system

Abstract

Provide a system. A means for a user to input and send a question using a terminal; A server receives and analyzes a query from the terminal; a means for inputting the question analyzed by the server into a natural language processing model to generate an answer; means for transmitting and displaying a response generated by the server to the terminal; A system including:

Description

[Technical Field]

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

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

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

[0004] When on-site workers encounter questions or problems amid their busy schedules, they find it difficult to get quick answers. Furthermore, if they lack the time or resources to contact other crew members, this hinders efficient work. Furthermore, the concentration of minor questions at call centers increases the burden on those centers, leading to the problem of soaring operating costs. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: a means for a user to input and send a question using a terminal; a server to receive and analyze the question from the terminal; a means for inputting the analyzed question into a natural language processing model to generate an answer; and a means for transmitting the answer generated by the server to the terminal and displaying it. Ultimately, this system allows users to quickly resolve their questions without consuming the resources of other crew members, thereby improving work efficiency and reducing the burden on call centers.

[0006] A "terminal" is a device that provides an interface for a user to input a question and send it to a server.

[0007] A "server" is a central processing unit for analyzing questions received from terminals, generating appropriate answers, and sending them to the terminals.

[0008] "User" refers to a person who uses the system to enter questions and receive answers.

[0009] A "question" is information or a question that a user inputs using a terminal and sends to a server.

[0010] A "natural language processing model" is a machine learning model that the server uses to analyze questions and generate appropriate answers.

[0011] An "answer" is information or a solution that the server generates in response to a question using a natural language processing model and provides to the user.

[0012] A "database" is a collection of information or data that a server references when processing a query.

[0013] A "message format" is the data structure or format used by the server to communicate the generated response to the user. [Brief explanation of the drawings]

[0014] [Figure 1]1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention is a system that includes a means for a user to input and send a question using a terminal, a means for a server to receive and analyze the question from the terminal, a means for inputting the question analyzed by the server into a natural language processing model and generating an answer, and a means for transmitting the answer generated by the server to the terminal and displaying it.

[0036] Description of the embodiment

[0037] 1. User enters and submits a question

[0038] The user enters a question or problem that arises during work into a device (e.g., the LINE app on a smartphone) and clicks the send button. For example, to send a question such as, "Please tell me the stock status of this product."

[0039] 2. The server receives and analyzes the user's question.

[0040] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and the question content.

[0041] 3. The server passes the question to a natural language processing model to generate an answer.

[0042] The analyzed question data is passed to a natural language processing model on the server. The natural language processing model understands the intent of the question based on pre-trained data and generates an appropriate answer. At this time, it may refer to a database to obtain information as needed.

[0043] 4. The server generates a response, which is sent to the device and displayed.

[0044] The answer generated by the natural language processing model is converted back into a message format and sent to the device. The device displays the received message to the user, who can then check it and use it in their work.

[0045] Specific examples

[0046] Example user questions

[0047] User: "What is the availability of this item?"

[0048] System processing flow

[0049] 1. Terminal: The user types a message such as "Please tell me the stock status of this item" and clicks the send button.

[0050] 2. Server: After receiving the query data sent from the terminal, it analyzes its contents.

[0051] 3. Server:

[0052] Pass the question "What is the stock status of this product?" to the natural language processing model.

[0053] Natural language processing models understand the intent of the question and retrieve inventory information from a database as needed.

[0054] For example, generate a response such as "This item is currently in stock."

[0055] 4. Server: Converts the generated answer into a message format and sends it to the terminal.

[0056] 5. Terminal: Display the received response message "This product is currently in stock" to the user.

[0057] 6. User: Check the displayed answers and proceed with the task based on them.

[0058] In this way, the system of the present invention allows users to easily input questions and receive quick answers, which helps improve work efficiency. It also reduces the time spent requesting other crew members, thereby reducing the burden on the call center.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] A user opens the LINE app on their device and enters a question or problem. For example, the user enters "Please tell me the stock status of this product." and clicks the send button.

[0062] Step 2:

[0063] The device receives the user's input and sends it to the server via the LINE API. The data sent includes the user ID and message content.

[0064] Step 3:

[0065] The server receives a message from the user via the LINE API. The received data is in the format {"userId": "12345", "message": "Please let me know the stock status of this product."}, for example.

[0066] Step 4:

[0067] The server analyzes the contents of the received message. This analysis includes preprocessing such as tokenization and removal of stop words. For example, the message "Please tell me the stock status of this product" is analyzed and broken down into meaningful words.

[0068] Step 5:

[0069] The server inputs the preprocessed message into a natural language processing model, which analyzes the input message and understands the intent of the question. For example, it detects the presence of the keyword "stock status" in the message.

[0070] Step 6:

[0071] The server references a related database based on the output of the natural language processing model, for example, accessing an inventory management database to obtain stock information for the specified product.

[0072] Step 7:

[0073] The server generates a response based on the information it has obtained. For example, it obtains information such as "In stock" from an inventory management database and uses that information to create a response message such as "This product is currently in stock."

[0074] Step 8:

[0075] The server then converts the generated reply message back into a message format and sends it to the user's device via the LINE API. The data sent is in the following format, for example: {"replyToken": "TOKEN", "messages": [{"type": "text", "text": "This product is currently in stock."}]}.

[0076] Step 9:

[0077] The device receives the reply message from the server, which is then displayed to the user on the LINE app.

[0078] Step 10:

[0079] The user checks the displayed response message, for example, "This product is currently in stock," and proceeds with the task based on that message.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] In recent years, users have been demanding quick and efficient access to information, but conventional systems often require complex and time-consuming processes to obtain appropriate answers to questions. Furthermore, there is a problem in that it is difficult to provide appropriate and satisfactory answers to questions entered by users.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes means for a user to input and send a question using an information processing device, means for the server to receive and analyze the question from the information processing device, means for inputting the analyzed question into a generative AI model, constructing a prompt sentence, and generating an answer, and means for transmitting the generated answer to the information processing device and displaying it, thereby enabling a user to automatically obtain a quick and accurate answer to a question input by the user.

[0085] A "user" is an individual or organization that utilizes an information system to enter questions and obtain information.

[0086] An "information processing device" is a device that allows a user to input and send a question, and includes devices such as smartphones, tablets, and personal computers.

[0087] The "server" is a central processing unit that receives and analyzes a user's question, generates an answer using a generative AI model, and transmits the answer to an information processing device.

[0088] A "question" is the content of an inquiry that a user inputs into an information processing device to obtain information and that is sent to a server.

[0089] "Analysis" refers to the process by which the server understands the content of the question received and the generative AI model generates an appropriate answer.

[0090] A "generative AI model" is an algorithm or system that uses natural language processing techniques to generate appropriate answers to user questions.

[0091] A "prompt" is an instructional sentence that inputs the analyzed question content into a generative AI model, providing hints and context for the model to generate an answer.

[0092] An "answer" is information generated by a generative AI model based on a user's question, and is a message containing the information the user is looking for.

[0093] A "data resource" is a storage location for information that a generative AI model references when generating answers, including databases and knowledge bases.

[0094] The "message format" refers to the format of the response sent from the server to the information processing device, and refers to text or graphics displayed in a form that is visually easy for the user to recognize.

[0095] The present invention is a system in which a user inputs and sends a question using an information processing device. This system includes a function in which a server receives the question from the user's information processing device, analyzes it, generates an answer using a generative AI model, and sends the answer to the user's information processing device for display. Specific details of the use of the specific hardware and software, as well as the specific data processing and data calculation, are described below.

[0096] Hardware and software used

[0097] Information processing equipment:

[0098] Using devices such as smartphones, tablets, and computers, users can easily enter and submit questions anytime, anywhere.

[0099] server:

[0100] The server is a central processing unit that receives and analyzes questions, generates answers using a generative AI model, and transmits the generated answers. The server is equipped with a high-performance CPU and memory, allowing it to quickly perform complex data processing.

[0101] Generative AI models:

[0102] These are algorithms that use natural language processing technology, such as BERT (Bidirectional Encoder Representations from Transformers) and GPT-3 (registered trademark) (Generative Pre-trained Transformer 3). These models are pre-trained using large datasets, enabling advanced question answering.

[0103] Specific details of data processing and data calculation

[0104] 1. User enters and submits a question:

[0105] Users use information processing devices such as smartphones and PCs to input questions or problems that arise in their daily work or life. For example, a user launches the LINE app, types a message such as "Please tell me the stock status of this product," and clicks the send button. This operation sends the input question to the server.

[0106] 2. Receiving and parsing questions:

[0107] The server receives the HTTP request sent from the information processing device and parses the question data in JSON format. As a result, the user ID and question content are extracted. For example, the analysis may yield the question "User 12345 sent the question 'Please tell me the stock status of this product.'"

[0108] 3. Building input prompts for the generative AI model:

[0109] The server constructs a prompt sentence to be posed to the generative AI model based on the analyzed question content. The prompt sentence includes the question content as well as the necessary context information. For example, a prompt sentence such as "I want to know inventory information. Please tell me the inventory status of this product." is generated.

[0110] 4. Answer generation using generative AI models:

[0111] The constructed prompt is input to a generative AI model (e.g., GPT-3). The model analyzes the prompt and generates an appropriate response. For example, the text generated is "This item is currently in stock."

[0112] 5. Submitting and Viewing Answers:

[0113] The server receives the generated response and converts it into a message format. The converted message is parsed again into JSON format and sent to the information processing device as an HTTP response. The information processing device analyzes this message and displays on the screen the message "This product is currently in stock."

[0114] Specific examples

[0115] Example user questions:

[0116] User: "What is the availability of this item?"

[0117] System process flow:

[0118] 1. User: Opens the LINE app on their smartphone, types "Please let me know the stock status of this product," and clicks the send button.

[0119] 2. Server: Analyze the received question and record it as "Question from user 12345: 'Please tell me the stock status of this product.'"

[0120] 3. Server: Based on the analysis results, generate a prompt sentence such as "I want to know the inventory information. Please tell me the inventory status of this product." and pass it to the generative AI model.

[0121] 4. Generative AI model: Analyzes the prompt and generates the answer, "This item is currently in stock."

[0122] 5. Server: Sends the generated answer to the information processing device, which displays the answer to the user.

[0123] This allows users to easily send questions from their devices and receive instant answers, improving work efficiency and reducing the burden on other members and the support center.

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

[0125] Step 1:

[0126] User enters a question

[0127] User: Using an information processing device (such as a smartphone or computer), enter a question into the message input field on the screen.

[0128] Specific operation: For example, a user opens the LINE app, types a message such as "Please let me know the stock status of this product," and clicks the send button.

[0129] Input: The text "What is the availability of this item?"

[0130] Output: The action of clicking the submit button and submitting the question.

[0131] Step 2:

[0132] The device sends a question

[0133] Terminal: Holds and transmits questions entered by the user.

[0134] Specific behavior: The entered text is converted into JSON format data and sent to the server as an HTTP request.

[0135] Input: The question text entered by the user.

[0136] Output: The question is converted to JSON format and sent to the server as an HTTP request.

[0137] Step 3:

[0138] The server receives and analyzes the question

[0139] Server: Receives the HTTP request sent from the device and parses the question data in JSON format.

[0140] Specific operation: Analyze the received data and extract the user ID and question. The analysis results in "User 12345 sent the question 'Please tell me the stock status of this product.'"

[0141] Input: HTTP request sent from the terminal (question data in JSON format).

[0142] Output: Extracted user ID and question.

[0143] Step 4:

[0144] The server constructs a prompt

[0145] Server: Based on the extracted question content, constructs a prompt sentence to be input into the generative AI model.

[0146] What it does: The natural language processing model converts the question into a format that is easy to understand. The prompt generated is, "I want to know about inventory. Please tell me the inventory status of this product."

[0147] Input: The extracted question content.

[0148] Output: The generated prompt statement.

[0149] Step 5:

[0150] The server inputs a prompt to the generative AI model.

[0151] Server: The constructed prompt sentence is input to the generative AI model, which uses pre-trained data to generate an appropriate answer to the question.

[0152] What happens: The prompt is passed to a generative AI model (e.g., GPT-3), which parses the prompt and generates the answer, "This item is currently in stock."

[0153] Input: The generated prompt statement.

[0154] Output: The answer generated by the generative AI model.

[0155] Step 6:

[0156] The server sends the answer

[0157] Server: Converts the generated response back into a message format and sends it to the information processing device.

[0158] Specific operation: The generated answer is sent to the information processing device as an HTTP response. "Send the answer 'This product is currently in stock' to user 12345."

[0159] Input: The generated answer.

[0160] Output: The answer, formatted as a message, sent as an HTTP response.

[0161] Step 7:

[0162] The device displays the answer

[0163] Terminal: Parse the response received from the server in JSON format and display it on the screen.

[0164] What happens: A message will appear on the screen saying "This item is currently in stock."

[0165] Input: The answer sent as an HTTP response.

[0166] Output: Messages that are displayed on the screen.

[0167] (Application example 1)

[0168] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0169] In autonomous vehicles, passengers need to be able to quickly and easily obtain information about the vehicle and its real-time status. However, conventional systems have limited means for passengers to ask questions about the vehicle's status and route information and receive answers, resulting in a lack of convenience. Furthermore, many systems do not support voice input or real-time data reference, which has hindered the user experience. Therefore, a system that allows passengers to efficiently obtain information while in the vehicle is needed.

[0170] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0171] In this invention, the server includes: means for a user to input and send a question using a terminal; means for the server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; means for inputting a question regarding the vehicle's status or route information using an in-vehicle display or a smartphone and converting the voice input into text using voice recognition software; means for referencing the vehicle's internal database in real time, obtaining information about the nearest facility using GPS data, and generating an answer; and means for returning the generated answer to the user in voice or text format. This enables passengers to efficiently obtain the information they need in an autonomous vehicle in real time, significantly improving convenience.

[0172] A "user" is an operator of a terminal that utilizes the system to input information and make requests to obtain answers.

[0173] A "terminal" is a device used by a user to input and send a question, and includes a smartphone, tablet, in-vehicle display, etc.

[0174] A "server" is a computer system that analyzes questions received from a terminal, generates answers using a natural language processing model, and sends them back to the terminal.

[0175] A "natural language processing model" is a machine learning and data analysis algorithm or model used to analyze natural language questions posed by users and generate appropriate answers.

[0176] A "question" is text or voice data that a user enters to obtain specific information.

[0177] An "answer" is text or audio data of information that the server generates using a natural language processing model and provides to the user.

[0178] "Speech recognition software" is a program that captures, analyzes, and converts voice input into text.

[0179] "Real-time" is the time frame in which a system acquires, processes, and provides data almost immediately.

[0180] An "in-vehicle display" is a screen that is installed in a vehicle and is used by the user to display and input information.

[0181] A "database" is a collection of information that stores the data required based on a question and that a natural language processing model references to generate an answer.

[0182] "GPS Data" means location information that includes satellite information for identifying a specific location on Earth.

[0183] To implement this invention, it is necessary to provide a system that allows a user to input and send a question using a terminal, a server that receives and analyzes the question from the terminal, a server that inputs the analyzed question into a natural language processing model to generate an answer, and a system that transmits the answer generated by the server to the terminal and displays it. A specific embodiment of this is described below.

[0184] User Interface

[0185] Users can use their smartphone, tablet, or in-car display to type and submit their question. When using voice input, a microphone in the vehicle captures the voice and converts it into text through speech recognition software (e.g., Google® Cloud Speech-to-Text API).

[0186] Server Processing

[0187] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and question content. The server then passes the question data to a natural language processing model (e.g., the BERT model by TENSORFLOW (registered trademark)), analyzes the intent, and generates an appropriate answer. If necessary, the server references the vehicle's internal database to obtain real-time information (e.g., the vehicle's current speed and location).

[0188] Generate and reply to answers

[0189] The server converts the generated response back into a message format and sends it to the device. The device then displays the received message to the user. If a voice response is desired, the generated text is converted into speech (e.g., using the Google Cloud Text-to-Speech API) and played over the car's speakers.

[0190] Specific examples

[0191] Consider a case where a user types "How far is the next gas station?" into the in-car display and clicks the send button. The server receives and analyzes this question. The analyzed question is passed to a natural language processing model to understand the intent and obtain the necessary data (in this case, distance information using GPS). The server calculates the distance to the nearest gas station and generates an answer, "The distance to the next gas station is 5 km," which is sent back to the user. The user can then check this information on the in-car display and decide what to do next.

[0192] Prompt Sentence Examples

[0193] "What's your current speed?"

[0194] "How far is the next gas station?"

[0195] "How's the weather?"

[0196] This will enable users to obtain the information they need in real time and efficiently while in an autonomous vehicle, significantly improving convenience.

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1:

[0199] The user uses the device to input and send a question. The user inputs the question into a smartphone app or on the in-car display using text or voice. For example, the user might type, "How far is the next gas station?" and press the send button. In the case of voice input, the vehicle's microphone captures the voice and converts it into a string of characters using speech recognition software (e.g., Google Cloud Speech-to-Text API). The input is the question data in text format, and the output is the data to be sent to the server.

[0200] Step 2:

[0201] The server receives and analyzes the question from the terminal. The server analyzes the question data received from the terminal and extracts the user ID and question content. For example, a question such as "How far is the next gas station?" arrives in text format at the server. The input is the question data received from the terminal, and the output is the analyzed question data.

[0202] Step 3:

[0203] The server inputs the parsed question into a natural language processing model to generate an answer. The server inputs the parsed question data into a natural language processing model (e.g., a BERT model using TensorFlow) to understand the intent of the question. It then references the vehicle's internal database as needed to obtain real-time data. For example, it uses the vehicle's current location to calculate the distance to the nearest gas station. The input is the parsed question data, and the output is the generated answer data.

[0204] Step 4:

[0205] The answer generated by the server is sent to the terminal and displayed. The server then converts the answer generated by the natural language processing model back into a message format and sends it to the terminal. For example, an answer such as "The distance to the next gas station is 5 km" is generated and sent to the terminal. The input is the generated answer data, and the output is the data sent to the terminal.

[0206] Step 5:

[0207] The device displays the received response message to the user. The device then displays the received message to the user. If voice response is also used, the generated text is converted into speech (e.g., Google Cloud Text-to-Speech API) and played from the car's speakers. For example, a response such as "The distance to the next gas station is 5 km" is displayed on the car's display and simultaneously played aloud. The input is the response data sent to the device, and the output is the display and audio playback data for the user.

[0208] This allows users to efficiently obtain the information they need in real time while in an autonomous vehicle, significantly improving convenience.

[0209] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0210] The present invention is a system including: means for a user to input and send a question using a terminal; means for a server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; and an emotion engine that recognizes the user's emotions based on the content of the question input by the user.

[0211] Description of the embodiment

[0212] 1. User enters and submits a question

[0213] The user enters a question or problem that arises during work into a device (e.g., the LINE app on a smartphone) and clicks the send button. For example, to send a question such as, "Please tell me the stock status of this product."

[0214] 2. The server receives and analyzes the user's question.

[0215] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and the question content.

[0216] 3. The server analyzes the question using an emotion engine

[0217] The server recognizes the user's emotions from the words and context of the user's question. For example, the emotion engine may detect that the user is feeling "frustrated" based on the tone and context of the question.

[0218] 4. The server passes the question to a natural language processing model to generate an answer.

[0219] The analyzed question data and the emotion recognition results from the emotion engine are input into a natural language processing model, which uses pre-trained data to understand the intent of the question and generate an appropriate answer.

[0220] 5. The server generates a response, which is sent to the device and displayed.

[0221] The answer generated by the natural language processing model is converted back into a message format and sent to the device. The device displays the received message to the user, who can then check it and use it in their work.

[0222] Specific examples

[0223] Example user questions

[0224] User: "What is the availability of this item?"

[0225] System processing flow

[0226] 1. Terminal: The user types a message such as "Please tell me the stock status of this item" and clicks the send button.

[0227] 2. Server: After receiving the query data sent from the terminal, it analyzes its contents.

[0228] 3. Server:

[0229] The emotion engine analyzes the user's emotions from the question, for example recognizing that the user is anxious.

[0230] The natural language processing model is given the user's question and emotional information. For example, the model recognizes that the question is about "stock availability" and that the user is anxious.

[0231] 4. Server:

[0232] The natural language processing model generates an appropriate answer based on the question and emotional information.

[0233] For example, information such as "We have it in stock" can be obtained from an inventory management database, and a reply message such as "It's okay. This item is currently in stock" can be created based on that information. The reply is provided in a tone that will ease the user's impatience.

[0234] 5. Server: The generated response message is converted back into a message format and sent to the user's device via the LINE API.

[0235] 6. Terminal: The received response message "It's OK. This item is currently in stock." is displayed to the user.

[0236] 7. User: Check the displayed answers and proceed with the task based on them.

[0237] In this way, by combining the system of the present invention with an emotion engine, it is possible to respond in a detailed manner according to the user's emotions, which not only allows for quick and accurate resolution of questions but also increases user satisfaction, making it possible to provide an environment in which users can carry out their work with peace of mind.

[0238] The processing flow will be explained below.

[0239] Step 1:

[0240] A user opens the LINE app on their device and enters a question or problem. For example, the user enters "Please tell me the stock status of this product." and clicks the send button.

[0241] Step 2:

[0242] The device receives the user's input and sends it to the server via the LINE API. The data sent includes the user ID and message content.

[0243] Step 3:

[0244] The server receives a message from the user via the LINE API. The received data is in the format {"userId": "12345", "message": "Please let me know the stock status of this product."}, for example.

[0245] Step 4:

[0246] In order to analyze the contents of the message received by the server, preprocessing such as tokenization and stop word removal is performed. For example, a message such as "Please tell me the stock status of this product" is analyzed and broken down into meaningful words.

[0247] Step 5:

[0248] The server inputs the preprocessed message into the emotion engine, which analyzes the user's emotion from the message text and returns the result. For example, the emotion engine may determine that the user is anxious.

[0249] Step 6:

[0250] The server receives the results from the emotion engine and inputs them into the natural language processing model. The natural language processing model analyzes the input question and emotional information to understand the intent of the question. For example, it detects that the keyword "stock status" is included.

[0251] Step 7:

[0252] The server references a related database based on the output of the natural language processing model, for example, accessing an inventory management database to obtain stock information for the specified product.

[0253] Step 8:

[0254] The server generates a response based on the information it has acquired and the results of the emotion engine. For example, it acquires information such as "In stock" from an inventory management database and uses that information to create a response message such as "It's OK. This item is currently in stock." This response includes a tone of voice to calm the user's impatience.

[0255] Step 9:

[0256] The server then converts the generated reply message back into a message format and sends it to the user's device via the LINE API. The data sent is in the following format, for example: {"replyToken": "TOKEN", "messages": [{"type": "text", "text": "No problem. This item is currently in stock."}]}

[0257] Step 10:

[0258] The device receives the reply message from the server, which is then displayed to the user on the LINE app.

[0259] Step 11:

[0260] The user checks the displayed response message, for example, "It's OK. This item is currently in stock," and proceeds with the task based on that message.

[0261] Example 2

[0262] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0263] In conventional systems, even when users input questions or problems, responses that do not reflect the emotional nuances of the question are not provided, resulting in low user satisfaction. Furthermore, because answers are generated based solely on the content of the question, it is difficult to provide a fast and appropriate service.

[0264] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0265] In this invention, the server includes means for a user to input and send a question using a terminal, means for the server to receive and analyze the question from the terminal, means for the server to analyze the question data with an emotion engine and recognize the user's emotion, means for the server to input the question and emotion analyzed by the server into a natural language processing model and generate an answer, and means for transmitting the answer generated by the server to the terminal and displaying it. This enables detailed responses according to the user's emotion and enables the provision of quick and accurate answers to questions.

[0266] A "user" is an entity that uses the system to enter questions and receive answers.

[0267] "Terminal" refers to an information and communication device that allows a user to input and send a question, and includes, for example, a smartphone or a personal computer.

[0268] A "server" is a computer device that receives and analyzes question data sent from a user's terminal, and generates and sends answers.

[0269] A "question" is a message about a question or problem that a user inputs and sends via a terminal.

[0270] "Reception" refers to the process in which the server receives question data sent from the user's terminal.

[0271] "Analysis" refers to the process in which the server understands the content of the question data received and extracts the necessary information.

[0272] The "emotion engine" is a software component that recognizes the user's emotions from the keywords and context contained in the question data.

[0273] "Emotion" refers to the psychological state that the user reflects in the question, and includes, for example, "joy," "sadness," and "impatience."

[0274] A "natural language processing model" is a model that uses artificial intelligence technology to generate appropriate answers based on analyzed question data and emotional information.

[0275] An "answer" is an appropriate response to a question that the server generates using a natural language processing model.

[0276] "Send" refers to the process of sending the response generated by the server to the user's terminal.

[0277] "Display" refers to the process of visually presenting the received answers on the user's terminal.

[0278] In this system, a user inputs a question using a terminal, the server receives and analyzes the question, generates an appropriate answer, and sends it back to the user's terminal, thereby quickly resolving the user's doubts and problems. A specific embodiment of this system will be described below.

[0279] System configuration

[0280] The system includes the following components:

[0281] 1. User device: Refers to the information and communication device that users use to input and send questions. Examples include smartphones and personal computers.

[0282] 2. Server: A central processing unit for analyzing questions received from user terminals and generating appropriate answers. The server includes the following major hardware and software components:

[0283] Receiving and analyzing module: receives and analyzes user question data.

[0284] Emotion Engine: A software component for recognizing user emotions from received question data.

[0285] Natural language processing model: A model that uses artificial intelligence techniques to generate answers based on analyzed question data and emotional information. Specific examples include generative AI models such as GPT-3.

[0286] Transmission module: Transmits the generated answer to the user terminal.

[0287] 3. Database: A storage device that stores necessary information and references it when generating answers to questions.

[0288] Data processing flow

[0289] 1. User enters question and submits it

[0290] The user opens a chat application on a device (e.g., a smartphone or a PC) and enters a question in text format. For example, the user sends a message such as, "Please tell me the stock status of this product."

[0291] 2. The server receives and analyzes the user's question.

[0292] The server receives the question data sent from the device. It then analyzes the received data and extracts the question content, user ID, etc. The analysis results are stored in an internal database as structured data.

[0293] 3. The server analyzes the question using an emotion engine

[0294] The server passes the question data to the emotion engine to recognize the user's emotion. The emotion engine determines emotions such as "joy," "sadness," and "impatience" based on the keywords and context contained in the question. For example, the emotion engine determines that the user is impatient based on the content of the question.

[0295] 4. The server passes the question to a natural language processing model to generate an answer

[0296] The server inputs the analyzed question data and emotion recognition results into a natural language processing model (e.g., GPT-3), which then generates an appropriate answer based on this data.

[0297] Example prompt: "The user is asking, 'What is the availability of this item?' They also seem impatient. Please generate a response in the appropriate tone."

[0298] 5. The server generates a response, which is sent to the device and displayed.

[0299] The server converts the generated response into a message format and sends it to the user's device via LINE's API, etc. The device displays the received response message to the user, who then confirms it and continues working.

[0300] Specific example explanation

[0301] For example, if a user sends a question via the LINE app, such as "Please tell me the stock status of this item," the server receives the question, analyzes its content, and uses its emotion engine to recognize the user's emotion as "anxious." Based on the information "In stock," the server generates a response in a reassuring tone, "Don't worry. This item is currently in stock," using the GPT-3 model. This response is then sent to the user in the form of a LINE message, and the device displays the message to the user. The user can then confirm the displayed response and continue their work based on it.

[0302] In this way, by generating answers that take the user's feelings into consideration, this system is able to improve user satisfaction and provide quick and accurate solutions to questions.

[0303] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0304] Step 1:

[0305] User enters question and submits it

[0306] Specific actions: The user opens a chat application on a device such as a smartphone or PC and enters their question or problem in text format. They type, "Please tell me the stock status of this product," and clicks the send button.

[0307] Input: The question text entered by the user

[0308] Output: Sending query data from the terminal to the server

[0309] Step 2:

[0310] The server receives and analyzes the user's question.

[0311] Specific operation: The server receives the question data sent from the device. The server analyzes the received data to extract the user ID and question content. For example, it extracts the user_id and text from the JSON format message and stores them in an internal database.

[0312] Input: Question data sent from the terminal

[0313] Output: Extract user ID and question content, store in database

[0314] Step 3:

[0315] The server analyzes the question using an emotion engine

[0316] Specific operation: The server passes the received question data to the emotion engine, which analyzes the user's emotions. The emotion engine determines emotions such as "joy," "sadness," and "impatience" from the content of the question text. For example, from the text "Please tell me the stock status of this product," it recognizes that the user is impatient.

[0317] Input: Parsed question content

[0318] Output: Emotion data as the analysis result (e.g., {"emotion": "anxious"})

[0319] Step 4:

[0320] The server passes the question to a natural language processing model to generate an answer.

[0321] Specific operation: The server inputs the analyzed question data and the emotion recognition results into a natural language processing model. The natural language processing model (e.g., GPT-3) generates an appropriate answer based on the prompt sentence.

[0322] Example prompt: A specific prompt used for the interaction is, "The user is asking, 'What is the availability of this item?' and seems impatient. Please generate a response in an appropriate tone."

[0323] Input: Question content and emotion data

[0324] Output: Answer text generated from the natural language processing model (e.g., "No problem. This item is currently in stock.")

[0325] Step 5:

[0326] The server generates a response, which is sent to the device and displayed.

[0327] Specific operation: The server converts the generated response text into a message format and sends it to the user's device via the LINE API. The user's device displays the received message.

[0328] Input: Generated answer text

[0329] Output: Send and display the reply message to the user's terminal

[0330] This process allows users to receive prompt and appropriate responses, and in the process, it is possible to respond in a way that takes into consideration the user's feelings.

[0331] (Application example 2)

[0332] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0333] Conventional content delivery services provide uniform answers and recommendations without considering the user's emotions, resulting in low user satisfaction. When a user is in a specific emotional state, content appropriate for that emotion is often not provided, so there is a need to improve the user experience.

[0334] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input and send a question using a terminal; means for the server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; means for the server to recognize the user's emotion based on the user's question; and means for passing the emotion recognition result to the natural language processing model and generating an optimal answer according to the user's emotion. This makes it possible to deliver optimal content according to the user's emotion.

[0335] A "terminal" is an electronic device that a user uses to enter and submit a question.

[0336] A "server" is a computer system that receives queries from users and analyzes and processes the queries.

[0337] A "question" is information or a question that a user inputs through a terminal.

[0338] A "natural language processing model" is an artificial intelligence technology that analyzes text data written in natural language and generates appropriate answers.

[0339] An "answer" is a response generated in response to a question, which contains information that is useful to the user.

[0340] "Emotion recognition" is a method of analyzing and identifying a user's emotional state from the content of the question entered by the user.

[0341] An "information database" is a system or storage device that stores data or information related to a query.

[0342] A system for implementing this invention includes a means for a user to input and send a question using a terminal, a server to receive and analyze the question, generate an answer using a natural language processing model, and send the answer to the terminal for display. Meanwhile, the server further has a means for recognizing emotions based on the user's question, and generates an optimal answer using the natural language processing model based on the recognition results.

[0343] System Configuration

[0344] Device: The device through which the user enters the question. Examples include a smartphone or tablet.

[0345] Server: Responsible for receiving questions, analyzing them, performing emotion recognition, and inputting them into a natural language processing model to generate answers.

[0346] Natural language processing model: Uses a pre-trained model (e.g., GPT-3) to generate appropriate answers based on the input question and sentiment information.

[0347] Emotion recognition engine: Analyzes the emotions expressed by the user's questions and identifies emotions such as joy, sadness, or impatience.

[0348] Software processing and data calculations

[0349] When the server receives a question, it first analyzes the user's emotions using an emotion recognition engine. For example, it uses the Transformers library to run an emotion analysis model. Next, based on the analysis results, it inputs the prompt sentence into a natural language processing model to generate the optimal answer. In this process, a generative AI model (e.g., GPT-3) is used.

[0350] After generating the answer, the server sends it to the user's device, which displays it in the form of a message. For example, if a user asks, "Tell me a movie that will help me relax today," the emotion recognition engine analyzes the emotion "I want to relax," and the natural language processing model generates the answer, "Currently, the movie that is recommended for relaxation is 'Your Name.' Why don't you watch it?"

[0351] Usage example

[0352] For example, use the following prompt:

[0353] User Question: "What movie can I watch to relax today?"

[0354] Example prompt: "The user's emotion is wanting to relax, and the question is 'What movie would make me relax today?'"

[0355] This prompt is then fed into a natural language processing model to generate the most appropriate answer for the user, such as "There's a movie called 'Your Name.' that's relaxing. Why don't you check it out?"

[0356] As a result, it is possible to provide the most appropriate answer according to the user's emotions, which is expected to improve the user experience.

[0357] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0358] Step 1:

[0359] The user uses the device to input and send a question. For example, the user inputs "Tell me a relaxing movie to watch today" into a smartphone application and clicks the send button. This input is sent from the device to the server.

[0360] Step 2:

[0361] The server receives the question sent from the terminal. The server analyzes the question data and extracts the user ID and question content. In this step, the question content is provided as input data, and the analyzed question information is obtained as output data.

[0362] Step 3:

[0363] The server passes the question to an emotion recognition engine to analyze the user's emotion. The emotion recognition engine identifies the emotion from the context of the question. Specifically, emotion analysis is performed using the Transformers library. For example, it detects the emotion "I want to relax." The input for this step is the question, and the output is the user's emotional information.

[0364] Step 4:

[0365] The server creates a prompt sentence based on the emotional information and the analyzed question content and inputs it into the natural language processing model. For example, the prompt sentence might be, "The user's emotional state is that they want to relax, and the question is, 'Tell me a relaxing movie to watch today.'" This prompt sentence is passed to a generative AI model (e.g., GPT-3). The inputs to this step are the question content and emotional information, and the output is the prompt sentence.

[0366] Step 5:

[0367] The natural language processing model generates an answer based on the prompt sentence. The generative AI model uses pre-trained data to generate an appropriate answer based on the user's question and emotions. For example, it generates the answer, "Currently, 'Your Name' is a relaxing movie. Why don't you watch it?" The input of this step is the prompt sentence, and the output is the generated answer.

[0368] Step 6:

[0369] The server sends the generated answer to the terminal. The server converts the generated answer into a message format and sends it to the terminal. The input of this step is the generated answer, and the output is data in message format.

[0370] Step 7:

[0371] The device displays the received answer to the user. For example, a message such as "Currently, 'Your Name' is available as a relaxing movie. Why not check it out?" is displayed. The user checks the displayed message and takes the corresponding action. The input of this step is data in the form of a message, and the output is information acquired by the user's visual recognition.

[0372] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0373] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0374] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0375] [Second embodiment]

[0376] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0377] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0378] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0379] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0380] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0381] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0382] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0383] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0384] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0385] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0386] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0387] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0388] The present invention is a system that includes a means for a user to input and send a question using a terminal, a means for a server to receive and analyze the question from the terminal, a means for inputting the question analyzed by the server into a natural language processing model and generating an answer, and a means for transmitting the answer generated by the server to the terminal and displaying it.

[0389] Description of the embodiment

[0390] 1. User enters and submits a question

[0391] The user enters a question or problem that arises during work into a device (e.g., the LINE app on a smartphone) and clicks the send button. For example, to send a question such as, "Please tell me the stock status of this product."

[0392] 2. The server receives and analyzes the user's question.

[0393] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and the question content.

[0394] 3. The server passes the question to a natural language processing model to generate an answer.

[0395] The analyzed question data is passed to a natural language processing model on the server. The natural language processing model understands the intent of the question based on pre-trained data and generates an appropriate answer. At this time, it may refer to a database to obtain information as needed.

[0396] 4. The server generates a response, which is sent to the device and displayed.

[0397] The answer generated by the natural language processing model is converted back into a message format and sent to the device. The device displays the received message to the user, who can then check it and use it in their work.

[0398] Specific examples

[0399] Example user questions

[0400] User: "What is the availability of this item?"

[0401] System processing flow

[0402] 1. Terminal: The user types a message such as "Please tell me the stock status of this item" and clicks the send button.

[0403] 2. Server: After receiving the query data sent from the terminal, it analyzes its contents.

[0404] 3. Server:

[0405] Pass the question "What is the stock status of this product?" to the natural language processing model.

[0406] Natural language processing models understand the intent of the question and retrieve inventory information from a database as needed.

[0407] For example, generate a response such as "This item is currently in stock."

[0408] 4. Server: Converts the generated answer into a message format and sends it to the terminal.

[0409] 5. Terminal: Display the received response message "This product is currently in stock" to the user.

[0410] 6. User: Check the displayed answers and proceed with the task based on them.

[0411] In this way, the system of the present invention allows users to easily input questions and receive quick answers, which helps improve work efficiency. It also reduces the time spent requesting other crew members, thereby reducing the burden on the call center.

[0412] The processing flow will be explained below.

[0413] Step 1:

[0414] A user opens the LINE app on their device and enters a question or problem. For example, the user enters "Please tell me the stock status of this product." and clicks the send button.

[0415] Step 2:

[0416] The device receives the user's input and sends it to the server via the LINE API. The data sent includes the user ID and message content.

[0417] Step 3:

[0418] The server receives a message from the user via the LINE API. The received data is in the format {"userId": "12345", "message": "Please let me know the stock status of this product."}, for example.

[0419] Step 4:

[0420] The server analyzes the contents of the received message. This analysis includes preprocessing such as tokenization and removal of stop words. For example, the message "Please tell me the stock status of this product" is analyzed and broken down into meaningful words.

[0421] Step 5:

[0422] The server inputs the preprocessed message into a natural language processing model, which analyzes the input message and understands the intent of the question. For example, it detects the presence of the keyword "stock status" in the message.

[0423] Step 6:

[0424] The server references a related database based on the output of the natural language processing model, for example, accessing an inventory management database to obtain stock information for the specified product.

[0425] Step 7:

[0426] The server generates a response based on the information it has obtained. For example, it obtains information such as "In stock" from an inventory management database and uses that information to create a response message such as "This product is currently in stock."

[0427] Step 8:

[0428] The server then converts the generated reply message back into a message format and sends it to the user's device via the LINE API. The data sent is in the following format, for example: {"replyToken": "TOKEN", "messages": [{"type": "text", "text": "This product is currently in stock."}]}.

[0429] Step 9:

[0430] The device receives the reply message from the server, which is then displayed to the user on the LINE app.

[0431] Step 10:

[0432] The user checks the displayed response message, for example, "This product is currently in stock," and proceeds with the task based on that message.

[0433] Example 1

[0434] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0435] In recent years, users have been demanding quick and efficient access to information, but conventional systems often require complex and time-consuming processes to obtain appropriate answers to questions. Furthermore, there is a problem in that it is difficult to provide appropriate and satisfactory answers to questions entered by users.

[0436] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0437] In this invention, the server includes means for a user to input and send a question using an information processing device, means for the server to receive and analyze the question from the information processing device, means for inputting the analyzed question into a generative AI model, constructing a prompt sentence, and generating an answer, and means for transmitting the generated answer to the information processing device and displaying it, thereby enabling a user to automatically obtain a quick and accurate answer to a question input by the user.

[0438] A "user" is an individual or organization that utilizes an information system to enter questions and obtain information.

[0439] An "information processing device" is a device that allows a user to input and send a question, and includes devices such as smartphones, tablets, and personal computers.

[0440] The "server" is a central processing unit that receives and analyzes a user's question, generates an answer using a generative AI model, and transmits the answer to an information processing device.

[0441] A "question" is the content of an inquiry that a user inputs into an information processing device to obtain information and that is sent to a server.

[0442] "Analysis" refers to the process by which the server understands the content of the question received and the generative AI model generates an appropriate answer.

[0443] A "generative AI model" is an algorithm or system that uses natural language processing techniques to generate appropriate answers to user questions.

[0444] A "prompt" is an instructional sentence that inputs the analyzed question content into a generative AI model, providing hints and context for the model to generate an answer.

[0445] An "answer" is information generated by a generative AI model based on a user's question, and is a message containing the information the user is looking for.

[0446] A "data resource" is a storage location for information that a generative AI model references when generating answers, including databases and knowledge bases.

[0447] The "message format" refers to the format of the response sent from the server to the information processing device, and refers to text or graphics displayed in a form that is visually easy for the user to recognize.

[0448] The present invention is a system in which a user inputs and sends a question using an information processing device. This system includes a function in which a server receives the question from the user's information processing device, analyzes it, generates an answer using a generative AI model, and sends the answer to the user's information processing device for display. Specific details of the use of the specific hardware and software, as well as the specific data processing and data calculation, are described below.

[0449] Hardware and software used

[0450] Information processing equipment:

[0451] Using devices such as smartphones, tablets, and computers, users can easily enter and submit questions anytime, anywhere.

[0452] server:

[0453] The server is a central processing unit that receives and analyzes questions, generates answers using a generative AI model, and transmits the generated answers. The server is equipped with a high-performance CPU and memory, allowing it to quickly perform complex data processing.

[0454] Generative AI models:

[0455] These are algorithms that use natural language processing technology, such as BERT (Bidirectional Encoder Representations from Transformers) and GPT-3 (Generative Pre-trained Transformer 3). These models are pre-trained using large datasets, enabling advanced question answering.

[0456] Specific details of data processing and data calculation

[0457] 1. User enters and submits a question:

[0458] Users use information processing devices such as smartphones and PCs to input questions or problems that arise in their daily work or life. For example, a user launches the LINE app, types a message such as "Please tell me the stock status of this product," and clicks the send button. This operation sends the input question to the server.

[0459] 2. Receiving and parsing questions:

[0460] The server receives the HTTP request sent from the information processing device and parses the question data in JSON format. As a result, the user ID and question content are extracted. For example, the analysis may yield the question "User 12345 sent the question 'Please tell me the stock status of this product.'"

[0461] 3. Building input prompts for the generative AI model:

[0462] The server constructs a prompt sentence to be posed to the generative AI model based on the analyzed question content. The prompt sentence includes the question content as well as the necessary context information. For example, a prompt sentence such as "I want to know inventory information. Please tell me the inventory status of this product." is generated.

[0463] 4. Answer generation using generative AI models:

[0464] The constructed prompt is input to a generative AI model (e.g., GPT-3). The model analyzes the prompt and generates an appropriate response. For example, the text generated is "This item is currently in stock."

[0465] 5. Submitting and Viewing Answers:

[0466] The server receives the generated response and converts it into a message format. The converted message is parsed again into JSON format and sent to the information processing device as an HTTP response. The information processing device analyzes this message and displays on the screen the message "This product is currently in stock."

[0467] Specific examples

[0468] Example user questions:

[0469] User: "What is the availability of this item?"

[0470] System process flow:

[0471] 1. User: Opens the LINE app on their smartphone, types "Please let me know the stock status of this product," and clicks the send button.

[0472] 2. Server: Analyze the received question and record it as "Question from user 12345: 'Please tell me the stock status of this product.'"

[0473] 3. Server: Based on the analysis results, generate a prompt sentence such as "I want to know the inventory information. Please tell me the inventory status of this product." and pass it to the generative AI model.

[0474] 4. Generative AI model: Analyzes the prompt and generates the answer, "This item is currently in stock."

[0475] 5. Server: Sends the generated answer to the information processing device, which displays the answer to the user.

[0476] This allows users to easily send questions from their devices and receive instant answers, improving work efficiency and reducing the burden on other members and the support center.

[0477] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0478] Step 1:

[0479] User enters a question

[0480] User: Using an information processing device (such as a smartphone or computer), enter a question into the message input field on the screen.

[0481] Specific operation: For example, a user opens the LINE app, types a message such as "Please let me know the stock status of this product," and clicks the send button.

[0482] Input: The text "What is the availability of this item?"

[0483] Output: The action of clicking the submit button and submitting the question.

[0484] Step 2:

[0485] The device sends a question

[0486] Terminal: Holds and transmits questions entered by the user.

[0487] Specific behavior: The entered text is converted into JSON format data and sent to the server as an HTTP request.

[0488] Input: The question text entered by the user.

[0489] Output: The question is converted to JSON format and sent to the server as an HTTP request.

[0490] Step 3:

[0491] The server receives and analyzes the question

[0492] Server: Receives the HTTP request sent from the device and parses the question data in JSON format.

[0493] Specific operation: Analyze the received data and extract the user ID and question. The analysis results in "User 12345 sent the question 'Please tell me the stock status of this product.'"

[0494] Input: HTTP request sent from the terminal (question data in JSON format).

[0495] Output: Extracted user ID and question.

[0496] Step 4:

[0497] The server constructs a prompt

[0498] Server: Based on the extracted question content, constructs a prompt sentence to be input into the generative AI model.

[0499] What it does: The natural language processing model converts the question into a format that is easy to understand. The prompt generated is, "I want to know about inventory. Please tell me the inventory status of this product."

[0500] Input: The extracted question content.

[0501] Output: The generated prompt statement.

[0502] Step 5:

[0503] The server inputs a prompt to the generative AI model.

[0504] Server: The constructed prompt sentence is input to the generative AI model, which uses pre-trained data to generate an appropriate answer to the question.

[0505] What happens: The prompt is passed to a generative AI model (e.g., GPT-3), which parses the prompt and generates the answer, "This item is currently in stock."

[0506] Input: The generated prompt statement.

[0507] Output: The answer generated by the generative AI model.

[0508] Step 6:

[0509] The server sends the answer

[0510] Server: Converts the generated response back into a message format and sends it to the information processing device.

[0511] Specific operation: The generated answer is sent to the information processing device as an HTTP response. "Send the answer 'This product is currently in stock' to user 12345."

[0512] Input: The generated answer.

[0513] Output: The answer, formatted as a message, sent as an HTTP response.

[0514] Step 7:

[0515] The device displays the answer

[0516] Terminal: Parse the response received from the server in JSON format and display it on the screen.

[0517] What happens: A message will appear on the screen saying "This item is currently in stock."

[0518] Input: The answer sent as an HTTP response.

[0519] Output: Messages that are displayed on the screen.

[0520] (Application example 1)

[0521] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0522] In autonomous vehicles, passengers need to be able to quickly and easily obtain information about the vehicle and its real-time status. However, conventional systems have limited means for passengers to ask questions about the vehicle's status and route information and receive answers, resulting in a lack of convenience. Furthermore, many systems do not support voice input or real-time data reference, which has hindered the user experience. Therefore, a system that allows passengers to efficiently obtain information while in the vehicle is needed.

[0523] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0524] In this invention, the server includes: means for a user to input and send a question using a terminal; means for the server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; means for inputting a question regarding the vehicle's status or route information using an in-vehicle display or a smartphone and converting the voice input into text using voice recognition software; means for referencing the vehicle's internal database in real time, obtaining information about the nearest facility using GPS data, and generating an answer; and means for returning the generated answer to the user in voice or text format. This enables passengers to efficiently obtain the information they need in an autonomous vehicle in real time, significantly improving convenience.

[0525] A "user" is an operator of a terminal that utilizes the system to input information and make requests to obtain answers.

[0526] A "terminal" is a device used by a user to input and send a question, and includes a smartphone, tablet, in-vehicle display, etc.

[0527] A "server" is a computer system that analyzes questions received from a terminal, generates answers using a natural language processing model, and sends them back to the terminal.

[0528] A "natural language processing model" is a machine learning and data analysis algorithm or model used to analyze natural language questions posed by users and generate appropriate answers.

[0529] A "question" is text or voice data that a user enters to obtain specific information.

[0530] An "answer" is text or audio data of information that the server generates using a natural language processing model and provides to the user.

[0531] "Speech recognition software" is a program that captures, analyzes, and converts voice input into text.

[0532] "Real-time" is the time frame in which a system acquires, processes, and provides data almost immediately.

[0533] An "in-vehicle display" is a screen that is installed in a vehicle and is used by the user to display and input information.

[0534] A "database" is a collection of information that stores the data required based on a question and that a natural language processing model references to generate an answer.

[0535] "GPS Data" means location information that includes satellite information for identifying a specific location on Earth.

[0536] To implement this invention, it is necessary to provide a system that allows a user to input and send a question using a terminal, a server that receives and analyzes the question from the terminal, a server that inputs the analyzed question into a natural language processing model to generate an answer, and a system that transmits the answer generated by the server to the terminal and displays it. A specific embodiment of this is described below.

[0537] User Interface

[0538] Users can use their smartphone, tablet, or in-car display to type and submit their question. When using voice input, a microphone in the vehicle captures the voice and converts it into text through speech recognition software (e.g., Google Cloud Speech-to-Text API).

[0539] Server Processing

[0540] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and question content. The server then passes the question data to a natural language processing model (e.g., the BERT model using TensorFlow) to analyze the intent and generate an appropriate answer. If necessary, the server references the vehicle's internal database to obtain real-time information (e.g., the vehicle's current speed and location).

[0541] Generate and reply to answers

[0542] The server converts the generated response back into a message format and sends it to the device. The device then displays the received message to the user. If a voice response is desired, the generated text is converted into speech (e.g., using the Google Cloud Text-to-Speech API) and played over the car's speakers.

[0543] Specific examples

[0544] Consider a case where a user types "How far is the next gas station?" into the in-car display and clicks the send button. The server receives and analyzes this question. The analyzed question is passed to a natural language processing model to understand the intent and obtain the necessary data (in this case, distance information using GPS). The server calculates the distance to the nearest gas station and generates an answer, "The distance to the next gas station is 5 km," which is sent back to the user. The user can then check this information on the in-car display and decide what to do next.

[0545] Prompt Sentence Examples

[0546] "What's your current speed?"

[0547] "How far is the next gas station?"

[0548] "How's the weather?"

[0549] This will enable users to obtain the information they need in real time and efficiently while in an autonomous vehicle, significantly improving convenience.

[0550] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0551] Step 1:

[0552] The user uses the device to input and send a question. The user inputs the question into a smartphone app or on the in-car display using text or voice. For example, the user might type, "How far is the next gas station?" and press the send button. In the case of voice input, the vehicle's microphone captures the voice and converts it into a string of characters using speech recognition software (e.g., Google Cloud Speech-to-Text API). The input is the question data in text format, and the output is the data to be sent to the server.

[0553] Step 2:

[0554] The server receives and analyzes the question from the terminal. The server analyzes the question data received from the terminal and extracts the user ID and question content. For example, a question such as "How far is the next gas station?" arrives in text format at the server. The input is the question data received from the terminal, and the output is the analyzed question data.

[0555] Step 3:

[0556] The server inputs the parsed question into a natural language processing model to generate an answer. The server inputs the parsed question data into a natural language processing model (e.g., a BERT model using TensorFlow) to understand the intent of the question. It then references the vehicle's internal database as needed to obtain real-time data. For example, it uses the vehicle's current location to calculate the distance to the nearest gas station. The input is the parsed question data, and the output is the generated answer data.

[0557] Step 4:

[0558] The answer generated by the server is sent to the terminal and displayed. The server then converts the answer generated by the natural language processing model back into a message format and sends it to the terminal. For example, an answer such as "The distance to the next gas station is 5 km" is generated and sent to the terminal. The input is the generated answer data, and the output is the data sent to the terminal.

[0559] Step 5:

[0560] The device displays the received response message to the user. The device then displays the received message to the user. If voice response is also used, the generated text is converted into speech (e.g., Google Cloud Text-to-Speech API) and played from the car's speakers. For example, a response such as "The distance to the next gas station is 5 km" is displayed on the car's display and simultaneously played aloud. The input is the response data sent to the device, and the output is the display and audio playback data for the user.

[0561] This allows users to efficiently obtain the information they need in real time while in an autonomous vehicle, significantly improving convenience.

[0562] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0563] The present invention is a system including: means for a user to input and send a question using a terminal; means for a server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; and an emotion engine that recognizes the user's emotions based on the content of the question input by the user.

[0564] Description of the embodiment

[0565] 1. User enters and submits a question

[0566] The user enters a question or problem that arises during work into a device (e.g., the LINE app on a smartphone) and clicks the send button. For example, to send a question such as, "Please tell me the stock status of this product."

[0567] 2. The server receives and analyzes the user's question.

[0568] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and the question content.

[0569] 3. The server analyzes the question using an emotion engine

[0570] The server recognizes the user's emotions from the words and context of the user's question. For example, the emotion engine may detect that the user is feeling "frustrated" based on the tone and context of the question.

[0571] 4. The server passes the question to a natural language processing model to generate an answer.

[0572] The analyzed question data and the emotion recognition results from the emotion engine are input into a natural language processing model, which uses pre-trained data to understand the intent of the question and generate an appropriate answer.

[0573] 5. The server generates a response, which is sent to the device and displayed.

[0574] The answer generated by the natural language processing model is converted back into a message format and sent to the device. The device displays the received message to the user, who can then check it and use it in their work.

[0575] Specific examples

[0576] Example user questions

[0577] User: "What is the availability of this item?"

[0578] System processing flow

[0579] 1. Terminal: The user types a message such as "Please tell me the stock status of this item" and clicks the send button.

[0580] 2. Server: After receiving the query data sent from the terminal, it analyzes its contents.

[0581] 3. Server:

[0582] The emotion engine analyzes the user's emotions from the question, for example recognizing that the user is anxious.

[0583] The natural language processing model is given the user's question and emotional information. For example, the model recognizes that the question is about "stock availability" and that the user is anxious.

[0584] 4. Server:

[0585] The natural language processing model generates an appropriate answer based on the question and emotional information.

[0586] For example, information such as "We have it in stock" can be obtained from an inventory management database, and a reply message such as "It's okay. This item is currently in stock" can be created based on that information. The reply is provided in a tone that will ease the user's impatience.

[0587] 5. Server: The generated response message is converted back into a message format and sent to the user's device via the LINE API.

[0588] 6. Terminal: The received response message "It's OK. This item is currently in stock." is displayed to the user.

[0589] 7. User: Check the displayed answers and proceed with the task based on them.

[0590] In this way, by combining the system of the present invention with an emotion engine, it is possible to respond in a detailed manner according to the user's emotions, which not only allows for quick and accurate resolution of questions but also increases user satisfaction, making it possible to provide an environment in which users can carry out their work with peace of mind.

[0591] The processing flow will be explained below.

[0592] Step 1:

[0593] A user opens the LINE app on their device and enters a question or problem. For example, the user enters "Please tell me the stock status of this product." and clicks the send button.

[0594] Step 2:

[0595] The device receives the user's input and sends it to the server via the LINE API. The data sent includes the user ID and message content.

[0596] Step 3:

[0597] The server receives a message from the user via the LINE API. The received data is in the format {"userId": "12345", "message": "Please let me know the stock status of this product."}, for example.

[0598] Step 4:

[0599] In order to analyze the contents of the message received by the server, preprocessing such as tokenization and stop word removal is performed. For example, a message such as "Please tell me the stock status of this product" is analyzed and broken down into meaningful words.

[0600] Step 5:

[0601] The server inputs the preprocessed message into the emotion engine, which analyzes the user's emotion from the message text and returns the result. For example, the emotion engine may determine that the user is anxious.

[0602] Step 6:

[0603] The server receives the results from the emotion engine and inputs them into the natural language processing model. The natural language processing model analyzes the input question and emotional information to understand the intent of the question. For example, it detects that the keyword "stock status" is included.

[0604] Step 7:

[0605] The server references a related database based on the output of the natural language processing model, for example, accessing an inventory management database to obtain stock information for the specified product.

[0606] Step 8:

[0607] The server generates a response based on the information it has acquired and the results of the emotion engine. For example, it acquires information such as "In stock" from an inventory management database and uses that information to create a response message such as "It's OK. This item is currently in stock." This response includes a tone of voice to calm the user's impatience.

[0608] Step 9:

[0609] The server then converts the generated reply message back into a message format and sends it to the user's device via the LINE API. The data sent is in the following format, for example: {"replyToken": "TOKEN", "messages": [{"type": "text", "text": "No problem. This item is currently in stock."}]}

[0610] Step 10:

[0611] The device receives the reply message from the server, which is then displayed to the user on the LINE app.

[0612] Step 11:

[0613] The user checks the displayed response message, for example, "It's OK. This item is currently in stock," and proceeds with the task based on that message.

[0614] Example 2

[0615] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0616] In conventional systems, even when users input questions or problems, responses that do not reflect the emotional nuances of the question are not provided, resulting in low user satisfaction. Furthermore, because answers are generated based solely on the content of the question, it is difficult to provide a fast and appropriate service.

[0617] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0618] In this invention, the server includes means for a user to input and send a question using a terminal, means for the server to receive and analyze the question from the terminal, means for the server to analyze the question data with an emotion engine and recognize the user's emotion, means for the server to input the question and emotion analyzed by the server into a natural language processing model and generate an answer, and means for transmitting the answer generated by the server to the terminal and displaying it. This enables detailed responses according to the user's emotion and enables the provision of quick and accurate answers to questions.

[0619] A "user" is an entity that uses the system to enter questions and receive answers.

[0620] "Terminal" refers to an information and communication device that allows a user to input and send a question, and includes, for example, a smartphone or a personal computer.

[0621] A "server" is a computer device that receives and analyzes question data sent from a user's terminal, and generates and sends answers.

[0622] A "question" is a message about a question or problem that a user inputs and sends via a terminal.

[0623] "Reception" refers to the process in which the server receives question data sent from the user's terminal.

[0624] "Analysis" refers to the process in which the server understands the content of the question data received and extracts the necessary information.

[0625] The "emotion engine" is a software component that recognizes the user's emotions from the keywords and context contained in the question data.

[0626] "Emotion" refers to the psychological state that the user reflects in the question, and includes, for example, "joy," "sadness," and "impatience."

[0627] A "natural language processing model" is a model that uses artificial intelligence technology to generate appropriate answers based on analyzed question data and emotional information.

[0628] An "answer" is an appropriate response to a question that the server generates using a natural language processing model.

[0629] "Send" refers to the process of sending the response generated by the server to the user's terminal.

[0630] "Display" refers to the process of visually presenting the received answers on the user's terminal.

[0631] In this system, a user inputs a question using a terminal, the server receives and analyzes the question, generates an appropriate answer, and sends it back to the user's terminal, thereby quickly resolving the user's doubts and problems. A specific embodiment of this system will be described below.

[0632] System configuration

[0633] The system includes the following components:

[0634] 1. User device: Refers to the information and communication device that users use to input and send questions. Examples include smartphones and personal computers.

[0635] 2. Server: A central processing unit for analyzing questions received from user terminals and generating appropriate answers. The server includes the following major hardware and software components:

[0636] Receiving and analyzing module: receives and analyzes user question data.

[0637] Emotion Engine: A software component for recognizing user emotions from received question data.

[0638] Natural language processing model: A model that uses artificial intelligence techniques to generate answers based on analyzed question data and emotional information. Specific examples include generative AI models such as GPT-3.

[0639] Transmission module: Transmits the generated answer to the user terminal.

[0640] 3. Database: A storage device that stores necessary information and references it when generating answers to questions.

[0641] Data processing flow

[0642] 1. User enters question and submits it

[0643] The user opens a chat application on a device (e.g., a smartphone or a PC) and enters a question in text format. For example, the user sends a message such as, "Please tell me the stock status of this product."

[0644] 2. The server receives and analyzes the user's question.

[0645] The server receives the question data sent from the device. It then analyzes the received data and extracts the question content, user ID, etc. The analysis results are stored in an internal database as structured data.

[0646] 3. The server analyzes the question using an emotion engine

[0647] The server passes the question data to the emotion engine to recognize the user's emotion. The emotion engine determines emotions such as "joy," "sadness," and "impatience" based on the keywords and context contained in the question. For example, the emotion engine determines that the user is impatient based on the content of the question.

[0648] 4. The server passes the question to a natural language processing model to generate an answer

[0649] The server inputs the analyzed question data and emotion recognition results into a natural language processing model (e.g., GPT-3), which then generates an appropriate answer based on this data.

[0650] Example prompt: "The user is asking, 'What is the availability of this item?' They also seem impatient. Please generate a response in the appropriate tone."

[0651] 5. The server generates a response, which is sent to the device and displayed.

[0652] The server converts the generated response into a message format and sends it to the user's device via LINE's API, etc. The device displays the received response message to the user, who then confirms it and continues working.

[0653] Specific example explanation

[0654] For example, if a user sends a question via the LINE app, such as "Please tell me the stock status of this item," the server receives the question, analyzes its content, and uses its emotion engine to recognize the user's emotion as "anxious." Based on the information "In stock," the server generates a response in a reassuring tone, "Don't worry. This item is currently in stock," using the GPT-3 model. This response is then sent to the user in the form of a LINE message, and the device displays the message to the user. The user can then confirm the displayed response and continue their work based on it.

[0655] In this way, by generating answers that take the user's feelings into consideration, this system is able to improve user satisfaction and provide quick and accurate solutions to questions.

[0656] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0657] Step 1:

[0658] User enters question and submits it

[0659] Specific actions: The user opens a chat application on a device such as a smartphone or PC and enters their question or problem in text format. They type, "Please tell me the stock status of this product," and clicks the send button.

[0660] Input: The question text entered by the user

[0661] Output: Sending query data from the terminal to the server

[0662] Step 2:

[0663] The server receives and analyzes the user's question.

[0664] Specific operation: The server receives the question data sent from the device. The server analyzes the received data to extract the user ID and question content. For example, it extracts the user_id and text from the JSON format message and stores them in an internal database.

[0665] Input: Question data sent from the terminal

[0666] Output: Extract user ID and question content, store in database

[0667] Step 3:

[0668] The server analyzes the question using an emotion engine

[0669] Specific operation: The server passes the received question data to the emotion engine, which analyzes the user's emotions. The emotion engine determines emotions such as "joy," "sadness," and "impatience" from the content of the question text. For example, from the text "Please tell me the stock status of this product," it recognizes that the user is impatient.

[0670] Input: Parsed question content

[0671] Output: Emotion data as the analysis result (e.g., {"emotion": "anxious"})

[0672] Step 4:

[0673] The server passes the question to a natural language processing model to generate an answer.

[0674] Specific operation: The server inputs the analyzed question data and the emotion recognition results into a natural language processing model. The natural language processing model (e.g., GPT-3) generates an appropriate answer based on the prompt sentence.

[0675] Example prompt: A specific prompt used for the interaction is, "The user is asking, 'What is the availability of this item?' and seems impatient. Please generate a response in an appropriate tone."

[0676] Input: Question content and emotion data

[0677] Output: Answer text generated from the natural language processing model (e.g., "No problem. This item is currently in stock.")

[0678] Step 5:

[0679] The server generates a response, which is sent to the device and displayed.

[0680] Specific operation: The server converts the generated response text into a message format and sends it to the user's device via the LINE API. The user's device displays the received message.

[0681] Input: Generated answer text

[0682] Output: Send and display the reply message to the user's terminal

[0683] This process allows users to receive prompt and appropriate responses, and in the process, it is possible to respond in a way that takes into consideration the user's feelings.

[0684] (Application example 2)

[0685] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0686] Conventional content delivery services provide uniform answers and recommendations without considering the user's emotions, resulting in low user satisfaction. When a user is in a specific emotional state, content appropriate for that emotion is often not provided, so there is a need to improve the user experience.

[0687] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input and send a question using a terminal; means for the server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; means for the server to recognize the user's emotion based on the user's question; and means for passing the emotion recognition result to the natural language processing model and generating an optimal answer according to the user's emotion. This makes it possible to deliver optimal content according to the user's emotion.

[0688] A "terminal" is an electronic device that a user uses to enter and submit a question.

[0689] A "server" is a computer system that receives queries from users and analyzes and processes the queries.

[0690] A "question" is information or a question that a user inputs through a terminal.

[0691] A "natural language processing model" is an artificial intelligence technology that analyzes text data written in natural language and generates appropriate answers.

[0692] An "answer" is a response generated in response to a question, which contains information that is useful to the user.

[0693] "Emotion recognition" is a method of analyzing and identifying a user's emotional state from the content of the question entered by the user.

[0694] An "information database" is a system or storage device that stores data or information related to a query.

[0695] A system for implementing this invention includes a means for a user to input and send a question using a terminal, a server to receive and analyze the question, generate an answer using a natural language processing model, and send the answer to the terminal for display. Meanwhile, the server further has a means for recognizing emotions based on the user's question, and generates an optimal answer using the natural language processing model based on the recognition results.

[0696] System Configuration

[0697] Device: The device through which the user enters the question. Examples include a smartphone or tablet.

[0698] Server: Responsible for receiving questions, analyzing them, performing emotion recognition, and inputting them into a natural language processing model to generate answers.

[0699] Natural language processing model: Uses a pre-trained model (e.g., GPT-3) to generate appropriate answers based on the input question and sentiment information.

[0700] Emotion recognition engine: Analyzes the emotions expressed by the user's questions and identifies emotions such as joy, sadness, or impatience.

[0701] Software processing and data calculations

[0702] When the server receives a question, it first analyzes the user's emotions using an emotion recognition engine. For example, it uses the Transformers library to run an emotion analysis model. Next, based on the analysis results, it inputs the prompt sentence into a natural language processing model to generate the optimal answer. In this process, a generative AI model (e.g., GPT-3) is used.

[0703] After generating the answer, the server sends it to the user's device, which displays it in the form of a message. For example, if a user asks, "Tell me a movie that will help me relax today," the emotion recognition engine analyzes the emotion "I want to relax," and the natural language processing model generates the answer, "Currently, the movie that is recommended for relaxation is 'Your Name.' Why don't you watch it?"

[0704] Usage example

[0705] For example, use the following prompt:

[0706] User Question: "What movie can I watch to relax today?"

[0707] Example prompt: "The user's emotion is wanting to relax, and the question is 'What movie would make me relax today?'"

[0708] This prompt is then fed into a natural language processing model to generate the most appropriate answer for the user, such as "There's a movie called 'Your Name.' that's relaxing. Why don't you check it out?"

[0709] As a result, it is possible to provide the most appropriate answer according to the user's emotions, which is expected to improve the user experience.

[0710] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0711] Step 1:

[0712] The user uses the device to input and send a question. For example, the user inputs "Tell me a relaxing movie to watch today" into a smartphone application and clicks the send button. This input is sent from the device to the server.

[0713] Step 2:

[0714] The server receives the question sent from the terminal. The server analyzes the question data and extracts the user ID and question content. In this step, the question content is provided as input data, and the analyzed question information is obtained as output data.

[0715] Step 3:

[0716] The server passes the question to an emotion recognition engine to analyze the user's emotion. The emotion recognition engine identifies the emotion from the context of the question. Specifically, emotion analysis is performed using the Transformers library. For example, it detects the emotion "I want to relax." The input for this step is the question, and the output is the user's emotional information.

[0717] Step 4:

[0718] The server creates a prompt sentence based on the emotional information and the analyzed question content and inputs it into the natural language processing model. For example, the prompt sentence might be, "The user's emotional state is that they want to relax, and the question is, 'Tell me a relaxing movie to watch today.'" This prompt sentence is passed to a generative AI model (e.g., GPT-3). The inputs to this step are the question content and emotional information, and the output is the prompt sentence.

[0719] Step 5:

[0720] The natural language processing model generates an answer based on the prompt sentence. The generative AI model uses pre-trained data to generate an appropriate answer based on the user's question and emotions. For example, it generates the answer, "Currently, 'Your Name' is a relaxing movie. Why don't you watch it?" The input of this step is the prompt sentence, and the output is the generated answer.

[0721] Step 6:

[0722] The server sends the generated answer to the terminal. The server converts the generated answer into a message format and sends it to the terminal. The input of this step is the generated answer, and the output is data in message format.

[0723] Step 7:

[0724] The device displays the received answer to the user. For example, a message such as "Currently, 'Your Name' is available as a relaxing movie. Why not check it out?" is displayed. The user checks the displayed message and takes the corresponding action. The input of this step is data in the form of a message, and the output is information acquired by the user's visual recognition.

[0725] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0726] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0727] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0728] [Third embodiment]

[0729] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0730] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0731] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0732] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0733] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0734] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0735] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0736] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0737] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0738] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0739] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0740] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0741] The present invention is a system that includes a means for a user to input and send a question using a terminal, a means for a server to receive and analyze the question from the terminal, a means for inputting the question analyzed by the server into a natural language processing model and generating an answer, and a means for transmitting the answer generated by the server to the terminal and displaying it.

[0742] Description of the embodiment

[0743] 1. User enters and submits a question

[0744] The user enters a question or problem that arises during work into a device (e.g., the LINE app on a smartphone) and clicks the send button. For example, to send a question such as, "Please tell me the stock status of this product."

[0745] 2. The server receives and analyzes the user's question.

[0746] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and the question content.

[0747] 3. The server passes the question to a natural language processing model to generate an answer.

[0748] The analyzed question data is passed to a natural language processing model on the server. The natural language processing model understands the intent of the question based on pre-trained data and generates an appropriate answer. At this time, it may refer to a database to obtain information as needed.

[0749] 4. The server generates a response, which is sent to the device and displayed.

[0750] The answer generated by the natural language processing model is converted back into a message format and sent to the device. The device displays the received message to the user, who can then check it and use it in their work.

[0751] Specific examples

[0752] Example user questions

[0753] User: "What is the availability of this item?"

[0754] System processing flow

[0755] 1. Terminal: The user types a message such as "Please tell me the stock status of this item" and clicks the send button.

[0756] 2. Server: After receiving the query data sent from the terminal, it analyzes its contents.

[0757] 3. Server:

[0758] Pass the question "What is the stock status of this product?" to the natural language processing model.

[0759] Natural language processing models understand the intent of the question and retrieve inventory information from a database as needed.

[0760] For example, generate a response such as "This item is currently in stock."

[0761] 4. Server: Converts the generated answer into a message format and sends it to the terminal.

[0762] 5. Terminal: Display the received response message "This product is currently in stock" to the user.

[0763] 6. User: Check the displayed answers and proceed with the task based on them.

[0764] In this way, the system of the present invention allows users to easily input questions and receive quick answers, which helps improve work efficiency. It also reduces the time spent requesting other crew members, thereby reducing the burden on the call center.

[0765] The processing flow will be explained below.

[0766] Step 1:

[0767] A user opens the LINE app on their device and enters a question or problem. For example, the user enters "Please tell me the stock status of this product." and clicks the send button.

[0768] Step 2:

[0769] The device receives the user's input and sends it to the server via the LINE API. The data sent includes the user ID and message content.

[0770] Step 3:

[0771] The server receives a message from the user via the LINE API. The received data is in the format {"userId": "12345", "message": "Please let me know the stock status of this product."}, for example.

[0772] Step 4:

[0773] The server analyzes the contents of the received message. This analysis includes preprocessing such as tokenization and removal of stop words. For example, the message "Please tell me the stock status of this product" is analyzed and broken down into meaningful words.

[0774] Step 5:

[0775] The server inputs the preprocessed message into a natural language processing model, which analyzes the input message and understands the intent of the question. For example, it detects the presence of the keyword "stock status" in the message.

[0776] Step 6:

[0777] The server references a related database based on the output of the natural language processing model, for example, accessing an inventory management database to obtain stock information for the specified product.

[0778] Step 7:

[0779] The server generates a response based on the information it has obtained. For example, it obtains information such as "In stock" from an inventory management database and uses that information to create a response message such as "This product is currently in stock."

[0780] Step 8:

[0781] The server then converts the generated reply message back into a message format and sends it to the user's device via the LINE API. The data sent is in the following format, for example: {"replyToken": "TOKEN", "messages": [{"type": "text", "text": "This product is currently in stock."}]}.

[0782] Step 9:

[0783] The device receives the reply message from the server, which is then displayed to the user on the LINE app.

[0784] Step 10:

[0785] The user checks the displayed response message, for example, "This product is currently in stock," and proceeds with the task based on that message.

[0786] Example 1

[0787] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0788] In recent years, users have been demanding quick and efficient access to information, but conventional systems often require complex and time-consuming processes to obtain appropriate answers to questions. Furthermore, there is a problem in that it is difficult to provide appropriate and satisfactory answers to questions entered by users.

[0789] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0790] In this invention, the server includes means for a user to input and send a question using an information processing device, means for the server to receive and analyze the question from the information processing device, means for inputting the analyzed question into a generative AI model, constructing a prompt sentence, and generating an answer, and means for transmitting the generated answer to the information processing device and displaying it, thereby enabling a user to automatically obtain a quick and accurate answer to a question input by the user.

[0791] A "user" is an individual or organization that utilizes an information system to enter questions and obtain information.

[0792] An "information processing device" is a device that allows a user to input and send a question, and includes devices such as smartphones, tablets, and personal computers.

[0793] The "server" is a central processing unit that receives and analyzes a user's question, generates an answer using a generative AI model, and transmits the answer to an information processing device.

[0794] A "question" is the content of an inquiry that a user inputs into an information processing device to obtain information and that is sent to a server.

[0795] "Analysis" refers to the process by which the server understands the content of the question received and the generative AI model generates an appropriate answer.

[0796] A "generative AI model" is an algorithm or system that uses natural language processing techniques to generate appropriate answers to user questions.

[0797] A "prompt" is an instructional sentence that inputs the analyzed question content into a generative AI model, providing hints and context for the model to generate an answer.

[0798] An "answer" is information generated by a generative AI model based on a user's question, and is a message containing the information the user is looking for.

[0799] A "data resource" is a storage location for information that a generative AI model references when generating answers, including databases and knowledge bases.

[0800] The "message format" refers to the format of the response sent from the server to the information processing device, and refers to text or graphics displayed in a form that is visually easy for the user to recognize.

[0801] The present invention is a system in which a user inputs and sends a question using an information processing device. This system includes a function in which a server receives the question from the user's information processing device, analyzes it, generates an answer using a generative AI model, and sends the answer to the user's information processing device for display. Specific details of the use of the specific hardware and software, as well as the specific data processing and data calculation, are described below.

[0802] Hardware and software used

[0803] Information processing equipment:

[0804] Using devices such as smartphones, tablets, and computers, users can easily enter and submit questions anytime, anywhere.

[0805] server:

[0806] The server is a central processing unit that receives and analyzes questions, generates answers using a generative AI model, and transmits the generated answers. The server is equipped with a high-performance CPU and memory, allowing it to quickly perform complex data processing.

[0807] Generative AI models:

[0808] These are algorithms that use natural language processing technology, such as BERT (Bidirectional Encoder Representations from Transformers) and GPT-3 (Generative Pre-trained Transformer 3). These models are pre-trained using large datasets, enabling advanced question answering.

[0809] Specific details of data processing and data calculation

[0810] 1. User enters and submits a question:

[0811] Users use information processing devices such as smartphones and PCs to input questions or problems that arise in their daily work or life. For example, a user launches the LINE app, types a message such as "Please tell me the stock status of this product," and clicks the send button. This operation sends the input question to the server.

[0812] 2. Receiving and parsing questions:

[0813] The server receives the HTTP request sent from the information processing device and parses the question data in JSON format. As a result, the user ID and question content are extracted. For example, the analysis may yield the question "User 12345 sent the question 'Please tell me the stock status of this product.'"

[0814] 3. Building input prompts for the generative AI model:

[0815] The server constructs a prompt sentence to be posed to the generative AI model based on the analyzed question content. The prompt sentence includes the question content as well as the necessary context information. For example, a prompt sentence such as "I want to know inventory information. Please tell me the inventory status of this product." is generated.

[0816] 4. Answer generation using generative AI models:

[0817] The constructed prompt is input to a generative AI model (e.g., GPT-3). The model analyzes the prompt and generates an appropriate response. For example, the text generated is "This item is currently in stock."

[0818] 5. Submitting and Viewing Answers:

[0819] The server receives the generated response and converts it into a message format. The converted message is parsed again into JSON format and sent to the information processing device as an HTTP response. The information processing device analyzes this message and displays on the screen the message "This product is currently in stock."

[0820] Specific examples

[0821] Example user questions:

[0822] User: "What is the availability of this item?"

[0823] System process flow:

[0824] 1. User: Opens the LINE app on their smartphone, types "Please let me know the stock status of this product," and clicks the send button.

[0825] 2. Server: Analyze the received question and record it as "Question from user 12345: 'Please tell me the stock status of this product.'"

[0826] 3. Server: Based on the analysis results, generate a prompt sentence such as "I want to know the inventory information. Please tell me the inventory status of this product." and pass it to the generative AI model.

[0827] 4. Generative AI model: Analyzes the prompt and generates the answer, "This item is currently in stock."

[0828] 5. Server: Sends the generated answer to the information processing device, which displays the answer to the user.

[0829] This allows users to easily send questions from their devices and receive instant answers, improving work efficiency and reducing the burden on other members and the support center.

[0830] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0831] Step 1:

[0832] User enters a question

[0833] User: Using an information processing device (such as a smartphone or computer), enter a question into the message input field on the screen.

[0834] Specific operation: For example, a user opens the LINE app, types a message such as "Please let me know the stock status of this product," and clicks the send button.

[0835] Input: The text "What is the availability of this item?"

[0836] Output: The action of clicking the submit button and submitting the question.

[0837] Step 2:

[0838] The device sends a question

[0839] Terminal: Holds and transmits questions entered by the user.

[0840] Specific behavior: The entered text is converted into JSON format data and sent to the server as an HTTP request.

[0841] Input: The question text entered by the user.

[0842] Output: The question is converted to JSON format and sent to the server as an HTTP request.

[0843] Step 3:

[0844] The server receives and analyzes the question

[0845] Server: Receives the HTTP request sent from the device and parses the question data in JSON format.

[0846] Specific operation: Analyze the received data and extract the user ID and question. The analysis results in "User 12345 sent the question 'Please tell me the stock status of this product.'"

[0847] Input: HTTP request sent from the terminal (question data in JSON format).

[0848] Output: Extracted user ID and question.

[0849] Step 4:

[0850] The server constructs a prompt

[0851] Server: Based on the extracted question content, constructs a prompt sentence to be input into the generative AI model.

[0852] What it does: The natural language processing model converts the question into a format that is easy to understand. The prompt generated is, "I want to know about inventory. Please tell me the inventory status of this product."

[0853] Input: The extracted question content.

[0854] Output: The generated prompt statement.

[0855] Step 5:

[0856] The server inputs a prompt to the generative AI model.

[0857] Server: The constructed prompt sentence is input to the generative AI model, which uses pre-trained data to generate an appropriate answer to the question.

[0858] What happens: The prompt is passed to a generative AI model (e.g., GPT-3), which parses the prompt and generates the answer, "This item is currently in stock."

[0859] Input: The generated prompt statement.

[0860] Output: The answer generated by the generative AI model.

[0861] Step 6:

[0862] The server sends the answer

[0863] Server: Converts the generated response back into a message format and sends it to the information processing device.

[0864] Specific operation: The generated answer is sent to the information processing device as an HTTP response. "Send the answer 'This product is currently in stock' to user 12345."

[0865] Input: The generated answer.

[0866] Output: The answer, formatted as a message, sent as an HTTP response.

[0867] Step 7:

[0868] The device displays the answer

[0869] Terminal: Parse the response received from the server in JSON format and display it on the screen.

[0870] What happens: A message will appear on the screen saying "This item is currently in stock."

[0871] Input: The answer sent as an HTTP response.

[0872] Output: Messages that are displayed on the screen.

[0873] (Application example 1)

[0874] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0875] In autonomous vehicles, passengers need to be able to quickly and easily obtain information about the vehicle and its real-time status. However, conventional systems have limited means for passengers to ask questions about the vehicle's status and route information and receive answers, resulting in a lack of convenience. Furthermore, many systems do not support voice input or real-time data reference, which has hindered the user experience. Therefore, a system that allows passengers to efficiently obtain information while in the vehicle is needed.

[0876] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0877] In this invention, the server includes: means for a user to input and send a question using a terminal; means for the server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; means for inputting a question regarding the vehicle's status or route information using an in-vehicle display or a smartphone and converting the voice input into text using voice recognition software; means for referencing the vehicle's internal database in real time, obtaining information about the nearest facility using GPS data, and generating an answer; and means for returning the generated answer to the user in voice or text format. This enables passengers to efficiently obtain the information they need in an autonomous vehicle in real time, significantly improving convenience.

[0878] A "user" is an operator of a terminal that utilizes the system to input information and make requests to obtain answers.

[0879] A "terminal" is a device used by a user to input and send a question, and includes a smartphone, tablet, in-vehicle display, etc.

[0880] A "server" is a computer system that analyzes questions received from a terminal, generates answers using a natural language processing model, and sends them back to the terminal.

[0881] A "natural language processing model" is a machine learning and data analysis algorithm or model used to analyze natural language questions posed by users and generate appropriate answers.

[0882] A "question" is text or voice data that a user enters to obtain specific information.

[0883] An "answer" is text or audio data of information that the server generates using a natural language processing model and provides to the user.

[0884] "Speech recognition software" is a program that captures, analyzes, and converts voice input into text.

[0885] "Real-time" is the time frame in which a system acquires, processes, and provides data almost immediately.

[0886] An "in-vehicle display" is a screen that is installed in a vehicle and is used by the user to display and input information.

[0887] A "database" is a collection of information that stores the data required based on a question and that a natural language processing model references to generate an answer.

[0888] "GPS Data" means location information that includes satellite information for identifying a specific location on Earth.

[0889] To implement this invention, it is necessary to provide a system that allows a user to input and send a question using a terminal, a server that receives and analyzes the question from the terminal, a server that inputs the analyzed question into a natural language processing model to generate an answer, and a system that transmits the answer generated by the server to the terminal and displays it. A specific embodiment of this is described below.

[0890] User Interface

[0891] Users can use their smartphone, tablet, or in-car display to type and submit their question. When using voice input, a microphone in the vehicle captures the voice and converts it into text through speech recognition software (e.g., Google Cloud Speech-to-Text API).

[0892] Server Processing

[0893] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and question content. The server then passes the question data to a natural language processing model (e.g., the BERT model using TensorFlow) to analyze the intent and generate an appropriate answer. If necessary, the server references the vehicle's internal database to obtain real-time information (e.g., the vehicle's current speed and location).

[0894] Generate and reply to answers

[0895] The server converts the generated response back into a message format and sends it to the device. The device then displays the received message to the user. If a voice response is desired, the generated text is converted into speech (e.g., using the Google Cloud Text-to-Speech API) and played over the car's speakers.

[0896] Specific examples

[0897] Consider a case where a user types "How far is the next gas station?" into the in-car display and clicks the send button. The server receives and analyzes this question. The analyzed question is passed to a natural language processing model to understand the intent and obtain the necessary data (in this case, distance information using GPS). The server calculates the distance to the nearest gas station and generates an answer, "The distance to the next gas station is 5 km," which is sent back to the user. The user can then check this information on the in-car display and decide what to do next.

[0898] Prompt Sentence Examples

[0899] "What's your current speed?"

[0900] "How far is the next gas station?"

[0901] "How's the weather?"

[0902] This will enable users to obtain the information they need in real time and efficiently while in an autonomous vehicle, significantly improving convenience.

[0903] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0904] Step 1:

[0905] The user uses the device to input and send a question. The user inputs the question into a smartphone app or on the in-car display using text or voice. For example, the user might type, "How far is the next gas station?" and press the send button. In the case of voice input, the vehicle's microphone captures the voice and converts it into a string of characters using speech recognition software (e.g., Google Cloud Speech-to-Text API). The input is the question data in text format, and the output is the data to be sent to the server.

[0906] Step 2:

[0907] The server receives and analyzes the question from the terminal. The server analyzes the question data received from the terminal and extracts the user ID and question content. For example, a question such as "How far is the next gas station?" arrives in text format at the server. The input is the question data received from the terminal, and the output is the analyzed question data.

[0908] Step 3:

[0909] The server inputs the parsed question into a natural language processing model to generate an answer. The server inputs the parsed question data into a natural language processing model (e.g., a BERT model using TensorFlow) to understand the intent of the question. It then references the vehicle's internal database as needed to obtain real-time data. For example, it uses the vehicle's current location to calculate the distance to the nearest gas station. The input is the parsed question data, and the output is the generated answer data.

[0910] Step 4:

[0911] The answer generated by the server is sent to the terminal and displayed. The server then converts the answer generated by the natural language processing model back into a message format and sends it to the terminal. For example, an answer such as "The distance to the next gas station is 5 km" is generated and sent to the terminal. The input is the generated answer data, and the output is the data sent to the terminal.

[0912] Step 5:

[0913] The device displays the received response message to the user. The device then displays the received message to the user. If voice response is also used, the generated text is converted into speech (e.g., Google Cloud Text-to-Speech API) and played from the car's speakers. For example, a response such as "The distance to the next gas station is 5 km" is displayed on the car's display and simultaneously played aloud. The input is the response data sent to the device, and the output is the display and audio playback data for the user.

[0914] This allows users to efficiently obtain the information they need in real time while in an autonomous vehicle, significantly improving convenience.

[0915] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0916] The present invention is a system including: means for a user to input and send a question using a terminal; means for a server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; and an emotion engine that recognizes the user's emotions based on the content of the question input by the user.

[0917] Description of the embodiment

[0918] 1. User enters and submits a question

[0919] The user enters a question or problem that arises during work into a device (e.g., the LINE app on a smartphone) and clicks the send button. For example, to send a question such as, "Please tell me the stock status of this product."

[0920] 2. The server receives and analyzes the user's question.

[0921] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and the question content.

[0922] 3. The server analyzes the question using an emotion engine

[0923] The server recognizes the user's emotions from the words and context of the user's question. For example, the emotion engine may detect that the user is feeling "frustrated" based on the tone and context of the question.

[0924] 4. The server passes the question to a natural language processing model to generate an answer.

[0925] The analyzed question data and the emotion recognition results from the emotion engine are input into a natural language processing model, which uses pre-trained data to understand the intent of the question and generate an appropriate answer.

[0926] 5. The server generates a response, which is sent to the device and displayed.

[0927] The answer generated by the natural language processing model is converted back into a message format and sent to the device. The device displays the received message to the user, who can then check it and use it in their work.

[0928] Specific examples

[0929] Example user questions

[0930] User: "What is the availability of this item?"

[0931] System processing flow

[0932] 1. Terminal: The user types a message such as "Please tell me the stock status of this item" and clicks the send button.

[0933] 2. Server: After receiving the query data sent from the terminal, it analyzes its contents.

[0934] 3. Server:

[0935] The emotion engine analyzes the user's emotions from the question, for example recognizing that the user is anxious.

[0936] The natural language processing model is given the user's question and emotional information. For example, the model recognizes that the question is about "stock availability" and that the user is anxious.

[0937] 4. Server:

[0938] The natural language processing model generates an appropriate answer based on the question and emotional information.

[0939] For example, information such as "We have it in stock" can be obtained from an inventory management database, and a reply message such as "It's okay. This item is currently in stock" can be created based on that information. The reply is provided in a tone that will ease the user's impatience.

[0940] 5. Server: The generated response message is converted back into a message format and sent to the user's device via the LINE API.

[0941] 6. Terminal: The received response message "It's OK. This item is currently in stock." is displayed to the user.

[0942] 7. User: Check the displayed answers and proceed with the task based on them.

[0943] In this way, by combining the system of the present invention with an emotion engine, it is possible to respond in a detailed manner according to the user's emotions, which not only allows for quick and accurate resolution of questions but also increases user satisfaction, making it possible to provide an environment in which users can carry out their work with peace of mind.

[0944] The processing flow will be explained below.

[0945] Step 1:

[0946] A user opens the LINE app on their device and enters a question or problem. For example, the user enters "Please tell me the stock status of this product." and clicks the send button.

[0947] Step 2:

[0948] The device receives the user's input and sends it to the server via the LINE API. The data sent includes the user ID and message content.

[0949] Step 3:

[0950] The server receives a message from the user via the LINE API. The received data is in the format {"userId": "12345", "message": "Please let me know the stock status of this product."}, for example.

[0951] Step 4:

[0952] In order to analyze the contents of the message received by the server, preprocessing such as tokenization and stop word removal is performed. For example, a message such as "Please tell me the stock status of this product" is analyzed and broken down into meaningful words.

[0953] Step 5:

[0954] The server inputs the preprocessed message into the emotion engine, which analyzes the user's emotion from the message text and returns the result. For example, the emotion engine may determine that the user is anxious.

[0955] Step 6:

[0956] The server receives the results from the emotion engine and inputs them into the natural language processing model. The natural language processing model analyzes the input question and emotional information to understand the intent of the question. For example, it detects that the keyword "stock status" is included.

[0957] Step 7:

[0958] The server references a related database based on the output of the natural language processing model, for example, accessing an inventory management database to obtain stock information for the specified product.

[0959] Step 8:

[0960] The server generates a response based on the information it has acquired and the results of the emotion engine. For example, it acquires information such as "In stock" from an inventory management database and uses that information to create a response message such as "It's OK. This item is currently in stock." This response includes a tone of voice to calm the user's impatience.

[0961] Step 9:

[0962] The server then converts the generated reply message back into a message format and sends it to the user's device via the LINE API. The data sent is in the following format, for example: {"replyToken": "TOKEN", "messages": [{"type": "text", "text": "No problem. This item is currently in stock."}]}

[0963] Step 10:

[0964] The device receives the reply message from the server, which is then displayed to the user on the LINE app.

[0965] Step 11:

[0966] The user checks the displayed response message, for example, "It's OK. This item is currently in stock," and proceeds with the task based on that message.

[0967] Example 2

[0968] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0969] In conventional systems, even when users input questions or problems, responses that do not reflect the emotional nuances of the question are not provided, resulting in low user satisfaction. Furthermore, because answers are generated based solely on the content of the question, it is difficult to provide a fast and appropriate service.

[0970] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0971] In this invention, the server includes means for a user to input and send a question using a terminal, means for the server to receive and analyze the question from the terminal, means for the server to analyze the question data with an emotion engine and recognize the user's emotion, means for the server to input the question and emotion analyzed by the server into a natural language processing model and generate an answer, and means for transmitting the answer generated by the server to the terminal and displaying it. This enables detailed responses according to the user's emotion and enables the provision of quick and accurate answers to questions.

[0972] A "user" is an entity that uses the system to enter questions and receive answers.

[0973] "Terminal" refers to an information and communication device that allows a user to input and send a question, and includes, for example, a smartphone or a personal computer.

[0974] A "server" is a computer device that receives and analyzes question data sent from a user's terminal, and generates and sends answers.

[0975] A "question" is a message about a question or problem that a user inputs and sends via a terminal.

[0976] "Reception" refers to the process in which the server receives question data sent from the user's terminal.

[0977] "Analysis" refers to the process in which the server understands the content of the question data received and extracts the necessary information.

[0978] The "emotion engine" is a software component that recognizes the user's emotions from the keywords and context contained in the question data.

[0979] "Emotion" refers to the psychological state that the user reflects in the question, and includes, for example, "joy," "sadness," and "impatience."

[0980] A "natural language processing model" is a model that uses artificial intelligence technology to generate appropriate answers based on analyzed question data and emotional information.

[0981] An "answer" is an appropriate response to a question that the server generates using a natural language processing model.

[0982] "Send" refers to the process of sending the response generated by the server to the user's terminal.

[0983] "Display" refers to the process of visually presenting the received answers on the user's terminal.

[0984] In this system, a user inputs a question using a terminal, the server receives and analyzes the question, generates an appropriate answer, and sends it back to the user's terminal, thereby quickly resolving the user's doubts and problems. A specific embodiment of this system will be described below.

[0985] System configuration

[0986] The system includes the following components:

[0987] 1. User device: Refers to the information and communication device that users use to input and send questions. Examples include smartphones and personal computers.

[0988] 2. Server: A central processing unit for analyzing questions received from user terminals and generating appropriate answers. The server includes the following major hardware and software components:

[0989] Receiving and analyzing module: receives and analyzes user question data.

[0990] Emotion Engine: A software component for recognizing user emotions from received question data.

[0991] Natural language processing model: A model that uses artificial intelligence techniques to generate answers based on analyzed question data and emotional information. Specific examples include generative AI models such as GPT-3.

[0992] Transmission module: Transmits the generated answer to the user terminal.

[0993] 3. Database: A storage device that stores necessary information and references it when generating answers to questions.

[0994] Data processing flow

[0995] 1. User enters question and submits it

[0996] The user opens a chat application on a device (e.g., a smartphone or a PC) and enters a question in text format. For example, the user sends a message such as, "Please tell me the stock status of this product."

[0997] 2. The server receives and analyzes the user's question.

[0998] The server receives the question data sent from the device. It then analyzes the received data and extracts the question content, user ID, etc. The analysis results are stored in an internal database as structured data.

[0999] 3. The server analyzes the question using an emotion engine

[1000] The server passes the question data to the emotion engine to recognize the user's emotion. The emotion engine determines emotions such as "joy," "sadness," and "impatience" based on the keywords and context contained in the question. For example, the emotion engine determines that the user is impatient based on the content of the question.

[1001] 4. The server passes the question to a natural language processing model to generate an answer

[1002] The server inputs the analyzed question data and emotion recognition results into a natural language processing model (e.g., GPT-3), which then generates an appropriate answer based on this data.

[1003] Example prompt: "The user is asking, 'What is the availability of this item?' They also seem impatient. Please generate a response in the appropriate tone."

[1004] 5. The server generates a response, which is sent to the device and displayed.

[1005] The server converts the generated response into a message format and sends it to the user's device via LINE's API, etc. The device displays the received response message to the user, who then confirms it and continues working.

[1006] Specific example explanation

[1007] For example, if a user sends a question via the LINE app, such as "Please tell me the stock status of this item," the server receives the question, analyzes its content, and uses its emotion engine to recognize the user's emotion as "anxious." Based on the information "In stock," the server generates a response in a reassuring tone, "Don't worry. This item is currently in stock," using the GPT-3 model. This response is then sent to the user in the form of a LINE message, and the device displays the message to the user. The user can then confirm the displayed response and continue their work based on it.

[1008] In this way, by generating answers that take the user's feelings into consideration, this system is able to improve user satisfaction and provide quick and accurate solutions to questions.

[1009] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1010] Step 1:

[1011] User enters question and submits it

[1012] Specific actions: The user opens a chat application on a device such as a smartphone or PC and enters their question or problem in text format. They type, "Please tell me the stock status of this product," and clicks the send button.

[1013] Input: The question text entered by the user

[1014] Output: Sending query data from the terminal to the server

[1015] Step 2:

[1016] The server receives and analyzes the user's question.

[1017] Specific operation: The server receives the question data sent from the device. The server analyzes the received data to extract the user ID and question content. For example, it extracts the user_id and text from the JSON format message and stores them in an internal database.

[1018] Input: Question data sent from the terminal

[1019] Output: Extract user ID and question content, store in database

[1020] Step 3:

[1021] The server analyzes the question using an emotion engine

[1022] Specific operation: The server passes the received question data to the emotion engine, which analyzes the user's emotions. The emotion engine determines emotions such as "joy," "sadness," and "impatience" from the content of the question text. For example, from the text "Please tell me the stock status of this product," it recognizes that the user is impatient.

[1023] Input: Parsed question content

[1024] Output: Emotion data as the analysis result (e.g., {"emotion": "anxious"})

[1025] Step 4:

[1026] The server passes the question to a natural language processing model to generate an answer.

[1027] Specific operation: The server inputs the analyzed question data and the emotion recognition results into a natural language processing model. The natural language processing model (e.g., GPT-3) generates an appropriate answer based on the prompt sentence.

[1028] Example prompt: A specific prompt used for the interaction is, "The user is asking, 'What is the availability of this item?' and seems impatient. Please generate a response in an appropriate tone."

[1029] Input: Question content and emotion data

[1030] Output: Answer text generated from the natural language processing model (e.g., "No problem. This item is currently in stock.")

[1031] Step 5:

[1032] The server generates a response, which is sent to the device and displayed.

[1033] Specific operation: The server converts the generated response text into a message format and sends it to the user's device via the LINE API. The user's device displays the received message.

[1034] Input: Generated answer text

[1035] Output: Send and display the reply message to the user's terminal

[1036] This process allows users to receive prompt and appropriate responses, and in the process, it is possible to respond in a way that takes into consideration the user's feelings.

[1037] (Application example 2)

[1038] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1039] Conventional content delivery services provide uniform answers and recommendations without considering the user's emotions, resulting in low user satisfaction. When a user is in a specific emotional state, content appropriate for that emotion is often not provided, so there is a need to improve the user experience.

[1040] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input and send a question using a terminal; means for the server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; means for the server to recognize the user's emotion based on the user's question; and means for passing the emotion recognition result to the natural language processing model and generating an optimal answer according to the user's emotion. This makes it possible to deliver optimal content according to the user's emotion.

[1041] A "terminal" is an electronic device that a user uses to enter and submit a question.

[1042] A "server" is a computer system that receives queries from users and analyzes and processes the queries.

[1043] A "question" is information or a question that a user inputs through a terminal.

[1044] A "natural language processing model" is an artificial intelligence technology that analyzes text data written in natural language and generates appropriate answers.

[1045] An "answer" is a response generated in response to a question, which contains information that is useful to the user.

[1046] "Emotion recognition" is a method of analyzing and identifying a user's emotional state from the content of the question entered by the user.

[1047] An "information database" is a system or storage device that stores data or information related to a query.

[1048] A system for implementing this invention includes a means for a user to input and send a question using a terminal, a server to receive and analyze the question, generate an answer using a natural language processing model, and send the answer to the terminal for display. Meanwhile, the server further has a means for recognizing emotions based on the user's question, and generates an optimal answer using the natural language processing model based on the recognition results.

[1049] System Configuration

[1050] Device: The device through which the user enters the question. Examples include a smartphone or tablet.

[1051] Server: Responsible for receiving questions, analyzing them, performing emotion recognition, and inputting them into a natural language processing model to generate answers.

[1052] Natural language processing model: Uses a pre-trained model (e.g., GPT-3) to generate appropriate answers based on the input question and sentiment information.

[1053] Emotion recognition engine: Analyzes the emotions expressed by the user's questions and identifies emotions such as joy, sadness, or impatience.

[1054] Software processing and data calculations

[1055] When the server receives a question, it first analyzes the user's emotions using an emotion recognition engine. For example, it uses the Transformers library to run an emotion analysis model. Next, based on the analysis results, it inputs the prompt sentence into a natural language processing model to generate the optimal answer. In this process, a generative AI model (e.g., GPT-3) is used.

[1056] After generating the answer, the server sends it to the user's device, which displays it in the form of a message. For example, if a user asks, "Tell me a movie that will help me relax today," the emotion recognition engine analyzes the emotion "I want to relax," and the natural language processing model generates the answer, "Currently, the movie that is recommended for relaxation is 'Your Name.' Why don't you watch it?"

[1057] Usage example

[1058] For example, use the following prompt:

[1059] User Question: "What movie can I watch to relax today?"

[1060] Example prompt: "The user's emotion is wanting to relax, and the question is 'What movie would make me relax today?'"

[1061] This prompt is then fed into a natural language processing model to generate the most appropriate answer for the user, such as "There's a movie called 'Your Name.' that's relaxing. Why don't you check it out?"

[1062] As a result, it is possible to provide the most appropriate answer according to the user's emotions, which is expected to improve the user experience.

[1063] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1064] Step 1:

[1065] The user uses the device to input and send a question. For example, the user inputs "Tell me a relaxing movie to watch today" into a smartphone application and clicks the send button. This input is sent from the device to the server.

[1066] Step 2:

[1067] The server receives the question sent from the terminal. The server analyzes the question data and extracts the user ID and question content. In this step, the question content is provided as input data, and the analyzed question information is obtained as output data.

[1068] Step 3:

[1069] The server passes the question to an emotion recognition engine to analyze the user's emotion. The emotion recognition engine identifies the emotion from the context of the question. Specifically, emotion analysis is performed using the Transformers library. For example, it detects the emotion "I want to relax." The input for this step is the question, and the output is the user's emotional information.

[1070] Step 4:

[1071] The server creates a prompt sentence based on the emotional information and the analyzed question content and inputs it into the natural language processing model. For example, the prompt sentence might be, "The user's emotional state is that they want to relax, and the question is, 'Tell me a relaxing movie to watch today.'" This prompt sentence is passed to a generative AI model (e.g., GPT-3). The inputs to this step are the question content and emotional information, and the output is the prompt sentence.

[1072] Step 5:

[1073] The natural language processing model generates an answer based on the prompt sentence. The generative AI model uses pre-trained data to generate an appropriate answer based on the user's question and emotions. For example, it generates the answer, "Currently, 'Your Name' is a relaxing movie. Why don't you watch it?" The input of this step is the prompt sentence, and the output is the generated answer.

[1074] Step 6:

[1075] The server sends the generated answer to the terminal. The server converts the generated answer into a message format and sends it to the terminal. The input of this step is the generated answer, and the output is data in message format.

[1076] Step 7:

[1077] The device displays the received answer to the user. For example, a message such as "Currently, 'Your Name' is available as a relaxing movie. Why not check it out?" is displayed. The user checks the displayed message and takes the corresponding action. The input of this step is data in the form of a message, and the output is information acquired by the user's visual recognition.

[1078] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1079] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1080] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1081] [Fourth embodiment]

[1082] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1083] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1084] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1085] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1086] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1087] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1088] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1089] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1090] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1091] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1092] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1093] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1094] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1095] The present invention is a system that includes a means for a user to input and send a question using a terminal, a means for a server to receive and analyze the question from the terminal, a means for inputting the question analyzed by the server into a natural language processing model and generating an answer, and a means for transmitting the answer generated by the server to the terminal and displaying it.

[1096] Description of the embodiment

[1097] 1. User enters and submits a question

[1098] The user enters a question or problem that arises during work into a device (e.g., the LINE app on a smartphone) and clicks the send button. For example, to send a question such as, "Please tell me the stock status of this product."

[1099] 2. The server receives and analyzes the user's question.

[1100] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and the question content.

[1101] 3. The server passes the question to a natural language processing model to generate an answer.

[1102] The analyzed question data is passed to a natural language processing model on the server. The natural language processing model understands the intent of the question based on pre-trained data and generates an appropriate answer. At this time, it may refer to a database to obtain information as needed.

[1103] 4. The server generates a response, which is sent to the device and displayed.

[1104] The answer generated by the natural language processing model is converted back into a message format and sent to the device. The device displays the received message to the user, who can then check it and use it in their work.

[1105] Specific examples

[1106] Example user questions

[1107] User: "What is the availability of this item?"

[1108] System processing flow

[1109] 1. Terminal: The user types a message such as "Please tell me the stock status of this item" and clicks the send button.

[1110] 2. Server: After receiving the query data sent from the terminal, it analyzes its contents.

[1111] 3. Server:

[1112] Pass the question "What is the stock status of this product?" to the natural language processing model.

[1113] Natural language processing models understand the intent of the question and retrieve inventory information from a database as needed.

[1114] For example, generate a response such as "This item is currently in stock."

[1115] 4. Server: Converts the generated answer into a message format and sends it to the terminal.

[1116] 5. Terminal: Display the received response message "This product is currently in stock" to the user.

[1117] 6. User: Check the displayed answers and proceed with the task based on them.

[1118] In this way, the system of the present invention allows users to easily input questions and receive quick answers, which helps improve work efficiency. It also reduces the time spent requesting other crew members, thereby reducing the burden on the call center.

[1119] The processing flow will be explained below.

[1120] Step 1:

[1121] A user opens the LINE app on their device and enters a question or problem. For example, the user enters "Please tell me the stock status of this product." and clicks the send button.

[1122] Step 2:

[1123] The device receives the user's input and sends it to the server via the LINE API. The data sent includes the user ID and message content.

[1124] Step 3:

[1125] The server receives a message from the user via the LINE API. The received data is in the format {"userId": "12345", "message": "Please let me know the stock status of this product."}, for example.

[1126] Step 4:

[1127] The server analyzes the contents of the received message. This analysis includes preprocessing such as tokenization and removal of stop words. For example, the message "Please tell me the stock status of this product" is analyzed and broken down into meaningful words.

[1128] Step 5:

[1129] The server inputs the preprocessed message into a natural language processing model, which analyzes the input message and understands the intent of the question. For example, it detects the presence of the keyword "stock status" in the message.

[1130] Step 6:

[1131] The server references a related database based on the output of the natural language processing model, for example, accessing an inventory management database to obtain stock information for the specified product.

[1132] Step 7:

[1133] The server generates a response based on the information it has obtained. For example, it obtains information such as "In stock" from an inventory management database and uses that information to create a response message such as "This product is currently in stock."

[1134] Step 8:

[1135] The server then converts the generated reply message back into a message format and sends it to the user's device via the LINE API. The data sent is in the following format, for example: {"replyToken": "TOKEN", "messages": [{"type": "text", "text": "This product is currently in stock."}]}.

[1136] Step 9:

[1137] The device receives the reply message from the server, which is then displayed to the user on the LINE app.

[1138] Step 10:

[1139] The user checks the displayed response message, for example, "This product is currently in stock," and proceeds with the task based on that message.

[1140] Example 1

[1141] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1142] In recent years, users have been demanding quick and efficient access to information, but conventional systems often require complex and time-consuming processes to obtain appropriate answers to questions. Furthermore, there is a problem in that it is difficult to provide appropriate and satisfactory answers to questions entered by users.

[1143] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1144] In this invention, the server includes means for a user to input and send a question using an information processing device, means for the server to receive and analyze the question from the information processing device, means for inputting the analyzed question into a generative AI model, constructing a prompt sentence, and generating an answer, and means for transmitting the generated answer to the information processing device and displaying it, thereby enabling a user to automatically obtain a quick and accurate answer to a question input by the user.

[1145] A "user" is an individual or organization that utilizes an information system to enter questions and obtain information.

[1146] An "information processing device" is a device that allows a user to input and send a question, and includes devices such as smartphones, tablets, and personal computers.

[1147] The "server" is a central processing unit that receives and analyzes a user's question, generates an answer using a generative AI model, and transmits the answer to an information processing device.

[1148] A "question" is the content of an inquiry that a user inputs into an information processing device to obtain information and that is sent to a server.

[1149] "Analysis" refers to the process by which the server understands the content of the question received and the generative AI model generates an appropriate answer.

[1150] A "generative AI model" is an algorithm or system that uses natural language processing techniques to generate appropriate answers to user questions.

[1151] A "prompt" is an instructional sentence that inputs the analyzed question content into a generative AI model, providing hints and context for the model to generate an answer.

[1152] An "answer" is information generated by a generative AI model based on a user's question, and is a message containing the information the user is looking for.

[1153] A "data resource" is a storage location for information that a generative AI model references when generating answers, including databases and knowledge bases.

[1154] The "message format" refers to the format of the response sent from the server to the information processing device, and refers to text or graphics displayed in a form that is visually easy for the user to recognize.

[1155] The present invention is a system in which a user inputs and sends a question using an information processing device. This system includes a function in which a server receives the question from the user's information processing device, analyzes it, generates an answer using a generative AI model, and sends the answer to the user's information processing device for display. Specific details of the use of the specific hardware and software, as well as the specific data processing and data calculation, are described below.

[1156] Hardware and software used

[1157] Information processing equipment:

[1158] Using devices such as smartphones, tablets, and computers, users can easily enter and submit questions anytime, anywhere.

[1159] server:

[1160] The server is a central processing unit that receives and analyzes questions, generates answers using a generative AI model, and transmits the generated answers. The server is equipped with a high-performance CPU and memory, allowing it to quickly perform complex data processing.

[1161] Generative AI models:

[1162] These are algorithms that use natural language processing technology, such as BERT (Bidirectional Encoder Representations from Transformers) and GPT-3 (Generative Pre-trained Transformer 3). These models are pre-trained using large datasets, enabling advanced question answering.

[1163] Specific details of data processing and data calculation

[1164] 1. User enters and submits a question:

[1165] Users use information processing devices such as smartphones and PCs to input questions or problems that arise in their daily work or life. For example, a user launches the LINE app, types a message such as "Please tell me the stock status of this product," and clicks the send button. This operation sends the input question to the server.

[1166] 2. Receiving and parsing questions:

[1167] The server receives the HTTP request sent from the information processing device and parses the question data in JSON format. As a result, the user ID and question content are extracted. For example, the analysis may yield the question "User 12345 sent the question 'Please tell me the stock status of this product.'"

[1168] 3. Building input prompts for the generative AI model:

[1169] The server constructs a prompt sentence to be posed to the generative AI model based on the analyzed question content. The prompt sentence includes the question content as well as the necessary context information. For example, a prompt sentence such as "I want to know inventory information. Please tell me the inventory status of this product." is generated.

[1170] 4. Answer generation using generative AI models:

[1171] The constructed prompt is input to a generative AI model (e.g., GPT-3). The model analyzes the prompt and generates an appropriate response. For example, the text generated is "This item is currently in stock."

[1172] 5. Submitting and Viewing Answers:

[1173] The server receives the generated response and converts it into a message format. The converted message is parsed again into JSON format and sent to the information processing device as an HTTP response. The information processing device analyzes this message and displays on the screen the message "This product is currently in stock."

[1174] Specific examples

[1175] Example user questions:

[1176] User: "What is the availability of this item?"

[1177] System process flow:

[1178] 1. User: Opens the LINE app on their smartphone, types "Please let me know the stock status of this product," and clicks the send button.

[1179] 2. Server: Analyze the received question and record it as "Question from user 12345: 'Please tell me the stock status of this product.'"

[1180] 3. Server: Based on the analysis results, generate a prompt sentence such as "I want to know the inventory information. Please tell me the inventory status of this product." and pass it to the generative AI model.

[1181] 4. Generative AI model: Analyzes the prompt and generates the answer, "This item is currently in stock."

[1182] 5. Server: Sends the generated answer to the information processing device, which displays the answer to the user.

[1183] This allows users to easily send questions from their devices and receive instant answers, improving work efficiency and reducing the burden on other members and the support center.

[1184] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1185] Step 1:

[1186] User enters a question

[1187] User: Using an information processing device (such as a smartphone or computer), enter a question into the message input field on the screen.

[1188] Specific operation: For example, a user opens the LINE app, types a message such as "Please let me know the stock status of this product," and clicks the send button.

[1189] Input: The text "What is the availability of this item?"

[1190] Output: The action of clicking the submit button and submitting the question.

[1191] Step 2:

[1192] The device sends a question

[1193] Terminal: Holds and transmits questions entered by the user.

[1194] Specific behavior: The entered text is converted into JSON format data and sent to the server as an HTTP request.

[1195] Input: The question text entered by the user.

[1196] Output: The question is converted to JSON format and sent to the server as an HTTP request.

[1197] Step 3:

[1198] The server receives and analyzes the question

[1199] Server: Receives the HTTP request sent from the device and parses the question data in JSON format.

[1200] Specific operation: Analyze the received data and extract the user ID and question. The analysis results in "User 12345 sent the question 'Please tell me the stock status of this product.'"

[1201] Input: HTTP request sent from the terminal (question data in JSON format).

[1202] Output: Extracted user ID and question.

[1203] Step 4:

[1204] The server constructs a prompt

[1205] Server: Based on the extracted question content, constructs a prompt sentence to be input into the generative AI model.

[1206] What it does: The natural language processing model converts the question into a format that is easy to understand. The prompt generated is, "I want to know about inventory. Please tell me the inventory status of this product."

[1207] Input: The extracted question content.

[1208] Output: The generated prompt statement.

[1209] Step 5:

[1210] The server inputs a prompt to the generative AI model.

[1211] Server: The constructed prompt sentence is input to the generative AI model, which uses pre-trained data to generate an appropriate answer to the question.

[1212] What happens: The prompt is passed to a generative AI model (e.g., GPT-3), which parses the prompt and generates the answer, "This item is currently in stock."

[1213] Input: The generated prompt statement.

[1214] Output: The answer generated by the generative AI model.

[1215] Step 6:

[1216] The server sends the answer

[1217] Server: Converts the generated response back into a message format and sends it to the information processing device.

[1218] Specific operation: The generated answer is sent to the information processing device as an HTTP response. "Send the answer 'This product is currently in stock' to user 12345."

[1219] Input: The generated answer.

[1220] Output: The answer, formatted as a message, sent as an HTTP response.

[1221] Step 7:

[1222] The device displays the answer

[1223] Terminal: Parse the response received from the server in JSON format and display it on the screen.

[1224] What happens: A message will appear on the screen saying "This item is currently in stock."

[1225] Input: The answer sent as an HTTP response.

[1226] Output: Messages that are displayed on the screen.

[1227] (Application example 1)

[1228] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1229] In autonomous vehicles, passengers need to be able to quickly and easily obtain information about the vehicle and its real-time status. However, conventional systems have limited means for passengers to ask questions about the vehicle's status and route information and receive answers, resulting in a lack of convenience. Furthermore, many systems do not support voice input or real-time data reference, which has hindered the user experience. Therefore, a system that allows passengers to efficiently obtain information while in the vehicle is needed.

[1230] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1231] In this invention, the server includes: means for a user to input and send a question using a terminal; means for the server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; means for inputting a question regarding the vehicle's status or route information using an in-vehicle display or a smartphone and converting the voice input into text using voice recognition software; means for referencing the vehicle's internal database in real time, obtaining information about the nearest facility using GPS data, and generating an answer; and means for returning the generated answer to the user in voice or text format. This enables passengers to efficiently obtain the information they need in an autonomous vehicle in real time, significantly improving convenience.

[1232] A "user" is an operator of a terminal that utilizes the system to input information and make requests to obtain answers.

[1233] A "terminal" is a device used by a user to input and send a question, and includes a smartphone, tablet, in-vehicle display, etc.

[1234] A "server" is a computer system that analyzes questions received from a terminal, generates answers using a natural language processing model, and sends them back to the terminal.

[1235] A "natural language processing model" is a machine learning and data analysis algorithm or model used to analyze natural language questions posed by users and generate appropriate answers.

[1236] A "question" is text or voice data that a user enters to obtain specific information.

[1237] An "answer" is text or audio data of information that the server generates using a natural language processing model and provides to the user.

[1238] "Speech recognition software" is a program that captures, analyzes, and converts voice input into text.

[1239] "Real-time" is the time frame in which a system acquires, processes, and provides data almost immediately.

[1240] An "in-vehicle display" is a screen that is installed in a vehicle and is used by the user to display and input information.

[1241] A "database" is a collection of information that stores the data required based on a question and that a natural language processing model references to generate an answer.

[1242] "GPS Data" means location information that includes satellite information for identifying a specific location on Earth.

[1243] To implement this invention, it is necessary to provide a system that allows a user to input and send a question using a terminal, a server that receives and analyzes the question from the terminal, a server that inputs the analyzed question into a natural language processing model to generate an answer, and a system that transmits the answer generated by the server to the terminal and displays it. A specific embodiment of this is described below.

[1244] User Interface

[1245] Users can use their smartphone, tablet, or in-car display to type and submit their question. When using voice input, a microphone in the vehicle captures the voice and converts it into text through speech recognition software (e.g., Google Cloud Speech-to-Text API).

[1246] Server Processing

[1247] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and question content. The server then passes the question data to a natural language processing model (e.g., the BERT model using TensorFlow) to analyze the intent and generate an appropriate answer. If necessary, the server references the vehicle's internal database to obtain real-time information (e.g., the vehicle's current speed and location).

[1248] Generate and reply to answers

[1249] The server converts the generated response back into a message format and sends it to the device. The device then displays the received message to the user. If a voice response is desired, the generated text is converted into speech (e.g., using the Google Cloud Text-to-Speech API) and played over the car's speakers.

[1250] Specific examples

[1251] Consider a case where a user types "How far is the next gas station?" into the in-car display and clicks the send button. The server receives and analyzes this question. The analyzed question is passed to a natural language processing model to understand the intent and obtain the necessary data (in this case, distance information using GPS). The server calculates the distance to the nearest gas station and generates an answer, "The distance to the next gas station is 5 km," which is sent back to the user. The user can then check this information on the in-car display and decide what to do next.

[1252] Prompt Sentence Examples

[1253] "What's your current speed?"

[1254] "How far is the next gas station?"

[1255] "How's the weather?"

[1256] This will enable users to obtain the information they need in real time and efficiently while in an autonomous vehicle, significantly improving convenience.

[1257] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1258] Step 1:

[1259] The user uses the device to input and send a question. The user inputs the question into a smartphone app or on the in-car display using text or voice. For example, the user might type, "How far is the next gas station?" and press the send button. In the case of voice input, the vehicle's microphone captures the voice and converts it into a string of characters using speech recognition software (e.g., Google Cloud Speech-to-Text API). The input is the question data in text format, and the output is the data to be sent to the server.

[1260] Step 2:

[1261] The server receives and analyzes the question from the terminal. The server analyzes the question data received from the terminal and extracts the user ID and question content. For example, a question such as "How far is the next gas station?" arrives in text format at the server. The input is the question data received from the terminal, and the output is the analyzed question data.

[1262] Step 3:

[1263] The server inputs the parsed question into a natural language processing model to generate an answer. The server inputs the parsed question data into a natural language processing model (e.g., a BERT model using TensorFlow) to understand the intent of the question. It then references the vehicle's internal database as needed to obtain real-time data. For example, it uses the vehicle's current location to calculate the distance to the nearest gas station. The input is the parsed question data, and the output is the generated answer data.

[1264] Step 4:

[1265] The answer generated by the server is sent to the terminal and displayed. The server then converts the answer generated by the natural language processing model back into a message format and sends it to the terminal. For example, an answer such as "The distance to the next gas station is 5 km" is generated and sent to the terminal. The input is the generated answer data, and the output is the data sent to the terminal.

[1266] Step 5:

[1267] The device displays the received response message to the user. The device then displays the received message to the user. If voice response is also used, the generated text is converted into speech (e.g., Google Cloud Text-to-Speech API) and played from the car's speakers. For example, a response such as "The distance to the next gas station is 5 km" is displayed on the car's display and simultaneously played aloud. The input is the response data sent to the device, and the output is the display and audio playback data for the user.

[1268] This allows users to efficiently obtain the information they need in real time while in an autonomous vehicle, significantly improving convenience.

[1269] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1270] The present invention is a system including: means for a user to input and send a question using a terminal; means for a server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; and an emotion engine that recognizes the user's emotions based on the content of the question input by the user.

[1271] Description of the embodiment

[1272] 1. User enters and submits a question

[1273] The user enters a question or problem that arises during work into a device (e.g., the LINE app on a smartphone) and clicks the send button. For example, to send a question such as, "Please tell me the stock status of this product."

[1274] 2. The server receives and analyzes the user's question.

[1275] The server receives the question data sent from the device and analyzes its contents. The analyzed data is formatted to include the user ID and the question content.

[1276] 3. The server analyzes the question using an emotion engine

[1277] The server recognizes the user's emotions from the words and context of the user's question. For example, the emotion engine may detect that the user is feeling "frustrated" based on the tone and context of the question.

[1278] 4. The server passes the question to a natural language processing model to generate an answer.

[1279] The analyzed question data and the emotion recognition results from the emotion engine are input into a natural language processing model, which uses pre-trained data to understand the intent of the question and generate an appropriate answer.

[1280] 5. The server generates a response, which is sent to the device and displayed.

[1281] The answer generated by the natural language processing model is converted back into a message format and sent to the device. The device displays the received message to the user, who can then check it and use it in their work.

[1282] Specific examples

[1283] Example user questions

[1284] User: "What is the availability of this item?"

[1285] System processing flow

[1286] 1. Terminal: The user types a message such as "Please tell me the stock status of this item" and clicks the send button.

[1287] 2. Server: After receiving the query data sent from the terminal, it analyzes its contents.

[1288] 3. Server:

[1289] The emotion engine analyzes the user's emotions from the question, for example recognizing that the user is anxious.

[1290] The natural language processing model is given the user's question and emotional information. For example, the model recognizes that the question is about "stock availability" and that the user is anxious.

[1291] 4. Server:

[1292] The natural language processing model generates an appropriate answer based on the question and emotional information.

[1293] For example, information such as "We have it in stock" can be obtained from an inventory management database, and a reply message such as "It's okay. This item is currently in stock" can be created based on that information. The reply is provided in a tone that will ease the user's impatience.

[1294] 5. Server: The generated response message is converted back into a message format and sent to the user's device via the LINE API.

[1295] 6. Terminal: The received response message "It's OK. This item is currently in stock." is displayed to the user.

[1296] 7. User: Check the displayed answers and proceed with the task based on them.

[1297] In this way, by combining the system of the present invention with an emotion engine, it is possible to respond in a detailed manner according to the user's emotions, which not only allows for quick and accurate resolution of questions but also increases user satisfaction, making it possible to provide an environment in which users can carry out their work with peace of mind.

[1298] The processing flow will be explained below.

[1299] Step 1:

[1300] A user opens the LINE app on their device and enters a question or problem. For example, the user enters "Please tell me the stock status of this product." and clicks the send button.

[1301] Step 2:

[1302] The device receives the user's input and sends it to the server via the LINE API. The data sent includes the user ID and message content.

[1303] Step 3:

[1304] The server receives a message from the user via the LINE API. The received data is in the format {"userId": "12345", "message": "Please let me know the stock status of this product."}, for example.

[1305] Step 4:

[1306] In order to analyze the contents of the message received by the server, preprocessing such as tokenization and stop word removal is performed. For example, a message such as "Please tell me the stock status of this product" is analyzed and broken down into meaningful words.

[1307] Step 5:

[1308] The server inputs the preprocessed message into the emotion engine, which analyzes the user's emotion from the message text and returns the result. For example, the emotion engine may determine that the user is anxious.

[1309] Step 6:

[1310] The server receives the results from the emotion engine and inputs them into the natural language processing model. The natural language processing model analyzes the input question and emotional information to understand the intent of the question. For example, it detects that the keyword "stock status" is included.

[1311] Step 7:

[1312] The server references a related database based on the output of the natural language processing model, for example, accessing an inventory management database to obtain stock information for the specified product.

[1313] Step 8:

[1314] The server generates a response based on the information it has acquired and the results of the emotion engine. For example, it acquires information such as "In stock" from an inventory management database and uses that information to create a response message such as "It's OK. This item is currently in stock." This response includes a tone of voice to calm the user's impatience.

[1315] Step 9:

[1316] The server then converts the generated reply message back into a message format and sends it to the user's device via the LINE API. The data sent is in the following format, for example: {"replyToken": "TOKEN", "messages": [{"type": "text", "text": "No problem. This item is currently in stock."}]}

[1317] Step 10:

[1318] The device receives the reply message from the server, which is then displayed to the user on the LINE app.

[1319] Step 11:

[1320] The user checks the displayed response message, for example, "It's OK. This item is currently in stock," and proceeds with the task based on that message.

[1321] Example 2

[1322] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1323] In conventional systems, even when users input questions or problems, responses that do not reflect the emotional nuances of the question are not provided, resulting in low user satisfaction. Furthermore, because answers are generated based solely on the content of the question, it is difficult to provide a fast and appropriate service.

[1324] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1325] In this invention, the server includes means for a user to input and send a question using a terminal, means for the server to receive and analyze the question from the terminal, means for the server to analyze the question data with an emotion engine and recognize the user's emotion, means for the server to input the question and emotion analyzed by the server into a natural language processing model and generate an answer, and means for transmitting the answer generated by the server to the terminal and displaying it. This enables detailed responses according to the user's emotion and enables the provision of quick and accurate answers to questions.

[1326] A "user" is an entity that uses the system to enter questions and receive answers.

[1327] "Terminal" refers to an information and communication device that allows a user to input and send a question, and includes, for example, a smartphone or a personal computer.

[1328] A "server" is a computer device that receives and analyzes question data sent from a user's terminal, and generates and sends answers.

[1329] A "question" is a message about a question or problem that a user inputs and sends via a terminal.

[1330] "Reception" refers to the process in which the server receives question data sent from the user's terminal.

[1331] "Analysis" refers to the process in which the server understands the content of the question data received and extracts the necessary information.

[1332] The "emotion engine" is a software component that recognizes the user's emotions from the keywords and context contained in the question data.

[1333] "Emotion" refers to the psychological state that the user reflects in the question, and includes, for example, "joy," "sadness," and "impatience."

[1334] A "natural language processing model" is a model that uses artificial intelligence technology to generate appropriate answers based on analyzed question data and emotional information.

[1335] An "answer" is an appropriate response to a question that the server generates using a natural language processing model.

[1336] "Send" refers to the process of sending the response generated by the server to the user's terminal.

[1337] "Display" refers to the process of visually presenting the received answers on the user's terminal.

[1338] In this system, a user inputs a question using a terminal, the server receives and analyzes the question, generates an appropriate answer, and sends it back to the user's terminal, thereby quickly resolving the user's doubts and problems. A specific embodiment of this system will be described below.

[1339] System configuration

[1340] The system includes the following components:

[1341] 1. User device: Refers to the information and communication device that users use to input and send questions. Examples include smartphones and personal computers.

[1342] 2. Server: A central processing unit for analyzing questions received from user terminals and generating appropriate answers. The server includes the following major hardware and software components:

[1343] Receiving and analyzing module: receives and analyzes user question data.

[1344] Emotion Engine: A software component for recognizing user emotions from received question data.

[1345] Natural language processing model: A model that uses artificial intelligence techniques to generate answers based on analyzed question data and emotional information. Specific examples include generative AI models such as GPT-3.

[1346] Transmission module: Transmits the generated answer to the user terminal.

[1347] 3. Database: A storage device that stores necessary information and references it when generating answers to questions.

[1348] Data processing flow

[1349] 1. User enters question and submits it

[1350] The user opens a chat application on a device (e.g., a smartphone or a PC) and enters a question in text format. For example, the user sends a message such as, "Please tell me the stock status of this product."

[1351] 2. The server receives and analyzes the user's question.

[1352] The server receives the question data sent from the device. It then analyzes the received data and extracts the question content, user ID, etc. The analysis results are stored in an internal database as structured data.

[1353] 3. The server analyzes the question using an emotion engine

[1354] The server passes the question data to the emotion engine to recognize the user's emotion. The emotion engine determines emotions such as "joy," "sadness," and "impatience" based on the keywords and context contained in the question. For example, the emotion engine determines that the user is impatient based on the content of the question.

[1355] 4. The server passes the question to a natural language processing model to generate an answer

[1356] The server inputs the analyzed question data and emotion recognition results into a natural language processing model (e.g., GPT-3), which then generates an appropriate answer based on this data.

[1357] Example prompt: "The user is asking, 'What is the availability of this item?' They also seem impatient. Please generate a response in the appropriate tone."

[1358] 5. The server generates a response, which is sent to the device and displayed.

[1359] The server converts the generated response into a message format and sends it to the user's device via LINE's API, etc. The device displays the received response message to the user, who then confirms it and continues working.

[1360] Specific example explanation

[1361] For example, if a user sends a question via the LINE app, such as "Please tell me the stock status of this item," the server receives the question, analyzes its content, and uses its emotion engine to recognize the user's emotion as "anxious." Based on the information "In stock," the server generates a response in a reassuring tone, "Don't worry. This item is currently in stock," using the GPT-3 model. This response is then sent to the user in the form of a LINE message, and the device displays the message to the user. The user can then confirm the displayed response and continue their work based on it.

[1362] In this way, by generating answers that take the user's feelings into consideration, this system is able to improve user satisfaction and provide quick and accurate solutions to questions.

[1363] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1364] Step 1:

[1365] User enters question and submits it

[1366] Specific actions: The user opens a chat application on a device such as a smartphone or PC and enters their question or problem in text format. They type, "Please tell me the stock status of this product," and clicks the send button.

[1367] Input: The question text entered by the user

[1368] Output: Sending query data from the terminal to the server

[1369] Step 2:

[1370] The server receives and analyzes the user's question.

[1371] Specific operation: The server receives the question data sent from the device. The server analyzes the received data to extract the user ID and question content. For example, it extracts the user_id and text from the JSON format message and stores them in an internal database.

[1372] Input: Question data sent from the terminal

[1373] Output: Extract user ID and question content, store in database

[1374] Step 3:

[1375] The server analyzes the question using an emotion engine

[1376] Specific operation: The server passes the received question data to the emotion engine, which analyzes the user's emotions. The emotion engine determines emotions such as "joy," "sadness," and "impatience" from the content of the question text. For example, from the text "Please tell me the stock status of this product," it recognizes that the user is impatient.

[1377] Input: Parsed question content

[1378] Output: Emotion data as the analysis result (e.g., {"emotion": "anxious"})

[1379] Step 4:

[1380] The server passes the question to a natural language processing model to generate an answer.

[1381] Specific operation: The server inputs the analyzed question data and the emotion recognition results into a natural language processing model. The natural language processing model (e.g., GPT-3) generates an appropriate answer based on the prompt sentence.

[1382] Example prompt: A specific prompt used for the interaction is, "The user is asking, 'What is the availability of this item?' and seems impatient. Please generate a response in an appropriate tone."

[1383] Input: Question content and emotion data

[1384] Output: Answer text generated from the natural language processing model (e.g., "No problem. This item is currently in stock.")

[1385] Step 5:

[1386] The server generates a response, which is sent to the device and displayed.

[1387] Specific operation: The server converts the generated response text into a message format and sends it to the user's device via the LINE API. The user's device displays the received message.

[1388] Input: Generated answer text

[1389] Output: Send and display the reply message to the user's terminal

[1390] This process allows users to receive prompt and appropriate responses, and in the process, it is possible to respond in a way that takes into consideration the user's feelings.

[1391] (Application example 2)

[1392] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1393] Conventional content delivery services provide uniform answers and recommendations without considering the user's emotions, resulting in low user satisfaction. When a user is in a specific emotional state, content appropriate for that emotion is often not provided, so there is a need to improve the user experience.

[1394] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input and send a question using a terminal; means for the server to receive and analyze the question from the terminal; means for inputting the question analyzed by the server into a natural language processing model and generating an answer; means for transmitting the answer generated by the server to the terminal and displaying it; means for the server to recognize the user's emotion based on the user's question; and means for passing the emotion recognition result to the natural language processing model and generating an optimal answer according to the user's emotion. This makes it possible to deliver optimal content according to the user's emotion.

[1395] A "terminal" is an electronic device that a user uses to enter and submit a question.

[1396] A "server" is a computer system that receives queries from users and analyzes and processes the queries.

[1397] A "question" is information or a question that a user inputs through a terminal.

[1398] A "natural language processing model" is an artificial intelligence technology that analyzes text data written in natural language and generates appropriate answers.

[1399] An "answer" is a response generated in response to a question, which contains information that is useful to the user.

[1400] "Emotion recognition" is a method of analyzing and identifying a user's emotional state from the content of the question entered by the user.

[1401] An "information database" is a system or storage device that stores data or information related to a query.

[1402] A system for implementing this invention includes a means for a user to input and send a question using a terminal, a server to receive and analyze the question, generate an answer using a natural language processing model, and send the answer to the terminal for display. Meanwhile, the server further has a means for recognizing emotions based on the user's question, and generates an optimal answer using the natural language processing model based on the recognition results.

[1403] System Configuration

[1404] Device: The device through which the user enters the question. Examples include a smartphone or tablet.

[1405] Server: Responsible for receiving questions, analyzing them, performing emotion recognition, and inputting them into a natural language processing model to generate answers.

[1406] Natural language processing model: Uses a pre-trained model (e.g., GPT-3) to generate appropriate answers based on the input question and sentiment information.

[1407] Emotion recognition engine: Analyzes the emotions expressed by the user's questions and identifies emotions such as joy, sadness, or impatience.

[1408] Software processing and data calculations

[1409] When the server receives a question, it first analyzes the user's emotions using an emotion recognition engine. For example, it uses the Transformers library to run an emotion analysis model. Next, based on the analysis results, it inputs the prompt sentence into a natural language processing model to generate the optimal answer. In this process, a generative AI model (e.g., GPT-3) is used.

[1410] After generating the answer, the server sends it to the user's device, which displays it in the form of a message. For example, if a user asks, "Tell me a movie that will help me relax today," the emotion recognition engine analyzes the emotion "I want to relax," and the natural language processing model generates the answer, "Currently, the movie that is recommended for relaxation is 'Your Name.' Why don't you watch it?"

[1411] Usage example

[1412] For example, use the following prompt:

[1413] User Question: "What movie can I watch to relax today?"

[1414] Example prompt: "The user's emotion is wanting to relax, and the question is 'What movie would make me relax today?'"

[1415] This prompt is then fed into a natural language processing model to generate the most appropriate answer for the user, such as "There's a movie called 'Your Name.' that's relaxing. Why don't you check it out?"

[1416] As a result, it is possible to provide the most appropriate answer according to the user's emotions, which is expected to improve the user experience.

[1417] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1418] Step 1:

[1419] The user uses the device to input and send a question. For example, the user inputs "Tell me a relaxing movie to watch today" into a smartphone application and clicks the send button. This input is sent from the device to the server.

[1420] Step 2:

[1421] The server receives the question sent from the terminal. The server analyzes the question data and extracts the user ID and question content. In this step, the question content is provided as input data, and the analyzed question information is obtained as output data.

[1422] Step 3:

[1423] The server passes the question to an emotion recognition engine to analyze the user's emotion. The emotion recognition engine identifies the emotion from the context of the question. Specifically, emotion analysis is performed using the Transformers library. For example, it detects the emotion "I want to relax." The input for this step is the question, and the output is the user's emotional information.

[1424] Step 4:

[1425] The server creates a prompt sentence based on the emotional information and the analyzed question content and inputs it into the natural language processing model. For example, the prompt sentence might be, "The user's emotional state is that they want to relax, and the question is, 'Tell me a relaxing movie to watch today.'" This prompt sentence is passed to a generative AI model (e.g., GPT-3). The inputs to this step are the question content and emotional information, and the output is the prompt sentence.

[1426] Step 5:

[1427] The natural language processing model generates an answer based on the prompt sentence. The generative AI model uses pre-trained data to generate an appropriate answer based on the user's question and emotions. For example, it generates the answer, "Currently, 'Your Name' is a relaxing movie. Why don't you watch it?" The input of this step is the prompt sentence, and the output is the generated answer.

[1428] Step 6:

[1429] The server sends the generated answer to the terminal. The server converts the generated answer into a message format and sends it to the terminal. The input of this step is the generated answer, and the output is data in message format.

[1430] Step 7:

[1431] The device displays the received answer to the user. For example, a message such as "Currently, 'Your Name' is available as a relaxing movie. Why not check it out?" is displayed. The user checks the displayed message and takes the corresponding action. The input of this step is data in the form of a message, and the output is information acquired by the user's visual recognition.

[1432] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1433] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1434] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1435] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1436] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1437] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1438] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1439] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1440] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1441] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1442] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1443] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1444] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1445] 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.

[1446] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1447] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1448] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1449] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1450] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1451] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1452] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1453] The following is further disclosed regarding the above embodiment.

[1454] (Claim 1)

[1455] means for a user to input and submit a question using a terminal;

[1456] A server receives and analyzes a query from the terminal;

[1457] a means for inputting the question analyzed by the server into a natural language processing model to generate an answer;

[1458] means for transmitting and displaying a response generated by the server to the terminal;

[1459] A system including:

[1460] (Claim 2)

[1461] 10. The system of claim 1, wherein the server includes means for using a natural language processing model to reference a database related to the question and generate an answer.

[1462] (Claim 3)

[1463] 2. The system of claim 1, wherein the terminal includes means for displaying the answer to the user in the form of a message.

[1464] "Example 1"

[1465] (Claim 1)

[1466] A means for a user to input and send a question using an information processing device;

[1467] A server receives and analyzes a query from the information processing device;

[1468] A means for inputting the question analyzed by the server into a generative AI model, constructing a prompt sentence, and generating an answer;

[1469] means for transmitting a response generated by the server to the information processing device and displaying the response;

[1470] A system including:

[1471] (Claim 2)

[1472] 10. The system of claim 1, wherein the server includes means for using the generative AI model to reference data resources related to the question and generate an answer.

[1473] (Claim 3)

[1474] 2. The system according to claim 1, wherein the information processing device includes means for displaying the answer to the user in the form of a message.

[1475] "Application Example 1"

[1476] (Claim 1)

[1477] means for a user to input and submit a question using a terminal;

[1478] A server receives and analyzes a query from the terminal;

[1479] a means for inputting the question analyzed by the server into a natural language processing model to generate an answer;

[1480] means for transmitting and displaying a response generated by the server to the terminal;

[1481] A means for inputting questions about vehicle status and route information using an in-vehicle display or a smartphone and converting the voice input into text through voice recognition software;

[1482] means for referencing the vehicle's internal database in real time and using GPS data to obtain information about the nearest facility and generate a response;

[1483] means for returning the generated answer to the user in voice or text form;

[1484] A system including:

[1485] (Claim 2)

[1486] 10. The system of claim 1, wherein the server includes means for using a natural language processing model to reference a database related to the question and generate an answer.

[1487] (Claim 3)

[1488] 2. The system of claim 1, wherein the terminal includes means for displaying the answer to the user in the form of a message.

[1489] "Example 2: Combining Emotion Engines"

[1490] (Claim 1)

[1491] means for a user to input and submit a question using a terminal;

[1492] A server receives and analyzes a query from the terminal;

[1493] A means for the server to analyze the question data using an emotion engine and recognize the user's emotion;

[1494] A means for inputting the question and sentiment analyzed by the server into a natural language processing model to generate an answer;

[1495] means for transmitting and displaying a response generated by the server to the terminal;

[1496] A system including:

[1497] (Claim 2)

[1498] 10. The system of claim 1, wherein the server includes means for using a natural language processing model to reference a database related to the question and generate an answer.

[1499] (Claim 3)

[1500] 2. The system of claim 1, wherein the terminal includes means for displaying the answer to the user in the form of a message.

[1501] "Application example 2 when combining emotion engines"

[1502] (Claim 1)

[1503] means for a user to input and submit a question using a terminal;

[1504] A server receives and analyzes a query from the terminal;

[1505] a means for inputting the question analyzed by the server into a natural language processing model to generate an answer;

[1506] means for transmitting and displaying a response generated by the server to the terminal;

[1507] A means for the server to recognize the user's emotion based on the user's question;

[1508] A means for passing the emotion recognition results to a natural language processing model to generate an optimal answer according to the user's emotion;

[1509] A system including:

[1510] (Claim 2)

[1511] 2. The system of claim 1, wherein the server includes means for using a natural language processing model to refer to a database of information related to the question and generating a response taking into account the user's emotions.

[1512] (Claim 3)

[1513] 2. The system of claim 1, wherein the terminal includes means for displaying the answer to the user in the form of a message. [Explanation of symbols]

[1514] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for a user to input and submit a question using a terminal; A server receives and analyzes a query from the terminal; a means for inputting the question analyzed by the server into a natural language processing model to generate an answer; means for transmitting and displaying a response generated by the server to the terminal; A system including:

2. 10. The system of claim 1, wherein the server includes means for using a natural language processing model to reference a database related to the question and generate an answer.

3. 2. The system of claim 1, wherein said terminal includes means for displaying the response to the user in the form of a message.

Images