system

Abstract

We provide the system. [Solution] The user terminal where the question is entered, A server that logs the questions received from the user terminal, A means for sending the questions recorded in the log to a generative artificial intelligence system and causing it to generate answers, A system including means for returning the generated response to the user terminal.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In events such as orientations, it is often impossible to respond quickly and accurately to a wide variety of questions from new participants by conventional methods. In particular, in large-scale orientations or events held remotely, the processing of questions causes an increase in cost and labor. In addition, dissatisfaction may arise due to a shortage of human resources or oversight of questions. Furthermore, it is also difficult to answer multiple questions consistently. There is a need for a system that solves these problems and realizes an efficient and consistent response.

Means for Solving the Problems

[0005] The present invention provides a system that receives questions from a user terminal, logs the questions, and transmits the logged questions to a generative artificial intelligence system to generate answers. Specifically, the system includes a user terminal for inputting questions, a server that logs the questions received from the user terminal, means for transmitting the logged questions to a generative artificial intelligence system to generate answers, and means for returning the generated answers to the user terminal, enabling quick and efficient answers to questions. Furthermore, by including means for displaying the generated answers, the user can immediately confirm the answers. In addition, by using a natural language processing model in the generative artificial intelligence system, it is possible to provide consistent answers.

[0006] A "user terminal for entering questions" refers to a device used by users to enter questions in natural language, and generally includes forms such as personal computers, smartphones, and tablets.

[0007] A "logging server" is a computer system that has the function of receiving questions sent from user terminals and saving them to a database.

[0008] A "generative artificial intelligence system" is a system equipped with algorithms and models for generating appropriate answers to received questions, and it utilizes machine learning and natural language processing technologies.

[0009] "Means for generating answers" refers to methods or devices that input a question into a generative artificial intelligence system and perform the process of calculating and generating an answer corresponding to that question.

[0010] "Means for returning generated responses to the user's terminal" refers to communication methods or software for sending responses obtained from a generative artificial intelligence system to the terminal accessed by the user and displaying them.

[0011] "Means for displaying generated responses" refers to a user interface for visually displaying responses generated on the user's terminal.

[0012] A "natural language processing model" is a machine learning model or algorithm designed to analyze text data and understand and generate human language. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] A specific embodiment of the present invention will now be described.

[0035] This invention provides a question-and-answer system comprising a user terminal, a server, and a generative artificial intelligence system. The user inputs a question from the terminal, the question is sent to the generative artificial intelligence system via the server, and the answer generated by the AI ​​is returned to the user terminal.

[0036] System Configuration

[0037] 1. User terminal

[0038] A user terminal is a device used by the user to input questions. Examples include personal computers, smartphones, and tablets. Users use these devices to input orientation-related questions in text format.

[0039] 2. Server

[0040] The server receives questions sent from user terminals and records them in a log. The server has a database for storing question logs, and records received questions sequentially. The server also sends questions to a generative artificial intelligence system and returns the AI-generated answers to the user terminal.

[0041] 3. Generative Artificial Intelligence Systems

[0042] Generative artificial intelligence systems receive questions sent from a server and generate appropriate answers. Specifically, they use natural language processing models to analyze the meaning of the questions and create the optimal response.

[0043] Program Processing Description

[0044] 1. Enter and submit your question.

[0045] The user enters a question about the orientation into their terminal. For example, they might enter, "What is the date and time of the orientation?" The user then sends this question to the server.

[0046] 2. Receiving and logging questions

[0047] The server receives questions from the user's terminal. Received questions are recorded in the server's question log. This allows users to refer to the question content later.

[0048] 3. AI-powered response generation

[0049] The server sends the logged question to a generative artificial intelligence system. The generative AI system uses a natural language processing model to analyze the question and generate an appropriate answer. For example, it might generate the answer, "The orientation will begin at 10:00 on November 1, 2023."

[0050] 4. Return and display of responses

[0051] The server sends the response received from the generative artificial intelligence system back to the user terminal. The user terminal receives this response and displays it on the screen. This allows the user to immediately check the answer to their question.

[0052] Specific example

[0053] For example, if a user asks about the date and time of an orientation, the following process takes place: The user types "Please tell me the date and time of the orientation" and sends it from their terminal to the server. The server logs this question and sends it to a generative artificial intelligence system. The AI ​​generates the answer "The orientation will start on November 1, 2023 at 10:00" and sends it back to the server. The server sends this answer back to the user's terminal, and the user's terminal displays the answer.

[0054] The above describes specific embodiments for carrying out the present invention. The present invention allows users to obtain quick and accurate answers to their questions, thus enabling efficient question-and-answer sessions during orientation.

[0055] The following describes the processing flow.

[0056] Step 1:

[0057] The user enters a question into their terminal.

[0058] For example, a user might type, "Please tell me the date and time of the orientation."

[0059] Step 2:

[0060] The user terminal receives user input and sends that question to the server.

[0061] This process involves the user terminal sending question data to the server via the network.

[0062] Step 3:

[0063] The server receives the question sent from the user's terminal.

[0064] The server analyzes the received data and extracts the question content.

[0065] Step 4:

[0066] The server logs the questions it receives.

[0067] The server accesses the database and saves the question as a new entry.

[0068] Step 5:

[0069] The server sends the question to the generative artificial intelligence system.

[0070] The server calls the API of the generative artificial intelligence system and sends a question.

[0071] Step 6:

[0072] A generative artificial intelligence system generates answers to questions sent from a server.

[0073] The AI ​​system uses a natural language processing model to generate appropriate answers.

[0074] Step 7:

[0075] The generative artificial intelligence system sends the generated response back to the server.

[0076] The AI ​​system sends the response data to the server.

[0077] Step 8:

[0078] The server receives the generated response and sends it back to the user's terminal.

[0079] The server packages the response data and sends it to the user's terminal via the network.

[0080] Step 9:

[0081] The user terminal displays the response received from the server to the user.

[0082] The user's terminal displays the received response on the screen so that the user can confirm it.

[0083] The above outlines the specific steps involved in question processing using a user terminal, server, and generative artificial intelligence system.

[0084] (Example 1)

[0085] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0086] In today's information society, users are required to obtain information quickly and accurately. However, conventional information retrieval systems often take a long time to provide appropriate answers to questions, which impairs user convenience. Furthermore, insufficient logging of questions and management of generated answers make it difficult to refer to and analyze question history.

[0087] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0088] In this invention, the server includes means for logging questions received from a terminal, means for sending the logged questions to a generative artificial intelligence model to generate answers, means for returning the generated answers to the terminal, and means for displaying the generated answers. This enables users to quickly obtain appropriate answers and facilitates the management and analysis of question history.

[0089] A "terminal" is a device used by a user to input questions, and includes personal computers, smartphones, tablets, and other similar devices.

[0090] A "computer" is a server that has the function of logging questions received from terminals and sending those questions to a generative artificial intelligence model.

[0091] A "generative artificial intelligence model" is an artificial intelligence system that uses natural language processing technology to analyze input questions and generate appropriate answers.

[0092] A "log" refers to a database or file used to record questions received from a terminal.

[0093] A "question" refers to information or data entered by the user through their device. A generative artificial intelligence model performs analysis based on this question.

[0094] "Answer" refers to the information and data generated by a generative artificial intelligence model after analyzing a question, and its purpose is to provide information to the user.

[0095] "Formatting" refers to arranging data into a specific format or converting it into an appropriate structure for communication purposes.

[0096] An "HTTP request" is a type of communication protocol used by a terminal to send a question to a computer.

[0097] The present invention is a question-and-answer system for providing quick and appropriate answers to user questions. This system includes a terminal, a server, and a generative artificial intelligence model.

[0098] System Configuration

[0099] 1. Terminal

[0100] A terminal is a device used by the user to input questions, and specific examples include personal computers, smartphones, and tablets. Users use these terminals to input orientation-related questions in text format.

[0101] 2. Server

[0102] The server is responsible for receiving questions sent from user terminals and logging them. The server has a database for storing question logs, and it records received questions sequentially. The server also sends questions to a generative artificial intelligence model and returns the AI-generated answers to the user terminal.

[0103] 3. Generative artificial intelligence models

[0104] Generative artificial intelligence models receive questions sent from a server and generate optimal answers using natural language processing techniques. Specifically, they use natural language processing models (for example, GPT-4®) to analyze the meaning of the questions and create the best possible answers.

[0105] Operation details

[0106] 1. Enter and submit your question.

[0107] The user enters a question about the orientation into the terminal. For example, a question such as "What is the date and time of the orientation?" is entered. The terminal then sends this question to the server. Typically, it is sent as an HTTP POST request.

[0108] 2. Receiving and logging questions

[0109] The server receives a question from the user's terminal and saves it as a new entry in the "questions_logs" table in the database. For example, it might record "id=1, question='Please tell me the date and time of the orientation.', timestamp='2023-11-01 09:00:00'". Once logging is complete, the server sends the question data to a generative artificial intelligence model.

[0110] 3. AI-powered response generation

[0111] The server sends the recorded question data as an API request to a generative artificial intelligence model. The generative AI model receives the question data, uses a natural language processing model to analyze the content of the question, and generates an appropriate answer. For example, it might generate the answer, "The orientation will begin at 10:00 on November 1, 2023."

[0112] 4. Return and display of responses

[0113] The server sends the response received from the generative artificial intelligence model back to the user terminal, which then receives and displays the response on its screen. This allows the user to immediately see the answer to their question.

[0114] Specific example

[0115] For example, if a user asks about the date and time of the orientation, they might enter a prompt like this: "Please tell me the date and time of the orientation." The terminal sends this question to the server, which logs the question and then sends it to a generative artificial intelligence model. The AI ​​analyzes the question and generates the answer, "The orientation will start on November 1, 2023 at 10:00," and sends it back to the server. The server then sends this answer to the user's terminal, which displays the answer.

[0116] Thus, the present invention provides an effective means for providing quick and accurate answers to user questions, and can significantly improve the efficiency of question and answer sessions.

[0117] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0118] Step 1:

[0119] The user enters a question using a terminal. For example, the user enters "Please tell me the date and time of the orientation." The input is a text-based question. The output is the formatted data of this question. This formatted data is sent to the server as an HTTP POST request.

[0120] Step 2:

[0121] The terminal sends the question entered by the user to the server. The input is question data in text format. The output is an HTTP request sent to the server. Specifically, the terminal parses the input data into JSON format, constructs the HTTP request, and sends it to the server's API endpoint.

[0122] Step 3:

[0123] The server logs questions received from user terminals. The input is the question data received as an HTTP request. The output is the question entry recorded in the log database. Specifically, the server extracts the question content from the request and adds a new entry to the "questions_logs" table in the database. For example, it will be recorded in the format "id=1, question='Please tell me the date and time of the orientation.', timestamp='2023-11-01 09:00:00'".

[0124] Step 4:

[0125] The server sends the logged questions to a generative artificial intelligence model. The input is question data stored in a database. The output is an API request to the generative artificial intelligence model. Specifically, the server retrieves the question data, constructs the API request, and sends it to the generative artificial intelligence model.

[0126] Step 5:

[0127] A generative artificial intelligence model receives question data and generates an appropriate answer. The input is the question data received as an API request. The output is the generated answer data. Specifically, the generative AI model uses natural language processing techniques to analyze the content of the question and generate the optimal answer. For example, it might generate the answer, "The orientation will start at 10:00 on November 1, 2023."

[0128] Step 6:

[0129] A generative artificial intelligence system sends the generated answer back to the server. The input is the generated answer data. The output is the API response sent to the server. Specifically, the generative AI model packages the answer data as an API response and sends it to the server.

[0130] Step 7:

[0131] The server sends the generated response to the user's terminal. The input is the response data received from the generative artificial intelligence model. The output is the HTTP response sent to the user's terminal. Specifically, the server converts the response data into JSON format and sends it to the user's terminal as an HTTP response.

[0132] Step 8:

[0133] The terminal displays the response received from the server. The input is the response data received as an HTTP response. The output is the response text displayed on the user interface. Specifically, the terminal parses the received response data and displays on the screen, "The orientation will begin at 10:00 on November 1, 2023."

[0134] (Application Example 1)

[0135] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0136] In physical stores, responding quickly and accurately to customer inquiries is essential for improving customer satisfaction. However, with traditional methods, store staff are not always available, and not all inquiries can be answered immediately. As a result, customers may become dissatisfied. Furthermore, it involves high labor costs and requires staff training, placing a significant burden on operations. To solve these problems, there is a need for a system that automatically answers customer questions in physical stores.

[0137] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0138] In this invention, the server includes a user terminal for inputting questions, means for logging the questions received from the user terminal, means for transmitting the questions recorded in the log to a generative artificial intelligence system for generating answers, means for returning the generated answers to the user terminal, and means for performing question answering in a physical store, which has a display device for displaying the answers. This makes it possible to respond to customer inquiries immediately in a physical store, reduce the burden on store staff, and improve customer satisfaction.

[0139] A "user terminal for entering questions" is a device used by customers to enter questions in text or voice.

[0140] A "log" is a database or file used to record questions sent from a user's terminal.

[0141] A "server" is a computer system that records questions received from user terminals as logs and sends them to a generative artificial intelligence system to generate answers.

[0142] A "generative artificial intelligence system" is an artificial intelligence system that uses natural language processing technology to generate appropriate answers to input questions.

[0143] "Means for generating answers" refers to means that include the process of creating the optimal answer to an input question using a generative artificial intelligence system.

[0144] "Means of returning to the user terminal" refers to means of sending the generated response to the user terminal so that the customer can receive it.

[0145] A "display device" is a device that visually displays the generated responses in a physical store.

[0146] "Means of answering questions in physical stores" refers to a series of system components for automatically answering customer questions in a physical store.

[0147] The embodiments for carrying out the present invention are described below. This system is for automatically providing answers to customer questions in a physical store and includes a user terminal for inputting questions, a server for receiving questions and recording them in a log, a generative artificial intelligence system, and means for returning the generated answers to the user terminal.

[0148] System Configuration

[0149] First, the user terminal is a device that customers use to input questions. Specifically, this includes smartphones, smart glasses, or interface devices installed in stores. This allows customers to ask questions using voice input or text input.

[0150] Next, the server receives and logs the questions sent from the user terminal. The server is built using, for example, Flask (a Python®-based web framework). A database such as MySQL® or PostgreSQL is used to record the questions. The logged questions are sent to a generative artificial intelligence system.

[0151] Generative artificial intelligence systems generate answers to questions using natural language processing techniques. These systems utilize advanced natural language processing models, such as GPT-4 (API example: OpenAI®). This allows them to analyze the content of a question and automatically generate the optimal answer.

[0152] The generated response is returned to the user's terminal by the server and then communicated to the customer via a display or audio output device built into the terminal. This series of processes allows customers to receive quick and appropriate service in physical stores.

[0153] Specific example

[0154] For example, consider a scenario where a customer enters the question, "Where is the product located?" via their smartphone. The user's device sends this question to the server. The server logs the question and sends it to a generative artificial intelligence system. The AI ​​generates an answer, such as "The product is on the second floor, on the left," and returns it to the server. The server then sends the answer to the user's smartphone, which displays the answer on its screen. In this way, the customer can quickly obtain the information they need.

[0155] Example of a prompt

[0156] Examples of prompt statements are shown below.

[0157] Question: Where can I find the product?

[0158] Answer: The item is located on the left side of the second floor.

[0159] This system allows for immediate responses to customer inquiries in physical stores, thereby improving the efficiency of store operations. This can lead to increased customer satisfaction and reduced workload for store staff.

[0160] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0161] Step 1:

[0162] The user terminal receives questions from customers. Customers input questions using their smartphones or smart glasses in voice or text format. The input question data is formatted for transmission to the server. For example, if the input is voice, it is converted to text using speech recognition software. The output is the input data formatted as a question in text format.

[0163] Step 2:

[0164] The server receives questions sent from the user's terminal. The received question data is stored in a database for logging purposes. The input data is the question text sent by the user, and the output is the question log stored in the database. For example, a web server built using Flask receives question data and stores it in a MySQL or PostgreSQL database.

[0165] Step 3:

[0166] The server sends the logged questions to the generative artificial intelligence system. In doing so, it converts the question data into an appropriate format for an API request. The input data is the question log read from the database, and the output is an API request to the generative artificial intelligence system. For example, when using OpenAI's GPT-4 API, the question text is sent as a prompt.

[0167] Step 4:

[0168] The generative artificial intelligence system analyzes the received question and generates an answer. Using a natural language processing model, it understands the meaning of the question and generates the most appropriate response. The input data for this step is the question sent from the server, and the output data is the generated answer.

[0169] Step 5:

[0170] The server returns the response received from the generative artificial intelligence system to the user terminal. It formats the received response data into an appropriate format for transmission to the user terminal. The input data is the response text sent from the generative artificial intelligence system, and the output data is the formatted response data sent to the user terminal.

[0171] Step 6:

[0172] The user terminal receives the response sent from the server and displays it to the customer. It also outputs the response as needed. The input data for this step is the response text returned from the server, and the output data is the response information displayed on the user terminal. Specifically, the response text is displayed on the smartphone screen, or the response is played back as audio using speech synthesis software.

[0173] The above outlines the specific processing steps involved in implementing the present invention. This makes it possible to provide quick and appropriate answers to customer inquiries in physical stores.

[0174] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0175] A specific embodiment of the present invention will now be described.

[0176] The present invention provides a question-and-answer system that further combines a user terminal for inputting questions, a server for logging questions, means for transmitting the logged questions to a generative artificial intelligence system for generating answers, and means for returning the generated answers to the user terminal with an emotion engine that recognizes the user's emotions.

[0177] System Configuration

[0178] 1. User terminal

[0179] A user terminal is a device used by the user to input questions and send emotional information recognized by the emotion engine to the server. Examples include personal computers, smartphones, and tablets. Users use these terminals to input orientation-related questions in text format and to acquire emotional data through the camera, microphone, etc.

[0180] 2. Emotional Engine

[0181] The emotion engine is a system that analyzes audio and image data acquired from the user's device to identify the user's emotions. The emotion engine identifies emotions such as joy, anger, sadness, and happiness by analyzing the user's voice tone and facial expressions.

[0182] 3. Server

[0183] The server receives and logs questions and sentiment data sent from the user terminal. The server has a database for storing questions and associated sentiment information. The server also transmits the questions and sentiment data to a generative artificial intelligence system and returns the AI-generated answers to the user terminal.

[0184] 4. Generative Artificial Intelligence Systems

[0185] The generative artificial intelligence system receives question and sentiment data sent from a server and generates appropriate answers. Specifically, it uses natural language processing models and sentiment-responding algorithms to analyze the content of the question and generate responses that reflect the sentiment.

[0186] Program Processing Description

[0187] 1. Question input and sentiment recognition

[0188] Users input questions about the orientation into their devices and provide emotional data through the device's camera and microphone. For example, they might ask, "Please tell me the date and time of the orientation," along with sending an anxious facial expression and tone of voice to the device.

[0189] 2. Sending questions and sentiment data

[0190] The user terminal analyzes the user's input and acquired sentiment data, and sends that information to the server. The questions and sentiment data are packaged in an appropriate format.

[0191] 3. Receiving and logging questions and sentiment data.

[0192] The server receives questions and sentiment data sent from the user's terminal and records them in the database. This ensures that the questions and the corresponding sentiments are saved as logs.

[0193] 4. AI-powered response generation

[0194] The server sends the question and sentiment data to a generative artificial intelligence system. The generative AI system uses a natural language processing model and sentiment-responding algorithms to generate an answer that is appropriate to the content of the question and the user's sentiment. For example, it might generate an answer such as, "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry; detailed instructions will be distributed later."

[0195] 5. Return and display of responses

[0196] The server sends the response received from the generative artificial intelligence system back to the user terminal. The user terminal receives this response and displays it on the screen. This allows the user to immediately see the answer to their question and emotionally sensitive commentary.

[0197] Specific example

[0198] For example, if a user is worried about orientation, the following process takes place: The user types, "Please tell me the date and time of the orientation," and the device picks up on the user's anxious facial expression and tone of voice. The device sends this information to the server, which logs the question and emotion data. The server sends this data to a generative artificial intelligence system, which generates the response, "The orientation will start at 10:00 on November 1, 2023. There is no need to worry; detailed instructions will be distributed later." The server sends this response back to the user's device, which then displays it.

[0199] The above describes specific embodiments for carrying out the present invention. The present invention allows users to not only obtain quick and accurate answers to their questions, but also receive responses that take their emotions into consideration, enabling efficient question-and-answer sessions during orientation.

[0200] The following describes the processing flow.

[0201] Step 1:

[0202] Users input questions into their devices and provide emotional data through audio and video.

[0203] For example, a user might type, "Please tell me the date and time of the orientation," and convey an anxious expression or a tense tone of voice to the device.

[0204] Step 2:

[0205] The user terminal receives and analyzes the user's input text and emotional data (facial expressions and vocal characteristics).

[0206] The emotion engine analyzes the user's facial expressions and tone of voice to recognize when the user is feeling anxious.

[0207] Step 3:

[0208] The user's terminal analyzes the questions and sentiment data and sends it to the server.

[0209] Here, the emotional state (e.g., anxiety) is packaged along with the question content and sent to the server via the network.

[0210] Step 4:

[0211] The server receives the question and sentiment data sent from the user's terminal.

[0212] The received data is analyzed to extract questions and sentiment information.

[0213] Step 5:

[0214] The server logs the questions and sentiment data it receives.

[0215] By saving the question content and emotional state in a database, they can be referenced later.

[0216] Step 6:

[0217] The server sends the question and emotion data to the generative artificial intelligence system.

[0218] The API of a generative artificial intelligence system is called, and questions and sentiment data are sent.

[0219] Step 7:

[0220] A generative artificial intelligence system receives questions and sentiment data sent from a server and generates answers.

[0221] Using natural language processing models and emotion-response algorithms, we create responses that take the user's emotions into consideration.

[0222] Step 8:

[0223] The generative artificial intelligence system sends the generated response back to the server.

[0224] The generated response data is sent to the server.

[0225] Step 9:

[0226] The server returns the response received from the generative artificial intelligence system to the user's terminal.

[0227] The response data is packaged and sent to the user's terminal via the network.

[0228] Step 10:

[0229] The user terminal displays the response received from the server to the user.

[0230] The user's terminal displays the received response on the screen for the user to confirm. For example, a response such as "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later." might be displayed.

[0231] The above outlines the specific steps for question processing using the user terminal, server, generative artificial intelligence system, and emotion engine.

[0232] (Example 2)

[0233] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 will be referred to as the "terminal".

[0234] Traditional question-and-answer systems can provide appropriate answers to user-submitted questions, but they lacked responses that took user emotions into account. Therefore, they were unable to respond flexibly to changes in user emotions, making it difficult to improve the user experience. Especially in situations involving tension and anxiety, such as orientation sessions, responses that consider emotions are essential.

[0235] The identification processing performed 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 an information processing device for recording questions, means for acquiring emotion data along with the questions, means for analyzing the acquired emotion data, means for transmitting the questions recorded in the log to a generative artificial intelligence system to generate answers, and means for returning the generated answers to an information terminal. This makes it possible to quickly provide appropriate answers that take into account the user's emotions in response to questions entered by the user.

[0236] A "question" is text data entered by the user, which requests information from the system.

[0237] An "information terminal" is a device used by a user to input questions, and includes personal computers, smartphones, tablets, and other similar devices.

[0238] An "information processing device" is a device that receives and records questions transmitted from an information terminal, and includes servers, among other things.

[0239] "Emotional data" refers to data related to emotions obtained from the user's facial expressions, voice, etc., and indicates states such as anxiety or joy.

[0240] "Means of acquiring emotions" refers to methods of acquiring a user's emotions using devices such as cameras and microphones.

[0241] "Means for analyzing emotions" refers to methods for analyzing and identifying a user's emotions based on acquired emotional data, and an emotion engine falls under this category.

[0242] A "generative artificial intelligence system" is a system that uses a natural language processing model to generate appropriate answers based on input question data and sentiment data.

[0243] "Methods for generating answers" refers to a method of sending questions and sentiment data to a generative artificial intelligence system and having it generate answers.

[0244] "Method of returning to the information terminal" refers to a method of returning the response generated by the generative artificial intelligence system to the information terminal and displaying it to the user.

[0245] "Means of recording" refers to a method of storing received questions and sentiment data in a database for later analysis and reference.

[0246] This invention provides a question-and-answer system in which a user inputs a question and the system recognizes the emotions associated with that question. This system consists of an information terminal, an information processing device (server), an emotion analysis engine, and a generative artificial intelligence system.

[0247] System Configuration

[0248] 1. Information terminal

[0249] Information terminals are devices that allow users to input questions and provide sentiment data. Specifically, this includes personal computers, smartphones, and tablets. Users can use these devices to input questions in text format and have sentiment data acquired through the camera and microphone.

[0250] 2. Emotion Analysis Engine

[0251] An emotion analysis engine is a system that analyzes audio and image data acquired from an information terminal to identify the user's emotions. By analyzing the user's voice tone and facial expressions, the emotion analysis engine identifies emotions such as joy, anger, sadness, and happiness, and transmits this data as emotion information to an information processing device.

[0252] 3. Information processing equipment (server)

[0253] The information processing device (server) receives and records question and sentiment data transmitted from information terminals. It has the function of storing question and sentiment data in a database and accumulates the data as logs for post-processing. The server also plays the role of transmitting this data to a generative artificial intelligence system and returning the generated answers to the information terminals.

[0254] 4. Generative Artificial Intelligence Systems

[0255] Generative artificial intelligence systems are systems that generate appropriate answers using question and sentiment data received from a server. Specifically, they use natural language processing models and sentiment response algorithms to generate appropriate responses that match the content of the question and the user's emotions.

[0256] Specific example

[0257] For example, if a user is feeling anxious about orientation, the following actions are performed: The user texts "Please tell me the date and time of the orientation" on their information terminal, and their anxious facial expression and tone of voice are captured by the camera and microphone on the terminal. The information terminal sends this to a server, which logs the question and emotion data. Next, the server sends this data to a generative artificial intelligence system, which generates a response such as "The orientation will start at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later." The server sends this response back to the information terminal, which displays it. This example demonstrates how users can quickly obtain answers to their questions and receive polite responses that also address their emotions.

[0258] Example of a prompt

[0259] Here are some examples of specific prompt statements:

[0260] User question: "What is the date and time of the orientation?"

[0261] User's emotion: "Anxiety"

[0262] Using this prompt, the generative AI model generates an appropriate answer based on the user's question and sentiment.

[0263] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0264] Step 1:

[0265] Question input and sentiment recognition

[0266] Specific actions:

[0267] Users input questions about the orientation in text format into an information terminal. At the same time, they provide voice and facial expressions using the terminal's camera and microphone. For example, a user might input "Please tell me the date and time of the orientation," and then display an anxious expression and a trembling voice.

[0268] input:

[0269] Text-based questions such as "Please tell me the date and time of the orientation," and audio and image data from the camera and microphone.

[0270] Data processing:

[0271] The information terminal collects image data from the camera and audio data from the microphone.

[0272] output:

[0273] Collected text questions and sentiment data.

[0274] Step 2:

[0275] Sending questions and sentiment data

[0276] Specific actions:

[0277] The information terminal analyzes the acquired questions and sentiment data, formats them, and sends them to the information processing device (server).

[0278] input:

[0279] Text-based questions and sentiment data.

[0280] Data processing:

[0281] Integrate question text data and sentiment data into a single message and package it in an appropriate format.

[0282] output:

[0283] Formatted question data and sentiment data.

[0284] Step 3:

[0285] Receiving and logging questions and sentiment data

[0286] Specific operations:

[0287] The server receives the questions and sentiment data sent from the information terminal and records them in the database. As a result, the questions and sentiment information are saved as logs and can be referred to later.

[0288] Input:

[0289] Formatted question data and sentiment data.

[0290] Data processing:

[0291] Record the received data in the database.

[0292] Output:

[0293] Question and sentiment data stored in the database.

[0294] Step 4:

[0295] Answer generation by AI

[0296] Specific operations:

[0297] The server sends the questions and sentiment data stored in the database to a generative artificial intelligence system to generate appropriate answers. The generative artificial intelligence system creates answers using a generative AI model based on the question content and sentiment.

[0298] Input:

[0299] Question and sentiment data stored in the database.

[0300] Data processing:

[0301] Using the natural language processing model and emotion response algorithm of the generative artificial intelligence system, generate answers according to questions and emotions.

[0302] Output:

[0303] The generated answer.

[0304] Step 5:

[0305] Return and display of the answer

[0306] Specific operations:

[0307] The server returns the answer received from the generative artificial intelligence system to the information terminal. The information terminal receives this answer and displays it to the user. As a specific example, "The orientation will start at 10:00 on November 1, 2023. There is no need to worry, and detailed guidance will also be distributed at a later date." is displayed.

[0308] Input:

[0309] The generated answer.

[0310] Data processing:

[0311] Send the answer data to the user terminal.

[0312] Output:

[0313] The answer displayed on the information terminal.

[0314] (Application Example 2)

[0315] Next, Application Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0316] Conventional question-and-answer systems only generate appropriate answers to user-entered questions, failing to provide responses that take into account the user's emotional state. Therefore, particularly in security services, when users are experiencing anxiety or stress, the lack of empathetic responses can lead to decreased user satisfaction. Solving this problem is essential.

[0317] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a user terminal for inputting questions, means for logging the questions received from the user terminal, means for transmitting the questions recorded in the log to a generative artificial intelligence system to generate answers, means for returning the generated answers to the user terminal, an emotion engine for recognizing the user's emotions, means for adjusting the answers generated based on the emotions recognized by the emotion engine, and means for displaying the generated answers. This makes it possible to provide appropriate answers while taking into account the user's emotional state.

[0318] A "user terminal" is a device used by users to input questions, acquire emotional data through an emotional engine, and send it to a server.

[0319] A "server" is a computer whose role is to receive and log questions and sentiment data sent from user terminals, send that data to a generative artificial intelligence system to generate answers, and then return those answers to the user terminals.

[0320] A "generative artificial intelligence system" is a system that uses a natural language processing model to generate appropriate answers based on questions and sentiment data sent from a server.

[0321] An "emotion engine" is a system that analyzes audio and image data acquired from a user's device to identify the user's emotions.

[0322] "Response adjustment" is the process of appropriately modifying responses generated by a generative artificial intelligence system, based on emotional information recognized by the emotion engine, to take the user's emotions into consideration.

[0323] "Inputting a question" refers to the act of a user entering information they want to know into their device in the form of text or voice.

[0324] A "display means" is an interface for visually presenting the response generated on the user's terminal to the user.

[0325] The present invention will now be described in detail. To implement the invention, four main elements are required: a user terminal, an emotion engine, a server, and a generative artificial intelligence system. These elements work together to create a system that provides appropriate answers to user questions and emotions.

[0326] User terminal

[0327] The user terminal is a device used by the user to input questions and acquire emotional data. Specifically, smartphones, tablets, and personal computers are used. The user uses these devices to input questions in text or voice format, and emotional data such as facial expressions and voice tone is acquired through the camera and microphone.

[0328] Emotional Engine

[0329] An emotion engine is software that analyzes image and audio data transmitted from a user's device to identify the user's emotions. For example, image data analysis can be performed using OpenCV and Keras for face detection and emotion recognition. Audio data analysis can be performed using an audio processing library to analyze the tone of voice.

[0330] server

[0331] The server receives questions and sentiment data sent from user terminals and logs them in a database. The server also transmits questions and sentiment data to a generative artificial intelligence system, receives the generated answers, and sends them back to the user terminal. The server also incorporates a database management system (DBMS) for log management and data storage.

[0332] Generative artificial intelligence systems

[0333] The generative artificial intelligence system generates appropriate answers using a natural language processing model based on questions and sentiment data sent from the server. Specifically, it uses OpenAI's GPT-2 and modules for natural language processing. This results in the generation of answers that take sentiment into consideration.

[0334] Specific example

[0335] For example, if a user asks with an anxious expression, "What measures should I take to protect my home?", the emotion engine analyzes the expression and identifies the emotion as "anxiety." The server sends this emotion information and the question to a generative artificial intelligence system, which then generates an answer such as, "As a measure to protect your home, first install an outdoor light to deter intruders. Also, installing security cameras will give you peace of mind."

[0336] Example of a prompt

[0337] The prompt will look like this:

[0338] The user is feeling anxious and asks: What measures should I take to protect my home from crime?

[0339] By inputting this prompt into a generative artificial intelligence system, an appropriate response that corresponds to the user's emotions can be obtained.

[0340] This invention realizes an emotion-responsive question-and-answer system, which is expected to have the effect of reducing user anxiety and stress, particularly in the field of security services.

[0341] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0342] Step 1:

[0343] The user enters a question, and sentiment data is collected on the user's device.

[0344] Input: The user enters the question, "What measures should I take to improve home security?" into the user's device. Emotional data is acquired through the camera and microphone to recognize anxious facial expressions and tone of voice.

[0345] Data processing: The device generates question data in text format, analyzes image and audio data acquired by the camera and microphone, and identifies emotions from facial expressions and tone of voice.

[0346] Output: Questionnaire data in text format and emotion data for "anxiety" recognized by the emotion engine.

[0347] Step 2:

[0348] The user's terminal sends the question and sentiment data to the server.

[0349] Input: Question data and sentiment data generated in Step 1.

[0350] Data processing: The user terminal packages the question data and sentiment data and sends it to the server in the appropriate format.

[0351] Output: Question data and sentiment data sent to the server.

[0352] Step 3:

[0353] The server receives the question and sentiment data and records it in the database.

[0354] Input: Question data and sentiment data sent from the user's terminal.

[0355] Data processing: The server records the received data in a database and saves it as a log.

[0356] Output: Question data and sentiment data stored in the database.

[0357] Step 4:

[0358] The server sends the question and sentiment data to the generative artificial intelligence system.

[0359] Input: Question data and sentiment data recorded in the database.

[0360] Data processing: The server sends question data and sentiment data to the generative artificial intelligence system in an appropriate format.

[0361] Output: Question data and sentiment data sent to a generative artificial intelligence system.

[0362] Step 5:

[0363] The generative artificial intelligence system generates answers that are tailored to the question and the emotions it evokes.

[0364] Input: Question data and sentiment data sent from the server.

[0365] Data Processing: Generative artificial intelligence systems use natural language processing models and sentiment-responding algorithms to generate answers that correspond to the content and emotions of a question. For example, using the GPT-2 model, the prompt "User is feeling anxious and asks: What measures should I take to protect my home?" is processed as input.

[0366] Output: A response that takes emotions into consideration, generated by a generative artificial intelligence system (Example: "As a security measure for my home, I will first install an outdoor light to deter intruders. I will also gain peace of mind by installing a security camera.")

[0367] Step 6:

[0368] The server sends the generated response back to the user's terminal.

[0369] Input: Answer generated by a generative artificial intelligence system.

[0370] Data processing: The server sends the generated response to the user's terminal in the appropriate format.

[0371] Output: Generated response sent to the user's terminal.

[0372] Step 7:

[0373] The user terminal displays the generated response.

[0374] Input: Generated response sent from the server.

[0375] Data processing: The user terminal generates the response and displays it on the screen.

[0376] Output: Generated response that the user can view on the screen.

[0377] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0378] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0379] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0380] [Second Embodiment]

[0381] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0382] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0383] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0384] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0385] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0386] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0387] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0388] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0389] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0390] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0391] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0392] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0393] A specific embodiment of the present invention will now be described.

[0394] This invention provides a question-and-answer system comprising a user terminal, a server, and a generative artificial intelligence system. The user inputs a question from the terminal, the question is sent to the generative artificial intelligence system via the server, and the answer generated by the AI ​​is returned to the user terminal.

[0395] System Configuration

[0396] 1. User terminal

[0397] A user terminal is a device used by the user to input questions. Examples include personal computers, smartphones, and tablets. Users use these devices to input orientation-related questions in text format.

[0398] 2. Server

[0399] The server receives questions sent from user terminals and records them in a log. The server has a database for storing question logs, and records received questions sequentially. The server also sends questions to a generative artificial intelligence system and returns the AI-generated answers to the user terminal.

[0400] 3. Generative Artificial Intelligence Systems

[0401] Generative artificial intelligence systems receive questions sent from a server and generate appropriate answers. Specifically, they use natural language processing models to analyze the meaning of the questions and create the optimal response.

[0402] Program Processing Description

[0403] 1. Enter and submit your question.

[0404] The user enters a question about the orientation into their terminal. For example, they might enter, "What is the date and time of the orientation?" The user then sends this question to the server.

[0405] 2. Receiving and logging questions

[0406] The server receives questions from the user's terminal. Received questions are recorded in the server's question log. This allows users to refer to the question content later.

[0407] 3. AI-powered response generation

[0408] The server sends the logged question to a generative artificial intelligence system. The generative AI system uses a natural language processing model to analyze the question and generate an appropriate answer. For example, it might generate the answer, "The orientation will begin at 10:00 on November 1, 2023."

[0409] 4. Return and display of responses

[0410] The server sends the response received from the generative artificial intelligence system back to the user terminal. The user terminal receives this response and displays it on the screen. This allows the user to immediately check the answer to their question.

[0411] Specific example

[0412] For example, if a user asks about the date and time of an orientation, the following process takes place: The user types "Please tell me the date and time of the orientation" and sends it from their terminal to the server. The server logs this question and sends it to a generative artificial intelligence system. The AI ​​generates the answer "The orientation will start on November 1, 2023 at 10:00" and sends it back to the server. The server sends this answer back to the user's terminal, and the user's terminal displays the answer.

[0413] The above describes specific embodiments for carrying out the present invention. The present invention allows users to obtain quick and accurate answers to their questions, thus enabling efficient question-and-answer sessions during orientation.

[0414] The following describes the processing flow.

[0415] Step 1:

[0416] The user enters a question into their terminal.

[0417] For example, a user might type, "Please tell me the date and time of the orientation."

[0418] Step 2:

[0419] The user terminal receives user input and sends that question to the server.

[0420] This process involves the user terminal sending question data to the server via the network.

[0421] Step 3:

[0422] The server receives the question sent from the user's terminal.

[0423] The server analyzes the received data and extracts the question content.

[0424] Step 4:

[0425] The server logs the questions it receives.

[0426] The server accesses the database and saves the question as a new entry.

[0427] Step 5:

[0428] The server sends the question to the generative artificial intelligence system.

[0429] The server calls the API of the generative artificial intelligence system and sends a question.

[0430] Step 6:

[0431] A generative artificial intelligence system generates answers to questions sent from a server.

[0432] The AI ​​system uses a natural language processing model to generate appropriate answers.

[0433] Step 7:

[0434] The generative artificial intelligence system sends the generated response back to the server.

[0435] The AI ​​system sends the response data to the server.

[0436] Step 8:

[0437] The server receives the generated response and sends it back to the user's terminal.

[0438] The server packages the response data and sends it to the user's terminal via the network.

[0439] Step 9:

[0440] The user terminal displays the response received from the server to the user.

[0441] The user's terminal displays the received response on the screen so that the user can confirm it.

[0442] The above outlines the specific steps involved in question processing using a user terminal, server, and generative artificial intelligence system.

[0443] (Example 1)

[0444] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0445] In today's information society, users are required to obtain information quickly and accurately. However, conventional information retrieval systems often take a long time to provide appropriate answers to questions, which impairs user convenience. Furthermore, insufficient logging of questions and management of generated answers make it difficult to refer to and analyze question history.

[0446] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0447] In this invention, the server includes means for logging questions received from a terminal, means for sending the logged questions to a generative artificial intelligence model to generate answers, means for returning the generated answers to the terminal, and means for displaying the generated answers. This enables users to quickly obtain appropriate answers and facilitates the management and analysis of question history.

[0448] A "terminal" is a device used by a user to input questions, and includes personal computers, smartphones, tablets, and other similar devices.

[0449] A "computer" is a server that has the function of logging questions received from terminals and sending those questions to a generative artificial intelligence model.

[0450] A "generative artificial intelligence model" is an artificial intelligence system that uses natural language processing technology to analyze input questions and generate appropriate answers.

[0451] A "log" refers to a database or file used to record questions received from a terminal.

[0452] A "question" refers to information or data entered by the user through their device. A generative artificial intelligence model performs analysis based on this question.

[0453] "Answer" refers to the information and data generated by a generative artificial intelligence model after analyzing a question, and its purpose is to provide information to the user.

[0454] "Formatting" refers to arranging data into a specific format or converting it into an appropriate structure for communication purposes.

[0455] An "HTTP request" is a type of communication protocol used by a terminal to send a question to a computer.

[0456] The present invention is a question-and-answer system for providing quick and appropriate answers to user questions. This system includes a terminal, a server, and a generative artificial intelligence model.

[0457] System Configuration

[0458] 1. Terminal

[0459] A terminal is a device used by the user to input questions, and specific examples include personal computers, smartphones, and tablets. Users use these terminals to input orientation-related questions in text format.

[0460] 2. Server

[0461] The server is responsible for receiving questions sent from user terminals and logging them. The server has a database for storing question logs, and it records received questions sequentially. The server also sends questions to a generative artificial intelligence model and returns the AI-generated answers to the user terminal.

[0462] 3. Generative artificial intelligence models

[0463] Generative artificial intelligence models receive questions sent from a server and generate optimal answers using natural language processing techniques. Specifically, they use a natural language processing model (e.g., GPT-4) to analyze the meaning of the question and create the best possible answer.

[0464] Operation details

[0465] 1. Enter and submit your question.

[0466] The user enters a question about the orientation into the terminal. For example, a question such as "What is the date and time of the orientation?" is entered. The terminal then sends this question to the server. Typically, it is sent as an HTTP POST request.

[0467] 2. Receiving and logging questions

[0468] The server receives a question from the user's terminal and saves it as a new entry in the "questions_logs" table in the database. For example, it might record "id=1, question='Please tell me the date and time of the orientation.', timestamp='2023-11-01 09:00:00'". Once logging is complete, the server sends the question data to a generative artificial intelligence model.

[0469] 3. AI-powered response generation

[0470] The server sends the recorded question data as an API request to a generative artificial intelligence model. The generative AI model receives the question data, uses a natural language processing model to analyze the content of the question, and generates an appropriate answer. For example, it might generate the answer, "The orientation will begin at 10:00 on November 1, 2023."

[0471] 4. Return and display of responses

[0472] The server sends the response received from the generative artificial intelligence model back to the user terminal, which then receives and displays the response on its screen. This allows the user to immediately see the answer to their question.

[0473] Specific example

[0474] For example, if a user asks about the date and time of the orientation, they might enter a prompt like this: "Please tell me the date and time of the orientation." The terminal sends this question to the server, which logs the question and then sends it to a generative artificial intelligence model. The AI ​​analyzes the question and generates the answer, "The orientation will start on November 1, 2023 at 10:00," and sends it back to the server. The server then sends this answer to the user's terminal, which displays the answer.

[0475] Thus, the present invention provides an effective means for providing quick and accurate answers to user questions, and can significantly improve the efficiency of question and answer sessions.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The user enters a question using a terminal. For example, the user enters "Please tell me the date and time of the orientation." The input is a text-based question. The output is the formatted data of this question. This formatted data is sent to the server as an HTTP POST request.

[0479] Step 2:

[0480] The terminal sends the question entered by the user to the server. The input is question data in text format. The output is an HTTP request sent to the server. Specifically, the terminal parses the input data into JSON format, constructs the HTTP request, and sends it to the server's API endpoint.

[0481] Step 3:

[0482] The server logs questions received from user terminals. The input is the question data received as an HTTP request. The output is the question entry recorded in the log database. Specifically, the server extracts the question content from the request and adds a new entry to the "questions_logs" table in the database. For example, it will be recorded in the format "id=1, question='Please tell me the date and time of the orientation.', timestamp='2023-11-01 09:00:00'".

[0483] Step 4:

[0484] The server sends the logged questions to a generative artificial intelligence model. The input is question data stored in a database. The output is an API request to the generative artificial intelligence model. Specifically, the server retrieves the question data, constructs the API request, and sends it to the generative artificial intelligence model.

[0485] Step 5:

[0486] A generative artificial intelligence model receives question data and generates an appropriate answer. The input is the question data received as an API request. The output is the generated answer data. Specifically, the generative AI model uses natural language processing techniques to analyze the content of the question and generate the optimal answer. For example, it might generate the answer, "The orientation will start at 10:00 on November 1, 2023."

[0487] Step 6:

[0488] A generative artificial intelligence system sends the generated answer back to the server. The input is the generated answer data. The output is the API response sent to the server. Specifically, the generative AI model packages the answer data as an API response and sends it to the server.

[0489] Step 7:

[0490] The server sends the generated response to the user's terminal. The input is the response data received from the generative artificial intelligence model. The output is the HTTP response sent to the user's terminal. Specifically, the server converts the response data into JSON format and sends it to the user's terminal as an HTTP response.

[0491] Step 8:

[0492] The terminal displays the response received from the server. The input is the response data received as an HTTP response. The output is the response text displayed on the user interface. Specifically, the terminal parses the received response data and displays on the screen, "The orientation will begin at 10:00 on November 1, 2023."

[0493] (Application Example 1)

[0494] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0495] In physical stores, responding quickly and accurately to customer inquiries is essential for improving customer satisfaction. However, with traditional methods, store staff are not always available, and not all inquiries can be answered immediately. As a result, customers may become dissatisfied. Furthermore, it involves high labor costs and requires staff training, placing a significant burden on operations. To solve these problems, there is a need for a system that automatically answers customer questions in physical stores.

[0496] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0497] In this invention, the server includes a user terminal for inputting questions, means for logging the questions received from the user terminal, means for transmitting the questions recorded in the log to a generative artificial intelligence system for generating answers, means for returning the generated answers to the user terminal, and means for performing question answering in a physical store, which has a display device for displaying the answers. This makes it possible to respond to customer inquiries immediately in a physical store, reduce the burden on store staff, and improve customer satisfaction.

[0498] A "user terminal for entering questions" is a device used by customers to enter questions in text or voice.

[0499] A "log" is a database or file used to record questions sent from a user's terminal.

[0500] A "server" is a computer system that records questions received from user terminals as logs and sends them to a generative artificial intelligence system to generate answers.

[0501] A "generative artificial intelligence system" is an artificial intelligence system that uses natural language processing technology to generate appropriate answers to input questions.

[0502] "Means for generating answers" refers to means that include the process of creating the optimal answer to an input question using a generative artificial intelligence system.

[0503] "Means of returning to the user terminal" refers to means of sending the generated response to the user terminal so that the customer can receive it.

[0504] A "display device" is a device that visually displays the generated responses in a physical store.

[0505] "Means of answering questions in physical stores" refers to a series of system components for automatically answering customer questions in a physical store.

[0506] The embodiments for carrying out the present invention are described below. This system is for automatically providing answers to customer questions in a physical store and includes a user terminal for inputting questions, a server for receiving questions and recording them in a log, a generative artificial intelligence system, and means for returning the generated answers to the user terminal.

[0507] System Configuration

[0508] First, the user terminal is a device that customers use to input questions. Specifically, this includes smartphones, smart glasses, or interface devices installed in stores. This allows customers to ask questions using voice input or text input.

[0509] Next, the server receives and logs the questions sent from the user terminal. The server is built using, for example, Flask (a Python-based web framework). A database such as MySQL or PostgreSQL is used to record the questions. The logged questions are sent to a generative artificial intelligence system.

[0510] Generative artificial intelligence systems use natural language processing techniques to generate answers to questions. These systems employ advanced natural language processing models, such as GPT-4 (API example: OpenAI). This allows them to analyze the content of a question and automatically generate the optimal answer.

[0511] The generated response is returned to the user's terminal by the server and then communicated to the customer via a display or audio output device built into the terminal. This series of processes allows customers to receive quick and appropriate service in physical stores.

[0512] Specific example

[0513] For example, consider a scenario where a customer enters the question, "Where is the product located?" via their smartphone. The user's device sends this question to the server. The server logs the question and sends it to a generative artificial intelligence system. The AI ​​generates an answer, such as "The product is on the second floor, on the left," and returns it to the server. The server then sends the answer to the user's smartphone, which displays the answer on its screen. In this way, the customer can quickly obtain the information they need.

[0514] Example of a prompt

[0515] Examples of prompt statements are shown below.

[0516] Question: Where can I find the product?

[0517] Answer: The item is located on the left side of the second floor.

[0518] This system allows for immediate responses to customer inquiries in physical stores, thereby improving the efficiency of store operations. This can lead to increased customer satisfaction and reduced workload for store staff.

[0519] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0520] Step 1:

[0521] The user terminal receives questions from customers. Customers input questions using their smartphones or smart glasses in voice or text format. The input question data is formatted for transmission to the server. For example, if the input is voice, it is converted to text using speech recognition software. The output is the input data formatted as a question in text format.

[0522] Step 2:

[0523] The server receives questions sent from the user's terminal. The received question data is stored in a database for logging purposes. The input data is the question text sent by the user, and the output is the question log stored in the database. For example, a web server built using Flask receives question data and stores it in a MySQL or PostgreSQL database.

[0524] Step 3:

[0525] The server sends the logged questions to the generative artificial intelligence system. In doing so, it converts the question data into an appropriate format for an API request. The input data is the question log read from the database, and the output is an API request to the generative artificial intelligence system. For example, when using OpenAI's GPT-4 API, the question text is sent as a prompt.

[0526] Step 4:

[0527] The generative artificial intelligence system analyzes the received question and generates an answer. Using a natural language processing model, it understands the meaning of the question and generates the most appropriate response. The input data for this step is the question sent from the server, and the output data is the generated answer.

[0528] Step 5:

[0529] The server returns the response received from the generative artificial intelligence system to the user terminal. It formats the received response data into an appropriate format for transmission to the user terminal. The input data is the response text sent from the generative artificial intelligence system, and the output data is the formatted response data sent to the user terminal.

[0530] Step 6:

[0531] The user terminal receives the response sent from the server and displays it to the customer. It also outputs the response as needed. The input data for this step is the response text returned from the server, and the output data is the response information displayed on the user terminal. Specifically, the response text is displayed on the smartphone screen, or the response is played back as audio using speech synthesis software.

[0532] The above outlines the specific processing steps involved in implementing the present invention. This makes it possible to provide quick and appropriate answers to customer inquiries in physical stores.

[0533] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0534] A specific embodiment of the present invention will now be described.

[0535] The present invention provides a question-and-answer system that further combines a user terminal for inputting questions, a server for logging questions, means for transmitting the logged questions to a generative artificial intelligence system for generating answers, and means for returning the generated answers to the user terminal with an emotion engine that recognizes the user's emotions.

[0536] System Configuration

[0537] 1. User terminal

[0538] A user terminal is a device used by the user to input questions and send emotional information recognized by the emotion engine to the server. Examples include personal computers, smartphones, and tablets. Users use these terminals to input orientation-related questions in text format and to acquire emotional data through the camera, microphone, etc.

[0539] 2. Emotional Engine

[0540] The emotion engine is a system that analyzes audio and image data acquired from the user's device to identify the user's emotions. The emotion engine identifies emotions such as joy, anger, sadness, and happiness by analyzing the user's voice tone and facial expressions.

[0541] 3. Server

[0542] The server receives and logs questions and sentiment data sent from the user terminal. The server has a database for storing questions and associated sentiment information. The server also transmits the questions and sentiment data to a generative artificial intelligence system and returns the AI-generated answers to the user terminal.

[0543] 4. Generative Artificial Intelligence Systems

[0544] The generative artificial intelligence system receives question and sentiment data sent from a server and generates appropriate answers. Specifically, it uses natural language processing models and sentiment-responding algorithms to analyze the content of the question and generate responses that reflect the sentiment.

[0545] Program Processing Description

[0546] 1. Question input and sentiment recognition

[0547] Users input questions about the orientation into their devices and provide emotional data through the device's camera and microphone. For example, they might ask, "Please tell me the date and time of the orientation," along with sending an anxious facial expression and tone of voice to the device.

[0548] 2. Sending questions and sentiment data

[0549] The user terminal analyzes the user's input and acquired sentiment data, and sends that information to the server. The questions and sentiment data are packaged in an appropriate format.

[0550] 3. Receiving and logging questions and sentiment data.

[0551] The server receives questions and sentiment data sent from the user's terminal and records them in the database. This ensures that the questions and the corresponding sentiments are saved as logs.

[0552] 4. AI-powered response generation

[0553] The server sends the question and sentiment data to a generative artificial intelligence system. The generative AI system uses a natural language processing model and sentiment-responding algorithms to generate an answer that is appropriate to the content of the question and the user's sentiment. For example, it might generate an answer such as, "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry; detailed instructions will be distributed later."

[0554] 5. Return and display of responses

[0555] The server sends the response received from the generative artificial intelligence system back to the user terminal. The user terminal receives this response and displays it on the screen. This allows the user to immediately see the answer to their question and emotionally sensitive commentary.

[0556] Specific example

[0557] For example, if a user is worried about orientation, the following process takes place: The user types, "Please tell me the date and time of the orientation," and the device picks up on the user's anxious facial expression and tone of voice. The device sends this information to the server, which logs the question and emotion data. The server sends this data to a generative artificial intelligence system, which generates the response, "The orientation will start at 10:00 on November 1, 2023. There is no need to worry; detailed instructions will be distributed later." The server sends this response back to the user's device, which then displays it.

[0558] The above describes specific embodiments for carrying out the present invention. The present invention allows users to not only obtain quick and accurate answers to their questions, but also receive responses that take their emotions into consideration, enabling efficient question-and-answer sessions during orientation.

[0559] The following describes the processing flow.

[0560] Step 1:

[0561] Users input questions into their devices and provide emotional data through audio and video.

[0562] For example, a user might type, "Please tell me the date and time of the orientation," and convey an anxious expression or a tense tone of voice to the device.

[0563] Step 2:

[0564] The user terminal receives and analyzes the user's input text and emotional data (facial expressions and vocal characteristics).

[0565] The emotion engine analyzes the user's facial expressions and tone of voice to recognize when the user is feeling anxious.

[0566] Step 3:

[0567] The user's terminal analyzes the questions and sentiment data and sends it to the server.

[0568] Here, the emotional state (e.g., anxiety) is packaged along with the question content and sent to the server via the network.

[0569] Step 4:

[0570] The server receives the question and sentiment data sent from the user's terminal.

[0571] The received data is analyzed to extract questions and sentiment information.

[0572] Step 5:

[0573] The server logs the questions and sentiment data it receives.

[0574] By saving the question content and emotional state in a database, they can be referenced later.

[0575] Step 6:

[0576] The server sends the question and emotion data to the generative artificial intelligence system.

[0577] The API of a generative artificial intelligence system is called, and questions and sentiment data are sent.

[0578] Step 7:

[0579] A generative artificial intelligence system receives questions and sentiment data sent from a server and generates answers.

[0580] Using natural language processing models and emotion-response algorithms, we create responses that take the user's emotions into consideration.

[0581] Step 8:

[0582] The generative artificial intelligence system sends the generated response back to the server.

[0583] The generated response data is sent to the server.

[0584] Step 9:

[0585] The server returns the response received from the generative artificial intelligence system to the user's terminal.

[0586] The response data is packaged and sent to the user's terminal via the network.

[0587] Step 10:

[0588] The user terminal displays the response received from the server to the user.

[0589] The user's terminal displays the received response on the screen for the user to confirm. For example, a response such as "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later." might be displayed.

[0590] The above outlines the specific steps for question processing using the user terminal, server, generative artificial intelligence system, and emotion engine.

[0591] (Example 2)

[0592] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0593] Traditional question-and-answer systems can provide appropriate answers to user-submitted questions, but they lacked responses that took user emotions into account. Therefore, they were unable to respond flexibly to changes in user emotions, making it difficult to improve the user experience. Especially in situations involving tension and anxiety, such as orientation sessions, responses that consider emotions are essential.

[0594] The identification processing performed 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 an information processing device for recording questions, means for acquiring emotion data along with the questions, means for analyzing the acquired emotion data, means for transmitting the questions recorded in the log to a generative artificial intelligence system to generate answers, and means for returning the generated answers to an information terminal. This makes it possible to quickly provide appropriate answers that take into account the user's emotions in response to questions entered by the user.

[0595] A "question" is text data entered by the user, which requests information from the system.

[0596] An "information terminal" is a device used by a user to input questions, and includes personal computers, smartphones, tablets, and other similar devices.

[0597] An "information processing device" is a device that receives and records questions transmitted from an information terminal, and includes servers, among other things.

[0598] "Emotional data" refers to data related to emotions obtained from the user's facial expressions, voice, etc., and indicates states such as anxiety or joy.

[0599] "Means of acquiring emotions" refers to methods of acquiring a user's emotions using devices such as cameras and microphones.

[0600] "Means for analyzing emotions" refers to methods for analyzing and identifying a user's emotions based on acquired emotional data, and an emotion engine falls under this category.

[0601] A "generative artificial intelligence system" is a system that uses a natural language processing model to generate appropriate answers based on input question data and sentiment data.

[0602] "Methods for generating answers" refers to a method of sending questions and sentiment data to a generative artificial intelligence system and having it generate answers.

[0603] "Method of returning to the information terminal" refers to a method of returning the response generated by the generative artificial intelligence system to the information terminal and displaying it to the user.

[0604] "Means of recording" refers to a method of storing received questions and sentiment data in a database for later analysis and reference.

[0605] This invention provides a question-and-answer system in which a user inputs a question and the system recognizes the emotions associated with that question. This system consists of an information terminal, an information processing device (server), an emotion analysis engine, and a generative artificial intelligence system.

[0606] System Configuration

[0607] 1. Information terminal

[0608] Information terminals are devices that allow users to input questions and provide sentiment data. Specifically, this includes personal computers, smartphones, and tablets. Users can use these devices to input questions in text format and have sentiment data acquired through the camera and microphone.

[0609] 2. Emotion Analysis Engine

[0610] An emotion analysis engine is a system that analyzes audio and image data acquired from an information terminal to identify the user's emotions. By analyzing the user's voice tone and facial expressions, the emotion analysis engine identifies emotions such as joy, anger, sadness, and happiness, and transmits this data as emotion information to an information processing device.

[0611] 3. Information processing equipment (server)

[0612] The information processing device (server) receives and records question and sentiment data transmitted from information terminals. It has the function of storing question and sentiment data in a database and accumulates the data as logs for post-processing. The server also plays the role of transmitting this data to a generative artificial intelligence system and returning the generated answers to the information terminals.

[0613] 4. Generative Artificial Intelligence Systems

[0614] Generative artificial intelligence systems are systems that generate appropriate answers using question and sentiment data received from a server. Specifically, they use natural language processing models and sentiment response algorithms to generate appropriate responses that match the content of the question and the user's emotions.

[0615] Specific example

[0616] For example, if a user is feeling anxious about orientation, the following actions are performed: The user texts "Please tell me the date and time of the orientation" on their information terminal, and their anxious facial expression and tone of voice are captured by the camera and microphone on the terminal. The information terminal sends this to a server, which logs the question and emotion data. Next, the server sends this data to a generative artificial intelligence system, which generates a response such as "The orientation will start at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later." The server sends this response back to the information terminal, which displays it. This example demonstrates how users can quickly obtain answers to their questions and receive polite responses that also address their emotions.

[0617] Example of a prompt

[0618] Here are some examples of specific prompt statements:

[0619] User question: "What is the date and time of the orientation?"

[0620] User's emotion: "Anxiety"

[0621] Using this prompt, the generative AI model generates an appropriate answer based on the user's question and sentiment.

[0622] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0623] Step 1:

[0624] Question input and sentiment recognition

[0625] Specific actions:

[0626] Users input questions about the orientation in text format into an information terminal. At the same time, they provide voice and facial expressions using the terminal's camera and microphone. For example, a user might input "Please tell me the date and time of the orientation," and then display an anxious expression and a trembling voice.

[0627] input:

[0628] Text-based questions such as "Please tell me the date and time of the orientation," and audio and image data from the camera and microphone.

[0629] Data processing:

[0630] The information terminal collects image data from the camera and audio data from the microphone.

[0631] output:

[0632] Collected text questions and sentiment data.

[0633] Step 2:

[0634] Sending questions and sentiment data

[0635] Specific actions:

[0636] The information terminal analyzes the acquired questions and sentiment data, formats them, and sends them to the information processing device (server).

[0637] input:

[0638] Text-based questions and sentiment data.

[0639] Data processing:

[0640] Integrate question text data and sentiment data into a single message and package it in an appropriate format.

[0641] output:

[0642] Formatted questionnaire data and sentiment data.

[0643] Step 3:

[0644] Receiving and logging of questions and sentiment data.

[0645] Specific actions:

[0646] The server receives question and sentiment data sent from information terminals and records it in a database. This saves the question and sentiment information as a log, which can then be referenced later.

[0647] input:

[0648] Formatted questionnaire data and sentiment data.

[0649] Data processing:

[0650] The received data is recorded in the database.

[0651] output:

[0652] Question and sentiment data stored in the database.

[0653] Step 4:

[0654] AI-generated answers

[0655] Specific actions:

[0656] The server sends question and sentiment data stored in the database to a generative artificial intelligence system to generate appropriate answers. The generative AI system uses a generative AI model to create answers based on the question content and sentiment.

[0657] input:

[0658] Question and sentiment data stored in the database.

[0659] Data processing:

[0660] Using a generative artificial intelligence system's natural language processing model and sentiment-responding algorithm, we generate questions and sentiment-sensitive answers.

[0661] output:

[0662] The generated answer.

[0663] Step 5:

[0664] Return and display of responses

[0665] Specific actions:

[0666] The server sends the response received from the generative artificial intelligence system back to the information terminal. The information terminal receives this response and displays it to the user. For example, it might display: "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later."

[0667] input:

[0668] The generated answer.

[0669] Data processing:

[0670] Send the response data to the user's terminal.

[0671] output:

[0672] The answer displayed on the information terminal.

[0673] (Application Example 2)

[0674] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0675] Conventional question-and-answer systems only generate appropriate answers to user-entered questions, failing to provide responses that take into account the user's emotional state. Therefore, particularly in security services, when users are experiencing anxiety or stress, the lack of empathetic responses can lead to decreased user satisfaction. Solving this problem is essential.

[0676] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a user terminal for inputting questions, means for logging the questions received from the user terminal, means for transmitting the questions recorded in the log to a generative artificial intelligence system to generate answers, means for returning the generated answers to the user terminal, an emotion engine for recognizing the user's emotions, means for adjusting the answers generated based on the emotions recognized by the emotion engine, and means for displaying the generated answers. This makes it possible to provide appropriate answers while taking into account the user's emotional state.

[0677] A "user terminal" is a device used by users to input questions, acquire emotional data through an emotional engine, and send it to a server.

[0678] A "server" is a computer whose role is to receive and log questions and sentiment data sent from user terminals, send that data to a generative artificial intelligence system to generate answers, and then return those answers to the user terminals.

[0679] A "generative artificial intelligence system" is a system that uses a natural language processing model to generate appropriate answers based on questions and sentiment data sent from a server.

[0680] An "emotion engine" is a system that analyzes audio and image data acquired from a user's device to identify the user's emotions.

[0681] "Response adjustment" is the process of appropriately modifying responses generated by a generative artificial intelligence system, based on emotional information recognized by the emotion engine, to take the user's emotions into consideration.

[0682] "Inputting a question" refers to the act of a user entering information they want to know into their device in the form of text or voice.

[0683] A "display means" is an interface for visually presenting the response generated on the user's terminal to the user.

[0684] The present invention will now be described in detail. To implement the invention, four main elements are required: a user terminal, an emotion engine, a server, and a generative artificial intelligence system. These elements work together to create a system that provides appropriate answers to user questions and emotions.

[0685] User terminal

[0686] The user terminal is a device used by the user to input questions and acquire emotional data. Specifically, smartphones, tablets, and personal computers are used. The user uses these devices to input questions in text or voice format, and emotional data such as facial expressions and voice tone is acquired through the camera and microphone.

[0687] Emotional Engine

[0688] An emotion engine is software that analyzes image and audio data transmitted from a user's device to identify the user's emotions. For example, image data analysis can be performed using OpenCV and Keras for face detection and emotion recognition. Audio data analysis can be performed using an audio processing library to analyze the tone of voice.

[0689] server

[0690] The server receives questions and sentiment data sent from user terminals and logs them in a database. The server also transmits questions and sentiment data to a generative artificial intelligence system, receives the generated answers, and sends them back to the user terminal. The server also incorporates a database management system (DBMS) for log management and data storage.

[0691] Generative artificial intelligence systems

[0692] The generative artificial intelligence system generates appropriate answers using a natural language processing model based on questions and sentiment data sent from the server. Specifically, it uses OpenAI's GPT-2 and modules for natural language processing. This results in the generation of answers that take sentiment into consideration.

[0693] Specific example

[0694] For example, if a user asks with an anxious expression, "What measures should I take to protect my home?", the emotion engine analyzes the expression and identifies the emotion as "anxiety." The server sends this emotion information and the question to a generative artificial intelligence system, which then generates an answer such as, "As a measure to protect your home, first install an outdoor light to deter intruders. Also, installing security cameras will give you peace of mind."

[0695] Example of a prompt

[0696] The prompt will look like this:

[0697] The user is feeling anxious and asks: What measures should I take to protect my home from crime?

[0698] By inputting this prompt into a generative artificial intelligence system, an appropriate response that corresponds to the user's emotions can be obtained.

[0699] This invention realizes an emotion-responsive question-and-answer system, which is expected to have the effect of reducing user anxiety and stress, particularly in the field of security services.

[0700] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0701] Step 1:

[0702] The user enters a question, and sentiment data is collected on the user's device.

[0703] Input: The user enters the question, "What measures should I take to improve home security?" into the user's device. Emotional data is acquired through the camera and microphone to recognize anxious facial expressions and tone of voice.

[0704] Data processing: The device generates question data in text format, analyzes image and audio data acquired by the camera and microphone, and identifies emotions from facial expressions and tone of voice.

[0705] Output: Questionnaire data in text format and emotion data for "anxiety" recognized by the emotion engine.

[0706] Step 2:

[0707] The user's terminal sends the question and sentiment data to the server.

[0708] Input: Question data and sentiment data generated in Step 1.

[0709] Data processing: The user terminal packages the question data and sentiment data and sends it to the server in the appropriate format.

[0710] Output: Question data and sentiment data sent to the server.

[0711] Step 3:

[0712] The server receives the question and sentiment data and records it in the database.

[0713] Input: Question data and sentiment data sent from the user's terminal.

[0714] Data processing: The server records the received data in a database and saves it as a log.

[0715] Output: Question data and sentiment data stored in the database.

[0716] Step 4:

[0717] The server sends the question and sentiment data to the generative artificial intelligence system.

[0718] Input: Question data and sentiment data recorded in the database.

[0719] Data processing: The server sends question data and sentiment data to the generative artificial intelligence system in an appropriate format.

[0720] Output: Question data and sentiment data sent to a generative artificial intelligence system.

[0721] Step 5:

[0722] The generative artificial intelligence system generates answers that are tailored to the question and the emotions it evokes.

[0723] Input: Question data and sentiment data sent from the server.

[0724] Data Processing: Generative artificial intelligence systems use natural language processing models and sentiment-responding algorithms to generate answers that correspond to the content and emotions of a question. For example, using the GPT-2 model, the prompt "User is feeling anxious and asks: What measures should I take to protect my home?" is processed as input.

[0725] Output: A response that takes emotions into consideration, generated by a generative artificial intelligence system (Example: "As a security measure for my home, I will first install an outdoor light to deter intruders. I will also gain peace of mind by installing a security camera.")

[0726] Step 6:

[0727] The server sends the generated response back to the user's terminal.

[0728] Input: Answer generated by a generative artificial intelligence system.

[0729] Data processing: The server sends the generated response to the user's terminal in the appropriate format.

[0730] Output: Generated response sent to the user's terminal.

[0731] Step 7:

[0732] The user terminal displays the generated response.

[0733] Input: Generated response sent from the server.

[0734] Data processing: The user terminal generates the response and displays it on the screen.

[0735] Output: Generated response that the user can view on the screen.

[0736] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0737] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0738] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0739] [Third Embodiment]

[0740] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0741] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0742] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0743] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0744] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0745] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0746] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0747] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0748] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0749] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0750] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0751] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0752] A specific embodiment of the present invention will now be described.

[0753] This invention provides a question-and-answer system comprising a user terminal, a server, and a generative artificial intelligence system. The user inputs a question from the terminal, the question is sent to the generative artificial intelligence system via the server, and the answer generated by the AI ​​is returned to the user terminal.

[0754] System Configuration

[0755] 1. User terminal

[0756] A user terminal is a device used by the user to input questions. Examples include personal computers, smartphones, and tablets. Users use these devices to input orientation-related questions in text format.

[0757] 2. Server

[0758] The server receives questions sent from user terminals and records them in a log. The server has a database for storing question logs, and records received questions sequentially. The server also sends questions to a generative artificial intelligence system and returns the AI-generated answers to the user terminal.

[0759] 3. Generative Artificial Intelligence Systems

[0760] Generative artificial intelligence systems receive questions sent from a server and generate appropriate answers. Specifically, they use natural language processing models to analyze the meaning of the questions and create the optimal response.

[0761] Program Processing Description

[0762] 1. Enter and submit your question.

[0763] The user enters a question about the orientation into their terminal. For example, they might enter, "What is the date and time of the orientation?" The user then sends this question to the server.

[0764] 2. Receiving and logging questions

[0765] The server receives questions from the user's terminal. Received questions are recorded in the server's question log. This allows users to refer to the question content later.

[0766] 3. AI-powered response generation

[0767] The server sends the logged question to a generative artificial intelligence system. The generative AI system uses a natural language processing model to analyze the question and generate an appropriate answer. For example, it might generate the answer, "The orientation will begin at 10:00 on November 1, 2023."

[0768] 4. Return and display of responses

[0769] The server sends the response received from the generative artificial intelligence system back to the user terminal. The user terminal receives this response and displays it on the screen. This allows the user to immediately check the answer to their question.

[0770] Specific example

[0771] For example, if a user asks about the date and time of an orientation, the following process takes place: The user types "Please tell me the date and time of the orientation" and sends it from their terminal to the server. The server logs this question and sends it to a generative artificial intelligence system. The AI ​​generates the answer "The orientation will start on November 1, 2023 at 10:00" and sends it back to the server. The server sends this answer back to the user's terminal, and the user's terminal displays the answer.

[0772] The above describes specific embodiments for carrying out the present invention. The present invention allows users to obtain quick and accurate answers to their questions, thus enabling efficient question-and-answer sessions during orientation.

[0773] The following describes the processing flow.

[0774] Step 1:

[0775] The user enters a question into their terminal.

[0776] For example, a user might type, "Please tell me the date and time of the orientation."

[0777] Step 2:

[0778] The user terminal receives user input and sends that question to the server.

[0779] This process involves the user terminal sending question data to the server via the network.

[0780] Step 3:

[0781] The server receives the question sent from the user's terminal.

[0782] The server analyzes the received data and extracts the question content.

[0783] Step 4:

[0784] The server logs the questions it receives.

[0785] The server accesses the database and saves the question as a new entry.

[0786] Step 5:

[0787] The server sends the question to the generative artificial intelligence system.

[0788] The server calls the API of the generative artificial intelligence system and sends a question.

[0789] Step 6:

[0790] A generative artificial intelligence system generates answers to questions sent from a server.

[0791] The AI ​​system uses a natural language processing model to generate appropriate answers.

[0792] Step 7:

[0793] The generative artificial intelligence system sends the generated response back to the server.

[0794] The AI ​​system sends the response data to the server.

[0795] Step 8:

[0796] The server receives the generated response and sends it back to the user's terminal.

[0797] The server packages the response data and sends it to the user's terminal via the network.

[0798] Step 9:

[0799] The user terminal displays the response received from the server to the user.

[0800] The user's terminal displays the received response on the screen so that the user can confirm it.

[0801] The above outlines the specific steps involved in question processing using a user terminal, server, and generative artificial intelligence system.

[0802] (Example 1)

[0803] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0804] In today's information society, users are required to obtain information quickly and accurately. However, conventional information retrieval systems often take a long time to provide appropriate answers to questions, which impairs user convenience. Furthermore, insufficient logging of questions and management of generated answers make it difficult to refer to and analyze question history.

[0805] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0806] In this invention, the server includes means for logging questions received from a terminal, means for sending the logged questions to a generative artificial intelligence model to generate answers, means for returning the generated answers to the terminal, and means for displaying the generated answers. This enables users to quickly obtain appropriate answers and facilitates the management and analysis of question history.

[0807] A "terminal" is a device used by a user to input questions, and includes personal computers, smartphones, tablets, and other similar devices.

[0808] A "computer" is a server that has the function of logging questions received from terminals and sending those questions to a generative artificial intelligence model.

[0809] A "generative artificial intelligence model" is an artificial intelligence system that uses natural language processing technology to analyze input questions and generate appropriate answers.

[0810] A "log" refers to a database or file used to record questions received from a terminal.

[0811] A "question" refers to information or data entered by the user through their device. A generative artificial intelligence model performs analysis based on this question.

[0812] "Answer" refers to the information and data generated by a generative artificial intelligence model after analyzing a question, and its purpose is to provide information to the user.

[0813] "Formatting" refers to arranging data into a specific format or converting it into an appropriate structure for communication purposes.

[0814] An "HTTP request" is a type of communication protocol used by a terminal to send a question to a computer.

[0815] The present invention is a question-and-answer system for providing quick and appropriate answers to user questions. This system includes a terminal, a server, and a generative artificial intelligence model.

[0816] System Configuration

[0817] 1. Terminal

[0818] A terminal is a device used by the user to input questions, and specific examples include personal computers, smartphones, and tablets. Users use these terminals to input orientation-related questions in text format.

[0819] 2. Server

[0820] The server is responsible for receiving questions sent from user terminals and logging them. The server has a database for storing question logs, and it records received questions sequentially. The server also sends questions to a generative artificial intelligence model and returns the AI-generated answers to the user terminal.

[0821] 3. Generative artificial intelligence models

[0822] Generative artificial intelligence models receive questions sent from a server and generate optimal answers using natural language processing techniques. Specifically, they use a natural language processing model (e.g., GPT-4) to analyze the meaning of the question and create the best possible answer.

[0823] Operation details

[0824] 1. Enter and submit your question.

[0825] The user enters a question about the orientation into the terminal. For example, a question such as "What is the date and time of the orientation?" is entered. The terminal then sends this question to the server. Typically, it is sent as an HTTP POST request.

[0826] 2. Receiving and logging questions

[0827] The server receives a question from the user's terminal and saves it as a new entry in the "questions_logs" table in the database. For example, it might record "id=1, question='Please tell me the date and time of the orientation.', timestamp='2023-11-01 09:00:00'". Once logging is complete, the server sends the question data to a generative artificial intelligence model.

[0828] 3. AI-powered response generation

[0829] The server sends the recorded question data as an API request to a generative artificial intelligence model. The generative AI model receives the question data, uses a natural language processing model to analyze the content of the question, and generates an appropriate answer. For example, it might generate the answer, "The orientation will begin at 10:00 on November 1, 2023."

[0830] 4. Return and display of responses

[0831] The server sends the response received from the generative artificial intelligence model back to the user terminal, which then receives and displays the response on its screen. This allows the user to immediately see the answer to their question.

[0832] Specific example

[0833] For example, if a user asks about the date and time of the orientation, they might enter a prompt like this: "Please tell me the date and time of the orientation." The terminal sends this question to the server, which logs the question and then sends it to a generative artificial intelligence model. The AI ​​analyzes the question and generates the answer, "The orientation will start on November 1, 2023 at 10:00," and sends it back to the server. The server then sends this answer to the user's terminal, which displays the answer.

[0834] Thus, the present invention provides an effective means for providing quick and accurate answers to user questions, and can significantly improve the efficiency of question and answer sessions.

[0835] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0836] Step 1:

[0837] The user enters a question using a terminal. For example, the user enters "Please tell me the date and time of the orientation." The input is a text-based question. The output is the formatted data of this question. This formatted data is sent to the server as an HTTP POST request.

[0838] Step 2:

[0839] The terminal sends the question entered by the user to the server. The input is question data in text format. The output is an HTTP request sent to the server. Specifically, the terminal parses the input data into JSON format, constructs the HTTP request, and sends it to the server's API endpoint.

[0840] Step 3:

[0841] The server logs questions received from user terminals. The input is the question data received as an HTTP request. The output is the question entry recorded in the log database. Specifically, the server extracts the question content from the request and adds a new entry to the "questions_logs" table in the database. For example, it will be recorded in the format "id=1, question='Please tell me the date and time of the orientation.', timestamp='2023-11-01 09:00:00'".

[0842] Step 4:

[0843] The server sends the logged questions to a generative artificial intelligence model. The input is question data stored in a database. The output is an API request to the generative artificial intelligence model. Specifically, the server retrieves the question data, constructs the API request, and sends it to the generative artificial intelligence model.

[0844] Step 5:

[0845] A generative artificial intelligence model receives question data and generates an appropriate answer. The input is the question data received as an API request. The output is the generated answer data. Specifically, the generative AI model uses natural language processing techniques to analyze the content of the question and generate the optimal answer. For example, it might generate the answer, "The orientation will start at 10:00 on November 1, 2023."

[0846] Step 6:

[0847] A generative artificial intelligence system sends the generated answer back to the server. The input is the generated answer data. The output is the API response sent to the server. Specifically, the generative AI model packages the answer data as an API response and sends it to the server.

[0848] Step 7:

[0849] The server sends the generated response to the user's terminal. The input is the response data received from the generative artificial intelligence model. The output is the HTTP response sent to the user's terminal. Specifically, the server converts the response data into JSON format and sends it to the user's terminal as an HTTP response.

[0850] Step 8:

[0851] The terminal displays the response received from the server. The input is the response data received as an HTTP response. The output is the response text displayed on the user interface. Specifically, the terminal parses the received response data and displays on the screen, "The orientation will begin at 10:00 on November 1, 2023."

[0852] (Application Example 1)

[0853] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0854] In physical stores, responding quickly and accurately to customer inquiries is essential for improving customer satisfaction. However, with traditional methods, store staff are not always available, and not all inquiries can be answered immediately. As a result, customers may become dissatisfied. Furthermore, it involves high labor costs and requires staff training, placing a significant burden on operations. To solve these problems, there is a need for a system that automatically answers customer questions in physical stores.

[0855] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0856] In this invention, the server includes a user terminal for inputting questions, means for logging the questions received from the user terminal, means for transmitting the questions recorded in the log to a generative artificial intelligence system for generating answers, means for returning the generated answers to the user terminal, and means for performing question answering in a physical store, which has a display device for displaying the answers. This makes it possible to respond to customer inquiries immediately in a physical store, reduce the burden on store staff, and improve customer satisfaction.

[0857] A "user terminal for entering questions" is a device used by customers to enter questions in text or voice.

[0858] A "log" is a database or file used to record questions sent from a user's terminal.

[0859] A "server" is a computer system that records questions received from user terminals as logs and sends them to a generative artificial intelligence system to generate answers.

[0860] A "generative artificial intelligence system" is an artificial intelligence system that uses natural language processing technology to generate appropriate answers to input questions.

[0861] "Means for generating answers" refers to means that include the process of creating the optimal answer to an input question using a generative artificial intelligence system.

[0862] "Means of returning to the user terminal" refers to means of sending the generated response to the user terminal so that the customer can receive it.

[0863] A "display device" is a device that visually displays the generated responses in a physical store.

[0864] "Means of answering questions in physical stores" refers to a series of system components for automatically answering customer questions in a physical store.

[0865] The embodiments for carrying out the present invention are described below. This system is for automatically providing answers to customer questions in a physical store and includes a user terminal for inputting questions, a server for receiving questions and recording them in a log, a generative artificial intelligence system, and means for returning the generated answers to the user terminal.

[0866] System Configuration

[0867] First, the user terminal is a device that customers use to input questions. Specifically, this includes smartphones, smart glasses, or interface devices installed in stores. This allows customers to ask questions using voice input or text input.

[0868] Next, the server receives and logs the questions sent from the user terminal. The server is built using, for example, Flask (a Python-based web framework). A database such as MySQL or PostgreSQL is used to record the questions. The logged questions are sent to a generative artificial intelligence system.

[0869] Generative artificial intelligence systems use natural language processing techniques to generate answers to questions. These systems employ advanced natural language processing models, such as GPT-4 (API example: OpenAI). This allows them to analyze the content of a question and automatically generate the optimal answer.

[0870] The generated response is returned to the user's terminal by the server and then communicated to the customer via a display or audio output device built into the terminal. This series of processes allows customers to receive quick and appropriate service in physical stores.

[0871] Specific example

[0872] For example, consider a scenario where a customer enters the question, "Where is the product located?" via their smartphone. The user's device sends this question to the server. The server logs the question and sends it to a generative artificial intelligence system. The AI ​​generates an answer, such as "The product is on the second floor, on the left," and returns it to the server. The server then sends the answer to the user's smartphone, which displays the answer on its screen. In this way, the customer can quickly obtain the information they need.

[0873] Example of a prompt

[0874] Examples of prompt statements are shown below.

[0875] Question: Where can I find the product?

[0876] Answer: The item is located on the left side of the second floor.

[0877] This system allows for immediate responses to customer inquiries in physical stores, thereby improving the efficiency of store operations. This can lead to increased customer satisfaction and reduced workload for store staff.

[0878] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0879] Step 1:

[0880] The user terminal receives questions from customers. Customers input questions using their smartphones or smart glasses in voice or text format. The input question data is formatted for transmission to the server. For example, if the input is voice, it is converted to text using speech recognition software. The output is the input data formatted as a question in text format.

[0881] Step 2:

[0882] The server receives questions sent from the user's terminal. The received question data is stored in a database for logging purposes. The input data is the question text sent by the user, and the output is the question log stored in the database. For example, a web server built using Flask receives question data and stores it in a MySQL or PostgreSQL database.

[0883] Step 3:

[0884] The server sends the logged questions to the generative artificial intelligence system. In doing so, it converts the question data into an appropriate format for an API request. The input data is the question log read from the database, and the output is an API request to the generative artificial intelligence system. For example, when using OpenAI's GPT-4 API, the question text is sent as a prompt.

[0885] Step 4:

[0886] The generative artificial intelligence system analyzes the received question and generates an answer. Using a natural language processing model, it understands the meaning of the question and generates the most appropriate response. The input data for this step is the question sent from the server, and the output data is the generated answer.

[0887] Step 5:

[0888] The server returns the response received from the generative artificial intelligence system to the user terminal. It formats the received response data into an appropriate format for transmission to the user terminal. The input data is the response text sent from the generative artificial intelligence system, and the output data is the formatted response data sent to the user terminal.

[0889] Step 6:

[0890] The user terminal receives the response sent from the server and displays it to the customer. It also outputs the response as needed. The input data for this step is the response text returned from the server, and the output data is the response information displayed on the user terminal. Specifically, the response text is displayed on the smartphone screen, or the response is played back as audio using speech synthesis software.

[0891] The above outlines the specific processing steps involved in implementing the present invention. This makes it possible to provide quick and appropriate answers to customer inquiries in physical stores.

[0892] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0893] A specific embodiment of the present invention will now be described.

[0894] The present invention provides a question-and-answer system that further combines a user terminal for inputting questions, a server for logging questions, means for transmitting the logged questions to a generative artificial intelligence system for generating answers, and means for returning the generated answers to the user terminal with an emotion engine that recognizes the user's emotions.

[0895] System Configuration

[0896] 1. User terminal

[0897] A user terminal is a device used by the user to input questions and send emotional information recognized by the emotion engine to the server. Examples include personal computers, smartphones, and tablets. Users use these terminals to input orientation-related questions in text format and to acquire emotional data through the camera, microphone, etc.

[0898] 2. Emotional Engine

[0899] The emotion engine is a system that analyzes audio and image data acquired from the user's device to identify the user's emotions. The emotion engine identifies emotions such as joy, anger, sadness, and happiness by analyzing the user's voice tone and facial expressions.

[0900] 3. Server

[0901] The server receives and logs questions and sentiment data sent from the user terminal. The server has a database for storing questions and associated sentiment information. The server also transmits the questions and sentiment data to a generative artificial intelligence system and returns the AI-generated answers to the user terminal.

[0902] 4. Generative Artificial Intelligence Systems

[0903] The generative artificial intelligence system receives question and sentiment data sent from a server and generates appropriate answers. Specifically, it uses natural language processing models and sentiment-responding algorithms to analyze the content of the question and generate responses that reflect the sentiment.

[0904] Program Processing Description

[0905] 1. Question input and sentiment recognition

[0906] Users input questions about the orientation into their devices and provide emotional data through the device's camera and microphone. For example, they might ask, "Please tell me the date and time of the orientation," along with sending an anxious facial expression and tone of voice to the device.

[0907] 2. Sending questions and sentiment data

[0908] The user terminal analyzes the user's input and acquired sentiment data, and sends that information to the server. The questions and sentiment data are packaged in an appropriate format.

[0909] 3. Receiving and logging questions and sentiment data.

[0910] The server receives questions and sentiment data sent from the user's terminal and records them in the database. This ensures that the questions and the corresponding sentiments are saved as logs.

[0911] 4. AI-powered response generation

[0912] The server sends the question and sentiment data to a generative artificial intelligence system. The generative AI system uses a natural language processing model and sentiment-responding algorithms to generate an answer that is appropriate to the content of the question and the user's sentiment. For example, it might generate an answer such as, "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry; detailed instructions will be distributed later."

[0913] 5. Return and display of responses

[0914] The server sends the response received from the generative artificial intelligence system back to the user terminal. The user terminal receives this response and displays it on the screen. This allows the user to immediately see the answer to their question and emotionally sensitive commentary.

[0915] Specific example

[0916] For example, if a user is worried about orientation, the following process takes place: The user types, "Please tell me the date and time of the orientation," and the device picks up on the user's anxious facial expression and tone of voice. The device sends this information to the server, which logs the question and emotion data. The server sends this data to a generative artificial intelligence system, which generates the response, "The orientation will start at 10:00 on November 1, 2023. There is no need to worry; detailed instructions will be distributed later." The server sends this response back to the user's device, which then displays it.

[0917] The above describes specific embodiments for carrying out the present invention. The present invention allows users to not only obtain quick and accurate answers to their questions, but also receive responses that take their emotions into consideration, enabling efficient question-and-answer sessions during orientation.

[0918] The following describes the processing flow.

[0919] Step 1:

[0920] Users input questions into their devices and provide emotional data through audio and video.

[0921] For example, a user might type, "Please tell me the date and time of the orientation," and convey an anxious expression or a tense tone of voice to the device.

[0922] Step 2:

[0923] The user terminal receives and analyzes the user's input text and emotional data (facial expressions and vocal characteristics).

[0924] The emotion engine analyzes the user's facial expressions and tone of voice to recognize when the user is feeling anxious.

[0925] Step 3:

[0926] The user's terminal analyzes the questions and sentiment data and sends it to the server.

[0927] Here, the emotional state (e.g., anxiety) is packaged along with the question content and sent to the server via the network.

[0928] Step 4:

[0929] The server receives the question and sentiment data sent from the user's terminal.

[0930] The received data is analyzed to extract questions and sentiment information.

[0931] Step 5:

[0932] The server logs the questions and sentiment data it receives.

[0933] By saving the question content and emotional state in a database, they can be referenced later.

[0934] Step 6:

[0935] The server sends the question and emotion data to the generative artificial intelligence system.

[0936] The API of a generative artificial intelligence system is called, and questions and sentiment data are sent.

[0937] Step 7:

[0938] A generative artificial intelligence system receives questions and sentiment data sent from a server and generates answers.

[0939] Using natural language processing models and emotion-response algorithms, we create responses that take the user's emotions into consideration.

[0940] Step 8:

[0941] The generative artificial intelligence system sends the generated response back to the server.

[0942] The generated response data is sent to the server.

[0943] Step 9:

[0944] The server returns the response received from the generative artificial intelligence system to the user's terminal.

[0945] The response data is packaged and sent to the user's terminal via the network.

[0946] Step 10:

[0947] The user terminal displays the response received from the server to the user.

[0948] The user's terminal displays the received response on the screen for the user to confirm. For example, a response such as "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later." might be displayed.

[0949] The above outlines the specific steps for question processing using the user terminal, server, generative artificial intelligence system, and emotion engine.

[0950] (Example 2)

[0951] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0952] Traditional question-and-answer systems can provide appropriate answers to user-submitted questions, but they lacked responses that took user emotions into account. Therefore, they were unable to respond flexibly to changes in user emotions, making it difficult to improve the user experience. Especially in situations involving tension and anxiety, such as orientation sessions, responses that consider emotions are essential.

[0953] The identification processing performed 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 an information processing device for recording questions, means for acquiring emotion data along with the questions, means for analyzing the acquired emotion data, means for transmitting the questions recorded in the log to a generative artificial intelligence system to generate answers, and means for returning the generated answers to an information terminal. This makes it possible to quickly provide appropriate answers that take into account the user's emotions in response to questions entered by the user.

[0954] A "question" is text data entered by the user, which requests information from the system.

[0955] An "information terminal" is a device used by a user to input questions, and includes personal computers, smartphones, tablets, and other similar devices.

[0956] An "information processing device" is a device that receives and records questions transmitted from an information terminal, and includes servers, among other things.

[0957] "Emotional data" refers to data related to emotions obtained from the user's facial expressions, voice, etc., and indicates states such as anxiety or joy.

[0958] "Means of acquiring emotions" refers to methods of acquiring a user's emotions using devices such as cameras and microphones.

[0959] "Means for analyzing emotions" refers to methods for analyzing and identifying a user's emotions based on acquired emotional data, and an emotion engine falls under this category.

[0960] A "generative artificial intelligence system" is a system that uses a natural language processing model to generate appropriate answers based on input question data and sentiment data.

[0961] "Methods for generating answers" refers to a method of sending questions and sentiment data to a generative artificial intelligence system and having it generate answers.

[0962] "Method of returning to the information terminal" refers to a method of returning the response generated by the generative artificial intelligence system to the information terminal and displaying it to the user.

[0963] "Means of recording" refers to a method of storing received questions and sentiment data in a database for later analysis and reference.

[0964] This invention provides a question-and-answer system in which a user inputs a question and the system recognizes the emotions associated with that question. This system consists of an information terminal, an information processing device (server), an emotion analysis engine, and a generative artificial intelligence system.

[0965] System Configuration

[0966] 1. Information terminal

[0967] Information terminals are devices that allow users to input questions and provide sentiment data. Specifically, this includes personal computers, smartphones, and tablets. Users can use these devices to input questions in text format and have sentiment data acquired through the camera and microphone.

[0968] 2. Emotion Analysis Engine

[0969] An emotion analysis engine is a system that analyzes audio and image data acquired from an information terminal to identify the user's emotions. By analyzing the user's voice tone and facial expressions, the emotion analysis engine identifies emotions such as joy, anger, sadness, and happiness, and transmits this data as emotion information to an information processing device.

[0970] 3. Information processing equipment (server)

[0971] The information processing device (server) receives and records question and sentiment data transmitted from information terminals. It has the function of storing question and sentiment data in a database and accumulates the data as logs for post-processing. The server also plays the role of transmitting this data to a generative artificial intelligence system and returning the generated answers to the information terminals.

[0972] 4. Generative Artificial Intelligence Systems

[0973] Generative artificial intelligence systems are systems that generate appropriate answers using question and sentiment data received from a server. Specifically, they use natural language processing models and sentiment response algorithms to generate appropriate responses that match the content of the question and the user's emotions.

[0974] Specific example

[0975] For example, if a user is feeling anxious about orientation, the following actions are performed: The user texts "Please tell me the date and time of the orientation" on their information terminal, and their anxious facial expression and tone of voice are captured by the camera and microphone on the terminal. The information terminal sends this to a server, which logs the question and emotion data. Next, the server sends this data to a generative artificial intelligence system, which generates a response such as "The orientation will start at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later." The server sends this response back to the information terminal, which displays it. This example demonstrates how users can quickly obtain answers to their questions and receive polite responses that also address their emotions.

[0976] Example of a prompt

[0977] Here are some examples of specific prompt statements:

[0978] User question: "What is the date and time of the orientation?"

[0979] User's emotion: "Anxiety"

[0980] Using this prompt, the generative AI model generates an appropriate answer based on the user's question and sentiment.

[0981] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0982] Step 1:

[0983] Question input and sentiment recognition

[0984] Specific actions:

[0985] Users input questions about the orientation in text format into an information terminal. At the same time, they provide voice and facial expressions using the terminal's camera and microphone. For example, a user might input "Please tell me the date and time of the orientation," and then display an anxious expression and a trembling voice.

[0986] input:

[0987] Text-based questions such as "Please tell me the date and time of the orientation," and audio and image data from the camera and microphone.

[0988] Data processing:

[0989] The information terminal collects image data from the camera and audio data from the microphone.

[0990] output:

[0991] Collected text questions and sentiment data.

[0992] Step 2:

[0993] Sending questions and sentiment data

[0994] Specific actions:

[0995] The information terminal analyzes the acquired questions and sentiment data, formats them, and sends them to the information processing device (server).

[0996] input:

[0997] Text-based questions and sentiment data.

[0998] Data processing:

[0999] Integrate question text data and sentiment data into a single message and package it in an appropriate format.

[1000] output:

[1001] Formatted questionnaire data and sentiment data.

[1002] Step 3:

[1003] Receiving and logging of questions and sentiment data.

[1004] Specific actions:

[1005] The server receives question and sentiment data sent from information terminals and records it in a database. This saves the question and sentiment information as a log, which can then be referenced later.

[1006] input:

[1007] Formatted questionnaire data and sentiment data.

[1008] Data processing:

[1009] The received data is recorded in the database.

[1010] output:

[1011] Question and sentiment data stored in the database.

[1012] Step 4:

[1013] AI-generated answers

[1014] Specific actions:

[1015] The server sends question and sentiment data stored in the database to a generative artificial intelligence system to generate appropriate answers. The generative AI system uses a generative AI model to create answers based on the question content and sentiment.

[1016] input:

[1017] Question and sentiment data stored in the database.

[1018] Data processing:

[1019] Using a generative artificial intelligence system's natural language processing model and sentiment-responding algorithm, we generate questions and sentiment-sensitive answers.

[1020] output:

[1021] The generated answer.

[1022] Step 5:

[1023] Return and display of responses

[1024] Specific actions:

[1025] The server sends the response received from the generative artificial intelligence system back to the information terminal. The information terminal receives this response and displays it to the user. For example, it might display: "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later."

[1026] input:

[1027] The generated answer.

[1028] Data processing:

[1029] Send the response data to the user's terminal.

[1030] output:

[1031] The answer displayed on the information terminal.

[1032] (Application Example 2)

[1033] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1034] Conventional question-and-answer systems only generate appropriate answers to user-entered questions, failing to provide responses that take into account the user's emotional state. Therefore, particularly in security services, when users are experiencing anxiety or stress, the lack of empathetic responses can lead to decreased user satisfaction. Solving this problem is essential.

[1035] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a user terminal for inputting questions, means for logging the questions received from the user terminal, means for transmitting the questions recorded in the log to a generative artificial intelligence system to generate answers, means for returning the generated answers to the user terminal, an emotion engine for recognizing the user's emotions, means for adjusting the answers generated based on the emotions recognized by the emotion engine, and means for displaying the generated answers. This makes it possible to provide appropriate answers while taking into account the user's emotional state.

[1036] A "user terminal" is a device used by users to input questions, acquire emotional data through an emotional engine, and send it to a server.

[1037] A "server" is a computer whose role is to receive and log questions and sentiment data sent from user terminals, send that data to a generative artificial intelligence system to generate answers, and then return those answers to the user terminals.

[1038] A "generative artificial intelligence system" is a system that uses a natural language processing model to generate appropriate answers based on questions and sentiment data sent from a server.

[1039] An "emotion engine" is a system that analyzes audio and image data acquired from a user's device to identify the user's emotions.

[1040] "Response adjustment" is the process of appropriately modifying responses generated by a generative artificial intelligence system, based on emotional information recognized by the emotion engine, to take the user's emotions into consideration.

[1041] "Inputting a question" refers to the act of a user entering information they want to know into their device in the form of text or voice.

[1042] A "display means" is an interface for visually presenting the response generated on the user's terminal to the user.

[1043] The present invention will now be described in detail. To implement the invention, four main elements are required: a user terminal, an emotion engine, a server, and a generative artificial intelligence system. These elements work together to create a system that provides appropriate answers to user questions and emotions.

[1044] User terminal

[1045] The user terminal is a device used by the user to input questions and acquire emotional data. Specifically, smartphones, tablets, and personal computers are used. The user uses these devices to input questions in text or voice format, and emotional data such as facial expressions and voice tone is acquired through the camera and microphone.

[1046] Emotional Engine

[1047] An emotion engine is software that analyzes image and audio data transmitted from a user's device to identify the user's emotions. For example, image data analysis can be performed using OpenCV and Keras for face detection and emotion recognition. Audio data analysis can be performed using an audio processing library to analyze the tone of voice.

[1048] server

[1049] The server receives questions and sentiment data sent from user terminals and logs them in a database. The server also transmits questions and sentiment data to a generative artificial intelligence system, receives the generated answers, and sends them back to the user terminal. The server also incorporates a database management system (DBMS) for log management and data storage.

[1050] Generative artificial intelligence systems

[1051] The generative artificial intelligence system generates appropriate answers using a natural language processing model based on questions and sentiment data sent from the server. Specifically, it uses OpenAI's GPT-2 and modules for natural language processing. This results in the generation of answers that take sentiment into consideration.

[1052] Specific example

[1053] For example, if a user asks with an anxious expression, "What measures should I take to protect my home?", the emotion engine analyzes the expression and identifies the emotion as "anxiety." The server sends this emotion information and the question to a generative artificial intelligence system, which then generates an answer such as, "As a measure to protect your home, first install an outdoor light to deter intruders. Also, installing security cameras will give you peace of mind."

[1054] Example of a prompt

[1055] The prompt will look like this:

[1056] The user is feeling anxious and asks: What measures should I take to protect my home from crime?

[1057] By inputting this prompt into a generative artificial intelligence system, an appropriate response that corresponds to the user's emotions can be obtained.

[1058] This invention realizes an emotion-responsive question-and-answer system, which is expected to have the effect of reducing user anxiety and stress, particularly in the field of security services.

[1059] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1060] Step 1:

[1061] The user enters a question, and sentiment data is collected on the user's device.

[1062] Input: The user enters the question, "What measures should I take to improve home security?" into the user's device. Emotional data is acquired through the camera and microphone to recognize anxious facial expressions and tone of voice.

[1063] Data processing: The device generates question data in text format, analyzes image and audio data acquired by the camera and microphone, and identifies emotions from facial expressions and tone of voice.

[1064] Output: Questionnaire data in text format and emotion data for "anxiety" recognized by the emotion engine.

[1065] Step 2:

[1066] The user's terminal sends the question and sentiment data to the server.

[1067] Input: Question data and sentiment data generated in Step 1.

[1068] Data processing: The user terminal packages the question data and sentiment data and sends it to the server in the appropriate format.

[1069] Output: Question data and sentiment data sent to the server.

[1070] Step 3:

[1071] The server receives the question and sentiment data and records it in the database.

[1072] Input: Question data and sentiment data sent from the user's terminal.

[1073] Data processing: The server records the received data in a database and saves it as a log.

[1074] Output: Question data and sentiment data stored in the database.

[1075] Step 4:

[1076] The server sends the question and sentiment data to the generative artificial intelligence system.

[1077] Input: Question data and sentiment data recorded in the database.

[1078] Data processing: The server sends question data and sentiment data to the generative artificial intelligence system in an appropriate format.

[1079] Output: Question data and sentiment data sent to a generative artificial intelligence system.

[1080] Step 5:

[1081] The generative artificial intelligence system generates answers that are tailored to the question and the emotions it evokes.

[1082] Input: Question data and sentiment data sent from the server.

[1083] Data Processing: Generative artificial intelligence systems use natural language processing models and sentiment-responding algorithms to generate answers that correspond to the content and emotions of a question. For example, using the GPT-2 model, the prompt "User is feeling anxious and asks: What measures should I take to protect my home?" is processed as input.

[1084] Output: A response that takes emotions into consideration, generated by a generative artificial intelligence system (Example: "As a security measure for my home, I will first install an outdoor light to deter intruders. I will also gain peace of mind by installing a security camera.")

[1085] Step 6:

[1086] The server sends the generated response back to the user's terminal.

[1087] Input: Answer generated by a generative artificial intelligence system.

[1088] Data processing: The server sends the generated response to the user's terminal in the appropriate format.

[1089] Output: Generated response sent to the user's terminal.

[1090] Step 7:

[1091] The user terminal displays the generated response.

[1092] Input: Generated response sent from the server.

[1093] Data processing: The user terminal generates the response and displays it on the screen.

[1094] Output: Generated response that the user can view on the screen.

[1095] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1096] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1097] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1098] [Fourth Embodiment]

[1099] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1100] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1101] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1102] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1103] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1104] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1105] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1106] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1107] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1108] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1109] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1110] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1111] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1112] A specific embodiment of the present invention will now be described.

[1113] This invention provides a question-and-answer system comprising a user terminal, a server, and a generative artificial intelligence system. The user inputs a question from the terminal, the question is sent to the generative artificial intelligence system via the server, and the answer generated by the AI ​​is returned to the user terminal.

[1114] System Configuration

[1115] 1. User terminal

[1116] A user terminal is a device used by the user to input questions. Examples include personal computers, smartphones, and tablets. Users use these devices to input orientation-related questions in text format.

[1117] 2. Server

[1118] The server receives questions sent from user terminals and records them in a log. The server has a database for storing question logs, and records received questions sequentially. The server also sends questions to a generative artificial intelligence system and returns the AI-generated answers to the user terminal.

[1119] 3. Generative Artificial Intelligence Systems

[1120] Generative artificial intelligence systems receive questions sent from a server and generate appropriate answers. Specifically, they use natural language processing models to analyze the meaning of the questions and create the optimal response.

[1121] Program Processing Description

[1122] 1. Enter and submit your question.

[1123] The user enters a question about the orientation into their terminal. For example, they might enter, "What is the date and time of the orientation?" The user then sends this question to the server.

[1124] 2. Receiving and logging questions

[1125] The server receives questions from the user's terminal. Received questions are recorded in the server's question log. This allows users to refer to the question content later.

[1126] 3. AI-powered response generation

[1127] The server sends the logged question to a generative artificial intelligence system. The generative AI system uses a natural language processing model to analyze the question and generate an appropriate answer. For example, it might generate the answer, "The orientation will begin at 10:00 on November 1, 2023."

[1128] 4. Return and display of responses

[1129] The server sends the response received from the generative artificial intelligence system back to the user terminal. The user terminal receives this response and displays it on the screen. This allows the user to immediately check the answer to their question.

[1130] Specific example

[1131] For example, if a user asks about the date and time of an orientation, the following process takes place: The user types "Please tell me the date and time of the orientation" and sends it from their terminal to the server. The server logs this question and sends it to a generative artificial intelligence system. The AI ​​generates the answer "The orientation will start on November 1, 2023 at 10:00" and sends it back to the server. The server sends this answer back to the user's terminal, and the user's terminal displays the answer.

[1132] The above describes specific embodiments for carrying out the present invention. The present invention allows users to obtain quick and accurate answers to their questions, thus enabling efficient question-and-answer sessions during orientation.

[1133] The following describes the processing flow.

[1134] Step 1:

[1135] The user enters a question into their terminal.

[1136] For example, a user might type, "Please tell me the date and time of the orientation."

[1137] Step 2:

[1138] The user terminal receives user input and sends that question to the server.

[1139] This process involves the user terminal sending question data to the server via the network.

[1140] Step 3:

[1141] The server receives the question sent from the user's terminal.

[1142] The server analyzes the received data and extracts the question content.

[1143] Step 4:

[1144] The server logs the questions it receives.

[1145] The server accesses the database and saves the question as a new entry.

[1146] Step 5:

[1147] The server sends the question to the generative artificial intelligence system.

[1148] The server calls the API of the generative artificial intelligence system and sends a question.

[1149] Step 6:

[1150] A generative artificial intelligence system generates answers to questions sent from a server.

[1151] The AI ​​system uses a natural language processing model to generate appropriate answers.

[1152] Step 7:

[1153] The generative artificial intelligence system sends the generated response back to the server.

[1154] The AI ​​system sends the response data to the server.

[1155] Step 8:

[1156] The server receives the generated response and sends it back to the user's terminal.

[1157] The server packages the response data and sends it to the user's terminal via the network.

[1158] Step 9:

[1159] The user terminal displays the response received from the server to the user.

[1160] The user's terminal displays the received response on the screen so that the user can confirm it.

[1161] The above outlines the specific steps involved in question processing using a user terminal, server, and generative artificial intelligence system.

[1162] (Example 1)

[1163] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1164] In today's information society, users are required to obtain information quickly and accurately. However, conventional information retrieval systems often take a long time to provide appropriate answers to questions, which impairs user convenience. Furthermore, insufficient logging of questions and management of generated answers make it difficult to refer to and analyze question history.

[1165] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1166] In this invention, the server includes means for logging questions received from a terminal, means for sending the logged questions to a generative artificial intelligence model to generate answers, means for returning the generated answers to the terminal, and means for displaying the generated answers. This enables users to quickly obtain appropriate answers and facilitates the management and analysis of question history.

[1167] A "terminal" is a device used by a user to input questions, and includes personal computers, smartphones, tablets, and other similar devices.

[1168] A "computer" is a server that has the function of logging questions received from terminals and sending those questions to a generative artificial intelligence model.

[1169] A "generative artificial intelligence model" is an artificial intelligence system that uses natural language processing technology to analyze input questions and generate appropriate answers.

[1170] A "log" refers to a database or file used to record questions received from a terminal.

[1171] A "question" refers to information or data entered by the user through their device. A generative artificial intelligence model performs analysis based on this question.

[1172] "Answer" refers to the information and data generated by a generative artificial intelligence model after analyzing a question, and its purpose is to provide information to the user.

[1173] "Formatting" refers to arranging data into a specific format or converting it into an appropriate structure for communication purposes.

[1174] An "HTTP request" is a type of communication protocol used by a terminal to send a question to a computer.

[1175] The present invention is a question-and-answer system for providing quick and appropriate answers to user questions. This system includes a terminal, a server, and a generative artificial intelligence model.

[1176] System Configuration

[1177] 1. Terminal

[1178] A terminal is a device used by the user to input questions, and specific examples include personal computers, smartphones, and tablets. Users use these terminals to input orientation-related questions in text format.

[1179] 2. Server

[1180] The server is responsible for receiving questions sent from user terminals and logging them. The server has a database for storing question logs, and it records received questions sequentially. The server also sends questions to a generative artificial intelligence model and returns the AI-generated answers to the user terminal.

[1181] 3. Generative artificial intelligence models

[1182] Generative artificial intelligence models receive questions sent from a server and generate optimal answers using natural language processing techniques. Specifically, they use a natural language processing model (e.g., GPT-4) to analyze the meaning of the question and create the best possible answer.

[1183] Operation details

[1184] 1. Enter and submit your question.

[1185] The user enters a question about the orientation into the terminal. For example, a question such as "What is the date and time of the orientation?" is entered. The terminal then sends this question to the server. Typically, it is sent as an HTTP POST request.

[1186] 2. Receiving and logging questions

[1187] The server receives a question from the user's terminal and saves it as a new entry in the "questions_logs" table in the database. For example, it might record "id=1, question='Please tell me the date and time of the orientation.', timestamp='2023-11-01 09:00:00'". Once logging is complete, the server sends the question data to a generative artificial intelligence model.

[1188] 3. AI-powered response generation

[1189] The server sends the recorded question data as an API request to a generative artificial intelligence model. The generative AI model receives the question data, uses a natural language processing model to analyze the content of the question, and generates an appropriate answer. For example, it might generate the answer, "The orientation will begin at 10:00 on November 1, 2023."

[1190] 4. Return and display of responses

[1191] The server sends the response received from the generative artificial intelligence model back to the user terminal, which then receives and displays the response on its screen. This allows the user to immediately see the answer to their question.

[1192] Specific example

[1193] For example, if a user asks about the date and time of the orientation, they might enter a prompt like this: "Please tell me the date and time of the orientation." The terminal sends this question to the server, which logs the question and then sends it to a generative artificial intelligence model. The AI ​​analyzes the question and generates the answer, "The orientation will start on November 1, 2023 at 10:00," and sends it back to the server. The server then sends this answer to the user's terminal, which displays the answer.

[1194] Thus, the present invention provides an effective means for providing quick and accurate answers to user questions, and can significantly improve the efficiency of question and answer sessions.

[1195] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1196] Step 1:

[1197] The user enters a question using a terminal. For example, the user enters "Please tell me the date and time of the orientation." The input is a text-based question. The output is the formatted data of this question. This formatted data is sent to the server as an HTTP POST request.

[1198] Step 2:

[1199] The terminal sends the question entered by the user to the server. The input is question data in text format. The output is an HTTP request sent to the server. Specifically, the terminal parses the input data into JSON format, constructs the HTTP request, and sends it to the server's API endpoint.

[1200] Step 3:

[1201] The server logs questions received from user terminals. The input is the question data received as an HTTP request. The output is the question entry recorded in the log database. Specifically, the server extracts the question content from the request and adds a new entry to the "questions_logs" table in the database. For example, it will be recorded in the format "id=1, question='Please tell me the date and time of the orientation.', timestamp='2023-11-01 09:00:00'".

[1202] Step 4:

[1203] The server sends the logged questions to a generative artificial intelligence model. The input is question data stored in a database. The output is an API request to the generative artificial intelligence model. Specifically, the server retrieves the question data, constructs the API request, and sends it to the generative artificial intelligence model.

[1204] Step 5:

[1205] A generative artificial intelligence model receives question data and generates an appropriate answer. The input is the question data received as an API request. The output is the generated answer data. Specifically, the generative AI model uses natural language processing techniques to analyze the content of the question and generate the optimal answer. For example, it might generate the answer, "The orientation will start at 10:00 on November 1, 2023."

[1206] Step 6:

[1207] A generative artificial intelligence system sends the generated answer back to the server. The input is the generated answer data. The output is the API response sent to the server. Specifically, the generative AI model packages the answer data as an API response and sends it to the server.

[1208] Step 7:

[1209] The server sends the generated response to the user's terminal. The input is the response data received from the generative artificial intelligence model. The output is the HTTP response sent to the user's terminal. Specifically, the server converts the response data into JSON format and sends it to the user's terminal as an HTTP response.

[1210] Step 8:

[1211] The terminal displays the response received from the server. The input is the response data received as an HTTP response. The output is the response text displayed on the user interface. Specifically, the terminal parses the received response data and displays on the screen, "The orientation will begin at 10:00 on November 1, 2023."

[1212] (Application Example 1)

[1213] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1214] In physical stores, responding quickly and accurately to customer inquiries is essential for improving customer satisfaction. However, with traditional methods, store staff are not always available, and not all inquiries can be answered immediately. As a result, customers may become dissatisfied. Furthermore, it involves high labor costs and requires staff training, placing a significant burden on operations. To solve these problems, there is a need for a system that automatically answers customer questions in physical stores.

[1215] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1216] In this invention, the server includes a user terminal for inputting questions, means for logging the questions received from the user terminal, means for transmitting the questions recorded in the log to a generative artificial intelligence system for generating answers, means for returning the generated answers to the user terminal, and means for performing question answering in a physical store, which has a display device for displaying the answers. This makes it possible to respond to customer inquiries immediately in a physical store, reduce the burden on store staff, and improve customer satisfaction.

[1217] A "user terminal for entering questions" is a device used by customers to enter questions in text or voice.

[1218] A "log" is a database or file used to record questions sent from a user's terminal.

[1219] A "server" is a computer system that records questions received from user terminals as logs and sends them to a generative artificial intelligence system to generate answers.

[1220] A "generative artificial intelligence system" is an artificial intelligence system that uses natural language processing technology to generate appropriate answers to input questions.

[1221] "Means for generating answers" refers to means that include the process of creating the optimal answer to an input question using a generative artificial intelligence system.

[1222] "Means of returning to the user terminal" refers to means of sending the generated response to the user terminal so that the customer can receive it.

[1223] A "display device" is a device that visually displays the generated responses in a physical store.

[1224] "Means of answering questions in physical stores" refers to a series of system components for automatically answering customer questions in a physical store.

[1225] The embodiments for carrying out the present invention are described below. This system is for automatically providing answers to customer questions in a physical store and includes a user terminal for inputting questions, a server for receiving questions and recording them in a log, a generative artificial intelligence system, and means for returning the generated answers to the user terminal.

[1226] System Configuration

[1227] First, the user terminal is a device that customers use to input questions. Specifically, this includes smartphones, smart glasses, or interface devices installed in stores. This allows customers to ask questions using voice input or text input.

[1228] Next, the server receives and logs the questions sent from the user terminal. The server is built using, for example, Flask (a Python-based web framework). A database such as MySQL or PostgreSQL is used to record the questions. The logged questions are sent to a generative artificial intelligence system.

[1229] Generative artificial intelligence systems use natural language processing techniques to generate answers to questions. These systems employ advanced natural language processing models, such as GPT-4 (API example: OpenAI). This allows them to analyze the content of a question and automatically generate the optimal answer.

[1230] The generated response is returned to the user's terminal by the server and then communicated to the customer via a display or audio output device built into the terminal. This series of processes allows customers to receive quick and appropriate service in physical stores.

[1231] Specific example

[1232] For example, consider a scenario where a customer enters the question, "Where is the product located?" via their smartphone. The user's device sends this question to the server. The server logs the question and sends it to a generative artificial intelligence system. The AI ​​generates an answer, such as "The product is on the second floor, on the left," and returns it to the server. The server then sends the answer to the user's smartphone, which displays the answer on its screen. In this way, the customer can quickly obtain the information they need.

[1233] Example of a prompt

[1234] Examples of prompt statements are shown below.

[1235] Question: Where can I find the product?

[1236] Answer: The item is located on the left side of the second floor.

[1237] This system allows for immediate responses to customer inquiries in physical stores, thereby improving the efficiency of store operations. This can lead to increased customer satisfaction and reduced workload for store staff.

[1238] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1239] Step 1:

[1240] The user terminal receives questions from customers. Customers input questions using their smartphones or smart glasses in voice or text format. The input question data is formatted for transmission to the server. For example, if the input is voice, it is converted to text using speech recognition software. The output is the input data formatted as a question in text format.

[1241] Step 2:

[1242] The server receives questions sent from the user's terminal. The received question data is stored in a database for logging purposes. The input data is the question text sent by the user, and the output is the question log stored in the database. For example, a web server built using Flask receives question data and stores it in a MySQL or PostgreSQL database.

[1243] Step 3:

[1244] The server sends the logged questions to the generative artificial intelligence system. In doing so, it converts the question data into an appropriate format for an API request. The input data is the question log read from the database, and the output is an API request to the generative artificial intelligence system. For example, when using OpenAI's GPT-4 API, the question text is sent as a prompt.

[1245] Step 4:

[1246] The generative artificial intelligence system analyzes the received question and generates an answer. Using a natural language processing model, it understands the meaning of the question and generates the most appropriate response. The input data for this step is the question sent from the server, and the output data is the generated answer.

[1247] Step 5:

[1248] The server returns the response received from the generative artificial intelligence system to the user terminal. It formats the received response data into an appropriate format for transmission to the user terminal. The input data is the response text sent from the generative artificial intelligence system, and the output data is the formatted response data sent to the user terminal.

[1249] Step 6:

[1250] The user terminal receives the response sent from the server and displays it to the customer. It also outputs the response as needed. The input data for this step is the response text returned from the server, and the output data is the response information displayed on the user terminal. Specifically, the response text is displayed on the smartphone screen, or the response is played back as audio using speech synthesis software.

[1251] The above outlines the specific processing steps involved in implementing the present invention. This makes it possible to provide quick and appropriate answers to customer inquiries in physical stores.

[1252] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1253] A specific embodiment of the present invention will now be described.

[1254] The present invention provides a question-and-answer system that further combines a user terminal for inputting questions, a server for logging questions, means for transmitting the logged questions to a generative artificial intelligence system for generating answers, and means for returning the generated answers to the user terminal with an emotion engine that recognizes the user's emotions.

[1255] System Configuration

[1256] 1. User terminal

[1257] A user terminal is a device used by the user to input questions and send emotional information recognized by the emotion engine to the server. Examples include personal computers, smartphones, and tablets. Users use these terminals to input orientation-related questions in text format and to acquire emotional data through the camera, microphone, etc.

[1258] 2. Emotional Engine

[1259] The emotion engine is a system that analyzes audio and image data acquired from the user's device to identify the user's emotions. The emotion engine identifies emotions such as joy, anger, sadness, and happiness by analyzing the user's voice tone and facial expressions.

[1260] 3. Server

[1261] The server receives and logs questions and sentiment data sent from the user terminal. The server has a database for storing questions and associated sentiment information. The server also transmits the questions and sentiment data to a generative artificial intelligence system and returns the AI-generated answers to the user terminal.

[1262] 4. Generative Artificial Intelligence Systems

[1263] The generative artificial intelligence system receives question and sentiment data sent from a server and generates appropriate answers. Specifically, it uses natural language processing models and sentiment-responding algorithms to analyze the content of the question and generate responses that reflect the sentiment.

[1264] Program Processing Description

[1265] 1. Question input and sentiment recognition

[1266] Users input questions about the orientation into their devices and provide emotional data through the device's camera and microphone. For example, they might ask, "Please tell me the date and time of the orientation," along with sending an anxious facial expression and tone of voice to the device.

[1267] 2. Sending questions and sentiment data

[1268] The user terminal analyzes the user's input and acquired sentiment data, and sends that information to the server. The questions and sentiment data are packaged in an appropriate format.

[1269] 3. Receiving and logging questions and sentiment data.

[1270] The server receives questions and sentiment data sent from the user's terminal and records them in the database. This ensures that the questions and the corresponding sentiments are saved as logs.

[1271] 4. AI-powered response generation

[1272] The server sends the question and sentiment data to a generative artificial intelligence system. The generative AI system uses a natural language processing model and sentiment-responding algorithms to generate an answer that is appropriate to the content of the question and the user's sentiment. For example, it might generate an answer such as, "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry; detailed instructions will be distributed later."

[1273] 5. Return and display of responses

[1274] The server sends the response received from the generative artificial intelligence system back to the user terminal. The user terminal receives this response and displays it on the screen. This allows the user to immediately see the answer to their question and emotionally sensitive commentary.

[1275] Specific example

[1276] For example, if a user is worried about orientation, the following process takes place: The user types, "Please tell me the date and time of the orientation," and the device picks up on the user's anxious facial expression and tone of voice. The device sends this information to the server, which logs the question and emotion data. The server sends this data to a generative artificial intelligence system, which generates the response, "The orientation will start at 10:00 on November 1, 2023. There is no need to worry; detailed instructions will be distributed later." The server sends this response back to the user's device, which then displays it.

[1277] The above describes specific embodiments for carrying out the present invention. The present invention allows users to not only obtain quick and accurate answers to their questions, but also receive responses that take their emotions into consideration, enabling efficient question-and-answer sessions during orientation.

[1278] The following describes the processing flow.

[1279] Step 1:

[1280] Users input questions into their devices and provide emotional data through audio and video.

[1281] For example, a user might type, "Please tell me the date and time of the orientation," and convey an anxious expression or a tense tone of voice to the device.

[1282] Step 2:

[1283] The user terminal receives and analyzes the user's input text and emotional data (facial expressions and vocal characteristics).

[1284] The emotion engine analyzes the user's facial expressions and tone of voice to recognize when the user is feeling anxious.

[1285] Step 3:

[1286] The user's terminal analyzes the questions and sentiment data and sends it to the server.

[1287] Here, the emotional state (e.g., anxiety) is packaged along with the question content and sent to the server via the network.

[1288] Step 4:

[1289] The server receives the question and sentiment data sent from the user's terminal.

[1290] The received data is analyzed to extract questions and sentiment information.

[1291] Step 5:

[1292] The server logs the questions and sentiment data it receives.

[1293] By saving the question content and emotional state in a database, they can be referenced later.

[1294] Step 6:

[1295] The server sends the question and emotion data to the generative artificial intelligence system.

[1296] The API of a generative artificial intelligence system is called, and questions and sentiment data are sent.

[1297] Step 7:

[1298] A generative artificial intelligence system receives questions and sentiment data sent from a server and generates answers.

[1299] Using natural language processing models and emotion-response algorithms, we create responses that take the user's emotions into consideration.

[1300] Step 8:

[1301] The generative artificial intelligence system sends the generated response back to the server.

[1302] The generated response data is sent to the server.

[1303] Step 9:

[1304] The server returns the response received from the generative artificial intelligence system to the user's terminal.

[1305] The response data is packaged and sent to the user's terminal via the network.

[1306] Step 10:

[1307] The user terminal displays the response received from the server to the user.

[1308] The user's terminal displays the received response on the screen for the user to confirm. For example, a response such as "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later." might be displayed.

[1309] The above outlines the specific steps for question processing using the user terminal, server, generative artificial intelligence system, and emotion engine.

[1310] (Example 2)

[1311] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1312] Traditional question-and-answer systems can provide appropriate answers to user-submitted questions, but they lacked responses that took user emotions into account. Therefore, they were unable to respond flexibly to changes in user emotions, making it difficult to improve the user experience. Especially in situations involving tension and anxiety, such as orientation sessions, responses that consider emotions are essential.

[1313] The identification processing performed 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 an information processing device for recording questions, means for acquiring emotion data along with the questions, means for analyzing the acquired emotion data, means for transmitting the questions recorded in the log to a generative artificial intelligence system to generate answers, and means for returning the generated answers to an information terminal. This makes it possible to quickly provide appropriate answers that take into account the user's emotions in response to questions entered by the user.

[1314] A "question" is text data entered by the user, which requests information from the system.

[1315] An "information terminal" is a device used by a user to input questions, and includes personal computers, smartphones, tablets, and other similar devices.

[1316] An "information processing device" is a device that receives and records questions transmitted from an information terminal, and includes servers, among other things.

[1317] "Emotional data" refers to data related to emotions obtained from the user's facial expressions, voice, etc., and indicates states such as anxiety or joy.

[1318] "Means of acquiring emotions" refers to methods of acquiring a user's emotions using devices such as cameras and microphones.

[1319] "Means for analyzing emotions" refers to methods for analyzing and identifying a user's emotions based on acquired emotional data, and an emotion engine falls under this category.

[1320] A "generative artificial intelligence system" is a system that uses a natural language processing model to generate appropriate answers based on input question data and sentiment data.

[1321] "Methods for generating answers" refers to a method of sending questions and sentiment data to a generative artificial intelligence system and having it generate answers.

[1322] "Method of returning to the information terminal" refers to a method of returning the response generated by the generative artificial intelligence system to the information terminal and displaying it to the user.

[1323] "Means of recording" refers to a method of storing received questions and sentiment data in a database for later analysis and reference.

[1324] This invention provides a question-and-answer system in which a user inputs a question and the system recognizes the emotions associated with that question. This system consists of an information terminal, an information processing device (server), an emotion analysis engine, and a generative artificial intelligence system.

[1325] System Configuration

[1326] 1. Information terminal

[1327] Information terminals are devices that allow users to input questions and provide sentiment data. Specifically, this includes personal computers, smartphones, and tablets. Users can use these devices to input questions in text format and have sentiment data acquired through the camera and microphone.

[1328] 2. Emotion Analysis Engine

[1329] An emotion analysis engine is a system that analyzes audio and image data acquired from an information terminal to identify the user's emotions. By analyzing the user's voice tone and facial expressions, the emotion analysis engine identifies emotions such as joy, anger, sadness, and happiness, and transmits this data as emotion information to an information processing device.

[1330] 3. Information processing equipment (server)

[1331] The information processing device (server) receives and records question and sentiment data transmitted from information terminals. It has the function of storing question and sentiment data in a database and accumulates the data as logs for post-processing. The server also plays the role of transmitting this data to a generative artificial intelligence system and returning the generated answers to the information terminals.

[1332] 4. Generative Artificial Intelligence Systems

[1333] Generative artificial intelligence systems are systems that generate appropriate answers using question and sentiment data received from a server. Specifically, they use natural language processing models and sentiment response algorithms to generate appropriate responses that match the content of the question and the user's emotions.

[1334] Specific example

[1335] For example, if a user is feeling anxious about orientation, the following actions are performed: The user texts "Please tell me the date and time of the orientation" on their information terminal, and their anxious facial expression and tone of voice are captured by the camera and microphone on the terminal. The information terminal sends this to a server, which logs the question and emotion data. Next, the server sends this data to a generative artificial intelligence system, which generates a response such as "The orientation will start at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later." The server sends this response back to the information terminal, which displays it. This example demonstrates how users can quickly obtain answers to their questions and receive polite responses that also address their emotions.

[1336] Example of a prompt

[1337] Here are some examples of specific prompt statements:

[1338] User question: "What is the date and time of the orientation?"

[1339] User's emotion: "Anxiety"

[1340] Using this prompt, the generative AI model generates an appropriate answer based on the user's question and sentiment.

[1341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1342] Step 1:

[1343] Question input and sentiment recognition

[1344] Specific actions:

[1345] Users input questions about the orientation in text format into an information terminal. At the same time, they provide voice and facial expressions using the terminal's camera and microphone. For example, a user might input "Please tell me the date and time of the orientation," and then display an anxious expression and a trembling voice.

[1346] input:

[1347] Text-based questions such as "Please tell me the date and time of the orientation," and audio and image data from the camera and microphone.

[1348] Data processing:

[1349] The information terminal collects image data from the camera and audio data from the microphone.

[1350] output:

[1351] Collected text questions and sentiment data.

[1352] Step 2:

[1353] Sending questions and sentiment data

[1354] Specific actions:

[1355] The information terminal analyzes the acquired questions and sentiment data, formats them, and sends them to the information processing device (server).

[1356] input:

[1357] Text-based questions and sentiment data.

[1358] Data processing:

[1359] Integrate question text data and sentiment data into a single message and package it in an appropriate format.

[1360] output:

[1361] Formatted questionnaire data and sentiment data.

[1362] Step 3:

[1363] Receiving and logging of questions and sentiment data.

[1364] Specific actions:

[1365] The server receives question and sentiment data sent from information terminals and records it in a database. This saves the question and sentiment information as a log, which can then be referenced later.

[1366] input:

[1367] Formatted questionnaire data and sentiment data.

[1368] Data processing:

[1369] The received data is recorded in the database.

[1370] output:

[1371] Question and sentiment data stored in the database.

[1372] Step 4:

[1373] AI-generated answers

[1374] Specific actions:

[1375] The server sends question and sentiment data stored in the database to a generative artificial intelligence system to generate appropriate answers. The generative AI system uses a generative AI model to create answers based on the question content and sentiment.

[1376] input:

[1377] Question and sentiment data stored in the database.

[1378] Data processing:

[1379] Using a generative artificial intelligence system's natural language processing model and sentiment-responding algorithm, we generate questions and sentiment-sensitive answers.

[1380] output:

[1381] The generated answer.

[1382] Step 5:

[1383] Return and display of responses

[1384] Specific actions:

[1385] The server sends the response received from the generative artificial intelligence system back to the information terminal. The information terminal receives this response and displays it to the user. For example, it might display: "The orientation will begin at 10:00 on November 1, 2023. There is no need to worry, detailed instructions will be distributed later."

[1386] input:

[1387] The generated answer.

[1388] Data processing:

[1389] Send the response data to the user's terminal.

[1390] output:

[1391] The answer displayed on the information terminal.

[1392] (Application Example 2)

[1393] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1394] Conventional question-and-answer systems only generate appropriate answers to user-entered questions, failing to provide responses that take into account the user's emotional state. Therefore, particularly in security services, when users are experiencing anxiety or stress, the lack of empathetic responses can lead to decreased user satisfaction. Solving this problem is essential.

[1395] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes a user terminal for inputting questions, means for logging the questions received from the user terminal, means for transmitting the questions recorded in the log to a generative artificial intelligence system to generate answers, means for returning the generated answers to the user terminal, an emotion engine for recognizing the user's emotions, means for adjusting the answers generated based on the emotions recognized by the emotion engine, and means for displaying the generated answers. This makes it possible to provide appropriate answers while taking into account the user's emotional state.

[1396] A "user terminal" is a device used by users to input questions, acquire emotional data through an emotional engine, and send it to a server.

[1397] A "server" is a computer whose role is to receive and log questions and sentiment data sent from user terminals, send that data to a generative artificial intelligence system to generate answers, and then return those answers to the user terminals.

[1398] A "generative artificial intelligence system" is a system that uses a natural language processing model to generate appropriate answers based on questions and sentiment data sent from a server.

[1399] An "emotion engine" is a system that analyzes audio and image data acquired from a user's device to identify the user's emotions.

[1400] "Response adjustment" is the process of appropriately modifying responses generated by a generative artificial intelligence system, based on emotional information recognized by the emotion engine, to take the user's emotions into consideration.

[1401] "Inputting a question" refers to the act of a user entering information they want to know into their device in the form of text or voice.

[1402] A "display means" is an interface for visually presenting the response generated on the user's terminal to the user.

[1403] The present invention will now be described in detail. To implement the invention, four main elements are required: a user terminal, an emotion engine, a server, and a generative artificial intelligence system. These elements work together to create a system that provides appropriate answers to user questions and emotions.

[1404] User terminal

[1405] The user terminal is a device used by the user to input questions and acquire emotional data. Specifically, smartphones, tablets, and personal computers are used. The user uses these devices to input questions in text or voice format, and emotional data such as facial expressions and voice tone is acquired through the camera and microphone.

[1406] Emotional Engine

[1407] An emotion engine is software that analyzes image and audio data transmitted from a user's device to identify the user's emotions. For example, image data analysis can be performed using OpenCV and Keras for face detection and emotion recognition. Audio data analysis can be performed using an audio processing library to analyze the tone of voice.

[1408] server

[1409] The server receives questions and sentiment data sent from user terminals and logs them in a database. The server also transmits questions and sentiment data to a generative artificial intelligence system, receives the generated answers, and sends them back to the user terminal. The server also incorporates a database management system (DBMS) for log management and data storage.

[1410] Generative artificial intelligence systems

[1411] The generative artificial intelligence system generates appropriate answers using a natural language processing model based on questions and sentiment data sent from the server. Specifically, it uses OpenAI's GPT-2 and modules for natural language processing. This results in the generation of answers that take sentiment into consideration.

[1412] Specific example

[1413] For example, if a user asks with an anxious expression, "What measures should I take to protect my home?", the emotion engine analyzes the expression and identifies the emotion as "anxiety." The server sends this emotion information and the question to a generative artificial intelligence system, which then generates an answer such as, "As a measure to protect your home, first install an outdoor light to deter intruders. Also, installing security cameras will give you peace of mind."

[1414] Example of a prompt

[1415] The prompt will look like this:

[1416] The user is feeling anxious and asks: What measures should I take to protect my home from crime?

[1417] By inputting this prompt into a generative artificial intelligence system, an appropriate response that corresponds to the user's emotions can be obtained.

[1418] This invention realizes an emotion-responsive question-and-answer system, which is expected to have the effect of reducing user anxiety and stress, particularly in the field of security services.

[1419] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1420] Step 1:

[1421] The user enters a question, and sentiment data is collected on the user's device.

[1422] Input: The user enters the question, "What measures should I take to improve home security?" into the user's device. Emotional data is acquired through the camera and microphone to recognize anxious facial expressions and tone of voice.

[1423] Data processing: The device generates question data in text format, analyzes image and audio data acquired by the camera and microphone, and identifies emotions from facial expressions and tone of voice.

[1424] Output: Questionnaire data in text format and emotion data for "anxiety" recognized by the emotion engine.

[1425] Step 2:

[1426] The user's terminal sends the question and sentiment data to the server.

[1427] Input: Question data and sentiment data generated in Step 1.

[1428] Data processing: The user terminal packages the question data and sentiment data and sends it to the server in the appropriate format.

[1429] Output: Question data and sentiment data sent to the server.

[1430] Step 3:

[1431] The server receives the question and sentiment data and records it in the database.

[1432] Input: Question data and sentiment data sent from the user's terminal.

[1433] Data processing: The server records the received data in a database and saves it as a log.

[1434] Output: Question data and sentiment data stored in the database.

[1435] Step 4:

[1436] The server sends the question and sentiment data to the generative artificial intelligence system.

[1437] Input: Question data and sentiment data recorded in the database.

[1438] Data processing: The server sends question data and sentiment data to the generative artificial intelligence system in an appropriate format.

[1439] Output: Question data and sentiment data sent to a generative artificial intelligence system.

[1440] Step 5:

[1441] The generative artificial intelligence system generates answers that are tailored to the question and the emotions it evokes.

[1442] Input: Question data and sentiment data sent from the server.

[1443] Data Processing: Generative artificial intelligence systems use natural language processing models and sentiment-responding algorithms to generate answers that correspond to the content and emotions of a question. For example, using the GPT-2 model, the prompt "User is feeling anxious and asks: What measures should I take to protect my home?" is processed as input.

[1444] Output: A response that takes emotions into consideration, generated by a generative artificial intelligence system (Example: "As a security measure for my home, I will first install an outdoor light to deter intruders. I will also gain peace of mind by installing a security camera.")

[1445] Step 6:

[1446] The server sends the generated response back to the user's terminal.

[1447] Input: Answer generated by a generative artificial intelligence system.

[1448] Data processing: The server sends the generated response to the user's terminal in the appropriate format.

[1449] Output: Generated response sent to the user's terminal.

[1450] Step 7:

[1451] The user terminal displays the generated response.

[1452] Input: Generated response sent from the server.

[1453] Data processing: The user terminal generates the response and displays it on the screen.

[1454] Output: Generated response that the user can view on the screen.

[1455] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1456] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1457] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1458] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1459] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1460] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1461] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1462] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1463] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1464] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1465] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1466] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1467] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1468] 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.

[1469] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1470] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1471] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1472] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1473] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1474] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1475] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1476] The following is further disclosed regarding the embodiments described above.

[1477] (Claim 1)

[1478] The user terminal where the question is entered,

[1479] A server that logs the questions received from the user terminal,

[1480] A means for sending the questions recorded in the log to a generative artificial intelligence system and causing it to generate answers,

[1481] A system including means for returning the generated response to the user terminal.

[1482] (Claim 2)

[1483] The system according to claim 1, including means for displaying the generated response.

[1484] (Claim 3)

[1485] The system according to claim 1, wherein the generative artificial intelligence system includes means for using a natural language processing model.

[1486] "Example 1"

[1487] (Claim 1)

[1488] A terminal for entering questions,

[1489] A computer that logs questions received from the aforementioned terminal,

[1490] A means for sending the questions recorded in the log to a generative artificial intelligence model and causing it to generate answers,

[1491] Means for returning the generated response to the terminal,

[1492] Means for displaying the generated response,

[1493] A system that includes this.

[1494] (Claim 2)

[1495] The system according to claim 1, wherein the generative artificial intelligence model includes means for using a natural language processing model.

[1496] (Claim 3)

[1497] The system according to claim 1, wherein the terminal includes means for formatting a question and transmitting it to the computer.

[1498] "Application Example 1"

[1499] (Claim 1)

[1500] The user terminal where the question is entered,

[1501] A server that logs the questions received from the user terminal,

[1502] A means for sending the questions recorded in the log to a generative artificial intelligence system and causing it to generate answers,

[1503] means for returning the generated response to the user terminal,

[1504] A means for performing question-and-answer sessions in a physical store, which has a display device that displays the aforementioned answer,

[1505] A system that includes this.

[1506] (Claim 2)

[1507] The system according to claim 1, including means for displaying the generated response.

[1508] (Claim 3)

[1509] The system according to claim 1, wherein the generative artificial intelligence system includes means for using a natural language processing model.

[1510] "Example 2 of combining an emotion engine"

[1511] (Claim 1)

[1512] An information terminal for entering questions,

[1513] An information processing device that records questions received from the aforementioned information terminal,

[1514] Along with the aforementioned questions, a means of obtaining sentiment data,

[1515] A means of analyzing the acquired emotional data,

[1516] A means for sending the questions recorded in the log to a generative artificial intelligence system and causing it to generate answers,

[1517] Means for returning the generated response to the information terminal,

[1518] A system that includes this.

[1519] (Claim 2)

[1520] The system according to claim 1, including means for displaying the generated response.

[1521] (Claim 3)

[1522] The system according to claim 1, wherein the generative artificial intelligence system includes means for using a natural language processing model.

[1523] "Application example 2 when combining with an emotional engine"

[1524] (Claim 1)

[1525] The user terminal where the question is entered,

[1526] A server that logs the questions received from the user terminal,

[1527] A means for sending the questions recorded in the log to a generative artificial intelligence system and causing it to generate answers,

[1528] means for returning the generated response to the user terminal,

[1529] An emotion engine that recognizes the user's emotions,

[1530] means for adjusting the response generated based on the emotion recognized by the emotion engine,

[1531] A system including means for displaying the generated response.

[1532] (Claim 2)

[1533] The system according to claim 1, including means for displaying the generated response.

[1534] (Claim 3)

[1535] The system according to claim 1, wherein the generative artificial intelligence system includes means for using a natural language processing model. [Explanation of Symbols]

[1536] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. The user terminal where the question is entered, A server that logs the questions received from the user terminal, A means for sending the questions recorded in the log to a generative artificial intelligence system and causing it to generate answers, A system including means for returning the generated response to the user terminal.

2. The system according to claim 1, including means for displaying the generated response.

3. The system according to claim 1, wherein the generative artificial intelligence system includes means for using a natural language processing model.

Images