System

Abstract

A system is provided.SOLUTION: A system, comprising: means for inputting a query content in a chat box by a user and transmitting the query content to a server via a client; means for analyzing the query content received by the server and classifying the query content into a category by using a natural language process technology; means for generating an appropriate response by a generation AI based on the category classified by the server; and means for transmitting the response generated by the server to the client, and displaying the response to the user by the client.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, many services require a significant amount of man-hours to respond to user inquiries. Because staff members respond manually, delays can occur when a quick response is required, making it difficult to provide efficient responses to specialized questions. Furthermore, many inquiries are similar, making it difficult to provide consistent answers. This can result in a poor user experience and damage to a company's image. The present invention solves these problems by providing a system that can respond to user inquiries quickly and efficiently. [Means for solving the problem]

[0005] The present invention solves these problems by providing a system that includes a means for allowing a user to input an inquiry via a chat box, a means for the terminal to send the inquiry to a server, a means for the server to analyze the received inquiry and classify it into categories using natural language processing technology, a means for a generation AI to generate an appropriate response based on the classified category, and a means for sending the generated response to the terminal, which then displays the response to the user.

[0006] Specifically, the server uses natural language processing technology to analyze the content of inquiries and classify them into categories, providing quick and accurate responses to questions in specific fields. These responses are generated by generative AI based on prior training data. Furthermore, even if a user enters multiple questions in succession, responses can be generated and provided for each question. This significantly reduces the amount of work required to respond to inquiries, improves the user experience, and contributes to improving the company's image.

[0007] "User" refers to any individual or entity making an inquiry using this system.

[0008] "Chat box" refers to an interface that allows users to enter inquiries in text format.

[0009] "Device" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[0010] "Server" refers to a computer system that receives user queries, analyzes them, and generates responses.

[0011] "Inquiry" refers to a question or problem that a User submits to the Server through the System.

[0012] "Natural language processing technology" refers to computer processing technology that enables a server to analyze user inquiries and understand and classify their content.

[0013] A "category" refers to a group that is classified into a specific theme or field based on the content of the inquiry analyzed using natural language processing technology.

[0014] "Generative AI" refers to the artificial intelligence model used by the server to generate appropriate responses to user queries.

[0015] "Response" refers to the reply that the server creates in response to a user's inquiry using generation AI.

[0016] "Training data" refers to a pre-prepared dataset used to train a generative AI model.

[0017] "Protocol" refers to the communication rules and regulations used to send and receive information between a terminal and a server. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] In the system of this invention, a user makes an inquiry through a chat box, and a generation AI automatically responds to the inquiry. Specific embodiments will be described below.

[0040] First, a user uses their own device to input a question into the chat box provided by the system. For example, they may input a specific question such as "I want to reset my password." This input is done through the device's interface, and the input is sent to the server by the device.

[0041] When the device sends the user's input, the server receives the message. The received message is analyzed using natural language processing (NLP) technology. As a result of the analysis, the message content is classified into a certain category. For example, categories such as "account management" and "technical support" are possible. This categorization identifies the field to which the inquiry relates.

[0042] Based on the analyzed message and category, the server requests the AI ​​to generate a response. The AI ​​has previously learned from the training data and can generate appropriate responses to similar queries. For example, the AI ​​might generate the response, "To reset your password, access the settings menu and select 'Password Reset'."

[0043] The server generates a response and sends it to the device, which displays it on the chat screen so the user can see it. If the user wants to ask a more detailed question, they can type it again in the chat box and the process repeats.

[0044] As a concrete example, consider a situation where the user continues to ask, "Can I do that from my smartphone?" This question is also sent from the device to the server, which analyzes it and generates an appropriate response. For example, a response such as "Yes, you can access the settings menu from your smartphone as well and select 'Reset Password'" is generated and displayed to the user.

[0045] In this way, the system is able to respond quickly and accurately to diverse and specialized inquiries from users, significantly reducing the man-hours required for companies to respond to inquiries and improving the user experience.In addition, the system is capable of providing automated responses 24 hours a day, 365 days a year, so it can help resolve users' questions at any time.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The user enters their inquiry into the chat box and presses the send button. For example, they enter an inquiry such as "I want to reset my password. What should I do?"

[0049] Step 2:

[0050] The device takes the user's input and sends the query to the server using a protocol such as WebSocket or an HTTP POST request.

[0051] Step 3:

[0052] The server stores the received inquiry in a database and passes it to the message processing module.

[0053] Step 4:

[0054] The server analyzes the query content through a message processing module and uses natural language processing (NLP) technology to interpret the content.

[0055] Step 5:

[0056] Based on the analysis results, the server classifies the inquiry into categories such as "account management" or "technical support." This classification identifies the field of the inquiry.

[0057] Step 6:

[0058] The server requests the AI ​​to generate an appropriate response based on the classification category. The AI ​​then refers to training data and generates the optimal response based on past response history.

[0059] Step 7:

[0060] The server receives the response created by the AI, formats it in a structured data format (such as JSON or XML), and sends it to the terminal.

[0061] Step 8:

[0062] The device will parse the response it receives and display it in a user-friendly chat box, for example, "To reset your password, access the Settings menu and select 'Password Reset'."

[0063] Step 9:

[0064] If the user wants to enter a question, they can re-enter it in the chat box and submit, and the process will repeat, allowing the user to obtain additional information.

[0065] Step 10:

[0066] The server analyzes the received inquiry again, generates a response using AI as needed, and sends it to the device. By repeatedly generating responses, continuous support is provided. For example, in response to the question, "Can I do that from my smartphone?", the server responds, "Yes, you can access the settings menu from your smartphone as well and select 'Password Reset'."

[0067] Example 1

[0068] 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."

[0069] Conventional inquiry response systems are required to respond to user inquiries accurately and quickly. However, conventional systems require manual intervention and are inefficient. It is also difficult to provide consistent responses to multiple inquiries, limiting the improvement of user satisfaction. Furthermore, in situations where automated responses are required 24 hours a day, 365 days a year, there are significant constraints on human resources. To solve these issues, a system that utilizes advanced natural language processing technology and generative AI models to automatically and efficiently respond to inquiries is needed.

[0070] 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.

[0071] In this invention, the server includes: a means for a user to input an inquiry into an input device and transmit the inquiry to a central processing unit via an information processing terminal; a means for the central processing unit to analyze the received inquiry and classify it into categories using natural language processing technology; a means for the central processing unit to generate an appropriate response using a generative AI model based on the classified category; a means for the central processing unit to transmit the generated response to the information processing terminal, which then displays the response to the user; a means for automatically generating a prompt sentence for generating a response based on the inquiry for the generative AI model; a means for transmitting the generated response using a standard communication protocol; and a means for providing a continuous response that can respond to multiple inquiries. This enables accurate and prompt responses to a variety of user inquiries, improving user satisfaction and reducing companies' response workload. Furthermore, the automated response system enables 24 / 7 response, overcoming human resource constraints.

[0072] "User" means an individual or legal entity that makes an inquiry using this system.

[0073] An "input device" is a device (such as a keyboard or touch screen) that allows a user to input a query.

[0074] An "information processing terminal" is a device (e.g., a smartphone or PC) that transmits and receives data between a user and a central processing unit.

[0075] A "central processing unit" is a computer server that analyzes and processes received data and generates a response.

[0076] "Natural language processing technology" is a technology that enables computers to understand and analyze natural human language.

[0077] A "generative AI model" is an artificial intelligence system that learns from training data in advance and generates appropriate responses to inquiries.

[0078] A "prompt sentence" is an input sentence provided to a generative AI model to prompt it to generate a response.

[0079] A "standard communication protocol" is a common communication protocol (e.g., HTTP or HTTPS) used to send and receive data.

[0080] MODE FOR CARRYING OUT THE INVENTION

[0081] In the system of this invention, a user makes an inquiry through a chat box, and a generation AI automatically responds to the inquiry. Specific embodiments will be described below.

[0082] First, a user uses their own information processing terminal (e.g., a smartphone or PC) to input a question into a chat box provided by the system. For example, they input a specific question such as "I want to reset my password." This input is made using the terminal's input device (e.g., a keyboard or touch screen), and the data is sent by the terminal to the central processing unit.

[0083] The terminal captures the data entered by the user and transmits it to a central processing unit over a network, using standard communication protocols (e.g., HTTP or HTTPS).

[0084] The server (central processing unit) receives messages sent by users. The received data is analyzed using natural language processing technology. Specifically, the server performs processes such as tokenizing the message, morphological analysis, and categorizing it. For example, a message saying "I would like to reset my password" would be classified as "Account Management."

[0085] Based on the analysis results, the central processing unit requests the generative AI model to generate a response. The generative AI model is a pre-trained model that receives the input data necessary to generate an appropriate response. A prompt sentence is then used as input to the generative AI model. The following prompt sentence is an example:

[0086] Prompt: "I want to reset my password. How do I do this?"

[0087] Response: "To reset your password, go to the Settings menu and select 'Password Reset'."

[0088]

[0089] Prompt: "Can I do that from my phone?"

[0090] Response: "Yes, you can access the settings menu on your phone as well and select 'Reset Password'."

[0091] Based on the message received, the generative AI model uses training data to generate an appropriate response. Response generation is done using advanced machine learning algorithms such as the Transformer model. For example, the generative AI model might generate the response, "To reset your password, visit the Settings menu and select 'Password Reset'."

[0092] The server then sends the generated response back to the information processing terminal, again using the standard communication protocol. The terminal displays the received response on the chat screen, allowing the user to review its content. If the user wishes to ask another question, they can enter it in the chat box again, and the same process is repeated.

[0093] Throughout this process, users can receive appropriate and prompt responses to their questions, which improves user satisfaction while reducing the company's response time. Furthermore, the automated response system allows for 24 / 7 support, overcoming the constraints of human resources.

[0094] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0095] Step 1:

[0096] The user inputs a question into the input device.

[0097] Specifically, a user uses the keyboard or touch screen of an information processing device (e.g., a smartphone or PC) to input a question into a chat box. For example, the user might input a question such as "I want to reset my password." The input at this point is text data of the user's inquiry.

[0098] Step 2:

[0099] The terminal sends the entered question to the server.

[0100] Specifically, the terminal sends text data stating "I would like to reset my password" to the server using a standard communication protocol such as an HTTP POST request. The input is the user's question data, and the output is the request data for sending it.

[0101] Step 3:

[0102] The server receives the user's question and applies natural language processing techniques.

[0103] Specifically, the server analyzes the received text and performs tokenization, morphological analysis, and categorization. For example, a message saying "I want to reset my password" is classified into the "account management" category. The input is the user's question data, and the output is the analyzed tokenized data and category information.

[0104] Step 4:

[0105] The server requests a generative AI model to generate a response based on the category.

[0106] Specifically, the server provides a prompt sentence to the generative AI model based on the analysis results and requests the model to generate an appropriate response. For example, based on the analyzed category "account management," the server inputs a prompt sentence to the generative AI model. The input is the prompt sentence and category information, and the output is a response generation request to the generative AI model.

[0107] Step 5:

[0108] A generative AI model generates a response based on the prompt.

[0109] Specifically, a generative AI model (e.g., a Transformer model) receives a prompt and uses training data to generate an appropriate response, such as "To reset your password, visit the Settings menu and select 'Password Reset.'" The input is the prompt, and the output is the generated response text.

[0110] Step 6:

[0111] The server sends the generated response to the terminal.

[0112] Specifically, the server receives the response from the generative AI model and sends it to the information processing terminal using an HTTP response. The input is the response text from the generative AI model, and the output is the response text sent as HTTP response data.

[0113] Step 7:

[0114] The terminal displays the received response to the user.

[0115] Specifically, the terminal displays the response received from the server on the chat screen, allowing the user to check how to resolve the issue. For example, a message such as "To reset your password, access the settings menu and select 'Password Reset'" may be displayed on the chat screen. The input is the response data received from the server, and the output is the response message displayed to the user.

[0116] (Application example 1)

[0117] 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."

[0118] There is a demand for a system that allows passengers in autonomous vehicles to easily check and change the vehicle's operating status and settings. However, conventional systems require passengers to perform cumbersome operations to directly check the operating status or change settings, resulting in low usability. Furthermore, there is a problem in that the system contains a lot of technical information that is difficult for ordinary passengers to understand, and lacks an intuitive interface.

[0119] 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.

[0120] In this invention, the server includes a means for a user to input an inquiry into a chat box and send it to an information processing platform via an information processing device, a means for the information processing platform to analyze the received inquiry and classify it into categories using natural language processing technology, and a means for generating an appropriate response using a generation AI based on the categories classified by the information processing platform. This allows a user to input an inquiry via an in-vehicle display or mobile device, and the vehicle's operating status and settings can be explained and changed accordingly.

[0121] "User" refers to a person who uses the System to make an inquiry.

[0122] "Chat box" refers to an interface that allows users to enter inquiries or messages in text format.

[0123] "Information processing device" refers to devices used by users, such as smartphones, tablets, and display devices inside vehicles.

[0124] "Information processing infrastructure" refers to a central server or cloud infrastructure that analyzes user inquiries and generates appropriate responses using generative AI.

[0125] "Natural language processing technology" refers to technology that analyzes users' text messages and understands their intent and meaning.

[0126] "Category" refers to the field or topic into which the analyzed inquiry content is categorized. Examples include "driving mode" and "navigation settings."

[0127] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to generate appropriate responses to user inquiries.

[0128] "Response" refers to the answer or instruction generated by the AI ​​based on the user's inquiry.

[0129] "In-vehicle displays" refer to display devices used by users inside a vehicle, typically installed in the driver's seat or rear seats.

[0130] "Mobile terminal" refers to a mobile device such as a smartphone or tablet carried by a user.

[0131] "Inquiry" refers to a question or request made by a user to the system.

[0132] "Operating status" refers to information indicating the current operating status and mode settings of the vehicle.

[0133] The system of this invention allows users inside an autonomous vehicle to easily check and change the vehicle's operating status and settings, and includes the following components:

[0134] System configuration and operation

[0135] 1. User Actions

[0136] The user enters their inquiry in text format into a chat box displayed on the vehicle's display or mobile device, such as "What is the current driving mode?"

[0137] 2. Transmission from the information processing device to the information processing infrastructure

[0138] The user's input is sent from an information processing device (smartphone, tablet, in-vehicle display, etc.) to an information processing infrastructure (central server or cloud infrastructure).

[0139] 3. Analysis of information processing infrastructure

[0140] The information processing infrastructure analyzes the received inquiry content using natural language processing technology (e.g., SpaCy or NLTK) and classifies the content into categories.

[0141] 4. Response generation using generative AI

[0142] The information processing platform then requests a generative AI (e.g., GPT-4) to generate a response based on the analysis results. The generative AI is trained in advance based on learning data and is able to generate appropriate responses.

[0143] 5. Sending and Displaying Responses

[0144] The information processing infrastructure transmits the generated response to the information processing device, which displays the response to the user.

[0145] Hardware and software used

[0146] Information processing devices: Smartphones, tablets, in-vehicle displays, etc.

[0147] Information processing infrastructure: central server or cloud infrastructure.

[0148] Natural language processing technology: SpaCy or NLTK.

[0149] Generative AI models: Advanced natural language generation AI such as GPT-4.

[0150] Specific examples

[0151] 1. Initial Inquiry

[0152] User Question: "What driving mode are you in?"

[0153] Category: Driving Mode

[0154] Generative AI response: "Autopilot mode is currently 'Highway mode'. Other options include 'City mode' and 'Parking assist mode'."

[0155] 2. Example prompts to be input to the generative AI model

[0156] User Question: "What driving mode are you in?"

[0157] Category: "Driving Mode"

[0158] Example response: "Self-driving mode is currently 'Highway Mode'. Other options include 'City Mode' and 'Parking Assist Mode'."

[0159] In this way, this system allows users to easily and intuitively check and change the operating status and settings of an autonomous vehicle, which is expected to improve the user experience and significantly enhance vehicle operability.

[0160] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0161] Step 1:

[0162] The user inputs the inquiry into the chat box using the in-vehicle display or a mobile terminal. The input text is transmitted from the user terminal to the information processing infrastructure. Specifically, the user inputs "Please tell me the current driving mode," and the data is transmitted to the information processing infrastructure via the information processing device.

[0163] Step 2:

[0164] The information processing platform receives inquiries sent by users. It analyzes the received data using natural language processing technology (e.g., SpaCy, NLTK) to extract important keywords from the inquiries. This analysis categorizes the inquiries as being related to "driving modes."

[0165] Step 3:

[0166] The information processing infrastructure sends a prompt to the generative AI model (e.g., GPT-4) based on the analysis results and category data. At this time, the prompt text includes the user's question and category information. An example of a prompt text is, "User question: 'What is the current driving mode?', Category: 'Driving mode'."

[0167] Step 4:

[0168] The generative AI model takes a prompt as input and generates a response based on it. The generative AI model uses pre-trained data to create an appropriate and grammatically correct response. The generated response might be something like, "Autopilot mode is currently 'Highway mode'. Other options are 'City mode' and 'Parking assist mode'."

[0169] Step 5:

[0170] The generated response is sent by the information processing platform to the user's information processing device. The information processing device displays the received response in a chat box and provides it to the user. This allows the user to immediately check the answer to their inquiry. Specifically, the information processing platform sends the response data obtained from the generative AI model to the user's terminal, and the terminal displays the response on its screen.

[0171] Step 6:

[0172] If the user wishes to ask a more detailed question or make an additional inquiry, they can enter another input into the chat box. This new input will then repeat the process from step 1. For example, if the user continues by asking, "Please tell me about other modes as well," the new input will be sent to the information processing infrastructure, which will then perform the same analysis and generate a response.

[0173] 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.

[0174] The system of this invention receives inquiries from users via a chat box and provides appropriate responses using generative AI. Furthermore, by combining it with an emotion engine, it is possible to recognize the user's emotions and provide more appropriate and personalized responses. The detailed operation of the system will be described based on this embodiment.

[0175] First, the user enters their inquiry into the chat box on their device. For example, they might enter, "I want to reset my password. What should I do?" At this time, the device is equipped with an emotion engine that analyzes the user's emotions based on the content, typing speed, and language characteristics of the input. The emotion analysis results (e.g., stress, anxiety, calm, etc.) are also sent to the server.

[0176] The device sends the user's inquiry and sentiment analysis results to the server. The server first stores the received message in a database and then passes the data to the message processing module. The message processing module uses natural language processing (NLP) technology to analyze the inquiry and classify the message into a specific category based on its content.

[0177] Once the message has been categorized, the server requests the generation AI to generate a response that takes the user's emotions into account. The generation AI generates an appropriate response to the question based on the training data, but also takes into account the analysis results from the emotion engine. For example, for a user who is "feeling stressed," the response could be tailored to something like, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[0178] The generated response is sent from the server to the device. The device analyzes the received response and displays it on the chat screen in a user-friendly format. This provides specific guidance, such as "To reset your password, access the settings menu and select 'Password Reset'."

[0179] If the user wants to continue with a more detailed question, they can type it again in the chat box and the process will be repeated. For example, if the user asks, "Can I do that from my phone too?", this question will also be analyzed by the emotion engine and sent to the server along with the emotion data. Subsequent processing will be carried out in the same way, and a response will be generated and displayed to the user via the device, such as, "Yes, you can also access the settings menu from your phone and select 'Reset Password'."

[0180] In this way, by combining this system with an emotion engine, it can provide personalized support according to the user's emotional state, achieving higher levels of satisfaction. Furthermore, by automating inquiry responses, it enables companies to reduce their workload and respond more quickly.

[0181] The processing flow will be explained below.

[0182] Step 1:

[0183] The user enters their inquiry into the chat box and presses the send button. For example, they enter an inquiry such as "I want to reset my password. What should I do?"

[0184] Step 2:

[0185] The device receives the user's input. At this time, the emotion engine analyzes the user's input, input speed, language selection, etc. to determine the emotion (e.g., stress, anxiety, calm, etc.). The determined emotion data is sent to the server along with the query content.

[0186] Step 3:

[0187] The device sends the query and emotion data to the server using protocols such as WebSocket or HTTP POST requests.

[0188] Step 4:

[0189] The server receives the request, stores the query in a database, and then passes the data to the message processing module.

[0190] Step 5:

[0191] The server uses a message processing module to analyze the content of the received inquiry, using natural language processing (NLP) techniques to analyze the content and then using a classification algorithm to classify it into a specific category (e.g., "account management" or "technical support").

[0192] Step 6:

[0193] The server requests the AI ​​to generate a response based on the analyzed message and category. At this time, emotion data is also passed to the AI, and the emotion is taken into account when generating the response.

[0194] Step 7:

[0195] Based on the inquiry content and emotional data received, the generation AI generates the optimal response while referring to training data. For example, for a user who is "feeling stressed," it generates the response, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[0196] Step 8:

[0197] The server formats the generated response data and sends it to the terminal in a structured data format such as JSON or XML.

[0198] Step 9:

[0199] The device will then analyze the response and display it in a user-friendly format on the chat screen, for example, "To reset your password, access the settings menu and select 'Password Reset'."

[0200] Step 10:

[0201] If the user has additional questions, they can type them again into the chat box and submit, and the process can be repeated to obtain additional information.

[0202] Step 11:

[0203] The server again analyzes the received inquiry, generates a response using AI if necessary, and sends it to the device. For example, in response to the question, "Can I do that from my smartphone?", it provides the response, "Yes, you can access the settings menu from your smartphone as well and select 'Password Reset'."

[0204] Through the above steps, the present invention combines emotion engines to realize a system that provides personalized support according to the user's emotional state.

[0205] Example 2

[0206] 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."

[0207] Conventional inquiry systems could only provide uniform responses to user inquiries, making it difficult to provide personalized responses that took into account the user's emotions and circumstances. This also led to declining user satisfaction, and the systems were unable to provide adequate responses in today's business environment, where rapid responses are required. Furthermore, the processes for analyzing inquiry content and generating responses were inefficient, making it difficult for companies to reduce their workload.

[0208] 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.

[0209] In this invention, the server includes: a means for a user to input inquiry content and send it to the server via a terminal; a means for the terminal to perform sentiment analysis on the user's input content; a means for the server to analyze the received inquiry content and sentiment analysis results and classify them into categories using natural language processing technology; a means for the server to generate an appropriate response using a generation AI based on the classified category and sentiment analysis results; and a means for the server to send the generated response to the terminal and for the terminal to display the response to the user. This enables personalized responses according to the user's emotions and situation, improving user satisfaction and enabling companies to reduce their workload and provide faster responses.

[0210] "User" means an individual or equivalent entity that inputs a query into the system.

[0211] A "terminal" is a hardware or software device that allows a user to enter a query into a chat box and send it to a server.

[0212] "Server" means a computer system for receiving and processing data sent by users, and is a device that includes a database, a message processing module, and a generating AI.

[0213] "Sentiment analysis" is the process of assessing a user's emotional state based on their input, typing speed, and language characteristics.

[0214] "Natural language processing technology" is a technology that allows computers to understand and process human language, and is a technology that analyzes the content of inquiries and classifies them into categories.

[0215] "Generative AI" is artificial intelligence that generates appropriate responses to user inquiries based on training data.

[0216] "Displaying a response" refers to the act of analyzing the response received by the terminal and displaying it on the chat screen in a format that is easy for the user to see.

[0217] "Training data" is a data set used to train a generative AI to generate appropriate responses.

[0218] A "prompt sentence" is an instruction sentence that instructs the generation AI to generate an appropriate response.

[0219] This invention is a system that generates an appropriate response based on the content of a user's inquiry entered through a chat box and the results of an analysis of the user's emotions. The system aims to increase user satisfaction by providing a personalized response that reflects the user's emotional state.

[0220] A user enters a query into the chat box from their device. For example, they might enter, "I want to reset my password. What should I do?" At this time, the device is equipped with an emotion engine that analyzes the user's input, input speed, and language characteristics to recognize their emotions. The analysis results (e.g., stress, anxiety, calm, etc.) are sent to the server along with the query.

[0221] The device sends the user's inquiry and the results of the sentiment analysis to the server, which temporarily stores the received data in a database. The data is then passed to the message processing module, which uses natural language processing (NLP) technology to analyze the inquiry and classify it into specific categories.

[0222] The server then uses the analyzed data to generate a response that takes into account the user's emotions, and requests the AI ​​to generate a response along with a prompt. Specific examples of prompts are as follows:

[0223] User asks: "I want to reset my password. How do I do that?"

[0224] Sentiment analysis result: "Stress"

[0225] Generate an appropriate response.

[0226] The generative AI generates the optimal response to the inquiry based on the training data. In doing so, it also takes into account the analysis results of the emotion engine, so if the user is "stressed," for example, it will generate a response such as, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[0227] The generated response is sent from the server to the device, which then analyzes it and displays it on the chat screen in a user-friendly format. For example, specific guidance such as "To reset your password, access the settings menu and select 'Password Reset'" is provided.

[0228] If the user wants to ask a more detailed question, they can type it again into the chat box. This is also analyzed by the emotion engine and sent to the server along with the emotion data. A similar process is followed to generate a response, such as "Yes, you can also access the settings menu on your smartphone and select 'Reset Password'," which is then displayed to the user via their device.

[0229] This system provides personalized support combined with sentiment analysis, improving user satisfaction. It also automates inquiry responses, reducing the workload of companies and enabling faster responses.

[0230] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0231] Step 1:

[0232] The user inputs the inquiry.

[0233] Specific operation: The user opens a chat box on their device and types in a question, for example, "I want to reset my password. How do I do this?"

[0234] Input: User text input

[0235] Output: Your input is saved to your device

[0236] Step 2:

[0237] The device passes the user's input to the emotion engine for emotion analysis.

[0238] Specific operation: The input text content is sent to the emotion engine in real time and analyzed for the user's emotions (stress, anxiety, calm, etc.).

[0239] Input: User text input

[0240] Output: Sentiment analysis result (e.g., stress, confidence level 0.86)

[0241] Step 3:

[0242] The device sends the emotion analysis results and the inquiry content to the server.

[0243] Specific operation: The sentiment analysis results are compiled in JSON format and sent to the server along with the query content via an HTTP request.

[0244] Input: Enquiry content and sentiment analysis results

[0245] Output: JSON data sent to the server

[0246] Step 4:

[0247] The server stores the received data in a database.

[0248] Specific operation: Parse the received JSON data and record the inquiry content and sentiment analysis results in a database.

[0249] Input: Received JSON data

[0250] Output: Data stored in the database

[0251] Step 5:

[0252] The server passes the data to the message processing module, which analyzes and classifies the query content.

[0253] Specific operation: The query content retrieved from the database is analyzed using natural language processing (NLP) technology and classified into categories such as "password reset."

[0254] Input: Query retrieved from the database

[0255] Output: The category (e.g., password reset)

[0256] Step 6:

[0257] The server creates a prompt sentence for the generation AI and asks it to generate a response.

[0258] Specific operation: A prompt sentence is generated based on the category classification results and sentiment analysis results and sent to the generation AI.

[0259] Input: Category classification results and sentiment analysis results

[0260] Output: Prompt sentence for the generation AI (Example: User inquiry: "I want to reset my password. What should I do?" Sentiment analysis result: "Stressed". Generate an appropriate response.)

[0261] Step 7:

[0262] The generative AI generates a response based on the prompt text.

[0263] How it works: Generative AI refers to a training dataset and generates an appropriate response, taking into account the user's emotions.

[0264] Input: Prompt for the generation AI

[0265] Output: The response generated (e.g. Don't worry, resetting your password is a simple process. Just follow the steps below.)

[0266] Step 8:

[0267] The server sends the generated response to the terminal.

[0268] Specific behavior: Receives the generated response and sends it to the user's device.

[0269] Input: The generated response

[0270] Output: Response data to the terminal

[0271] Step 9:

[0272] The terminal analyzes the received response and displays it to the user.

[0273] What it does: The device parses the received response and displays it on the chat screen in a user-friendly format, such as "Don't worry, resetting your password is a simple process. Just go to the settings menu and select 'Password Reset'."

[0274] Input: Received response data

[0275] Output: The response displayed in the user's chat screen

[0276] (Application example 2)

[0277] 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."

[0278] Conventional driver assistance systems and chatbots generate mechanical responses without considering the user's emotional state, which means they are unable to provide appropriate support, especially to drivers who are stressed or fatigued. There is also a need for systems that can respond in real time to inquiries and requests from drivers while driving, while also being flexible and taking into account the driver's emotional state. To solve this problem, a system incorporating emotion recognition functionality is required.

[0279] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0280] In this invention, the server includes a means for a user to input an inquiry into a chat box and send it to a data processing device via a terminal, a means for the data processing device to analyze the received inquiry and classify it into categories using natural language processing technology, and a means for the data processing device to generate an appropriate response using a generation AI based on the classified category and the emotion analysis result. This makes it possible to provide a driving support function according to the driver's emotional state, reducing stress and suggesting appropriate breaks.

[0281] "User" means an individual or entity who uses the system and inputs inquiries via a terminal.

[0282] A "chat box" is an interface for users to enter their inquiries.

[0283] "Terminal" refers to a computer, smartphone, or other device used by a user, which is a means for communicating with the server.

[0284] "Data Processing Device" means the computer server or cloud infrastructure used to receive and analyze user inquiries and generate responses.

[0285] "Natural language processing technology" is a technology for analyzing text data and performing semantic understanding and category classification.

[0286] A "category" is a classification criterion for classifying user inquiries into specific groups or classes.

[0287] "Emotion analysis result" is information indicating the emotional state extracted from the user's input content.

[0288] "Generative AI" is an artificial intelligence technology that generates appropriate responses to user inquiries based on training data.

[0289] "Response" means a system-generated reply or instruction to a user's inquiry.

[0290] "Driving support functions" are a series of functions to assist drivers while driving, including playing relaxation music and suggesting rest spots.

[0291] "Relaxation music" is music played to relieve the driver's stress and anxiety.

[0292] "Route Guidance" is a navigation function that provides directions for the driver to reach their destination.

[0293] To implement this invention, it is necessary to build a system that applies a chat system using an emotion analysis engine and generative AI to driving support. This system is composed of the following elements.

[0294] 1. User Interface:

[0295] A chat box is provided for drivers (users) to enter their inquiries or requests, which typically runs on the in-car infotainment system or on a smartphone.

[0296] 2. Sentiment Analysis Engine:

[0297] It analyzes user input in real time to identify their emotional state (e.g., stressed, anxious, calm, etc.) using the Python library TextBlob and Hugging Face Transformers.

[0298] 3. Data Processing Unit:

[0299] The system receives the user's inquiry along with the sentiment analysis results and categorizes them using natural language processing techniques, using the Hugging Face Transformers model.

[0300] 4. Generative AI Models:

[0301] The data processing device generates an appropriate response based on the categorized inquiry content received and the results of sentiment analysis, using generative AI models such as Microsoft's DialoGPT.

[0302] 5. Send and display the response:

[0303] The response generated by the data processing device is sent to the user's device and displayed in a format that the user can view, allowing the user to receive specific guidance and driving support in response to the request.

[0304] For example, if a driver types, "I'm very tired today. Is there anywhere nearby where I can rest?", the emotion analysis engine will identify the emotional state of "fatigue," and the data processing device will analyze and classify the content. The generative AI model will generate a response providing information on "nearby rest spots," and will display a reply on the user's device such as, "There are several places to rest nearby. The nearest rest spot is 10 km away, and we recommend you take a break there."

[0305] In addition, if a driver who is stressed by traffic jams types in, "I'm frustrated by the traffic jam. Please tell me how I can calm myself down right now," the emotion analysis engine will detect "frustration," and the generative AI model will generate a response suggesting things like "playing relaxation music" or "routes to avoid the traffic jam."

[0306] Example prompt sentence:

[0307] "I'm very tired today. Is there anywhere nearby where I can rest?"

[0308] "I'm frustrated with the traffic. Can you tell me how to calm myself down right now?"

[0309] This allows drivers to receive appropriate support in real time based on their emotional state while driving.

[0310] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0311] Step 1:

[0312] The user (driver) enters an inquiry or request into the chat box from the car's infotainment system or smartphone. The entered data is sent to the sentiment analysis engine. At this point, the input is the user's text message, for example, "I'm very tired today. Is there anywhere nearby where I can rest?"

[0313] Step 2:

[0314] The device sends the received user input to a sentiment analysis engine (e.g., TextBlob), which analyzes the input and identifies the user's emotional state (e.g., fatigue, stress). The input is the user's text message, and the output is the emotional state (e.g., "fatigue").

[0315] Step 3:

[0316] The device sends the user's input and the emotion analysis results to a data processing device, which analyzes and classifies the data using natural language processing technology to identify a category (e.g., "rest spot suggestions"). The input is the user's text message and emotional state information, and the output is category information.

[0317] Step 4:

[0318] The data processing device makes a generative AI model (e.g., DialoGPT) generate an appropriate response based on the classified category and the emotion analysis results. The generative AI model generates a response based on the training data. This process involves running a generative algorithm, which generates a generated response (e.g., "There are several places to rest nearby. The nearest rest spot is 10 km away, and we recommend you take a break there."). The input is category information and emotional state information, and the output is a response message.

[0319] Step 5:

[0320] The data processing device sends the generated response to the terminal. The terminal analyzes the received response and displays it in a format that can be confirmed by the user. Specifically, it displays a text message on the chat screen. The input is the generated response message, and the output is the response message that is displayed to the user.

[0321] Step 6:

[0322] If the user enters another question or request, the above steps are repeated again. For example, if the user adds, "Can I do that from my phone?", this new inquiry is also processed again through the sentiment analysis engine, data processing unit, and generative AI model. The input is the new user message, and the output is the corresponding response message.

[0323] 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.

[0324] 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.

[0325] 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.

[0326] [Second embodiment]

[0327] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0328] 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.

[0329] 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).

[0330] 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.

[0331] 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.

[0332] 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).

[0333] 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.

[0334] 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.

[0335] 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.

[0336] 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.

[0337] 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.

[0338] 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."

[0339] In the system of this invention, a user makes an inquiry through a chat box, and a generation AI automatically responds to the inquiry. Specific embodiments will be described below.

[0340] First, a user uses their own device to input a question into the chat box provided by the system. For example, they may input a specific question such as "I want to reset my password." This input is done through the device's interface, and the input is sent to the server by the device.

[0341] When the device sends the user's input, the server receives the message. The received message is analyzed using natural language processing (NLP) technology. As a result of the analysis, the message content is classified into a certain category. For example, categories such as "account management" and "technical support" are possible. This categorization identifies the field to which the inquiry relates.

[0342] Based on the analyzed message and category, the server requests the AI ​​to generate a response. The AI ​​has previously learned from the training data and can generate appropriate responses to similar queries. For example, the AI ​​might generate the response, "To reset your password, access the settings menu and select 'Password Reset'."

[0343] The server generates a response and sends it to the device, which displays it on the chat screen so the user can see it. If the user wants to ask a more detailed question, they can type it again in the chat box and the process repeats.

[0344] As a concrete example, consider a situation where the user continues to ask, "Can I do that from my smartphone?" This question is also sent from the device to the server, which analyzes it and generates an appropriate response. For example, a response such as "Yes, you can access the settings menu from your smartphone as well and select 'Reset Password'" is generated and displayed to the user.

[0345] In this way, the system is able to respond quickly and accurately to diverse and specialized inquiries from users, significantly reducing the man-hours required for companies to respond to inquiries and improving the user experience.In addition, the system is capable of providing automated responses 24 hours a day, 365 days a year, so it can help resolve users' questions at any time.

[0346] The processing flow will be explained below.

[0347] Step 1:

[0348] The user enters their inquiry into the chat box and presses the send button. For example, they enter an inquiry such as "I want to reset my password. What should I do?"

[0349] Step 2:

[0350] The device takes the user's input and sends the query to the server using a protocol such as WebSocket or an HTTP POST request.

[0351] Step 3:

[0352] The server stores the received inquiry in a database and passes it to the message processing module.

[0353] Step 4:

[0354] The server analyzes the query content through a message processing module and uses natural language processing (NLP) technology to interpret the content.

[0355] Step 5:

[0356] Based on the analysis results, the server classifies the inquiry into categories such as "account management" or "technical support." This classification identifies the field of the inquiry.

[0357] Step 6:

[0358] The server requests the AI ​​to generate an appropriate response based on the classification category. The AI ​​then refers to training data and generates the optimal response based on past response history.

[0359] Step 7:

[0360] The server receives the response created by the AI, formats it in a structured data format (such as JSON or XML), and sends it to the terminal.

[0361] Step 8:

[0362] The device will parse the response it receives and display it in a user-friendly chat box, for example, "To reset your password, access the Settings menu and select 'Password Reset'."

[0363] Step 9:

[0364] If the user wants to enter a question, they can re-enter it in the chat box and submit, and the process will repeat, allowing the user to obtain additional information.

[0365] Step 10:

[0366] The server analyzes the received inquiry again, generates a response using AI as needed, and sends it to the device. By repeatedly generating responses, continuous support is provided. For example, in response to the question, "Can I do that from my smartphone?", the server responds, "Yes, you can access the settings menu from your smartphone as well and select 'Password Reset'."

[0367] Example 1

[0368] 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."

[0369] Conventional inquiry response systems are required to respond to user inquiries accurately and quickly. However, conventional systems require manual intervention and are inefficient. It is also difficult to provide consistent responses to multiple inquiries, limiting the improvement of user satisfaction. Furthermore, in situations where automated responses are required 24 hours a day, 365 days a year, there are significant constraints on human resources. To solve these issues, a system that utilizes advanced natural language processing technology and generative AI models to automatically and efficiently respond to inquiries is needed.

[0370] 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.

[0371] In this invention, the server includes: a means for a user to input an inquiry into an input device and transmit the inquiry to a central processing unit via an information processing terminal; a means for the central processing unit to analyze the received inquiry and classify it into categories using natural language processing technology; a means for the central processing unit to generate an appropriate response using a generative AI model based on the classified category; a means for the central processing unit to transmit the generated response to the information processing terminal, which then displays the response to the user; a means for automatically generating a prompt sentence for generating a response based on the inquiry for the generative AI model; a means for transmitting the generated response using a standard communication protocol; and a means for providing a continuous response that can respond to multiple inquiries. This enables accurate and prompt responses to a variety of user inquiries, improving user satisfaction and reducing companies' response workload. Furthermore, the automated response system enables 24 / 7 response, overcoming human resource constraints.

[0372] "User" means an individual or legal entity that makes an inquiry using this system.

[0373] An "input device" is a device (such as a keyboard or touch screen) that allows a user to input a query.

[0374] An "information processing terminal" is a device (e.g., a smartphone or PC) that transmits and receives data between a user and a central processing unit.

[0375] A "central processing unit" is a computer server that analyzes and processes received data and generates a response.

[0376] "Natural language processing technology" is a technology that enables computers to understand and analyze natural human language.

[0377] A "generative AI model" is an artificial intelligence system that learns from training data in advance and generates appropriate responses to inquiries.

[0378] A "prompt sentence" is an input sentence provided to a generative AI model to prompt it to generate a response.

[0379] A "standard communication protocol" is a common communication protocol (e.g., HTTP or HTTPS) used to send and receive data.

[0380] MODE FOR CARRYING OUT THE INVENTION

[0381] In the system of this invention, a user makes an inquiry through a chat box, and a generation AI automatically responds to the inquiry. Specific embodiments will be described below.

[0382] First, a user uses their own information processing terminal (e.g., a smartphone or PC) to input a question into a chat box provided by the system. For example, they input a specific question such as "I want to reset my password." This input is made using the terminal's input device (e.g., a keyboard or touch screen), and the data is sent by the terminal to the central processing unit.

[0383] The terminal captures the data entered by the user and transmits it to a central processing unit over a network, using standard communication protocols (e.g., HTTP or HTTPS).

[0384] The server (central processing unit) receives messages sent by users. The received data is analyzed using natural language processing technology. Specifically, the server performs processes such as tokenizing the message, morphological analysis, and categorizing it. For example, a message saying "I would like to reset my password" would be classified as "Account Management."

[0385] Based on the analysis results, the central processing unit requests the generative AI model to generate a response. The generative AI model is a pre-trained model that receives the input data necessary to generate an appropriate response. A prompt sentence is then used as input to the generative AI model. The following prompt sentence is an example:

[0386] Prompt: "I want to reset my password. How do I do this?"

[0387] Response: "To reset your password, go to the Settings menu and select 'Password Reset'."

[0388]

[0389] Prompt: "Can I do that from my phone?"

[0390] Response: "Yes, you can access the settings menu on your phone as well and select 'Reset Password'."

[0391] Based on the message received, the generative AI model uses training data to generate an appropriate response. Response generation is done using advanced machine learning algorithms such as the Transformer model. For example, the generative AI model might generate the response, "To reset your password, visit the Settings menu and select 'Password Reset'."

[0392] The server then sends the generated response back to the information processing terminal, again using the standard communication protocol. The terminal displays the received response on the chat screen, allowing the user to review its content. If the user wishes to ask another question, they can enter it in the chat box again, and the same process is repeated.

[0393] Throughout this process, users can receive appropriate and prompt responses to their questions, which improves user satisfaction while reducing the company's response time. Furthermore, the automated response system allows for 24 / 7 support, overcoming the constraints of human resources.

[0394] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0395] Step 1:

[0396] The user inputs a question into the input device.

[0397] Specifically, a user uses the keyboard or touch screen of an information processing device (e.g., a smartphone or PC) to input a question into a chat box. For example, the user might input a question such as "I want to reset my password." The input at this point is text data of the user's inquiry.

[0398] Step 2:

[0399] The terminal sends the entered question to the server.

[0400] Specifically, the terminal sends text data stating "I would like to reset my password" to the server using a standard communication protocol such as an HTTP POST request. The input is the user's question data, and the output is the request data for sending it.

[0401] Step 3:

[0402] The server receives the user's question and applies natural language processing techniques.

[0403] Specifically, the server analyzes the received text and performs tokenization, morphological analysis, and categorization. For example, a message saying "I want to reset my password" is classified into the "account management" category. The input is the user's question data, and the output is the analyzed tokenized data and category information.

[0404] Step 4:

[0405] The server requests a generative AI model to generate a response based on the category.

[0406] Specifically, the server provides a prompt sentence to the generative AI model based on the analysis results and requests the model to generate an appropriate response. For example, based on the analyzed category "account management," the server inputs a prompt sentence to the generative AI model. The input is the prompt sentence and category information, and the output is a response generation request to the generative AI model.

[0407] Step 5:

[0408] A generative AI model generates a response based on the prompt.

[0409] Specifically, a generative AI model (e.g., a Transformer model) receives a prompt and uses training data to generate an appropriate response, such as "To reset your password, visit the Settings menu and select 'Password Reset.'" The input is the prompt, and the output is the generated response text.

[0410] Step 6:

[0411] The server sends the generated response to the terminal.

[0412] Specifically, the server receives the response from the generative AI model and sends it to the information processing terminal using an HTTP response. The input is the response text from the generative AI model, and the output is the response text sent as HTTP response data.

[0413] Step 7:

[0414] The terminal displays the received response to the user.

[0415] Specifically, the terminal displays the response received from the server on the chat screen, allowing the user to check how to resolve the issue. For example, a message such as "To reset your password, access the settings menu and select 'Password Reset'" may be displayed on the chat screen. The input is the response data received from the server, and the output is the response message displayed to the user.

[0416] (Application example 1)

[0417] 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."

[0418] There is a demand for a system that allows passengers in autonomous vehicles to easily check and change the vehicle's operating status and settings. However, conventional systems require passengers to perform cumbersome operations to directly check the operating status or change settings, resulting in low usability. Furthermore, there is a problem in that the system contains a lot of technical information that is difficult for ordinary passengers to understand, and lacks an intuitive interface.

[0419] 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.

[0420] In this invention, the server includes a means for a user to input an inquiry into a chat box and send it to an information processing platform via an information processing device, a means for the information processing platform to analyze the received inquiry and classify it into categories using natural language processing technology, and a means for generating an appropriate response using a generation AI based on the categories classified by the information processing platform. This allows a user to input an inquiry via an in-vehicle display or mobile device, and the vehicle's operating status and settings can be explained and changed accordingly.

[0421] "User" refers to a person who uses the System to make an inquiry.

[0422] "Chat box" refers to an interface that allows users to enter inquiries or messages in text format.

[0423] "Information processing device" refers to devices used by users, such as smartphones, tablets, and display devices inside vehicles.

[0424] "Information processing infrastructure" refers to a central server or cloud infrastructure that analyzes user inquiries and generates appropriate responses using generative AI.

[0425] "Natural language processing technology" refers to technology that analyzes users' text messages and understands their intent and meaning.

[0426] "Category" refers to the field or topic into which the analyzed inquiry content is categorized. Examples include "driving mode" and "navigation settings."

[0427] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to generate appropriate responses to user inquiries.

[0428] "Response" refers to the answer or instruction generated by the AI ​​based on the user's inquiry.

[0429] "In-vehicle displays" refer to display devices used by users inside a vehicle, typically installed in the driver's seat or rear seats.

[0430] "Mobile terminal" refers to a mobile device such as a smartphone or tablet carried by a user.

[0431] "Inquiry" refers to a question or request made by a user to the system.

[0432] "Operating status" refers to information indicating the current operating status and mode settings of the vehicle.

[0433] The system of this invention allows users inside an autonomous vehicle to easily check and change the vehicle's operating status and settings, and includes the following components:

[0434] System configuration and operation

[0435] 1. User Actions

[0436] The user enters their inquiry in text format into a chat box displayed on the vehicle's display or mobile device, such as "What is the current driving mode?"

[0437] 2. Transmission from the information processing device to the information processing infrastructure

[0438] The user's input is sent from an information processing device (smartphone, tablet, in-vehicle display, etc.) to an information processing infrastructure (central server or cloud infrastructure).

[0439] 3. Analysis of information processing infrastructure

[0440] The information processing infrastructure analyzes the received inquiry content using natural language processing technology (e.g., SpaCy or NLTK) and classifies the content into categories.

[0441] 4. Response generation using generative AI

[0442] The information processing platform then requests a generative AI (e.g., GPT-4) to generate a response based on the analysis results. The generative AI is trained in advance based on learning data and is able to generate appropriate responses.

[0443] 5. Sending and Displaying Responses

[0444] The information processing infrastructure transmits the generated response to the information processing device, which displays the response to the user.

[0445] Hardware and software used

[0446] Information processing devices: Smartphones, tablets, in-vehicle displays, etc.

[0447] Information processing infrastructure: central server or cloud infrastructure.

[0448] Natural language processing technology: SpaCy or NLTK.

[0449] Generative AI models: Advanced natural language generation AI such as GPT-4.

[0450] Specific examples

[0451] 1. Initial Inquiry

[0452] User Question: "What driving mode are you in?"

[0453] Category: Driving Mode

[0454] Generative AI response: "Autopilot mode is currently 'Highway mode'. Other options include 'City mode' and 'Parking assist mode'."

[0455] 2. Example prompts to be input to the generative AI model

[0456] User Question: "What driving mode are you in?"

[0457] Category: "Driving Mode"

[0458] Example response: "Self-driving mode is currently 'Highway Mode'. Other options include 'City Mode' and 'Parking Assist Mode'."

[0459] In this way, this system allows users to easily and intuitively check and change the operating status and settings of an autonomous vehicle, which is expected to improve the user experience and significantly enhance vehicle operability.

[0460] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0461] Step 1:

[0462] The user inputs the inquiry into the chat box using the in-vehicle display or a mobile terminal. The input text is transmitted from the user terminal to the information processing infrastructure. Specifically, the user inputs "Please tell me the current driving mode," and the data is transmitted to the information processing infrastructure via the information processing device.

[0463] Step 2:

[0464] The information processing platform receives inquiries sent by users. It analyzes the received data using natural language processing technology (e.g., SpaCy, NLTK) to extract important keywords from the inquiries. This analysis categorizes the inquiries as being related to "driving modes."

[0465] Step 3:

[0466] The information processing infrastructure sends a prompt to the generative AI model (e.g., GPT-4) based on the analysis results and category data. At this time, the prompt text includes the user's question and category information. An example of a prompt text is, "User question: 'What is the current driving mode?', Category: 'Driving mode'."

[0467] Step 4:

[0468] The generative AI model takes a prompt as input and generates a response based on it. The generative AI model uses pre-trained data to create an appropriate and grammatically correct response. The generated response might be something like, "Autopilot mode is currently 'Highway mode'. Other options are 'City mode' and 'Parking assist mode'."

[0469] Step 5:

[0470] The generated response is sent by the information processing platform to the user's information processing device. The information processing device displays the received response in a chat box and provides it to the user. This allows the user to immediately check the answer to their inquiry. Specifically, the information processing platform sends the response data obtained from the generative AI model to the user's terminal, and the terminal displays the response on its screen.

[0471] Step 6:

[0472] If the user wishes to ask a more detailed question or make an additional inquiry, they can enter another input into the chat box. This new input will then repeat the process from step 1. For example, if the user continues by asking, "Please tell me about other modes as well," the new input will be sent to the information processing infrastructure, which will then perform the same analysis and generate a response.

[0473] 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.

[0474] The system of this invention receives inquiries from users via a chat box and provides appropriate responses using generative AI. Furthermore, by combining it with an emotion engine, it is possible to recognize the user's emotions and provide more appropriate and personalized responses. The detailed operation of the system will be described based on this embodiment.

[0475] First, the user enters their inquiry into the chat box on their device. For example, they might enter, "I want to reset my password. What should I do?" At this time, the device is equipped with an emotion engine that analyzes the user's emotions based on the content, typing speed, and language characteristics of the input. The emotion analysis results (e.g., stress, anxiety, calm, etc.) are also sent to the server.

[0476] The device sends the user's inquiry and sentiment analysis results to the server. The server first stores the received message in a database and then passes the data to the message processing module. The message processing module uses natural language processing (NLP) technology to analyze the inquiry and classify the message into a specific category based on its content.

[0477] Once the message has been categorized, the server requests the generation AI to generate a response that takes the user's emotions into account. The generation AI generates an appropriate response to the question based on the training data, but also takes into account the analysis results from the emotion engine. For example, for a user who is "feeling stressed," the response could be tailored to something like, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[0478] The generated response is sent from the server to the device. The device analyzes the received response and displays it on the chat screen in a user-friendly format. This provides specific guidance, such as "To reset your password, access the settings menu and select 'Password Reset'."

[0479] If the user wants to continue with a more detailed question, they can type it again in the chat box and the process will be repeated. For example, if the user asks, "Can I do that from my phone too?", this question will also be analyzed by the emotion engine and sent to the server along with the emotion data. Subsequent processing will be carried out in the same way, and a response will be generated and displayed to the user via the device, such as, "Yes, you can also access the settings menu from your phone and select 'Reset Password'."

[0480] In this way, by combining this system with an emotion engine, it can provide personalized support according to the user's emotional state, achieving higher levels of satisfaction. Furthermore, by automating inquiry responses, it enables companies to reduce their workload and respond more quickly.

[0481] The processing flow will be explained below.

[0482] Step 1:

[0483] The user enters their inquiry into the chat box and presses the send button. For example, they enter an inquiry such as "I want to reset my password. What should I do?"

[0484] Step 2:

[0485] The device receives the user's input. At this time, the emotion engine analyzes the user's input, input speed, language selection, etc. to determine the emotion (e.g., stress, anxiety, calm, etc.). The determined emotion data is sent to the server along with the query content.

[0486] Step 3:

[0487] The device sends the query and emotion data to the server using protocols such as WebSocket or HTTP POST requests.

[0488] Step 4:

[0489] The server receives the request, stores the query in a database, and then passes the data to the message processing module.

[0490] Step 5:

[0491] The server uses a message processing module to analyze the content of the received inquiry, using natural language processing (NLP) techniques to analyze the content and then using a classification algorithm to classify it into a specific category (e.g., "account management" or "technical support").

[0492] Step 6:

[0493] The server requests the AI ​​to generate a response based on the analyzed message and category. At this time, emotion data is also passed to the AI, and the emotion is taken into account when generating the response.

[0494] Step 7:

[0495] Based on the inquiry content and emotional data received, the generation AI generates the optimal response while referring to training data. For example, for a user who is "feeling stressed," it generates the response, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[0496] Step 8:

[0497] The server formats the generated response data and sends it to the terminal in a structured data format such as JSON or XML.

[0498] Step 9:

[0499] The device will then analyze the response and display it in a user-friendly format on the chat screen, for example, "To reset your password, access the settings menu and select 'Password Reset'."

[0500] Step 10:

[0501] If the user has additional questions, they can type them again into the chat box and submit, and the process can be repeated to obtain additional information.

[0502] Step 11:

[0503] The server again analyzes the received inquiry, generates a response using AI if necessary, and sends it to the device. For example, in response to the question, "Can I do that from my smartphone?", it provides the response, "Yes, you can access the settings menu from your smartphone as well and select 'Password Reset'."

[0504] Through the above steps, the present invention combines emotion engines to realize a system that provides personalized support according to the user's emotional state.

[0505] Example 2

[0506] 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."

[0507] Conventional inquiry systems could only provide uniform responses to user inquiries, making it difficult to provide personalized responses that took into account the user's emotions and circumstances. This also led to declining user satisfaction, and the systems were unable to provide adequate responses in today's business environment, where rapid responses are required. Furthermore, the processes for analyzing inquiry content and generating responses were inefficient, making it difficult for companies to reduce their workload.

[0508] 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.

[0509] In this invention, the server includes: a means for a user to input inquiry content and send it to the server via a terminal; a means for the terminal to perform sentiment analysis on the user's input content; a means for the server to analyze the received inquiry content and sentiment analysis results and classify them into categories using natural language processing technology; a means for the server to generate an appropriate response using a generation AI based on the classified category and sentiment analysis results; and a means for the server to send the generated response to the terminal and for the terminal to display the response to the user. This enables personalized responses according to the user's emotions and situation, improving user satisfaction and enabling companies to reduce their workload and provide faster responses.

[0510] "User" means an individual or equivalent entity that inputs a query into the system.

[0511] A "terminal" is a hardware or software device that allows a user to enter a query into a chat box and send it to a server.

[0512] "Server" means a computer system for receiving and processing data sent by users, and is a device that includes a database, a message processing module, and a generating AI.

[0513] "Sentiment analysis" is the process of assessing a user's emotional state based on their input, typing speed, and language characteristics.

[0514] "Natural language processing technology" is a technology that allows computers to understand and process human language, and is a technology that analyzes the content of inquiries and classifies them into categories.

[0515] "Generative AI" is artificial intelligence that generates appropriate responses to user inquiries based on training data.

[0516] "Displaying a response" refers to the act of analyzing the response received by the terminal and displaying it on the chat screen in a format that is easy for the user to see.

[0517] "Training data" is a data set used to train a generative AI to generate appropriate responses.

[0518] A "prompt sentence" is an instruction sentence that instructs the generation AI to generate an appropriate response.

[0519] This invention is a system that generates an appropriate response based on the content of a user's inquiry entered through a chat box and the results of an analysis of the user's emotions. The system aims to increase user satisfaction by providing a personalized response that reflects the user's emotional state.

[0520] A user enters a query into the chat box from their device. For example, they might enter, "I want to reset my password. What should I do?" At this time, the device is equipped with an emotion engine that analyzes the user's input, input speed, and language characteristics to recognize their emotions. The analysis results (e.g., stress, anxiety, calm, etc.) are sent to the server along with the query.

[0521] The device sends the user's inquiry and the results of the sentiment analysis to the server, which temporarily stores the received data in a database. The data is then passed to the message processing module, which uses natural language processing (NLP) technology to analyze the inquiry and classify it into specific categories.

[0522] The server then uses the analyzed data to generate a response that takes into account the user's emotions, and requests the AI ​​to generate a response along with a prompt. Specific examples of prompts are as follows:

[0523] User asks: "I want to reset my password. How do I do that?"

[0524] Sentiment analysis result: "Stress"

[0525] Generate an appropriate response.

[0526] The generative AI generates the optimal response to the inquiry based on the training data. In doing so, it also takes into account the analysis results of the emotion engine, so if the user is "stressed," for example, it will generate a response such as, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[0527] The generated response is sent from the server to the device, which then analyzes it and displays it on the chat screen in a user-friendly format. For example, specific guidance such as "To reset your password, access the settings menu and select 'Password Reset'" is provided.

[0528] If the user wants to ask a more detailed question, they can type it again into the chat box. This is also analyzed by the emotion engine and sent to the server along with the emotion data. A similar process is followed to generate a response, such as "Yes, you can also access the settings menu on your smartphone and select 'Reset Password'," which is then displayed to the user via their device.

[0529] This system provides personalized support combined with sentiment analysis, improving user satisfaction. It also automates inquiry responses, reducing the workload of companies and enabling faster responses.

[0530] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0531] Step 1:

[0532] The user inputs the inquiry.

[0533] Specific operation: The user opens a chat box on their device and types in a question, for example, "I want to reset my password. How do I do this?"

[0534] Input: User text input

[0535] Output: Your input is saved to your device

[0536] Step 2:

[0537] The device passes the user's input to the emotion engine for emotion analysis.

[0538] Specific operation: The input text content is sent to the emotion engine in real time and analyzed for the user's emotions (stress, anxiety, calm, etc.).

[0539] Input: User text input

[0540] Output: Sentiment analysis result (e.g., stress, confidence level 0.86)

[0541] Step 3:

[0542] The device sends the emotion analysis results and the inquiry content to the server.

[0543] Specific operation: The sentiment analysis results are compiled in JSON format and sent to the server along with the query content via an HTTP request.

[0544] Input: Enquiry content and sentiment analysis results

[0545] Output: JSON data sent to the server

[0546] Step 4:

[0547] The server stores the received data in a database.

[0548] Specific operation: Parse the received JSON data and record the inquiry content and sentiment analysis results in a database.

[0549] Input: Received JSON data

[0550] Output: Data stored in the database

[0551] Step 5:

[0552] The server passes the data to the message processing module, which analyzes and classifies the query content.

[0553] Specific operation: The query content retrieved from the database is analyzed using natural language processing (NLP) technology and classified into categories such as "password reset."

[0554] Input: Query retrieved from the database

[0555] Output: The category (e.g., password reset)

[0556] Step 6:

[0557] The server creates a prompt sentence for the generation AI and asks it to generate a response.

[0558] Specific operation: A prompt sentence is generated based on the category classification results and sentiment analysis results and sent to the generation AI.

[0559] Input: Category classification results and sentiment analysis results

[0560] Output: Prompt sentence for the generation AI (Example: User inquiry: "I want to reset my password. What should I do?" Sentiment analysis result: "Stressed". Generate an appropriate response.)

[0561] Step 7:

[0562] The generative AI generates a response based on the prompt text.

[0563] How it works: Generative AI refers to a training dataset and generates an appropriate response, taking into account the user's emotions.

[0564] Input: Prompt for the generation AI

[0565] Output: The response generated (e.g. Don't worry, resetting your password is a simple process. Just follow the steps below.)

[0566] Step 8:

[0567] The server sends the generated response to the terminal.

[0568] Specific behavior: Receives the generated response and sends it to the user's device.

[0569] Input: The generated response

[0570] Output: Response data to the terminal

[0571] Step 9:

[0572] The terminal analyzes the received response and displays it to the user.

[0573] What it does: The device parses the received response and displays it on the chat screen in a user-friendly format, such as "Don't worry, resetting your password is a simple process. Just go to the settings menu and select 'Password Reset'."

[0574] Input: Received response data

[0575] Output: The response displayed in the user's chat screen

[0576] (Application example 2)

[0577] 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."

[0578] Conventional driver assistance systems and chatbots generate mechanical responses without considering the user's emotional state, which means they are unable to provide appropriate support, especially to drivers who are stressed or fatigued. There is also a need for systems that can respond in real time to inquiries and requests from drivers while driving, while also being flexible and taking into account the driver's emotional state. To solve this problem, a system incorporating emotion recognition functionality is required.

[0579] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0580] In this invention, the server includes a means for a user to input an inquiry into a chat box and send it to a data processing device via a terminal, a means for the data processing device to analyze the received inquiry and classify it into categories using natural language processing technology, and a means for the data processing device to generate an appropriate response using a generation AI based on the classified category and the emotion analysis result. This makes it possible to provide a driving support function according to the driver's emotional state, reducing stress and suggesting appropriate breaks.

[0581] "User" means an individual or entity who uses the system and inputs inquiries via a terminal.

[0582] A "chat box" is an interface for users to enter their inquiries.

[0583] "Terminal" refers to a computer, smartphone, or other device used by a user, which is a means for communicating with the server.

[0584] "Data Processing Device" means the computer server or cloud infrastructure used to receive and analyze user inquiries and generate responses.

[0585] "Natural language processing technology" is a technology for analyzing text data and performing semantic understanding and category classification.

[0586] A "category" is a classification criterion for classifying user inquiries into specific groups or classes.

[0587] "Emotion analysis result" is information indicating the emotional state extracted from the user's input content.

[0588] "Generative AI" is an artificial intelligence technology that generates appropriate responses to user inquiries based on training data.

[0589] "Response" means a system-generated reply or instruction to a user's inquiry.

[0590] "Driving support functions" are a series of functions to assist drivers while driving, including playing relaxation music and suggesting rest spots.

[0591] "Relaxation music" is music played to relieve the driver's stress and anxiety.

[0592] "Route Guidance" is a navigation function that provides directions for the driver to reach their destination.

[0593] To implement this invention, it is necessary to build a system that applies a chat system using an emotion analysis engine and generative AI to driving support. This system is composed of the following elements.

[0594] 1. User Interface:

[0595] A chat box is provided for drivers (users) to enter their inquiries or requests, which typically runs on the in-car infotainment system or on a smartphone.

[0596] 2. Sentiment Analysis Engine:

[0597] It analyzes user input in real time to identify their emotional state (e.g., stressed, anxious, calm, etc.) using the Python library TextBlob and Hugging Face Transformers.

[0598] 3. Data Processing Unit:

[0599] The system receives the user's inquiry along with the sentiment analysis results and categorizes them using natural language processing techniques, using the Hugging Face Transformers model.

[0600] 4. Generative AI Models:

[0601] The data processing device generates an appropriate response based on the categorized inquiry content received and the results of sentiment analysis, using generative AI models such as Microsoft's DialoGPT.

[0602] 5. Send and display the response:

[0603] The response generated by the data processing device is sent to the user's device and displayed in a format that the user can view, allowing the user to receive specific guidance and driving support in response to the request.

[0604] For example, if a driver types, "I'm very tired today. Is there anywhere nearby where I can rest?", the emotion analysis engine will identify the emotional state of "fatigue," and the data processing device will analyze and classify the content. The generative AI model will generate a response providing information on "nearby rest spots," and will display a reply on the user's device such as, "There are several places to rest nearby. The nearest rest spot is 10 km away, and we recommend you take a break there."

[0605] In addition, if a driver who is stressed by traffic jams types in, "I'm frustrated by the traffic jam. Please tell me how I can calm myself down right now," the emotion analysis engine will detect "frustration," and the generative AI model will generate a response suggesting things like "playing relaxation music" or "routes to avoid the traffic jam."

[0606] Example prompt sentence:

[0607] "I'm very tired today. Is there anywhere nearby where I can rest?"

[0608] "I'm frustrated with the traffic. Can you tell me how to calm myself down right now?"

[0609] This allows drivers to receive appropriate support in real time based on their emotional state while driving.

[0610] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0611] Step 1:

[0612] The user (driver) enters an inquiry or request into the chat box from the car's infotainment system or smartphone. The entered data is sent to the sentiment analysis engine. At this point, the input is the user's text message, for example, "I'm very tired today. Is there anywhere nearby where I can rest?"

[0613] Step 2:

[0614] The device sends the received user input to a sentiment analysis engine (e.g., TextBlob), which analyzes the input and identifies the user's emotional state (e.g., fatigue, stress). The input is the user's text message, and the output is the emotional state (e.g., "fatigue").

[0615] Step 3:

[0616] The device sends the user's input and the emotion analysis results to a data processing device, which analyzes and classifies the data using natural language processing technology to identify a category (e.g., "rest spot suggestions"). The input is the user's text message and emotional state information, and the output is category information.

[0617] Step 4:

[0618] The data processing device makes a generative AI model (e.g., DialoGPT) generate an appropriate response based on the classified category and the emotion analysis results. The generative AI model generates a response based on the training data. This process involves running a generative algorithm, which generates a generated response (e.g., "There are several places to rest nearby. The nearest rest spot is 10 km away, and we recommend you take a break there."). The input is category information and emotional state information, and the output is a response message.

[0619] Step 5:

[0620] The data processing device sends the generated response to the terminal. The terminal analyzes the received response and displays it in a format that can be confirmed by the user. Specifically, it displays a text message on the chat screen. The input is the generated response message, and the output is the response message that is displayed to the user.

[0621] Step 6:

[0622] If the user enters another question or request, the above steps are repeated again. For example, if the user adds, "Can I do that from my phone?", this new inquiry is also processed again through the sentiment analysis engine, data processing unit, and generative AI model. The input is the new user message, and the output is the corresponding response message.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] [Third embodiment]

[0627] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0628] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0629] 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).

[0630] 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.

[0631] 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.

[0632] 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).

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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."

[0639] In the system of this invention, a user makes an inquiry through a chat box, and a generation AI automatically responds to the inquiry. Specific embodiments will be described below.

[0640] First, a user uses their own device to input a question into the chat box provided by the system. For example, they may input a specific question such as "I want to reset my password." This input is done through the device's interface, and the input is sent to the server by the device.

[0641] When the device sends the user's input, the server receives the message. The received message is analyzed using natural language processing (NLP) technology. As a result of the analysis, the message content is classified into a certain category. For example, categories such as "account management" and "technical support" are possible. This categorization identifies the field to which the inquiry relates.

[0642] Based on the analyzed message and category, the server requests the AI ​​to generate a response. The AI ​​has previously learned from the training data and can generate appropriate responses to similar queries. For example, the AI ​​might generate the response, "To reset your password, access the settings menu and select 'Password Reset'."

[0643] The server generates a response and sends it to the device, which displays it on the chat screen so the user can see it. If the user wants to ask a more detailed question, they can type it again in the chat box and the process repeats.

[0644] As a concrete example, consider a situation where the user continues to ask, "Can I do that from my smartphone?" This question is also sent from the device to the server, which analyzes it and generates an appropriate response. For example, a response such as "Yes, you can access the settings menu from your smartphone as well and select 'Reset Password'" is generated and displayed to the user.

[0645] In this way, the system is able to respond quickly and accurately to diverse and specialized inquiries from users, significantly reducing the man-hours required for companies to respond to inquiries and improving the user experience.In addition, the system is capable of providing automated responses 24 hours a day, 365 days a year, so it can help resolve users' questions at any time.

[0646] The processing flow will be explained below.

[0647] Step 1:

[0648] The user enters their inquiry into the chat box and presses the send button. For example, they enter an inquiry such as "I want to reset my password. What should I do?"

[0649] Step 2:

[0650] The device takes the user's input and sends the query to the server using a protocol such as WebSocket or an HTTP POST request.

[0651] Step 3:

[0652] The server stores the received inquiry in a database and passes it to the message processing module.

[0653] Step 4:

[0654] The server analyzes the query content through a message processing module and uses natural language processing (NLP) technology to interpret the content.

[0655] Step 5:

[0656] Based on the analysis results, the server classifies the inquiry into categories such as "account management" or "technical support." This classification identifies the field of the inquiry.

[0657] Step 6:

[0658] The server requests the AI ​​to generate an appropriate response based on the classification category. The AI ​​then refers to training data and generates the optimal response based on past response history.

[0659] Step 7:

[0660] The server receives the response created by the AI, formats it in a structured data format (such as JSON or XML), and sends it to the terminal.

[0661] Step 8:

[0662] The device will parse the response it receives and display it in a user-friendly chat box, for example, "To reset your password, access the settings menu and select 'Password Reset'."

[0663] Step 9:

[0664] If the user wants to enter a question, they can re-enter it in the chat box and submit, and the process will repeat, allowing the user to obtain additional information.

[0665] Step 10:

[0666] The server analyzes the received inquiry again, generates a response using AI as needed, and sends it to the device. By repeatedly generating responses, continuous support is provided. For example, in response to the question, "Can I do that from my smartphone?", the server responds, "Yes, you can access the settings menu from your smartphone as well and select 'Password Reset'."

[0667] Example 1

[0668] 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."

[0669] Conventional inquiry response systems are required to respond to user inquiries accurately and quickly. However, conventional systems require manual intervention and are inefficient. It is also difficult to provide consistent responses to multiple inquiries, limiting the improvement of user satisfaction. Furthermore, in situations where automated responses are required 24 hours a day, 365 days a year, there are significant constraints on human resources. To solve these issues, a system that utilizes advanced natural language processing technology and generative AI models to automatically and efficiently respond to inquiries is needed.

[0670] 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.

[0671] In this invention, the server includes: a means for a user to input an inquiry into an input device and transmit the inquiry to a central processing unit via an information processing terminal; a means for the central processing unit to analyze the received inquiry and classify it into categories using natural language processing technology; a means for the central processing unit to generate an appropriate response using a generative AI model based on the classified category; a means for the central processing unit to transmit the generated response to the information processing terminal, which then displays the response to the user; a means for automatically generating a prompt sentence for generating a response based on the inquiry for the generative AI model; a means for transmitting the generated response using a standard communication protocol; and a means for providing a continuous response that can respond to multiple inquiries. This enables accurate and prompt responses to a variety of user inquiries, improving user satisfaction and reducing companies' response workload. Furthermore, the automated response system enables 24 / 7 response, overcoming human resource constraints.

[0672] "User" means an individual or legal entity that makes an inquiry using this system.

[0673] An "input device" is a device (such as a keyboard or touch screen) that allows a user to input a query.

[0674] An "information processing terminal" is a device (e.g., a smartphone or PC) that transmits and receives data between a user and a central processing unit.

[0675] A "central processing unit" is a computer server that analyzes and processes received data and generates a response.

[0676] "Natural language processing technology" is a technology that enables computers to understand and analyze natural human language.

[0677] A "generative AI model" is an artificial intelligence system that learns from training data in advance and generates appropriate responses to inquiries.

[0678] A "prompt sentence" is an input sentence provided to a generative AI model to prompt it to generate a response.

[0679] A "standard communication protocol" is a common communication protocol (e.g., HTTP or HTTPS) used to send and receive data.

[0680] MODE FOR CARRYING OUT THE INVENTION

[0681] In the system of this invention, a user makes an inquiry through a chat box, and a generation AI automatically responds to the inquiry. Specific embodiments will be described below.

[0682] First, a user uses their own information processing terminal (e.g., a smartphone or PC) to input a question into a chat box provided by the system. For example, they input a specific question such as "I want to reset my password." This input is made using the terminal's input device (e.g., a keyboard or touch screen), and the data is sent by the terminal to the central processing unit.

[0683] The terminal captures the data entered by the user and transmits it to a central processing unit over a network, using standard communication protocols (e.g., HTTP or HTTPS).

[0684] The server (central processing unit) receives messages sent by users. The received data is analyzed using natural language processing technology. Specifically, the server performs processes such as tokenizing the message, morphological analysis, and categorizing it. For example, a message saying "I would like to reset my password" would be classified as "Account Management."

[0685] Based on the analysis results, the central processing unit requests the generative AI model to generate a response. The generative AI model is a pre-trained model that receives the input data necessary to generate an appropriate response. A prompt sentence is then used as input to the generative AI model. The following prompt sentence is an example:

[0686] Prompt: "I want to reset my password. How do I do this?"

[0687] Response: "To reset your password, go to the Settings menu and select 'Password Reset'."

[0688]

[0689] Prompt: "Can I do that from my phone?"

[0690] Response: "Yes, you can access the settings menu on your phone as well and select 'Reset Password'."

[0691] Based on the message received, the generative AI model uses training data to generate an appropriate response. Response generation is done using advanced machine learning algorithms such as the Transformer model. For example, the generative AI model might generate the response, "To reset your password, visit the Settings menu and select 'Password Reset'."

[0692] The server then sends the generated response back to the information processing terminal, again using standard communication protocols. The terminal displays the received response on the chat screen, allowing the user to review its content. If the user wishes to ask another question, they can enter it in the chat box again, and the same process is repeated.

[0693] Throughout this process, users can receive appropriate and prompt responses to their questions, which improves user satisfaction while reducing the company's response time. Furthermore, the automated response system allows for 24 / 7 support, overcoming human resource constraints.

[0694] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0695] Step 1:

[0696] The user inputs a question into the input device.

[0697] Specifically, a user uses the keyboard or touch screen of an information processing device (e.g., a smartphone or PC) to input a question into a chat box. For example, the user might input a question such as "I want to reset my password." The input at this point is text data of the user's inquiry.

[0698] Step 2:

[0699] The terminal sends the entered question to the server.

[0700] Specifically, the terminal sends text data stating "I would like to reset my password" to the server using a standard communication protocol such as an HTTP POST request. The input is the user's question data, and the output is the request data for sending it.

[0701] Step 3:

[0702] The server receives the user's question and applies natural language processing techniques.

[0703] Specifically, the server analyzes the received text and performs tokenization, morphological analysis, and categorization. For example, a message saying "I want to reset my password" is classified into the "account management" category. The input is the user's question data, and the output is the analyzed tokenized data and category information.

[0704] Step 4:

[0705] The server requests a generative AI model to generate a response based on the category.

[0706] Specifically, the server provides a prompt sentence to the generative AI model based on the analysis results and requests the model to generate an appropriate response. For example, based on the analyzed category "account management," the server inputs a prompt sentence to the generative AI model. The input is the prompt sentence and category information, and the output is a response generation request to the generative AI model.

[0707] Step 5:

[0708] A generative AI model generates a response based on the prompt.

[0709] Specifically, a generative AI model (e.g., a Transformer model) receives a prompt and uses training data to generate an appropriate response, such as "To reset your password, visit the Settings menu and select 'Password Reset.'" The input is the prompt, and the output is the generated response text.

[0710] Step 6:

[0711] The server sends the generated response to the terminal.

[0712] Specifically, the server receives the response from the generative AI model and sends it to the information processing terminal using an HTTP response. The input is the response text from the generative AI model, and the output is the response text sent as HTTP response data.

[0713] Step 7:

[0714] The terminal displays the received response to the user.

[0715] Specifically, the terminal displays the response received from the server on the chat screen, allowing the user to check how to resolve the issue. For example, a message such as "To reset your password, access the settings menu and select 'Password Reset'" may be displayed on the chat screen. The input is the response data received from the server, and the output is the response message displayed to the user.

[0716] (Application example 1)

[0717] 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."

[0718] There is a demand for a system that allows passengers in autonomous vehicles to easily check and change the vehicle's operating status and settings. However, conventional systems require passengers to perform cumbersome operations to directly check the operating status or change settings, resulting in low usability. Furthermore, there is a problem in that the system contains a lot of technical information that is difficult for ordinary passengers to understand, and lacks an intuitive interface.

[0719] 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.

[0720] In this invention, the server includes a means for a user to input an inquiry into a chat box and send it to an information processing platform via an information processing device, a means for the information processing platform to analyze the received inquiry and classify it into categories using natural language processing technology, and a means for generating an appropriate response using a generation AI based on the categories classified by the information processing platform. This allows a user to input an inquiry via an in-vehicle display or mobile device, and the vehicle's operating status and settings can be explained and changed accordingly.

[0721] "User" refers to a person who uses the System to make an inquiry.

[0722] "Chat box" refers to an interface that allows users to enter inquiries or messages in text format.

[0723] "Information processing device" refers to devices used by users, such as smartphones, tablets, and display devices inside vehicles.

[0724] "Information processing infrastructure" refers to a central server or cloud infrastructure that analyzes user inquiries and generates appropriate responses using generative AI.

[0725] "Natural language processing technology" refers to technology that analyzes users' text messages and understands their intent and meaning.

[0726] "Category" refers to the field or topic into which the analyzed inquiry content is categorized. Examples include "driving mode" and "navigation settings."

[0727] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to generate appropriate responses to user inquiries.

[0728] "Response" refers to the answer or instruction generated by the AI ​​based on the user's inquiry.

[0729] "In-vehicle displays" refer to display devices used by users inside a vehicle, typically installed in the driver's seat or rear seats.

[0730] "Mobile terminal" refers to a mobile device such as a smartphone or tablet carried by a user.

[0731] "Inquiry" refers to a question or request made by a user to the system.

[0732] "Operating status" refers to information indicating the current operating status and mode setting of the vehicle.

[0733] The system of this invention allows users inside an autonomous vehicle to easily check and change the vehicle's operating status and settings, and includes the following components:

[0734] System configuration and operation

[0735] 1. User Actions

[0736] The user enters their inquiry in text format into a chat box displayed on the vehicle's display or mobile device, such as "What is the current driving mode?"

[0737] 2. Transmission from the information processing device to the information processing infrastructure

[0738] The user's input is sent from an information processing device (smartphone, tablet, in-vehicle display, etc.) to an information processing infrastructure (central server or cloud infrastructure).

[0739] 3. Analysis of information processing infrastructure

[0740] The information processing infrastructure analyzes the received inquiry content using natural language processing technology (e.g., SpaCy or NLTK) and classifies the content into categories.

[0741] 4. Response generation using generative AI

[0742] The information processing platform then requests a generative AI (e.g., GPT-4) to generate a response based on the analysis results. The generative AI is trained in advance based on learning data and is able to generate appropriate responses.

[0743] 5. Sending and Displaying Responses

[0744] The information processing infrastructure transmits the generated response to the information processing device, which displays the response to the user.

[0745] Hardware and software used

[0746] Information processing devices: smartphones, tablets, in-vehicle displays, etc.

[0747] Information processing infrastructure: central server or cloud infrastructure.

[0748] Natural language processing technology: SpaCy or NLTK.

[0749] Generative AI models: Advanced natural language generation AI such as GPT-4.

[0750] Specific examples

[0751] 1. Initial Inquiry

[0752] User Question: "What driving mode are you in?"

[0753] Category: Driving Mode

[0754] Generative AI response: "Autopilot mode is currently 'Highway mode'. Other options include 'City mode' and 'Parking assist mode'."

[0755] 2. Example prompts to be input to the generative AI model

[0756] User Question: "What driving mode are you in?"

[0757] Category: "Driving Mode"

[0758] Example response: "Self-driving mode is currently 'Highway Mode'. Other options include 'City Mode' and 'Parking Assist Mode'."

[0759] In this way, this system allows users to easily and intuitively check and change the operating status and settings of an autonomous vehicle, which is expected to improve the user experience and significantly enhance vehicle operability.

[0760] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0761] Step 1:

[0762] The user inputs the inquiry into the chat box using the in-vehicle display or a mobile terminal. The input text is transmitted from the user terminal to the information processing infrastructure. Specifically, the user inputs "Please tell me the current driving mode," and the data is transmitted to the information processing infrastructure via the information processing device.

[0763] Step 2:

[0764] The information processing platform receives inquiries sent by users. It analyzes the received data using natural language processing technology (e.g., SpaCy, NLTK) to extract important keywords from the inquiries. This analysis categorizes the inquiries as being related to "driving modes."

[0765] Step 3:

[0766] The information processing infrastructure sends a prompt to the generative AI model (e.g., GPT-4) based on the analysis results and category data. At this time, the prompt text includes the user's question and category information. An example of a prompt text is, "User question: 'What is the current driving mode?', Category: 'Driving mode'."

[0767] Step 4:

[0768] The generative AI model takes a prompt as input and generates a response based on it. The generative AI model uses pre-trained data to create an appropriate and grammatically correct response. The generated response might be something like, "Autopilot mode is currently 'Highway mode'. Other options are 'City mode' and 'Parking assist mode'."

[0769] Step 5:

[0770] The generated response is sent by the information processing platform to the user's information processing device. The information processing device displays the received response in a chat box and provides it to the user. This allows the user to immediately check the answer to their inquiry. Specifically, the information processing platform sends the response data obtained from the generative AI model to the user's terminal, and the terminal displays the response on its screen.

[0771] Step 6:

[0772] If the user wishes to ask a more detailed question or make an additional inquiry, they can enter another input into the chat box. This new input will then repeat the process from step 1. For example, if the user continues by asking, "Please tell me about other modes as well," the new input will be sent to the information processing infrastructure, which will then perform the same analysis and generate a response.

[0773] 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.

[0774] The system of this invention receives inquiries from users via a chat box and provides appropriate responses using generative AI. Furthermore, by combining it with an emotion engine, it is possible to recognize the user's emotions and provide more appropriate and personalized responses. The detailed operation of the system will be described based on this embodiment.

[0775] First, the user enters their inquiry into the chat box on their device. For example, they might enter, "I want to reset my password. What should I do?" At this time, the device is equipped with an emotion engine that analyzes the user's emotions based on the content, typing speed, and language characteristics of the input. The emotion analysis results (e.g., stress, anxiety, calm, etc.) are also sent to the server.

[0776] The device sends the user's inquiry and sentiment analysis results to the server. The server first stores the received message in a database and then passes the data to the message processing module. The message processing module uses natural language processing (NLP) technology to analyze the inquiry and classify the message into a specific category based on its content.

[0777] Once the message has been categorized, the server requests the generation AI to generate a response that takes the user's emotions into account. The generation AI generates an appropriate response to the question based on the training data, but also takes into account the analysis results from the emotion engine. For example, for a user who is "feeling stressed," the response could be tailored to something like, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[0778] The generated response is sent from the server to the device. The device analyzes the received response and displays it on the chat screen in a user-friendly format. This provides specific guidance, such as "To reset your password, access the settings menu and select 'Password Reset'."

[0779] If the user wants to continue with a more detailed question, they can type it again in the chat box and the process will be repeated. For example, if the user asks, "Can I do that from my phone too?", this question will also be analyzed by the emotion engine and sent to the server along with the emotion data. Subsequent processing will be carried out in the same way, and a response will be generated and displayed to the user via the device, such as, "Yes, you can also access the settings menu from your phone and select 'Reset Password'."

[0780] In this way, by combining this system with an emotion engine, it can provide personalized support according to the user's emotional state, achieving higher levels of satisfaction. Furthermore, by automating inquiry responses, it enables companies to reduce their workload and respond more quickly.

[0781] The processing flow will be explained below.

[0782] Step 1:

[0783] The user enters their inquiry into the chat box and presses the send button. For example, they enter an inquiry such as "I want to reset my password. What should I do?"

[0784] Step 2:

[0785] The device receives the user's input. At this time, the emotion engine analyzes the user's input, input speed, language selection, etc. to determine the emotion (e.g., stress, anxiety, calm, etc.). The determined emotion data is sent to the server along with the query content.

[0786] Step 3:

[0787] The device sends the query and emotion data to the server using protocols such as WebSocket or HTTP POST requests.

[0788] Step 4:

[0789] The server receives the request, stores the query in a database, and then passes the data to the message processing module.

[0790] Step 5:

[0791] The server uses a message processing module to analyze the content of the received inquiry, using natural language processing (NLP) techniques to analyze the content and then using a classification algorithm to classify it into a specific category (e.g., "account management" or "technical support").

[0792] Step 6:

[0793] The server requests the AI ​​to generate a response based on the analyzed message and category. At this time, emotion data is also passed to the AI, and the emotion is taken into account when generating the response.

[0794] Step 7:

[0795] Based on the inquiry content and emotional data received, the generation AI generates the optimal response while referring to training data. For example, for a user who is "feeling stressed," it generates the response, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[0796] Step 8:

[0797] The server formats the generated response data and sends it to the terminal in a structured data format such as JSON or XML.

[0798] Step 9:

[0799] The device will then analyze the response and display it in a user-friendly format on the chat screen, for example, "To reset your password, access the settings menu and select 'Password Reset'."

[0800] Step 10:

[0801] If the user has additional questions, they can type them again into the chat box and submit, and the process can be repeated to obtain additional information.

[0802] Step 11:

[0803] The server again analyzes the received inquiry, generates a response using AI if necessary, and sends it to the device. For example, in response to the question, "Can I do that from my smartphone?", it provides the response, "Yes, you can access the settings menu from your smartphone as well and select 'Password Reset'."

[0804] Through the above steps, the present invention combines emotion engines to realize a system that provides personalized support according to the user's emotional state.

[0805] Example 2

[0806] 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."

[0807] Conventional inquiry systems could only provide uniform responses to user inquiries, making it difficult to provide personalized responses that took into account the user's emotions and circumstances. This also led to declining user satisfaction, and the systems were unable to provide adequate responses in today's business environment, where rapid responses are required. Furthermore, the processes for analyzing inquiry content and generating responses were inefficient, making it difficult for companies to reduce their workload.

[0808] 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.

[0809] In this invention, the server includes: a means for a user to input inquiry content and send it to the server via a terminal; a means for the terminal to perform sentiment analysis on the user's input content; a means for the server to analyze the received inquiry content and sentiment analysis results and classify them into categories using natural language processing technology; a means for the server to generate an appropriate response using a generation AI based on the classified category and sentiment analysis results; and a means for the server to send the generated response to the terminal and for the terminal to display the response to the user. This enables personalized responses according to the user's emotions and situation, improving user satisfaction and enabling companies to reduce their workload and provide faster responses.

[0810] "User" means an individual or equivalent entity that inputs a query into the system.

[0811] A "terminal" is a hardware or software device that allows a user to enter a query into a chat box and send it to a server.

[0812] "Server" means a computer system for receiving and processing data sent by users, and is a device that includes a database, a message processing module, and a generating AI.

[0813] "Sentiment analysis" is the process of assessing a user's emotional state based on their input, typing speed, and language characteristics.

[0814] "Natural language processing technology" is a technology that allows computers to understand and process human language, and is a technology that analyzes the content of inquiries and classifies them into categories.

[0815] "Generative AI" is artificial intelligence that generates appropriate responses to user inquiries based on training data.

[0816] "Displaying a response" refers to the act of analyzing the response received by the terminal and displaying it on the chat screen in a format that is easy for the user to see.

[0817] "Training data" is a data set used to train a generative AI to generate appropriate responses.

[0818] A "prompt sentence" is an instruction sentence that instructs the generation AI to generate an appropriate response.

[0819] This invention is a system that generates an appropriate response based on the content of a user's inquiry entered through a chat box and the results of an analysis of the user's emotions. The system aims to increase user satisfaction by providing a personalized response that corresponds to the user's emotional state.

[0820] A user enters a query into the chat box from their device. For example, they might enter, "I want to reset my password. What should I do?" At this time, the device is equipped with an emotion engine that analyzes the user's input, input speed, and language characteristics to recognize their emotions. The analysis results (e.g., stress, anxiety, calm, etc.) are sent to the server along with the query.

[0821] The device sends the user's inquiry and the results of the sentiment analysis to the server, which temporarily stores the received data in a database. The data is then passed to the message processing module, which uses natural language processing (NLP) technology to analyze the inquiry and classify it into specific categories.

[0822] The server then uses the analyzed data to generate a response that takes into account the user's emotions, and requests the AI ​​to generate a response along with a prompt. Specific examples of prompts are as follows:

[0823] User asks: "I want to reset my password. How do I do that?"

[0824] Sentiment analysis result: "Stress"

[0825] Generate an appropriate response.

[0826] The generative AI generates the optimal response to the inquiry based on the training data. In doing so, it also takes into account the analysis results of the emotion engine, so if the user is "stressed," for example, it will generate a response such as, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[0827] The generated response is sent from the server to the device, which then analyzes it and displays it on the chat screen in a user-friendly format. For example, specific guidance such as "To reset your password, access the settings menu and select 'Password Reset'" is provided.

[0828] If the user wants to ask a more detailed question, they can type it again into the chat box. This is also analyzed by the emotion engine and sent to the server along with the emotion data. A similar process is followed to generate a response, such as "Yes, you can also access the settings menu on your smartphone and select 'Reset Password'," which is then displayed to the user via their device.

[0829] This system provides personalized support combined with sentiment analysis, improving user satisfaction. It also automates inquiry responses, reducing the workload of companies and enabling faster responses.

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

[0831] Step 1:

[0832] The user inputs the inquiry.

[0833] Specific operation: The user opens a chat box on their device and types in a question. For example, they type, "I want to reset my password. How do I do this?"

[0834] Input: User text input

[0835] Output: Your input is saved to your device

[0836] Step 2:

[0837] The device passes the user's input to the emotion engine for emotion analysis.

[0838] Specific operation: The input text content is sent to the emotion engine in real time and analyzed for the user's emotions (stress, anxiety, calm, etc.).

[0839] Input: User text input

[0840] Output: Sentiment analysis result (e.g., stress, confidence level 0.86)

[0841] Step 3:

[0842] The device sends the emotion analysis results and the inquiry content to the server.

[0843] Specific operation: The sentiment analysis results are compiled in JSON format and sent to the server along with the query content via an HTTP request.

[0844] Input: Enquiry content and sentiment analysis results

[0845] Output: JSON data sent to the server

[0846] Step 4:

[0847] The server stores the received data in a database.

[0848] Specific operation: Parse the received JSON data and record the inquiry content and sentiment analysis results in a database.

[0849] Input: Received JSON data

[0850] Output: Data stored in the database

[0851] Step 5:

[0852] The server passes the data to the message processing module, which analyzes and classifies the query content.

[0853] Specific operation: The query content retrieved from the database is analyzed using natural language processing (NLP) technology and classified into categories such as "password reset."

[0854] Input: Query retrieved from the database

[0855] Output: The category (e.g., password reset)

[0856] Step 6:

[0857] The server creates a prompt sentence for the generation AI and asks it to generate a response.

[0858] Specific operation: A prompt sentence is generated based on the category classification results and sentiment analysis results and sent to the generation AI.

[0859] Input: Category classification results and sentiment analysis results

[0860] Output: Prompt sentence for the generation AI (Example: User inquiry: "I want to reset my password. What should I do?" Sentiment analysis result: "Stressed". Generate an appropriate response.)

[0861] Step 7:

[0862] The generative AI generates a response based on the prompt text.

[0863] How it works: Generative AI refers to a training dataset and generates an appropriate response, taking into account the user's emotions.

[0864] Input: Prompt for the generation AI

[0865] Output: The response generated (e.g. Don't worry, resetting your password is a simple process. Just follow the steps below.)

[0866] Step 8:

[0867] The server sends the generated response to the terminal.

[0868] Specific behavior: Receives the generated response and sends it to the user's device.

[0869] Input: The generated response

[0870] Output: Response data to the terminal

[0871] Step 9:

[0872] The terminal analyzes the received response and displays it to the user.

[0873] What it does: The device parses the received response and displays it on the chat screen in a user-friendly format, such as "Don't worry, resetting your password is a simple process. Just go to the settings menu and select 'Password Reset'."

[0874] Input: Received response data

[0875] Output: The response displayed in the user's chat screen

[0876] (Application example 2)

[0877] 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."

[0878] Conventional driver assistance systems and chatbots generate mechanical responses without considering the user's emotional state, which means they are unable to provide appropriate support, especially to drivers who are stressed or fatigued. There is also a need for systems that can respond in real time to inquiries and requests from drivers while driving, while also being flexible and taking into account the driver's emotional state. To solve this problem, a system incorporating emotion recognition functionality is required.

[0879] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0880] In this invention, the server includes a means for a user to input an inquiry into a chat box and send it to a data processing device via a terminal, a means for the data processing device to analyze the received inquiry and classify it into categories using natural language processing technology, and a means for the data processing device to generate an appropriate response using a generation AI based on the classified category and the emotion analysis result. This makes it possible to provide a driving support function according to the driver's emotional state, reducing stress and suggesting appropriate breaks.

[0881] "User" means an individual or entity who uses the system and inputs inquiries via a terminal.

[0882] A "chat box" is an interface for users to enter their inquiries.

[0883] "Terminal" refers to a computer, smartphone, or other device used by a user, which is a means for communicating with the server.

[0884] "Data Processing Device" means the computer server or cloud infrastructure used to receive and analyze user inquiries and generate responses.

[0885] "Natural language processing technology" is a technology for analyzing text data and performing semantic understanding and category classification.

[0886] A "category" is a classification criterion for classifying user inquiries into specific groups or classes.

[0887] "Emotion analysis result" is information indicating the emotional state extracted from the user's input content.

[0888] "Generative AI" is an artificial intelligence technology that generates appropriate responses to user inquiries based on training data.

[0889] "Response" means a system-generated reply or instruction to a user's inquiry.

[0890] "Driving support functions" are a series of functions to assist drivers while driving, including playing relaxation music and suggesting rest spots.

[0891] "Relaxation music" is music played to relieve the driver's stress and anxiety.

[0892] "Route Guidance" is a navigation function that provides directions for the driver to reach their destination.

[0893] To implement this invention, it is necessary to build a system that applies a chat system using an emotion analysis engine and generative AI to driving support. This system is composed of the following elements.

[0894] 1. User Interface:

[0895] A chat box is provided for drivers (users) to enter their inquiries or requests, which typically runs on the in-car infotainment system or on a smartphone.

[0896] 2. Sentiment Analysis Engine:

[0897] It analyzes user input in real time to identify their emotional state (e.g., stressed, anxious, calm, etc.) using the Python library TextBlob and Hugging Face Transformers.

[0898] 3. Data Processing Unit:

[0899] The system receives the user's inquiry along with the sentiment analysis results and categorizes them using natural language processing techniques, using the Hugging Face Transformers model.

[0900] 4. Generative AI Models:

[0901] The data processing device generates an appropriate response based on the categorized inquiry content received and the results of sentiment analysis, using generative AI models such as Microsoft's DialoGPT.

[0902] 5. Send and display the response:

[0903] The response generated by the data processing device is sent to the user's device and displayed in a format that the user can view, allowing the user to receive specific guidance and driving support in response to the request.

[0904] For example, if a driver types, "I'm very tired today. Is there anywhere nearby where I can rest?", the emotion analysis engine will identify the emotional state of "fatigue," and the data processing device will analyze and classify the content. The generative AI model will generate a response providing information on "nearby rest spots," and will display a reply on the user's device such as, "There are several places to rest nearby. The nearest rest spot is 10 km away, and we recommend you take a break there."

[0905] In addition, if a driver who is stressed by traffic jams types in, "I'm frustrated by the traffic jam. Please tell me how I can calm myself down right now," the emotion analysis engine will detect "frustration," and the generative AI model will generate a response suggesting things like "playing relaxation music" or "routes to avoid the traffic jam."

[0906] Example prompt sentence:

[0907] "I'm very tired today. Is there anywhere nearby where I can rest?"

[0908] "I'm frustrated with the traffic. Can you tell me how to calm myself down right now?"

[0909] This allows drivers to receive appropriate support in real time based on their emotional state while driving.

[0910] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0911] Step 1:

[0912] The user (driver) enters an inquiry or request into the chat box from the car's infotainment system or smartphone. The entered data is sent to the sentiment analysis engine. At this point, the input is the user's text message, for example, "I'm very tired today. Is there anywhere nearby where I can rest?"

[0913] Step 2:

[0914] The device sends the received user input to a sentiment analysis engine (e.g., TextBlob), which analyzes the input and identifies the user's emotional state (e.g., fatigue, stress). The input is the user's text message, and the output is the emotional state (e.g., "fatigue").

[0915] Step 3:

[0916] The device sends the user's input and the emotion analysis results to a data processing device, which analyzes and classifies the data using natural language processing technology to identify a category (e.g., "rest spot suggestions"). The input is the user's text message and emotional state information, and the output is category information.

[0917] Step 4:

[0918] The data processing device makes a generative AI model (e.g., DialoGPT) generate an appropriate response based on the classified category and the emotion analysis results. The generative AI model generates a response based on the training data. This process involves running a generative algorithm, which generates a generated response (e.g., "There are several places to rest nearby. The nearest rest spot is 10 km away, and we recommend you take a break there."). The input is category information and emotional state information, and the output is a response message.

[0919] Step 5:

[0920] The data processing device sends the generated response to the terminal. The terminal analyzes the received response and displays it in a format that can be confirmed by the user. Specifically, it displays a text message on the chat screen. The input is the generated response message, and the output is the response message that is displayed to the user.

[0921] Step 6:

[0922] If the user enters another question or request, the above steps are repeated again. For example, if the user adds, "Can I do that from my phone?", this new inquiry is also processed again through the sentiment analysis engine, data processing unit, and generative AI model. The input is the new user message, and the output is the corresponding response message.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] [Fourth embodiment]

[0927] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0928] 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.

[0929] 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).

[0930] 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.

[0931] 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.

[0932] 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).

[0933] 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.

[0934] 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.

[0935] 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.

[0936] 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.

[0937] 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.

[0938] 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.

[0939] 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."

[0940] In the system of this invention, a user makes an inquiry through a chat box, and a generation AI automatically responds to the inquiry. Specific embodiments will be described below.

[0941] First, a user uses their own device to input a question into the chat box provided by the system. For example, they may input a specific question such as "I want to reset my password." This input is done through the device's interface, and the input is sent to the server by the device.

[0942] When the device sends the user's input, the server receives the message. The received message is analyzed using natural language processing (NLP) technology. As a result of the analysis, the message content is classified into a certain category. For example, categories such as "account management" and "technical support" are possible. This categorization identifies the field to which the inquiry relates.

[0943] Based on the analyzed message and category, the server requests the AI ​​to generate a response. The AI ​​has previously learned from the training data and can generate appropriate responses to similar queries. For example, the AI ​​might generate the response, "To reset your password, access the settings menu and select 'Password Reset'."

[0944] The server generates a response and sends it to the device, which displays it on the chat screen so the user can see it. If the user wants to ask a more detailed question, they can type it again in the chat box and the process repeats.

[0945] As a concrete example, consider a situation where the user continues to ask, "Can I do that from my smartphone?" This question is also sent from the device to the server, which analyzes it and generates an appropriate response. For example, a response such as "Yes, you can access the settings menu from your smartphone as well and select 'Reset Password'" is generated and displayed to the user.

[0946] In this way, the system is able to respond quickly and accurately to diverse and specialized inquiries from users, significantly reducing the man-hours required for companies to respond to inquiries and improving the user experience.In addition, the system is capable of providing automated responses 24 hours a day, 365 days a year, so it can help resolve users' questions at any time.

[0947] The processing flow will be explained below.

[0948] Step 1:

[0949] The user enters their inquiry into the chat box and presses the send button. For example, they enter an inquiry such as "I want to reset my password. What should I do?"

[0950] Step 2:

[0951] The device takes the user's input and sends the query to the server using a protocol such as WebSocket or an HTTP POST request.

[0952] Step 3:

[0953] The server stores the received inquiry in a database and passes it to the message processing module.

[0954] Step 4:

[0955] The server analyzes the query content through a message processing module and uses natural language processing (NLP) technology to interpret the content.

[0956] Step 5:

[0957] Based on the analysis results, the server classifies the inquiry into categories such as "account management" or "technical support." This classification identifies the field of the inquiry.

[0958] Step 6:

[0959] The server requests the AI ​​to generate an appropriate response based on the classification category. The AI ​​then refers to training data and generates the optimal response based on past response history.

[0960] Step 7:

[0961] The server receives the response created by the AI, formats it in a structured data format (such as JSON or XML), and sends it to the terminal.

[0962] Step 8:

[0963] The device will parse the response it receives and display it in a user-friendly chat box, for example, "To reset your password, access the settings menu and select 'Password Reset'."

[0964] Step 9:

[0965] If the user wants to enter a question, they can re-enter it in the chat box and submit, and the process will repeat, allowing the user to obtain additional information.

[0966] Step 10:

[0967] The server analyzes the received inquiry again, generates a response using AI as needed, and sends it to the device. By repeatedly generating responses, continuous support is provided. For example, in response to the question, "Can I do that from my smartphone?", the server responds, "Yes, you can access the settings menu from your smartphone as well and select 'Password Reset'."

[0968] Example 1

[0969] 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."

[0970] Conventional inquiry response systems are required to respond to user inquiries accurately and quickly. However, conventional systems require manual intervention and are inefficient. It is also difficult to provide consistent responses to multiple inquiries, limiting the improvement of user satisfaction. Furthermore, in situations where automated responses are required 24 hours a day, 365 days a year, there are significant constraints on human resources. To solve these issues, a system that utilizes advanced natural language processing technology and generative AI models to automatically and efficiently respond to inquiries is needed.

[0971] 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.

[0972] In this invention, the server includes: a means for a user to input an inquiry into an input device and transmit the inquiry to a central processing unit via an information processing terminal; a means for the central processing unit to analyze the received inquiry and classify it into categories using natural language processing technology; a means for the central processing unit to generate an appropriate response using a generative AI model based on the classified category; a means for the central processing unit to transmit the generated response to the information processing terminal, which then displays the response to the user; a means for automatically generating a prompt sentence for generating a response based on the inquiry for the generative AI model; a means for transmitting the generated response using a standard communication protocol; and a means for providing a continuous response that can respond to multiple inquiries. This enables accurate and prompt responses to a variety of user inquiries, improving user satisfaction and reducing companies' response workload. Furthermore, the automated response system enables 24 / 7 response, overcoming human resource constraints.

[0973] "User" means an individual or legal entity that makes an inquiry using this system.

[0974] An "input device" is a device (such as a keyboard or touch screen) that allows a user to input a query.

[0975] An "information processing terminal" is a device (e.g., a smartphone or PC) that transmits and receives data between a user and a central processing unit.

[0976] A "central processing unit" is a computer server that analyzes and processes received data and generates a response.

[0977] "Natural language processing technology" is a technology that enables computers to understand and analyze natural human language.

[0978] A "generative AI model" is an artificial intelligence system that learns from training data in advance and generates appropriate responses to inquiries.

[0979] A "prompt sentence" is an input sentence provided to a generative AI model to prompt it to generate a response.

[0980] A "standard communication protocol" is a common communication protocol (e.g., HTTP or HTTPS) used to send and receive data.

[0981] MODE FOR CARRYING OUT THE INVENTION

[0982] In the system of this invention, a user makes an inquiry through a chat box, and a generation AI automatically responds to the inquiry. Specific embodiments will be described below.

[0983] First, a user uses their own information processing terminal (e.g., a smartphone or PC) to input a question into a chat box provided by the system. For example, they input a specific question such as "I want to reset my password." This input is made using the terminal's input device (e.g., a keyboard or touch screen), and the data is sent by the terminal to the central processing unit.

[0984] The terminal captures the data entered by the user and transmits it to a central processing unit over a network, using standard communication protocols (e.g., HTTP or HTTPS).

[0985] The server (central processing unit) receives messages sent by users. The received data is analyzed using natural language processing technology. Specifically, the server performs processes such as tokenizing the message, morphological analysis, and categorizing it. For example, a message saying "I would like to reset my password" would be classified as "Account Management."

[0986] Based on the analysis results, the central processing unit requests the generative AI model to generate a response. The generative AI model is a pre-trained model that receives the input data necessary to generate an appropriate response. A prompt sentence is then used as input to the generative AI model. The following prompt sentence is an example:

[0987] Prompt: "I want to reset my password. How do I do this?"

[0988] Response: "To reset your password, go to the Settings menu and select 'Password Reset'."

[0989]

[0990] Prompt: "Can I do that from my phone?"

[0991] Response: "Yes, you can access the settings menu on your phone as well and select 'Reset Password'."

[0992] Based on the message received, the generative AI model uses training data to generate an appropriate response. Response generation is done using advanced machine learning algorithms such as the Transformer model. For example, the generative AI model might generate the response, "To reset your password, visit the Settings menu and select 'Password Reset'."

[0993] The server then sends the generated response back to the information processing terminal, again using standard communication protocols. The terminal displays the received response on the chat screen, allowing the user to review its content. If the user wishes to ask another question, they can enter it in the chat box again, and the same process is repeated.

[0994] Throughout this process, users can receive appropriate and prompt responses to their questions, which improves user satisfaction while reducing the company's response time. Furthermore, the automated response system allows for 24 / 7 support, overcoming human resource constraints.

[0995] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0996] Step 1:

[0997] The user inputs a question into the input device.

[0998] Specifically, a user uses the keyboard or touch screen of an information processing device (e.g., a smartphone or PC) to input a question into a chat box. For example, the user might input a question such as "I want to reset my password." The input at this point is text data of the user's inquiry.

[0999] Step 2:

[1000] The terminal sends the entered question to the server.

[1001] Specifically, the terminal sends text data stating "I would like to reset my password" to the server using a standard communication protocol such as an HTTP POST request. The input is the user's question data, and the output is the request data for sending it.

[1002] Step 3:

[1003] The server receives the user's question and applies natural language processing techniques.

[1004] Specifically, the server analyzes the received text and performs tokenization, morphological analysis, and categorization. For example, a message saying "I want to reset my password" is classified into the "account management" category. The input is the user's question data, and the output is the analyzed tokenized data and category information.

[1005] Step 4:

[1006] The server requests a generative AI model to generate a response based on the category.

[1007] Specifically, the server provides a prompt sentence to the generative AI model based on the analysis results and requests the model to generate an appropriate response. For example, based on the analyzed category "account management," the server inputs a prompt sentence to the generative AI model. The input is the prompt sentence and category information, and the output is a response generation request to the generative AI model.

[1008] Step 5:

[1009] A generative AI model generates a response based on the prompt.

[1010] Specifically, a generative AI model (e.g., a Transformer model) receives a prompt and uses training data to generate an appropriate response, such as "To reset your password, visit the Settings menu and select 'Password Reset.'" The input is the prompt, and the output is the generated response text.

[1011] Step 6:

[1012] The server sends the generated response to the terminal.

[1013] Specifically, the server receives the response from the generative AI model and sends it to the information processing terminal using an HTTP response. The input is the response text from the generative AI model, and the output is the response text sent as HTTP response data.

[1014] Step 7:

[1015] The terminal displays the received response to the user.

[1016] Specifically, the terminal displays the response received from the server on the chat screen, allowing the user to check how to resolve the issue. For example, a message such as "To reset your password, access the settings menu and select 'Password Reset'" may be displayed on the chat screen. The input is the response data received from the server, and the output is the response message displayed to the user.

[1017] (Application example 1)

[1018] 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."

[1019] There is a demand for a system that allows passengers in autonomous vehicles to easily check and change the vehicle's operating status and settings. However, conventional systems require passengers to perform cumbersome operations to directly check the operating status or change settings, resulting in low usability. Furthermore, there is a problem in that the system contains a lot of technical information that is difficult for ordinary passengers to understand, and lacks an intuitive interface.

[1020] 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.

[1021] In this invention, the server includes a means for a user to input an inquiry into a chat box and send it to an information processing platform via an information processing device, a means for the information processing platform to analyze the received inquiry and classify it into categories using natural language processing technology, and a means for generating an appropriate response using a generation AI based on the categories classified by the information processing platform. This allows a user to input an inquiry via an in-vehicle display or mobile device, and the vehicle's operating status and settings can be explained and changed accordingly.

[1022] "User" refers to a person who uses the System to make an inquiry.

[1023] "Chat box" refers to an interface that allows users to enter inquiries or messages in text format.

[1024] "Information processing device" refers to devices used by users, such as smartphones, tablets, and display devices inside vehicles.

[1025] "Information processing infrastructure" refers to a central server or cloud infrastructure that analyzes user inquiries and generates appropriate responses using generative AI.

[1026] "Natural language processing technology" refers to technology that analyzes users' text messages and understands their intent and meaning.

[1027] "Category" refers to the field or topic into which the analyzed inquiry content is categorized. Examples include "driving mode" and "navigation settings."

[1028] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to generate appropriate responses to user inquiries.

[1029] "Response" refers to the answer or instruction generated by the AI ​​based on the user's inquiry.

[1030] "In-vehicle displays" refer to display devices used by users inside a vehicle, typically installed in the driver's seat or rear seats.

[1031] "Mobile terminal" refers to a mobile device such as a smartphone or tablet carried by a user.

[1032] "Inquiry" refers to a question or request made by a user to the system.

[1033] "Operating status" refers to information indicating the current operating status and mode setting of the vehicle.

[1034] The system of this invention allows users inside an autonomous vehicle to easily check and change the vehicle's operating status and settings, and includes the following components:

[1035] System configuration and operation

[1036] 1. User Actions

[1037] The user enters their inquiry in text format into a chat box displayed on the vehicle's display or mobile device, such as "What is the current driving mode?"

[1038] 2. Transmission from the information processing device to the information processing infrastructure

[1039] The user's input is sent from an information processing device (smartphone, tablet, in-vehicle display, etc.) to an information processing infrastructure (central server or cloud infrastructure).

[1040] 3. Analysis of information processing infrastructure

[1041] The information processing infrastructure analyzes the received inquiry content using natural language processing technology (e.g., SpaCy or NLTK) and classifies the content into categories.

[1042] 4. Response generation using generative AI

[1043] The information processing platform then requests a generative AI (e.g., GPT-4) to generate a response based on the analysis results. The generative AI is trained in advance based on learning data and is able to generate appropriate responses.

[1044] 5. Sending and Displaying Responses

[1045] The information processing infrastructure transmits the generated response to the information processing device, which displays the response to the user.

[1046] Hardware and software used

[1047] Information processing devices: smartphones, tablets, in-vehicle displays, etc.

[1048] Information processing infrastructure: central server or cloud infrastructure.

[1049] Natural language processing technology: SpaCy or NLTK.

[1050] Generative AI models: Advanced natural language generation AI such as GPT-4.

[1051] Specific examples

[1052] 1. Initial Inquiry

[1053] User Question: "What driving mode are you in?"

[1054] Category: Driving Mode

[1055] Generative AI response: "Autopilot mode is currently 'Highway mode'. Other options include 'City mode' and 'Parking assist mode'."

[1056] 2. Example prompts to be input to the generative AI model

[1057] User Question: "What driving mode are you in?"

[1058] Category: "Driving Mode"

[1059] Example response: "Self-driving mode is currently 'Highway Mode'. Other options include 'City Mode' and 'Parking Assist Mode'."

[1060] In this way, this system allows users to easily and intuitively check and change the operating status and settings of an autonomous vehicle, which is expected to improve the user experience and significantly enhance vehicle operability.

[1061] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1062] Step 1:

[1063] The user inputs the inquiry into the chat box using the in-vehicle display or a mobile terminal. The input text is transmitted from the user terminal to the information processing infrastructure. Specifically, the user inputs "Please tell me the current driving mode," and the data is transmitted to the information processing infrastructure via the information processing device.

[1064] Step 2:

[1065] The information processing platform receives inquiries sent by users. It analyzes the received data using natural language processing technology (e.g., SpaCy, NLTK) to extract important keywords from the inquiries. This analysis categorizes the inquiries as being related to "driving modes."

[1066] Step 3:

[1067] The information processing infrastructure sends a prompt to the generative AI model (e.g., GPT-4) based on the analysis results and category data. At this time, the prompt text includes the user's question and category information. An example of a prompt text is, "User question: 'What is the current driving mode?', Category: 'Driving mode'."

[1068] Step 4:

[1069] The generative AI model takes a prompt as input and generates a response based on it. The generative AI model uses pre-trained data to create an appropriate and grammatically correct response. The generated response might be something like, "Autopilot mode is currently 'Highway mode'. Other options are 'City mode' and 'Parking assist mode'."

[1070] Step 5:

[1071] The generated response is sent by the information processing platform to the user's information processing device. The information processing device displays the received response in a chat box and provides it to the user. This allows the user to immediately check the answer to their inquiry. Specifically, the information processing platform sends the response data obtained from the generative AI model to the user's terminal, and the terminal displays the response on its screen.

[1072] Step 6:

[1073] If the user wishes to ask a more detailed question or make an additional inquiry, they can enter another input into the chat box. This new input will then repeat the process from step 1. For example, if the user continues by asking, "Please tell me about other modes as well," the new input will be sent to the information processing infrastructure, which will then perform the same analysis and generate a response.

[1074] 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.

[1075] The system of this invention receives inquiries from users via a chat box and provides appropriate responses using generative AI. Furthermore, by combining it with an emotion engine, it is possible to recognize the user's emotions and provide more appropriate and personalized responses. The detailed operation of the system will be described based on this embodiment.

[1076] First, the user enters their inquiry into the chat box on their device. For example, they might enter, "I want to reset my password. What should I do?" At this time, the device is equipped with an emotion engine that analyzes the user's emotions based on the content, typing speed, and language characteristics of the input. The emotion analysis results (e.g., stress, anxiety, calm, etc.) are also sent to the server.

[1077] The device sends the user's inquiry and sentiment analysis results to the server. The server first stores the received message in a database and then passes the data to the message processing module. The message processing module uses natural language processing (NLP) technology to analyze the inquiry and classify the message into a specific category based on its content.

[1078] Once the message has been categorized, the server requests the generation AI to generate a response that takes the user's emotions into account. The generation AI generates an appropriate response to the question based on the training data, but also takes into account the analysis results from the emotion engine. For example, for a user who is "feeling stressed," the response could be tailored to something like, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[1079] The generated response is sent from the server to the device. The device analyzes the received response and displays it on the chat screen in a user-friendly format. This provides specific guidance, such as "To reset your password, access the settings menu and select 'Password Reset'."

[1080] If the user wants to continue with a more detailed question, they can type it again in the chat box and the process will be repeated. For example, if the user asks, "Can I do that from my phone too?", this question will also be analyzed by the emotion engine and sent to the server along with the emotion data. Subsequent processing will be carried out in the same way, and a response will be generated and displayed to the user via the device, such as, "Yes, you can also access the settings menu from your phone and select 'Reset Password'."

[1081] In this way, by combining this system with an emotion engine, it can provide personalized support according to the user's emotional state, achieving higher levels of satisfaction. Furthermore, by automating inquiry responses, it enables companies to reduce their workload and respond more quickly.

[1082] The processing flow will be explained below.

[1083] Step 1:

[1084] The user enters their inquiry into the chat box and presses the send button. For example, they enter an inquiry such as "I want to reset my password. What should I do?"

[1085] Step 2:

[1086] The device receives the user's input. At this time, the emotion engine analyzes the user's input, input speed, language selection, etc. to determine the emotion (e.g., stress, anxiety, calm, etc.). The determined emotion data is sent to the server along with the query content.

[1087] Step 3:

[1088] The device sends the query and emotion data to the server using protocols such as WebSocket or HTTP POST requests.

[1089] Step 4:

[1090] The server receives the request, stores the query in a database, and then passes the data to the message processing module.

[1091] Step 5:

[1092] The server uses a message processing module to analyze the content of the received inquiry, using natural language processing (NLP) techniques to analyze the content and then using a classification algorithm to classify it into a specific category (e.g., "account management" or "technical support").

[1093] Step 6:

[1094] The server requests the AI ​​to generate a response based on the analyzed message and category. At this time, emotion data is also passed to the AI, and the emotion is taken into account when generating the response.

[1095] Step 7:

[1096] Based on the inquiry content and emotional data received, the generation AI generates the optimal response while referring to training data. For example, for a user who is "feeling stressed," it generates the response, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[1097] Step 8:

[1098] The server formats the generated response data and sends it to the terminal in a structured data format such as JSON or XML.

[1099] Step 9:

[1100] The device will then analyze the response and display it in a user-friendly format on the chat screen, for example, "To reset your password, access the settings menu and select 'Password Reset'."

[1101] Step 10:

[1102] If the user has additional questions, they can type them again into the chat box and submit, and the process can be repeated to obtain additional information.

[1103] Step 11:

[1104] The server again analyzes the received inquiry, generates a response using AI if necessary, and sends it to the device. For example, in response to the question, "Can I do that from my smartphone?", it provides the response, "Yes, you can access the settings menu from your smartphone as well and select 'Password Reset'."

[1105] Through the above steps, the present invention combines emotion engines to realize a system that provides personalized support according to the user's emotional state.

[1106] Example 2

[1107] 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."

[1108] Conventional inquiry systems could only provide uniform responses to user inquiries, making it difficult to provide personalized responses that took into account the user's emotions and circumstances. This also led to declining user satisfaction, and the systems were unable to provide adequate responses in today's business environment, where rapid responses are required. Furthermore, the processes for analyzing inquiry content and generating responses were inefficient, making it difficult for companies to reduce their workload.

[1109] 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.

[1110] In this invention, the server includes: a means for a user to input inquiry content and send it to the server via a terminal; a means for the terminal to perform sentiment analysis on the user's input content; a means for the server to analyze the received inquiry content and sentiment analysis results and classify them into categories using natural language processing technology; a means for the server to generate an appropriate response using a generation AI based on the classified category and sentiment analysis results; and a means for the server to send the generated response to the terminal and for the terminal to display the response to the user. This enables personalized responses according to the user's emotions and situation, improving user satisfaction and enabling companies to reduce their workload and provide faster responses.

[1111] "User" means an individual or equivalent entity that inputs a query into the system.

[1112] A "terminal" is a hardware or software device that allows a user to enter a query into a chat box and send it to a server.

[1113] "Server" means a computer system for receiving and processing data sent by users, and is a device that includes a database, a message processing module, and a generating AI.

[1114] "Sentiment analysis" is the process of assessing a user's emotional state based on their input, typing speed, and language characteristics.

[1115] "Natural language processing technology" is a technology that allows computers to understand and process human language, and is a technology that analyzes the content of inquiries and classifies them into categories.

[1116] "Generative AI" is artificial intelligence that generates appropriate responses to user inquiries based on training data.

[1117] "Displaying a response" refers to the act of analyzing the response received by the terminal and displaying it on the chat screen in a format that is easy for the user to see.

[1118] "Training data" is a data set used to train a generative AI to generate appropriate responses.

[1119] A "prompt sentence" is an instruction sentence that instructs the generation AI to generate an appropriate response.

[1120] This invention is a system that generates an appropriate response based on the content of a user's inquiry entered through a chat box and the results of an analysis of the user's emotions. The system aims to increase user satisfaction by providing a personalized response that corresponds to the user's emotional state.

[1121] A user enters a query into the chat box from their device. For example, they might enter, "I want to reset my password. What should I do?" At this time, the device is equipped with an emotion engine that analyzes the user's input, input speed, and language characteristics to recognize their emotions. The analysis results (e.g., stress, anxiety, calm, etc.) are sent to the server along with the query.

[1122] The device sends the user's inquiry and the results of the sentiment analysis to the server, which temporarily stores the received data in a database. The data is then passed to the message processing module, which uses natural language processing (NLP) technology to analyze the inquiry and classify it into specific categories.

[1123] The server then uses the analyzed data to generate a response that takes into account the user's emotions, and requests the AI ​​to generate a response along with a prompt. Specific examples of prompts are as follows:

[1124] User asks: "I want to reset my password. How do I do that?"

[1125] Sentiment analysis result: "Stress"

[1126] Generate an appropriate response.

[1127] The generative AI generates the optimal response to the inquiry based on the training data. In doing so, it also takes into account the analysis results of the emotion engine, so if the user is "stressed," for example, it will generate a response such as, "Don't worry. Resetting your password is a simple process. Just follow the steps below."

[1128] The generated response is sent from the server to the device, which then analyzes it and displays it on the chat screen in a user-friendly format. For example, specific guidance such as "To reset your password, access the settings menu and select 'Password Reset'" is provided.

[1129] If the user wants to ask a more detailed question, they can type it again into the chat box. This is also analyzed by the emotion engine and sent to the server along with the emotion data. A similar process is followed to generate a response, such as "Yes, you can also access the settings menu on your smartphone and select 'Reset Password'," which is then displayed to the user via their device.

[1130] This system provides personalized support combined with sentiment analysis, improving user satisfaction. It also automates inquiry responses, reducing the workload of companies and enabling faster responses.

[1131] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1132] Step 1:

[1133] The user inputs the inquiry.

[1134] Specific operation: The user opens a chat box on their device and types in a question. For example, they type, "I want to reset my password. How do I do this?"

[1135] Input: User text input

[1136] Output: Your input is saved to your device

[1137] Step 2:

[1138] The device passes the user's input to the emotion engine for emotion analysis.

[1139] Specific operation: The input text content is sent to the emotion engine in real time and analyzed for the user's emotions (stress, anxiety, calm, etc.).

[1140] Input: User text input

[1141] Output: Sentiment analysis result (e.g., stress, confidence level 0.86)

[1142] Step 3:

[1143] The device sends the emotion analysis results and the inquiry content to the server.

[1144] Specific operation: The sentiment analysis results are compiled in JSON format and sent to the server along with the query content via an HTTP request.

[1145] Input: Enquiry content and sentiment analysis results

[1146] Output: JSON data sent to the server

[1147] Step 4:

[1148] The server stores the received data in a database.

[1149] Specific operation: Parse the received JSON data and record the inquiry content and sentiment analysis results in a database.

[1150] Input: Received JSON data

[1151] Output: Data stored in the database

[1152] Step 5:

[1153] The server passes the data to the message processing module, which analyzes and classifies the query content.

[1154] Specific operation: The query content retrieved from the database is analyzed using natural language processing (NLP) technology and classified into categories such as "password reset."

[1155] Input: Query retrieved from the database

[1156] Output: The category (e.g., password reset)

[1157] Step 6:

[1158] The server creates a prompt sentence for the generation AI and asks it to generate a response.

[1159] Specific operation: A prompt sentence is generated based on the category classification results and sentiment analysis results and sent to the generation AI.

[1160] Input: Category classification results and sentiment analysis results

[1161] Output: Prompt sentence for the generation AI (Example: User inquiry: "I want to reset my password. What should I do?" Sentiment analysis result: "Stressed". Generate an appropriate response.)

[1162] Step 7:

[1163] The generative AI generates a response based on the prompt text.

[1164] How it works: Generative AI refers to a training dataset and generates an appropriate response, taking into account the user's emotions.

[1165] Input: Prompt for the generation AI

[1166] Output: The response generated (e.g. Don't worry, resetting your password is a simple process. Just follow the steps below.)

[1167] Step 8:

[1168] The server sends the generated response to the terminal.

[1169] Specific behavior: Receives the generated response and sends it to the user's device.

[1170] Input: The generated response

[1171] Output: Response data to the terminal

[1172] Step 9:

[1173] The terminal analyzes the received response and displays it to the user.

[1174] What it does: The device parses the received response and displays it on the chat screen in a user-friendly format, such as "Don't worry, resetting your password is a simple process. Just go to the settings menu and select 'Password Reset'."

[1175] Input: Received response data

[1176] Output: The response displayed in the user's chat screen

[1177] (Application example 2)

[1178] 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."

[1179] Conventional driver assistance systems and chatbots generate mechanical responses without considering the user's emotional state, which means they are unable to provide appropriate support, especially to drivers who are stressed or fatigued. There is also a need for systems that can respond in real time to inquiries and requests from drivers while driving, while also being flexible and taking into account the driver's emotional state. To solve this problem, a system incorporating emotion recognition functionality is required.

[1180] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1181] In this invention, the server includes a means for a user to input an inquiry into a chat box and send it to a data processing device via a terminal, a means for the data processing device to analyze the received inquiry and classify it into categories using natural language processing technology, and a means for the data processing device to generate an appropriate response using a generation AI based on the classified category and the emotion analysis result. This makes it possible to provide a driving support function according to the driver's emotional state, reducing stress and suggesting appropriate breaks.

[1182] "User" means an individual or entity who uses the system and inputs inquiries via a terminal.

[1183] A "chat box" is an interface for users to enter their inquiries.

[1184] "Terminal" refers to a computer, smartphone, or other device used by a user, which is a means for communicating with the server.

[1185] "Data Processing Device" means the computer server or cloud infrastructure used to receive and analyze user inquiries and generate responses.

[1186] "Natural language processing technology" is a technology for analyzing text data and performing semantic understanding and category classification.

[1187] A "category" is a classification criterion for classifying user inquiries into specific groups or classes.

[1188] "Emotion analysis result" is information indicating the emotional state extracted from the user's input content.

[1189] "Generative AI" is an artificial intelligence technology that generates appropriate responses to user inquiries based on training data.

[1190] "Response" means a system-generated reply or instruction to a user's inquiry.

[1191] "Driving support functions" are a series of functions to assist drivers while driving, including playing relaxation music and suggesting rest spots.

[1192] "Relaxation music" is music played to relieve the driver's stress and anxiety.

[1193] "Route Guidance" is a navigation function that provides directions for the driver to reach their destination.

[1194] To implement this invention, it is necessary to build a system that applies a chat system using an emotion analysis engine and generative AI to driving support. This system is composed of the following elements.

[1195] 1. User Interface:

[1196] A chat box is provided for drivers (users) to enter their inquiries or requests, which typically runs on the in-car infotainment system or on a smartphone.

[1197] 2. Sentiment Analysis Engine:

[1198] It analyzes user input in real time to identify their emotional state (e.g., stressed, anxious, calm, etc.) using the Python library TextBlob and Hugging Face Transformers.

[1199] 3. Data Processing Unit:

[1200] The system receives the user's inquiry along with the sentiment analysis results and categorizes them using natural language processing techniques, using the Hugging Face Transformers model.

[1201] 4. Generative AI Models:

[1202] The data processing device generates an appropriate response based on the categorized inquiry content received and the results of sentiment analysis, using generative AI models such as Microsoft's DialoGPT.

[1203] 5. Send and display the response:

[1204] The response generated by the data processing device is sent to the user's device and displayed in a format that the user can view, allowing the user to receive specific guidance and driving support in response to the request.

[1205] For example, if a driver types, "I'm very tired today. Is there anywhere nearby where I can rest?", the emotion analysis engine will identify the emotional state of "fatigue," and the data processing device will analyze and classify the content. The generative AI model will generate a response providing information on "nearby rest spots," and will display a reply on the user's device such as, "There are several places to rest nearby. The nearest rest spot is 10 km away, and we recommend you take a break there."

[1206] In addition, if a driver who is stressed by traffic jams types in, "I'm frustrated by the traffic jam. Please tell me how I can calm myself down right now," the emotion analysis engine will detect "frustration," and the generative AI model will generate a response suggesting things like "playing relaxation music" or "routes to avoid the traffic jam."

[1207] Example prompt sentence:

[1208] "I'm very tired today. Is there anywhere nearby where I can rest?"

[1209] "I'm frustrated with the traffic. Can you tell me how to calm myself down right now?"

[1210] This allows drivers to receive appropriate support in real time based on their emotional state while driving.

[1211] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1212] Step 1:

[1213] The user (driver) enters an inquiry or request into the chat box from the car's infotainment system or smartphone. The entered data is sent to the sentiment analysis engine. At this point, the input is the user's text message, for example, "I'm very tired today. Is there anywhere nearby where I can rest?"

[1214] Step 2:

[1215] The device sends the received user input to a sentiment analysis engine (e.g., TextBlob), which analyzes the input and identifies the user's emotional state (e.g., fatigue, stress). The input is the user's text message, and the output is the emotional state (e.g., "fatigue").

[1216] Step 3:

[1217] The device sends the user's input and the emotion analysis results to a data processing device, which analyzes and classifies the data using natural language processing technology to identify a category (e.g., "rest spot suggestions"). The input is the user's text message and emotional state information, and the output is category information.

[1218] Step 4:

[1219] The data processing device makes a generative AI model (e.g., DialoGPT) generate an appropriate response based on the classified category and the emotion analysis results. The generative AI model generates a response based on the training data. This process involves running a generative algorithm, which generates a generated response (e.g., "There are several places to rest nearby. The nearest rest spot is 10 km away, and we recommend you take a break there."). The input is category information and emotional state information, and the output is a response message.

[1220] Step 5:

[1221] The data processing device sends the generated response to the terminal. The terminal analyzes the received response and displays it in a format that can be confirmed by the user. Specifically, it displays a text message on the chat screen. The input is the generated response message, and the output is the response message that is displayed to the user.

[1222] Step 6:

[1223] If the user enters another question or request, the above steps are repeated again. For example, if the user adds, "Can I do that from my phone?", this new inquiry is also processed again through the sentiment analysis engine, data processing unit, and generative AI model. The input is the new user message, and the output is the corresponding response message.

[1224] 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.

[1225] 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.

[1226] 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.

[1227] 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.

[1228] 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.

[1229] 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.

[1230] 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).

[1231] 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.

[1232] 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."

[1233] 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.

[1234] 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).

[1235] 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.

[1236] 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.

[1237] 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.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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.

[1242] 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.

[1243] 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.

[1244] 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.

[1245] The following is further disclosed regarding the above embodiment.

[1246] (Claim 1)

[1247] A means for a user to input an inquiry into a chat box and transmit it to a server via a terminal;

[1248] A means for analyzing the content of the inquiry received by the server and classifying it into categories using natural language processing technology;

[1249] A means for the server to generate an appropriate response using a generation AI based on the classified category;

[1250] The system includes means for transmitting a server-generated response to the terminal, and for the terminal to display the response to the user.

[1251] (Claim 2)

[1252] The system of claim 1, wherein the generation AI accesses training data and executes the generation algorithm based on the query content analyzed by the server.

[1253] (Claim 3)

[1254] 2. The system according to claim 1, wherein the terminal retransmits multiple inquiries from the user to the server, and the server generates and transmits a response to each of the inquiries.

[1255] "Example 1"

[1256] (Claim 1)

[1257] A means for a user to input an inquiry into an input device and transmit the inquiry to a central processing unit via an information processing terminal;

[1258] A means for analyzing the content of the inquiry received by the central processing unit and classifying it into categories using natural language processing technology;

[1259] A means for the central processing unit to generate an appropriate response using a generative AI model based on the classified category;

[1260] means for transmitting the response generated by the central processing unit to the information processing terminal, and for the information processing terminal to display the response to a user;

[1261] A means for automatically generating a prompt sentence for response generation based on the inquiry content for the generative AI model;

[1262] means for transmitting the generated response using a standard communications protocol;

[1263] The response can be multiple queries and means for providing a continuous response;

[1264] ...

[1265] A system including:

[1266] (Claim 2)

[1267] 10. The system of claim 1, wherein the generative AI model accesses pre-trained data and executes a generative algorithm based on the query content analyzed by the central processing unit.

[1268] (Claim 3)

[1269] 2. The system according to claim 1, wherein the information processing terminal transmits a plurality of inquiries from the user to the central processing unit again, and the central processing unit generates and transmits a response to each inquiry.

[1270] "Application Example 1"

[1271] (Claim 1)

[1272] A means for a user to input an inquiry into a chat box and transmit the inquiry to an information processing infrastructure via an information processing device;

[1273] A means for analyzing the content of the inquiry received by the information processing infrastructure and classifying it into categories using natural language processing technology;

[1274] A means for generating an appropriate response by a generative AI based on the categories classified by the information processing infrastructure;

[1275] a means for transmitting the response generated by the information processing infrastructure to the information processing device, and for the information processing device to display the response to the user;

[1276] A system that includes a means for users to input queries via a display in the vehicle or a mobile device, and to explain and change the vehicle's operating status and settings in response.

[1277] (Claim 2)

[1278] The system of claim 1, wherein the generation AI accesses learning data and executes the generation algorithm based on the query content analyzed by the information processing infrastructure.

[1279] (Claim 3)

[1280] 2. The system according to claim 1, wherein the information processing device retransmits a plurality of inquiries from the user to the information processing infrastructure, and the information processing infrastructure generates and transmits a response to each of the inquiries.

[1281] "Example 2: Combining Emotion Engines"

[1282] (Claim 1)

[1283] A means for a user to input the content of an inquiry and transmit it to a server via a terminal;

[1284] A means for the device to perform emotion analysis of the user's input;

[1285] A means for analyzing the content of the inquiry and the sentiment analysis results received by the server and classifying them into categories using natural language processing technology;

[1286] A means for the server to generate an appropriate response using a generation AI based on the classified category and the emotion analysis result;

[1287] A means for the server to send the generated response to the terminal, and for the terminal to display the response to the user

[1288] A system including:

[1289] (Claim 2)

[1290] The system of claim 1, wherein the generation AI accesses training data and executes the generation algorithm based on the query content and sentiment analysis results analyzed by the server.

[1291] (Claim 3)

[1292] 2. The system according to claim 1, wherein the terminal retransmits multiple inquiries from the user to the server, and the server generates and transmits a response to each of the inquiries.

[1293] "Application example 2 when combining emotion engines"

[1294] (Claim 1)

[1295] A means for a user to input an inquiry into a chat box and transmit the inquiry to a data processing device via a terminal;

[1296] means for analyzing the content of the inquiry received by the data processing device and classifying it into categories using natural language processing technology;

[1297] A means for generating an appropriate response by a generation AI based on the classified category and the emotion analysis result by the data processing device;

[1298] means for transmitting a response generated by the data processing device to the terminal and for the terminal to display the response to the user;

[1299] means for analyzing an emotional state of a driver and generating a response, including a specific behavior, according to the emotional state;

[1300] Responses include driving support features such as playing relaxation music while driving, suggesting hydration spots, and route guidance.

[1301] A system including:

[1302] (Claim 2)

[1303] The system of claim 1, wherein the generation AI accesses training data and executes the generation algorithm based on the query content and sentiment analysis results analyzed by the data processing device.

[1304] (Claim 3)

[1305] 2. The system according to claim 1, wherein the terminal transmits multiple inquiries from the user to the data processing device again, and the data processing device generates and transmits a response to each inquiry and emotional state. [Explanation of symbols]

[1306] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for a user to input an inquiry into a chat box and transmit it to a server via a terminal; A means for analyzing the content of the inquiry received by the server and classifying it into categories using natural language processing technology; A means for the server to generate an appropriate response using a generation AI based on the classified category; The system includes means for transmitting a server-generated response to the terminal, and for the terminal to display the response to the user.

2. The system of claim 1, wherein the generation AI accesses training data and executes the generation algorithm based on the query content analyzed by the server.

3. 2. The system according to claim 1, wherein the terminal transmits a plurality of inquiries from the user to the server again, and the server generates and transmits a response to each of the inquiries.

Images