or higher), queries the answer to an external source.

[0818] Input: Rating score from device

[0819] Output: Scores stored in a database and query requests sent to external sources

[0820] Step 7:

[0821] The external source receives the query request from the server and verifies the authenticity of the generated answer, which is then sent back to the server.

[0822] Input: A query request from the server

[0823] Output: Reliability check result

[0824] Step 8:

[0825] The server receives the results of the trust verification from the external source, stores them in a database, and notifies the user of the results.

[0826] Input: Reliability check results from external sources

[0827] Output: Trust verification results stored in the database and notified to the user

[0828] Through these steps, the system generates appropriate answers to users' questions, guarantees their reliability, and collects feedback, including users' emotions.

[0829] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0830] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0831] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0832] [Third embodiment]

[0833] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0834] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0835] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0836] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0837] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0838] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0839] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0840] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0841] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0842] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0843] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0844] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0845] The present invention is a system in which a user inputs a question, obtains an answer from a generation AI, and evaluates and scores the validity of the answer. The system includes a server, a terminal, a user means, a database means, an external source, and a query means.

[0846] Enter your question

[0847] Terminal: The user uses the terminal to input a question. The terminal must have an input field and a submit button. When the user inputs a question and clicks the submit button, the question is sent to the server.

[0848] Receiving and processing questions

[0849] Server: Parses the received question and formats it as a request to the generation AI. An API request is made to send the question to the generation AI and get the answer.

[0850] Generate and display answers

[0851] Generative AI: Generates an appropriate answer to the input question and sends it back to the server. The server then sends the received answer back to the user's device and displays it on the device.

[0852] Terminal: The received answers are displayed on the screen. The interface for users to check the answers should be designed with ease of viewing and operation in mind.

[0853] Scoring

[0854] User: The user inputs an evaluation score for the displayed answer. The scoring interface can be, for example, a format where a user selects a number from 1 to 5. After inputting the score, the user clicks the submit button to send the score to the server.

[0855] Score storage and management

[0856] Server: Stores the received scores along with the corresponding questions and answers in a database. This database should employ an appropriate database management system (DBMS) to effectively manage the scoring information.

[0857] Extracting and querying high-scoring answers

[0858] Server: Regularly checks the database and extracts answers with high scores. For example, a system is built to extract answers with a score of 4 or higher.

[0859] External sources: The extracted answers are checked against external expert databases and reliable information sources. The data obtained from external sources is used to strengthen the reliability of the generated AI's answers.

[0860] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification to the user saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[0861] Manage your subscription

[0862] Server: Manages the user's subscription status, notifies them of expiration dates, and connects with the payment system to process periodic charges.

[0863] Specific examples

[0864] User: For example, a user types and submits a question: "Which is the largest planet in the solar system?"

[0865] Server: Receives the question and sends a request to the generation AI.

[0866] Generation AI: Generates the answer "It's Jupiter" and sends it back to the server.

[0867] Server: Receives the response and sends it to the device.

[0868] Terminal: Shows the answer, and the user enters a score of "5 / 5" and submits.

[0869] Server: Receives the scores and stores them in a database.

[0870] Server: Periodically extracts high-scoring answers and queries them against external specialized databases.

[0871] Server: Notifies the user that the authenticity has been confirmed based on the query results.

[0872] In this way, the present invention provides a system that allows users to evaluate the validity of answers generated by AI and obtain reliable information. This system is easy for users to use and can provide reliable information.

[0873] The processing flow will be explained below.

[0874] Step 1:

[0875] User: Enters a question using a device and clicks the "Submit Question" button.

[0876] Step 2:

[0877] Terminal: Takes the entered question and sends it to the server as JSON format data. This data includes the format {"question": "Which is the largest planet in the solar system?"}.

[0878] Step 3:

[0879] Server: Receives question data, formats the question into an appropriate format, and prepares an API request to the generation AI.

[0880] Step 4:

[0881] Server: Sends a request containing question data to the generation AI.

[0882] Step 5:

[0883] Generative AI: Analyzes the question data received from the server and generates an answer to the question. For example, it generates an answer such as "It's Jupiter" and sends it back to the server.

[0884] Step 6:

[0885] Server: Receives the answer returned by the generation AI and sends it to the user's device.

[0886] Step 7:

[0887] Device: Displays the received answer on the screen, e.g., the text "Jupiter" is displayed in a visible form to the user.

[0888] Step 8:

[0889] User: Enter a rating score for the displayed answer. For example, rate it from 1 to 5 and give it a score of "5 / 5." Click the "Submit Score" button.

[0890] Step 9:

[0891] Device: The entered score is sent to the server as JSON format data, which includes the format "{"question_id": 123, "score": 5}", for example.

[0892] Step 10:

[0893] Server: Stores the received scores in a database along with the corresponding question and answer data.

[0894] Step 11:

[0895] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher.

[0896] Step 12:

[0897] Server: Query the extracted high-scoring answers using external sources (e.g., specialized databases or reliable information sources).

[0898] Step 13:

[0899] External Source: Provides query results in response to queries received from the server, e.g., returns data such as "Confirmed that Jupiter is the largest planet in the solar system."

[0900] Step 14:

[0901] Server: Stores the query results in a database and notifies the user of the results. The user is informed that the information is reliable.

[0902] Step 15:

[0903] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing appropriately. For example, if a user's subscription is due for renewal, the server initiates billing.

[0904] Example 1

[0905] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0906] Conventional question-answering systems do not guarantee the validity or reliability of the generated answers, and users have limited means to evaluate the information provided. Furthermore, for answers with high scores, there is no way to verify their reliability with an external, reliable information source, making it difficult to provide users with reliable information. These issues need to be addressed.

[0907] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0908] In this invention, the server includes a means for receiving questions and sending them to the generative AI model, a means for acquiring the generated answers and returning them to the user's terminal, and a means for storing the evaluated scores in a database, which allows high-scoring answers to be extracted and queried in an external reliable information source.

[0909] "Information processing device means" refers to the device used by the user to input a query, and typically includes a desktop computer, laptop, smartphone, tablet, etc.

[0910] "Data processing means" refers to a server that has the functionality to receive input questions and send requests to the generative AI model to obtain answers.

[0911] The "evaluation means" refers to an interface that allows a user to input a score for a generated answer and evaluate it.

[0912] "Storage means" refers to a database system for storing and managing users' scores and corresponding questions and answers.

[0913] "Generative AI model" refers to an artificial intelligence model used to generate appropriate answers to input questions.

[0914] "External sources" refers to reliable databases or sources used to verify the reliability of the generated answers, examples of which include specialist databases and recognized sources.

[0915] "Scoring" refers to the rating points that users give to generated answers, typically in the form of selecting a number between 1 and 5.

[0916] "Consulting" refers to the process of using external sources to verify the accuracy and reliability of the generated answers.

[0917] The present invention provides a system in which a user inputs a question, obtains an answer from a generative AI model, and the user evaluates the validity of the answer. The system includes an information processing device, a data processing device, an evaluation device, a storage device, and an external information source.

[0918] information processing device means

[0919] The user uses a data processing device to input the question, typically a desktop computer, laptop, smartphone, or tablet. The user uses the data processing device to enter the question into an input field and clicks a submit button.

[0920] Data Processing Means

[0921] The server, which is the data processing means, receives the question sent from the information processing means. The server analyzes the question and formats it as a request to the generative AI model. The server then sends an API request to the generative AI model to obtain the answer.

[0922] Generative AI Models

[0923] The generative AI model generates appropriate answers to questions received from the server. For example, if a user sends a question such as "Which is the largest planet in the solar system?", the generative AI model generates the answer "Jupiter" and sends it back to the server.

[0924] Returning and displaying answers

[0925] The server returns the answer received from the generative AI model to the information processing device means, which displays the answer on a screen so that the user can easily check it.

[0926] Evaluation methods

[0927] The user inputs an evaluation score for the displayed answer. This evaluation is done by selecting a number, for example, from 1 to 5. When the user inputs the score and clicks the submit button, the evaluation score is sent to the server.

[0928] storage means

[0929] The server stores the received scores together with the corresponding questions and answers in a storage means or database, which may employ a suitable database management system such as MySQL.

[0930] Extracting and querying high-scoring answers

[0931] The server periodically checks the database and extracts high-scoring answers. For example, answers with a score of 4 or higher are automatically extracted. For the extracted answers, the server queries external sources to verify the accuracy and reliability of the generated AI model's answers. For example, it verifies that "Jupiter is the largest planet in the solar system" with specialized databases and authorized sources.

[0932] Manage your subscription

[0933] The server manages the user's subscription status, notifies them when the expiration date is approaching, and handles periodic billing, which is handled in cooperation with a payment system (e.g., Stripe, PayPal, etc.).

[0934] Specific examples

[0935] For example, a user inputs and submits the question "Which is the largest planet in the solar system?" The server receives this question and sends a request to the generative AI model. After receiving the answer "Jupiter" from the generative AI model, the server transmits this answer to the information processing means and displays it. The user inputs a rating of "5 / 5" for the displayed answer and transmits it. The server receives the score and stores it in the storage means. The server periodically checks the database, extracts answers with high scores, and queries external information sources. The user is notified of the confirmed, reliable answers.

[0936] In this way, the present invention provides a system that allows users to evaluate the validity of the answers of generative AI models and obtain reliable information.

[0937] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0938] Step 1:

[0939] The user types a question into the terminal.

[0940] Specific Actions: Using the input field on the device, the user enters a question and clicks the submit button.

[0941] Input: Text entered by the user (e.g., "Which is the largest planet in the solar system?").

[0942] Output: The entered question data is sent to the server.

[0943] Step 2:

[0944] The server receives the query and parses it.

[0945] Specific operation: The server receives the query data from the terminal, analyzes the content, and converts it into an appropriate data format.

[0946] Input: Question data sent from the terminal.

[0947] Output: Data formatted for API requests to the generative AI model.

[0948] Step 3:

[0949] The server sends an API request to the generative AI model.

[0950] Specific operation: The server sends a formatted request to the API endpoint of the generative AI model.

[0951] Input: Question data in the form of an API request.

[0952] Output: The answer data generated by the generative AI model.

[0953] Step 4:

[0954] A generative AI model generates answers to questions.

[0955] How it works: The generative AI model analyzes the requested question and generates an appropriate answer.

[0956] Input: Question data in the form of an API request from the server.

[0957] Output: The generated answer data (e.g., "It's Jupiter").

[0958] Step 5:

[0959] The server receives the response and sends it to the terminal.

[0960] Specific operation: The server receives the response data from the generative AI model and sends it to the terminal.

[0961] Input: Answer data from the generative AI model.

[0962] Output: The response data sent to the device.

[0963] Step 6:

[0964] The device will display the answer.

[0965] Specific operation: The terminal displays the received response data on the screen in a format that is easy for the user to view.

[0966] Input: The response data sent from the server.

[0967] Output: The answer that appears on the screen (e.g., "Jupiter").

[0968] Step 7:

[0969] The user enters a score for the answer.

[0970] Specific operation: The user enters an evaluation score for the displayed answer and clicks the submit button.

[0971] Input: The score entered by the user (e.g., "5 / 5").

[0972] Output: The entered score data is sent to the server.

[0973] Step 8:

[0974] The server receives the scores and stores them in a database.

[0975] Specific Operation: The server stores the received score data in a database along with the associated question and answer data.

[0976] Input: Score data submitted by the user.

[0977] Output: Score, question and answer data stored in a database.

[0978] Step 9:

[0979] The server extracts the answers with the highest scores.

[0980] Specific operation: The server periodically checks the database and extracts answers with a score of 4 or higher.

[0981] Input: Score, question and answer data stored in the database.

[0982] Output: Extracted high-scoring answer data.

[0983] Step 10:

[0984] The server queries the external information source.

[0985] Specific operation: The server queries the extracted high-scoring answers using external information sources to verify their accuracy and reliability.

[0986] Input: Extracted high-scoring answer data.

[0987] Output: Query result data obtained from external sources.

[0988] Step 11:

[0989] The server stores the query results in a database and notifies the user.

[0990] Specific operation: The query results are saved in the database and the confirmed information is notified to the user.

[0991] Input: Query result data from external sources.

[0992] Output: A notification with the confirmed information (e.g., "Jupiter has been confirmed to be the largest planet in the solar system").

[0993] (Application example 1)

[0994] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0995] Modern electronic payment services require rapid and accurate responses to user information requests. However, many current systems rely on human intervention to meet these requests, resulting in problems of inefficiency and reliability. Furthermore, these systems lack a means to effectively evaluate user satisfaction and reflect that evaluation in service improvements. Therefore, there is a need for an efficient system that can provide rapid and accurate answers to user questions and reflect user evaluations of those answers in the system.

[0996] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0997] In this invention, the server includes a means for causing the generative AI model to generate answers in real time, a means for displaying the answers generated by the generative AI model and providing a dedicated interface for users to input their ratings, and a means for enhancing reliability based on the results of inquiries in external information sources, thereby enabling quick and accurate answers to users' questions and effective collection and management of ratings for the answers.

[0998] A "terminal means" is a device used by a user to input a question.

[0999] "Server means" refers to a central processing unit that receives input questions and transmits them to a generative AI model to provide answers.

[1000] "User means" refers to the interface and functionality that allows a user to score the generated answers.

[1001] "Database means" refers to a database system for storing and managing scores, questions and answers.

[1002] "External Source" means an external, reliable source of information used to query and augment the reliability of the answers provided by the generative AI model.

[1003] A "generative AI model" is an artificial intelligence model that generates answers to input questions.

[1004] The "dedicated interface" refers to a dedicated operation screen and function that allows users to check the answers of the generated AI model and enter evaluation scores.

[1005] "Real-time" means that processing occurs almost instantaneously, with immediate response to user input.

[1006] "Measures to enhance trustworthiness" refers to a function that verifies the accuracy of the answers of the generated AI model based on the results of inquiries from external information sources, thereby improving trustworthiness.

[1007] MODE FOR CARRYING OUT THE INVENTION

[1008] This invention provides a system that quickly and accurately answers user questions. The system includes a terminal, a server, a generative AI model, a database, an external information source, and a dedicated interface. The specific functions and operations of each element are described below.

[1009] Terminal means

[1010] Users enter questions using devices such as smartphones or computers. The devices have an input field and a submit button, and the questions entered by the user are sent to the server.

[1011] Server Means

[1012] The server receives questions sent by users and sends them to the generative AI model. This process involves a program running on the server. Specifically, a web server using Flask receives the question and sends it to the generative AI model using OpenAI's API. The server then receives the generated answer and sends it back to the user's device.

[1013] Generative AI Models

[1014] A generative AI model (e.g., OpenAI's GPT-3) generates answers to user questions. The generative AI model generates answers based on questions sent from the server and sends the answers back to the server. An example of a prompt sentence used here is, "What should I do if I don't receive my electronic payment receipt?"

[1015] Dedicated Interface

[1016] The generated answers are displayed on the user's device, and the dedicated interface includes a scoring function for evaluating the answers, allowing the user to rate the appropriateness of the answers on a scale of 1 to 5. The entered score is then sent to the server.

[1017] Database Means

[1018] The server stores the received scores and the corresponding questions and answers in a database, using a database management system such as SQLite. The stored data is later used to extract and analyze high-scoring answers.

[1019] external information sources

[1020] The server periodically checks the database and extracts the highest-scoring answers, then queries and strengthens the reliability of these answers using external sources, such as trusted data sources and specialized databases.

[1021] Specific examples of programs

[1022] For example, a user enters a question such as, "What should I do if I don't receive my electronic payment receipt?" The question is immediately received by the server and sent to a generative AI model (GPT-3). The generated answer is returned as, "Contact your electronic payment company and provide them with the transaction ID to request confirmation." The user rates this answer as "5 / 5" and enters a score. The server stores this score in a database and later extracts it as a high-scoring answer, verifying its reliability with an external source.

[1023] The system allows users to receive fast and accurate answers, improving the efficiency and reliability of electronic payment services.

[1024] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1025] Step 1:

[1026] A user inputs a question using a terminal. The user generates question data by entering the question in an input field on the terminal and clicking the send button. The input data is the user's question text. This question text is sent to the server.

[1027] Step 2:

[1028] The server receives the question sent by the user. It analyzes the received question text and formats it into a request format to send to the generative AI model. This request data is JSON format data including the question text. The server sends this data to the API that provides the generative AI model.

[1029] Step 3:

[1030] The generative AI model receives the API request and generates an answer to the question. The generated answer is sent back to the server in the form of an API response. This response data contains the text of the answer. The generative AI model analyzes the input question text and uses its internal algorithm to create the optimal answer text.

[1031] Step 4:

[1032] The server receives the answer returned from the generative AI model and sends it back to the user's device. The received answer data is JSON format data containing the answer text and related metadata. The server sends this data to the user's device.

[1033] Step 5:

[1034] The user's device displays the received answer on the user interface. The user checks the displayed answer and inputs an evaluation score for the answer using the scoring interface. The input data based on the scoring is the score value. When the user inputs the score and clicks the submit button, the score data is sent to the server.

[1035] Step 6:

[1036] The server receives the score data sent by the user, associates it with the question and answer, and stores it in a database. This score data includes the score value and metadata such as question ID and answer ID. The server manages this data by inserting it into the database.

[1037] Step 7:

[1038] The server periodically checks the database and extracts the top-scoring answers by analyzing the scores in the database using queries, which are then used to query external sources.

[1039] Step 8:

[1040] The server uses external information sources to verify the reliability of high-scoring answers. The data obtained from the external information sources is matched with the answer text of the generative AI model. Answer data that is verified as reliable through this verification process is stored in a database and notified to the user.

[1041] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1042] The present invention combines a system in which a user inputs a question, obtains an answer from a generation AI, evaluates the validity of the answer, and scores it, with an emotion engine that recognizes the user's emotions. This system includes a server, a terminal, user means, database means, an external source, a query means, and an emotion engine.

[1043] Enter your question

[1044] Terminal: The user uses the terminal to input a question. The terminal has an input field and a send button, and when the user inputs a question and clicks the send button, the question is sent to the server.

[1045] Receiving and processing questions

[1046] Server: Parses the received question and formats it as a request to the generation AI. An API request is made to send the question to the generation AI and retrieve the answer.

[1047] Generate and display answers

[1048] Generative AI: Generates an appropriate answer to the input question and sends it back to the server. The server then sends the received answer back to the user's device and displays it on the device.

[1049] Device: The received answer is displayed on the screen. For example, the answer "Jupiter" is displayed.

[1050] Scoring

[1051] User: Checks the answers and enters an evaluation score. The scoring interface is a form where a user selects a number, for example, from 1 to 5. The user enters the score and clicks the submit button, which sends the score to the server.

[1052] Emotion recognition by emotion engine

[1053] Emotion engine: It has the ability to analyze and recognize emotions from user input and behavior (e.g., typing speed, response confirmation time, etc.). Emotion data is used to improve the quality of user responses and feedback.

[1054] Storing and managing score and emotion data

[1055] Server: Stores the received scores and sentiment data in a database along with the corresponding questions and answers.

[1056] Extracting and querying high-scoring answers

[1057] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher. The extracted answers are then compared with external specialized databases and reliable information sources.

[1058] Saving and notifying query results

[1059] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[1060] Manage your subscription

[1061] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[1062] Specific examples

[1063] User: For example, a user types and submits a question: "Which is the largest planet in the solar system?"

[1064] Server: Receives the question and sends a request to the generation AI.

[1065] Generation AI: Generates the answer "It's Jupiter" and sends it back to the server.

[1066] Server: Receives the response and sends it to the device.

[1067] Terminal: Shows the answer, and the user enters a score of "5 / 5" and submits.

[1068] Emotion engine: Recognizes emotions from the user's input speed and behavior patterns and records that data.

[1069] Server: Receives scores and emotion data and stores them in a database.

[1070] Server: Periodically extracts high-scoring answers and queries them against external specialized databases.

[1071] Server: Notifies the user that the authenticity has been confirmed based on the query results.

[1072] Server: Manages user subscription status, notifies expiration and processes billing.

[1073] In this way, the present invention provides a system that allows users to evaluate the validity of the answers of the AI ​​generator and obtain reliable information through feedback that includes emotions. This system is easy for users to use and can provide reliable information.

[1074] The processing flow will be explained below.

[1075] Step 1:

[1076] User: Enters a question using a device and clicks the "Submit Question" button.

[1077] Step 2:

[1078] Terminal: Takes the entered question and sends it to the server as JSON format data, for example, "{"question": "Which is the largest planet in the solar system?"}".

[1079] Step 3:

[1080] Server: Receives question data, formats the question appropriately, and creates an API request to the generation AI.

[1081] Step 4:

[1082] Server: Sends a request containing question data to the generation AI.

[1083] Step 5:

[1084] Generative AI: Analyzes the question data received from the server and generates an answer to the question. For example, it generates an answer such as "It's Jupiter" and sends it back to the server.

[1085] Step 6:

[1086] Server: Receives the answer returned by the generation AI and sends it to the user's device.

[1087] Step 7:

[1088] Terminal: Displays the received answer on the screen. For example, the answer "Jupiter" is displayed on the screen.

[1089] Step 8:

[1090] User: Enter a rating score for the displayed answer. For example, rate it from 1 to 5 and give it a score of "5 / 5." Click the "Submit Score" button.

[1091] Step 9:

[1092] Device: The entered score is sent to the server as JSON format data, for example, "{"question_id": 123, "score": 5}".

[1093] Step 10:

[1094] Server: Stores the received scores in a database along with the corresponding question and answer data.

[1095] Step 11:

[1096] Emotion engine: Recognizes the user's emotions by analyzing the user's input speed, typing patterns, and response confirmation time. For example, if the input speed is slow, it is recognized as "anxious," and if it is fast, it is recognized as "confident."

[1097] Step 12:

[1098] Server: Receives emotion data obtained from the emotion engine and stores it in a database along with the corresponding question and answer data.

[1099] Step 13:

[1100] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher.

[1101] Step 14:

[1102] Server: queries external sources (specialized databases and reliable information sources) for extracted high-scoring answers.

[1103] Step 15:

[1104] External Source: Provides data in response to a query from the server, e.g., sends back to the server information that "Jupiter has been confirmed to be the largest planet in the solar system."

[1105] Step 16:

[1106] Server: Stores the query results from external sources in a database and notifies the user of the results, for example, sending a notification that "Jupiter has been confirmed to be the largest planet in the solar system."

[1107] Step 17:

[1108] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[1109] Example 2

[1110] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1111] Conventional systems do not properly evaluate the validity of the answers received from the AI ​​generator and provide scoring and feedback to ensure reliable information. As a result, the reliability of the information received by the user is reduced, resulting in an unsatisfactory user experience. Furthermore, there is a lack of means to improve the quality of the feedback by utilizing user emotional data.

[1112] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means having a function of receiving an input question, analyzing it, formatting it for the generation AI, and obtaining an answer, means for displaying the generated answer on a terminal and allowing the user to score it, means having a function of analyzing the user's emotional data using an emotion engine, database means for saving and managing scores and related emotional data, and means for extracting answers with high scores and checking their reliability with an external information source. This allows the user to evaluate the validity of the answer from the generation AI and obtain reliable information, while also making it possible to improve the quality of the user experience based on the emotional data.

[1113] The "device means for inputting a question" refers to a terminal or device that allows a user to freely input a question and transmits the input question to a server for subsequent processing.

[1114] "Server means having the function of receiving, analyzing, formatting for the generation AI, and obtaining the answer" refers to the server function of receiving a question entered by a user, analyzing it, converting it into an appropriate format for the generation AI, and obtaining the answer.

[1115] "A means for the generated answers to be displayed on the device and scored by the user" refers to a function that displays the answers obtained from the generation AI on the user's device and provides an interface for the user to evaluate the answers.

[1116] "Means having a function for analyzing user emotional data using an emotion engine" refers to a function within the system for analyzing emotions from user input and behavioral patterns and collecting that data.

[1117] "Database means for saving and managing scores and related emotional data" refers to the function of a database for saving and managing scores entered by users and the emotional data associated with them.

[1118] "Means for extracting answers with high scores and checking their reliability with external information sources" refers to a system function that periodically extracts answers that have received particularly high scores from the stored scores and checks their reliability by checking with external, reliable databases or information sources.

[1119] The present invention relates to a system in which a user inputs a question, obtains an answer from a generation AI, and the user evaluates the validity of the answer and scores it. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the feedback can be improved. This system includes a server, a terminal, user means, database means, an external source, query means, and an emotion engine.

[1120] Enter your question

[1121] Terminal: The user uses the terminal to input a question. The terminal has an input field and a send button, and when the user inputs a question and clicks the send button, the question is sent to the server.

[1122] Receiving and processing questions

[1123] Server: Parses the received questions and formats them as requests for the generation AI. Protocols such as RESTful APIs and GraphQL can be used to enable API communication with other systems.

[1124] Generate and display answers

[1125] Generative AI: Generates an appropriate answer to the input question and returns the answer to the server. Generative AI can use, for example, a large-scale language model. Below is a specific example of a prompt sentence.

[1126] Examples:

[1127] User-supplied question: "Which is the largest planet in the solar system?"

[1128] The AI ​​responds: "Jupiter."

[1129] Server: Returns the received answer to the user's terminal and displays it on the terminal.

[1130] Terminal: Displays the received response on the screen.

[1131] Scoring

[1132] User: Checks the answers and enters an evaluation score. The scoring interface allows users to select a number from 1 to 5, for example. The user enters the score and clicks the submit button, which sends the score to the server.

[1133] Emotion recognition by emotion engine

[1134] Emotion engine: It has the ability to analyze and recognize emotions from user input and behavior (e.g., typing speed, response confirmation time, etc.). Emotion data is used to improve the quality of user responses and feedback.

[1135] Storing and managing score and emotion data

[1136] Server: Stores the received scores and emotion data along with the corresponding questions and answers in a database. The database can be, for example, a relational database or a NoSQL database.

[1137] Extracting and querying high-scoring answers

[1138] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher. The extracted answers are then compared with external specialized databases and reliable information sources.

[1139] Saving and notifying query results

[1140] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[1141] Manage your subscription

[1142] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[1143] In this way, by providing a system that comprehensively handles everything from question input to answer generation, scoring, emotion recognition, extraction and query of high-scoring answers, and even subscription management, it is possible to provide users with highly reliable information. Furthermore, the introduction of an emotion engine is expected to improve the user experience.

[1144] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1145] Step 1:

[1146] User: The user uses the terminal to input a question. Specifically, the user writes the question in the input field displayed on the terminal and clicks the send button. The input data is a text-based question. For example, the user might enter "Which is the largest planet in the solar system?" The output of this step is the input question sent to the server as a data packet.

[1147] Step 2:

[1148] Server: Receives the question sent from the device. The received data is a text-formatted question. The server analyzes the received question and formats it as a request for the generation AI. Specifically, it converts the question into an API request format such as JSON. The converted request data is sent to the generation AI, which is the output of this step.

[1149] Step 3:

[1150] Server: Sends an API request to the generation AI. The request includes the converted question. The server sends an HTTP POST request specifying the generation AI's endpoint URL and providing the necessary API key or token. The input to this step is the formatted API request data, and the output is the answer data returned by the generation AI.

[1151] Step 4:

[1152] Generative AI: Generates answers based on the received API request. Generative AI uses a large language model to create an answer to the input question. For example, the answer to the question "Which is the largest planet in the solar system?" is generated as "Jupiter." The generated answer data is sent back to the server as the output of this step.

[1153] Step 5:

[1154] Server: Sends the answer data received from the generation AI to the user's device. Analyzes the received answer data and converts it into a format that can be displayed on the device. Specifically, the answer from the generation AI is included in the HTTP response as a text message. The converted answer data is sent to the device and becomes the output of this step.

[1155] Step 6:

[1156] Terminal: The received answer is displayed on the screen. For example, the answer "Jupiter" is displayed on the user's terminal. The user confirms the displayed answer in this step.

[1157] Step 7:

[1158] User: The user evaluates the displayed answers and enters a score. The user follows the scoring interface to select a numerical score, for example, between 1 and 5. After entering the score, the user clicks the submit button, which sends the score to the server. The output of this step is the entered score data.

[1159] Step 8:

[1160] Emotion engine: Analyzes emotions from the user's input speed and behavioral patterns. Behavioral data such as input speed and response confirmation time are input. The emotion engine analyzes this data and determines the user's emotions. For example, if the typing speed is fast, it is analyzed as being excited. The analysis results are sent to the server and become the output of this step.

[1161] Step 9:

[1162] Server: Stores the received score and emotion data in the database. Creates a new record in the database to store the question, answer, and their corresponding score and emotion data. The input of this step is the score data and emotion data, and the output is a message confirming the stored data.

[1163] Step 10:

[1164] Server: Periodically checks the database and extracts answers with high scores. Specifically, it uses a query to extract records with a score of 4 or higher. It then queries external sources for verification of those records. It communicates with external databases to verify the accuracy and reliability of the answers. The output of this step is external data for verification of reliability.

[1165] Step 11:

[1166] Server: Stores the query results obtained from external sources in a database and notifies the user. Stores the query results as a new record and sends a message to the user device informing them of the results. For example, "Jupiter has been confirmed to be the largest planet in the solar system." The output of this step is the storage of the query results and a message to the user.

[1167] Step 12:

[1168] Server: Manages the user's subscription status and notifies them when the expiration date approaches. Specifically, it monitors the subscription expiration date and sends reminder notifications to the user when the expiration date approaches. It also handles billing as needed. The output of this step is a subscription renewal notification and a billing confirmation message.

[1169] (Application example 2)

[1170] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1171] Conventional question-answering systems using generative AI do not fully consider user emotions and feedback, and have limited means to guarantee the reliability of generated answers. This can result in low user satisfaction with the validity and reliability of answers. Furthermore, in the security field, the accuracy of the information provided is extremely important, and inquiries from reliable sources are essential. The present invention aims to solve these issues and provide a question-answering system that users can use with confidence.

[1172] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1173] In this invention, the server includes terminal means for inputting a question, server means for receiving the input question and providing a generated answer, user means for scoring the generated answer, database means for saving and managing the scores, means for extracting answers with high scores and querying external sources, emotion engine means for analyzing and recognizing emotions from the user's input and actions, and query means for confirming the reliability of answers to user questions with external expert information sources. This makes it possible to generate appropriate answers to user questions and guarantee their reliability, as well as to provide better services based on the user's emotions and feedback.

[1174] The "terminal means for inputting a question" refers to a device that allows a user to input and submit a question. This device includes an input field and a submit button.

[1175] "Server means for receiving input questions and providing generated answers" refers to a server that has the function of receiving questions from users, generating appropriate answers using generation AI, and sending them to the terminal.

[1176] "User means for scoring generated answers" refers to an interface for users to input rating scores for generated answers, thereby collecting user ratings.

[1177] "Database means for storing and managing scores" refers to a database system that stores scores entered by users and other related data and that can be accessed as needed.

[1178] "Means for extracting highly scored answers and querying external sources" refers to the functionality for selecting highly scored answers from the database and querying their reliability with external expert sources.

[1179] "Emotion engine means for analyzing and recognizing emotions from user input and behavior" refers to a system that reads and analyzes emotions from the user's input speed, behavioral patterns, etc. This data will be used to improve services.

[1180] "A means for checking the reliability of answers to user questions from external expert information sources" refers to a function for querying the accuracy and reliability of generated answers from external expert information sources and reflecting the results.

[1181] "Generative AI model" refers to an artificial intelligence model used to generate appropriate answers based on user questions.

[1182] A "prompt" is a text that describes a question or request to the generation AI, which then generates an answer based on the prompt.

[1183] This invention is a system in which a user inputs a question, a generative AI provides an answer to that question, and evaluates the validity of the answer. The system includes an emotion engine that analyzes the user's emotions and also includes a function to verify the reliability of the generated answer with an external expert information source. A method for implementing this system is described below.

[1184] Terminal means:

[1185] Users input questions using devices such as smartphones and personal computers. The devices have an input field for entering questions and a submit button.

[1186] Server means:

[1187] The server receives the question sent from the device, converts it into an appropriate format, and sends a request to the generative AI model. The generative AI model generates an answer to the question and sends it back to the server. The server receives the answer and sends it to the device to display it to the user. Specifically, a web server can be built using the Python-based Flask framework, for example. A commonly used generative AI model could be GPT-3.

[1188] Emotion Engine means:

[1189] The server contains an emotion engine that analyzes and recognizes emotions from the user's input speed and behavioral patterns. The emotion engine is implemented using, for example, TextBlob, a natural language processing library. It analyzes the speed and timing of the user's input of questions and quantifies positive or negative emotions.

[1190] User means:

[1191] Once a user receives the generated answer, they can assign a rating to it. The user interface uses a scoring system ranging from 1 to 5. Once the user enters and submits the score, it is stored on the server.

[1192] Database Methods:

[1193] The server stores the scores and emotion data entered by the user in a database, which can be constructed using SQLite or MySQL, for example.

[1194] Inquiry methods:

[1195] The server periodically checks the database and extracts the top-scoring answers, then queries external sources, such as specialized information services or APIs, to verify the reliability of the generated answers.

[1196] Examples:

[1197] For example, a user enters a question such as, "How can I improve my home Wi-Fi security?" The server sends this question to a generative AI model, which responds, "We recommend using a strong password, using the latest encryption methods, and updating your router's firmware." The answer is then provided to the user via the server. The user rates this answer "5 / 5," and the server stores this score and sentiment data. The server periodically checks this answer against expert sources, and if its reliability is confirmed, records the information in a database and notifies the user.

[1198] As a result, this system allows users to evaluate the validity of the generated AI's answers and provide feedback that includes emotions, making it possible to provide users with more reliable information.

[1199] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1200] Step 1:

[1201] The terminal accepts questions from the user in an input field. When the user enters a question and presses the send button, the question is sent to the server.

[1202] Input: The question entered by the user

[1203] Output: The question sent to the server

[1204] Step 2:

[1205] The server parses the received question and formats it as a request to the generative AI model, which then sends the request to the generative AI model.

[1206] Input: Question received from the terminal

[1207] Output: The request sent to the generative AI model

[1208] Step 3:

[1209] The generative AI model receives the formatted request and generates an appropriate answer to the question, which is then sent back to the server.

[1210] Input: The request sent by the server

[1211] Output: The generated answer

[1212] Step 4:

[1213] The server sends the answer received from the generative AI model back to the device and displays it to the user.

[1214] Input: The answer received from the generative AI model

[1215] Output: Answer sent back to the terminal

[1216] Step 5:

[1217] The terminal displays the received answer to the user. The user checks the answer and enters an evaluation score. The evaluation score is entered and sent.

[1218] Input: The answer returned by the server

[1219] Output: User-entered rating score

[1220] Step 6:

[1221] The server receives the user-submitted rating score, stores the data in a database, and, if the rating score is high (e.g., 4 or higher), queries the answer to an external source.

[1222] Input: Rating score from device

[1223] Output: Scores stored in a database and query requests sent to external sources

[1224] Step 7:

[1225] The external source receives the query request from the server and verifies the authenticity of the generated answer, which is then sent back to the server.

[1226] Input: A query request from the server

[1227] Output: Reliability check result

[1228] Step 8:

[1229] The server receives the results of the trust verification from the external source, stores them in a database, and notifies the user of the results.

[1230] Input: Reliability check results from external sources

[1231] Output: Trust verification results stored in the database and notified to the user

[1232] Through these steps, the system generates appropriate answers to users' questions, guarantees their reliability, and collects feedback, including users' emotions.

[1233] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1234] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1235] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1236] [Fourth embodiment]

[1237] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1238] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1239] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1240] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1241] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1242] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1243] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1244] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1245] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1246] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1247] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1248] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1249] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1250] The present invention is a system in which a user inputs a question, obtains an answer from a generation AI, and evaluates and scores the validity of the answer. The system includes a server, a terminal, a user means, a database means, an external source, and a query means.

[1251] Enter your question

[1252] Terminal: The user uses the terminal to input a question. The terminal must have an input field and a submit button. When the user inputs a question and clicks the submit button, the question is sent to the server.

[1253] Receiving and processing questions

[1254] Server: Parses the received question and formats it as a request to the generation AI. An API request is made to send the question to the generation AI and get the answer.

[1255] Generate and display answers

[1256] Generative AI: Generates an appropriate answer to the input question and sends it back to the server. The server then sends the received answer back to the user's device and displays it on the device.

[1257] Terminal: The received answers are displayed on the screen. The interface for users to check the answers should be designed with ease of viewing and operation in mind.

[1258] Scoring

[1259] User: The user inputs an evaluation score for the displayed answer. The scoring interface can be, for example, a format where a user selects a number from 1 to 5. After inputting the score, the user clicks the submit button to send the score to the server.

[1260] Score storage and management

[1261] Server: Stores the received scores along with the corresponding questions and answers in a database. This database should employ an appropriate database management system (DBMS) to effectively manage the scoring information.

[1262] Extracting and querying high-scoring answers

[1263] Server: Regularly checks the database and extracts answers with high scores. For example, a system is built to extract answers with a score of 4 or higher.

[1264] External sources: The extracted answers are checked against external expert databases and reliable information sources. The data obtained from external sources is used to strengthen the reliability of the generated AI's answers.

[1265] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification to the user saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[1266] Manage your subscription

[1267] Server: Manages the user's subscription status, notifies them of expiration dates, and connects with the payment system to process periodic charges.

[1268] Specific examples

[1269] User: For example, a user types and submits a question: "Which is the largest planet in the solar system?"

[1270] Server: Receives the question and sends a request to the generation AI.

[1271] Generation AI: Generates the answer "It's Jupiter" and sends it back to the server.

[1272] Server: Receives the response and sends it to the device.

[1273] Terminal: Shows the answer, and the user enters a score of "5 / 5" and submits.

[1274] Server: Receives the scores and stores them in a database.

[1275] Server: Periodically extracts high-scoring answers and queries them against external specialized databases.

[1276] Server: Notifies the user that the authenticity has been confirmed based on the query results.

[1277] In this way, the present invention provides a system that allows users to evaluate the validity of answers generated by AI and obtain reliable information. This system is easy for users to use and can provide reliable information.

[1278] The processing flow will be explained below.

[1279] Step 1:

[1280] User: Enters a question using a device and clicks the "Submit Question" button.

[1281] Step 2:

[1282] Terminal: Takes the entered question and sends it to the server as JSON format data. This data includes the format {"question": "Which is the largest planet in the solar system?"}.

[1283] Step 3:

[1284] Server: Receives question data, formats the question into an appropriate format, and prepares an API request to the generation AI.

[1285] Step 4:

[1286] Server: Sends a request containing question data to the generation AI.

[1287] Step 5:

[1288] Generative AI: Analyzes the question data received from the server and generates an answer to the question. For example, it generates an answer such as "It's Jupiter" and sends it back to the server.

[1289] Step 6:

[1290] Server: Receives the answer returned by the generation AI and sends it to the user's device.

[1291] Step 7:

[1292] Device: Displays the received answer on the screen, e.g., the text "Jupiter" is displayed in a visible form to the user.

[1293] Step 8:

[1294] User: Enter a rating score for the displayed answer. For example, rate it from 1 to 5 and give it a score of "5 / 5." Click the "Submit Score" button.

[1295] Step 9:

[1296] Device: The entered score is sent to the server as JSON format data, which includes the format "{"question_id": 123, "score": 5}", for example.

[1297] Step 10:

[1298] Server: Stores the received scores in a database along with the corresponding question and answer data.

[1299] Step 11:

[1300] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher.

[1301] Step 12:

[1302] Server: Query the extracted high-scoring answers using external sources (e.g., specialized databases or reliable information sources).

[1303] Step 13:

[1304] External Source: Provides query results in response to queries received from the server, e.g., returns data such as "Confirmed that Jupiter is the largest planet in the solar system."

[1305] Step 14:

[1306] Server: Stores the query results in a database and notifies the user of the results. The user is informed that the information is reliable.

[1307] Step 15:

[1308] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing appropriately. For example, if a user's subscription is due for renewal, the server initiates billing.

[1309] Example 1

[1310] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1311] Conventional question-answering systems do not guarantee the validity or reliability of the generated answers, and users have limited means to evaluate the information provided. Furthermore, for answers with high scores, there is no way to verify their reliability with an external, reliable information source, making it difficult to provide users with reliable information. These issues need to be addressed.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1313] In this invention, the server includes a means for receiving questions and sending them to the generative AI model, a means for acquiring the generated answers and returning them to the user's terminal, and a means for storing the evaluated scores in a database, which allows high-scoring answers to be extracted and queried in an external reliable information source.

[1314] "Information processing device means" refers to the device used by the user to input a query, and typically includes a desktop computer, laptop, smartphone, tablet, etc.

[1315] "Data processing means" refers to a server that has the functionality to receive input questions and send requests to the generative AI model to obtain answers.

[1316] The "evaluation means" refers to an interface that allows a user to input a score for a generated answer and evaluate it.

[1317] "Storage means" refers to a database system for storing and managing users' scores and corresponding questions and answers.

[1318] "Generative AI model" refers to an artificial intelligence model used to generate appropriate answers to input questions.

[1319] "External sources" refers to reliable databases or sources used to verify the reliability of the generated answers, examples of which include specialist databases and recognized sources.

[1320] "Scoring" refers to the rating points that users give to generated answers, typically in the form of selecting a number between 1 and 5.

[1321] "Consulting" refers to the process of using external sources to verify the accuracy and reliability of the generated answers.

[1322] The present invention provides a system in which a user inputs a question, obtains an answer from a generative AI model, and the user evaluates the validity of the answer. The system includes an information processing device, a data processing device, an evaluation device, a storage device, and an external information source.

[1323] information processing device means

[1324] The user uses a data processing device to input the question, typically a desktop computer, laptop, smartphone, or tablet. The user uses the data processing device to enter the question into an input field and clicks a submit button.

[1325] Data Processing Means

[1326] The server, which is the data processing means, receives the question sent from the information processing means. The server analyzes the question and formats it as a request to the generative AI model. The server then sends an API request to the generative AI model to obtain the answer.

[1327] Generative AI Models

[1328] The generative AI model generates appropriate answers to questions received from the server. For example, if a user sends a question such as "Which is the largest planet in the solar system?", the generative AI model generates the answer "Jupiter" and sends it back to the server.

[1329] Returning and displaying answers

[1330] The server returns the answer received from the generative AI model to the information processing device means, which displays the answer on a screen so that the user can easily check it.

[1331] Evaluation methods

[1332] The user inputs an evaluation score for the displayed answer. This evaluation is done by selecting a number, for example, from 1 to 5. When the user inputs the score and clicks the submit button, the evaluation score is sent to the server.

[1333] storage means

[1334] The server stores the received scores together with the corresponding questions and answers in a storage means or database, which may employ a suitable database management system such as MySQL.

[1335] Extracting and querying high-scoring answers

[1336] The server periodically checks the database and extracts high-scoring answers. For example, answers with a score of 4 or higher are automatically extracted. For the extracted answers, the server queries external sources to verify the accuracy and reliability of the generated AI model's answers. For example, it verifies that "Jupiter is the largest planet in the solar system" with specialized databases and authorized sources.

[1337] Manage your subscription

[1338] The server manages the user's subscription status, notifies them when the expiration date is approaching, and handles periodic billing, which is handled in cooperation with a payment system (e.g., Stripe, PayPal, etc.).

[1339] Specific examples

[1340] For example, a user inputs and submits the question "Which is the largest planet in the solar system?" The server receives this question and sends a request to the generative AI model. After receiving the answer "Jupiter" from the generative AI model, the server transmits this answer to the information processing means and displays it. The user inputs a rating of "5 / 5" for the displayed answer and transmits it. The server receives the score and stores it in the storage means. The server periodically checks the database, extracts answers with high scores, and queries external information sources. The user is notified of the confirmed, reliable answers.

[1341] In this way, the present invention provides a system that allows users to evaluate the validity of the answers of generative AI models and obtain reliable information.

[1342] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1343] Step 1:

[1344] The user types a question into the terminal.

[1345] Specific Actions: Using the input field on the device, the user enters a question and clicks the submit button.

[1346] Input: Text entered by the user (e.g., "Which is the largest planet in the solar system?").

[1347] Output: The entered question data is sent to the server.

[1348] Step 2:

[1349] The server receives the query and parses it.

[1350] Specific operation: The server receives the query data from the terminal, analyzes the content, and converts it into an appropriate data format.

[1351] Input: Question data sent from the terminal.

[1352] Output: Data formatted for API requests to the generative AI model.

[1353] Step 3:

[1354] The server sends an API request to the generative AI model.

[1355] Specific operation: The server sends a formatted request to the API endpoint of the generative AI model.

[1356] Input: Question data in the form of an API request.

[1357] Output: The answer data generated by the generative AI model.

[1358] Step 4:

[1359] A generative AI model generates answers to questions.

[1360] How it works: The generative AI model analyzes the requested question and generates an appropriate answer.

[1361] Input: Question data in the form of an API request from the server.

[1362] Output: The generated answer data (e.g., "It's Jupiter").

[1363] Step 5:

[1364] The server receives the response and sends it to the terminal.

[1365] Specific operation: The server receives the response data from the generative AI model and sends it to the terminal.

[1366] Input: Answer data from the generative AI model.

[1367] Output: The response data sent to the device.

[1368] Step 6:

[1369] The device will display the answer.

[1370] Specific operation: The terminal displays the received response data on the screen in a format that is easy for the user to view.

[1371] Input: The response data sent from the server.

[1372] Output: The answer that appears on the screen (e.g., "Jupiter").

[1373] Step 7:

[1374] The user enters a score for the answer.

[1375] Specific operation: The user enters an evaluation score for the displayed answer and clicks the submit button.

[1376] Input: The score entered by the user (e.g., "5 / 5").

[1377] Output: The entered score data is sent to the server.

[1378] Step 8:

[1379] The server receives the scores and stores them in a database.

[1380] Specific Operation: The server stores the received score data in a database along with the associated question and answer data.

[1381] Input: Score data submitted by the user.

[1382] Output: Score, question and answer data stored in a database.

[1383] Step 9:

[1384] The server extracts the answers with the highest scores.

[1385] Specific operation: The server periodically checks the database and extracts answers with a score of 4 or higher.

[1386] Input: Score, question and answer data stored in the database.

[1387] Output: Extracted high-scoring answer data.

[1388] Step 10:

[1389] The server queries the external information source.

[1390] Specific operation: The server queries the extracted high-scoring answers using external information sources to verify their accuracy and reliability.

[1391] Input: Extracted high-scoring answer data.

[1392] Output: Query result data obtained from external sources.

[1393] Step 11:

[1394] The server stores the query results in a database and notifies the user.

[1395] Specific operation: The query results are saved in the database and the confirmed information is notified to the user.

[1396] Input: Query result data from external sources.

[1397] Output: A notification with the confirmed information (e.g., "Jupiter has been confirmed to be the largest planet in the solar system").

[1398] (Application example 1)

[1399] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1400] Modern electronic payment services require rapid and accurate responses to user information requests. However, many current systems rely on human intervention to meet these requests, resulting in problems of inefficiency and reliability. Furthermore, these systems lack a means to effectively evaluate user satisfaction and reflect that evaluation in service improvements. Therefore, there is a need for an efficient system that can provide rapid and accurate answers to user questions and reflect user evaluations of those answers in the system.

[1401] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1402] In this invention, the server includes a means for causing the generative AI model to generate answers in real time, a means for displaying the answers generated by the generative AI model and providing a dedicated interface for users to input their ratings, and a means for enhancing reliability based on the results of inquiries in external information sources, thereby enabling quick and accurate answers to users' questions and effective collection and management of ratings for the answers.

[1403] A "terminal means" is a device used by a user to input a question.

[1404] "Server means" refers to a central processing unit that receives input questions and transmits them to a generative AI model to provide answers.

[1405] "User means" refers to the interface and functionality that allows a user to score the generated answers.

[1406] "Database means" refers to a database system for storing and managing scores, questions and answers.

[1407] "External Source" means an external, reliable source of information used to query and augment the reliability of the answers provided by the generative AI model.

[1408] A "generative AI model" is an artificial intelligence model that generates answers to input questions.

[1409] The "dedicated interface" refers to a dedicated operation screen and function that allows users to check the answers of the generated AI model and enter evaluation scores.

[1410] "Real-time" means that processing occurs almost instantaneously, with immediate response to user input.

[1411] "Measures to enhance trustworthiness" refers to a function that verifies the accuracy of the answers of the generated AI model based on the results of inquiries from external information sources, thereby improving trustworthiness.

[1412] MODE FOR CARRYING OUT THE INVENTION

[1413] This invention provides a system that quickly and accurately answers user questions. The system includes a terminal, a server, a generative AI model, a database, an external information source, and a dedicated interface. The specific functions and operations of each element are described below.

[1414] Terminal means

[1415] Users enter questions using devices such as smartphones or computers. The devices have an input field and a submit button, and the questions entered by the user are sent to the server.

[1416] Server Means

[1417] The server receives questions sent by users and sends them to the generative AI model. This process involves a program running on the server. Specifically, a web server using Flask receives the question and sends it to the generative AI model using OpenAI's API. The server then receives the generated answer and sends it back to the user's device.

[1418] Generative AI Models

[1419] A generative AI model (e.g., OpenAI's GPT-3) generates answers to user questions. The generative AI model generates answers based on questions sent from the server and sends the answers back to the server. An example of a prompt sentence used here is, "What should I do if I don't receive my electronic payment receipt?"

[1420] Dedicated Interface

[1421] The generated answers are displayed on the user's device, and the dedicated interface includes a scoring function for evaluating the answers, allowing the user to rate the appropriateness of the answers on a scale of 1 to 5. The entered score is then sent to the server.

[1422] Database Means

[1423] The server stores the received scores and the corresponding questions and answers in a database, using a database management system such as SQLite. The stored data is later used to extract and analyze high-scoring answers.

[1424] external information sources

[1425] The server periodically checks the database and extracts the highest-scoring answers, then queries and strengthens the reliability of these answers using external sources, such as trusted data sources and specialized databases.

[1426] Specific examples of programs

[1427] For example, a user enters a question such as, "What should I do if I don't receive my electronic payment receipt?" The question is immediately received by the server and sent to a generative AI model (GPT-3). The generated answer is returned as, "Contact your electronic payment company and provide them with the transaction ID to request confirmation." The user rates this answer as "5 / 5" and enters a score. The server stores this score in a database and later extracts it as a high-scoring answer, verifying its reliability with an external source.

[1428] The system allows users to receive fast and accurate answers, improving the efficiency and reliability of electronic payment services.

[1429] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1430] Step 1:

[1431] A user inputs a question using a terminal. The user generates question data by entering the question in an input field on the terminal and clicking the send button. The input data is the user's question text. This question text is sent to the server.

[1432] Step 2:

[1433] The server receives the question sent by the user. It analyzes the received question text and formats it into a request format to send to the generative AI model. This request data is JSON format data including the question text. The server sends this data to the API that provides the generative AI model.

[1434] Step 3:

[1435] The generative AI model receives the API request and generates an answer to the question. The generated answer is sent back to the server in the form of an API response. This response data contains the text of the answer. The generative AI model analyzes the input question text and uses its internal algorithm to create the optimal answer text.

[1436] Step 4:

[1437] The server receives the answer returned from the generative AI model and sends it back to the user's device. The received answer data is JSON format data containing the answer text and related metadata. The server sends this data to the user's device.

[1438] Step 5:

[1439] The user's device displays the received answer on the user interface. The user checks the displayed answer and inputs an evaluation score for the answer using the scoring interface. The input data based on the scoring is the score value. When the user inputs the score and clicks the submit button, the score data is sent to the server.

[1440] Step 6:

[1441] The server receives the score data sent by the user, associates it with the question and answer, and stores it in a database. This score data includes the score value and metadata such as question ID and answer ID. The server manages this data by inserting it into the database.

[1442] Step 7:

[1443] The server periodically checks the database and extracts the top-scoring answers by analyzing the scores in the database using queries, which are then used to query external sources.

[1444] Step 8:

[1445] The server uses external information sources to verify the reliability of high-scoring answers. The data obtained from the external information sources is matched with the answer text of the generative AI model. Answer data that is verified as reliable through this verification process is stored in a database and notified to the user.

[1446] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1447] The present invention combines a system in which a user inputs a question, obtains an answer from a generation AI, evaluates the validity of the answer, and scores it, with an emotion engine that recognizes the user's emotions. This system includes a server, a terminal, user means, database means, an external source, a query means, and an emotion engine.

[1448] Enter your question

[1449] Terminal: The user uses the terminal to input a question. The terminal has an input field and a send button, and when the user inputs a question and clicks the send button, the question is sent to the server.

[1450] Receiving and processing questions

[1451] Server: Parses the received question and formats it as a request to the generation AI. An API request is made to send the question to the generation AI and retrieve the answer.

[1452] Generate and display answers

[1453] Generative AI: Generates an appropriate answer to the input question and sends it back to the server. The server then sends the received answer back to the user's device and displays it on the device.

[1454] Device: The received answer is displayed on the screen. For example, the answer "Jupiter" is displayed.

[1455] Scoring

[1456] User: Checks the answers and enters an evaluation score. The scoring interface is a form where a user selects a number, for example, from 1 to 5. The user enters the score and clicks the submit button, which sends the score to the server.

[1457] Emotion recognition by emotion engine

[1458] Emotion engine: It has the ability to analyze and recognize emotions from user input and behavior (e.g., typing speed, response confirmation time, etc.). Emotion data is used to improve the quality of user responses and feedback.

[1459] Storing and managing score and emotion data

[1460] Server: Stores the received scores and sentiment data in a database along with the corresponding questions and answers.

[1461] Extracting and querying high-scoring answers

[1462] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher. The extracted answers are then compared with external specialized databases and reliable information sources.

[1463] Saving and notifying query results

[1464] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[1465] Manage your subscription

[1466] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[1467] Specific examples

[1468] User: For example, a user types and submits a question: "Which is the largest planet in the solar system?"

[1469] Server: Receives the question and sends a request to the generation AI.

[1470] Generation AI: Generates the answer "It's Jupiter" and sends it back to the server.

[1471] Server: Receives the response and sends it to the device.

[1472] Terminal: Shows the answer, and the user enters a score of "5 / 5" and submits.

[1473] Emotion engine: Recognizes emotions from the user's input speed and behavior patterns and records that data.

[1474] Server: Receives scores and emotion data and stores them in a database.

[1475] Server: Periodically extracts high-scoring answers and queries them against external specialized databases.

[1476] Server: Notifies the user that the authenticity has been confirmed based on the query results.

[1477] Server: Manages user subscription status, notifies expiration and processes billing.

[1478] In this way, the present invention provides a system that allows users to evaluate the validity of the answers of the AI ​​generator and obtain reliable information through feedback that includes emotions. This system is easy for users to use and can provide reliable information.

[1479] The processing flow will be explained below.

[1480] Step 1:

[1481] User: Enters a question using a device and clicks the "Submit Question" button.

[1482] Step 2:

[1483] Terminal: Takes the entered question and sends it to the server as JSON format data, for example, "{"question": "Which is the largest planet in the solar system?"}".

[1484] Step 3:

[1485] Server: Receives question data, formats the question appropriately, and creates an API request to the generation AI.

[1486] Step 4:

[1487] Server: Sends a request containing question data to the generation AI.

[1488] Step 5:

[1489] Generative AI: Analyzes the question data received from the server and generates an answer to the question. For example, it generates an answer such as "It's Jupiter" and sends it back to the server.

[1490] Step 6:

[1491] Server: Receives the answer returned by the generation AI and sends it to the user's device.

[1492] Step 7:

[1493] Terminal: Displays the received answer on the screen. For example, the answer "Jupiter" is displayed on the screen.

[1494] Step 8:

[1495] User: Enter a rating score for the displayed answer. For example, rate it from 1 to 5 and give it a score of "5 / 5." Click the "Submit Score" button.

[1496] Step 9:

[1497] Device: The entered score is sent to the server as JSON format data, for example, "{"question_id": 123, "score": 5}".

[1498] Step 10:

[1499] Server: Stores the received scores in a database along with the corresponding question and answer data.

[1500] Step 11:

[1501] Emotion engine: Recognizes the user's emotions by analyzing the user's input speed, typing patterns, and response confirmation time. For example, if the input speed is slow, it is recognized as "anxious," and if it is fast, it is recognized as "confident."

[1502] Step 12:

[1503] Server: Receives emotion data obtained from the emotion engine and stores it in a database along with the corresponding question and answer data.

[1504] Step 13:

[1505] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher.

[1506] Step 14:

[1507] Server: queries external sources (specialized databases and reliable information sources) for extracted high-scoring answers.

[1508] Step 15:

[1509] External Source: Provides data in response to a query from the server, e.g., sends back to the server information that "Jupiter has been confirmed to be the largest planet in the solar system."

[1510] Step 16:

[1511] Server: Stores the query results from external sources in a database and notifies the user of the results, for example, sending a notification that "Jupiter has been confirmed to be the largest planet in the solar system."

[1512] Step 17:

[1513] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[1514] Example 2

[1515] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1516] Conventional systems do not properly evaluate the validity of the answers received from the AI ​​generator and provide scoring and feedback to ensure reliable information. As a result, the reliability of the information received by the user is reduced, resulting in an unsatisfactory user experience. Furthermore, there is a lack of means to improve the quality of the feedback by utilizing user emotional data.

[1517] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means having a function of receiving an input question, analyzing it, formatting it for the generation AI, and obtaining an answer, means for displaying the generated answer on a terminal and allowing the user to score it, means having a function of analyzing the user's emotional data using an emotion engine, database means for saving and managing scores and related emotional data, and means for extracting answers with high scores and checking their reliability with an external information source. This allows the user to evaluate the validity of the answer from the generation AI and obtain reliable information, while also making it possible to improve the quality of the user experience based on the emotional data.

[1518] The "device means for inputting a question" refers to a terminal or device that allows a user to freely input a question and transmits the input question to a server for subsequent processing.

[1519] "Server means having the function of receiving, analyzing, formatting for the generation AI, and obtaining the answer" refers to the server function of receiving a question entered by a user, analyzing it, converting it into an appropriate format for the generation AI, and obtaining the answer.

[1520] "A means for the generated answers to be displayed on the device and scored by the user" refers to a function that displays the answers obtained from the generation AI on the user's device and provides an interface for the user to evaluate the answers.

[1521] "Means having a function for analyzing user emotional data using an emotion engine" refers to a function within the system for analyzing emotions from user input and behavioral patterns and collecting that data.

[1522] "Database means for saving and managing scores and related emotional data" refers to the function of a database for saving and managing scores entered by users and the emotional data associated with them.

[1523] "Means for extracting answers with high scores and checking their reliability with external information sources" refers to a system function that periodically extracts answers that have received particularly high scores from the stored scores and checks their reliability by checking with external, reliable databases or information sources.

[1524] The present invention relates to a system in which a user inputs a question, obtains an answer from a generation AI, and the user evaluates the validity of the answer and scores it. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the feedback can be improved. This system includes a server, a terminal, user means, database means, an external source, query means, and an emotion engine.

[1525] Enter your question

[1526] Terminal: The user uses the terminal to input a question. The terminal has an input field and a send button, and when the user inputs a question and clicks the send button, the question is sent to the server.

[1527] Receiving and processing questions

[1528] Server: Parses the received questions and formats them as requests for the generation AI. Protocols such as RESTful APIs and GraphQL can be used to enable API communication with other systems.

[1529] Generate and display answers

[1530] Generative AI: Generates an appropriate answer to the input question and returns the answer to the server. Generative AI can use, for example, a large-scale language model. Below is a specific example of a prompt sentence.

[1531] Examples:

[1532] User-supplied question: "Which is the largest planet in the solar system?"

[1533] The AI ​​responds: "Jupiter."

[1534] Server: Returns the received answer to the user's terminal and displays it on the terminal.

[1535] Terminal: Displays the received response on the screen.

[1536] Scoring

[1537] User: Checks the answers and enters an evaluation score. The scoring interface allows users to select a number from 1 to 5, for example. The user enters the score and clicks the submit button, which sends the score to the server.

[1538] Emotion recognition by emotion engine

[1539] Emotion engine: It has the ability to analyze and recognize emotions from user input and behavior (e.g., typing speed, response confirmation time, etc.). Emotion data is used to improve the quality of user responses and feedback.

[1540] Storing and managing score and emotion data

[1541] Server: Stores the received scores and emotion data along with the corresponding questions and answers in a database. The database can be, for example, a relational database or a NoSQL database.

[1542] Extracting and querying high-scoring answers

[1543] Server: Periodically checks the database and extracts answers with high scores, for example, answers with a score of 4 or higher. The extracted answers are then compared with external specialized databases and reliable information sources.

[1544] Saving and notifying query results

[1545] Server: Stores the query results in a database and notifies the user of the results. For example, it sends a notification saying, "Jupiter has been confirmed to be the largest planet in the solar system."

[1546] Manage your subscription

[1547] Server: Manages the user's subscription status, notifies them of expiration dates, and processes billing. For example, it sends notifications when the subscription renewal date approaches and processes billing.

[1548] In this way, by providing a system that comprehensively handles everything from question input to answer generation, scoring, emotion recognition, extraction and query of high-scoring answers, and even subscription management, it is possible to provide users with highly reliable information. Furthermore, the introduction of an emotion engine is expected to improve the user experience.

[1549] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1550] Step 1:

[1551] User: The user uses the terminal to input a question. Specifically, the user writes the question in the input field displayed on the terminal and clicks the send button. The input data is a text-based question. For example, the user might enter "Which is the largest planet in the solar system?" The output of this step is the input question sent to the server as a data packet.

[1552] Step 2:

[1553] Server: Receives the question sent from the device. The received data is a text-formatted question. The server analyzes the received question and formats it as a request for the generation AI. Specifically, it converts the question into an API request format such as JSON. The converted request data is sent to the generation AI, which is the output of this step.

[1554] Step 3:

[1555] Server: Sends an API request to the generation AI. The request includes the converted question. The server sends an HTTP POST request specifying the generation AI's endpoint URL and providing the necessary API key or token. The input to this step is the formatted API request data, and the output is the answer data returned by the generation AI.

[1556] Step 4:

[1557] Generative AI: Generates answers based on the received API request. Generative AI uses a large language model to create an answer to the input question. For example, the answer to the question "Which is the largest planet in the solar system?" is generated as "Jupiter." The generated answer data is sent back to the server as the output of this step.

[1558] Step 5:

[1559] Server: Sends the answer data received from the generation AI to the user's device. Analyzes the received answer data and converts it into a format that can be displayed on the device. Specifically, the answer from the generation AI is included in the HTTP response as a text message. The converted answer data is sent to the device and becomes the output of this step.

[1560] Step 6:

[1561] Terminal: The received answer is displayed on the screen. For example, the answer "Jupiter" is displayed on the user's terminal. The user confirms the displayed answer in this step.

[1562] Step 7:

[1563] User: The user evaluates the displayed answers and enters a score. The user follows the scoring interface to select a numerical score, for example, between 1 and 5. After entering the score, the user clicks the submit button, which sends the score to the server. The output of this step is the entered score data.

[1564] Step 8:

[1565] Emotion engine: Analyzes emotions from the user's input speed and behavioral patterns. Behavioral data such as input speed and response confirmation time are input. The emotion engine analyzes this data and determines the user's emotions. For example, if the typing speed is fast, it is analyzed as being excited. The analysis results are sent to the server and become the output of this step.

[1566] Step 9:

[1567] Server: Stores the received score and emotion data in the database. Creates a new record in the database to store the question, answer, and their corresponding score and emotion data. The input of this step is the score data and emotion data, and the output is a message confirming the stored data.

[1568] Step 10:

[1569] Server: Periodically checks the database and extracts answers with high scores. Specifically, it uses a query to extract records with a score of 4 or higher. It then queries external sources for verification of those records. It communicates with external databases to verify the accuracy and reliability of the answers. The output of this step is external data for verification of reliability.

[1570] Step 11:

[1571] Server: Stores the query results obtained from external sources in a database and notifies the user. Stores the query results as a new record and sends a message to the user device informing them of the results. For example, "Jupiter has been confirmed to be the largest planet in the solar system." The output of this step is the storage of the query results and a message to the user.

[1572] Step 12:

[1573] Server: Manages the user's subscription status and notifies them when the expiration date approaches. Specifically, it monitors the subscription expiration date and sends reminder notifications to the user when the expiration date approaches. It also handles billing as needed. The output of this step is a subscription renewal notification and a billing confirmation message.

[1574] (Application example 2)

[1575] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1576] Conventional question-answering systems using generative AI do not fully consider user emotions and feedback, and have limited means to guarantee the reliability of generated answers. This can result in low user satisfaction with the validity and reliability of answers. Furthermore, in the security field, the accuracy of the information provided is extremely important, and inquiries from reliable sources are essential. The present invention aims to solve these issues and provide a question-answering system that users can use with confidence.

[1577] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1578] In this invention, the server includes terminal means for inputting a question, server means for receiving the input question and providing a generated answer, user means for scoring the generated answer, database means for saving and managing the scores, means for extracting answers with high scores and querying external sources, emotion engine means for analyzing and recognizing emotions from the user's input and actions, and query means for confirming the reliability of answers to user questions with external expert information sources. This makes it possible to generate appropriate answers to user questions and guarantee their reliability, as well as to provide better services based on the user's emotions and feedback.

[1579] The "terminal means for inputting a question" refers to a device that allows a user to input and submit a question. This device includes an input field and a submit button.

[1580] "Server means for receiving input questions and providing generated answers" refers to a server that has the function of receiving questions from users, generating appropriate answers using generation AI, and sending them to the terminal.

[1581] "User means for scoring generated answers" refers to an interface for users to input rating scores for generated answers, thereby collecting user ratings.

[1582] "Database means for storing and managing scores" refers to a database system that stores scores entered by users and other related data and that can be accessed as needed.

[1583] "Means for extracting highly scored answers and querying external sources" refers to the functionality for selecting highly scored answers from the database and querying their reliability with external expert sources.

[1584] "Emotion engine means for analyzing and recognizing emotions from user input and behavior" refers to a system that reads and analyzes emotions from the user's input speed, behavioral patterns, etc. This data will be used to improve services.

[1585] "A means for checking the reliability of answers to user questions from external expert information sources" refers to a function for querying the accuracy and reliability of generated answers from external expert information sources and reflecting the results.

[1586] "Generative AI model" refers to an artificial intelligence model used to generate appropriate answers based on user questions.

[1587] A "prompt" is a text that describes a question or request to the generation AI, which then generates an answer based on the prompt.

[1588] This invention is a system in which a user inputs a question, a generative AI provides an answer to that question, and evaluates the validity of the answer. The system includes an emotion engine that analyzes the user's emotions and also includes a function to verify the reliability of the generated answer with an external expert information source. A method for implementing this system is described below.

[1589] Terminal means:

[1590] Users input questions using devices such as smartphones and personal computers. The devices have an input field for entering questions and a submit button.

[1591] Server means:

[1592] The server receives the question sent from the device, converts it into an appropriate format, and sends a request to the generative AI model. The generative AI model generates an answer to the question and sends it back to the server. The server receives the answer and sends it to the device to display it to the user. Specifically, a web server can be built using the Python-based Flask framework, for example. A commonly used generative AI model could be GPT-3.

[1593] Emotion Engine means:

[1594] The server contains an emotion engine that analyzes and recognizes emotions from the user's input speed and behavioral patterns. The emotion engine is implemented using, for example, TextBlob, a natural language processing library. It analyzes the speed and timing of the user's input of questions and quantifies positive or negative emotions.

[1595] User means:

[1596] Once a user receives the generated answer, they can assign a rating to it. The user interface uses a scoring system ranging from 1 to 5. Once the user enters and submits the score, it is stored on the server.

[1597] Database Methods:

[1598] The server stores the scores and emotion data entered by the user in a database, which can be constructed using SQLite or MySQL, for example.

[1599] Inquiry methods:

[1600] The server periodically checks the database and extracts the top-scoring answers, then queries external sources, such as specialized information services or APIs, to verify the reliability of the generated answers.

[1601] Examples:

[1602] For example, a user enters a question such as, "How can I improve my home Wi-Fi security?" The server sends this question to a generative AI model, which responds, "We recommend using a strong password, using the latest encryption methods, and updating your router's firmware." The answer is then provided to the user via the server. The user rates this answer "5 / 5," and the server stores this score and sentiment data. The server periodically checks this answer against expert sources, and if its reliability is confirmed, records the information in a database and notifies the user.

[1603] As a result, this system allows users to evaluate the validity of the generated AI's answers and provide feedback that includes emotions, making it possible to provide users with more reliable information.

[1604] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1605] Step 1:

[1606] The terminal accepts questions from the user in an input field. When the user enters a question and presses the send button, the question is sent to the server.

[1607] Input: The question entered by the user

[1608] Output: The question sent to the server

[1609] Step 2:

[1610] The server parses the received question and formats it as a request to the generative AI model, which then sends the request to the generative AI model.

[1611] Input: Question received from the terminal

[1612] Output: The request sent to the generative AI model

[1613] Step 3:

[1614] The generative AI model receives the formatted request and generates an appropriate answer to the question, which is then sent back to the server.

[1615] Input: The request sent by the server

[1616] Output: The generated answer

[1617] Step 4:

[1618] The server sends the answer received from the generative AI model back to the device and displays it to the user.

[1619] Input: The answer received from the generative AI model

[1620] Output: Answer sent back to the terminal

[1621] Step 5:

[1622] The terminal displays the received answer to the user. The user checks the answer and enters an evaluation score. The evaluation score is entered and sent.

[1623] Input: The answer returned by the server

[1624] Output: User-entered rating score

[1625] Step 6:

[1626] The server receives the user-submitted rating score, stores the data in a database, and, if the rating score is high (e.g., 4 or higher), queries the answer to an external source.

[1627] Input: Rating score from device

[1628] Output: Scores stored in a database and query requests sent to external sources

[1629] Step 7:

[1630] The external source receives the query request from the server and verifies the authenticity of the generated answer, which is then sent back to the server.

[1631] Input: A query request from the server

[1632] Output: Reliability check result

[1633] Step 8:

[1634] The server receives the results of the trust verification from the external source, stores them in a database, and notifies the user of the results.

[1635] Input: Reliability check results from external sources

[1636] Output: Trust verification results stored in the database and notified to the user

[1637] Through these steps, the system generates appropriate answers to users' questions, guarantees their reliability, and collects feedback, including users' emotions.

[1638] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1639] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1640] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1641] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1642] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1643] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1644] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1645] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1646] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1647] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1648] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1649] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1650] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1651] 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.

[1652] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1653] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1654] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1655] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1656] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1657] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1658] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1659] The following is further disclosed regarding the above embodiment.

[1660] (Claim 1)

[1661] a terminal means for inputting a question;

[1662] server means for receiving input questions and providing generated answers;

[1663] a user means for scoring the generated answers;

[1664] a database means for storing and managing scores;

[1665] A means of extracting the highest scoring answers and querying them in external sources;

[1666] A system including:

[1667] (Claim 2)

[1668] 10. The system of claim 1, further comprising: server means operable to send questions to the generating AI and receive answers.

[1669] (Claim 3)

[1670] 2. The system of claim 1, further comprising: means for periodically extracting answers for which scores have been entered by users.

[1671] "Example 1"

[1672] (Claim 1)

[1673] an information processing device for inputting a question;

[1674] data processing means for receiving an input question and providing a generated answer;

[1675] an evaluation means for scoring the generated answers;

[1676] storage means for storing and managing scores;

[1677] A means of extracting highly scored responses and querying them in external sources;

[1678] A system including:

[1679] (Claim 2)

[1680] 10. The system of claim 1, comprising data processing means operable to send questions to the generative AI model and receive answers.

[1681] (Claim 3)

[1682] 2. The system according to claim 1, further comprising means for periodically extracting answers for which scores have been input by the evaluation means.

[1683] "Application Example 1"

[1684] (Claim 1)

[1685] a terminal means for inputting a question;

[1686] server means for receiving input questions and providing generated answers;

[1687] a user means for scoring the generated answers;

[1688] a database means for storing and managing scores;

[1689] A means of extracting highly scored responses and querying them in external sources;

[1690] A means for causing a generative AI model to generate an answer in real time based on a question from a terminal means;

[1691] A means for displaying the answer generated by the generative AI model and providing a dedicated interface for the user to input an evaluation;

[1692] Measures to strengthen credibility based on external source inquiries; and

[1693] A system including:

[1694] (Claim 2)

[1695] 10. The system of claim 1, further comprising: server means operable to send questions to the generating AI and receive answers.

[1696] (Claim 3)

[1697] 2. The system of claim 1, further comprising: means for periodically extracting answers for which scores have been entered by users.

[1698] "Example 2: Combining Emotion Engines"

[1699] (Claim 1)

[1700] a device means for inputting a question;

[1701] A server means having a function of receiving an input question, analyzing it, formatting it for the generation AI, and obtaining an answer;

[1702] A means for displaying the generated answers on a terminal and allowing the user to score them;

[1703] database means for storing and managing scores and associated emotion data;

[1704] A means of extracting high-scoring answers and conducting verification checks with external sources of information;

[1705] A system including:

[1706] (Claim 2)

[1707] 10. The system of claim 1, further comprising: server means having a function for analyzing user emotion data by an emotion engine.

[1708] (Claim 3)

[1709] 10. The system of claim 1, further comprising means for periodically extracting answers entered by users with high scores and performing queries against an external database.

[1710] "Application example 2 when combining emotion engines"

[1711] (Claim 1)

[1712] a terminal means for inputting a question;

[1713] server means for receiving input questions and providing generated answers;

[1714] a user means for scoring the generated answers;

[1715] a database means for storing and managing scores;

[1716] A means of extracting the highest scoring answers and querying them in external sources;

[1717] an emotion engine means for analyzing and recognizing emotions from user inputs and actions;

[1718] a means for verifying the reliability of answers to user questions with external expert sources;

[1719] A system including:

[1720] (Claim 2)

[1721] 10. The system of claim 1, further comprising: server means operable to send questions to the generating AI and receive answers.

[1722] (Claim 3)

[1723] 2. The system of claim 1, further comprising: means for periodically extracting answers for which scores have been entered by users. [Explanation of symbols]

[1724] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a terminal means for inputting a question; server means for receiving input questions and providing generated answers; a user means for scoring the generated answers; a database means for storing and managing scores; A means of extracting the highest scoring answers and querying them in external sources; A system including:

2. 2. The system of claim 1, further comprising server means having the function of sending questions to the generating AI and receiving answers.

3. 2. The system according to claim 1, further comprising means for periodically extracting answers for which scores have been entered by users.

Images