system

Abstract

We provide the system. [Solution] A means for receiving input from the user, A means of sending user input to a server, A means of analyzing user input within the server using a natural language processing engine, A means of obtaining relevant data from a database based on the analysis results, A generative AI system that generates appropriate answers based on acquired data, A means of sending the generated response to the user's terminal, A means of displaying the answer on the user's terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, the financial difficulties and personnel shortages in local governments have become serious, making it difficult to respond quickly and accurately to inquiries from residents. Also, smooth information provision is necessary for users with low IT literacy such as the elderly. In many cases, the current administrative services do not have sufficient response capabilities for these problems. Therefore, there is a need to develop a system that efficiently provides resident services with limited resources and provides an interface that is particularly easy for the elderly to use.

Means for Solving the Problems

[0005] The present invention solves the above-mentioned problems with a system that includes means for receiving input from a user, means for transmitting the user's input to a server, means for analyzing the user's input on the server using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating an appropriate answer based on the acquired data, means for transmitting the generated answer to a user terminal, and means for displaying it on the user terminal. Furthermore, by providing speech-to-text conversion software that converts the user's voice input into text data and automatic speech software that converts the generated text answer into voice data, the system is designed to be accessible to the elderly and users with low IT literacy.

[0006] A "user" is an individual or group that uses this system.

[0007] "Means of receiving input" refers to an interface for users to input questions or information, and includes devices and software such as keyboards, microphones, and touchscreens.

[0008] A "server" is a computer system that processes input data sent by users and provides appropriate functions and services.

[0009] A "natural language processing engine" refers to algorithms and technologies that analyze input text data and understand its content. This makes it possible to identify the user's question and search for relevant information.

[0010] A "database" is a system that stores information such as relevant laws, ordinances, regulations, and past case examples.

[0011] "Generative AI methods" refer to artificial intelligence technologies that automatically generate appropriate answers based on acquired data, and include natural language generation (NLG) technology.

[0012] "User terminal" refers to a device that the user directly operates, and includes personal computers, smartphones, tablets, and other similar devices.

[0013] "Speech-to-text conversion software" is software used to convert audio data into text data.

[0014] "Automatic speech software" is software that converts text data into speech data, using speech synthesis technology.

[0015] "Means of display" refers to an interface for providing text data or audio data to the user visually or audibly on a terminal. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

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

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

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

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0037] A detailed description of embodiments for carrying out the present invention is provided below. This embodiment provides a system that efficiently handles resident services for local governments and enables smooth information provision, especially for the elderly and users with low IT literacy.

[0038] System Overview

[0039] This system consists of the following main components:

[0040] A terminal for user input.

[0041] Server for receiving and processing input data

[0042] Natural Language Processing Engine

[0043] database

[0044] Generative AI

[0045] Speech-to-text software

[0046] Automated voice software

[0047] Program Processing Description

[0048] 1. User input

[0049] Users access the system using a device (e.g., a personal computer or smartphone) and input questions or information. Users may input questions in text format, or, in some cases, elderly individuals may dictate their questions verbally.

[0050] Specific example:

[0051] The user enters, "When is the deadline for paying next year's resident tax?"

[0052] 2. Data transmission by the terminal

[0053] The terminal converts data entered by the user into text data and sends it to the server. If voice input is used, speech-to-text conversion software is used to convert the voice data into text data. The converted text data is then sent to the server by the terminal.

[0054] 3. Question analysis by the server

[0055] The server passes the received text data to a natural language processing engine for analysis. The natural language processing engine extracts keywords and important phrases from the text data to understand the intent of the question.

[0056] Specific example:

[0057] We analyze important keywords such as "resident tax," "payment deadline," and "next fiscal year."

[0058] 4. Database search by server

[0059] Based on the analysis results, the server searches the database for relevant information. The database contains information such as laws, regulations, and past response examples.

[0060] Specific example:

[0061] Search database entries related to "resident tax," "payment deadline," and "next fiscal year."

[0062] 5. Server-driven response generation

[0063] The server uses generative AI to generate appropriate answers based on the acquired data. The generative AI generates natural-sounding sentences and provides clear answers to the user's questions.

[0064] Specific example:

[0065] Generate the response: "The deadline for paying next year's resident tax is June 1, 2023."

[0066] 6. Sending responses from the server to the terminal.

[0067] The generated response is sent from the server to the terminal and provided to the user. If the response is in text format, it is sent as is. If an audio response is required, automated speech software is used to convert the text into audio data, which is then sent to the terminal.

[0068] 7. Display of answers via device

[0069] The device displays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[0070] Specific example:

[0071] The message "The deadline for paying next year's resident tax is June 1, 2023" is displayed or played.

[0072] This system efficiently handles inquiries about basic administrative services and provides a user-friendly interface that is considerate of the elderly. This configuration allows for the effective use of limited resources within local governments and improves resident satisfaction.

[0073] The following describes the processing flow.

[0074] Step 1:

[0075] The user accesses the system using a terminal and enters a question. For example, the user might enter "When is the deadline for paying next year's resident tax?" in text format.

[0076] Step 2:

[0077] The terminal sends the entered text data to the server. Since the terminal sends the user's text input directly to the server, no special data conversion is performed in this step.

[0078] Step 3:

[0079] The server receives the text data and passes it to the natural language processing engine to begin analysis. The natural language processing engine extracts keywords and important phrases from the text data and understands the intent of the question.

[0080] Step 4:

[0081] The server searches the database for relevant information based on the analysis results. The database stores laws, regulations, and past case examples. For example, it searches for entries related to "resident tax," "payment deadline," and "next fiscal year."

[0082] Step 5:

[0083] Based on information retrieved from the database by the server, a generative AI is used to generate appropriate answers. The generative AI constructs natural-sounding sentences and provides clear answers to the user's questions.

[0084] Step 6:

[0085] The server sends the generated response to the terminal in text format. For example, the text data "The deadline for paying next year's resident tax is June 1, 2023" is sent.

[0086] Step 7:

[0087] The device displays the received response on the screen. The user can view the response in text format.

[0088] Step 8:

[0089] Only when voice input is detected, the terminal passes the user's voice data to speech-to-text software, which converts it into text data. This converted text data is then sent to the server.

[0090] Step 9:

[0091] If voice output is required, the server converts the generated text response into an automated speech-to-speech program to produce audio data. The generated audio data is then sent to the terminal.

[0092] Step 10:

[0093] The device plays back the received audio data and provides the user with an audio response. This makes it possible to support users with low IT literacy, such as the elderly.

[0094] (Example 1)

[0095] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] The present invention aims to provide a system that enables smooth information provision in local government resident services, particularly for the elderly and users with low IT literacy. Current systems have the problem of requiring users to spend a considerable amount of time and effort to obtain information. Furthermore, in environments where voice input and output cannot be properly utilized, the system is particularly difficult for the elderly to use. There is a need to provide a system that solves these problems.

[0097] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0098] In this invention, the server includes means for receiving input from a user, means for a terminal to convert the user's input into data and transmit it to the server, means for the server to analyze the user's input using a natural language processing engine, means for obtaining relevant information from a storage device based on the analysis results, means for generating an appropriate response based on the acquired information using a generation AI, means for transmitting the generated response to the user terminal, and means for displaying the response on the user terminal. This enables the rapid and accurate provision of information regarding the user's input. Furthermore, by incorporating voice input and voice output functions, the system can be made particularly easy to use for the elderly, thereby improving the efficiency of services for residents.

[0099] A "user" is an entity that uses a system to input information and receive responses.

[0100] A "terminal" is a device used by a user to access and input data into a system, and includes personal computers and smartphones.

[0101] A "server" is a computing device that receives input data from users and performs processing such as analysis, data acquisition, and response generation.

[0102] A "natural language processing engine" is software or an algorithm that analyzes text data, extracts keywords and important phrases, and understands the intent of a question.

[0103] A "storage device" is a device that stores data for a server to retrieve relevant information based on analysis results, and includes databases and the like.

[0104] "Generative AI means" refers to a device or program that uses artificial intelligence technology to generate appropriate answers based on acquired data.

[0105] "Voice-to-text conversion software" is software that converts a user's voice input into text data.

[0106] "Automated voice software" is software that converts generated text responses into audio data and enables audio output.

[0107] "Means for receiving input" refers to an interface that allows users to input information such as questions into a terminal.

[0108] "Means of converting and transmitting data" refers to a function that allows a terminal to convert user input into text data or an appropriate format and send it to a server.

[0109] "Means of analysis" refers to the process by which a server uses a natural language processing engine to analyze user input data and understand the intent behind the question.

[0110] "Means of acquisition" refers to the function that allows the server to search for and retrieve relevant information from storage devices based on the analysis results.

[0111] "Means of transmission" refers to the communication function that allows the server to send the generated response back to the user's terminal.

[0112] "Means of display" refers to display devices and audio output functions that allow the user terminal to present the response sent from the server to the user.

[0113] This invention is a system designed to efficiently handle resident services for local governments, and is particularly capable of providing smooth information to elderly people and users with low IT literacy. The system mainly consists of a terminal for user input, a server for receiving and processing input data, a natural language processing engine, a database, a generative AI, and speech-to-text conversion software or automated speech software.

[0114] Users access the system using devices such as personal computers and smartphones and input questions and information. For example, a user might input, "When is the deadline for paying next year's resident tax?" It is also conceivable that an elderly person might ask a question by voice, such as, "Please tell me about the resident tax payment deadline."

[0115] The terminal converts data entered by the user into text data and sends it to the server. If voice input is used, the terminal uses speech-to-text software to convert the voice data into text. The converted text data is then sent to the server by the terminal.

[0116] The server passes the received text data to a natural language processing engine (e.g., natural language processing engine software) for analysis. The natural language processing engine extracts primitive keywords and important phrases from the text data to understand the intent of the user's question. For example, it analyzes keywords such as "resident tax," "payment deadline," and "next fiscal year."

[0117] Based on the analysis results, the server searches for relevant information from a database (e.g., a database management system). The database stores information such as laws, regulations, and past case examples, and the server retrieves the most relevant information based on this. For example, it searches for database entries related to "resident tax," "payment deadline," and "next fiscal year."

[0118] The server uses generative AI (e.g., a generative AI model) to generate appropriate answers based on the acquired data. This generative AI generates natural-sounding sentences and provides clear answers to user questions. For example, in response to the prompt "When is the deadline for paying next year's resident tax?", it generates the answer "The deadline for paying next year's resident tax is June 1, 2023."

[0119] The generated responses are sent from the server to the terminal and provided to the user. If the response is in text format, it is sent as is. If an audio response is required, the text is converted into audio data using automated speech software (e.g., automated speech generation software), and the audio data is sent to the terminal.

[0120] The device displays the response received from the server to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker. For example, the message "The deadline for paying next year's resident tax is June 1, 2023." might be displayed on the screen, or the same content might be played as audio.

[0121] In this way, the system of the present invention can respond to a variety of user inputs and provide appropriate information efficiently and quickly.

[0122] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0123] Step 1:

[0124] User input

[0125] Users access the system using a device (such as a computer or smartphone) and input questions or information. Specifically, a user might type "When is the deadline for paying next year's resident tax?" as text, or say "Please tell me about the resident tax payment deadline" as voice. In this step, if the user's input is in text format, it is entered directly into the device; if it is in voice format, the voice is recorded.

[0126] Step 2:

[0127] Data transmission by terminal

[0128] The terminal processes the data entered by the user. Text data is treated directly as a text file, while voice data is converted to text data using speech-to-text software. For example, voice input is converted to the text "Please tell me about the deadline for paying resident tax." The converted text data is then sent to the server by the terminal. The process of converting voice input to text data and sending it is completed here.

[0129] Step 3:

[0130] Server-based question analysis

[0131] The server receives user input data and passes it to a natural language processing engine (e.g., natural language processing engine software). The natural language processing engine extracts important keywords and phrases from the text data. Specifically, it identifies important elements such as "resident tax," "payment deadline," and "next fiscal year" to understand the intent of the question. Through this analysis, the server generates a dataset containing semantically important information.

[0132] Step 4:

[0133] Server-based database search

[0134] Based on the analysis results, the server searches for relevant information from its storage device (database management system). The database contains laws, regulations, and past case examples. For example, the server searches the database entries related to "resident tax," "payment deadline," and "next fiscal year," and retrieves that information. In this step, the server collects the relevant data and prepares it for use in the next step.

[0135] Step 5:

[0136] Server-based response generation

[0137] Based on the data acquired by the server, a generative AI (e.g., a generative AI model) is used to generate an appropriate answer. A prompt is input to the generative AI model, and a response in a natural sentence format is generated. For example, in response to the prompt "When is the deadline for paying next year's resident tax?", the model generates the answer "The deadline for paying next year's resident tax is June 1, 2023." In this step, the generative AI model generates accurate and easy-to-understand sentences.

[0138] Step 6:

[0139] Sending responses from the server to the terminal.

[0140] The generated responses are sent from the server to the terminal. Text-based responses are sent as is, while if an audio response is required, automated speech software is used to convert the text to speech, and that audio data is sent to the terminal. For example, the text response "The deadline for paying next year's resident tax is June 1, 2023." is sent to the terminal.

[0141] Step 7:

[0142] Display of answers via device

[0143] The device displays the response received from the server to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker. Specifically, a message such as "The deadline for paying next year's resident tax is June 1, 2023" might be displayed on the screen or played aloud. In this step, the user can obtain the answer to their question visually or audibly.

[0144] (Application Example 1)

[0145] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0146] In modern society, the number of elderly users and users with low IT literacy is increasing, making it difficult to provide information smoothly to these users. Furthermore, while there is a need to provide product information and service guidance quickly and effectively in physical stores, current technology is insufficient to meet this demand. In particular, there is a need for intuitive interfaces that can be used by elderly users and users with low IT literacy.

[0147] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0148] In this invention, the server includes means for receiving input from a user, means for transmitting the user's input to the server, means for analyzing the user's input within the server using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating an appropriate response based on the acquired data, means for transmitting the generated response to a user terminal, means for displaying the response on the user terminal, means for recognizing the user's gaze direction using a gaze detection sensor and transmitting it to the server, means for providing product information and service guidance within the physical store based on the gaze direction, and means for receiving questions regarding product information and service guidance within the physical store via voice input. This makes it possible to provide information intuitively and effectively to elderly people and users with low IT literacy in physical stores.

[0149] "Means of receiving user input" refers to an interface that allows users to input information into a system. This includes smart glasses, smartphones, and computers.

[0150] "Means of sending user input to a server" refers to the function of sending information entered by the user to a server via a network. This utilizes internet connectivity or wireless communication technology.

[0151] "Methods for analyzing user input within a server using a natural language processing engine" refers to technologies that analyze text and audio data received by the server to understand the user's intent. The natural language processing engine plays this role.

[0152] "Means of obtaining relevant data from a database based on analysis results" refers to a function that searches for and retrieves necessary information from a database based on the results of analysis performed by a natural language processing engine.

[0153] "Generative AI methods for generating appropriate answers" refers to AI technology that generates appropriate answers to user questions based on acquired data. Generative AI plays this role.

[0154] "Means of sending generated responses to the user's terminal" refers to the function of transferring responses created by a generative AI to the user's device. This is done via the internet or wireless communication.

[0155] "Means of displaying answers on the user's device" refers to an interface that displays the generated answers on the user's device. This role is fulfilled by the display of smart glasses or the screen of a smartphone.

[0156] "A means of recognizing the direction of the user's gaze using a gaze detection sensor and transmitting it to a server" refers to a technology that detects the direction the user is looking and transmits that information to a server. The gaze detection sensor plays this role.

[0157] "Means of providing product information and service guidance within a physical store based on the direction of gaze" refers to a function that provides detailed information about products and services based on the direction the user is looking.

[0158] "A means of receiving questions about product information and service guidance within a physical store via voice input" refers to a function that captures user voice questions, converts them into text data, and analyzes them. Voice-to-text conversion software fulfills this role.

[0159] A specific embodiment for carrying out the present invention is shown below. This embodiment makes it possible to provide information intuitively and effectively to elderly people and users with low IT literacy in physical stores.

[0160] System Configuration

[0161] This system consists of the following main components:

[0162] 1. A device that accepts user input (such as smart glasses or a smartphone)

[0163] 2. Server

[0164] 3. Natural Language Processing Engine

[0165] 4. Database

[0166] 5. Generative AI

[0167] 6. Eye-tracking sensor

[0168] 7. Speech-to-text conversion software

[0169] 8. Automated voice software

[0170] Hardware and software usage

[0171] The primary device used is a pair of smart glasses. These smart glasses are equipped with an eye-tracking sensor to recognize the user's gaze direction. They also have a microphone for voice input.

[0172] On the server side, a natural language processing engine (e.g., spaCy), speech-to-text software (e.g., Mozilla DeepSpeech), generative AI (e.g., OpenAI® GPT-3®), and a database system (e.g., PostgreSQL) are used. These software components work together to analyze user input data and generate appropriate responses.

[0173] Methods for data processing and data calculation

[0174] Processing of eye-tracking data

[0175] When a user looks at products or services in a store through their smart glasses, an eye-tracking sensor recognizes the direction of their gaze and sends that data to a server. The server analyzes the eye-tracking data to identify information about products the user is interested in.

[0176] Analysis of voice input

[0177] When a user enters a question by voice, the microphone in the smart glasses collects the voice and sends the voice data to a server. The voice data is then converted into text data using speech-to-text software.

[0178] Natural language processing and database search

[0179] The server passes the converted text data to a natural language processing engine to analyze the user's question. Based on the analysis results, it searches the database for relevant product information and service details.

[0180] Answer generation

[0181] Based on the acquired information, a generative AI generates appropriate answers to the user's questions. The answers are generated in natural-sounding sentences.

[0182] Information provision

[0183] The generated response is sent back to the smart glasses via the server and displayed in the user's field of view. If output in audio format is requested, the text is converted into audio data using automated speech software and played back through the smart glasses' speaker.

[0184] Examples of prompt statements

[0185] The following are specific examples of questions users might ask smart glasses in a physical store:

[0186] "What are the features of this product?"

[0187] "How much does this item cost?"

[0188] "Where can I find this product?"

[0189] As described above, the system based on the present invention enables intuitive and effective information provision in physical stores, particularly for elderly people and users with low IT literacy.

[0190] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0191] Step 1:

[0192] The user wears smart glasses and walks around a physical store. When the user looks at a product or service that interests them, the eye-tracking sensor recognizes the direction of their gaze. The input is gaze direction data, and the output is data related to gaze direction. The server receives this gaze direction data and proceeds to the next step.

[0193] Step 2:

[0194] The user provides voice input. For example, they might ask, "What are the features of this product?" The smart glasses' microphone collects the voice data and sends it to the server. The input is voice data, and the output is the raw voice data sent to the server.

[0195] Step 3:

[0196] The server converts the received audio data into text data using speech-to-text software (e.g., Mozilla DeepSpeech). The input is audio data, and the output is the converted text data. This allows the user's questions to be analyzed in text format.

[0197] Step 4:

[0198] The server passes text data to a natural language processing engine (e.g., spaCy) to analyze the user's question. The input is text data, and the output is keywords and important phrases included in the analysis results. Based on the analysis results, the server understands the user's intent.

[0199] Step 5:

[0200] The server searches a database (e.g., PostgreSQL) for information on products of interest based on the analysis results and eye-tracking data. The input is the analysis results and eye-tracking data, and the output is detailed information on related products. This allows the server to retrieve appropriate information.

[0201] Step 6:

[0202] The server uses generative AI (e.g., OpenAI GPT-3) to generate appropriate answers to user questions based on the acquired information. The input is detailed product information, and the output is the generated text-based answer. The generative AI generates natural-sounding sentences, creating answers that are easy for the user to understand.

[0203] Step 7:

[0204] The server sends the generated text-formatted response to the smart glasses. The input is the generated text-formatted response, and the output is the text data sent to the smart glasses. This allows the user to receive the response.

[0205] Step 8:

[0206] The user's smart glasses display the received text data on a screen, and, if necessary, convert it into audio data using automated voice software and play it through the speaker. The input is text data, and the output is the response displayed in the user's field of vision and the audio data. This allows the user to see the response visually and hear it aloud.

[0207] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0208] A detailed description of embodiments for carrying out the present invention is provided below. This embodiment provides a system that efficiently handles resident services for local governments and enables smooth information provision, especially for the elderly and users with low IT literacy. Furthermore, by combining it with an emotion engine, responses based on the user's emotions can also be realized.

[0209] System Overview

[0210] This system consists of the following main components:

[0211] A terminal for user input.

[0212] Server for receiving and processing input data

[0213] Natural Language Processing Engine

[0214] database

[0215] Generative AI

[0216] Speech-to-text software

[0217] Automated voice software

[0218] Emotional Engine

[0219] Program Processing Description

[0220] 1. User input

[0221] Users access the system using a device (e.g., a personal computer or smartphone) and input questions or information. Users may input questions in text format, or, in some cases, elderly individuals may dictate their questions verbally.

[0222] Specific example:

[0223] The user enters, "Please tell me the opening hours of the nearby library."

[0224] 2. Data transmission by the terminal

[0225] The terminal sends the entered text data to the server. If voice input is used, the voice data is converted to text data using speech-to-text software. The converted text data is then sent to the server by the terminal.

[0226] 3. Question analysis by the server

[0227] The server passes the received text data to a natural language processing engine to begin analysis. The natural language processing engine extracts keywords and important phrases from the text data and understands the intent of the question.

[0228] Specific example:

[0229] We analyze important keywords such as "library" and "opening hours."

[0230] 4. Database search by server

[0231] Based on the analysis results, the server searches the database for relevant information. The database stores laws, regulations, and past case examples.

[0232] Specific example:

[0233] Search database entries related to "library" and "opening hours".

[0234] 5. User emotion analysis using an emotion engine

[0235] The server passes user input data and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions (e.g., joy, anger, sadness, surprise) from the user's text and voice data.

[0236] Specific example:

[0237] The emotion engine detects when the user's voice sounds tense and identifies it as "tension."

[0238] 6. Server-driven response generation

[0239] Based on the analysis results and the output of the emotion engine, the server uses generative AI to generate appropriate responses. The generative AI constructs natural-sounding sentences and provides clear and emotionally sensitive answers to the user's questions.

[0240] Specific example:

[0241] The system generates the response: "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0242] 7. Sending responses from the server to the terminal.

[0243] The generated response is sent from the server to the terminal. If the response is in text format, it is sent as is. If an audio response is required, automated speech software is used to convert the text into audio data, which is then sent to the terminal.

[0244] 8. Display of answers via device

[0245] The device displays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[0246] Specific example:

[0247] A message is displayed or played saying, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0248] This configuration allows the system to efficiently handle inquiries about basic administrative services, provide a user-friendly interface that is considerate of the elderly, and deliver kind responses that are sensitive to the user's feelings. This enables the effective use of limited resources within local governments and improves resident satisfaction.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] Users access the system using a terminal and enter their questions. For example, a user might type "What are the opening hours of the nearby library?" in text format. Users can also dictate their questions aloud.

[0252] Step 2:

[0253] The terminal sends the entered text or voice data to the server. If voice input is used, the terminal uses speech-to-text software to convert the voice data into text data and then sends it.

[0254] Step 3:

[0255] The server receives the text data and passes it to a natural language processing engine, which then begins analyzing the question. The natural language processing engine extracts keywords and important phrases from the text data to understand the intent of the question.

[0256] Specific example:

[0257] Extract important keywords such as "library" and "opening hours."

[0258] Step 4:

[0259] The server searches the database for relevant information based on the analysis results. The server sends queries to the database, which stores laws, regulations, and past case examples, and retrieves the relevant information.

[0260] Specific example:

[0261] Search database entries related to "library" and "opening hours" to retrieve information on "opening hours of nearby libraries".

[0262] Step 5:

[0263] The server passes user input data and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies the user's emotions (e.g., joy, anger, sadness, surprise) from the text and voice data.

[0264] Specific example:

[0265] The emotion engine detects when the user's voice sounds tense and identifies it as "tension."

[0266] Step 6:

[0267] The server uses generative AI to generate appropriate answers based on the analysis results and the output of the emotion engine. The generative AI constructs natural-sounding sentences and provides clear and emotionally sensitive answers to the user's questions.

[0268] Specific example:

[0269] The system generates the response: "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0270] Step 7:

[0271] The server sends the generated response to the terminal in text format. If necessary, the server uses automated speech software to convert the generated text into audio data and sends it to the terminal.

[0272] Specific example:

[0273] Send a message in text or voice format saying, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0274] Step 8:

[0275] The device displays or plays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[0276] Specific example:

[0277] A message appears on the screen or is played as audio stating, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0278] This step enables the system to efficiently handle inquiries about basic administrative services, providing a user-friendly interface that is considerate of the elderly and users with low IT literacy, as well as providing kind and empathetic responses. This allows for the effective use of limited resources within local governments and improves resident satisfaction.

[0279] (Example 2)

[0280] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0281] The current local government's resident service system has problems such as being difficult for the elderly and users with low IT literacy to use, and time and effort are required for inquiry responses. There is also an issue that it is difficult to provide responses that consider the emotions of users, and it is difficult to improve resident satisfaction.

[0282] 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.

[0283] In this invention, the server includes means for analyzing the user's input using a natural language processing engine, means for obtaining related data from a database based on the analysis result, generative AI means for generating an appropriate answer based on the obtained data, and sentiment analysis means for analyzing the user's emotion. Thereby, an interface that can be easily used by the elderly and users with low IT literacy is provided, and a quick and appropriate response that takes into account the user's emotion becomes possible.

[0284] The "user" refers to a person who accesses the system and inputs questions or information.

[0285] The "user terminal" is a device used by the user to access the system, and refers to a personal computer, smartphone, etc.

[0286] The "server" refers to a device that receives input data from a user terminal and performs analysis and processing.

[0287] The "natural language processing engine" refers to software that analyzes text data, extracts keywords and important phrases, and understands the intention of a question.

[0288] The "database" refers to an information storage system that stores and manages related information, including laws, regulations, past response cases, etc.

[0289] "Generative AI methods" refer to artificial intelligence technologies that generate appropriate answers based on acquired data.

[0290] "Emotion analysis methods" refer to technologies that identify and analyze emotions from user input data and voice data.

[0291] "Speech-to-text conversion software" refers to software that converts audio data into text data.

[0292] "Automatic voice software" refers to software that converts text data into speech data.

[0293] This invention is a system for improving resident services in local governments, and provides an interface that is particularly easy to use for the elderly and users with low IT literacy. It also utilizes an emotion engine to provide responses that take the user's emotions into consideration. A detailed description of the system follows.

[0294] System Overview

[0295] This system consists of the following main components:

[0296] A device for the user to input data (e.g., a personal computer, a smartphone)

[0297] Server for receiving and processing input data

[0298] Natural language processing engine (e.g., natural language processing API)

[0299] Database (e.g., relational database management system)

[0300] Generative AI (e.g., generative model AI)

[0301] Speech-to-text conversion software (e.g., speech recognition software)

[0302] Automatic voice software (e.g., speech synthesis software)

[0303] Emotion engine (e.g., emotion analysis software)

[0304] Program processing description

[0305] 1. Input by user

[0306] The user accesses the system using a terminal and inputs questions or information. The input method can be in text format or voice format. For example, when the user asks "Please tell me the business hours of the nearby library" in voice, the microphone of the smartphone is used.

[0307] 2. Data transmission by terminal

[0308] The terminal transmits the input data to the server. In the case of voice input, voice text conversion software (e.g., speech recognition software) is used to convert the voice data into text data. Then, the text data is transmitted to the server.

[0309] Specific example: The smartphone converts the voice input into text using speech recognition software and transmits "Please tell me the business hours of the nearby library" to the server.

[0310] 3. Question analysis by server

[0311] The server passes the received text data to a natural language processing engine (e.g., natural language processing API) to analyze the intention of the question. For example, by extracting keywords such as "library" and "business hours", the content of the user's question is understood.

[0312] [[ID=,38]] 4. Database search by server

[0313] Based on the analysis result, the server searches for and retrieves relevant information from a database (e.g., relational database management system). For example, it retrieves data related to "library" and "business hours".

[0314] 5. User emotion analysis using an emotion engine

[0315] The server passes user input data and voice data to an emotion engine (e.g., emotion analysis software) to analyze the user's emotions. The emotion engine can identify emotions such as joy, anger, sadness, and surprise.

[0316] Specific example: The server identifies that the user is "stressed" from their input.

[0317] 6. Server-driven response generation

[0318] Based on the analysis results and the output of the emotion engine, the server uses generative AI (e.g., generative model AI) to generate an appropriate response. For example, it might generate a response like, "The nearby library is open from 8am to 8pm on weekdays. Please feel free to go out."

[0319] Example of a prompt:

[0320] "Please tell me the opening hours of the nearby library. The user is feeling anxious. Please generate a kind and reassuring answer."

[0321] 7. Sending responses from the server to the terminal.

[0322] The generated response is sent from the server to the terminal. If necessary, automated speech software (e.g., text-to-speech software) is used to convert the text into speech data.

[0323] 8. Display of answers via device

[0324] The device displays the received response to the user. If it's in text format, it's displayed on the screen; if it's in audio format, it's played through the speaker. For example, a smartphone might display or play the message, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0325] This system efficiently handles inquiries about resident services from local governments and provides a user-friendly interface that is considerate of the elderly. Furthermore, it enables responses that respond to user emotions, thereby improving resident satisfaction.

[0326] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0327] Step 1: User input

[0328] Users access the system using their smartphones or computers and input questions and information. For example, they might ask a question by voice, such as, "Please tell me the opening hours of the nearby library." The input data is in voice format and is saved on the device as initial input information.

[0329] Step 2: Data transmission by the terminal

[0330] The terminal sends the voice data entered by the user to the server. The voice data is converted into text data using speech-to-text software (e.g., speech recognition software). The converted text data, "Please tell me the opening hours of the nearby library," is sent to the server.

[0331] Input: Audio data

[0332] Output: Text data

[0333] Specific operation: The smartphone captures the audio and converts it to text using speech recognition software.

[0334] Step 3: Server-based question analysis

[0335] The server passes the received text data to a natural language processing engine (e.g., a natural language processing API) for analysis. The natural language processing engine extracts keywords such as "library" and "opening hours" from the text data and understands the intent of the question.

[0336] Input: Text data

[0337] Output: Analyzed data (keywords and intent)

[0338] Specific operation: The server inputs text data into a natural language processing API, which then analyzes and extracts keywords and intent.

[0339] Step 4: Server-based database search

[0340] The server searches a database (e.g., a relational database management system) based on the analyzed keywords and intent, and retrieves relevant information. For example, the server searches database entries related to "library" and "opening hours" to retrieve the opening hours of the nearest library.

[0341] Input: Analyzed data (keywords and intent)

[0342] Output: Acquired information

[0343] Specific operation: The server generates a database query and searches for and retrieves the relevant data.

[0344] Step 5: User emotion analysis using an emotion engine

[0345] The server passes the user's input data (including voice data) to an emotion engine (e.g., emotion analysis software) to analyze the user's emotions. The emotion engine identifies emotions such as "tension" from the input data.

[0346] Input: Audio data or text data

[0347] Output: Analyzed sentiment data

[0348] Specific operation: The server inputs voice or text data into sentiment analysis software to identify emotions.

[0349] Step 6: Server generates response

[0350] The server uses generative AI (e.g., generative model AI) to generate an appropriate response based on the analysis of the question and the output of the sentiment engine. For example, it might generate a response like, "The nearby library is open from 8am to 8pm on weekdays. Please feel free to go out."

[0351] Input: Analyzed data (keywords, intent, sentiment)

[0352] Output: Generated response (text data)

[0353] Specific operation: The server inputs prompts and analysis data into the generative AI and generates an appropriate response.

[0354] Step 7: Sending the response from the server to the terminal

[0355] The generated responses are sent from the server to the terminal in text format or, if necessary, in audio format. For audio format, automated speech software (e.g., text-to-speech software) is used.

[0356] Input: Text format answer

[0357] Output: Answer in text or audio format

[0358] Specific operation: The server passes text data to the automated speech software, which converts it into speech data and sends it.

[0359] Step 8: Displaying the answer via the device

[0360] The device displays the received response to the user. If it's in text format, it's displayed on the screen; if it's in audio format, it's played through the speaker.

[0361] Input: Text or audio response

[0362] Output: Displayed on screen or played as audio.

[0363] Specific action: The smartphone displays a message on the screen or plays audio from the speaker.

[0364] (Application Example 2)

[0365] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0366] User interfaces in autonomous vehicles present challenges, particularly for the elderly and those with low IT literacy. Furthermore, conventional systems are insufficient in responding to user emotions, highlighting the need to improve passenger satisfaction and safety. Additionally, accurately analyzing user voice input and providing appropriate responses to inquiries presents technical challenges.

[0367] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for transmitting the user's input to the server, means for analyzing the user's input within the server using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating an appropriate response based on the acquired data, means for transmitting the generated response to a user terminal, means for displaying the response on the user terminal, emotion engine means for analyzing the user's emotions within the autonomous vehicle and generating an appropriate response based on those emotions, and means for converting the generated response into voice data and providing it to the user. This makes it possible for users to easily access information even within an autonomous vehicle and to provide responses that take the user's emotions into consideration.

[0368] "Means of receiving user input" refers to an interface that allows users to input questions or instructions to the system in voice or text format.

[0369] "Means of sending user input to the server" refers to communication methods for transferring data entered by the user to the server in real time.

[0370] "Means for analyzing user input within a server using a natural language processing engine" refers to a means of analyzing received user input data using a natural language processing engine to understand the user's intent.

[0371] "Means for obtaining relevant data from a database based on analysis results" refers to methods for searching and obtaining relevant information from a database based on the analysis results of a natural language processing engine.

[0372] "Generative AI methods that generate appropriate answers based on acquired data" refers to generative artificial intelligence that generates answers suitable for user questions based on information acquired from a database.

[0373] "Means for sending the generated response to the user's terminal" refers to means for sending the generated response to the user's terminal so that it can be displayed or played back.

[0374] "Means for displaying answers on the user's terminal" refers to means for displaying the generated answers on the screen of the user's terminal.

[0375] "An emotion engine means for analyzing user emotions within an autonomous vehicle and generating appropriate emotion-based responses" refers to an engine with emotion analysis capabilities that analyzes user emotions from voice and text data and generates responses corresponding to those emotions.

[0376] "Means for converting generated responses into audio data and providing them to the user" refers to means for converting text-based responses into audio data and allowing the user to listen to them through speakers or headphones.

[0377] A mode for carrying out this invention relates to an interaction system used in an autonomous vehicle. This system allows passengers to receive user-friendly and emotionally sensitive responses when obtaining information or getting answers to questions while the vehicle is in motion.

[0378] System Overview

[0379] This system consists of the following main hardware and software components:

[0380] Hardware:

[0381] Communication devices (tablets, smartphones, etc.) inside autonomous vehicles

[0382] Microphone (for voice input)

[0383] Speaker (for voice response)

[0384] software:

[0385] Natural language processing engine (e.g., Google® NLP)

[0386] Speech-to-text software (e.g., Google Speech-to-Text)

[0387] Automated speech software (e.g., Google Text-to-Speech)

[0388] Emotion engine (e.g., Affectiva SDK)

[0389] Generative AI (e.g., OpenAI GPT-4(registered trademark))

[0390] Processing flow

[0391] 1. User voice input

[0392] The user voice-inputs their questions into the microphone inside the autonomous vehicle. This voice data is converted into text data by speech-to-text software and sent to the server.

[0393] 2. Question analysis by the server

[0394] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP) to understand the intent behind the user's question.

[0395] 3. Database Search

[0396] Based on the analysis results, the server retrieves relevant data from the database. This database includes FAQs, traffic information, destination information, and more.

[0397] 4. Sentiment analysis and response generation

[0398] The server analyzes the user's text and voice data using an emotion engine (e.g., Affectiva SDK) to identify the user's emotions (e.g., distressed, relieved). Then, it uses a generative AI (e.g., OpenAI GPT-4) to generate appropriate responses that take the user's emotions into consideration.

[0399] 5. Text-to-speech conversion and response provision.

[0400] The generated responses are converted into audio data by automated speech-to-speech software (such as Google Text-to-Speech) and played back to the user through the speaker.

[0401] Specific example

[0402] For example, if a user asks "Where is the nearest parking lot?" into the in-car microphone, the audio is converted to text. The server uses a natural language processing engine to recognize the keyword "parking lot" and retrieves information about the nearest parking lot from the database. Once the emotion engine identifies the user's distress from the text data, the generative AI generates a response such as "The nearest parking lot is at the north exit of the station. Drive with peace of mind." This response is converted to audio data and played back through the speaker.

[0403] Example of a prompt

[0404] By inputting prompts like the following into a generative AI model, it will generate an appropriate response.

[0405] Please answer the following questions. If the user is having trouble, please add a kind explanation.

[0406] Question: Where is the nearest parking lot? User's sentiment: Troubled. Answer: The nearest parking lot is at the north exit of the station. Further explanation:

[0407] This configuration allows users to easily access information even within autonomous vehicles and provides responses that are sensitive to the user's emotions.

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The user inputs their question by voice into the microphone. The input data is "voice data".

[0411] Step 2:

[0412] The device uses speech-to-text software (such as Google Speech-to-Text) to convert audio data into text data. At this stage, the input is "audio data" and the output is "text data". Specifically, speech recognition software analyzes the audio data and converts it into the corresponding text.

[0413] Step 3:

[0414] The terminal sends the converted text data to the server. The input is "text data," and the output is "sending data to the server." Specifically, the terminal transfers data to the server via the network.

[0415] Step 4:

[0416] The server passes the received text data to a natural language processing engine (such as Google NLP) and begins analysis. The input is "text data," and the output is the "analysis result." Specifically, the natural language processing engine extracts keywords and phrases from the text and understands the intent of the user's question.

[0417] Step 5:

[0418] The server searches the database for relevant information based on the analysis results. The input is the "analysis results," and the output is the "related data." Specifically, a database query is executed, and the relevant data is retrieved.

[0419] Step 6:

[0420] The server passes the user's text data to an emotion engine (such as the Affectiva SDK) to analyze the user's emotions. The input is "text data," and the output is "emotion analysis results." Specifically, the emotion engine analyzes the characteristics of the text and voice to identify the user's emotional state.

[0421] Step 7:

[0422] The server generates an appropriate response using a generative AI model (such as OpenAI GPT-4) based on the analysis results and sentiment analysis results. The input is the "analysis results" and "sentiment analysis results," and the output is the "generated response." Specifically, the generative AI model generates a natural response based on the input prompt sentence.

[0423] Step 8:

[0424] The server passes the generated response to speech-to-text software (such as Google Text-to-Speech) to convert it into audio data. The input is the "generated response," and the output is the "audio data." Specifically, the speech synthesis software analyzes the text data and converts it into speech.

[0425] Step 9:

[0426] The server sends audio data to the terminal. The input is "audio data," and the output is "data transmission to the terminal." Specifically, the server transfers the audio data to the terminal via the network.

[0427] Step 10:

[0428] The device plays the received audio data through its speaker. The input is "audio data," and the output is "audio playback." Specifically, the device decodes the audio file and plays the audio through its speaker.

[0429] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0430] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0431] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0432] [Second Embodiment]

[0433] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0434] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0435] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0436] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0437] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0438] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0439] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0440] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0441] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0442] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0443] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0444] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0445] A detailed description of embodiments for carrying out the present invention is provided below. This embodiment provides a system that efficiently handles resident services for local governments and enables smooth information provision, especially for the elderly and users with low IT literacy.

[0446] System Overview

[0447] This system consists of the following main components:

[0448] A terminal for user input.

[0449] Server for receiving and processing input data

[0450] Natural Language Processing Engine

[0451] database

[0452] Generative AI

[0453] Speech-to-text software

[0454] Automated voice software

[0455] Program Processing Description

[0456] 1. User input

[0457] Users access the system using a device (e.g., a personal computer or smartphone) and input questions or information. Users may input questions in text format, or, in some cases, elderly individuals may dictate their questions verbally.

[0458] Specific example:

[0459] The user enters, "When is the deadline for paying next year's resident tax?"

[0460] 2. Data transmission by the terminal

[0461] The terminal converts data entered by the user into text data and sends it to the server. If voice input is used, speech-to-text conversion software is used to convert the voice data into text data. The converted text data is then sent to the server by the terminal.

[0462] 3. Question analysis by the server

[0463] The server passes the received text data to a natural language processing engine for analysis. The natural language processing engine extracts keywords and important phrases from the text data to understand the intent of the question.

[0464] Specific example:

[0465] We analyze important keywords such as "resident tax," "payment deadline," and "next fiscal year."

[0466] 4. Database search by server

[0467] Based on the analysis results, the server searches the database for relevant information. The database contains information such as laws, regulations, and past response examples.

[0468] Specific example:

[0469] Search database entries related to "resident tax," "payment deadline," and "next fiscal year."

[0470] 5. Server-driven response generation

[0471] The server uses generative AI to generate appropriate answers based on the acquired data. The generative AI generates natural-sounding sentences and provides clear answers to the user's questions.

[0472] Specific example:

[0473] Generate the response: "The deadline for paying next year's resident tax is June 1, 2023."

[0474] 6. Sending responses from the server to the terminal.

[0475] The generated response is sent from the server to the terminal and provided to the user. If the response is in text format, it is sent as is. If an audio response is required, automated speech software is used to convert the text into audio data, which is then sent to the terminal.

[0476] 7. Display of answers via device

[0477] The device displays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[0478] Specific example:

[0479] The message "The deadline for paying next year's resident tax is June 1, 2023" is displayed or played.

[0480] This system efficiently handles inquiries about basic administrative services and provides a user-friendly interface that is considerate of the elderly. This configuration allows for the effective use of limited resources within local governments and improves resident satisfaction.

[0481] The following describes the processing flow.

[0482] Step 1:

[0483] The user accesses the system using a terminal and enters a question. For example, the user might enter "When is the deadline for paying next year's resident tax?" in text format.

[0484] Step 2:

[0485] The terminal sends the entered text data to the server. Since the terminal sends the user's text input directly to the server, no special data conversion is performed in this step.

[0486] Step 3:

[0487] The server receives the text data and passes it to the natural language processing engine to begin analysis. The natural language processing engine extracts keywords and important phrases from the text data and understands the intent of the question.

[0488] Step 4:

[0489] The server searches the database for relevant information based on the analysis results. The database stores laws, regulations, and past case examples. For example, it searches for entries related to "resident tax," "payment deadline," and "next fiscal year."

[0490] Step 5:

[0491] Based on information retrieved from the database by the server, a generative AI is used to generate appropriate answers. The generative AI constructs natural-sounding sentences and provides clear answers to the user's questions.

[0492] Step 6:

[0493] The server sends the generated response to the terminal in text format. For example, the text data "The deadline for paying next year's resident tax is June 1, 2023" is sent.

[0494] Step 7:

[0495] The device displays the received response on the screen. The user can view the response in text format.

[0496] Step 8:

[0497] Only when voice input is detected, the terminal passes the user's voice data to speech-to-text software, which converts it into text data. This converted text data is then sent to the server.

[0498] Step 9:

[0499] If voice output is required, the server converts the generated text response into an automated speech-to-speech program to produce audio data. The generated audio data is then sent to the terminal.

[0500] Step 10:

[0501] The device plays back the received audio data and provides the user with an audio response. This makes it possible to support users with low IT literacy, such as the elderly.

[0502] (Example 1)

[0503] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0504] The present invention aims to provide a system that enables smooth information provision in local government resident services, particularly for the elderly and users with low IT literacy. Current systems have the problem of requiring users to spend a considerable amount of time and effort to obtain information. Furthermore, in environments where voice input and output cannot be properly utilized, the system is particularly difficult for the elderly to use. There is a need to provide a system that solves these problems.

[0505] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0506] In this invention, the server includes means for receiving input from a user, means for a terminal to convert the user's input into data and transmit it to the server, means for the server to analyze the user's input using a natural language processing engine, means for obtaining relevant information from a storage device based on the analysis results, means for generating an appropriate response based on the acquired information using a generation AI, means for transmitting the generated response to the user terminal, and means for displaying the response on the user terminal. This enables the rapid and accurate provision of information regarding the user's input. Furthermore, by incorporating voice input and voice output functions, the system can be made particularly easy to use for the elderly, thereby improving the efficiency of services for residents.

[0507] A "user" is an entity that uses a system to input information and receive responses.

[0508] A "terminal" is a device used by a user to access and input data into a system, and includes personal computers and smartphones.

[0509] A "server" is a computing device that receives input data from users and performs processing such as analysis, data acquisition, and response generation.

[0510] A "natural language processing engine" is software or an algorithm that analyzes text data, extracts keywords and important phrases, and understands the intent of a question.

[0511] A "storage device" is a device that stores data for a server to retrieve relevant information based on analysis results, and includes databases and the like.

[0512] "Generative AI means" refers to a device or program that uses artificial intelligence technology to generate appropriate answers based on acquired data.

[0513] "Voice-to-text conversion software" is software that converts a user's voice input into text data.

[0514] "Automated voice software" is software that converts generated text responses into audio data and enables audio output.

[0515] "Means for receiving input" refers to an interface that allows users to input information such as questions into a terminal.

[0516] "Means of converting and transmitting data" refers to a function that allows a terminal to convert user input into text data or an appropriate format and send it to a server.

[0517] "Means of analysis" refers to the process by which a server uses a natural language processing engine to analyze user input data and understand the intent behind the question.

[0518] "Means of acquisition" refers to the function that allows the server to search for and retrieve relevant information from storage devices based on the analysis results.

[0519] "Means of transmission" refers to the communication function that allows the server to send the generated response back to the user's terminal.

[0520] "Means of display" refers to display devices and audio output functions that allow the user terminal to present the response sent from the server to the user.

[0521] This invention is a system designed to efficiently handle resident services for local governments, and is particularly capable of providing smooth information to elderly people and users with low IT literacy. The system mainly consists of a terminal for user input, a server for receiving and processing input data, a natural language processing engine, a database, a generative AI, and speech-to-text conversion software or automated speech software.

[0522] Users access the system using devices such as personal computers and smartphones and input questions and information. For example, a user might input, "When is the deadline for paying next year's resident tax?" It is also conceivable that an elderly person might ask a question by voice, such as, "Please tell me about the resident tax payment deadline."

[0523] The terminal converts data entered by the user into text data and sends it to the server. If voice input is used, the terminal uses speech-to-text software to convert the voice data into text. The converted text data is then sent to the server by the terminal.

[0524] The server passes the received text data to a natural language processing engine (e.g., natural language processing engine software) for analysis. The natural language processing engine extracts primitive keywords and important phrases from the text data to understand the intent of the user's question. For example, it analyzes keywords such as "resident tax," "payment deadline," and "next fiscal year."

[0525] Based on the analysis results, the server searches for relevant information from a database (e.g., a database management system). The database stores information such as laws, regulations, and past case examples, and the server retrieves the most relevant information based on this. For example, it searches for database entries related to "resident tax," "payment deadline," and "next fiscal year."

[0526] The server uses generative AI (e.g., a generative AI model) to generate appropriate answers based on the acquired data. This generative AI generates natural-sounding sentences and provides clear answers to user questions. For example, in response to the prompt "When is the deadline for paying next year's resident tax?", it generates the answer "The deadline for paying next year's resident tax is June 1, 2023."

[0527] The generated responses are sent from the server to the terminal and provided to the user. If the response is in text format, it is sent as is. If an audio response is required, the text is converted into audio data using automated speech software (e.g., automated speech generation software), and the audio data is sent to the terminal.

[0528] The device displays the response received from the server to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker. For example, the message "The deadline for paying next year's resident tax is June 1, 2023." might be displayed on the screen, or the same content might be played as audio.

[0529] In this way, the system of the present invention can respond to a variety of user inputs and provide appropriate information efficiently and quickly.

[0530] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0531] Step 1:

[0532] User input

[0533] Users access the system using a device (such as a computer or smartphone) and input questions or information. Specifically, a user might type "When is the deadline for paying next year's resident tax?" as text, or say "Please tell me about the resident tax payment deadline" as voice. In this step, if the user's input is in text format, it is entered directly into the device; if it is in voice format, the voice is recorded.

[0534] Step 2:

[0535] Data transmission by terminal

[0536] The terminal processes the data entered by the user. Text data is treated directly as a text file, while voice data is converted to text data using speech-to-text software. For example, voice input is converted to the text "Please tell me about the deadline for paying resident tax." The converted text data is then sent to the server by the terminal. The process of converting voice input to text data and sending it is completed here.

[0537] Step 3:

[0538] Server-based question analysis

[0539] The server receives user input data and passes it to a natural language processing engine (e.g., natural language processing engine software). The natural language processing engine extracts important keywords and phrases from the text data. Specifically, it identifies important elements such as "resident tax," "payment deadline," and "next fiscal year" to understand the intent of the question. Through this analysis, the server generates a dataset containing semantically important information.

[0540] Step 4:

[0541] Server-based database search

[0542] Based on the analysis results, the server searches for relevant information from its storage device (database management system). The database contains laws, regulations, and past case examples. For example, the server searches the database entries related to "resident tax," "payment deadline," and "next fiscal year," and retrieves that information. In this step, the server collects the relevant data and prepares it for use in the next step.

[0543] Step 5:

[0544] Server-based response generation

[0545] Based on the data acquired by the server, a generative AI (e.g., a generative AI model) is used to generate an appropriate answer. A prompt is input to the generative AI model, and a response in a natural sentence format is generated. For example, in response to the prompt "When is the deadline for paying next year's resident tax?", the model generates the answer "The deadline for paying next year's resident tax is June 1, 2023." In this step, the generative AI model generates accurate and easy-to-understand sentences.

[0546] Step 6:

[0547] Sending responses from the server to the terminal.

[0548] The generated responses are sent from the server to the terminal. Text-based responses are sent as is, while if an audio response is required, automated speech software is used to convert the text to speech, and that audio data is sent to the terminal. For example, the text response "The deadline for paying next year's resident tax is June 1, 2023." is sent to the terminal.

[0549] Step 7:

[0550] Display of answers via device

[0551] The device displays the response received from the server to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker. Specifically, a message such as "The deadline for paying next year's resident tax is June 1, 2023" might be displayed on the screen or played aloud. In this step, the user can obtain the answer to their question visually or audibly.

[0552] (Application Example 1)

[0553] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0554] In modern society, the number of elderly users and users with low IT literacy is increasing, making it difficult to provide information smoothly to these users. Furthermore, while there is a need to provide product information and service guidance quickly and effectively in physical stores, current technology is insufficient to meet this demand. In particular, there is a need for intuitive interfaces that can be used by elderly users and users with low IT literacy.

[0555] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0556] In this invention, the server includes means for receiving input from a user, means for transmitting the user's input to the server, means for analyzing the user's input within the server using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating an appropriate response based on the acquired data, means for transmitting the generated response to a user terminal, means for displaying the response on the user terminal, means for recognizing the user's gaze direction using a gaze detection sensor and transmitting it to the server, means for providing product information and service guidance within the physical store based on the gaze direction, and means for receiving questions regarding product information and service guidance within the physical store via voice input. This makes it possible to provide information intuitively and effectively to elderly people and users with low IT literacy in physical stores.

[0557] "Means of receiving user input" refers to an interface that allows users to input information into a system. This includes smart glasses, smartphones, and computers.

[0558] "Means of sending user input to a server" refers to the function of sending information entered by the user to a server via a network. This utilizes internet connectivity or wireless communication technology.

[0559] "Methods for analyzing user input within a server using a natural language processing engine" refers to technologies that analyze text and audio data received by the server to understand the user's intent. The natural language processing engine plays this role.

[0560] "Means of obtaining relevant data from a database based on analysis results" refers to a function that searches for and retrieves necessary information from a database based on the results of analysis performed by a natural language processing engine.

[0561] "Generative AI methods for generating appropriate answers" refers to AI technology that generates appropriate answers to user questions based on acquired data. Generative AI plays this role.

[0562] "Means of sending generated responses to the user's terminal" refers to the function of transferring responses created by a generative AI to the user's device. This is done via the internet or wireless communication.

[0563] "Means of displaying answers on the user's device" refers to an interface that displays the generated answers on the user's device. This role is fulfilled by the display of smart glasses or the screen of a smartphone.

[0564] "A means of recognizing the direction of the user's gaze using a gaze detection sensor and transmitting it to a server" refers to a technology that detects the direction the user is looking and transmits that information to a server. The gaze detection sensor plays this role.

[0565] "Means of providing product information and service guidance within a physical store based on the direction of gaze" refers to a function that provides detailed information about products and services based on the direction the user is looking.

[0566] "A means of receiving questions about product information and service guidance within a physical store via voice input" refers to a function that captures user voice questions, converts them into text data, and analyzes them. Voice-to-text conversion software fulfills this role.

[0567] A specific embodiment for carrying out the present invention is shown below. This embodiment makes it possible to provide information intuitively and effectively to elderly people and users with low IT literacy in physical stores.

[0568] System Configuration

[0569] This system consists of the following main components:

[0570] 1. A device that accepts user input (such as smart glasses or a smartphone)

[0571] 2. Server

[0572] 3. Natural Language Processing Engine

[0573] 4. Database

[0574] 5. Generative AI

[0575] 6. Eye-tracking sensor

[0576] 7. Speech-to-text conversion software

[0577] 8. Automated voice software

[0578] Hardware and software usage

[0579] The primary device used is a pair of smart glasses. These smart glasses are equipped with an eye-tracking sensor to recognize the user's gaze direction. They also have a microphone for voice input.

[0580] On the server side, a natural language processing engine (e.g., spaCy), speech-to-text software (e.g., Mozilla DeepSpeech), generative AI (e.g., OpenAI GPT-3), and a database system (e.g., PostgreSQL) are used. These software components work together to analyze user input data and generate appropriate responses.

[0581] Methods for data processing and data calculation

[0582] Processing of eye-tracking data

[0583] When a user looks at products or services in a store through their smart glasses, an eye-tracking sensor recognizes the direction of their gaze and sends that data to a server. The server analyzes the eye-tracking data to identify information about products the user is interested in.

[0584] Analysis of voice input

[0585] When a user enters a question by voice, the microphone in the smart glasses collects the voice and sends the voice data to a server. The voice data is then converted into text data using speech-to-text software.

[0586] Natural language processing and database search

[0587] The server passes the converted text data to a natural language processing engine to analyze the user's question. Based on the analysis results, it searches the database for relevant product information and service details.

[0588] Answer generation

[0589] Based on the acquired information, a generative AI generates appropriate answers to the user's questions. The answers are generated in natural-sounding sentences.

[0590] Information provision

[0591] The generated response is sent back to the smart glasses via the server and displayed in the user's field of view. If output in audio format is requested, the text is converted into audio data using automated speech software and played back through the smart glasses' speaker.

[0592] Examples of prompt statements

[0593] The following are specific examples of questions users might ask smart glasses in a physical store:

[0594] "What are the features of this product?"

[0595] "How much does this item cost?"

[0596] "Where can I find this product?"

[0597] As described above, the system based on the present invention enables intuitive and effective information provision in physical stores, particularly for elderly people and users with low IT literacy.

[0598] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0599] Step 1:

[0600] The user wears smart glasses and walks around a physical store. When the user looks at a product or service that interests them, the eye-tracking sensor recognizes the direction of their gaze. The input is gaze direction data, and the output is data related to gaze direction. The server receives this gaze direction data and proceeds to the next step.

[0601] Step 2:

[0602] The user provides voice input. For example, they might ask, "What are the features of this product?" The smart glasses' microphone collects the voice data and sends it to the server. The input is voice data, and the output is the raw voice data sent to the server.

[0603] Step 3:

[0604] The server converts the received audio data into text data using speech-to-text software (e.g., Mozilla DeepSpeech). The input is audio data, and the output is the converted text data. This allows the user's questions to be analyzed in text format.

[0605] Step 4:

[0606] The server passes text data to a natural language processing engine (e.g., spaCy) to analyze the user's question. The input is text data, and the output is keywords and important phrases included in the analysis results. Based on the analysis results, the server understands the user's intent.

[0607] Step 5:

[0608] The server searches a database (e.g., PostgreSQL) for information on products of interest based on the analysis results and eye-tracking data. The input is the analysis results and eye-tracking data, and the output is detailed information on related products. This allows the server to retrieve appropriate information.

[0609] Step 6:

[0610] The server uses generative AI (e.g., OpenAI GPT-3) to generate appropriate answers to user questions based on the acquired information. The input is detailed product information, and the output is the generated text-based answer. The generative AI generates natural-sounding sentences, creating answers that are easy for the user to understand.

[0611] Step 7:

[0612] The server sends the generated text-formatted response to the smart glasses. The input is the generated text-formatted response, and the output is the text data sent to the smart glasses. This allows the user to receive the response.

[0613] Step 8:

[0614] The user's smart glasses display the received text data on a screen, and, if necessary, convert it into audio data using automated voice software and play it through the speaker. The input is text data, and the output is the response displayed in the user's field of vision and the audio data. This allows the user to see the response visually and hear it aloud.

[0615] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0616] A detailed description of embodiments for carrying out the present invention is provided below. This embodiment provides a system that efficiently handles resident services for local governments and enables smooth information provision, especially for the elderly and users with low IT literacy. Furthermore, by combining it with an emotion engine, responses based on the user's emotions can also be realized.

[0617] System Overview

[0618] This system consists of the following main components:

[0619] A terminal for user input.

[0620] Server for receiving and processing input data

[0621] Natural Language Processing Engine

[0622] database

[0623] Generative AI

[0624] Speech-to-text software

[0625] Automated voice software

[0626] Emotional Engine

[0627] Program Processing Description

[0628] 1. User input

[0629] Users access the system using a device (e.g., a personal computer or smartphone) and input questions or information. Users may input questions in text format, or, in some cases, elderly individuals may dictate their questions verbally.

[0630] Specific example:

[0631] The user enters, "Please tell me the opening hours of the nearby library."

[0632] 2. Data transmission by the terminal

[0633] The terminal sends the entered text data to the server. If voice input is used, the voice data is converted to text data using speech-to-text software. The converted text data is then sent to the server by the terminal.

[0634] 3. Question analysis by the server

[0635] The server passes the received text data to a natural language processing engine to begin analysis. The natural language processing engine extracts keywords and important phrases from the text data and understands the intent of the question.

[0636] Specific example:

[0637] We analyze important keywords such as "library" and "opening hours."

[0638] 4. Database search by server

[0639] Based on the analysis results, the server searches the database for relevant information. The database stores laws, regulations, and past case examples.

[0640] Specific example:

[0641] Search database entries related to "library" and "opening hours".

[0642] 5. User emotion analysis using an emotion engine

[0643] The server passes user input data and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions (e.g., joy, anger, sadness, surprise) from the user's text and voice data.

[0644] Specific example:

[0645] The emotion engine detects when the user's voice sounds tense and identifies it as "tension."

[0646] 6. Server-driven response generation

[0647] Based on the analysis results and the output of the emotion engine, the server uses generative AI to generate appropriate responses. The generative AI constructs natural-sounding sentences and provides clear and emotionally sensitive answers to the user's questions.

[0648] Specific example:

[0649] The system generates the response: "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0650] 7. Sending responses from the server to the terminal.

[0651] The generated response is sent from the server to the terminal. If the response is in text format, it is sent as is. If an audio response is required, automated speech software is used to convert the text into audio data, which is then sent to the terminal.

[0652] 8. Display of answers via device

[0653] The device displays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[0654] Specific example:

[0655] A message is displayed or played saying, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0656] This configuration allows the system to efficiently handle inquiries about basic administrative services, provide a user-friendly interface that is considerate of the elderly, and deliver kind responses that are sensitive to the user's feelings. This enables the effective use of limited resources within local governments and improves resident satisfaction.

[0657] The following describes the processing flow.

[0658] Step 1:

[0659] Users access the system using a terminal and enter their questions. For example, a user might type "What are the opening hours of the nearby library?" in text format. Users can also dictate their questions aloud.

[0660] Step 2:

[0661] The terminal sends the entered text or voice data to the server. If voice input is used, the terminal uses speech-to-text software to convert the voice data into text data and then sends it.

[0662] Step 3:

[0663] The server receives the text data and passes it to a natural language processing engine, which then begins analyzing the question. The natural language processing engine extracts keywords and important phrases from the text data to understand the intent of the question.

[0664] Specific example:

[0665] Extract important keywords such as "library" and "opening hours."

[0666] Step 4:

[0667] The server searches the database for relevant information based on the analysis results. The server sends queries to the database, which stores laws, regulations, and past case examples, and retrieves the relevant information.

[0668] Specific example:

[0669] Search database entries related to "library" and "opening hours" to retrieve information on "opening hours of nearby libraries".

[0670] Step 5:

[0671] The server passes user input data and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies the user's emotions (e.g., joy, anger, sadness, surprise) from the text and voice data.

[0672] Specific example:

[0673] The emotion engine detects when the user's voice sounds tense and identifies it as "tension."

[0674] Step 6:

[0675] The server uses generative AI to generate appropriate answers based on the analysis results and the output of the emotion engine. The generative AI constructs natural-sounding sentences and provides clear and emotionally sensitive answers to the user's questions.

[0676] Specific example:

[0677] The system generates the response: "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0678] Step 7:

[0679] The server sends the generated response to the terminal in text format. If necessary, the server uses automated speech software to convert the generated text into audio data and sends it to the terminal.

[0680] Specific example:

[0681] Send a message in text or voice format saying, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0682] Step 8:

[0683] The device displays or plays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[0684] Specific example:

[0685] A message appears on the screen or is played as audio stating, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0686] This step enables the system to efficiently handle inquiries about basic administrative services, providing a user-friendly interface that is considerate of the elderly and users with low IT literacy, as well as providing kind and empathetic responses. This allows for the effective use of limited resources within local governments and improves resident satisfaction.

[0687] (Example 2)

[0688] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0689] Current municipal resident service systems are difficult for the elderly and users with low IT literacy to use, and responding to inquiries is time-consuming and labor-intensive. Furthermore, they fail to provide responses that are sensitive to users' feelings, making it difficult to improve resident satisfaction.

[0690] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0691] In this invention, the server includes means for analyzing user input using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating appropriate responses based on the obtained data, and sentiment analysis means for analyzing the user's emotions. This provides an interface that is easy to use even for the elderly and users with low IT literacy, and enables quick and appropriate responses that take the user's emotions into consideration.

[0692] A "user" refers to a person who accesses the system and enters questions or information.

[0693] A "user terminal" refers to a device used by a user to access a system, such as a personal computer or smartphone.

[0694] A "server" refers to a device that receives input data from user terminals and performs analysis and processing on it.

[0695] A "natural language processing engine" refers to software that analyzes text data, extracts keywords and important phrases, and understands the intent of a question.

[0696] A "database" refers to an information storage system that stores and manages related information, including laws, regulations, and past response examples.

[0697] "Generative AI methods" refer to artificial intelligence technologies that generate appropriate answers based on acquired data.

[0698] "Emotion analysis methods" refer to technologies that identify and analyze emotions from user input data and voice data.

[0699] "Speech-to-text conversion software" refers to software that converts audio data into text data.

[0700] "Automatic voice software" refers to software that converts text data into speech data.

[0701] This invention is a system for improving resident services in local governments, and provides an interface that is particularly easy to use for the elderly and users with low IT literacy. It also utilizes an emotion engine to provide responses that take the user's emotions into consideration. A detailed description of the system follows.

[0702] System Overview

[0703] This system consists of the following main components:

[0704] A device for the user to input data (e.g., a personal computer, a smartphone)

[0705] Server for receiving and processing input data

[0706] Natural language processing engine (e.g., natural language processing API)

[0707] Database (e.g., relational database management system)

[0708] Generative AI (e.g., generative model AI)

[0709] Speech-to-text conversion software (e.g., speech recognition software)

[0710] Automatic voice software (e.g., speech synthesis software)

[0711] Emotion engine (e.g., emotion analysis software)

[0712] Program Processing Description

[0713] 1. User input

[0714] Users access the system using their devices and input questions or information. Input can be in text or voice format. For example, if a user asks a question by voice, such as "What are the opening hours of the nearby library?", they would use their smartphone's microphone.

[0715] 2. Data transmission by the terminal

[0716] The terminal sends the input data to the server. In the case of voice input, speech-to-text software (e.g., speech recognition software) is used to convert the voice data into text data. The text data is then sent to the server.

[0717] Specific example: A smartphone converts voice input into text using speech recognition software and sends it to a server, saying, "Please tell me the opening hours of the nearby library."

[0718] 3. Question analysis by the server

[0719] The server passes the received text data to a natural language processing engine (e.g., a natural language processing API) to analyze the intent of the question. For example, by extracting keywords such as "library" and "opening hours," it understands the content of the user's question.

[0720] 4. Database search by server

[0721] Based on the analysis results, the server searches for and retrieves relevant information from a database (e.g., a relational database management system). For example, it retrieves data related to "library" and "opening hours."

[0722] 5. User emotion analysis using an emotion engine

[0723] The server passes user input data and voice data to an emotion engine (e.g., emotion analysis software) to analyze the user's emotions. The emotion engine can identify emotions such as joy, anger, sadness, and surprise.

[0724] Specific example: The server identifies that the user is "stressed" from their input.

[0725] 6. Server-driven response generation

[0726] Based on the analysis results and the output of the emotion engine, the server uses generative AI (e.g., generative model AI) to generate an appropriate response. For example, it might generate a response like, "The nearby library is open from 8am to 8pm on weekdays. Please feel free to go out."

[0727] Example of a prompt:

[0728] "Please tell me the opening hours of the nearby library. The user is feeling anxious. Please generate a kind and reassuring answer."

[0729] 7. Sending responses from the server to the terminal.

[0730] The generated response is sent from the server to the terminal. If necessary, automated speech software (e.g., text-to-speech software) is used to convert the text into speech data.

[0731] 8. Display of answers via device

[0732] The device displays the received response to the user. If it's in text format, it's displayed on the screen; if it's in audio format, it's played through the speaker. For example, a smartphone might display or play the message, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[0733] This system efficiently handles inquiries about resident services from local governments and provides a user-friendly interface that is considerate of the elderly. Furthermore, it enables responses that respond to user emotions, thereby improving resident satisfaction.

[0734] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0735] Step 1: User input

[0736] Users access the system using their smartphones or computers and input questions and information. For example, they might ask a question by voice, such as, "Please tell me the opening hours of the nearby library." The input data is in voice format and is saved on the device as initial input information.

[0737] Step 2: Data transmission by the terminal

[0738] The terminal sends the voice data entered by the user to the server. The voice data is converted into text data using speech-to-text software (e.g., speech recognition software). The converted text data, "Please tell me the opening hours of the nearby library," is sent to the server.

[0739] Input: Audio data

[0740] Output: Text data

[0741] Specific operation: The smartphone captures the audio and converts it to text using speech recognition software.

[0742] Step 3: Server-based question analysis

[0743] The server passes the received text data to a natural language processing engine (e.g., a natural language processing API) for analysis. The natural language processing engine extracts keywords such as "library" and "opening hours" from the text data and understands the intent of the question.

[0744] Input: Text data

[0745] Output: Analyzed data (keywords and intent)

[0746] Specific operation: The server inputs text data into a natural language processing API, which then analyzes and extracts keywords and intent.

[0747] Step 4: Server-based database search

[0748] The server searches a database (e.g., a relational database management system) based on the analyzed keywords and intent, and retrieves relevant information. For example, the server searches database entries related to "library" and "opening hours" to retrieve the opening hours of the nearest library.

[0749] Input: Analyzed data (keywords and intent)

[0750] Output: Acquired information

[0751] Specific operation: The server generates a database query and searches for and retrieves the relevant data.

[0752] Step 5: User emotion analysis using an emotion engine

[0753] The server passes the user's input data (including voice data) to an emotion engine (e.g., emotion analysis software) to analyze the user's emotions. The emotion engine identifies emotions such as "tension" from the input data.

[0754] Input: Audio data or text data

[0755] Output: Analyzed sentiment data

[0756] Specific operation: The server inputs voice or text data into sentiment analysis software to identify emotions.

[0757] Step 6: Server generates response

[0758] The server uses generative AI (e.g., generative model AI) to generate an appropriate response based on the analysis of the question and the output of the sentiment engine. For example, it might generate a response like, "The nearby library is open from 8am to 8pm on weekdays. Please feel free to go out."

[0759] Input: Analyzed data (keywords, intent, sentiment)

[0760] Output: Generated response (text data)

[0761] Specific operation: The server inputs prompts and analysis data into the generative AI and generates an appropriate response.

[0762] Step 7: Sending the response from the server to the terminal

[0763] The generated responses are sent from the server to the terminal in text format or, if necessary, in audio format. For audio format, automated speech software (e.g., text-to-speech software) is used.

[0764] Input: Text format answer

[0765] Output: Answer in text or audio format

[0766] Specific operation: The server passes text data to the automated speech software, which converts it into speech data and sends it.

[0767] Step 8: Displaying the answer via the device

[0768] The device displays the received response to the user. If it's in text format, it's displayed on the screen; if it's in audio format, it's played through the speaker.

[0769] Input: Text or audio response

[0770] Output: Displayed on screen or played as audio.

[0771] Specific action: The smartphone displays a message on the screen or plays audio from the speaker.

[0772] (Application Example 2)

[0773] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0774] User interfaces in autonomous vehicles present challenges, particularly for the elderly and those with low IT literacy. Furthermore, conventional systems are insufficient in responding to user emotions, highlighting the need to improve passenger satisfaction and safety. Additionally, accurately analyzing user voice input and providing appropriate responses to inquiries presents technical challenges.

[0775] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for transmitting the user's input to the server, means for analyzing the user's input within the server using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating an appropriate response based on the acquired data, means for transmitting the generated response to a user terminal, means for displaying the response on the user terminal, emotion engine means for analyzing the user's emotions within the autonomous vehicle and generating an appropriate response based on those emotions, and means for converting the generated response into voice data and providing it to the user. This makes it possible for users to easily access information even within an autonomous vehicle and to provide responses that take the user's emotions into consideration.

[0776] "Means of receiving user input" refers to an interface that allows users to input questions or instructions to the system in voice or text format.

[0777] "Means of sending user input to the server" refers to communication methods for transferring data entered by the user to the server in real time.

[0778] "Means for analyzing user input within a server using a natural language processing engine" refers to a means of analyzing received user input data using a natural language processing engine to understand the user's intent.

[0779] "Means for obtaining relevant data from a database based on analysis results" refers to methods for searching and obtaining relevant information from a database based on the analysis results of a natural language processing engine.

[0780] "Generative AI methods that generate appropriate answers based on acquired data" refers to generative artificial intelligence that generates answers suitable for user questions based on information acquired from a database.

[0781] "Means for sending the generated response to the user's terminal" refers to means for sending the generated response to the user's terminal so that it can be displayed or played back.

[0782] "Means for displaying answers on the user's terminal" refers to means for displaying the generated answers on the screen of the user's terminal.

[0783] "An emotion engine means for analyzing user emotions within an autonomous vehicle and generating appropriate emotion-based responses" refers to an engine with emotion analysis capabilities that analyzes user emotions from voice and text data and generates responses corresponding to those emotions.

[0784] "Means for converting generated responses into audio data and providing them to the user" refers to means for converting text-based responses into audio data and allowing the user to listen to them through speakers or headphones.

[0785] A mode for carrying out this invention relates to an interaction system used in an autonomous vehicle. This system allows passengers to receive user-friendly and emotionally sensitive responses when obtaining information or getting answers to questions while the vehicle is in motion.

[0786] System Overview

[0787] This system consists of the following main hardware and software components:

[0788] Hardware:

[0789] Communication devices (tablets, smartphones, etc.) inside autonomous vehicles

[0790] Microphone (for voice input)

[0791] Speaker (for voice response)

[0792] software:

[0793] Natural language processing engine (e.g., Google NLP)

[0794] Speech-to-text software (e.g., Google Speech-to-Text)

[0795] Automated speech software (e.g., Google Text-to-Speech)

[0796] Emotion engine (e.g., Affectiva SDK)

[0797] Generative AI (e.g. OpenAI GPT-4)

[0798] Processing flow

[0799] 1. User voice input

[0800] The user voice-inputs their questions into the microphone inside the autonomous vehicle. This voice data is converted into text data by speech-to-text software and sent to the server.

[0801] 2. Question analysis by the server

[0802] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP) to understand the intent behind the user's question.

[0803] 3. Database Search

[0804] Based on the analysis results, the server retrieves relevant data from the database. This database includes FAQs, traffic information, destination information, and more.

[0805] 4. Sentiment analysis and response generation

[0806] The server analyzes the user's text and voice data using an emotion engine (e.g., Affectiva SDK) to identify the user's emotions (e.g., distressed, relieved). Then, it uses a generative AI (e.g., OpenAI GPT-4) to generate appropriate responses that take the user's emotions into consideration.

[0807] 5. Text-to-speech conversion and response provision.

[0808] The generated responses are converted into audio data by automated speech-to-speech software (such as Google Text-to-Speech) and played back to the user through the speaker.

[0809] Specific example

[0810] For example, if a user asks "Where is the nearest parking lot?" into the in-car microphone, the audio is converted to text. The server uses a natural language processing engine to recognize the keyword "parking lot" and retrieves information about the nearest parking lot from the database. Once the emotion engine identifies the user's distress from the text data, the generative AI generates a response such as "The nearest parking lot is at the north exit of the station. Drive with peace of mind." This response is converted to audio data and played back through the speaker.

[0811] Example of a prompt

[0812] By inputting prompts like the following into a generative AI model, it will generate an appropriate response.

[0813] Please answer the following questions. If the user is having trouble, please add a kind explanation.

[0814] Question: Where is the nearest parking lot? User's sentiment: Troubled. Answer: The nearest parking lot is at the north exit of the station. Further explanation:

[0815] This configuration allows users to easily access information even within autonomous vehicles and provides responses that are sensitive to the user's emotions.

[0816] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0817] Step 1:

[0818] The user inputs their question by voice into the microphone. The input data is "voice data".

[0819] Step 2:

[0820] The device uses speech-to-text software (such as Google Speech-to-Text) to convert audio data into text data. At this stage, the input is "audio data" and the output is "text data". Specifically, speech recognition software analyzes the audio data and converts it into the corresponding text.

[0821] Step 3:

[0822] The terminal sends the converted text data to the server. The input is "text data," and the output is "sending data to the server." Specifically, the terminal transfers data to the server via the network.

[0823] Step 4:

[0824] The server passes the received text data to a natural language processing engine (such as Google NLP) and begins analysis. The input is "text data," and the output is the "analysis result." Specifically, the natural language processing engine extracts keywords and phrases from the text and understands the intent of the user's question.

[0825] Step 5:

[0826] The server searches the database for relevant information based on the analysis results. The input is the "analysis results," and the output is the "related data." Specifically, a database query is executed, and the relevant data is retrieved.

[0827] Step 6:

[0828] The server passes the user's text data to an emotion engine (such as the Affectiva SDK) to analyze the user's emotions. The input is "text data," and the output is "emotion analysis results." Specifically, the emotion engine analyzes the characteristics of the text and voice to identify the user's emotional state.

[0829] Step 7:

[0830] The server generates an appropriate response using a generative AI model (such as OpenAI GPT-4) based on the analysis results and sentiment analysis results. The input is the "analysis results" and "sentiment analysis results," and the output is the "generated response." Specifically, the generative AI model generates a natural response based on the input prompt sentence.

[0831] Step 8:

[0832] The server passes the generated response to speech-to-text software (such as Google Text-to-Speech) to convert it into audio data. The input is the "generated response," and the output is the "audio data." Specifically, the speech synthesis software analyzes the text data and converts it into speech.

[0833] Step 9:

[0834] The server sends audio data to the terminal. The input is "audio data," and the output is "data transmission to the terminal." Specifically, the server transfers the audio data to the terminal via the network.

[0835] Step 10:

[0836] The device plays the received audio data through its speaker. The input is "audio data," and the output is "audio playback." Specifically, the device decodes the audio file and plays the audio through its speaker.

[0837] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0838] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0839] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0840] [Third Embodiment]

[0841] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0842] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0843] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0844] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0845] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0846] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0847] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0848] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0849] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0850] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0851] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0852] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0853] A detailed description of embodiments for carrying out the present invention is provided below. This embodiment provides a system that efficiently handles resident services for local governments and enables smooth information provision, especially for the elderly and users with low IT literacy.

[0854] System Overview

[0855] This system consists of the following main components:

[0856] A terminal for user input.

[0857] Server for receiving and processing input data

[0858] Natural Language Processing Engine

[0859] database

[0860] Generative AI

[0861] Speech-to-text software

[0862] Automated voice software

[0863] Program Processing Description

[0864] 1. User input

[0865] Users access the system using a device (e.g., a personal computer or smartphone) and input questions or information. Users may input questions in text format, or, in some cases, elderly individuals may dictate their questions verbally.

[0866] Specific example:

[0867] The user enters, "When is the deadline for paying next year's resident tax?"

[0868] 2. Data transmission by the terminal

[0869] The terminal converts data entered by the user into text data and sends it to the server. If voice input is used, speech-to-text conversion software is used to convert the voice data into text data. The converted text data is then sent to the server by the terminal.

[0870] 3. Question analysis by the server

[0871] The server passes the received text data to a natural language processing engine for analysis. The natural language processing engine extracts keywords and important phrases from the text data to understand the intent of the question.

[0872] Specific example:

[0873] We analyze important keywords such as "resident tax," "payment deadline," and "next fiscal year."

[0874] 4. Database search by server

[0875] Based on the analysis results, the server searches the database for relevant information. The database contains information such as laws, regulations, and past response examples.

[0876] Specific example:

[0877] Search database entries related to "resident tax," "payment deadline," and "next fiscal year."

[0878] 5. Server-driven response generation

[0879] The server uses generative AI to generate appropriate answers based on the acquired data. The generative AI generates natural-sounding sentences and provides clear answers to the user's questions.

[0880] Specific example:

[0881] Generate the response: "The deadline for paying next year's resident tax is June 1, 2023."

[0882] 6. Sending responses from the server to the terminal.

[0883] The generated response is sent from the server to the terminal and provided to the user. If the response is in text format, it is sent as is. If an audio response is required, automated speech software is used to convert the text into audio data, which is then sent to the terminal.

[0884] 7. Display of answers via device

[0885] The device displays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[0886] Specific example:

[0887] The message "The deadline for paying next year's resident tax is June 1, 2023" is displayed or played.

[0888] This system efficiently handles inquiries about basic administrative services and provides a user-friendly interface that is considerate of the elderly. This configuration allows for the effective use of limited resources within local governments and improves resident satisfaction.

[0889] The following describes the processing flow.

[0890] Step 1:

[0891] The user accesses the system using a terminal and enters a question. For example, the user might enter "When is the deadline for paying next year's resident tax?" in text format.

[0892] Step 2:

[0893] The terminal sends the entered text data to the server. Since the terminal sends the user's text input directly to the server, no special data conversion is performed in this step.

[0894] Step 3:

[0895] The server receives the text data and passes it to the natural language processing engine to begin analysis. The natural language processing engine extracts keywords and important phrases from the text data and understands the intent of the question.

[0896] Step 4:

[0897] The server searches the database for relevant information based on the analysis results. The database stores laws, regulations, and past case examples. For example, it searches for entries related to "resident tax," "payment deadline," and "next fiscal year."

[0898] Step 5:

[0899] Based on information retrieved from the database by the server, a generative AI is used to generate appropriate answers. The generative AI constructs natural-sounding sentences and provides clear answers to the user's questions.

[0900] Step 6:

[0901] The server sends the generated response to the terminal in text format. For example, the text data "The deadline for paying next year's resident tax is June 1, 2023" is sent.

[0902] Step 7:

[0903] The device displays the received response on the screen. The user can view the response in text format.

[0904] Step 8:

[0905] Only when voice input is detected, the terminal passes the user's voice data to speech-to-text software, which converts it into text data. This converted text data is then sent to the server.

[0906] Step 9:

[0907] If voice output is required, the server converts the generated text response into an automated speech-to-speech program to produce audio data. The generated audio data is then sent to the terminal.

[0908] Step 10:

[0909] The device plays back the received audio data and provides the user with an audio response. This makes it possible to support users with low IT literacy, such as the elderly.

[0910] (Example 1)

[0911] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0912] The present invention aims to provide a system that enables smooth information provision in local government resident services, particularly for the elderly and users with low IT literacy. Current systems have the problem of requiring users to spend a considerable amount of time and effort to obtain information. Furthermore, in environments where voice input and output cannot be properly utilized, the system is particularly difficult for the elderly to use. There is a need to provide a system that solves these problems.

[0913] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0914] In this invention, the server includes means for receiving input from a user, means for a terminal to convert the user's input into data and transmit it to the server, means for the server to analyze the user's input using a natural language processing engine, means for obtaining relevant information from a storage device based on the analysis results, means for generating an appropriate response based on the acquired information using a generation AI, means for transmitting the generated response to the user terminal, and means for displaying the response on the user terminal. This enables the rapid and accurate provision of information regarding the user's input. Furthermore, by incorporating voice input and voice output functions, the system can be made particularly easy to use for the elderly, thereby improving the efficiency of services for residents.

[0915] A "user" is an entity that uses a system to input information and receive responses.

[0916] A "terminal" is a device used by a user to access and input data into a system, and includes personal computers and smartphones.

[0917] A "server" is a computing device that receives input data from users and performs processing such as analysis, data acquisition, and response generation.

[0918] A "natural language processing engine" is software or an algorithm that analyzes text data, extracts keywords and important phrases, and understands the intent of a question.

[0919] A "storage device" is a device that stores data for a server to retrieve relevant information based on analysis results, and includes databases and the like.

[0920] "Generative AI means" refers to a device or program that uses artificial intelligence technology to generate appropriate answers based on acquired data.

[0921] "Voice-to-text conversion software" is software that converts a user's voice input into text data.

[0922] "Automated voice software" is software that converts generated text responses into audio data and enables audio output.

[0923] "Means for receiving input" refers to an interface that allows users to input information such as questions into a terminal.

[0924] "Means of converting and transmitting data" refers to a function that allows a terminal to convert user input into text data or an appropriate format and send it to a server.

[0925] "Means of analysis" refers to the process by which a server uses a natural language processing engine to analyze user input data and understand the intent behind the question.

[0926] "Means of acquisition" refers to the function that allows the server to search for and retrieve relevant information from storage devices based on the analysis results.

[0927] "Means of transmission" refers to the communication function that allows the server to send the generated response back to the user's terminal.

[0928] "Means of display" refers to display devices and audio output functions that allow the user terminal to present the response sent from the server to the user.

[0929] This invention is a system designed to efficiently handle resident services for local governments, and is particularly capable of providing smooth information to elderly people and users with low IT literacy. The system mainly consists of a terminal for user input, a server for receiving and processing input data, a natural language processing engine, a database, a generative AI, and speech-to-text conversion software or automated speech software.

[0930] Users access the system using devices such as personal computers and smartphones and input questions and information. For example, a user might input, "When is the deadline for paying next year's resident tax?" It is also conceivable that an elderly person might ask a question by voice, such as, "Please tell me about the resident tax payment deadline."

[0931] The terminal converts data entered by the user into text data and sends it to the server. If voice input is used, the terminal uses speech-to-text software to convert the voice data into text. The converted text data is then sent to the server by the terminal.

[0932] The server passes the received text data to a natural language processing engine (e.g., natural language processing engine software) for analysis. The natural language processing engine extracts primitive keywords and important phrases from the text data to understand the intent of the user's question. For example, it analyzes keywords such as "resident tax," "payment deadline," and "next fiscal year."

[0933] Based on the analysis results, the server searches for relevant information from a database (e.g., a database management system). The database stores information such as laws, regulations, and past case examples, and the server retrieves the most relevant information based on this. For example, it searches for database entries related to "resident tax," "payment deadline," and "next fiscal year."

[0934] The server uses generative AI (e.g., a generative AI model) to generate appropriate answers based on the acquired data. This generative AI generates natural-sounding sentences and provides clear answers to user questions. For example, in response to the prompt "When is the deadline for paying next year's resident tax?", it generates the answer "The deadline for paying next year's resident tax is June 1, 2023."

[0935] The generated responses are sent from the server to the terminal and provided to the user. If the response is in text format, it is sent as is. If an audio response is required, the text is converted into audio data using automated speech software (e.g., automated speech generation software), and the audio data is sent to the terminal.

[0936] The device displays the response received from the server to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker. For example, the message "The deadline for paying next year's resident tax is June 1, 2023." might be displayed on the screen, or the same content might be played as audio.

[0937] In this way, the system of the present invention can respond to a variety of user inputs and provide appropriate information efficiently and quickly.

[0938] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0939] Step 1:

[0940] User input

[0941] Users access the system using a device (such as a computer or smartphone) and input questions or information. Specifically, a user might type "When is the deadline for paying next year's resident tax?" as text, or say "Please tell me about the resident tax payment deadline" as voice. In this step, if the user's input is in text format, it is entered directly into the device; if it is in voice format, the voice is recorded.

[0942] Step 2:

[0943] Data transmission by terminal

[0944] The terminal processes the data entered by the user. Text data is treated directly as a text file, while voice data is converted to text data using speech-to-text software. For example, voice input is converted to the text "Please tell me about the deadline for paying resident tax." The converted text data is then sent to the server by the terminal. The process of converting voice input to text data and sending it is completed here.

[0945] Step 3:

[0946] Server-based question analysis

[0947] The server receives user input data and passes it to a natural language processing engine (e.g., natural language processing engine software). The natural language processing engine extracts important keywords and phrases from the text data. Specifically, it identifies important elements such as "resident tax," "payment deadline," and "next fiscal year" to understand the intent of the question. Through this analysis, the server generates a dataset containing semantically important information.

[0948] Step 4:

[0949] Server-based database search

[0950] Based on the analysis results, the server searches for relevant information from its storage device (database management system). The database contains laws, regulations, and past case examples. For example, the server searches the database entries related to "resident tax," "payment deadline," and "next fiscal year," and retrieves that information. In this step, the server collects the relevant data and prepares it for use in the next step.

[0951] Step 5:

[0952] Server-based response generation

[0953] Based on the data acquired by the server, a generative AI (e.g., a generative AI model) is used to generate an appropriate answer. A prompt is input to the generative AI model, and a response in a natural sentence format is generated. For example, in response to the prompt "When is the deadline for paying next year's resident tax?", the model generates the answer "The deadline for paying next year's resident tax is June 1, 2023." In this step, the generative AI model generates accurate and easy-to-understand sentences.

[0954] Step 6:

[0955] Sending responses from the server to the terminal.

[0956] The generated responses are sent from the server to the terminal. Text-based responses are sent as is, while if an audio response is required, automated speech software is used to convert the text to speech, and that audio data is sent to the terminal. For example, the text response "The deadline for paying next year's resident tax is June 1, 2023." is sent to the terminal.

[0957] Step 7:

[0958] Display of answers via device

[0959] The device displays the response received from the server to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker. Specifically, a message such as "The deadline for paying next year's resident tax is June 1, 2023" might be displayed on the screen or played aloud. In this step, the user can obtain the answer to their question visually or audibly.

[0960] (Application Example 1)

[0961] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0962] In modern society, the number of elderly users and users with low IT literacy is increasing, making it difficult to provide information smoothly to these users. Furthermore, while there is a need to provide product information and service guidance quickly and effectively in physical stores, current technology is insufficient to meet this demand. In particular, there is a need for intuitive interfaces that can be used by elderly users and users with low IT literacy.

[0963] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0964] In this invention, the server includes means for receiving input from a user, means for transmitting the user's input to the server, means for analyzing the user's input within the server using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating an appropriate response based on the acquired data, means for transmitting the generated response to a user terminal, means for displaying the response on the user terminal, means for recognizing the user's gaze direction using a gaze detection sensor and transmitting it to the server, means for providing product information and service guidance within the physical store based on the gaze direction, and means for receiving questions regarding product information and service guidance within the physical store via voice input. This makes it possible to provide information intuitively and effectively to elderly people and users with low IT literacy in physical stores.

[0965] "Means of receiving user input" refers to an interface that allows users to input information into a system. This includes smart glasses, smartphones, and computers.

[0966] "Means of sending user input to a server" refers to the function of sending information entered by the user to a server via a network. This utilizes internet connectivity or wireless communication technology.

[0967] "Methods for analyzing user input within a server using a natural language processing engine" refers to technologies that analyze text and audio data received by the server to understand the user's intent. The natural language processing engine plays this role.

[0968] "Means of obtaining relevant data from a database based on analysis results" refers to a function that searches for and retrieves necessary information from a database based on the results of analysis performed by a natural language processing engine.

[0969] "Generative AI methods for generating appropriate answers" refers to AI technology that generates appropriate answers to user questions based on acquired data. Generative AI plays this role.

[0970] "Means of sending generated responses to the user's terminal" refers to the function of transferring responses created by a generative AI to the user's device. This is done via the internet or wireless communication.

[0971] "Means of displaying answers on the user's device" refers to an interface that displays the generated answers on the user's device. This role is fulfilled by the display of smart glasses or the screen of a smartphone.

[0972] "A means of recognizing the direction of the user's gaze using a gaze detection sensor and transmitting it to a server" refers to a technology that detects the direction the user is looking and transmits that information to a server. The gaze detection sensor plays this role.

[0973] "Means of providing product information and service guidance within a physical store based on the direction of gaze" refers to a function that provides detailed information about products and services based on the direction the user is looking.

[0974] "A means of receiving questions about product information and service guidance within a physical store via voice input" refers to a function that captures user voice questions, converts them into text data, and analyzes them. Voice-to-text conversion software fulfills this role.

[0975] A specific embodiment for carrying out the present invention is shown below. This embodiment makes it possible to provide information intuitively and effectively to elderly people and users with low IT literacy in physical stores.

[0976] System Configuration

[0977] This system consists of the following main components:

[0978] 1. A device that accepts user input (such as smart glasses or a smartphone)

[0979] 2. Server

[0980] 3. Natural Language Processing Engine

[0981] 4. Database

[0982] 5. Generative AI

[0983] 6. Eye-tracking sensor

[0984] 7. Speech-to-text conversion software

[0985] 8. Automated voice software

[0986] Hardware and software usage

[0987] The primary device used is a pair of smart glasses. These smart glasses are equipped with an eye-tracking sensor to recognize the user's gaze direction. They also have a microphone for voice input.

[0988] On the server side, a natural language processing engine (e.g., spaCy), speech-to-text software (e.g., Mozilla DeepSpeech), generative AI (e.g., OpenAI GPT-3), and a database system (e.g., PostgreSQL) are used. These software components work together to analyze user input data and generate appropriate responses.

[0989] Methods for data processing and data calculation

[0990] Processing of eye-tracking data

[0991] When a user looks at products or services in a store through their smart glasses, an eye-tracking sensor recognizes the direction of their gaze and sends that data to a server. The server analyzes the eye-tracking data to identify information about products the user is interested in.

[0992] Analysis of voice input

[0993] When a user enters a question by voice, the microphone in the smart glasses collects the voice and sends the voice data to a server. The voice data is then converted into text data using speech-to-text software.

[0994] Natural language processing and database search

[0995] The server passes the converted text data to a natural language processing engine to analyze the user's question. Based on the analysis results, it searches the database for relevant product information and service details.

[0996] Answer generation

[0997] Based on the acquired information, a generative AI generates appropriate answers to the user's questions. The answers are generated in natural-sounding sentences.

[0998] Information provision

[0999] The generated response is sent back to the smart glasses via the server and displayed in the user's field of view. If output in audio format is requested, the text is converted into audio data using automated speech software and played back through the smart glasses' speaker.

[1000] Examples of prompt statements

[1001] The following are specific examples of questions users might ask smart glasses in a physical store:

[1002] "What are the features of this product?"

[1003] "How much does this item cost?"

[1004] "Where can I find this product?"

[1005] As described above, the system based on the present invention enables intuitive and effective information provision in physical stores, particularly for elderly people and users with low IT literacy.

[1006] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1007] Step 1:

[1008] The user wears smart glasses and walks around a physical store. When the user looks at a product or service that interests them, the eye-tracking sensor recognizes the direction of their gaze. The input is gaze direction data, and the output is data related to gaze direction. The server receives this gaze direction data and proceeds to the next step.

[1009] Step 2:

[1010] The user provides voice input. For example, they might ask, "What are the features of this product?" The smart glasses' microphone collects the voice data and sends it to the server. The input is voice data, and the output is the raw voice data sent to the server.

[1011] Step 3:

[1012] The server converts the received audio data into text data using speech-to-text software (e.g., Mozilla DeepSpeech). The input is audio data, and the output is the converted text data. This allows the user's questions to be analyzed in text format.

[1013] Step 4:

[1014] The server passes text data to a natural language processing engine (e.g., spaCy) to analyze the user's question. The input is text data, and the output is keywords and important phrases included in the analysis results. Based on the analysis results, the server understands the user's intent.

[1015] Step 5:

[1016] The server searches a database (e.g., PostgreSQL) for information on products of interest based on the analysis results and eye-tracking data. The input is the analysis results and eye-tracking data, and the output is detailed information on related products. This allows the server to retrieve appropriate information.

[1017] Step 6:

[1018] The server uses generative AI (e.g., OpenAI GPT-3) to generate appropriate answers to user questions based on the acquired information. The input is detailed product information, and the output is the generated text-based answer. The generative AI generates natural-sounding sentences, creating answers that are easy for the user to understand.

[1019] Step 7:

[1020] The server sends the generated text-formatted response to the smart glasses. The input is the generated text-formatted response, and the output is the text data sent to the smart glasses. This allows the user to receive the response.

[1021] Step 8:

[1022] The user's smart glasses display the received text data on a screen, and, if necessary, convert it into audio data using automated voice software and play it through the speaker. The input is text data, and the output is the response displayed in the user's field of vision and the audio data. This allows the user to see the response visually and hear it aloud.

[1023] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1024] A detailed description of embodiments for carrying out the present invention is provided below. This embodiment provides a system that efficiently handles resident services for local governments and enables smooth information provision, especially for the elderly and users with low IT literacy. Furthermore, by combining it with an emotion engine, responses based on the user's emotions can also be realized.

[1025] System Overview

[1026] This system consists of the following main components:

[1027] A terminal for user input.

[1028] Server for receiving and processing input data

[1029] Natural Language Processing Engine

[1030] database

[1031] Generative AI

[1032] Speech-to-text software

[1033] Automated voice software

[1034] Emotional Engine

[1035] Program Processing Description

[1036] 1. User input

[1037] Users access the system using a device (e.g., a personal computer or smartphone) and input questions or information. Users may input questions in text format, or, in some cases, elderly individuals may dictate their questions verbally.

[1038] Specific example:

[1039] The user enters, "Please tell me the opening hours of the nearby library."

[1040] 2. Data transmission by the terminal

[1041] The terminal sends the entered text data to the server. If voice input is used, the voice data is converted to text data using speech-to-text software. The converted text data is then sent to the server by the terminal.

[1042] 3. Question analysis by the server

[1043] The server passes the received text data to a natural language processing engine to begin analysis. The natural language processing engine extracts keywords and important phrases from the text data and understands the intent of the question.

[1044] Specific example:

[1045] We analyze important keywords such as "library" and "opening hours."

[1046] 4. Database search by server

[1047] Based on the analysis results, the server searches the database for relevant information. The database stores laws, regulations, and past case examples.

[1048] Specific example:

[1049] Search database entries related to "library" and "opening hours".

[1050] 5. User emotion analysis using an emotion engine

[1051] The server passes user input data and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions (e.g., joy, anger, sadness, surprise) from the user's text and voice data.

[1052] Specific example:

[1053] The emotion engine detects when the user's voice sounds tense and identifies it as "tension."

[1054] 6. Server-driven response generation

[1055] Based on the analysis results and the output of the emotion engine, the server uses generative AI to generate appropriate responses. The generative AI constructs natural-sounding sentences and provides clear and emotionally sensitive answers to the user's questions.

[1056] Specific example:

[1057] The system generates the response: "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1058] 7. Sending responses from the server to the terminal.

[1059] The generated response is sent from the server to the terminal. If the response is in text format, it is sent as is. If an audio response is required, automated speech software is used to convert the text into audio data, which is then sent to the terminal.

[1060] 8. Display of answers via device

[1061] The device displays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[1062] Specific example:

[1063] A message is displayed or played saying, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1064] This configuration allows the system to efficiently handle inquiries about basic administrative services, provide a user-friendly interface that is considerate of the elderly, and deliver kind responses that are sensitive to the user's feelings. This enables the effective use of limited resources within local governments and improves resident satisfaction.

[1065] The following describes the processing flow.

[1066] Step 1:

[1067] Users access the system using a terminal and enter their questions. For example, a user might type "What are the opening hours of the nearby library?" in text format. Users can also dictate their questions aloud.

[1068] Step 2:

[1069] The terminal sends the entered text or voice data to the server. If voice input is used, the terminal uses speech-to-text software to convert the voice data into text data and then sends it.

[1070] Step 3:

[1071] The server receives the text data and passes it to a natural language processing engine, which then begins analyzing the question. The natural language processing engine extracts keywords and important phrases from the text data to understand the intent of the question.

[1072] Specific example:

[1073] Extract important keywords such as "library" and "opening hours."

[1074] Step 4:

[1075] The server searches the database for relevant information based on the analysis results. The server sends queries to the database, which stores laws, regulations, and past case examples, and retrieves the relevant information.

[1076] Specific example:

[1077] Search database entries related to "library" and "opening hours" to retrieve information on "opening hours of nearby libraries".

[1078] Step 5:

[1079] The server passes user input data and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies the user's emotions (e.g., joy, anger, sadness, surprise) from the text and voice data.

[1080] Specific example:

[1081] The emotion engine detects when the user's voice sounds tense and identifies it as "tension."

[1082] Step 6:

[1083] The server uses generative AI to generate appropriate answers based on the analysis results and the output of the emotion engine. The generative AI constructs natural-sounding sentences and provides clear and emotionally sensitive answers to the user's questions.

[1084] Specific example:

[1085] The system generates the response: "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1086] Step 7:

[1087] The server sends the generated response to the terminal in text format. If necessary, the server uses automated speech software to convert the generated text into audio data and sends it to the terminal.

[1088] Specific example:

[1089] Send a message in text or voice format saying, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1090] Step 8:

[1091] The device displays or plays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[1092] Specific example:

[1093] A message appears on the screen or is played as audio stating, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1094] This step enables the system to efficiently handle inquiries about basic administrative services, providing a user-friendly interface that is considerate of the elderly and users with low IT literacy, as well as providing kind and empathetic responses. This allows for the effective use of limited resources within local governments and improves resident satisfaction.

[1095] (Example 2)

[1096] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1097] Current municipal resident service systems are difficult for the elderly and users with low IT literacy to use, and responding to inquiries is time-consuming and labor-intensive. Furthermore, they fail to provide responses that are sensitive to users' feelings, making it difficult to improve resident satisfaction.

[1098] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1099] In this invention, the server includes means for analyzing user input using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating appropriate responses based on the obtained data, and sentiment analysis means for analyzing the user's emotions. This provides an interface that is easy to use even for the elderly and users with low IT literacy, and enables quick and appropriate responses that take the user's emotions into consideration.

[1100] A "user" refers to a person who accesses the system and enters questions or information.

[1101] A "user terminal" refers to a device used by a user to access a system, such as a personal computer or smartphone.

[1102] A "server" refers to a device that receives input data from user terminals and performs analysis and processing on it.

[1103] A "natural language processing engine" refers to software that analyzes text data, extracts keywords and important phrases, and understands the intent of a question.

[1104] A "database" refers to an information storage system that stores and manages related information, including laws, regulations, and past response examples.

[1105] "Generative AI methods" refer to artificial intelligence technologies that generate appropriate answers based on acquired data.

[1106] "Emotion analysis methods" refer to technologies that identify and analyze emotions from user input data and voice data.

[1107] "Speech-to-text conversion software" refers to software that converts audio data into text data.

[1108] "Automatic voice software" refers to software that converts text data into speech data.

[1109] This invention is a system for improving resident services in local governments, and provides an interface that is particularly easy to use for the elderly and users with low IT literacy. It also utilizes an emotion engine to provide responses that take the user's emotions into consideration. A detailed description of the system follows.

[1110] System Overview

[1111] This system consists of the following main components:

[1112] A device for the user to input data (e.g., a personal computer, a smartphone)

[1113] Server for receiving and processing input data

[1114] Natural language processing engine (e.g., natural language processing API)

[1115] Database (e.g., relational database management system)

[1116] Generative AI (e.g., generative model AI)

[1117] Speech-to-text conversion software (e.g., speech recognition software)

[1118] Automatic voice software (e.g., speech synthesis software)

[1119] Emotion engine (e.g., emotion analysis software)

[1120] Program Processing Description

[1121] 1. User input

[1122] Users access the system using their devices and input questions or information. Input can be in text or voice format. For example, if a user asks a question by voice, such as "What are the opening hours of the nearby library?", they would use their smartphone's microphone.

[1123] 2. Data transmission by the terminal

[1124] The terminal sends the input data to the server. In the case of voice input, speech-to-text software (e.g., speech recognition software) is used to convert the voice data into text data. The text data is then sent to the server.

[1125] Specific example: A smartphone converts voice input into text using speech recognition software and sends it to a server, saying, "Please tell me the opening hours of the nearby library."

[1126] 3. Question analysis by the server

[1127] The server passes the received text data to a natural language processing engine (e.g., a natural language processing API) to analyze the intent of the question. For example, by extracting keywords such as "library" and "opening hours," it understands the content of the user's question.

[1128] 4. Database search by server

[1129] Based on the analysis results, the server searches for and retrieves relevant information from a database (e.g., a relational database management system). For example, it retrieves data related to "library" and "opening hours."

[1130] 5. User emotion analysis using an emotion engine

[1131] The server passes user input data and voice data to an emotion engine (e.g., emotion analysis software) to analyze the user's emotions. The emotion engine can identify emotions such as joy, anger, sadness, and surprise.

[1132] Specific example: The server identifies that the user is "stressed" from their input.

[1133] 6. Server-driven response generation

[1134] Based on the analysis results and the output of the emotion engine, the server uses generative AI (e.g., generative model AI) to generate an appropriate response. For example, it might generate a response like, "The nearby library is open from 8am to 8pm on weekdays. Please feel free to go out."

[1135] Example of a prompt:

[1136] "Please tell me the opening hours of the nearby library. The user is feeling anxious. Please generate a kind and reassuring answer."

[1137] 7. Sending responses from the server to the terminal.

[1138] The generated response is sent from the server to the terminal. If necessary, automated speech software (e.g., text-to-speech software) is used to convert the text into speech data.

[1139] 8. Display of answers via device

[1140] The device displays the received response to the user. If it's in text format, it's displayed on the screen; if it's in audio format, it's played through the speaker. For example, a smartphone might display or play the message, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1141] This system efficiently handles inquiries about resident services from local governments and provides a user-friendly interface that is considerate of the elderly. Furthermore, it enables responses that respond to user emotions, thereby improving resident satisfaction.

[1142] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1143] Step 1: User input

[1144] Users access the system using their smartphones or computers and input questions and information. For example, they might ask a question by voice, such as, "Please tell me the opening hours of the nearby library." The input data is in voice format and is saved on the device as initial input information.

[1145] Step 2: Data transmission by the terminal

[1146] The terminal sends the voice data entered by the user to the server. The voice data is converted into text data using speech-to-text software (e.g., speech recognition software). The converted text data, "Please tell me the opening hours of the nearby library," is sent to the server.

[1147] Input: Audio data

[1148] Output: Text data

[1149] Specific operation: The smartphone captures the audio and converts it to text using speech recognition software.

[1150] Step 3: Server-based question analysis

[1151] The server passes the received text data to a natural language processing engine (e.g., a natural language processing API) for analysis. The natural language processing engine extracts keywords such as "library" and "opening hours" from the text data and understands the intent of the question.

[1152] Input: Text data

[1153] Output: Analyzed data (keywords and intent)

[1154] Specific operation: The server inputs text data into a natural language processing API, which then analyzes and extracts keywords and intent.

[1155] Step 4: Server-based database search

[1156] The server searches a database (e.g., a relational database management system) based on the analyzed keywords and intent, and retrieves relevant information. For example, the server searches database entries related to "library" and "opening hours" to retrieve the opening hours of the nearest library.

[1157] Input: Analyzed data (keywords and intent)

[1158] Output: Acquired information

[1159] Specific operation: The server generates a database query and searches for and retrieves the relevant data.

[1160] Step 5: User emotion analysis using an emotion engine

[1161] The server passes the user's input data (including voice data) to an emotion engine (e.g., emotion analysis software) to analyze the user's emotions. The emotion engine identifies emotions such as "tension" from the input data.

[1162] Input: Audio data or text data

[1163] Output: Analyzed sentiment data

[1164] Specific operation: The server inputs voice or text data into sentiment analysis software to identify emotions.

[1165] Step 6: Server generates response

[1166] The server uses generative AI (e.g., generative model AI) to generate an appropriate response based on the analysis of the question and the output of the sentiment engine. For example, it might generate a response like, "The nearby library is open from 8am to 8pm on weekdays. Please feel free to go out."

[1167] Input: Analyzed data (keywords, intent, sentiment)

[1168] Output: Generated response (text data)

[1169] Specific operation: The server inputs prompts and analysis data into the generative AI and generates an appropriate response.

[1170] Step 7: Sending the response from the server to the terminal

[1171] The generated responses are sent from the server to the terminal in text format or, if necessary, in audio format. For audio format, automated speech software (e.g., text-to-speech software) is used.

[1172] Input: Text format answer

[1173] Output: Answer in text or audio format

[1174] Specific operation: The server passes text data to the automated speech software, which converts it into speech data and sends it.

[1175] Step 8: Displaying the answer via the device

[1176] The device displays the received response to the user. If it's in text format, it's displayed on the screen; if it's in audio format, it's played through the speaker.

[1177] Input: Text or audio response

[1178] Output: Displayed on screen or played as audio.

[1179] Specific action: The smartphone displays a message on the screen or plays audio from the speaker.

[1180] (Application Example 2)

[1181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1182] User interfaces in autonomous vehicles present challenges, particularly for the elderly and those with low IT literacy. Furthermore, conventional systems are insufficient in responding to user emotions, highlighting the need to improve passenger satisfaction and safety. Additionally, accurately analyzing user voice input and providing appropriate responses to inquiries presents technical challenges.

[1183] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for transmitting the user's input to the server, means for analyzing the user's input within the server using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating an appropriate response based on the acquired data, means for transmitting the generated response to a user terminal, means for displaying the response on the user terminal, emotion engine means for analyzing the user's emotions within the autonomous vehicle and generating an appropriate response based on those emotions, and means for converting the generated response into voice data and providing it to the user. This makes it possible for users to easily access information even within an autonomous vehicle and to provide responses that take the user's emotions into consideration.

[1184] "Means of receiving user input" refers to an interface that allows users to input questions or instructions to the system in voice or text format.

[1185] "Means of sending user input to the server" refers to communication methods for transferring data entered by the user to the server in real time.

[1186] "Means for analyzing user input within a server using a natural language processing engine" refers to a means of analyzing received user input data using a natural language processing engine to understand the user's intent.

[1187] "Means for obtaining relevant data from a database based on analysis results" refers to methods for searching and obtaining relevant information from a database based on the analysis results of a natural language processing engine.

[1188] "Generative AI methods that generate appropriate answers based on acquired data" refers to generative artificial intelligence that generates answers suitable for user questions based on information acquired from a database.

[1189] "Means for sending the generated response to the user's terminal" refers to means for sending the generated response to the user's terminal so that it can be displayed or played back.

[1190] "Means for displaying answers on the user's terminal" refers to means for displaying the generated answers on the screen of the user's terminal.

[1191] "An emotion engine means for analyzing user emotions within an autonomous vehicle and generating appropriate emotion-based responses" refers to an engine with emotion analysis capabilities that analyzes user emotions from voice and text data and generates responses corresponding to those emotions.

[1192] "Means for converting generated responses into audio data and providing them to the user" refers to means for converting text-based responses into audio data and allowing the user to listen to them through speakers or headphones.

[1193] A mode for carrying out this invention relates to an interaction system used in an autonomous vehicle. This system allows passengers to receive user-friendly and emotionally sensitive responses when obtaining information or getting answers to questions while the vehicle is in motion.

[1194] System Overview

[1195] This system consists of the following main hardware and software components:

[1196] Hardware:

[1197] Communication devices (tablets, smartphones, etc.) inside autonomous vehicles

[1198] Microphone (for voice input)

[1199] Speaker (for voice response)

[1200] software:

[1201] Natural language processing engine (e.g., Google NLP)

[1202] Speech-to-text software (e.g., Google Speech-to-Text)

[1203] Automated speech software (e.g., Google Text-to-Speech)

[1204] Emotion engine (e.g., Affectiva SDK)

[1205] Generative AI (e.g. OpenAI GPT-4)

[1206] Processing flow

[1207] 1. User voice input

[1208] The user voice-inputs their questions into the microphone inside the autonomous vehicle. This voice data is converted into text data by speech-to-text software and sent to the server.

[1209] 2. Question analysis by the server

[1210] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP) to understand the intent behind the user's question.

[1211] 3. Database Search

[1212] Based on the analysis results, the server retrieves relevant data from the database. This database includes FAQs, traffic information, destination information, and more.

[1213] 4. Sentiment analysis and response generation

[1214] The server analyzes the user's text and voice data using an emotion engine (e.g., Affectiva SDK) to identify the user's emotions (e.g., distressed, relieved). Then, it uses a generative AI (e.g., OpenAI GPT-4) to generate appropriate responses that take the user's emotions into consideration.

[1215] 5. Text-to-speech conversion and response provision.

[1216] The generated responses are converted into audio data by automated speech-to-speech software (such as Google Text-to-Speech) and played back to the user through the speaker.

[1217] Specific example

[1218] For example, if a user asks "Where is the nearest parking lot?" into the in-car microphone, the audio is converted to text. The server uses a natural language processing engine to recognize the keyword "parking lot" and retrieves information about the nearest parking lot from the database. Once the emotion engine identifies the user's distress from the text data, the generative AI generates a response such as "The nearest parking lot is at the north exit of the station. Drive with peace of mind." This response is converted to audio data and played back through the speaker.

[1219] Example of a prompt

[1220] By inputting prompts like the following into a generative AI model, it will generate an appropriate response.

[1221] Please answer the following questions. If the user is having trouble, please add a kind explanation.

[1222] Question: Where is the nearest parking lot? User's sentiment: Troubled. Answer: The nearest parking lot is at the north exit of the station. Further explanation:

[1223] This configuration allows users to easily access information even within autonomous vehicles and provides responses that are sensitive to the user's emotions.

[1224] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1225] Step 1:

[1226] The user inputs their question by voice into the microphone. The input data is "voice data".

[1227] Step 2:

[1228] The device uses speech-to-text software (such as Google Speech-to-Text) to convert audio data into text data. At this stage, the input is "audio data" and the output is "text data". Specifically, speech recognition software analyzes the audio data and converts it into the corresponding text.

[1229] Step 3:

[1230] The terminal sends the converted text data to the server. The input is "text data," and the output is "sending data to the server." Specifically, the terminal transfers data to the server via the network.

[1231] Step 4:

[1232] The server passes the received text data to a natural language processing engine (such as Google NLP) and begins analysis. The input is "text data," and the output is the "analysis result." Specifically, the natural language processing engine extracts keywords and phrases from the text and understands the intent of the user's question.

[1233] Step 5:

[1234] The server searches the database for relevant information based on the analysis results. The input is the "analysis results," and the output is the "related data." Specifically, a database query is executed, and the relevant data is retrieved.

[1235] Step 6:

[1236] The server passes the user's text data to an emotion engine (such as the Affectiva SDK) to analyze the user's emotions. The input is "text data," and the output is "emotion analysis results." Specifically, the emotion engine analyzes the characteristics of the text and voice to identify the user's emotional state.

[1237] Step 7:

[1238] The server generates an appropriate response using a generative AI model (such as OpenAI GPT-4) based on the analysis results and sentiment analysis results. The input is the "analysis results" and "sentiment analysis results," and the output is the "generated response." Specifically, the generative AI model generates a natural response based on the input prompt sentence.

[1239] Step 8:

[1240] The server passes the generated response to speech-to-text software (such as Google Text-to-Speech) to convert it into audio data. The input is the "generated response," and the output is the "audio data." Specifically, the speech synthesis software analyzes the text data and converts it into speech.

[1241] Step 9:

[1242] The server sends audio data to the terminal. The input is "audio data," and the output is "data transmission to the terminal." Specifically, the server transfers the audio data to the terminal via the network.

[1243] Step 10:

[1244] The device plays the received audio data through its speaker. The input is "audio data," and the output is "audio playback." Specifically, the device decodes the audio file and plays the audio through its speaker.

[1245] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1246] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1247] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1248] [Fourth Embodiment]

[1249] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1250] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1251] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1252] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1253] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1254] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1255] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1256] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1257] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1258] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1259] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1260] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1261] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1262] A detailed description of embodiments for carrying out the present invention is provided below. This embodiment provides a system that efficiently handles resident services for local governments and enables smooth information provision, especially for the elderly and users with low IT literacy.

[1263] System Overview

[1264] This system consists of the following main components:

[1265] A terminal for user input.

[1266] Server for receiving and processing input data

[1267] Natural Language Processing Engine

[1268] database

[1269] Generative AI

[1270] Speech-to-text software

[1271] Automated voice software

[1272] Program Processing Description

[1273] 1. User input

[1274] Users access the system using a device (e.g., a personal computer or smartphone) and input questions or information. Users may input questions in text format, or, in some cases, elderly individuals may dictate their questions verbally.

[1275] Specific example:

[1276] The user enters, "When is the deadline for paying next year's resident tax?"

[1277] 2. Data transmission by the terminal

[1278] The terminal converts data entered by the user into text data and sends it to the server. If voice input is used, speech-to-text conversion software is used to convert the voice data into text data. The converted text data is then sent to the server by the terminal.

[1279] 3. Question analysis by the server

[1280] The server passes the received text data to a natural language processing engine for analysis. The natural language processing engine extracts keywords and important phrases from the text data to understand the intent of the question.

[1281] Specific example:

[1282] We analyze important keywords such as "resident tax," "payment deadline," and "next fiscal year."

[1283] 4. Database search by server

[1284] Based on the analysis results, the server searches the database for relevant information. The database contains information such as laws, regulations, and past response examples.

[1285] Specific example:

[1286] Search database entries related to "resident tax," "payment deadline," and "next fiscal year."

[1287] 5. Server-driven response generation

[1288] The server uses generative AI to generate appropriate answers based on the acquired data. The generative AI generates natural-sounding sentences and provides clear answers to the user's questions.

[1289] Specific example:

[1290] Generate the response: "The deadline for paying next year's resident tax is June 1, 2023."

[1291] 6. Sending responses from the server to the terminal.

[1292] The generated response is sent from the server to the terminal and provided to the user. If the response is in text format, it is sent as is. If an audio response is required, automated speech software is used to convert the text into audio data, which is then sent to the terminal.

[1293] 7. Display of answers via device

[1294] The device displays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[1295] Specific example:

[1296] The message "The deadline for paying next year's resident tax is June 1, 2023" is displayed or played.

[1297] This system efficiently handles inquiries about basic administrative services and provides a user-friendly interface that is considerate of the elderly. This configuration allows for the effective use of limited resources within local governments and improves resident satisfaction.

[1298] The following describes the processing flow.

[1299] Step 1:

[1300] The user accesses the system using a terminal and enters a question. For example, the user might enter "When is the deadline for paying next year's resident tax?" in text format.

[1301] Step 2:

[1302] The terminal sends the entered text data to the server. Since the terminal sends the user's text input directly to the server, no special data conversion is performed in this step.

[1303] Step 3:

[1304] The server receives the text data and passes it to the natural language processing engine to begin analysis. The natural language processing engine extracts keywords and important phrases from the text data and understands the intent of the question.

[1305] Step 4:

[1306] The server searches the database for relevant information based on the analysis results. The database stores laws, regulations, and past case examples. For example, it searches for entries related to "resident tax," "payment deadline," and "next fiscal year."

[1307] Step 5:

[1308] Based on information retrieved from the database by the server, a generative AI is used to generate appropriate answers. The generative AI constructs natural-sounding sentences and provides clear answers to the user's questions.

[1309] Step 6:

[1310] The server sends the generated response to the terminal in text format. For example, the text data "The deadline for paying next year's resident tax is June 1, 2023" is sent.

[1311] Step 7:

[1312] The device displays the received response on the screen. The user can view the response in text format.

[1313] Step 8:

[1314] Only when voice input is detected, the terminal passes the user's voice data to speech-to-text software, which converts it into text data. This converted text data is then sent to the server.

[1315] Step 9:

[1316] If voice output is required, the server converts the generated text response into an automated speech-to-speech program to produce audio data. The generated audio data is then sent to the terminal.

[1317] Step 10:

[1318] The device plays back the received audio data and provides the user with an audio response. This makes it possible to support users with low IT literacy, such as the elderly.

[1319] (Example 1)

[1320] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1321] The present invention aims to provide a system that enables smooth information provision in local government resident services, particularly for the elderly and users with low IT literacy. Current systems have the problem of requiring users to spend a considerable amount of time and effort to obtain information. Furthermore, in environments where voice input and output cannot be properly utilized, the system is particularly difficult for the elderly to use. There is a need to provide a system that solves these problems.

[1322] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1323] In this invention, the server includes means for receiving input from a user, means for a terminal to convert the user's input into data and transmit it to the server, means for the server to analyze the user's input using a natural language processing engine, means for obtaining relevant information from a storage device based on the analysis results, means for generating an appropriate response based on the acquired information using a generation AI, means for transmitting the generated response to the user terminal, and means for displaying the response on the user terminal. This enables the rapid and accurate provision of information regarding the user's input. Furthermore, by incorporating voice input and voice output functions, the system can be made particularly easy to use for the elderly, thereby improving the efficiency of services for residents.

[1324] A "user" is an entity that uses a system to input information and receive responses.

[1325] A "terminal" is a device used by a user to access and input data into a system, and includes personal computers and smartphones.

[1326] A "server" is a computing device that receives input data from users and performs processing such as analysis, data acquisition, and response generation.

[1327] A "natural language processing engine" is software or an algorithm that analyzes text data, extracts keywords and important phrases, and understands the intent of a question.

[1328] A "storage device" is a device that stores data for a server to retrieve relevant information based on analysis results, and includes databases and the like.

[1329] "Generative AI means" refers to a device or program that uses artificial intelligence technology to generate appropriate answers based on acquired data.

[1330] "Voice-to-text conversion software" is software that converts a user's voice input into text data.

[1331] "Automated voice software" is software that converts generated text responses into audio data and enables audio output.

[1332] "Means for receiving input" refers to an interface that allows users to input information such as questions into a terminal.

[1333] "Means of converting and transmitting data" refers to a function that allows a terminal to convert user input into text data or an appropriate format and send it to a server.

[1334] "Means of analysis" refers to the process by which a server uses a natural language processing engine to analyze user input data and understand the intent behind the question.

[1335] "Means of acquisition" refers to the function that allows the server to search for and retrieve relevant information from storage devices based on the analysis results.

[1336] "Means of transmission" refers to the communication function that allows the server to send the generated response back to the user's terminal.

[1337] "Means of display" refers to display devices and audio output functions that allow the user terminal to present the response sent from the server to the user.

[1338] This invention is a system designed to efficiently handle resident services for local governments, and is particularly capable of providing smooth information to elderly people and users with low IT literacy. The system mainly consists of a terminal for user input, a server for receiving and processing input data, a natural language processing engine, a database, a generative AI, and speech-to-text conversion software or automated speech software.

[1339] Users access the system using devices such as personal computers and smartphones and input questions and information. For example, a user might input, "When is the deadline for paying next year's resident tax?" It is also conceivable that an elderly person might ask a question by voice, such as, "Please tell me about the resident tax payment deadline."

[1340] The terminal converts data entered by the user into text data and sends it to the server. If voice input is used, the terminal uses speech-to-text software to convert the voice data into text. The converted text data is then sent to the server by the terminal.

[1341] The server passes the received text data to a natural language processing engine (e.g., natural language processing engine software) for analysis. The natural language processing engine extracts primitive keywords and important phrases from the text data to understand the intent of the user's question. For example, it analyzes keywords such as "resident tax," "payment deadline," and "next fiscal year."

[1342] Based on the analysis results, the server searches for relevant information from a database (e.g., a database management system). The database stores information such as laws, regulations, and past case examples, and the server retrieves the most relevant information based on this. For example, it searches for database entries related to "resident tax," "payment deadline," and "next fiscal year."

[1343] The server uses generative AI (e.g., a generative AI model) to generate appropriate answers based on the acquired data. This generative AI generates natural-sounding sentences and provides clear answers to user questions. For example, in response to the prompt "When is the deadline for paying next year's resident tax?", it generates the answer "The deadline for paying next year's resident tax is June 1, 2023."

[1344] The generated responses are sent from the server to the terminal and provided to the user. If the response is in text format, it is sent as is. If an audio response is required, the text is converted into audio data using automated speech software (e.g., automated speech generation software), and the audio data is sent to the terminal.

[1345] The device displays the response received from the server to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker. For example, the message "The deadline for paying next year's resident tax is June 1, 2023." might be displayed on the screen, or the same content might be played as audio.

[1346] In this way, the system of the present invention can respond to a variety of user inputs and provide appropriate information efficiently and quickly.

[1347] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1348] Step 1:

[1349] User input

[1350] Users access the system using a device (such as a computer or smartphone) and input questions or information. Specifically, a user might type "When is the deadline for paying next year's resident tax?" as text, or say "Please tell me about the resident tax payment deadline" as voice. In this step, if the user's input is in text format, it is entered directly into the device; if it is in voice format, the voice is recorded.

[1351] Step 2:

[1352] Data transmission by terminal

[1353] The terminal processes the data entered by the user. Text data is treated directly as a text file, while voice data is converted to text data using speech-to-text software. For example, voice input is converted to the text "Please tell me about the deadline for paying resident tax." The converted text data is then sent to the server by the terminal. The process of converting voice input to text data and sending it is completed here.

[1354] Step 3:

[1355] Server-based question analysis

[1356] The server receives user input data and passes it to a natural language processing engine (e.g., natural language processing engine software). The natural language processing engine extracts important keywords and phrases from the text data. Specifically, it identifies important elements such as "resident tax," "payment deadline," and "next fiscal year" to understand the intent of the question. Through this analysis, the server generates a dataset containing semantically important information.

[1357] Step 4:

[1358] Server-based database search

[1359] Based on the analysis results, the server searches for relevant information from its storage device (database management system). The database contains laws, regulations, and past case examples. For example, the server searches the database entries related to "resident tax," "payment deadline," and "next fiscal year," and retrieves that information. In this step, the server collects the relevant data and prepares it for use in the next step.

[1360] Step 5:

[1361] Server-based response generation

[1362] Based on the data acquired by the server, a generative AI (e.g., a generative AI model) is used to generate an appropriate answer. A prompt is input to the generative AI model, and a response in a natural sentence format is generated. For example, in response to the prompt "When is the deadline for paying next year's resident tax?", the model generates the answer "The deadline for paying next year's resident tax is June 1, 2023." In this step, the generative AI model generates accurate and easy-to-understand sentences.

[1363] Step 6:

[1364] Sending responses from the server to the terminal.

[1365] The generated responses are sent from the server to the terminal. Text-based responses are sent as is, while if an audio response is required, automated speech software is used to convert the text to speech, and that audio data is sent to the terminal. For example, the text response "The deadline for paying next year's resident tax is June 1, 2023." is sent to the terminal.

[1366] Step 7:

[1367] Display of answers via device

[1368] The device displays the response received from the server to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker. Specifically, a message such as "The deadline for paying next year's resident tax is June 1, 2023" might be displayed on the screen or played aloud. In this step, the user can obtain the answer to their question visually or audibly.

[1369] (Application Example 1)

[1370] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1371] In modern society, the number of elderly users and users with low IT literacy is increasing, making it difficult to provide information smoothly to these users. Furthermore, while there is a need to provide product information and service guidance quickly and effectively in physical stores, current technology is insufficient to meet this demand. In particular, there is a need for intuitive interfaces that can be used by elderly users and users with low IT literacy.

[1372] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1373] In this invention, the server includes means for receiving input from a user, means for transmitting the user's input to the server, means for analyzing the user's input within the server using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating an appropriate response based on the acquired data, means for transmitting the generated response to a user terminal, means for displaying the response on the user terminal, means for recognizing the user's gaze direction using a gaze detection sensor and transmitting it to the server, means for providing product information and service guidance within the physical store based on the gaze direction, and means for receiving questions regarding product information and service guidance within the physical store via voice input. This makes it possible to provide information intuitively and effectively to elderly people and users with low IT literacy in physical stores.

[1374] "Means of receiving user input" refers to an interface that allows users to input information into a system. This includes smart glasses, smartphones, and computers.

[1375] "Means of sending user input to a server" refers to the function of sending information entered by the user to a server via a network. This utilizes internet connectivity or wireless communication technology.

[1376] "Methods for analyzing user input within a server using a natural language processing engine" refers to technologies that analyze text and audio data received by the server to understand the user's intent. The natural language processing engine plays this role.

[1377] "Means of obtaining relevant data from a database based on analysis results" refers to a function that searches for and retrieves necessary information from a database based on the results of analysis performed by a natural language processing engine.

[1378] "Generative AI methods for generating appropriate answers" refers to AI technology that generates appropriate answers to user questions based on acquired data. Generative AI plays this role.

[1379] "Means of sending generated responses to the user's terminal" refers to the function of transferring responses created by a generative AI to the user's device. This is done via the internet or wireless communication.

[1380] "Means of displaying answers on the user's device" refers to an interface that displays the generated answers on the user's device. This role is fulfilled by the display of smart glasses or the screen of a smartphone.

[1381] "A means of recognizing the direction of the user's gaze using a gaze detection sensor and transmitting it to a server" refers to a technology that detects the direction the user is looking and transmits that information to a server. The gaze detection sensor plays this role.

[1382] "Means of providing product information and service guidance within a physical store based on the direction of gaze" refers to a function that provides detailed information about products and services based on the direction the user is looking.

[1383] "A means of receiving questions about product information and service guidance within a physical store via voice input" refers to a function that captures user voice questions, converts them into text data, and analyzes them. Voice-to-text conversion software fulfills this role.

[1384] A specific embodiment for carrying out the present invention is shown below. This embodiment makes it possible to provide information intuitively and effectively to elderly people and users with low IT literacy in physical stores.

[1385] System Configuration

[1386] This system consists of the following main components:

[1387] 1. A device that accepts user input (such as smart glasses or a smartphone)

[1388] 2. Server

[1389] 3. Natural Language Processing Engine

[1390] 4. Database

[1391] 5. Generative AI

[1392] 6. Eye-tracking sensor

[1393] 7. Speech-to-text conversion software

[1394] 8. Automated voice software

[1395] Hardware and software usage

[1396] The primary device used is a pair of smart glasses. These smart glasses are equipped with an eye-tracking sensor to recognize the user's gaze direction. They also have a microphone for voice input.

[1397] On the server side, a natural language processing engine (e.g., spaCy), speech-to-text software (e.g., Mozilla DeepSpeech), generative AI (e.g., OpenAI GPT-3), and a database system (e.g., PostgreSQL) are used. These software components work together to analyze user input data and generate appropriate responses.

[1398] Methods for data processing and data calculation

[1399] Processing of eye-tracking data

[1400] When a user looks at products or services in a store through their smart glasses, an eye-tracking sensor recognizes the direction of their gaze and sends that data to a server. The server analyzes the eye-tracking data to identify information about products the user is interested in.

[1401] Analysis of voice input

[1402] When a user enters a question by voice, the microphone in the smart glasses collects the voice and sends the voice data to a server. The voice data is then converted into text data using speech-to-text software.

[1403] Natural language processing and database search

[1404] The server passes the converted text data to a natural language processing engine to analyze the user's question. Based on the analysis results, it searches the database for relevant product information and service details.

[1405] Answer generation

[1406] Based on the acquired information, a generative AI generates appropriate answers to the user's questions. The answers are generated in natural-sounding sentences.

[1407] Information provision

[1408] The generated response is sent back to the smart glasses via the server and displayed in the user's field of view. If output in audio format is requested, the text is converted into audio data using automated speech software and played back through the smart glasses' speaker.

[1409] Examples of prompt statements

[1410] The following are specific examples of questions users might ask smart glasses in a physical store:

[1411] "What are the features of this product?"

[1412] "How much does this item cost?"

[1413] "Where can I find this product?"

[1414] As described above, the system based on the present invention enables intuitive and effective information provision in physical stores, particularly for elderly people and users with low IT literacy.

[1415] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1416] Step 1:

[1417] The user wears smart glasses and walks around a physical store. When the user looks at a product or service that interests them, the eye-tracking sensor recognizes the direction of their gaze. The input is gaze direction data, and the output is data related to gaze direction. The server receives this gaze direction data and proceeds to the next step.

[1418] Step 2:

[1419] The user provides voice input. For example, they might ask, "What are the features of this product?" The smart glasses' microphone collects the voice data and sends it to the server. The input is voice data, and the output is the raw voice data sent to the server.

[1420] Step 3:

[1421] The server converts the received audio data into text data using speech-to-text software (e.g., Mozilla DeepSpeech). The input is audio data, and the output is the converted text data. This allows the user's questions to be analyzed in text format.

[1422] Step 4:

[1423] The server passes text data to a natural language processing engine (e.g., spaCy) to analyze the user's question. The input is text data, and the output is keywords and important phrases included in the analysis results. Based on the analysis results, the server understands the user's intent.

[1424] Step 5:

[1425] The server searches a database (e.g., PostgreSQL) for information on products of interest based on the analysis results and eye-tracking data. The input is the analysis results and eye-tracking data, and the output is detailed information on related products. This allows the server to retrieve appropriate information.

[1426] Step 6:

[1427] The server uses generative AI (e.g., OpenAI GPT-3) to generate appropriate answers to user questions based on the acquired information. The input is detailed product information, and the output is the generated text-based answer. The generative AI generates natural-sounding sentences, creating answers that are easy for the user to understand.

[1428] Step 7:

[1429] The server sends the generated text-formatted response to the smart glasses. The input is the generated text-formatted response, and the output is the text data sent to the smart glasses. This allows the user to receive the response.

[1430] Step 8:

[1431] The user's smart glasses display the received text data on a screen, and, if necessary, convert it into audio data using automated voice software and play it through the speaker. The input is text data, and the output is the response displayed in the user's field of vision and the audio data. This allows the user to see the response visually and hear it aloud.

[1432] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1433] A detailed description of embodiments for carrying out the present invention is provided below. This embodiment provides a system that efficiently handles resident services for local governments and enables smooth information provision, especially for the elderly and users with low IT literacy. Furthermore, by combining it with an emotion engine, responses based on the user's emotions can also be realized.

[1434] System Overview

[1435] This system consists of the following main components:

[1436] A terminal for user input.

[1437] Server for receiving and processing input data

[1438] Natural Language Processing Engine

[1439] database

[1440] Generative AI

[1441] Speech-to-text software

[1442] Automated voice software

[1443] Emotional Engine

[1444] Program Processing Description

[1445] 1. User input

[1446] Users access the system using a device (e.g., a personal computer or smartphone) and input questions or information. Users may input questions in text format, or, in some cases, elderly individuals may dictate their questions verbally.

[1447] Specific example:

[1448] The user enters, "Please tell me the opening hours of the nearby library."

[1449] 2. Data transmission by the terminal

[1450] The terminal sends the entered text data to the server. If voice input is used, the voice data is converted to text data using speech-to-text software. The converted text data is then sent to the server by the terminal.

[1451] 3. Question analysis by the server

[1452] The server passes the received text data to a natural language processing engine to begin analysis. The natural language processing engine extracts keywords and important phrases from the text data and understands the intent of the question.

[1453] Specific example:

[1454] We analyze important keywords such as "library" and "opening hours."

[1455] 4. Database search by server

[1456] Based on the analysis results, the server searches the database for relevant information. The database stores laws, regulations, and past case examples.

[1457] Specific example:

[1458] Search database entries related to "library" and "opening hours".

[1459] 5. User emotion analysis using an emotion engine

[1460] The server passes user input data and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies emotions (e.g., joy, anger, sadness, surprise) from the user's text and voice data.

[1461] Specific example:

[1462] The emotion engine detects when the user's voice sounds tense and identifies it as "tension."

[1463] 6. Server-driven response generation

[1464] Based on the analysis results and the output of the emotion engine, the server uses generative AI to generate appropriate responses. The generative AI constructs natural-sounding sentences and provides clear and emotionally sensitive answers to the user's questions.

[1465] Specific example:

[1466] The system generates the response: "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1467] 7. Sending responses from the server to the terminal.

[1468] The generated response is sent from the server to the terminal. If the response is in text format, it is sent as is. If an audio response is required, automated speech software is used to convert the text into audio data, which is then sent to the terminal.

[1469] 8. Display of answers via device

[1470] The device displays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[1471] Specific example:

[1472] A message is displayed or played saying, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1473] This configuration allows the system to efficiently handle inquiries about basic administrative services, provide a user-friendly interface that is considerate of the elderly, and deliver kind responses that are sensitive to the user's feelings. This enables the effective use of limited resources within local governments and improves resident satisfaction.

[1474] The following describes the processing flow.

[1475] Step 1:

[1476] Users access the system using a terminal and enter their questions. For example, a user might type "What are the opening hours of the nearby library?" in text format. Users can also dictate their questions aloud.

[1477] Step 2:

[1478] The terminal sends the entered text or voice data to the server. If voice input is used, the terminal uses speech-to-text software to convert the voice data into text data and then sends it.

[1479] Step 3:

[1480] The server receives the text data and passes it to a natural language processing engine, which then begins analyzing the question. The natural language processing engine extracts keywords and important phrases from the text data to understand the intent of the question.

[1481] Specific example:

[1482] Extract important keywords such as "library" and "opening hours."

[1483] Step 4:

[1484] The server searches the database for relevant information based on the analysis results. The server sends queries to the database, which stores laws, regulations, and past case examples, and retrieves the relevant information.

[1485] Specific example:

[1486] Search database entries related to "library" and "opening hours" to retrieve information on "opening hours of nearby libraries".

[1487] Step 5:

[1488] The server passes user input data and voice data to the emotion engine, which analyzes the user's emotions. The emotion engine identifies the user's emotions (e.g., joy, anger, sadness, surprise) from the text and voice data.

[1489] Specific example:

[1490] The emotion engine detects when the user's voice sounds tense and identifies it as "tension."

[1491] Step 6:

[1492] The server uses generative AI to generate appropriate answers based on the analysis results and the output of the emotion engine. The generative AI constructs natural-sounding sentences and provides clear and emotionally sensitive answers to the user's questions.

[1493] Specific example:

[1494] The system generates the response: "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1495] Step 7:

[1496] The server sends the generated response to the terminal in text format. If necessary, the server uses automated speech software to convert the generated text into audio data and sends it to the terminal.

[1497] Specific example:

[1498] Send a message in text or voice format saying, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1499] Step 8:

[1500] The device displays or plays the received response to the user. If it's text data, it's displayed on the screen; if it's audio data, it's played through the speaker.

[1501] Specific example:

[1502] A message appears on the screen or is played as audio stating, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1503] This step enables the system to efficiently handle inquiries about basic administrative services, providing a user-friendly interface that is considerate of the elderly and users with low IT literacy, as well as providing kind and empathetic responses. This allows for the effective use of limited resources within local governments and improves resident satisfaction.

[1504] (Example 2)

[1505] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1506] Current municipal resident service systems are difficult for the elderly and users with low IT literacy to use, and responding to inquiries is time-consuming and labor-intensive. Furthermore, they fail to provide responses that are sensitive to users' feelings, making it difficult to improve resident satisfaction.

[1507] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1508] In this invention, the server includes means for analyzing user input using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating appropriate responses based on the obtained data, and sentiment analysis means for analyzing the user's emotions. This provides an interface that is easy to use even for the elderly and users with low IT literacy, and enables quick and appropriate responses that take the user's emotions into consideration.

[1509] A "user" refers to a person who accesses the system and enters questions or information.

[1510] A "user terminal" refers to a device used by a user to access a system, such as a personal computer or smartphone.

[1511] A "server" refers to a device that receives input data from user terminals and performs analysis and processing on it.

[1512] A "natural language processing engine" refers to software that analyzes text data, extracts keywords and important phrases, and understands the intent of a question.

[1513] A "database" refers to an information storage system that stores and manages related information, including laws, regulations, and past response examples.

[1514] "Generative AI methods" refer to artificial intelligence technologies that generate appropriate answers based on acquired data.

[1515] "Emotion analysis methods" refer to technologies that identify and analyze emotions from user input data and voice data.

[1516] "Speech-to-text conversion software" refers to software that converts audio data into text data.

[1517] "Automatic voice software" refers to software that converts text data into speech data.

[1518] This invention is a system for improving resident services in local governments, and provides an interface that is particularly easy to use for the elderly and users with low IT literacy. It also utilizes an emotion engine to provide responses that take the user's emotions into consideration. A detailed description of the system follows.

[1519] System Overview

[1520] This system consists of the following main components:

[1521] A device for the user to input data (e.g., a personal computer, a smartphone)

[1522] Server for receiving and processing input data

[1523] Natural language processing engine (e.g., natural language processing API)

[1524] Database (e.g., relational database management system)

[1525] Generative AI (e.g., generative model AI)

[1526] Speech-to-text conversion software (e.g., speech recognition software)

[1527] Automatic voice software (e.g., speech synthesis software)

[1528] Emotion engine (e.g., emotion analysis software)

[1529] Program Processing Description

[1530] 1. User input

[1531] Users access the system using their devices and input questions or information. Input can be in text or voice format. For example, if a user asks a question by voice, such as "What are the opening hours of the nearby library?", they would use their smartphone's microphone.

[1532] 2. Data transmission by the terminal

[1533] The terminal sends the input data to the server. In the case of voice input, speech-to-text software (e.g., speech recognition software) is used to convert the voice data into text data. The text data is then sent to the server.

[1534] Specific example: A smartphone converts voice input into text using speech recognition software and sends it to a server, saying, "Please tell me the opening hours of the nearby library."

[1535] 3. Question analysis by the server

[1536] The server passes the received text data to a natural language processing engine (e.g., a natural language processing API) to analyze the intent of the question. For example, by extracting keywords such as "library" and "opening hours," it understands the content of the user's question.

[1537] 4. Database search by server

[1538] Based on the analysis results, the server searches for and retrieves relevant information from a database (e.g., a relational database management system). For example, it retrieves data related to "library" and "opening hours."

[1539] 5. User emotion analysis using an emotion engine

[1540] The server passes user input data and voice data to an emotion engine (e.g., emotion analysis software) to analyze the user's emotions. The emotion engine can identify emotions such as joy, anger, sadness, and surprise.

[1541] Specific example: The server identifies that the user is "stressed" from their input.

[1542] 6. Server-driven response generation

[1543] Based on the analysis results and the output of the emotion engine, the server uses generative AI (e.g., generative model AI) to generate an appropriate response. For example, it might generate a response like, "The nearby library is open from 8am to 8pm on weekdays. Please feel free to go out."

[1544] Example of a prompt:

[1545] "Please tell me the opening hours of the nearby library. The user is feeling anxious. Please generate a kind and reassuring answer."

[1546] 7. Sending responses from the server to the terminal.

[1547] The generated response is sent from the server to the terminal. If necessary, automated speech software (e.g., text-to-speech software) is used to convert the text into speech data.

[1548] 8. Display of answers via device

[1549] The device displays the received response to the user. If it's in text format, it's displayed on the screen; if it's in audio format, it's played through the speaker. For example, a smartphone might display or play the message, "The nearby library is open from 8:00 AM to 8:00 PM on weekdays. Please feel free to visit."

[1550] This system efficiently handles inquiries about resident services from local governments and provides a user-friendly interface that is considerate of the elderly. Furthermore, it enables responses that respond to user emotions, thereby improving resident satisfaction.

[1551] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1552] Step 1: User input

[1553] Users access the system using their smartphones or computers and input questions and information. For example, they might ask a question by voice, such as, "Please tell me the opening hours of the nearby library." The input data is in voice format and is saved on the device as initial input information.

[1554] Step 2: Data transmission by the terminal

[1555] The terminal sends the voice data entered by the user to the server. The voice data is converted into text data using speech-to-text software (e.g., speech recognition software). The converted text data, "Please tell me the opening hours of the nearby library," is sent to the server.

[1556] Input: Audio data

[1557] Output: Text data

[1558] Specific operation: The smartphone captures the audio and converts it to text using speech recognition software.

[1559] Step 3: Server-based question analysis

[1560] The server passes the received text data to a natural language processing engine (e.g., a natural language processing API) for analysis. The natural language processing engine extracts keywords such as "library" and "opening hours" from the text data and understands the intent of the question.

[1561] Input: Text data

[1562] Output: Analyzed data (keywords and intent)

[1563] Specific operation: The server inputs text data into a natural language processing API, which then analyzes and extracts keywords and intent.

[1564] Step 4: Server-based database search

[1565] The server searches a database (e.g., a relational database management system) based on the analyzed keywords and intent, and retrieves relevant information. For example, the server searches database entries related to "library" and "opening hours" to retrieve the opening hours of the nearest library.

[1566] Input: Analyzed data (keywords and intent)

[1567] Output: Acquired information

[1568] Specific operation: The server generates a database query and searches for and retrieves the relevant data.

[1569] Step 5: User emotion analysis using an emotion engine

[1570] The server passes the user's input data (including voice data) to an emotion engine (e.g., emotion analysis software) to analyze the user's emotions. The emotion engine identifies emotions such as "tension" from the input data.

[1571] Input: Audio data or text data

[1572] Output: Analyzed sentiment data

[1573] Specific operation: The server inputs voice or text data into sentiment analysis software to identify emotions.

[1574] Step 6: Server generates response

[1575] The server uses generative AI (e.g., generative model AI) to generate an appropriate response based on the analysis of the question and the output of the sentiment engine. For example, it might generate a response like, "The nearby library is open from 8am to 8pm on weekdays. Please feel free to go out."

[1576] Input: Analyzed data (keywords, intent, sentiment)

[1577] Output: Generated response (text data)

[1578] Specific operation: The server inputs prompts and analysis data into the generative AI and generates an appropriate response.

[1579] Step 7: Sending the response from the server to the terminal

[1580] The generated responses are sent from the server to the terminal in text format or, if necessary, in audio format. For audio format, automated speech software (e.g., text-to-speech software) is used.

[1581] Input: Text format answer

[1582] Output: Answer in text or audio format

[1583] Specific operation: The server passes text data to the automated speech software, which converts it into speech data and sends it.

[1584] Step 8: Displaying the answer via the device

[1585] The device displays the received response to the user. If it's in text format, it's displayed on the screen; if it's in audio format, it's played through the speaker.

[1586] Input: Text or audio response

[1587] Output: Displayed on screen or played as audio.

[1588] Specific action: The smartphone displays a message on the screen or plays audio from the speaker.

[1589] (Application Example 2)

[1590] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1591] User interfaces in autonomous vehicles present challenges, particularly for the elderly and those with low IT literacy. Furthermore, conventional systems are insufficient in responding to user emotions, highlighting the need to improve passenger satisfaction and safety. Additionally, accurately analyzing user voice input and providing appropriate responses to inquiries presents technical challenges.

[1592] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for transmitting the user's input to the server, means for analyzing the user's input within the server using a natural language processing engine, means for obtaining relevant data from a database based on the analysis results, generative AI means for generating an appropriate response based on the acquired data, means for transmitting the generated response to a user terminal, means for displaying the response on the user terminal, emotion engine means for analyzing the user's emotions within the autonomous vehicle and generating an appropriate response based on those emotions, and means for converting the generated response into voice data and providing it to the user. This makes it possible for users to easily access information even within an autonomous vehicle and to provide responses that take the user's emotions into consideration.

[1593] "Means of receiving user input" refers to an interface that allows users to input questions or instructions to the system in voice or text format.

[1594] "Means of sending user input to the server" refers to communication methods for transferring data entered by the user to the server in real time.

[1595] "Means for analyzing user input within a server using a natural language processing engine" refers to a means of analyzing received user input data using a natural language processing engine to understand the user's intent.

[1596] "Means for obtaining relevant data from a database based on analysis results" refers to methods for searching and obtaining relevant information from a database based on the analysis results of a natural language processing engine.

[1597] "Generative AI methods that generate appropriate answers based on acquired data" refers to generative artificial intelligence that generates answers suitable for user questions based on information acquired from a database.

[1598] "Means for sending the generated response to the user's terminal" refers to means for sending the generated response to the user's terminal so that it can be displayed or played back.

[1599] "Means for displaying answers on the user's terminal" refers to means for displaying the generated answers on the screen of the user's terminal.

[1600] "An emotion engine means for analyzing user emotions within an autonomous vehicle and generating appropriate emotion-based responses" refers to an engine with emotion analysis capabilities that analyzes user emotions from voice and text data and generates responses corresponding to those emotions.

[1601] "Means for converting generated responses into audio data and providing them to the user" refers to means for converting text-based responses into audio data and allowing the user to listen to them through speakers or headphones.

[1602] A mode for carrying out this invention relates to an interaction system used in an autonomous vehicle. This system allows passengers to receive user-friendly and emotionally sensitive responses when obtaining information or getting answers to questions while the vehicle is in motion.

[1603] System Overview

[1604] This system consists of the following main hardware and software components:

[1605] Hardware:

[1606] Communication devices (tablets, smartphones, etc.) inside autonomous vehicles

[1607] Microphone (for voice input)

[1608] Speaker (for voice response)

[1609] software:

[1610] Natural language processing engine (e.g., Google NLP)

[1611] Speech-to-text software (e.g., Google Speech-to-Text)

[1612] Automated speech software (e.g., Google Text-to-Speech)

[1613] Emotion engine (e.g., Affectiva SDK)

[1614] Generative AI (e.g. OpenAI GPT-4)

[1615] Processing flow

[1616] 1. User voice input

[1617] The user voice-inputs their questions into the microphone inside the autonomous vehicle. This voice data is converted into text data by speech-to-text software and sent to the server.

[1618] 2. Question analysis by the server

[1619] The server analyzes the received text data using a natural language processing engine (e.g., Google NLP) to understand the intent behind the user's question.

[1620] 3. Database Search

[1621] Based on the analysis results, the server retrieves relevant data from the database. This database includes FAQs, traffic information, destination information, and more.

[1622] 4. Sentiment analysis and response generation

[1623] The server analyzes the user's text and voice data using an emotion engine (e.g., Affectiva SDK) to identify the user's emotions (e.g., distressed, relieved). Then, it uses a generative AI (e.g., OpenAI GPT-4) to generate appropriate responses that take the user's emotions into consideration.

[1624] 5. Text-to-speech conversion and response provision.

[1625] The generated responses are converted into audio data by automated speech-to-speech software (such as Google Text-to-Speech) and played back to the user through the speaker.

[1626] Specific example

[1627] For example, if a user asks "Where is the nearest parking lot?" into the in-car microphone, the audio is converted to text. The server uses a natural language processing engine to recognize the keyword "parking lot" and retrieves information about the nearest parking lot from the database. Once the emotion engine identifies the user's distress from the text data, the generative AI generates a response such as "The nearest parking lot is at the north exit of the station. Drive with peace of mind." This response is converted to audio data and played back through the speaker.

[1628] Example of a prompt

[1629] By inputting prompts like the following into a generative AI model, it will generate an appropriate response.

[1630] Please answer the following questions. If the user is having trouble, please add a kind explanation.

[1631] Question: Where is the nearest parking lot? User's sentiment: Troubled. Answer: The nearest parking lot is at the north exit of the station. Further explanation:

[1632] This configuration allows users to easily access information even within autonomous vehicles and provides responses that are sensitive to the user's emotions.

[1633] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1634] Step 1:

[1635] The user inputs their question by voice into the microphone. The input data is "voice data".

[1636] Step 2:

[1637] The device uses speech-to-text software (such as Google Speech-to-Text) to convert audio data into text data. At this stage, the input is "audio data" and the output is "text data". Specifically, speech recognition software analyzes the audio data and converts it into the corresponding text.

[1638] Step 3:

[1639] The terminal sends the converted text data to the server. The input is "text data," and the output is "sending data to the server." Specifically, the terminal transfers data to the server via the network.

[1640] Step 4:

[1641] The server passes the received text data to a natural language processing engine (such as Google NLP) and begins analysis. The input is "text data," and the output is the "analysis result." Specifically, the natural language processing engine extracts keywords and phrases from the text and understands the intent of the user's question.

[1642] Step 5:

[1643] The server searches the database for relevant information based on the analysis results. The input is the "analysis results," and the output is the "related data." Specifically, a database query is executed, and the relevant data is retrieved.

[1644] Step 6:

[1645] The server passes the user's text data to an emotion engine (such as the Affectiva SDK) to analyze the user's emotions. The input is "text data," and the output is "emotion analysis results." Specifically, the emotion engine analyzes the characteristics of the text and voice to identify the user's emotional state.

[1646] Step 7:

[1647] The server generates an appropriate response using a generative AI model (such as OpenAI GPT-4) based on the analysis results and sentiment analysis results. The input is the "analysis results" and "sentiment analysis results," and the output is the "generated response." Specifically, the generative AI model generates a natural response based on the input prompt sentence.

[1648] Step 8:

[1649] The server passes the generated response to speech-to-text software (such as Google Text-to-Speech) to convert it into audio data. The input is the "generated response," and the output is the "audio data." Specifically, the speech synthesis software analyzes the text data and converts it into speech.

[1650] Step 9:

[1651] The server sends audio data to the terminal. The input is "audio data," and the output is "data transmission to the terminal." Specifically, the server transfers the audio data to the terminal via the network.

[1652] Step 10:

[1653] The device plays the received audio data through its speaker. The input is "audio data," and the output is "audio playback." Specifically, the device decodes the audio file and plays the audio through its speaker.

[1654] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1655] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1656] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1657] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1658] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1659] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1660] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1661] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1662] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1663] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1664] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1665] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1666] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1667] 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.

[1668] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1669] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1670] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1671] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1672] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1673] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1674] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1675] The following is further disclosed regarding the embodiments described above.

[1676] (Claim 1)

[1677] A means of receiving input from the user,

[1678] A means of sending user input to a server,

[1679] A means of analyzing user input within the server using a natural language processing engine,

[1680] A means of obtaining relevant data from a database based on the analysis results,

[1681] A generative AI system that generates appropriate answers based on acquired data,

[1682] A means of sending the generated response to the user's terminal,

[1683] A means of displaying the answer on the user's terminal,

[1684] A system that includes this.

[1685] (Claim 2)

[1686] The system according to claim 1, comprising speech-to-text conversion software that converts user voice input into text data.

[1687] (Claim 3)

[1688] The system according to claim 1, comprising automatic voice software that converts generated text responses into audio data, and means for playing back the audio data.

[1689] "Example 1"

[1690] (Claim 1)

[1691] A means of receiving input from the user,

[1692] A means by which the terminal converts user input into data and sends it to the server,

[1693] A means by which the server analyzes user input using a natural language processing engine,

[1694] A means for obtaining relevant information from a storage device based on the analysis results,

[1695] A generation AI means that generates appropriate answers based on acquired information,

[1696] A means of sending the generated response to the user's terminal,

[1697] A means of displaying the answer on the user's terminal,

[1698] A system that includes this.

[1699] (Claim 2)

[1700] The system according to claim 1, comprising a processing device that converts user voice input into text data.

[1701] (Claim 3)

[1702] The system according to claim 1, comprising a processing device for converting generated text responses into audio data, and means for playing back the audio data.

[1703] "Application Example 1"

[1704] (Claim 1)

[1705] A means of receiving input from the user,

[1706] A means of sending user input to a server,

[1707] A means of analyzing user input within the server using a natural language processing engine,

[1708] A means of obtaining relevant data from a database based on the analysis results,

[1709] A generative AI system that generates appropriate answers based on acquired data,

[1710] A means of sending the generated response to the user's terminal,

[1711] A means of displaying the answer on the user's terminal,

[1712] A means for recognizing the direction of the user's gaze using a gaze detection sensor and transmitting it to a server,

[1713] A means of providing product information and service guidance within a physical store based on the direction of gaze,

[1714] A means of receiving questions about product information and service guidance within a physical store via voice input,

[1715] A system that includes this.

[1716] (Claim 2)

[1717] The system according to claim 1, comprising speech-to-text conversion software that converts user voice input into text data.

[1718] (Claim 3)

[1719] The system according to claim 1, comprising automatic voice software that converts generated text responses into audio data, and means for playing back the audio data.

[1720] "Example 2 of combining an emotion engine"

[1721] (Claim 1)

[1722] A means of receiving input from the user,

[1723] A means of sending user input from the user terminal to the server,

[1724] A means of analyzing user input within the server using a natural language processing engine,

[1725] A means of obtaining relevant data from a database based on the analysis results,

[1726] A generative AI system that generates appropriate answers based on acquired data,

[1727] A means of sending the generated response to the user's terminal,

[1728] A means of displaying the answer on the user's terminal,

[1729] A system that includes emotion analysis tools for analyzing user emotions.

[1730] (Claim 2)

[1731] The system according to claim 1, comprising speech-to-text conversion software that converts user voice input into text data.

[1732] (Claim 3)

[1733] The system according to claim 1, comprising automatic voice software that converts generated text responses into audio data, and means for playing back the audio data.

[1734] "Application example 2 when combining with an emotional engine"

[1735] (Claim 1)

[1736] A means of receiving input from the user,

[1737] A means of sending user input to a server,

[1738] A means of analyzing user input within the server using a natural language processing engine,

[1739] A means of obtaining relevant data from a database based on the analysis results,

[1740] A generative AI system that generates appropriate answers based on acquired data,

[1741] A means of sending the generated response to the user's terminal,

[1742] A means of displaying the answer on the user's terminal,

[1743] An emotion engine means that analyzes the user's emotions within an autonomous vehicle and generates appropriate emotion-based responses,

[1744] A means of converting the generated response into audio data and providing it to the user,

[1745] A system that includes this.

[1746] (Claim 2)

[1747] The system according to claim 1, comprising speech-to-text conversion software that converts user voice input into text data.

[1748] (Claim 3)

[1749] The system according to claim 1, comprising automatic voice software that converts generated text responses into audio data, and means for playing back the audio data. [Explanation of Symbols]

[1750] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving input from the user, A means of sending user input to a server, A means of analyzing user input within the server using a natural language processing engine, A means of obtaining relevant data from a database based on the analysis results, A generative AI system that generates appropriate answers based on acquired data, A means of sending the generated response to the user's terminal, A means of displaying the answer on the user's terminal, A system that includes this.

2. The system according to claim 1, comprising speech-to-text conversion software that converts user voice input into text data.

3. The system according to claim 1, comprising automatic voice software that converts generated text responses into audio data, and means for playing back the audio data.

Images