system

Abstract

We provide the system. [Solution] A means for users to contact the city hall using their devices, A means for classifying the user's inquiry content into categories by performing natural language analysis, A means for searching for appropriate information from a database based on the aforementioned categories, Means for providing the retrieved information to the user in text or audio format, 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 method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional city hall counter services have problems such as an increase in the burden on staff due to the large number of inquiries and a long waiting time. Also, on the user side, stress increases because an answer to an inquiry cannot be obtained quickly. Furthermore, it becomes difficult to handle when the content of the inquiry is complicated or there is a language barrier. There is a need for a system that solves such problems, improves the efficiency of city hall operations, and enables users to receive responses quickly.

Means for Solving the Problems

[0005] The present invention solves the aforementioned problem by providing a system that includes means for a user to make an inquiry to the city hall using a device, means for classifying the user's inquiry content by performing natural language analysis, means for searching for appropriate information from a database based on the category, and means for providing the retrieved information to the user in text or audio format. In addition, by including means for calling for expert assistance when appropriate information is not found in the database, it is possible to handle cases where more detailed information is needed. By including means for checking the type of device the user is using in advance and notifying the answer in an appropriate format, appropriate support can be provided to specific users, such as the elderly.

[0006] A "user" is an individual or group that uses city hall services, such as a citizen or user.

[0007] A "device" refers to any equipment that a user uses to make an inquiry, such as a smartphone, computer, or voice device.

[0008] An "inquiry" refers to a question or request from a citizen or user seeking information or support from the city hall.

[0009] "Natural language processing" is a technology that analyzes user inquiries to understand their meaning and intent.

[0010] A "category" is a classification item used to categorize inquiries, and includes items such as "waste disposal" and "medical institutions."

[0011] A "database" is a system used to store and make searchable information held by a city hall.

[0012] "Searching" is the operation or process of finding specific information from a database.

[0013] "Information" refers to the answers and data provided in response to user inquiries.

[0014] "Text format" refers to a format that provides information through text or character strings.

[0015] "Voice format" refers to a format that provides information through voice.

[0016] "Expert support" refers to a means of receiving support from a person with specialized knowledge for a specific inquiry.

[0017] "Confirmation of the type of user's device" refers to a process of pre-identifying the type of device used by the user.

[0018] "Notification of the answer" refers to the act of transmitting and informing the user of the retrieved information in an appropriate format.

Brief Explanation of Drawings

[0019] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which 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

[0020] 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.

[0021] First, the language used in the following description will be explained.

[0022] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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.

[0023] 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.

[0024] 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.

[0025] 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).

[0026] 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."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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".

[0040] This invention relates to a system that uses generative AI to handle counter services at city halls, and is implemented in the following form.

[0041] System Overview

[0042] This system begins with a user using a device to make an inquiry to the city hall. The user's inquiry is sent to a server and categorized using natural language processing. Based on that category, the server searches the database for appropriate information and provides the retrieved information to the user in text or audio format.

[0043] Overview of Program Processing

[0044] 1. Inquiry reception

[0045] Users can use their smartphones, computers, or voice devices to ask questions such as, "Please tell me how to sort my trash."

[0046] The terminal sends this query data to the server.

[0047] The server receives the query data, generates a unique user ID, and logs it.

[0048] 2. Content analysis

[0049] The server analyzes the received query content using a natural language processing engine.

[0050] The server classifies the data into categories such as "waste disposal" based on the analysis results.

[0051] The server logs these analysis results.

[0052] 3. Database Search

[0053] The server generates a database search query based on the analysis results.

[0054] The server sends a query to the database and searches for the appropriate answer.

[0055] 4. Answer generation

[0056] The server generates an answer based on the searched information.

[0057] The server formats the generated response into a user-friendly format.

[0058] The server logs the generated response.

[0059] 5. User Notifications

[0060] The server checks the device type (smartphone, voice-enabled device) of the pre-registered user.

[0061] The server will notify you of the response in text or audio format, depending on the device type.

[0062] The user receives the response through that device and confirms its contents.

[0063] Specific example

[0064] Inquiries about waste disposal

[0065] A user sends an inquiry using their smartphone asking, "Please tell me how to sort my trash."

[0066] The device sends this message to the server.

[0067] The server receives the message, generates a unique user ID, and logs it.

[0068] The server uses a natural language processing engine to analyze the message and categorize it as "garbage disposal".

[0069] The server queries the database for this category information and retrieves information on the appropriate sorting method.

[0070] The server generates a response based on the information it has obtained and formats it as a text message.

[0071] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[0072] The server sends the response to the user as a text message.

[0073] Users check the answers they receive on their smartphones and understand how to sort their trash.

[0074] In this way, the present invention provides a system that streamlines counter services at city halls and allows users to receive prompt assistance. This reduces waiting times at counters, alleviates the burden on staff, and improves user satisfaction.

[0075] The following describes the processing flow.

[0076] Step 1:

[0077] Users use smartphones, computers, or voice devices to enter inquiries to the city hall. For example, they might send a message like, "Please tell me how to sort my garbage."

[0078] Step 2:

[0079] The terminal sends the aforementioned query data to the server. The transmitted data includes the user's query.

[0080] Step 3:

[0081] The server receives the query data. At the same time, it generates a unique user ID to identify this query.

[0082] Step 4:

[0083] The server uses a natural language processing engine to analyze the user's query. This analysis is intended to understand the intent and content of the query.

[0084] Step 5:

[0085] The server determines the appropriate category based on the analysis results. For example, the category "waste disposal" might be determined.

[0086] Step 6:

[0087] The server logs the determined category information. This maintains a history of queries.

[0088] Step 7:

[0089] The server generates a database search query based on the category. This query is used to retrieve the appropriate information.

[0090] Step 8:

[0091] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[0092] Step 9:

[0093] The server generates a response based on information retrieved from the database. This response is a specific answer to the user's query.

[0094] Step 10:

[0095] The server formats the generated responses, for example, ensuring they are provided in a user-friendly text or audio format.

[0096] Step 11:

[0097] The server checks the user's device type. Based on pre-registered information, it determines whether it is a smartphone or a voice device.

[0098] Step 12:

[0099] The server will send a response based on the device type it has identified. If it is a smartphone, the response will be sent as a text message; if it is a voice device, the response will be sent as a voice message.

[0100] Step 13:

[0101] The user receives the answer through their device and confirms the information regarding their inquiry. For example, they might read a text message on their smartphone.

[0102] The above outlines the specific processing steps from inquiry to response. This system will streamline the city hall's counter services and allow users to receive prompt responses.

[0103] (Example 1)

[0104] 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."

[0105] In traditional local government service counters, users face long waiting times, and the burden on staff is increasing. Furthermore, the large number of inquiries by phone and email makes it difficult to respond quickly. This has led to problems such as decreased user satisfaction and operational inefficiency. The present invention aims to solve these problems and provide a system that allows users to quickly obtain the information they need and reduces the burden on staff.

[0106] 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.

[0107] In this invention, the server includes means for a user to make an inquiry to a local government using an information terminal; means for analyzing the user's inquiry using a natural language processing engine and classifying it into categories; means for searching for appropriate information from a database based on the categories; means for providing the retrieved information to the user in text or voice format; means for including the inquiry content and device information in the process of the information terminal transmitting the inquiry data to the server; means for the server to receive the inquiry data, generate a unique user ID, and record it in a log; means for the server to save the analysis results in an internal system and record them in a log; means for the server to generate an SQL query based on the category information and send it to a database; means for the server to format the generated response in text or voice format and record it in a log; and means for confirming the type of information terminal used by the user and notifying the user of the response in an appropriate format. This enables users to quickly obtain the necessary information, reduces the burden on staff, and improves operational efficiency and user satisfaction.

[0108] "User" refers to ordinary citizens or individuals who use this system to make inquiries.

[0109] "Information terminals" refer to digital devices such as smartphones, computers, tablets, and audio devices.

[0110] "Local government" refers to public institutions that provide administrative services to local residents, such as city halls and town halls.

[0111] "Inquiries" refer to questions or requests that users submit to local governments via information terminals.

[0112] A "natural language processing engine" refers to a software function that analyzes and understands the content of natural language text or audio input by a user.

[0113] A "category" refers to an item or theme used to classify inquiries (for example, waste disposal, issuance of resident registration certificates, etc.).

[0114] A "database" refers to a system that stores information for searching and retrieving appropriate information based on user queries.

[0115] A "server" refers to a central computer system that receives user inquiries, analyzes and processes them, and provides the final answer.

[0116] A "unique user ID" refers to a special identifier generated to uniquely identify each user.

[0117] A "log" refers to a file or data that records events and operations performed within a system.

[0118] A "SQL query" refers to a command with a specific syntax used to search for information within a database.

[0119] "Analysis results" refer to result information based on the understanding and classification of data obtained by a natural language processing engine.

[0120] "Text format" refers to the format of information expressed as a string of characters.

[0121] "Audio format" refers to the format in which the response is recorded or synthesized as audio.

[0122] "TTS technology" refers to the technology used to convert text into speech, or in other words, Text-to-Speech technology.

[0123] This invention relates to a system that automates and streamlines counter services at city halls. This system has a process in which a user makes an inquiry using an information terminal, a server analyzes the inquiry, and provides an appropriate answer to the user.

[0124] The overall system flow is as follows: First, the user makes an inquiry to the city hall using an information terminal (smartphone, computer, voice device, etc.). This inquiry data is sent from the terminal to the server. The server analyzes the received data and categorizes the content of the inquiry. Next, it generates an appropriate database search query to retrieve the necessary information from the database and generates the optimal response. Finally, depending on the type of device the user is using, the response is provided in either text or voice format.

[0125] Hardware and software to be used

[0126] Hardware:

[0127] Information terminals (smartphones, computers, tablets, voice devices)

[0128] Server (high-performance computer system)

[0129] software:

[0130] Natural language processing engines (such as Google® Natural Language API and IBM Watson®)

[0131] Database systems (MySQL®, MongoDB)

[0132] Text-to-speech technology (such as Amazon Polly)

[0133] Log management system

[0134] Specific processing of the program

[0135] When the server receives query data from a user, it first generates a unique user ID and logs this data. Next, it uses a natural language processing engine to analyze the query content and classifies the analysis results into categories. This analysis information is also logged.

[0136] Next, the server generates a database search query based on the category information and sends the query to the database. The database then returns the relevant information. Based on this information, the server generates a response for the user and formats it in text or audio format. This response is also logged.

[0137] Finally, the server checks the device type of the pre-registered user and sends a response accordingly. The user can receive this response on their device and review its contents.

[0138] Specific example

[0139] Inquiries about waste disposal

[0140] A user sends an inquiry using their smartphone asking, "Please tell me how to sort my trash."

[0141] The device sends this message to the server.

[0142] The server receives the message, generates a unique user ID, and logs it.

[0143] The server uses a natural language processing engine to analyze the message and categorize it as "garbage disposal".

[0144] The server queries the database for this category information and retrieves information on the appropriate sorting method.

[0145] The server generates a response based on the information it has obtained and formats it as a text message.

[0146] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[0147] The server generates a text message and sends it to the user's smartphone.

[0148] Users check the answers they receive on their smartphones and understand how to sort their trash.

[0149] Example of a prompt

[0150] User: "Could you tell me about the waste sorting methods at the city hall?"

[0151] AI response: "Thank you for your inquiry. The waste sorting instructions are as follows: Please put combustible waste in the red garbage bag and non-combustible waste in the blue garbage bag. For further details, please visit the city hall website."

[0152] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0153] Step 1:

[0154] Users make inquiries to local governments using information terminals. Specifically, users type messages such as "Please tell me how to sort my garbage" into their smartphones or computers and press the send button. The data entered at this time includes the inquiry content, user ID, and device information.

[0155] Input: User inquiry details, user ID, device information

[0156] Output: JSON format query data sent to the terminal

[0157] Step 2:

[0158] The terminal sends the user's inquiry data to the server. The terminal generates JSON data containing the entered inquiry details, user ID, and device information, and sends it to the server via an HTTP request.

[0159] Input: User query data (JSON format)

[0160] Output: HTTP request sent to the server

[0161] Step 3:

[0162] The server receives the query data, generates a unique user ID, and logs it. The server analyzes the received data and logs the user ID and query details. This log is managed by an internal system.

[0163] Input: HTTP request sent from the terminal

[0164] Output: User information and query details recorded in the log file

[0165] Step 4:

[0166] The server uses a natural language processing engine to analyze the received query. The server calls a natural language processing engine, such as the Google Natural Language API, to analyze the query and identify its category.

[0167] Input: User's inquiry

[0168] Output: Analysis results by a natural language processing engine (category information)

[0169] Step 5:

[0170] The server categorizes the query content based on the analysis results and stores this information in its internal system. For example, if it is categorized as "waste disposal," that category information is recorded in the log.

[0171] Input: Analysis results from a natural language processing engine

[0172] Output: Log file containing category information

[0173] Step 6:

[0174] The server generates a database search query based on the category information. For example, it creates an SQL query for the category "Waste Disposal".

[0175] Input: Category Information

[0176] Output: Generated SQL query

[0177] Step 7:

[0178] The server sends an SQL query to the database and retrieves the search results. The database (MySQL, MongoDB, etc.) returns the corresponding information.

[0179] Input: SQL query

[0180] Output: Search results retrieved from the database

[0181] Step 8:

[0182] The server generates responses to the user based on the search results it obtains. For example, it might generate information such as, "Please put combustible waste in the red garbage bag and non-combustible waste in the blue garbage bag."

[0183] Input: Search results from database

[0184] Output: Generated response (text or audio format)

[0185] Step 9:

[0186] The server formats the generated response into text or audio format. If in audio format, it uses Text-to-Speech (TTS) technology to generate the audio data.

[0187] Input: Generated answer

[0188] Output: Formatted response (text or audio format)

[0189] Step 10:

[0190] The server verifies the user's registration information and identifies the user's device type. Depending on the device type, it sends a response as either a text message or audio data.

[0191] Input: User's device information, formatted response

[0192] Output: Message sent to the user's device

[0193] Step 11:

[0194] The system checks the response received by the user on their device. For example, it might display a message on a smartphone screen saying, "Put combustible waste in the red garbage bag, and non-combustible waste in the blue garbage bag," and the system understands the content.

[0195] Input: Response message sent from the server

[0196] Output: Answers displayed in a format that the user can see.

[0197] (Application Example 1)

[0198] 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."

[0199] Traditional counter services at service facilities struggle to provide timely and accurate information to users, resulting in long waiting times, especially during peak hours, and decreased customer satisfaction. Furthermore, this increases the burden on service providers, making efficient operations difficult. There is a need to address these challenges and provide a system that benefits both users and service providers.

[0200] 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.

[0201] In this invention, the server includes means for a user to make an inquiry to a service facility using an electronic terminal, means for classifying the user's inquiry into categories by performing natural language analysis, means for retrieving appropriate information from an information storage unit based on the categories, means for generating a unique user ID and recording it in a log, and means for providing the retrieved information to the user in text or voice format. This enables users to quickly obtain appropriate answers, reduces the burden on service providers, and improves operational efficiency and customer satisfaction.

[0202] A "user" is a person who uses an electronic terminal to make inquiries to a service facility.

[0203] An "electronic terminal" is a device used by a user to contact a service facility, and includes smartphones, computers, and other similar devices.

[0204] A "service facility" refers to a physical store or counter where a user makes an inquiry.

[0205] "Natural language processing" is the process of analyzing text and audio data entered by a user and understanding its meaning.

[0206] "Means for classifying categories" refers to a function that sorts inquiry content into specific categories based on the results of natural language processing.

[0207] The "information storage unit" refers to the database where information answering inquiries is stored.

[0208] A "unique user ID" is a unique identifier generated to identify each user's inquiry.

[0209] "Means of recording in logs" refers to a function for saving inquiry details, analysis results, and search results as records.

[0210] "Text or audio format" refers to the format of the response provided to the user, and includes both text and audio data.

[0211] This invention relates to a system that provides information quickly and appropriately to users who make inquiries to service facilities using electronic terminals. The purpose of this invention is to improve user convenience and reduce the burden on service providers.

[0212] System Overview

[0213] The system of the present invention consists of the following main components.

[0214] 1. Electronic terminals: These are hardware devices used by users to make inquiries to service facilities. Examples include smartphones and computers.

[0215] 2. Server: This is the central hardware that processes query content and retrieves and provides appropriate information. A server includes multiple software components, including a natural language processing engine (Spacy), a database (MySQL, PostgreSQL, etc.), and a web framework (Flask).

[0216] Program Processing Overview

[0217] Hardware and software

[0218] Users make inquiries to service facilities using electronic devices (e.g., smartphones). These electronic devices include specific programs (e.g., mobile apps or web applications) that are executed.

[0219] Software used by the server:

[0220] Spacy: Used for natural language processing. It analyzes user inquiries and classifies them into categories.

[0221] Flask: Functions as an HTTP server for receiving, analyzing, searching, and generating responses to queries.

[0222] Database: MySQL, PostgreSQL, or similar databases are used to store the necessary information.

[0223] Data processing and data calculation

[0224] 1. Inquiry reception

[0225] Users contact service facilities using electronic devices in text or voice format. For example, they might send a message such as, "Please tell me the current stock of the latest smartphones you sell on your smartphone."

[0226] The terminal sends the query data to the server.

[0227] 2. Content analysis

[0228] The server uses Spacy to perform natural language processing on the query content.

[0229] This process involves understanding the intent of the inquiry and classifying it into the appropriate category, such as "product inventory."

[0230] 3. Database Search

[0231] Based on the category, the server sends the generated query to the database.

[0232] Search the database for the appropriate answer, such as inventory information.

[0233] 4. Answer generation

[0234] Based on the search results, the server generates an answer in a format that is easy for the user to understand.

[0235] Responses will be formatted as text or audio.

[0236] 5. User Notifications

[0237] The server verifies the type of electronic device used by the pre-registered user and sends the data in the appropriate format.

[0238] The user receives the response on their device and confirms its contents.

[0239] Specific example

[0240] As an example, consider a case where a user asks, "Please tell me the stock of the latest smartphones sold at this store." This inquiry, sent from an electronic device, undergoes natural language processing on the server to understand its category and content. Next, a search query is executed against the database to retrieve the appropriate stock information. The retrieved information is then provided to the user's electronic device in text or audio format.

[0241] Example of a prompt

[0242] Please tell me what the latest smartphones you sell are currently in stock.

[0243] In this way, the present invention enables users to quickly obtain appropriate answers, reduces the burden on service providers, and improves operational efficiency and customer satisfaction.

[0244] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0245] Step 1:

[0246] Users make inquiries using electronic devices.

[0247] Users use electronic devices such as smartphones to input inquiries via voice or text, such as, "Please tell me the current stock of the latest smartphones sold at this store." The input data is then transmitted from the user's electronic device to the server.

[0248] Input: User's inquiry (text or voice)

[0249] Output: Query data sent to the server

[0250] Step 2:

[0251] The server performs natural language processing on the query content.

[0252] The server analyzes the received query content using a natural language processing engine (Spacy). This analysis understands the intent of the query and classifies it into the appropriate category.

[0253] Input: Inquiry data

[0254] Output: Analysis results (category information)

[0255] Specific actions:

[0256] The server uses Spacy to tokenize the received data and analyze its meaning.

[0257] The terms and context are evaluated, and a category such as "product inventory" is assigned.

[0258] Step 3:

[0259] The server generates the database search query.

[0260] Based on the analysis results, the server generates a database search query. The query is used to retrieve information related to the inquiry.

[0261] Input: Analysis results (category information)

[0262] Output: Database search query

[0263] Specific actions:

[0264] The server defines the search criteria based on category information.

[0265] Generates database search queries in formats such as SQL.

[0266] Step 4:

[0267] The server performs a database search.

[0268] The server generates queries and sends them to the database to retrieve the necessary information. For example, it can retrieve inventory information for the latest smartphones.

[0269] Input: Database search query

[0270] Output: Search results (including inventory information)

[0271] Specific actions:

[0272] The server connects to the database and executes the query.

[0273] Record the results obtained from the database.

[0274] Step 5:

[0275] The server generates a response based on the information it has searched.

[0276] The server generates answers in a user-friendly format based on information retrieved from the database. The answers are formatted in either text or audio.

[0277] Input: Search results (stock information)

[0278] Output: Generated response (text or audio)

[0279] Specific actions:

[0280] The server converts the acquired information into human-readable text.

[0281] If the answer is in text format, it will generate a formatted text.

[0282] If the response is in audio format, it will be converted from text to audio.

[0283] Step 6:

[0284] The server notifies the user of the answer.

[0285] The server checks the type of the user's pre-registered electronic terminal and sends the answer to the user's electronic terminal in an appropriate format (text or voice).

[0286] Input: Generated answer (text or voice)

[0287] Output: Answer sent to the user's electronic terminal

[0288] Specific operations:

[0289] The server checks the user's terminal information and selects an appropriate format.

[0290] Send the answer to the user's electronic terminal, and the user receives and checks it. <0,

[0291] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0292] The present invention relates to a system for handling municipal office counter services with generative AI, and has a function of recognizing the user's emotion and optimizing the response. Hereinafter, embodiments for implementing the present invention will be described in detail.

[0293] System overview

[0294] This system starts with the user using a device to inquire at the municipal office. The content of the user's inquiry is sent to the server, and the category and emotion are classified by natural language analysis and emotion analysis. The server searches for appropriate information from the database based on the category and emotion, and provides the searched information to the user in text or voice format. The tone and content of the answer can be adjusted based on the user's emotion by the emotion engine.

[0295] Overview of Program Processing

[0296] 1. Inquiry Reception

[0297] The user makes an inquiry such as "Please teach me how to sort garbage" using a smartphone, computer, or voice device.

[0298] The terminal sends this inquiry data to the server.

[0299] The server receives the inquiry data, generates a unique user ID, and records it in the log.

[0300] 2. Content Analysis and Sentiment Analysis

[0301] The server analyzes the received inquiry content using a natural language processing engine. Also, it analyzes the sentiment included in the user's inquiry using a sentiment engine.

[0302] For example, a question like "Please teach me how to sort garbage" is classified into the category of "garbage disposal" and at the same time, the sentiment is determined to be "uneasy".

[0303] Based on the analysis results, the server determines the category and sentiment.

[0304] The server records this analysis result in the log.

[0305] 3. Database Search

[0306] Based on the category and sentiment, the server generates a database search query. This query is used to search for appropriate information.

[0307] The server sends the generated query to the database and executes the search. The database returns the relevant information.

[0308] 4. Answer Generation

[0309] The server generates responses based on information retrieved from the database. An emotion engine adjusts the tone and content according to the user's emotions.

[0310] For example, if the emotion of "anxiety" is recognized, the tone will be adjusted to something like, "Don't worry. Here's how to sort your trash."

[0311] The server formats the generated response into a user-friendly format.

[0312] The server logs the generated response.

[0313] 5. User Notifications

[0314] The server checks the device type (smartphone, voice-enabled device) of the pre-registered user.

[0315] The server will notify you of the response in text or audio format, depending on the device type.

[0316] The user receives the response through that device and confirms its contents.

[0317] Specific example

[0318] Inquiries about waste disposal

[0319] A user sends an inquiry via smartphone asking, "Please tell me how to sort my trash." At this time, they are feeling anxious about incorrect sorting.

[0320] The device sends this message to the server.

[0321] The server receives the message, generates a unique user ID, and logs it.

[0322] The server uses a natural language processing engine and an emotion engine to analyze the message and classify it into the category "garbage disposal" and the emotion "anxiety."

[0323] The server queries the database for this category information and sentiment information to obtain information on appropriate classification methods.

[0324] The server generates a response based on the information it obtains, adjusting the tone according to the user's mood. It formats the response as follows: "Don't worry. Here's how to separate your trash into combustible waste, non-combustible waste, plastics, etc."

[0325] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[0326] The server sends the response to the user as a text message.

[0327] Users can check the answers they receive on their smartphones, understand how to sort their trash, and have their anxieties alleviated.

[0328] Thus, this invention not only streamlines counter services at city halls and provides a system that allows users to receive prompt assistance, but also addresses users' emotions to provide more appropriate and satisfying services. As a result, waiting times at city hall counters are reduced, the burden on staff is lessened, and user satisfaction is improved.

[0329] The following describes the processing flow.

[0330] Step 1:

[0331] Users use smartphones, computers, or voice devices to enter inquiries into the city hall. For example, they might send a message like, "Please tell me how to sort my garbage." In these situations, users may be feeling anxious or confused.

[0332] Step 2:

[0333] The terminal sends the aforementioned query data to the server. The transmitted data includes the user's query.

[0334] Step 3:

[0335] The server receives the query data. Simultaneously, a unique user ID is generated to identify this query. The received data is logged.

[0336] Step 4:

[0337] The server uses a natural language processing engine to analyze the user's query. This analysis is intended to understand the intent and content of the query.

[0338] Step 5:

[0339] The server uses an emotion engine to analyze the user's emotions from their inquiry. For example, it can determine emotions such as "anxiety," "confusion," or "anger."

[0340] Step 6:

[0341] Based on the analysis results, the server categorizes user inquiries into categories such as "garbage disposal," while simultaneously recording their emotional responses.

[0342] Step 7:

[0343] The server logs category and sentiment information. This preserves the history of queries and the user's sentiment.

[0344] Step 8:

[0345] The server generates a database search query based on category and sentiment. This query is used to retrieve the appropriate information.

[0346] Step 9:

[0347] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[0348] Step 10:

[0349] The server generates responses based on information retrieved from the database. The emotion engine adjusts the tone and content according to the user's emotions. For example, if the emotion of "anxiety" is detected, a response will be generated in a tone such as, "Don't worry. Here's how to sort your trash."

[0350] Step 11:

[0351] The server formats the generated response into a user-friendly format, such as a text message or voice message.

[0352] Step 12:

[0353] The server checks the user's device type. Based on pre-registered information, it determines whether it is a smartphone or a voice device.

[0354] Step 13:

[0355] The server will send a response based on the device type it has identified. If it is a smartphone, the response will be sent as a text message; if it is a voice device, the response will be sent as a voice message.

[0356] Step 14:

[0357] The user receives the answer through their device and confirms the information regarding their inquiry. For example, they might read a text message on their smartphone to understand how to sort their trash and alleviate their concerns.

[0358] Thus, the present invention concretely realizes a series of processes from user inquiries to sentiment analysis, appropriate response generation, and notification to the user. Furthermore, by combining it with an emotion engine, it is possible to provide an optimal response that corresponds to the user's emotions.

[0359] (Example 2)

[0360] 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".

[0361] The objective of this invention is to provide a system for responding quickly and appropriately to user inquiries at city hall counter services. In particular, by providing optimal answers tailored to the user's emotions, the system aims to improve user satisfaction and reduce the burden on city hall staff.

[0362] 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.

[0363] In this invention, the server includes means for a user to make an inquiry using a device, means for performing natural language analysis on the user's inquiry and classifying it into categories and emotions, means for searching for appropriate information from a database based on the categories and emotions, means for adjusting the tone and content of the response according to the user's emotions, and means for providing the retrieved information to the user in text or audio format. This makes it possible to provide optimal information to the city hall in response to inquiries made by the user, taking emotions into consideration.

[0364] A "user" is an individual or organization that uses the system to make inquiries to the city hall.

[0365] A "device" is hardware used by a user to make inquiries, and includes smartphones, computers, voice devices, etc.

[0366] An "inquiry" refers to a question or request that a user submits to the city hall.

[0367] "Natural language processing" is the process of interpreting user inquiries and classifying them into specific categories or pieces of information.

[0368] A "category" refers to the type or field of a query classified by natural language processing.

[0369] "Emotions" refer to the psychological state inherent in a user's inquiry, and include, for example, "anxiety," "anger," and "joy."

[0370] A "database" is a digital information storage system that stores various types of information for the city hall.

[0371] "Information retrieval" is the process of finding information within a database based on specific categories or keywords.

[0372] "Adjusting tone and content according to emotions" is the process of considering the user's emotions and formulating a response using appropriate language and content.

[0373] "Text format" refers to a format that provides information as character data.

[0374] "Audio format" refers to a format in which information is provided as audio data.

[0375] This invention relates to a system that streamlines counter services at city halls, enabling users to receive prompt and appropriate assistance. In particular, it includes a function that recognizes the user's emotions and optimizes the response accordingly.

[0376] System Configuration

[0377] This system consists of the following main components:

[0378] 1. User device

[0379] Hardware such as smartphones, computers, and voice devices that users use to make inquiries.

[0380] 2. Server

[0381] This is the central system that receives user inquiries, analyzes them, retrieves information, and generates answers.

[0382] The software to be used is as follows:

[0383] Natural language processing engines: Examples) Google Cloud Natural Language API, IBM Watson NLP

[0384] Sentiment analysis engines: Examples include IBM Watson Tone Analyzer and Microsoft® Azure® Text Analytics.

[0385] Database: e.g., MySQL, PostgreSQL

[0386] Program Processing Overview

[0387] Inquiry reception

[0388] Users make inquiries using smartphones, computers, or voice devices. For example, they might type an inquiry such as, "Please tell me how to sort my trash." This message is sent from the device to the server, which generates a unique user ID and logs it.

[0389] Content analysis and sentiment analysis

[0390] The server analyzes the received query using a natural language processing engine and determines the user's emotions using an emotion analysis engine. As a result of the analysis, the query is classified into the category of "garbage disposal," and the emotion is determined to be "anxiety."

[0391] Database Search

[0392] Based on category and sentiment, the server generates a search query and sends it to the database. The relevant information is returned from the database and logged by the server.

[0393] Answer generation

[0394] The server generates responses based on information retrieved from the database. An emotion engine adjusts the tone and content according to the user's emotions. For example, if the emotion "anxiety" is recognized, the response will be adjusted to a tone such as, "Don't worry. Here's how to separate your trash into combustible waste, non-combustible waste, plastics, etc."

[0395] User notifications

[0396] The server checks the device type of the pre-registered user and notifies them of the response in the appropriate format (text or voice). Finally, the user receives the response through their device and confirms its contents.

[0397] Specific example

[0398] Consider a scenario where a user sends a message via smartphone asking, "Please tell me how to sort my trash." The user is anxious about incorrect sorting. The device sends this message to a server, which analyzes it and categorizes it as "trash disposal" and the user's emotion, "anxiety." Using this category and emotion information, the server queries a database to retrieve information on proper sorting methods. The server then generates a response, adjusting the tone according to the user's emotion, formatting it as, "Don't worry. Here's how to sort your trash: burnable, non-burnable, plastic, etc." Finally, the server verifies the pre-registered device type and sends the response to the user in text format. The user reviews the response on their smartphone, understands the trash sorting method, and their anxiety is relieved.

[0399] Examples of prompts for generative AI models

[0400] "Describe a system that uses a sentiment analysis engine and a natural language processing engine to categorize inquiries from citizens into categories and emotions, retrieves appropriate information from a database based on these categories, and provides it to the user's device in text or audio format."

[0401] By using this prompt, you can obtain detailed information about the specific operation and concepts of the system from the generating AI model.

[0402] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0403] Step 1: Inquiry Received

[0404] 1.1 A user makes an inquiry

[0405] Users enter inquiries using smartphones, computers, or voice devices. For example, a user might enter a message such as, "Please tell me how to sort my trash."

[0406] Input: The inquiry message sent from the user's device.

[0407] Output: Query data sent from the terminal to the server.

[0408] 1.2 The terminal sends the inquiry.

[0409] The terminal sends the query data to the server.

[0410] Specific operation: The terminal sends metadata to the server, including the query content and the user's device information (e.g., IP address, device ID).

[0411] Input: User inquiry message and metadata.

[0412] Output: Query data sent to the server.

[0413] 1.3 The server receives the query

[0414] The server receives the query data sent from the terminal and generates a unique user ID.

[0415] Specific operation: The server records the query details in the logging system and generates a user ID to associate with this log.

[0416] Input: Inquiry data sent from the terminal.

[0417] Output: Query data recorded in the log and the generated user ID.

[0418] Step 2: Content Analysis and Sentiment Analysis

[0419] 2.1 The server performs natural language processing.

[0420] The server uses a natural language processing engine to parse the query content.

[0421] Specific operation: The natural language processing engine analyzes the text data and classifies the query into categories such as "garbage disposal" based on keywords and context.

[0422] Input: Query data recorded on the server.

[0423] Output: Classified category information.

[0424] 2.2 The server performs sentiment analysis

[0425] The server uses an emotion analysis engine to determine the emotions contained in the query.

[0426] Specific operation: The emotion analysis engine analyzes the tone and expression of the text to detect emotions such as "anxiety," "anger," and "joy."

[0427] Input: Query data recorded on the server.

[0428] Output: Detected emotion information.

[0429] 2.3 The server records the analysis results.

[0430] The server integrates the results of natural language processing and sentiment analysis, and logs the categories and sentiments.

[0431] Input: Classified category information and detected sentiment information.

[0432] Output: Category and sentiment information recorded in the log.

[0433] Step 3: Database Search

[0434] 3.1 The server generates the search query

[0435] The server generates search queries based on category and sentiment.

[0436] Specific operation: The server generates database search queries, such as SQL queries, and sets conditions to search for specific information related to categories and sentiments.

[0437] Input: Category and sentiment information recorded in the log.

[0438] Output: The generated search query.

[0439] 3.2 The server sends a query to the database

[0440] The server sends a search query to the database and retrieves the information.

[0441] Specific operation: The server opens a database connection and executes the generated search query against the database.

[0442] Input: The generated search query.

[0443] Output: Search results returned from the database.

[0444] 3.3 The server receives the search results

[0445] The server receives the search results returned from the database and logs them.

[0446] Input: Search results from the database.

[0447] Output: Search results recorded in the log.

[0448] Step 4: Answer Generation

[0449] 4.1 The server generates the answer

[0450] The server generates an answer based on information retrieved from the database.

[0451] Specific operation: The server analyzes the acquired information and generates an appropriate response that aligns with the user's inquiry and sentiment.

[0452] Input: Search results from the database.

[0453] Output: The generated response.

[0454] 4.2 The server adjusts responses based on emotions.

[0455] The emotion engine adjusts the tone and content of responses according to the user's emotions.

[0456] Specific operation: The server modifies the wording and tone of the response based on the detected emotion. For example, if it determines that the user is "anxious," it will add phrases such as "don't worry."

[0457] Input: Generated response content and sentiment information.

[0458] Output: Adjusted response content.

[0459] 4.3 The server formats the response.

[0460] The server formats the adjusted responses into a user-friendly format.

[0461] Specific operation: The server converts the response into text or audio format, making it easy for the user to understand.

[0462] Input: Adjusted response content.

[0463] Output: Formatted response.

[0464] Step 5: User Notifications

[0465] 5.1 The server checks the user's device type.

[0466] The server checks the device type (smartphone, voice-enabled device) of the user who has been registered in advance.

[0467] Specific action: The server checks the device information listed in the user profile.

[0468] Input: User profile data.

[0469] Output: Device type information.

[0470] 5.2 The server sends the response

[0471] The server will send the response in either text or audio format, depending on the device type.

[0472] Specific operation: The server uses the corresponding communication protocol to send text messages and voice notifications to the user's device.

[0473] Input: Formatted response and device type information.

[0474] Output: The response sent to the user's device.

[0475] 5.3 The user receives the response

[0476] Users receive and review the responses via their smartphones or voice devices.

[0477] Specific actions: The user checks the device and views or listens to received messages.

[0478] Input: Response sent from the server.

[0479] Output: Confirmation of user responses.

[0480] (Application Example 2)

[0481] 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".

[0482] Traditional customer service in brick-and-mortar stores often involves providing the same service to all customers, making it difficult to respond flexibly to customers' emotions and circumstances. Furthermore, it placed a heavy burden on staff, and there was a demand for quick and efficient responses.

[0483] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0484] In this invention, the server includes means for a user to make a query using an information processing device, means for classifying the user's query content into categories and emotions by performing natural language analysis and sentiment analysis, means for retrieving appropriate information from a database based on the categories and emotions, and means for providing the retrieved information in text or audio format in a tone appropriate to the user's emotions. This enables flexible and rapid responses that are appropriate to the customer's emotions and circumstances.

[0485] An "information processing device" is a device used by users to input or process information, such as a smartphone or a robot.

[0486] "Natural language processing" is a technology that uses computers to analyze the language that humans use on a daily basis, with the aim of understanding and structuring the content of user inquiries.

[0487] "Sentiment analysis" is a technology that analyzes the emotions contained in a user's statements and writings, and identifies emotional states such as interest, anxiety, and confusion.

[0488] A "category" is a subject or theme used to classify user inquiries, and examples include product information and return procedures.

[0489] "Tone" refers to the element of adjusting the tone and expression of a response according to the user's emotional state. This includes, for example, a gentle tone to encourage reassurance or lively expressions to pique interest.

[0490] A "database" is a collection of information in which multiple pieces of information are systematically organized and stored, and is used to retrieve appropriate information in response to a query.

[0491] To implement this invention, the following system configuration is necessary. The system provides information to customers when they make inquiries at physical stores, and optimizes the response by also considering the customer's emotions.

[0492] System Overview

[0493] 1. Inquiry reception

[0494] The server provides a means for users to make inquiries using information processing devices (e.g., smartphones or in-store robots). Inquiry data sent from these information processing devices is transmitted to the cloud server.

[0495] 2. Content Analysis and Sentiment Analysis

[0496] The server analyzes the query content using a natural language processing engine (e.g., Google Cloud Natural Language API) to extract the query content and category. It also uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions and determine their emotional state.

[0497] 3. Database Search

[0498] The server searches the database for appropriate information based on the analyzed categories and sentiments. This database contains product information, procedure instructions, store information, and more.

[0499] 4. Answer generation

[0500] The server generates a response based on the information it has acquired. It adjusts the tone and expression according to the user's emotional state. This process generates a response that makes the user feel at ease.

[0501] 5. User Notifications

[0502] The server verifies the device type of the pre-registered user (smartphone, voice-enabled device, etc.) and provides the response in the appropriate format. The user can receive and confirm the response through the information processing device.

[0503] Specific example

[0504] For example, if a user uses their smartphone in a physical store and asks, "How do I return this item?", the following process will occur:

[0505] 1. Inquiry reception

[0506] A user submits an inquiry using their smartphone. This inquiry is sent to a cloud server.

[0507] 2. Content Analysis and Sentiment Analysis

[0508] The server uses the Google Cloud Natural Language API to analyze the inquiry and categorize it as "product information." Simultaneously, it uses IBM Watson Tone Analyzer to analyze the user's emotion as "confused."

[0509] 3. Database Search

[0510] The server searches the database based on the "product information" category and the "confusion" emotion to retrieve information on appropriate return procedures.

[0511] 4. Answer generation

[0512] Based on the information it retrieves, the server generates a response with a adjusted tone, such as, "Please rest assured. For instructions on how to return this product, please see the following steps."

[0513] 5. User Notifications

[0514] The server sends the response to the user's smartphone in text format, and the user checks the response on their smartphone.

[0515] Example of a prompt

[0516] Specifically, use the following prompt statements:

[0517] "When a user inquires, 'I want to know how to return an item,' and their emotion is perceived as 'confused,' please provide specific steps on how to generate a response."

[0518] Implementing such a system will enable flexible and rapid responses tailored to the user's emotions and circumstances.

[0519] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0520] Step 1:

[0521] The user makes an inquiry using an information processing device. The user inputs an inquiry, such as "How do I return this product?", using a smartphone or an in-store robot. The input inquiry data is sent to a cloud server by the terminal. Here, the input is the user's inquiry, and the output is the data sent to the cloud server.

[0522] Step 2:

[0523] The server analyzes received query data using natural language processing and sentiment analysis. Specifically, it uses the Google Cloud Natural Language API to analyze the query content and extract categories (e.g., "product information"). It also uses IBM Watson Tone Analyzer to determine the sentiment contained in the query (e.g., "confused"). The input is the user's query data, and the output is the analyzed category and sentiment information.

[0524] Step 3:

[0525] The server searches the database for appropriate information based on the analyzed categories and sentiments. Here, the server generates a database search query and performs the search against the database. The input is category and sentiment information, and the output is the information retrieved from the database.

[0526] Step 4:

[0527] The server generates a response based on information retrieved from the database. During this process, it adjusts the tone and expression according to the analyzed emotion. For example, if the emotion "confusion" is recognized, it will generate a response in a tone such as, "Please rest assured. For instructions on how to return this product, please see the following steps." The input consists of information and emotion data retrieved from the database, while the output is the adjusted response.

[0528] Step 5:

[0529] The server pre-verifies the type of information processing device the user is using and provides the response in the appropriate format. For example, if the user is using a smartphone, the response will be sent in text format. The input consists of the response and the user's device information, and the output is a response notification in the appropriate format.

[0530] Step 6:

[0531] Users receive and confirm answers through an information processing device. Specifically, users can receive text messages on their smartphones and learn how to resolve their inquiries by reviewing their content. The input is the provided answer, and the output is the user's improved understanding and satisfaction.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] [Second Embodiment]

[0536] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0537] 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.

[0538] 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).

[0539] 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.

[0540] 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.

[0541] 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).

[0542] 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.

[0543] 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.

[0544] 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.

[0545] 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.

[0546] 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.

[0547] 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".

[0548] This invention relates to a system that uses generative AI to handle counter services at city halls, and is implemented in the following form.

[0549] System Overview

[0550] This system begins with a user using a device to make an inquiry to the city hall. The user's inquiry is sent to a server and categorized using natural language processing. Based on that category, the server searches the database for appropriate information and provides the retrieved information to the user in text or audio format.

[0551] Overview of Program Processing

[0552] 1. Inquiry reception

[0553] Users can use their smartphones, computers, or voice devices to ask questions such as, "Please tell me how to sort my trash."

[0554] The terminal sends this query data to the server.

[0555] The server receives the query data, generates a unique user ID, and logs it.

[0556] 2. Content analysis

[0557] The server analyzes the received query content using a natural language processing engine.

[0558] The server classifies the data into categories such as "waste disposal" based on the analysis results.

[0559] The server logs these analysis results.

[0560] 3. Database Search

[0561] The server generates a database search query based on the analysis results.

[0562] The server sends a query to the database and searches for the appropriate answer.

[0563] 4. Answer generation

[0564] The server generates an answer based on the searched information.

[0565] The server formats the generated response into a user-friendly format.

[0566] The server logs the generated response.

[0567] 5. User Notifications

[0568] The server checks the device type (smartphone, voice-enabled device) of the pre-registered user.

[0569] The server will notify you of the response in text or audio format, depending on the device type.

[0570] The user receives the response through that device and confirms its contents.

[0571] Specific example

[0572] Inquiries about waste disposal

[0573] A user sends an inquiry using their smartphone asking, "Please tell me how to sort my trash."

[0574] The device sends this message to the server.

[0575] The server receives the message, generates a unique user ID, and logs it.

[0576] The server uses a natural language processing engine to analyze the message and categorize it as "garbage disposal".

[0577] The server queries the database for this category information and retrieves information on the appropriate sorting method.

[0578] The server generates a response based on the information it has obtained and formats it as a text message.

[0579] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[0580] The server sends the response to the user as a text message.

[0581] Users check the answers they receive on their smartphones and understand how to sort their trash.

[0582] In this way, the present invention provides a system that streamlines counter services at city halls and allows users to receive prompt assistance. This reduces waiting times at counters, alleviates the burden on staff, and improves user satisfaction.

[0583] The following describes the processing flow.

[0584] Step 1:

[0585] Users use smartphones, computers, or voice devices to enter inquiries to the city hall. For example, they might send a message like, "Please tell me how to sort my garbage."

[0586] Step 2:

[0587] The terminal sends the aforementioned query data to the server. The transmitted data includes the user's query.

[0588] Step 3:

[0589] The server receives the query data. At the same time, it generates a unique user ID to identify this query.

[0590] Step 4:

[0591] The server uses a natural language processing engine to analyze the user's query. This analysis is intended to understand the intent and content of the query.

[0592] Step 5:

[0593] The server determines the appropriate category based on the analysis results. For example, the category "waste disposal" might be determined.

[0594] Step 6:

[0595] The server logs the determined category information. This maintains a history of queries.

[0596] Step 7:

[0597] The server generates a database search query based on the category. This query is used to retrieve the appropriate information.

[0598] Step 8:

[0599] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[0600] Step 9:

[0601] The server generates a response based on information retrieved from the database. This response is a specific answer to the user's query.

[0602] Step 10:

[0603] The server formats the generated responses, for example, ensuring they are provided in a user-friendly text or audio format.

[0604] Step 11:

[0605] The server checks the user's device type. Based on pre-registered information, it determines whether it is a smartphone or a voice device.

[0606] Step 12:

[0607] The server will send a response based on the device type it has identified. If it is a smartphone, the response will be sent as a text message; if it is a voice device, the response will be sent as a voice message.

[0608] Step 13:

[0609] The user receives the answer through their device and confirms the information regarding their inquiry. For example, they might read a text message on their smartphone.

[0610] The above outlines the specific processing steps from inquiry to response. This system will streamline the city hall's counter services and allow users to receive prompt responses.

[0611] (Example 1)

[0612] 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."

[0613] In traditional local government service counters, users face long waiting times, and the burden on staff is increasing. Furthermore, the large number of inquiries by phone and email makes it difficult to respond quickly. This has led to problems such as decreased user satisfaction and operational inefficiency. The present invention aims to solve these problems and provide a system that allows users to quickly obtain the information they need and reduces the burden on staff.

[0614] 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.

[0615] In this invention, the server includes means for a user to make an inquiry to a local government using an information terminal; means for analyzing the user's inquiry using a natural language processing engine and classifying it into categories; means for searching for appropriate information from a database based on the categories; means for providing the retrieved information to the user in text or voice format; means for including the inquiry content and device information in the process of the information terminal transmitting the inquiry data to the server; means for the server to receive the inquiry data, generate a unique user ID, and record it in a log; means for the server to save the analysis results in an internal system and record them in a log; means for the server to generate an SQL query based on the category information and send it to a database; means for the server to format the generated response in text or voice format and record it in a log; and means for confirming the type of information terminal used by the user and notifying the user of the response in an appropriate format. This enables users to quickly obtain the necessary information, reduces the burden on staff, and improves operational efficiency and user satisfaction.

[0616] "User" refers to ordinary citizens or individuals who use this system to make inquiries.

[0617] "Information terminals" refer to digital devices such as smartphones, computers, tablets, and audio devices.

[0618] "Local government" refers to public institutions that provide administrative services to local residents, such as city halls and town halls.

[0619] "Inquiries" refer to questions or requests that users submit to local governments via information terminals.

[0620] A "natural language processing engine" refers to a software function that analyzes and understands the content of natural language text or audio input by a user.

[0621] A "category" refers to an item or theme used to classify inquiries (for example, waste disposal, issuance of resident registration certificates, etc.).

[0622] A "database" refers to a system that stores information for searching and retrieving appropriate information based on user queries.

[0623] A "server" refers to a central computer system that receives user inquiries, analyzes and processes them, and provides the final answer.

[0624] A "unique user ID" refers to a special identifier generated to uniquely identify each user.

[0625] A "log" refers to a file or data that records events and operations performed within a system.

[0626] A "SQL query" refers to a command with a specific syntax used to search for information within a database.

[0627] "Analysis results" refer to result information based on the understanding and classification of data obtained by a natural language processing engine.

[0628] "Text format" refers to the format of information expressed as a string of characters.

[0629] "Audio format" refers to the format in which the response is recorded or synthesized as audio.

[0630] "TTS technology" refers to the technology used to convert text into speech, or in other words, Text-to-Speech technology.

[0631] This invention relates to a system that automates and streamlines counter services at city halls. This system has a process in which a user makes an inquiry using an information terminal, a server analyzes the inquiry, and provides an appropriate answer to the user.

[0632] The overall system flow is as follows: First, the user makes an inquiry to the city hall using an information terminal (smartphone, computer, voice device, etc.). This inquiry data is sent from the terminal to the server. The server analyzes the received data and categorizes the content of the inquiry. Next, it generates an appropriate database search query to retrieve the necessary information from the database and generates the optimal response. Finally, depending on the type of device the user is using, the response is provided in either text or voice format.

[0633] Hardware and software to be used

[0634] Hardware:

[0635] Information terminals (smartphones, computers, tablets, voice devices)

[0636] Server (high-performance computer system)

[0637] software:

[0638] Natural language processing engines (Google Natural Language API, IBM Watson, etc.)

[0639] Database systems (MySQL, MongoDB)

[0640] Text-to-speech technology (such as Amazon Polly)

[0641] Log management system

[0642] Specific processing of the program

[0643] When the server receives query data from a user, it first generates a unique user ID and logs this data. Next, it uses a natural language processing engine to analyze the query content and classifies the analysis results into categories. This analysis information is also logged.

[0644] Next, the server generates a database search query based on the category information and sends the query to the database. The database then returns the relevant information. Based on this information, the server generates a response for the user and formats it in text or audio format. This response is also logged.

[0645] Finally, the server checks the device type of the pre-registered user and sends a response accordingly. The user can receive this response on their device and review its contents.

[0646] Specific example

[0647] Inquiries about waste disposal

[0648] A user sends an inquiry using their smartphone asking, "Please tell me how to sort my trash."

[0649] The device sends this message to the server.

[0650] The server receives the message, generates a unique user ID, and logs it.

[0651] The server uses a natural language processing engine to analyze the message and categorize it as "garbage disposal".

[0652] The server queries the database for this category information and retrieves information on the appropriate sorting method.

[0653] The server generates a response based on the information it has obtained and formats it as a text message.

[0654] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[0655] The server generates a text message and sends it to the user's smartphone.

[0656] Users check the answers they receive on their smartphones and understand how to sort their trash.

[0657] Example of a prompt

[0658] User: "Could you tell me about the waste sorting methods at the city hall?"

[0659] AI response: "Thank you for your inquiry. The waste sorting instructions are as follows: Please put combustible waste in the red garbage bag and non-combustible waste in the blue garbage bag. For further details, please visit the city hall website."

[0660] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0661] Step 1:

[0662] Users make inquiries to local governments using information terminals. Specifically, users type messages such as "Please tell me how to sort my garbage" into their smartphones or computers and press the send button. The data entered at this time includes the inquiry content, user ID, and device information.

[0663] Input: User inquiry details, user ID, device information

[0664] Output: JSON format query data sent to the terminal

[0665] Step 2:

[0666] The terminal sends the user's inquiry data to the server. The terminal generates JSON data containing the entered inquiry details, user ID, and device information, and sends it to the server via an HTTP request.

[0667] Input: User query data (JSON format)

[0668] Output: HTTP request sent to the server

[0669] Step 3:

[0670] The server receives the query data, generates a unique user ID, and logs it. The server analyzes the received data and logs the user ID and query details. This log is managed by an internal system.

[0671] Input: HTTP request sent from the terminal

[0672] Output: User information and query details recorded in the log file

[0673] Step 4:

[0674] The server uses a natural language processing engine to analyze the received query. The server calls a natural language processing engine, such as the Google Natural Language API, to analyze the query and identify its category.

[0675] Input: User's inquiry

[0676] Output: Analysis results by a natural language processing engine (category information)

[0677] Step 5:

[0678] The server categorizes the query content based on the analysis results and stores this information in its internal system. For example, if it is categorized as "waste disposal," that category information is recorded in the log.

[0679] Input: Analysis results from a natural language processing engine

[0680] Output: Log file containing category information

[0681] Step 6:

[0682] The server generates a database search query based on the category information. For example, it creates an SQL query for the category "Waste Disposal".

[0683] Input: Category Information

[0684] Output: Generated SQL query

[0685] Step 7:

[0686] The server sends an SQL query to the database and retrieves the search results. The database (MySQL, MongoDB, etc.) returns the corresponding information.

[0687] Input: SQL query

[0688] Output: Search results retrieved from the database

[0689] Step 8:

[0690] The server generates responses to the user based on the search results it obtains. For example, it might generate information such as, "Please put combustible waste in the red garbage bag and non-combustible waste in the blue garbage bag."

[0691] Input: Search results from database

[0692] Output: Generated response (text or audio format)

[0693] Step 9:

[0694] The server formats the generated response into text or audio format. If in audio format, it uses Text-to-Speech (TTS) technology to generate the audio data.

[0695] Input: Generated answer

[0696] Output: Formatted response (text or audio format)

[0697] Step 10:

[0698] The server verifies the user's registration information and identifies the user's device type. Depending on the device type, it sends a response as either a text message or audio data.

[0699] Input: User's device information, formatted response

[0700] Output: Message sent to the user's device

[0701] Step 11:

[0702] The system checks the response received by the user on their device. For example, it might display a message on a smartphone screen saying, "Put combustible waste in the red garbage bag, and non-combustible waste in the blue garbage bag," and the system understands the content.

[0703] Input: Response message sent from the server

[0704] Output: Answers displayed in a format that the user can see.

[0705] (Application Example 1)

[0706] 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."

[0707] Traditional counter services at service facilities struggle to provide timely and accurate information to users, resulting in long waiting times, especially during peak hours, and decreased customer satisfaction. Furthermore, this increases the burden on service providers, making efficient operations difficult. There is a need to address these challenges and provide a system that benefits both users and service providers.

[0708] 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.

[0709] In this invention, the server includes means for a user to make an inquiry to a service facility using an electronic terminal, means for classifying the user's inquiry into categories by performing natural language analysis, means for retrieving appropriate information from an information storage unit based on the categories, means for generating a unique user ID and recording it in a log, and means for providing the retrieved information to the user in text or voice format. This enables users to quickly obtain appropriate answers, reduces the burden on service providers, and improves operational efficiency and customer satisfaction.

[0710] A "user" is a person who uses an electronic terminal to make inquiries to a service facility.

[0711] An "electronic terminal" is a device used by a user to contact a service facility, and includes smartphones, computers, and other similar devices.

[0712] A "service facility" refers to a physical store or counter where a user makes an inquiry.

[0713] "Natural language processing" is the process of analyzing text and audio data entered by a user and understanding its meaning.

[0714] "Means for classifying categories" refers to a function that sorts inquiry content into specific categories based on the results of natural language processing.

[0715] The "information storage unit" refers to the database where information answering inquiries is stored.

[0716] A "unique user ID" is a unique identifier generated to identify each user's inquiry.

[0717] "Means of recording in logs" refers to a function for saving inquiry details, analysis results, and search results as records.

[0718] "Text or audio format" refers to the format of the response provided to the user, and includes both text and audio data.

[0719] This invention relates to a system that provides information quickly and appropriately to users who make inquiries to service facilities using electronic terminals. The purpose of this invention is to improve user convenience and reduce the burden on service providers.

[0720] System Overview

[0721] The system of the present invention consists of the following main components.

[0722] 1. Electronic terminals: These are hardware devices used by users to make inquiries to service facilities. Examples include smartphones and computers.

[0723] 2. Server: This is the central hardware that processes query content and retrieves and provides appropriate information. A server includes multiple software components, including a natural language processing engine (Spacy), a database (MySQL, PostgreSQL, etc.), and a web framework (Flask).

[0724] Program Processing Overview

[0725] Hardware and software

[0726] Users make inquiries to service facilities using electronic devices (e.g., smartphones). These electronic devices include specific programs (e.g., mobile apps or web applications) that are executed.

[0727] Software used by the server:

[0728] Spacy: Used for natural language processing. It analyzes user inquiries and classifies them into categories.

[0729] Flask: Functions as an HTTP server for receiving, analyzing, searching, and generating responses to queries.

[0730] Database: MySQL, PostgreSQL, or similar databases are used to store the necessary information.

[0731] Data processing and data calculation

[0732] 1. Inquiry reception

[0733] Users contact service facilities using electronic devices in text or voice format. For example, they might send a message such as, "Please tell me the current stock of the latest smartphones you sell on your smartphone."

[0734] The terminal sends the query data to the server.

[0735] 2. Content analysis

[0736] The server uses Spacy to perform natural language processing on the query content.

[0737] This process involves understanding the intent of the inquiry and classifying it into the appropriate category, such as "product inventory."

[0738] 3. Database Search

[0739] Based on the category, the server sends the generated query to the database.

[0740] Search the database for the appropriate answer, such as inventory information.

[0741] 4. Answer generation

[0742] Based on the search results, the server generates an answer in a format that is easy for the user to understand.

[0743] Responses will be formatted as text or audio.

[0744] 5. User Notifications

[0745] The server verifies the type of electronic device used by the pre-registered user and sends the data in the appropriate format.

[0746] The user receives the response on their device and confirms its contents.

[0747] Specific example

[0748] As an example, consider a case where a user asks, "Please tell me the stock of the latest smartphones sold at this store." This inquiry, sent from an electronic device, undergoes natural language processing on the server to understand its category and content. Next, a search query is executed against the database to retrieve the appropriate stock information. The retrieved information is then provided to the user's electronic device in text or audio format.

[0749] Example of a prompt

[0750] Please tell me what the latest smartphones you sell are currently in stock.

[0751] In this way, the present invention enables users to quickly obtain appropriate answers, reduces the burden on service providers, and improves operational efficiency and customer satisfaction.

[0752] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0753] Step 1:

[0754] Users make inquiries using electronic devices.

[0755] Users use electronic devices such as smartphones to input inquiries via voice or text, such as, "Please tell me the current stock of the latest smartphones sold at this store." The input data is then transmitted from the user's electronic device to the server.

[0756] Input: User's inquiry (text or voice)

[0757] Output: Query data sent to the server

[0758] Step 2:

[0759] The server performs natural language processing on the query content.

[0760] The server analyzes the received query content using a natural language processing engine (Spacy). This analysis understands the intent of the query and classifies it into the appropriate category.

[0761] Input: Inquiry data

[0762] Output: Analysis results (category information)

[0763] Specific actions:

[0764] The server uses Spacy to tokenize the received data and analyze its meaning.

[0765] The terms and context are evaluated, and a category such as "product inventory" is assigned.

[0766] Step 3:

[0767] The server generates the database search query.

[0768] Based on the analysis results, the server generates a database search query. The query is used to retrieve information related to the inquiry.

[0769] Input: Analysis results (category information)

[0770] Output: Database search query

[0771] Specific actions:

[0772] The server defines the search criteria based on category information.

[0773] Generates database search queries in formats such as SQL.

[0774] Step 4:

[0775] The server performs a database search.

[0776] The server generates queries and sends them to the database to retrieve the necessary information. For example, it can retrieve inventory information for the latest smartphones.

[0777] Input: Database search query

[0778] Output: Search results (including inventory information)

[0779] Specific actions:

[0780] The server connects to the database and executes the query.

[0781] Record the results obtained from the database.

[0782] Step 5:

[0783] The server generates a response based on the information it has searched.

[0784] The server generates answers in a user-friendly format based on information retrieved from the database. The answers are formatted in either text or audio.

[0785] Input: Search results (stock information)

[0786] Output: Generated response (text or audio)

[0787] Specific actions:

[0788] The server converts the acquired information into human-readable text.

[0789] If the answer is in text format, it will generate a formatted text.

[0790] If the response is in audio format, it will be converted from text to audio.

[0791] Step 6:

[0792] The server notifies the user of the answer.

[0793] The server verifies the type of electronic device used by the pre-registered user and sends the response to the user's electronic device in the appropriate format (text or audio).

[0794] Input: Generated response (text or audio)

[0795] Output: Response sent to the user's electronic device

[0796] Specific actions:

[0797] The server checks the user's terminal information and selects the appropriate format.

[0798] The response is sent to the user's electronic device, and the user receives and confirms it.

[0799] 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.

[0800] This invention relates to a system that uses generative AI to handle counter services at city halls, and includes a function to recognize user emotions and optimize responses accordingly. The embodiments for carrying out this invention will be described in detail below.

[0801] System Overview

[0802] This system begins with a user making an inquiry to the city hall using their device. The user's inquiry is sent to a server, where it is categorized and categorized based on natural language processing and sentiment analysis. The server then searches its database for appropriate information based on the category and sentiment, and provides the retrieved information to the user in text or audio format. The sentiment engine allows for the tone and content of the response to be adjusted based on the user's emotions.

[0803] Overview of Program Processing

[0804] 1. Inquiry reception

[0805] Users can use their smartphones, computers, or voice devices to ask questions such as, "Please tell me how to sort my trash."

[0806] The terminal sends this query data to the server.

[0807] The server receives the query data, generates a unique user ID, and logs it.

[0808] 2. Content Analysis and Sentiment Analysis

[0809] The server analyzes the received query content using a natural language processing engine. Additionally, it uses an emotion engine to analyze the emotions contained in the user's query.

[0810] For example, the question "Please tell me how to sort garbage" is classified under the category of "garbage disposal," and at the same time, the emotion associated with it is identified as "anxiety."

[0811] The server determines the category and sentiment based on the analysis results.

[0812] The server logs these analysis results.

[0813] 3. Database Search

[0814] The server generates a database search query based on category and sentiment. This query is used to retrieve the appropriate information.

[0815] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[0816] 4. Answer generation

[0817] The server generates responses based on information retrieved from the database. An emotion engine adjusts the tone and content according to the user's emotions.

[0818] For example, if the emotion of "anxiety" is recognized, the tone will be adjusted to something like, "Don't worry. Here's how to sort your trash."

[0819] The server formats the generated response into a user-friendly format.

[0820] The server logs the generated response.

[0821] 5. User Notifications

[0822] The server checks the device type (smartphone, voice-enabled device) of the pre-registered user.

[0823] The server will notify you of the response in text or audio format, depending on the device type.

[0824] The user receives the response through that device and confirms its contents.

[0825] Specific example

[0826] Inquiries about waste disposal

[0827] A user sends an inquiry via smartphone asking, "Please tell me how to sort my trash." At this time, they are feeling anxious about incorrect sorting.

[0828] The device sends this message to the server.

[0829] The server receives the message, generates a unique user ID, and logs it.

[0830] The server uses a natural language processing engine and an emotion engine to analyze the message and classify it into the category "garbage disposal" and the emotion "anxiety."

[0831] The server queries the database for this category information and sentiment information to obtain information on appropriate classification methods.

[0832] The server generates a response based on the information it obtains, adjusting the tone according to the user's mood. It formats the response as follows: "Don't worry. Here's how to separate your trash into combustible waste, non-combustible waste, plastics, etc."

[0833] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[0834] The server sends the response to the user as a text message.

[0835] Users can check the answers they receive on their smartphones, understand how to sort their trash, and have their anxieties alleviated.

[0836] Thus, this invention not only streamlines counter services at city halls and provides a system that allows users to receive prompt assistance, but also addresses users' emotions to provide more appropriate and satisfying services. As a result, waiting times at city hall counters are reduced, the burden on staff is lessened, and user satisfaction is improved.

[0837] The following describes the processing flow.

[0838] Step 1:

[0839] Users use smartphones, computers, or voice devices to enter inquiries into the city hall. For example, they might send a message like, "Please tell me how to sort my garbage." In these situations, users may be feeling anxious or confused.

[0840] Step 2:

[0841] The terminal sends the aforementioned query data to the server. The transmitted data includes the user's query.

[0842] Step 3:

[0843] The server receives the query data. Simultaneously, a unique user ID is generated to identify this query. The received data is logged.

[0844] Step 4:

[0845] The server uses a natural language processing engine to analyze the user's query. This analysis is intended to understand the intent and content of the query.

[0846] Step 5:

[0847] The server uses an emotion engine to analyze the user's emotions from their inquiry. For example, it can determine emotions such as "anxiety," "confusion," or "anger."

[0848] Step 6:

[0849] Based on the analysis results, the server categorizes user inquiries into categories such as "garbage disposal," while simultaneously recording their emotional responses.

[0850] Step 7:

[0851] The server logs category and sentiment information. This preserves the history of queries and the user's sentiment.

[0852] Step 8:

[0853] The server generates a database search query based on category and sentiment. This query is used to retrieve the appropriate information.

[0854] Step 9:

[0855] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[0856] Step 10:

[0857] The server generates responses based on information retrieved from the database. The emotion engine adjusts the tone and content according to the user's emotions. For example, if the emotion of "anxiety" is detected, a response will be generated in a tone such as, "Don't worry. Here's how to sort your trash."

[0858] Step 11:

[0859] The server formats the generated response into a user-friendly format, such as a text message or voice message.

[0860] Step 12:

[0861] The server checks the user's device type. Based on pre-registered information, it determines whether it is a smartphone or a voice device.

[0862] Step 13:

[0863] The server will send a response based on the device type it has identified. If it is a smartphone, the response will be sent as a text message; if it is a voice device, the response will be sent as a voice message.

[0864] Step 14:

[0865] The user receives the answer through their device and confirms the information regarding their inquiry. For example, they might read a text message on their smartphone to understand how to sort their trash and alleviate their concerns.

[0866] Thus, the present invention concretely realizes a series of processes from user inquiries to sentiment analysis, appropriate response generation, and notification to the user. Furthermore, by combining it with an emotion engine, it is possible to provide an optimal response that corresponds to the user's emotions.

[0867] (Example 2)

[0868] 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".

[0869] The objective of this invention is to provide a system for responding quickly and appropriately to user inquiries at city hall counter services. In particular, by providing optimal answers tailored to the user's emotions, the system aims to improve user satisfaction and reduce the burden on city hall staff.

[0870] 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.

[0871] In this invention, the server includes means for a user to make an inquiry using a device, means for performing natural language analysis on the user's inquiry and classifying it into categories and emotions, means for searching for appropriate information from a database based on the categories and emotions, means for adjusting the tone and content of the response according to the user's emotions, and means for providing the retrieved information to the user in text or audio format. This makes it possible to provide optimal information to the city hall in response to inquiries made by the user, taking emotions into consideration.

[0872] A "user" is an individual or organization that uses the system to make inquiries to the city hall.

[0873] A "device" is hardware used by a user to make inquiries, and includes smartphones, computers, voice devices, etc.

[0874] An "inquiry" refers to a question or request that a user submits to the city hall.

[0875] "Natural language processing" is the process of interpreting user inquiries and classifying them into specific categories or pieces of information.

[0876] A "category" refers to the type or field of a query classified by natural language processing.

[0877] "Emotions" refer to the psychological state inherent in a user's inquiry, and include, for example, "anxiety," "anger," and "joy."

[0878] A "database" is a digital information storage system that stores various types of information for the city hall.

[0879] "Information retrieval" is the process of finding information within a database based on specific categories or keywords.

[0880] "Adjusting tone and content according to emotions" is the process of considering the user's emotions and formulating a response using appropriate language and content.

[0881] "Text format" refers to a format that provides information as character data.

[0882] "Audio format" refers to a format in which information is provided as audio data.

[0883] This invention relates to a system that streamlines counter services at city halls, enabling users to receive prompt and appropriate assistance. In particular, it includes a function that recognizes the user's emotions and optimizes the response accordingly.

[0884] System Configuration

[0885] This system consists of the following main components:

[0886] 1. User device

[0887] Hardware such as smartphones, computers, and voice devices that users use to make inquiries.

[0888] 2. Server

[0889] This is the central system that receives user inquiries, analyzes them, retrieves information, and generates answers.

[0890] The software to be used is as follows:

[0891] Natural language processing engines: Examples) Google Cloud Natural Language API, IBM Watson NLP

[0892] Sentiment analysis engines: Examples) IBM Watson Tone Analyzer, Microsoft Azure Text Analytics

[0893] Database: e.g., MySQL, PostgreSQL

[0894] Program Processing Overview

[0895] Inquiry reception

[0896] Users make inquiries using smartphones, computers, or voice devices. For example, they might type an inquiry such as, "Please tell me how to sort my trash." This message is sent from the device to the server, which generates a unique user ID and logs it.

[0897] Content analysis and sentiment analysis

[0898] The server analyzes the received query using a natural language processing engine and determines the user's emotions using an emotion analysis engine. As a result of the analysis, the query is classified into the category of "garbage disposal," and the emotion is determined to be "anxiety."

[0899] Database Search

[0900] Based on category and sentiment, the server generates a search query and sends it to the database. The relevant information is returned from the database and logged by the server.

[0901] Answer generation

[0902] The server generates responses based on information retrieved from the database. An emotion engine adjusts the tone and content according to the user's emotions. For example, if the emotion "anxiety" is recognized, the response will be adjusted to a tone such as, "Don't worry. Here's how to separate your trash into combustible waste, non-combustible waste, plastics, etc."

[0903] User notifications

[0904] The server checks the device type of the pre-registered user and notifies them of the response in the appropriate format (text or voice). Finally, the user receives the response through their device and confirms its contents.

[0905] Specific example

[0906] Consider a scenario where a user sends a message via smartphone asking, "Please tell me how to sort my trash." The user is anxious about incorrect sorting. The device sends this message to a server, which analyzes it and categorizes it as "trash disposal" and the user's emotion, "anxiety." Using this category and emotion information, the server queries a database to retrieve information on proper sorting methods. The server then generates a response, adjusting the tone according to the user's emotion, formatting it as, "Don't worry. Here's how to sort your trash: burnable, non-burnable, plastic, etc." Finally, the server verifies the pre-registered device type and sends the response to the user in text format. The user reviews the response on their smartphone, understands the trash sorting method, and their anxiety is relieved.

[0907] Examples of prompts for generative AI models

[0908] "Describe a system that uses a sentiment analysis engine and a natural language processing engine to categorize inquiries from citizens into categories and emotions, retrieves appropriate information from a database based on these categories, and provides it to the user's device in text or audio format."

[0909] By using this prompt, you can obtain detailed information about the specific operation and concepts of the system from the generating AI model.

[0910] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0911] Step 1: Inquiry Received

[0912] 1.1 A user makes an inquiry

[0913] Users enter inquiries using smartphones, computers, or voice devices. For example, a user might enter a message such as, "Please tell me how to sort my trash."

[0914] Input: The inquiry message sent from the user's device.

[0915] Output: Query data sent from the terminal to the server.

[0916] 1.2 The terminal sends the inquiry.

[0917] The terminal sends the query data to the server.

[0918] Specific operation: The terminal sends metadata to the server, including the query content and the user's device information (e.g., IP address, device ID).

[0919] Input: User inquiry message and metadata.

[0920] Output: Query data sent to the server.

[0921] 1.3 The server receives the query

[0922] The server receives the query data sent from the terminal and generates a unique user ID.

[0923] Specific operation: The server records the query details in the logging system and generates a user ID to associate with this log.

[0924] Input: Inquiry data sent from the terminal.

[0925] Output: Query data recorded in the log and the generated user ID.

[0926] Step 2: Content Analysis and Sentiment Analysis

[0927] 2.1 The server performs natural language processing.

[0928] The server uses a natural language processing engine to parse the query content.

[0929] Specific operation: The natural language processing engine analyzes the text data and classifies the query into categories such as "garbage disposal" based on keywords and context.

[0930] Input: Query data recorded on the server.

[0931] Output: Classified category information.

[0932] 2.2 The server performs sentiment analysis

[0933] The server uses an emotion analysis engine to determine the emotions contained in the query.

[0934] Specific operation: The emotion analysis engine analyzes the tone and expression of the text to detect emotions such as "anxiety," "anger," and "joy."

[0935] Input: Query data recorded on the server.

[0936] Output: Detected emotion information.

[0937] 2.3 The server records the analysis results.

[0938] The server integrates the results of natural language processing and sentiment analysis, and logs the categories and sentiments.

[0939] Input: Classified category information and detected sentiment information.

[0940] Output: Category and sentiment information recorded in the log.

[0941] Step 3: Database Search

[0942] 3.1 The server generates the search query

[0943] The server generates search queries based on category and sentiment.

[0944] Specific operation: The server generates database search queries, such as SQL queries, and sets conditions to search for specific information related to categories and sentiments.

[0945] Input: Category and sentiment information recorded in the log.

[0946] Output: The generated search query.

[0947] 3.2 The server sends a query to the database

[0948] The server sends a search query to the database and retrieves the information.

[0949] Specific operation: The server opens a database connection and executes the generated search query against the database.

[0950] Input: The generated search query.

[0951] Output: Search results returned from the database.

[0952] 3.3 The server receives the search results

[0953] The server receives the search results returned from the database and logs them.

[0954] Input: Search results from the database.

[0955] Output: Search results recorded in the log.

[0956] Step 4: Answer Generation

[0957] 4.1 The server generates the answer

[0958] The server generates an answer based on information retrieved from the database.

[0959] Specific operation: The server analyzes the acquired information and generates an appropriate response that aligns with the user's inquiry and sentiment.

[0960] Input: Search results from the database.

[0961] Output: The generated response.

[0962] 4.2 The server adjusts responses based on emotions.

[0963] The emotion engine adjusts the tone and content of responses according to the user's emotions.

[0964] Specific operation: The server modifies the wording and tone of the response based on the detected emotion. For example, if it determines that the user is "anxious," it will add phrases such as "don't worry."

[0965] Input: Generated response content and sentiment information.

[0966] Output: Adjusted response content.

[0967] 4.3 The server formats the response.

[0968] The server formats the adjusted responses into a user-friendly format.

[0969] Specific operation: The server converts the response into text or audio format, making it easy for the user to understand.

[0970] Input: Adjusted response content.

[0971] Output: Formatted response.

[0972] Step 5: User Notifications

[0973] 5.1 The server checks the user's device type.

[0974] The server checks the device type (smartphone, voice-enabled device) of the user who has been registered in advance.

[0975] Specific action: The server checks the device information listed in the user profile.

[0976] Input: User profile data.

[0977] Output: Device type information.

[0978] 5.2 The server sends the response

[0979] The server will send the response in either text or audio format, depending on the device type.

[0980] Specific operation: The server uses the corresponding communication protocol to send text messages and voice notifications to the user's device.

[0981] Input: Formatted response and device type information.

[0982] Output: The response sent to the user's device.

[0983] 5.3 The user receives the response

[0984] Users receive and review the responses via their smartphones or voice devices.

[0985] Specific actions: The user checks the device and views or listens to received messages.

[0986] Input: Response sent from the server.

[0987] Output: Confirmation of user responses.

[0988] (Application Example 2)

[0989] 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."

[0990] Traditional customer service in brick-and-mortar stores often involves providing the same service to all customers, making it difficult to respond flexibly to customers' emotions and circumstances. Furthermore, it placed a heavy burden on staff, and there was a demand for quick and efficient responses.

[0991] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0992] In this invention, the server includes means for a user to make a query using an information processing device, means for classifying the user's query content into categories and emotions by performing natural language analysis and sentiment analysis, means for retrieving appropriate information from a database based on the categories and emotions, and means for providing the retrieved information in text or audio format in a tone appropriate to the user's emotions. This enables flexible and rapid responses that are appropriate to the customer's emotions and circumstances.

[0993] An "information processing device" is a device used by users to input or process information, such as a smartphone or a robot.

[0994] "Natural language processing" is a technology that uses computers to analyze the language that humans use on a daily basis, with the aim of understanding and structuring the content of user inquiries.

[0995] "Sentiment analysis" is a technology that analyzes the emotions contained in a user's statements and writings, and identifies emotional states such as interest, anxiety, and confusion.

[0996] A "category" is a subject or theme used to classify user inquiries, and examples include product information and return procedures.

[0997] "Tone" refers to the element of adjusting the tone and expression of a response according to the user's emotional state. This includes, for example, a gentle tone to encourage reassurance or lively expressions to pique interest.

[0998] A "database" is a collection of information in which multiple pieces of information are systematically organized and stored, and is used to retrieve appropriate information in response to a query.

[0999] To implement this invention, the following system configuration is necessary. The system provides information to customers when they make inquiries at physical stores, and optimizes the response by also considering the customer's emotions.

[1000] System Overview

[1001] 1. Inquiry reception

[1002] The server provides a means for users to make inquiries using information processing devices (e.g., smartphones or in-store robots). Inquiry data sent from these information processing devices is transmitted to the cloud server.

[1003] 2. Content Analysis and Sentiment Analysis

[1004] The server analyzes the query content using a natural language processing engine (e.g., Google Cloud Natural Language API) to extract the query content and category. It also uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions and determine their emotional state.

[1005] 3. Database Search

[1006] The server searches the database for appropriate information based on the analyzed categories and sentiments. This database contains product information, procedure instructions, store information, and more.

[1007] 4. Answer generation

[1008] The server generates a response based on the information it has acquired. It adjusts the tone and expression according to the user's emotional state. This process generates a response that makes the user feel at ease.

[1009] 5. User Notifications

[1010] The server verifies the device type of the pre-registered user (smartphone, voice-enabled device, etc.) and provides the response in the appropriate format. The user can receive and confirm the response through the information processing device.

[1011] Specific example

[1012] For example, if a user uses their smartphone in a physical store and asks, "How do I return this item?", the following process will occur:

[1013] 1. Inquiry reception

[1014] A user submits an inquiry using their smartphone. This inquiry is sent to a cloud server.

[1015] 2. Content Analysis and Sentiment Analysis

[1016] The server uses the Google Cloud Natural Language API to analyze the inquiry and categorize it as "product information." Simultaneously, it uses IBM Watson Tone Analyzer to analyze the user's emotion as "confused."

[1017] 3. Database Search

[1018] The server searches the database based on the "product information" category and the "confusion" emotion to retrieve information on appropriate return procedures.

[1019] 4. Answer generation

[1020] Based on the information it retrieves, the server generates a response with a adjusted tone, such as, "Please rest assured. For instructions on how to return this product, please see the following steps."

[1021] 5. User Notifications

[1022] The server sends the response to the user's smartphone in text format, and the user checks the response on their smartphone.

[1023] Example of a prompt

[1024] Specifically, use the following prompt statements:

[1025] "When a user inquires, 'I want to know how to return an item,' and their emotion is perceived as 'confused,' please provide specific steps on how to generate a response."

[1026] Implementing such a system will enable flexible and rapid responses tailored to the user's emotions and circumstances.

[1027] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1028] Step 1:

[1029] The user makes an inquiry using an information processing device. The user inputs an inquiry, such as "How do I return this product?", using a smartphone or an in-store robot. The input inquiry data is sent to a cloud server by the terminal. Here, the input is the user's inquiry, and the output is the data sent to the cloud server.

[1030] Step 2:

[1031] The server analyzes received query data using natural language processing and sentiment analysis. Specifically, it uses the Google Cloud Natural Language API to analyze the query content and extract categories (e.g., "product information"). It also uses IBM Watson Tone Analyzer to determine the sentiment contained in the query (e.g., "confused"). The input is the user's query data, and the output is the analyzed category and sentiment information.

[1032] Step 3:

[1033] The server searches the database for appropriate information based on the analyzed categories and sentiments. Here, the server generates a database search query and performs the search against the database. The input is category and sentiment information, and the output is the information retrieved from the database.

[1034] Step 4:

[1035] The server generates a response based on information retrieved from the database. During this process, it adjusts the tone and expression according to the analyzed emotion. For example, if the emotion "confusion" is recognized, it will generate a response in a tone such as, "Please rest assured. For instructions on how to return this product, please see the following steps." The input consists of information and emotion data retrieved from the database, while the output is the adjusted response.

[1036] Step 5:

[1037] The server pre-verifies the type of information processing device the user is using and provides the response in the appropriate format. For example, if the user is using a smartphone, the response will be sent in text format. The input consists of the response and the user's device information, and the output is a response notification in the appropriate format.

[1038] Step 6:

[1039] Users receive and confirm answers through an information processing device. Specifically, users can receive text messages on their smartphones and learn how to resolve their inquiries by reviewing their content. The input is the provided answer, and the output is the user's improved understanding and satisfaction.

[1040] 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.

[1041] 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.

[1042] 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.

[1043] [Third Embodiment]

[1044] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1045] 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.

[1046] 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).

[1047] 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.

[1048] 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.

[1049] 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).

[1050] 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.

[1051] 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.

[1052] 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.

[1053] 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.

[1054] 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.

[1055] 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".

[1056] This invention relates to a system that uses generative AI to handle counter services at city halls, and is implemented in the following form.

[1057] System Overview

[1058] This system begins with a user using a device to make an inquiry to the city hall. The user's inquiry is sent to a server and categorized using natural language processing. Based on that category, the server searches the database for appropriate information and provides the retrieved information to the user in text or audio format.

[1059] Overview of Program Processing

[1060] 1. Inquiry reception

[1061] Users can use their smartphones, computers, or voice devices to ask questions such as, "Please tell me how to sort my trash."

[1062] The terminal sends this query data to the server.

[1063] The server receives the query data, generates a unique user ID, and logs it.

[1064] 2. Content analysis

[1065] The server analyzes the received query content using a natural language processing engine.

[1066] The server classifies the data into categories such as "waste disposal" based on the analysis results.

[1067] The server logs these analysis results.

[1068] 3. Database Search

[1069] The server generates a database search query based on the analysis results.

[1070] The server sends a query to the database and searches for the appropriate answer.

[1071] 4. Answer generation

[1072] The server generates an answer based on the searched information.

[1073] The server formats the generated response into a user-friendly format.

[1074] The server logs the generated response.

[1075] 5. User Notifications

[1076] The server checks the device type (smartphone, voice-enabled device) of the pre-registered user.

[1077] The server will notify you of the response in text or audio format, depending on the device type.

[1078] The user receives the response through that device and confirms its contents.

[1079] Specific example

[1080] Inquiries about waste disposal

[1081] A user sends an inquiry using their smartphone asking, "Please tell me how to sort my trash."

[1082] The device sends this message to the server.

[1083] The server receives the message, generates a unique user ID, and logs it.

[1084] The server uses a natural language processing engine to analyze the message and categorize it as "garbage disposal".

[1085] The server queries the database for this category information and retrieves information on the appropriate sorting method.

[1086] The server generates a response based on the information it has obtained and formats it as a text message.

[1087] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[1088] The server sends the response to the user as a text message.

[1089] Users check the answers they receive on their smartphones and understand how to sort their trash.

[1090] In this way, the present invention provides a system that streamlines counter services at city halls and allows users to receive prompt assistance. This reduces waiting times at counters, alleviates the burden on staff, and improves user satisfaction.

[1091] The following describes the processing flow.

[1092] Step 1:

[1093] Users use smartphones, computers, or voice devices to enter inquiries to the city hall. For example, they might send a message like, "Please tell me how to sort my garbage."

[1094] Step 2:

[1095] The terminal sends the aforementioned query data to the server. The transmitted data includes the user's query.

[1096] Step 3:

[1097] The server receives the query data. At the same time, it generates a unique user ID to identify this query.

[1098] Step 4:

[1099] The server uses a natural language processing engine to analyze the user's query. This analysis is intended to understand the intent and content of the query.

[1100] Step 5:

[1101] The server determines the appropriate category based on the analysis results. For example, the category "waste disposal" might be determined.

[1102] Step 6:

[1103] The server logs the determined category information. This maintains a history of queries.

[1104] Step 7:

[1105] The server generates a database search query based on the category. This query is used to retrieve the appropriate information.

[1106] Step 8:

[1107] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[1108] Step 9:

[1109] The server generates a response based on information retrieved from the database. This response is a specific answer to the user's query.

[1110] Step 10:

[1111] The server formats the generated responses, for example, ensuring they are provided in a user-friendly text or audio format.

[1112] Step 11:

[1113] The server checks the user's device type. Based on pre-registered information, it determines whether it is a smartphone or a voice device.

[1114] Step 12:

[1115] The server will send a response based on the device type it has identified. If it is a smartphone, the response will be sent as a text message; if it is a voice device, the response will be sent as a voice message.

[1116] Step 13:

[1117] The user receives the answer through their device and confirms the information regarding their inquiry. For example, they might read a text message on their smartphone.

[1118] The above outlines the specific processing steps from inquiry to response. This system will streamline the city hall's counter services and allow users to receive prompt responses.

[1119] (Example 1)

[1120] 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."

[1121] In traditional local government service counters, users face long waiting times, and the burden on staff is increasing. Furthermore, the large number of inquiries by phone and email makes it difficult to respond quickly. This has led to problems such as decreased user satisfaction and operational inefficiency. The present invention aims to solve these problems and provide a system that allows users to quickly obtain the information they need and reduces the burden on staff.

[1122] 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.

[1123] In this invention, the server includes means for a user to make an inquiry to a local government using an information terminal; means for analyzing the user's inquiry using a natural language processing engine and classifying it into categories; means for searching for appropriate information from a database based on the categories; means for providing the retrieved information to the user in text or voice format; means for including the inquiry content and device information in the process of the information terminal transmitting the inquiry data to the server; means for the server to receive the inquiry data, generate a unique user ID, and record it in a log; means for the server to save the analysis results in an internal system and record them in a log; means for the server to generate an SQL query based on the category information and send it to a database; means for the server to format the generated response in text or voice format and record it in a log; and means for confirming the type of information terminal used by the user and notifying the user of the response in an appropriate format. This enables users to quickly obtain the necessary information, reduces the burden on staff, and improves operational efficiency and user satisfaction.

[1124] "User" refers to ordinary citizens or individuals who use this system to make inquiries.

[1125] "Information terminals" refer to digital devices such as smartphones, computers, tablets, and audio devices.

[1126] "Local government" refers to public institutions that provide administrative services to local residents, such as city halls and town halls.

[1127] "Inquiries" refer to questions or requests that users submit to local governments via information terminals.

[1128] A "natural language processing engine" refers to a software function that analyzes and understands the content of natural language text or audio input by a user.

[1129] A "category" refers to an item or theme used to classify inquiries (for example, waste disposal, issuance of resident registration certificates, etc.).

[1130] A "database" refers to a system that stores information for searching and retrieving appropriate information based on user queries.

[1131] A "server" refers to a central computer system that receives user inquiries, analyzes and processes them, and provides the final answer.

[1132] A "unique user ID" refers to a special identifier generated to uniquely identify each user.

[1133] A "log" refers to a file or data that records events and operations performed within a system.

[1134] A "SQL query" refers to a command with a specific syntax used to search for information within a database.

[1135] "Analysis results" refer to result information based on the understanding and classification of data obtained by a natural language processing engine.

[1136] "Text format" refers to the format of information expressed as a string of characters.

[1137] "Audio format" refers to the format in which the response is recorded or synthesized as audio.

[1138] "TTS technology" refers to the technology used to convert text into speech, or in other words, Text-to-Speech technology.

[1139] This invention relates to a system that automates and streamlines counter services at city halls. This system has a process in which a user makes an inquiry using an information terminal, a server analyzes the inquiry, and provides an appropriate answer to the user.

[1140] The overall system flow is as follows: First, the user makes an inquiry to the city hall using an information terminal (smartphone, computer, voice device, etc.). This inquiry data is sent from the terminal to the server. The server analyzes the received data and categorizes the content of the inquiry. Next, it generates an appropriate database search query to retrieve the necessary information from the database and generates the optimal response. Finally, depending on the type of device the user is using, the response is provided in either text or voice format.

[1141] Hardware and software to be used

[1142] Hardware:

[1143] Information terminals (smartphones, computers, tablets, voice devices)

[1144] Server (high-performance computer system)

[1145] software:

[1146] Natural language processing engines (Google Natural Language API, IBM Watson, etc.)

[1147] Database systems (MySQL, MongoDB)

[1148] Text-to-speech technology (such as Amazon Polly)

[1149] Log management system

[1150] Specific processing of the program

[1151] When the server receives query data from a user, it first generates a unique user ID and logs this data. Next, it uses a natural language processing engine to analyze the query content and classifies the analysis results into categories. This analysis information is also logged.

[1152] Next, the server generates a database search query based on the category information and sends the query to the database. The database then returns the relevant information. Based on this information, the server generates a response for the user and formats it in text or audio format. This response is also logged.

[1153] Finally, the server checks the device type of the pre-registered user and sends a response accordingly. The user can receive this response on their device and review its contents.

[1154] Specific example

[1155] Inquiries about waste disposal

[1156] A user sends an inquiry using their smartphone asking, "Please tell me how to sort my trash."

[1157] The device sends this message to the server.

[1158] The server receives the message, generates a unique user ID, and logs it.

[1159] The server uses a natural language processing engine to analyze the message and categorize it as "garbage disposal".

[1160] The server queries the database for this category information and retrieves information on the appropriate sorting method.

[1161] The server generates a response based on the information it has obtained and formats it as a text message.

[1162] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[1163] The server generates a text message and sends it to the user's smartphone.

[1164] Users check the answers they receive on their smartphones and understand how to sort their trash.

[1165] Example of a prompt

[1166] User: "Could you tell me about the waste sorting methods at the city hall?"

[1167] AI response: "Thank you for your inquiry. The waste sorting instructions are as follows: Please put combustible waste in the red garbage bag and non-combustible waste in the blue garbage bag. For further details, please visit the city hall website."

[1168] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1169] Step 1:

[1170] Users make inquiries to local governments using information terminals. Specifically, users type messages such as "Please tell me how to sort my garbage" into their smartphones or computers and press the send button. The data entered at this time includes the inquiry content, user ID, and device information.

[1171] Input: User inquiry details, user ID, device information

[1172] Output: JSON format query data sent to the terminal

[1173] Step 2:

[1174] The terminal sends the user's inquiry data to the server. The terminal generates JSON data containing the entered inquiry details, user ID, and device information, and sends it to the server via an HTTP request.

[1175] Input: User query data (JSON format)

[1176] Output: HTTP request sent to the server

[1177] Step 3:

[1178] The server receives the query data, generates a unique user ID, and logs it. The server analyzes the received data and logs the user ID and query details. This log is managed by an internal system.

[1179] Input: HTTP request sent from the terminal

[1180] Output: User information and query details recorded in the log file

[1181] Step 4:

[1182] The server uses a natural language processing engine to analyze the received query. The server calls a natural language processing engine, such as the Google Natural Language API, to analyze the query and identify its category.

[1183] Input: User's inquiry

[1184] Output: Analysis results by a natural language processing engine (category information)

[1185] Step 5:

[1186] The server categorizes the query content based on the analysis results and stores this information in its internal system. For example, if it is categorized as "waste disposal," that category information is recorded in the log.

[1187] Input: Analysis results from a natural language processing engine

[1188] Output: Log file containing category information

[1189] Step 6:

[1190] The server generates a database search query based on the category information. For example, it creates an SQL query for the category "Waste Disposal".

[1191] Input: Category Information

[1192] Output: Generated SQL query

[1193] Step 7:

[1194] The server sends an SQL query to the database and retrieves the search results. The database (MySQL, MongoDB, etc.) returns the corresponding information.

[1195] Input: SQL query

[1196] Output: Search results retrieved from the database

[1197] Step 8:

[1198] The server generates responses to the user based on the search results it obtains. For example, it might generate information such as, "Please put combustible waste in the red garbage bag and non-combustible waste in the blue garbage bag."

[1199] Input: Search results from database

[1200] Output: Generated response (text or audio format)

[1201] Step 9:

[1202] The server formats the generated response into text or audio format. If in audio format, it uses Text-to-Speech (TTS) technology to generate the audio data.

[1203] Input: Generated answer

[1204] Output: Formatted response (text or audio format)

[1205] Step 10:

[1206] The server verifies the user's registration information and identifies the user's device type. Depending on the device type, it sends a response as either a text message or audio data.

[1207] Input: User's device information, formatted response

[1208] Output: Message sent to the user's device

[1209] Step 11:

[1210] The system checks the response received by the user on their device. For example, it might display a message on a smartphone screen saying, "Put combustible waste in the red garbage bag, and non-combustible waste in the blue garbage bag," and the system understands the content.

[1211] Input: Response message sent from the server

[1212] Output: Answers displayed in a format that the user can see.

[1213] (Application Example 1)

[1214] 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."

[1215] Traditional counter services at service facilities struggle to provide timely and accurate information to users, resulting in long waiting times, especially during peak hours, and decreased customer satisfaction. Furthermore, this increases the burden on service providers, making efficient operations difficult. There is a need to address these challenges and provide a system that benefits both users and service providers.

[1216] 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.

[1217] In this invention, the server includes means for a user to make an inquiry to a service facility using an electronic terminal, means for classifying the user's inquiry into categories by performing natural language analysis, means for retrieving appropriate information from an information storage unit based on the categories, means for generating a unique user ID and recording it in a log, and means for providing the retrieved information to the user in text or voice format. This enables users to quickly obtain appropriate answers, reduces the burden on service providers, and improves operational efficiency and customer satisfaction.

[1218] A "user" is a person who uses an electronic terminal to make inquiries to a service facility.

[1219] An "electronic terminal" is a device used by a user to contact a service facility, and includes smartphones, computers, and other similar devices.

[1220] A "service facility" refers to a physical store or counter where a user makes an inquiry.

[1221] "Natural language processing" is the process of analyzing text and audio data entered by a user and understanding its meaning.

[1222] "Means for classifying categories" refers to a function that sorts inquiry content into specific categories based on the results of natural language processing.

[1223] The "information storage unit" refers to the database where information answering inquiries is stored.

[1224] A "unique user ID" is a unique identifier generated to identify each user's inquiry.

[1225] "Means of recording in logs" refers to a function for saving inquiry details, analysis results, and search results as records.

[1226] "Text or audio format" refers to the format of the response provided to the user, and includes both text and audio data.

[1227] This invention relates to a system that provides information quickly and appropriately to users who make inquiries to service facilities using electronic terminals. The purpose of this invention is to improve user convenience and reduce the burden on service providers.

[1228] System Overview

[1229] The system of the present invention consists of the following main components.

[1230] 1. Electronic terminals: These are hardware devices used by users to make inquiries to service facilities. Examples include smartphones and computers.

[1231] 2. Server: This is the central hardware that processes query content and retrieves and provides appropriate information. A server includes multiple software components, including a natural language processing engine (Spacy), a database (MySQL, PostgreSQL, etc.), and a web framework (Flask).

[1232] Program Processing Overview

[1233] Hardware and software

[1234] Users make inquiries to service facilities using electronic devices (e.g., smartphones). These electronic devices include specific programs (e.g., mobile apps or web applications) that are executed.

[1235] Software used by the server:

[1236] Spacy: Used for natural language processing. It analyzes user inquiries and classifies them into categories.

[1237] Flask: Functions as an HTTP server for receiving, analyzing, searching, and generating responses to queries.

[1238] Database: MySQL, PostgreSQL, or similar databases are used to store the necessary information.

[1239] Data processing and data calculation

[1240] 1. Inquiry reception

[1241] Users contact service facilities using electronic devices in text or voice format. For example, they might send a message such as, "Please tell me the current stock of the latest smartphones you sell on your smartphone."

[1242] The terminal sends the query data to the server.

[1243] 2. Content analysis

[1244] The server uses Spacy to perform natural language processing on the query content.

[1245] This process involves understanding the intent of the inquiry and classifying it into the appropriate category, such as "product inventory."

[1246] 3. Database Search

[1247] Based on the category, the server sends the generated query to the database.

[1248] Search the database for the appropriate answer, such as inventory information.

[1249] 4. Answer generation

[1250] Based on the search results, the server generates an answer in a format that is easy for the user to understand.

[1251] Responses will be formatted as text or audio.

[1252] 5. User Notifications

[1253] The server verifies the type of electronic device used by the pre-registered user and sends the data in the appropriate format.

[1254] The user receives the response on their device and confirms its contents.

[1255] Specific example

[1256] As an example, consider a case where a user asks, "Please tell me the stock of the latest smartphones sold at this store." This inquiry, sent from an electronic device, undergoes natural language processing on the server to understand its category and content. Next, a search query is executed against the database to retrieve the appropriate stock information. The retrieved information is then provided to the user's electronic device in text or audio format.

[1257] Example of a prompt

[1258] Please tell me what the latest smartphones you sell are currently in stock.

[1259] In this way, the present invention enables users to quickly obtain appropriate answers, reduces the burden on service providers, and improves operational efficiency and customer satisfaction.

[1260] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1261] Step 1:

[1262] Users make inquiries using electronic devices.

[1263] Users use electronic devices such as smartphones to input inquiries via voice or text, such as, "Please tell me the current stock of the latest smartphones sold at this store." The input data is then transmitted from the user's electronic device to the server.

[1264] Input: User's inquiry (text or voice)

[1265] Output: Query data sent to the server

[1266] Step 2:

[1267] The server performs natural language processing on the query content.

[1268] The server analyzes the received query content using a natural language processing engine (Spacy). This analysis understands the intent of the query and classifies it into the appropriate category.

[1269] Input: Inquiry data

[1270] Output: Analysis results (category information)

[1271] Specific actions:

[1272] The server uses Spacy to tokenize the received data and analyze its meaning.

[1273] The terms and context are evaluated, and a category such as "product inventory" is assigned.

[1274] Step 3:

[1275] The server generates the database search query.

[1276] Based on the analysis results, the server generates a database search query. The query is used to retrieve information related to the inquiry.

[1277] Input: Analysis results (category information)

[1278] Output: Database search query

[1279] Specific actions:

[1280] The server defines the search criteria based on category information.

[1281] Generates database search queries in formats such as SQL.

[1282] Step 4:

[1283] The server performs a database search.

[1284] The server generates queries and sends them to the database to retrieve the necessary information. For example, it can retrieve inventory information for the latest smartphones.

[1285] Input: Database search query

[1286] Output: Search results (including inventory information)

[1287] Specific actions:

[1288] The server connects to the database and executes the query.

[1289] Record the results obtained from the database.

[1290] Step 5:

[1291] The server generates a response based on the information it has searched.

[1292] The server generates answers in a user-friendly format based on information retrieved from the database. The answers are formatted in either text or audio.

[1293] Input: Search results (stock information)

[1294] Output: Generated response (text or audio)

[1295] Specific actions:

[1296] The server converts the acquired information into human-readable text.

[1297] If the answer is in text format, it will generate a formatted text.

[1298] If the response is in audio format, it will be converted from text to audio.

[1299] Step 6:

[1300] The server notifies the user of the answer.

[1301] The server verifies the type of electronic device used by the pre-registered user and sends the response to the user's electronic device in the appropriate format (text or audio).

[1302] Input: Generated response (text or audio)

[1303] Output: Response sent to the user's electronic device

[1304] Specific actions:

[1305] The server checks the user's terminal information and selects the appropriate format.

[1306] The response is sent to the user's electronic device, and the user receives and confirms it.

[1307] 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.

[1308] This invention relates to a system that uses generative AI to handle counter services at city halls, and includes a function to recognize user emotions and optimize responses accordingly. The embodiments for carrying out this invention will be described in detail below.

[1309] System Overview

[1310] This system begins with a user making an inquiry to the city hall using their device. The user's inquiry is sent to a server, where it is categorized and categorized based on natural language processing and sentiment analysis. The server then searches its database for appropriate information based on the category and sentiment, and provides the retrieved information to the user in text or audio format. The sentiment engine allows for the tone and content of the response to be adjusted based on the user's emotions.

[1311] Overview of Program Processing

[1312] 1. Inquiry reception

[1313] Users can use their smartphones, computers, or voice devices to ask questions such as, "Please tell me how to sort my trash."

[1314] The terminal sends this query data to the server.

[1315] The server receives the query data, generates a unique user ID, and logs it.

[1316] 2. Content Analysis and Sentiment Analysis

[1317] The server analyzes the received query content using a natural language processing engine. Additionally, it uses an emotion engine to analyze the emotions contained in the user's query.

[1318] For example, the question "Please tell me how to sort garbage" is classified under the category of "garbage disposal," and at the same time, the emotion associated with it is identified as "anxiety."

[1319] The server determines the category and sentiment based on the analysis results.

[1320] The server logs these analysis results.

[1321] 3. Database Search

[1322] The server generates a database search query based on category and sentiment. This query is used to retrieve the appropriate information.

[1323] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[1324] 4. Answer generation

[1325] The server generates responses based on information retrieved from the database. An emotion engine adjusts the tone and content according to the user's emotions.

[1326] For example, if the emotion of "anxiety" is recognized, the tone will be adjusted to something like, "Don't worry. Here's how to sort your trash."

[1327] The server formats the generated response into a user-friendly format.

[1328] The server logs the generated response.

[1329] 5. User Notifications

[1330] The server checks the device type (smartphone, voice-enabled device) of the pre-registered user.

[1331] The server will notify you of the response in text or audio format, depending on the device type.

[1332] The user receives the response through that device and confirms its contents.

[1333] Specific example

[1334] Inquiries about waste disposal

[1335] A user sends an inquiry via smartphone asking, "Please tell me how to sort my trash." At this time, they are feeling anxious about incorrect sorting.

[1336] The device sends this message to the server.

[1337] The server receives the message, generates a unique user ID, and logs it.

[1338] The server uses a natural language processing engine and an emotion engine to analyze the message and classify it into the category "garbage disposal" and the emotion "anxiety."

[1339] The server queries the database for this category information and sentiment information to obtain information on appropriate classification methods.

[1340] The server generates a response based on the information it obtains, adjusting the tone according to the user's mood. It formats the response as follows: "Don't worry. Here's how to separate your trash into combustible waste, non-combustible waste, plastics, etc."

[1341] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[1342] The server sends the response to the user as a text message.

[1343] Users can check the answers they receive on their smartphones, understand how to sort their trash, and have their anxieties alleviated.

[1344] Thus, this invention not only streamlines counter services at city halls and provides a system that allows users to receive prompt assistance, but also addresses users' emotions to provide more appropriate and satisfying services. As a result, waiting times at city hall counters are reduced, the burden on staff is lessened, and user satisfaction is improved.

[1345] The following describes the processing flow.

[1346] Step 1:

[1347] Users use smartphones, computers, or voice devices to enter inquiries into the city hall. For example, they might send a message like, "Please tell me how to sort my garbage." In these situations, users may be feeling anxious or confused.

[1348] Step 2:

[1349] The terminal sends the aforementioned query data to the server. The transmitted data includes the user's query.

[1350] Step 3:

[1351] The server receives the query data. Simultaneously, a unique user ID is generated to identify this query. The received data is logged.

[1352] Step 4:

[1353] The server uses a natural language processing engine to analyze the user's query. This analysis is intended to understand the intent and content of the query.

[1354] Step 5:

[1355] The server uses an emotion engine to analyze the user's emotions from their inquiry. For example, it can determine emotions such as "anxiety," "confusion," or "anger."

[1356] Step 6:

[1357] Based on the analysis results, the server categorizes user inquiries into categories such as "garbage disposal," while simultaneously recording their emotional responses.

[1358] Step 7:

[1359] The server logs category and sentiment information. This preserves the history of queries and the user's sentiment.

[1360] Step 8:

[1361] The server generates a database search query based on category and sentiment. This query is used to retrieve the appropriate information.

[1362] Step 9:

[1363] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[1364] Step 10:

[1365] The server generates responses based on information retrieved from the database. The emotion engine adjusts the tone and content according to the user's emotions. For example, if the emotion of "anxiety" is detected, a response will be generated in a tone such as, "Don't worry. Here's how to sort your trash."

[1366] Step 11:

[1367] The server formats the generated response into a user-friendly format, such as a text message or voice message.

[1368] Step 12:

[1369] The server checks the user's device type. Based on pre-registered information, it determines whether it is a smartphone or a voice device.

[1370] Step 13:

[1371] The server will send a response based on the device type it has identified. If it is a smartphone, the response will be sent as a text message; if it is a voice device, the response will be sent as a voice message.

[1372] Step 14:

[1373] The user receives the answer through their device and confirms the information regarding their inquiry. For example, they might read a text message on their smartphone to understand how to sort their trash and alleviate their concerns.

[1374] Thus, the present invention concretely realizes a series of processes from user inquiries to sentiment analysis, appropriate response generation, and notification to the user. Furthermore, by combining it with an emotion engine, it is possible to provide an optimal response that corresponds to the user's emotions.

[1375] (Example 2)

[1376] 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."

[1377] The objective of this invention is to provide a system for responding quickly and appropriately to user inquiries at city hall counter services. In particular, by providing optimal answers tailored to the user's emotions, the system aims to improve user satisfaction and reduce the burden on city hall staff.

[1378] 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.

[1379] In this invention, the server includes means for a user to make an inquiry using a device, means for performing natural language analysis on the user's inquiry and classifying it into categories and emotions, means for searching for appropriate information from a database based on the categories and emotions, means for adjusting the tone and content of the response according to the user's emotions, and means for providing the retrieved information to the user in text or audio format. This makes it possible to provide optimal information to the city hall in response to inquiries made by the user, taking emotions into consideration.

[1380] A "user" is an individual or organization that uses the system to make inquiries to the city hall.

[1381] A "device" is hardware used by a user to make inquiries, and includes smartphones, computers, voice devices, etc.

[1382] An "inquiry" refers to a question or request that a user submits to the city hall.

[1383] "Natural language processing" is the process of interpreting user inquiries and classifying them into specific categories or pieces of information.

[1384] A "category" refers to the type or field of a query classified by natural language processing.

[1385] "Emotions" refer to the psychological state inherent in a user's inquiry, and include, for example, "anxiety," "anger," and "joy."

[1386] A "database" is a digital information storage system that stores various types of information for the city hall.

[1387] "Information retrieval" is the process of finding information within a database based on specific categories or keywords.

[1388] "Adjusting tone and content according to emotions" is the process of considering the user's emotions and formulating a response using appropriate language and content.

[1389] "Text format" refers to a format that provides information as character data.

[1390] "Audio format" refers to a format in which information is provided as audio data.

[1391] This invention relates to a system that streamlines counter services at city halls, enabling users to receive prompt and appropriate assistance. In particular, it includes a function that recognizes the user's emotions and optimizes the response accordingly.

[1392] System Configuration

[1393] This system consists of the following main components:

[1394] 1. User device

[1395] Hardware such as smartphones, computers, and voice devices that users use to make inquiries.

[1396] 2. Server

[1397] This is the central system that receives user inquiries, analyzes them, retrieves information, and generates answers.

[1398] The software to be used is as follows:

[1399] Natural language processing engines: Examples) Google Cloud Natural Language API, IBM Watson NLP

[1400] Sentiment analysis engines: Examples) IBM Watson Tone Analyzer, Microsoft Azure Text Analytics

[1401] Database: e.g., MySQL, PostgreSQL

[1402] Program Processing Overview

[1403] Inquiry reception

[1404] Users make inquiries using smartphones, computers, or voice devices. For example, they might type an inquiry such as, "Please tell me how to sort my trash." This message is sent from the device to the server, which generates a unique user ID and logs it.

[1405] Content analysis and sentiment analysis

[1406] The server analyzes the received query using a natural language processing engine and determines the user's emotions using an emotion analysis engine. As a result of the analysis, the query is classified into the category of "garbage disposal," and the emotion is determined to be "anxiety."

[1407] Database Search

[1408] Based on category and sentiment, the server generates a search query and sends it to the database. The relevant information is returned from the database and logged by the server.

[1409] Answer generation

[1410] The server generates responses based on information retrieved from the database. An emotion engine adjusts the tone and content according to the user's emotions. For example, if the emotion "anxiety" is recognized, the response will be adjusted to a tone such as, "Don't worry. Here's how to separate your trash into combustible waste, non-combustible waste, plastics, etc."

[1411] User notifications

[1412] The server checks the device type of the pre-registered user and notifies them of the response in the appropriate format (text or voice). Finally, the user receives the response through their device and confirms its contents.

[1413] Specific example

[1414] Consider a scenario where a user sends a message via smartphone asking, "Please tell me how to sort my trash." The user is anxious about incorrect sorting. The device sends this message to a server, which analyzes it and categorizes it as "trash disposal" and the user's emotion, "anxiety." Using this category and emotion information, the server queries a database to retrieve information on proper sorting methods. The server then generates a response, adjusting the tone according to the user's emotion, formatting it as, "Don't worry. Here's how to sort your trash: burnable, non-burnable, plastic, etc." Finally, the server verifies the pre-registered device type and sends the response to the user in text format. The user reviews the response on their smartphone, understands the trash sorting method, and their anxiety is relieved.

[1415] Examples of prompts for generative AI models

[1416] "Describe a system that uses a sentiment analysis engine and a natural language processing engine to categorize inquiries from citizens into categories and emotions, retrieves appropriate information from a database based on these categories, and provides it to the user's device in text or audio format."

[1417] By using this prompt, you can obtain detailed information about the specific operation and concepts of the system from the generating AI model.

[1418] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1419] Step 1: Inquiry Received

[1420] 1.1 A user makes an inquiry

[1421] Users enter inquiries using smartphones, computers, or voice devices. For example, a user might enter a message such as, "Please tell me how to sort my trash."

[1422] Input: The inquiry message sent from the user's device.

[1423] Output: Query data sent from the terminal to the server.

[1424] 1.2 The terminal sends the inquiry.

[1425] The terminal sends the query data to the server.

[1426] Specific operation: The terminal sends metadata to the server, including the query content and the user's device information (e.g., IP address, device ID).

[1427] Input: User inquiry message and metadata.

[1428] Output: Query data sent to the server.

[1429] 1.3 The server receives the query

[1430] The server receives the query data sent from the terminal and generates a unique user ID.

[1431] Specific operation: The server records the query details in the logging system and generates a user ID to associate with this log.

[1432] Input: Inquiry data sent from the terminal.

[1433] Output: Query data recorded in the log and the generated user ID.

[1434] Step 2: Content Analysis and Sentiment Analysis

[1435] 2.1 The server performs natural language processing.

[1436] The server uses a natural language processing engine to parse the query content.

[1437] Specific operation: The natural language processing engine analyzes the text data and classifies the query into categories such as "garbage disposal" based on keywords and context.

[1438] Input: Query data recorded on the server.

[1439] Output: Classified category information.

[1440] 2.2 The server performs sentiment analysis

[1441] The server uses an emotion analysis engine to determine the emotions contained in the query.

[1442] Specific operation: The emotion analysis engine analyzes the tone and expression of the text to detect emotions such as "anxiety," "anger," and "joy."

[1443] Input: Query data recorded on the server.

[1444] Output: Detected emotion information.

[1445] 2.3 The server records the analysis results.

[1446] The server integrates the results of natural language processing and sentiment analysis, and logs the categories and sentiments.

[1447] Input: Classified category information and detected sentiment information.

[1448] Output: Category and sentiment information recorded in the log.

[1449] Step 3: Database Search

[1450] 3.1 The server generates the search query

[1451] The server generates search queries based on category and sentiment.

[1452] Specific operation: The server generates database search queries, such as SQL queries, and sets conditions to search for specific information related to categories and sentiments.

[1453] Input: Category and sentiment information recorded in the log.

[1454] Output: The generated search query.

[1455] 3.2 The server sends a query to the database

[1456] The server sends a search query to the database and retrieves the information.

[1457] Specific operation: The server opens a database connection and executes the generated search query against the database.

[1458] Input: The generated search query.

[1459] Output: Search results returned from the database.

[1460] 3.3 The server receives the search results

[1461] The server receives the search results returned from the database and logs them.

[1462] Input: Search results from the database.

[1463] Output: Search results recorded in the log.

[1464] Step 4: Answer Generation

[1465] 4.1 The server generates the answer

[1466] The server generates an answer based on information retrieved from the database.

[1467] Specific operation: The server analyzes the acquired information and generates an appropriate response that aligns with the user's inquiry and sentiment.

[1468] Input: Search results from the database.

[1469] Output: The generated response.

[1470] 4.2 The server adjusts responses based on emotions.

[1471] The emotion engine adjusts the tone and content of responses according to the user's emotions.

[1472] Specific operation: The server modifies the wording and tone of the response based on the detected emotion. For example, if it determines that the user is "anxious," it will add phrases such as "don't worry."

[1473] Input: Generated response content and sentiment information.

[1474] Output: Adjusted response content.

[1475] 4.3 The server formats the response.

[1476] The server formats the adjusted responses into a user-friendly format.

[1477] Specific operation: The server converts the response into text or audio format, making it easy for the user to understand.

[1478] Input: Adjusted response content.

[1479] Output: Formatted response.

[1480] Step 5: User Notifications

[1481] 5.1 The server checks the user's device type.

[1482] The server checks the device type (smartphone, voice-enabled device) of the user who has been registered in advance.

[1483] Specific action: The server checks the device information listed in the user profile.

[1484] Input: User profile data.

[1485] Output: Device type information.

[1486] 5.2 The server sends the response

[1487] The server will send the response in either text or audio format, depending on the device type.

[1488] Specific operation: The server uses the corresponding communication protocol to send text messages and voice notifications to the user's device.

[1489] Input: Formatted response and device type information.

[1490] Output: The response sent to the user's device.

[1491] 5.3 The user receives the response

[1492] Users receive and review the responses via their smartphones or voice devices.

[1493] Specific actions: The user checks the device and views or listens to received messages.

[1494] Input: Response sent from the server.

[1495] Output: Confirmation of user responses.

[1496] (Application Example 2)

[1497] 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."

[1498] Traditional customer service in brick-and-mortar stores often involves providing the same service to all customers, making it difficult to respond flexibly to customers' emotions and circumstances. Furthermore, it placed a heavy burden on staff, and there was a demand for quick and efficient responses.

[1499] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1500] In this invention, the server includes means for a user to make a query using an information processing device, means for classifying the user's query content into categories and emotions by performing natural language analysis and sentiment analysis, means for retrieving appropriate information from a database based on the categories and emotions, and means for providing the retrieved information in text or audio format in a tone appropriate to the user's emotions. This enables flexible and rapid responses that are appropriate to the customer's emotions and circumstances.

[1501] An "information processing device" is a device used by users to input or process information, such as a smartphone or a robot.

[1502] "Natural language processing" is a technology that uses computers to analyze the language that humans use on a daily basis, with the aim of understanding and structuring the content of user inquiries.

[1503] "Sentiment analysis" is a technology that analyzes the emotions contained in a user's statements and writings, and identifies emotional states such as interest, anxiety, and confusion.

[1504] A "category" is a subject or theme used to classify user inquiries, and examples include product information and return procedures.

[1505] "Tone" refers to the element of adjusting the tone and expression of a response according to the user's emotional state. This includes, for example, a gentle tone to encourage reassurance or lively expressions to pique interest.

[1506] A "database" is a collection of information in which multiple pieces of information are systematically organized and stored, and is used to retrieve appropriate information in response to a query.

[1507] To implement this invention, the following system configuration is necessary. The system provides information to customers when they make inquiries at physical stores, and optimizes the response by also considering the customer's emotions.

[1508] System Overview

[1509] 1. Inquiry reception

[1510] The server provides a means for users to make inquiries using information processing devices (e.g., smartphones or in-store robots). Inquiry data sent from these information processing devices is transmitted to the cloud server.

[1511] 2. Content Analysis and Sentiment Analysis

[1512] The server analyzes the query content using a natural language processing engine (e.g., Google Cloud Natural Language API) to extract the query content and category. It also uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions and determine their emotional state.

[1513] 3. Database Search

[1514] The server searches the database for appropriate information based on the analyzed categories and sentiments. This database contains product information, procedure instructions, store information, and more.

[1515] 4. Answer generation

[1516] The server generates a response based on the information it has acquired. It adjusts the tone and expression according to the user's emotional state. This process generates a response that makes the user feel at ease.

[1517] 5. User Notifications

[1518] The server verifies the device type of the pre-registered user (smartphone, voice-enabled device, etc.) and provides the response in the appropriate format. The user can receive and confirm the response through the information processing device.

[1519] Specific example

[1520] For example, if a user uses their smartphone in a physical store and asks, "How do I return this item?", the following process will occur:

[1521] 1. Inquiry reception

[1522] A user submits an inquiry using their smartphone. This inquiry is sent to a cloud server.

[1523] 2. Content Analysis and Sentiment Analysis

[1524] The server uses the Google Cloud Natural Language API to analyze the inquiry and categorize it as "product information." Simultaneously, it uses IBM Watson Tone Analyzer to analyze the user's emotion as "confused."

[1525] 3. Database Search

[1526] The server searches the database based on the "product information" category and the "confusion" emotion to retrieve information on appropriate return procedures.

[1527] 4. Answer generation

[1528] Based on the information it retrieves, the server generates a response with a adjusted tone, such as, "Please rest assured. For instructions on how to return this product, please see the following steps."

[1529] 5. User Notifications

[1530] The server sends the response to the user's smartphone in text format, and the user checks the response on their smartphone.

[1531] Example of a prompt

[1532] Specifically, use the following prompt statements:

[1533] "When a user inquires, 'I want to know how to return an item,' and their emotion is perceived as 'confused,' please provide specific steps on how to generate a response."

[1534] Implementing such a system will enable flexible and rapid responses tailored to the user's emotions and circumstances.

[1535] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1536] Step 1:

[1537] The user makes an inquiry using an information processing device. The user inputs an inquiry, such as "How do I return this product?", using a smartphone or an in-store robot. The input inquiry data is sent to a cloud server by the terminal. Here, the input is the user's inquiry, and the output is the data sent to the cloud server.

[1538] Step 2:

[1539] The server analyzes received query data using natural language processing and sentiment analysis. Specifically, it uses the Google Cloud Natural Language API to analyze the query content and extract categories (e.g., "product information"). It also uses IBM Watson Tone Analyzer to determine the sentiment contained in the query (e.g., "confused"). The input is the user's query data, and the output is the analyzed category and sentiment information.

[1540] Step 3:

[1541] The server searches the database for appropriate information based on the analyzed categories and sentiments. Here, the server generates a database search query and performs the search against the database. The input is category and sentiment information, and the output is the information retrieved from the database.

[1542] Step 4:

[1543] The server generates a response based on information retrieved from the database. During this process, it adjusts the tone and expression according to the analyzed emotion. For example, if the emotion "confusion" is recognized, it will generate a response in a tone such as, "Please rest assured. For instructions on how to return this product, please see the following steps." The input consists of information and emotion data retrieved from the database, while the output is the adjusted response.

[1544] Step 5:

[1545] The server pre-verifies the type of information processing device the user is using and provides the response in the appropriate format. For example, if the user is using a smartphone, the response will be sent in text format. The input consists of the response and the user's device information, and the output is a response notification in the appropriate format.

[1546] Step 6:

[1547] Users receive and confirm answers through an information processing device. Specifically, users can receive text messages on their smartphones and learn how to resolve their inquiries by reviewing their content. The input is the provided answer, and the output is the user's improved understanding and satisfaction.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] [Fourth Embodiment]

[1552] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1553] 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.

[1554] 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).

[1555] 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.

[1556] 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.

[1557] 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).

[1558] 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.

[1559] 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.

[1560] 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.

[1561] 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.

[1562] 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.

[1563] 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.

[1564] 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".

[1565] This invention relates to a system that uses generative AI to handle counter services at city halls, and is implemented in the following form.

[1566] System Overview

[1567] This system begins with a user using a device to make an inquiry to the city hall. The user's inquiry is sent to a server and categorized using natural language processing. Based on that category, the server searches the database for appropriate information and provides the retrieved information to the user in text or audio format.

[1568] Overview of Program Processing

[1569] 1. Inquiry reception

[1570] Users can use their smartphones, computers, or voice devices to ask questions such as, "Please tell me how to sort my trash."

[1571] The terminal sends this query data to the server.

[1572] The server receives the query data, generates a unique user ID, and logs it.

[1573] 2. Content analysis

[1574] The server analyzes the received query content using a natural language processing engine.

[1575] The server classifies the data into categories such as "waste disposal" based on the analysis results.

[1576] The server logs these analysis results.

[1577] 3. Database Search

[1578] The server generates a database search query based on the analysis results.

[1579] The server sends a query to the database and searches for the appropriate answer.

[1580] 4. Answer generation

[1581] The server generates an answer based on the searched information.

[1582] The server formats the generated response into a user-friendly format.

[1583] The server logs the generated response.

[1584] 5. User Notifications

[1585] The server checks the device type (smartphone, voice-enabled device) of the pre-registered user.

[1586] The server will notify you of the response in text or audio format, depending on the device type.

[1587] The user receives the response through that device and confirms its contents.

[1588] Specific example

[1589] Inquiries about waste disposal

[1590] A user sends an inquiry using their smartphone asking, "Please tell me how to sort my trash."

[1591] The device sends this message to the server.

[1592] The server receives the message, generates a unique user ID, and logs it.

[1593] The server uses a natural language processing engine to analyze the message and categorize it as "garbage disposal".

[1594] The server queries the database for this category information and retrieves information on the appropriate sorting method.

[1595] The server generates a response based on the information it has obtained and formats it as a text message.

[1596] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[1597] The server sends the response to the user as a text message.

[1598] Users check the answers they receive on their smartphones and understand how to sort their trash.

[1599] In this way, the present invention provides a system that streamlines counter services at city halls and allows users to receive prompt assistance. This reduces waiting times at counters, alleviates the burden on staff, and improves user satisfaction.

[1600] The following describes the processing flow.

[1601] Step 1:

[1602] Users use smartphones, computers, or voice devices to enter inquiries to the city hall. For example, they might send a message like, "Please tell me how to sort my garbage."

[1603] Step 2:

[1604] The terminal sends the aforementioned query data to the server. The transmitted data includes the user's query.

[1605] Step 3:

[1606] The server receives the query data. At the same time, it generates a unique user ID to identify this query.

[1607] Step 4:

[1608] The server uses a natural language processing engine to analyze the user's query. This analysis is intended to understand the intent and content of the query.

[1609] Step 5:

[1610] The server determines the appropriate category based on the analysis results. For example, the category "waste disposal" might be determined.

[1611] Step 6:

[1612] The server logs the determined category information. This maintains a history of queries.

[1613] Step 7:

[1614] The server generates a database search query based on the category. This query is used to retrieve the appropriate information.

[1615] Step 8:

[1616] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[1617] Step 9:

[1618] The server generates a response based on information retrieved from the database. This response is a specific answer to the user's query.

[1619] Step 10:

[1620] The server formats the generated responses, for example, ensuring they are provided in a user-friendly text or audio format.

[1621] Step 11:

[1622] The server checks the user's device type. Based on pre-registered information, it determines whether it is a smartphone or a voice device.

[1623] Step 12:

[1624] The server will send a response based on the device type it has identified. If it is a smartphone, the response will be sent as a text message; if it is a voice device, the response will be sent as a voice message.

[1625] Step 13:

[1626] The user receives the answer through their device and confirms the information regarding their inquiry. For example, they might read a text message on their smartphone.

[1627] The above outlines the specific processing steps from inquiry to response. This system will streamline the city hall's counter services and allow users to receive prompt responses.

[1628] (Example 1)

[1629] 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".

[1630] In traditional local government service counters, users face long waiting times, and the burden on staff is increasing. Furthermore, the large number of inquiries by phone and email makes it difficult to respond quickly. This has led to problems such as decreased user satisfaction and operational inefficiency. The present invention aims to solve these problems and provide a system that allows users to quickly obtain the information they need and reduces the burden on staff.

[1631] 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.

[1632] In this invention, the server includes means for a user to make an inquiry to a local government using an information terminal; means for analyzing the user's inquiry using a natural language processing engine and classifying it into categories; means for searching for appropriate information from a database based on the categories; means for providing the retrieved information to the user in text or voice format; means for including the inquiry content and device information in the process of the information terminal transmitting the inquiry data to the server; means for the server to receive the inquiry data, generate a unique user ID, and record it in a log; means for the server to save the analysis results in an internal system and record them in a log; means for the server to generate an SQL query based on the category information and send it to a database; means for the server to format the generated response in text or voice format and record it in a log; and means for confirming the type of information terminal used by the user and notifying the user of the response in an appropriate format. This enables users to quickly obtain the necessary information, reduces the burden on staff, and improves operational efficiency and user satisfaction.

[1633] "User" refers to ordinary citizens or individuals who use this system to make inquiries.

[1634] "Information terminals" refer to digital devices such as smartphones, computers, tablets, and audio devices.

[1635] "Local government" refers to public institutions that provide administrative services to local residents, such as city halls and town halls.

[1636] "Inquiries" refer to questions or requests that users submit to local governments via information terminals.

[1637] A "natural language processing engine" refers to a software function that analyzes and understands the content of natural language text or audio input by a user.

[1638] A "category" refers to an item or theme used to classify inquiries (for example, waste disposal, issuance of resident registration certificates, etc.).

[1639] A "database" refers to a system that stores information for searching and retrieving appropriate information based on user queries.

[1640] A "server" refers to a central computer system that receives user inquiries, analyzes and processes them, and provides the final answer.

[1641] A "unique user ID" refers to a special identifier generated to uniquely identify each user.

[1642] A "log" refers to a file or data that records events and operations performed within a system.

[1643] A "SQL query" refers to a command with a specific syntax used to search for information within a database.

[1644] "Analysis results" refer to result information based on the understanding and classification of data obtained by a natural language processing engine.

[1645] "Text format" refers to the format of information expressed as a string of characters.

[1646] "Audio format" refers to the format in which the response is recorded or synthesized as audio.

[1647] "TTS technology" refers to the technology used to convert text into speech, or in other words, Text-to-Speech technology.

[1648] This invention relates to a system that automates and streamlines counter services at city halls. This system has a process in which a user makes an inquiry using an information terminal, a server analyzes the inquiry, and provides an appropriate answer to the user.

[1649] The overall system flow is as follows: First, the user makes an inquiry to the city hall using an information terminal (smartphone, computer, voice device, etc.). This inquiry data is sent from the terminal to the server. The server analyzes the received data and categorizes the content of the inquiry. Next, it generates an appropriate database search query to retrieve the necessary information from the database and generates the optimal response. Finally, depending on the type of device the user is using, the response is provided in either text or voice format.

[1650] Hardware and software to be used

[1651] Hardware:

[1652] Information terminals (smartphones, computers, tablets, voice devices)

[1653] Server (high-performance computer system)

[1654] software:

[1655] Natural language processing engines (Google Natural Language API, IBM Watson, etc.)

[1656] Database systems (MySQL, MongoDB)

[1657] Text-to-speech technology (such as Amazon Polly)

[1658] Log management system

[1659] Specific processing of the program

[1660] When the server receives query data from a user, it first generates a unique user ID and logs this data. Next, it uses a natural language processing engine to analyze the query content and classifies the analysis results into categories. This analysis information is also logged.

[1661] Next, the server generates a database search query based on the category information and sends the query to the database. The database then returns the relevant information. Based on this information, the server generates a response for the user and formats it in text or audio format. This response is also logged.

[1662] Finally, the server checks the device type of the pre-registered user and sends a response accordingly. The user can receive this response on their device and review its contents.

[1663] Specific example

[1664] Inquiries about waste disposal

[1665] A user sends an inquiry using their smartphone asking, "Please tell me how to sort my trash."

[1666] The device sends this message to the server.

[1667] The server receives the message, generates a unique user ID, and logs it.

[1668] The server uses a natural language processing engine to analyze the message and categorize it as "garbage disposal".

[1669] The server queries the database for this category information and retrieves information on the appropriate sorting method.

[1670] The server generates a response based on the information it has obtained and formats it as a text message.

[1671] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[1672] The server generates a text message and sends it to the user's smartphone.

[1673] Users check the answers they receive on their smartphones and understand how to sort their trash.

[1674] Example of a prompt

[1675] User: "Could you tell me about the waste sorting methods at the city hall?"

[1676] AI response: "Thank you for your inquiry. The waste sorting instructions are as follows: Please put combustible waste in the red garbage bag and non-combustible waste in the blue garbage bag. For further details, please visit the city hall website."

[1677] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1678] Step 1:

[1679] Users make inquiries to local governments using information terminals. Specifically, users type messages such as "Please tell me how to sort my garbage" into their smartphones or computers and press the send button. The data entered at this time includes the inquiry content, user ID, and device information.

[1680] Input: User inquiry details, user ID, device information

[1681] Output: JSON format query data sent to the terminal

[1682] Step 2:

[1683] The terminal sends the user's inquiry data to the server. The terminal generates JSON data containing the entered inquiry details, user ID, and device information, and sends it to the server via an HTTP request.

[1684] Input: User query data (JSON format)

[1685] Output: HTTP request sent to the server

[1686] Step 3:

[1687] The server receives the query data, generates a unique user ID, and logs it. The server analyzes the received data and logs the user ID and query details. This log is managed by an internal system.

[1688] Input: HTTP request sent from the terminal

[1689] Output: User information and query details recorded in the log file

[1690] Step 4:

[1691] The server uses a natural language processing engine to analyze the received query. The server calls a natural language processing engine, such as the Google Natural Language API, to analyze the query and identify its category.

[1692] Input: User's inquiry

[1693] Output: Analysis results by a natural language processing engine (category information)

[1694] Step 5:

[1695] The server categorizes the query content based on the analysis results and stores this information in its internal system. For example, if it is categorized as "waste disposal," that category information is recorded in the log.

[1696] Input: Analysis results from a natural language processing engine

[1697] Output: Log file containing category information

[1698] Step 6:

[1699] The server generates a database search query based on the category information. For example, it creates an SQL query for the category "Waste Disposal".

[1700] Input: Category Information

[1701] Output: Generated SQL query

[1702] Step 7:

[1703] The server sends an SQL query to the database and retrieves the search results. The database (MySQL, MongoDB, etc.) returns the corresponding information.

[1704] Input: SQL query

[1705] Output: Search results retrieved from the database

[1706] Step 8:

[1707] The server generates responses to the user based on the search results it obtains. For example, it might generate information such as, "Please put combustible waste in the red garbage bag and non-combustible waste in the blue garbage bag."

[1708] Input: Search results from database

[1709] Output: Generated response (text or audio format)

[1710] Step 9:

[1711] The server formats the generated response into text or audio format. If in audio format, it uses Text-to-Speech (TTS) technology to generate the audio data.

[1712] Input: Generated answer

[1713] Output: Formatted response (text or audio format)

[1714] Step 10:

[1715] The server verifies the user's registration information and identifies the user's device type. Depending on the device type, it sends a response as either a text message or audio data.

[1716] Input: User's device information, formatted response

[1717] Output: Message sent to the user's device

[1718] Step 11:

[1719] The system checks the response received by the user on their device. For example, it might display a message on a smartphone screen saying, "Put combustible waste in the red garbage bag, and non-combustible waste in the blue garbage bag," and the system understands the content.

[1720] Input: Response message sent from the server

[1721] Output: Answers displayed in a format that the user can see.

[1722] (Application Example 1)

[1723] 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".

[1724] Traditional counter services at service facilities struggle to provide timely and accurate information to users, resulting in long waiting times, especially during peak hours, and decreased customer satisfaction. Furthermore, this increases the burden on service providers, making efficient operations difficult. There is a need to address these challenges and provide a system that benefits both users and service providers.

[1725] 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.

[1726] In this invention, the server includes means for a user to make an inquiry to a service facility using an electronic terminal, means for classifying the user's inquiry into categories by performing natural language analysis, means for retrieving appropriate information from an information storage unit based on the categories, means for generating a unique user ID and recording it in a log, and means for providing the retrieved information to the user in text or voice format. This enables users to quickly obtain appropriate answers, reduces the burden on service providers, and improves operational efficiency and customer satisfaction.

[1727] A "user" is a person who uses an electronic terminal to make inquiries to a service facility.

[1728] An "electronic terminal" is a device used by a user to contact a service facility, and includes smartphones, computers, and other similar devices.

[1729] A "service facility" refers to a physical store or counter where a user makes an inquiry.

[1730] "Natural language processing" is the process of analyzing text and audio data entered by a user and understanding its meaning.

[1731] "Means for classifying categories" refers to a function that sorts inquiry content into specific categories based on the results of natural language processing.

[1732] The "information storage unit" refers to the database where information answering inquiries is stored.

[1733] A "unique user ID" is a unique identifier generated to identify each user's inquiry.

[1734] "Means of recording in logs" refers to a function for saving inquiry details, analysis results, and search results as records.

[1735] "Text or audio format" refers to the format of the response provided to the user, and includes both text and audio data.

[1736] This invention relates to a system that provides information quickly and appropriately to users who make inquiries to service facilities using electronic terminals. The purpose of this invention is to improve user convenience and reduce the burden on service providers.

[1737] System Overview

[1738] The system of the present invention consists of the following main components.

[1739] 1. Electronic terminals: These are hardware devices used by users to make inquiries to service facilities. Examples include smartphones and computers.

[1740] 2. Server: This is the central hardware that processes query content and retrieves and provides appropriate information. A server includes multiple software components, including a natural language processing engine (Spacy), a database (MySQL, PostgreSQL, etc.), and a web framework (Flask).

[1741] Program Processing Overview

[1742] Hardware and software

[1743] Users make inquiries to service facilities using electronic devices (e.g., smartphones). These electronic devices include specific programs (e.g., mobile apps or web applications) that are executed.

[1744] Software used by the server:

[1745] Spacy: Used for natural language processing. It analyzes user inquiries and classifies them into categories.

[1746] Flask: Functions as an HTTP server for receiving, analyzing, searching, and generating responses to queries.

[1747] Database: MySQL, PostgreSQL, or similar databases are used to store the necessary information.

[1748] Data processing and data calculation

[1749] 1. Inquiry reception

[1750] Users contact service facilities using electronic devices in text or voice format. For example, they might send a message such as, "Please tell me the current stock of the latest smartphones you sell on your smartphone."

[1751] The terminal sends the query data to the server.

[1752] 2. Content analysis

[1753] The server uses Spacy to perform natural language processing on the query content.

[1754] This process involves understanding the intent of the inquiry and classifying it into the appropriate category, such as "product inventory."

[1755] 3. Database Search

[1756] Based on the category, the server sends the generated query to the database.

[1757] Search the database for the appropriate answer, such as inventory information.

[1758] 4. Answer generation

[1759] Based on the search results, the server generates an answer in a format that is easy for the user to understand.

[1760] Responses will be formatted as text or audio.

[1761] 5. User Notifications

[1762] The server verifies the type of electronic device used by the pre-registered user and sends the data in the appropriate format.

[1763] The user receives the response on their device and confirms its contents.

[1764] Specific example

[1765] As an example, consider a case where a user asks, "Please tell me the stock of the latest smartphones sold at this store." This inquiry, sent from an electronic device, undergoes natural language processing on the server to understand its category and content. Next, a search query is executed against the database to retrieve the appropriate stock information. The retrieved information is then provided to the user's electronic device in text or audio format.

[1766] Example of a prompt

[1767] Please tell me what the latest smartphones you sell are currently in stock.

[1768] In this way, the present invention enables users to quickly obtain appropriate answers, reduces the burden on service providers, and improves operational efficiency and customer satisfaction.

[1769] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1770] Step 1:

[1771] Users make inquiries using electronic devices.

[1772] Users use electronic devices such as smartphones to input inquiries via voice or text, such as, "Please tell me the current stock of the latest smartphones sold at this store." The input data is then transmitted from the user's electronic device to the server.

[1773] Input: User's inquiry (text or voice)

[1774] Output: Query data sent to the server

[1775] Step 2:

[1776] The server performs natural language processing on the query content.

[1777] The server analyzes the received query content using a natural language processing engine (Spacy). This analysis understands the intent of the query and classifies it into the appropriate category.

[1778] Input: Inquiry data

[1779] Output: Analysis results (category information)

[1780] Specific actions:

[1781] The server uses Spacy to tokenize the received data and analyze its meaning.

[1782] The terms and context are evaluated, and a category such as "product inventory" is assigned.

[1783] Step 3:

[1784] The server generates the database search query.

[1785] Based on the analysis results, the server generates a database search query. The query is used to retrieve information related to the inquiry.

[1786] Input: Analysis results (category information)

[1787] Output: Database search query

[1788] Specific actions:

[1789] The server defines the search criteria based on category information.

[1790] Generates database search queries in formats such as SQL.

[1791] Step 4:

[1792] The server performs a database search.

[1793] The server generates queries and sends them to the database to retrieve the necessary information. For example, it can retrieve inventory information for the latest smartphones.

[1794] Input: Database search query

[1795] Output: Search results (including inventory information)

[1796] Specific actions:

[1797] The server connects to the database and executes the query.

[1798] Record the results obtained from the database.

[1799] Step 5:

[1800] The server generates a response based on the information it has searched.

[1801] The server generates answers in a user-friendly format based on information retrieved from the database. The answers are formatted in either text or audio.

[1802] Input: Search results (stock information)

[1803] Output: Generated response (text or audio)

[1804] Specific actions:

[1805] The server converts the acquired information into human-readable text.

[1806] If the answer is in text format, it will generate a formatted text.

[1807] If the response is in audio format, it will be converted from text to audio.

[1808] Step 6:

[1809] The server notifies the user of the answer.

[1810] The server verifies the type of electronic device used by the pre-registered user and sends the response to the user's electronic device in the appropriate format (text or audio).

[1811] Input: Generated response (text or audio)

[1812] Output: Response sent to the user's electronic device

[1813] Specific actions:

[1814] The server checks the user's terminal information and selects the appropriate format.

[1815] The response is sent to the user's electronic device, and the user receives and confirms it.

[1816] 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.

[1817] This invention relates to a system that uses generative AI to handle counter services at city halls, and includes a function to recognize user emotions and optimize responses accordingly. The embodiments for carrying out this invention will be described in detail below.

[1818] System Overview

[1819] This system begins with a user making an inquiry to the city hall using their device. The user's inquiry is sent to a server, where it is categorized and categorized based on natural language processing and sentiment analysis. The server then searches its database for appropriate information based on the category and sentiment, and provides the retrieved information to the user in text or audio format. The sentiment engine allows for the tone and content of the response to be adjusted based on the user's emotions.

[1820] Overview of Program Processing

[1821] 1. Inquiry reception

[1822] Users can use their smartphones, computers, or voice devices to ask questions such as, "Please tell me how to sort my trash."

[1823] The terminal sends this query data to the server.

[1824] The server receives the query data, generates a unique user ID, and logs it.

[1825] 2. Content Analysis and Sentiment Analysis

[1826] The server analyzes the received query content using a natural language processing engine. Additionally, it uses an emotion engine to analyze the emotions contained in the user's query.

[1827] For example, the question "Please tell me how to sort garbage" is classified under the category of "garbage disposal," and at the same time, the emotion associated with it is identified as "anxiety."

[1828] The server determines the category and sentiment based on the analysis results.

[1829] The server logs these analysis results.

[1830] 3. Database Search

[1831] The server generates a database search query based on category and sentiment. This query is used to retrieve the appropriate information.

[1832] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[1833] 4. Answer generation

[1834] The server generates responses based on information retrieved from the database. An emotion engine adjusts the tone and content according to the user's emotions.

[1835] For example, if the emotion of "anxiety" is recognized, the tone will be adjusted to something like, "Don't worry. Here's how to sort your trash."

[1836] The server formats the generated response into a user-friendly format.

[1837] The server logs the generated response.

[1838] 5. User Notifications

[1839] The server checks the device type (smartphone, voice-enabled device) of the pre-registered user.

[1840] The server will notify you of the response in text or audio format, depending on the device type.

[1841] The user receives the response through that device and confirms its contents.

[1842] Specific example

[1843] Inquiries about waste disposal

[1844] A user sends an inquiry via smartphone asking, "Please tell me how to sort my trash." At this time, they are feeling anxious about incorrect sorting.

[1845] The device sends this message to the server.

[1846] The server receives the message, generates a unique user ID, and logs it.

[1847] The server uses a natural language processing engine and an emotion engine to analyze the message and classify it into the category "garbage disposal" and the emotion "anxiety."

[1848] The server queries the database for this category information and sentiment information to obtain information on appropriate classification methods.

[1849] The server generates a response based on the information it obtains, adjusting the tone according to the user's mood. It formats the response as follows: "Don't worry. Here's how to separate your trash into combustible waste, non-combustible waste, plastics, etc."

[1850] The server checks the device type of the pre-registered user and confirms that it is a smartphone.

[1851] The server sends the response to the user as a text message.

[1852] Users can check the answers they receive on their smartphones, understand how to sort their trash, and have their anxieties alleviated.

[1853] Thus, this invention not only streamlines counter services at city halls and provides a system that allows users to receive prompt assistance, but also addresses users' emotions to provide more appropriate and satisfying services. As a result, waiting times at city hall counters are reduced, the burden on staff is lessened, and user satisfaction is improved.

[1854] The following describes the processing flow.

[1855] Step 1:

[1856] Users use smartphones, computers, or voice devices to enter inquiries into the city hall. For example, they might send a message like, "Please tell me how to sort my garbage." In these situations, users may be feeling anxious or confused.

[1857] Step 2:

[1858] The terminal sends the aforementioned query data to the server. The transmitted data includes the user's query.

[1859] Step 3:

[1860] The server receives the query data. Simultaneously, a unique user ID is generated to identify this query. The received data is logged.

[1861] Step 4:

[1862] The server uses a natural language processing engine to analyze the user's query. This analysis is intended to understand the intent and content of the query.

[1863] Step 5:

[1864] The server uses an emotion engine to analyze the user's emotions from their inquiry. For example, it can determine emotions such as "anxiety," "confusion," or "anger."

[1865] Step 6:

[1866] Based on the analysis results, the server categorizes user inquiries into categories such as "garbage disposal," while simultaneously recording their emotional responses.

[1867] Step 7:

[1868] The server logs category and sentiment information. This preserves the history of queries and the user's sentiment.

[1869] Step 8:

[1870] The server generates a database search query based on category and sentiment. This query is used to retrieve the appropriate information.

[1871] Step 9:

[1872] The server sends the generated query to the database and performs the search. The database returns the relevant information.

[1873] Step 10:

[1874] The server generates responses based on information retrieved from the database. The emotion engine adjusts the tone and content according to the user's emotions. For example, if the emotion of "anxiety" is detected, a response will be generated in a tone such as, "Don't worry. Here's how to sort your trash."

[1875] Step 11:

[1876] The server formats the generated response into a user-friendly format, such as a text message or voice message.

[1877] Step 12:

[1878] The server checks the user's device type. Based on pre-registered information, it determines whether it is a smartphone or a voice device.

[1879] Step 13:

[1880] The server will send a response based on the device type it has identified. If it is a smartphone, the response will be sent as a text message; if it is a voice device, the response will be sent as a voice message.

[1881] Step 14:

[1882] The user receives the answer through their device and confirms the information regarding their inquiry. For example, they might read a text message on their smartphone to understand how to sort their trash and alleviate their concerns.

[1883] Thus, the present invention concretely realizes a series of processes from user inquiries to sentiment analysis, appropriate response generation, and notification to the user. Furthermore, by combining it with an emotion engine, it is possible to provide an optimal response that corresponds to the user's emotions.

[1884] (Example 2)

[1885] 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".

[1886] The objective of this invention is to provide a system for responding quickly and appropriately to user inquiries at city hall counter services. In particular, by providing optimal answers tailored to the user's emotions, the system aims to improve user satisfaction and reduce the burden on city hall staff.

[1887] 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.

[1888] In this invention, the server includes means for a user to make an inquiry using a device, means for performing natural language analysis on the user's inquiry and classifying it into categories and emotions, means for searching for appropriate information from a database based on the categories and emotions, means for adjusting the tone and content of the response according to the user's emotions, and means for providing the retrieved information to the user in text or audio format. This makes it possible to provide optimal information to the city hall in response to inquiries made by the user, taking emotions into consideration.

[1889] A "user" is an individual or organization that uses the system to make inquiries to the city hall.

[1890] A "device" is hardware used by a user to make inquiries, and includes smartphones, computers, voice devices, etc.

[1891] An "inquiry" refers to a question or request that a user submits to the city hall.

[1892] "Natural language processing" is the process of interpreting user inquiries and classifying them into specific categories or pieces of information.

[1893] A "category" refers to the type or field of a query classified by natural language processing.

[1894] "Emotions" refer to the psychological state inherent in a user's inquiry, and include, for example, "anxiety," "anger," and "joy."

[1895] A "database" is a digital information storage system that stores various types of information for the city hall.

[1896] "Information retrieval" is the process of finding information within a database based on specific categories or keywords.

[1897] "Adjusting tone and content according to emotions" is the process of considering the user's emotions and formulating a response using appropriate language and content.

[1898] "Text format" refers to a format that provides information as character data.

[1899] "Audio format" refers to a format in which information is provided as audio data.

[1900] This invention relates to a system that streamlines counter services at city halls, enabling users to receive prompt and appropriate assistance. In particular, it includes a function that recognizes the user's emotions and optimizes the response accordingly.

[1901] System Configuration

[1902] This system consists of the following main components:

[1903] 1. User device

[1904] Hardware such as smartphones, computers, and voice devices that users use to make inquiries.

[1905] 2. Server

[1906] This is the central system that receives user inquiries, analyzes them, retrieves information, and generates answers.

[1907] The software to be used is as follows:

[1908] Natural language processing engines: Examples) Google Cloud Natural Language API, IBM Watson NLP

[1909] Sentiment analysis engines: Examples) IBM Watson Tone Analyzer, Microsoft Azure Text Analytics

[1910] Database: e.g., MySQL, PostgreSQL

[1911] Program Processing Overview

[1912] Inquiry reception

[1913] Users make inquiries using smartphones, computers, or voice devices. For example, they might type an inquiry such as, "Please tell me how to sort my trash." This message is sent from the device to the server, which generates a unique user ID and logs it.

[1914] Content analysis and sentiment analysis

[1915] The server analyzes the received query using a natural language processing engine and determines the user's emotions using an emotion analysis engine. As a result of the analysis, the query is classified into the category of "garbage disposal," and the emotion is determined to be "anxiety."

[1916] Database Search

[1917] Based on category and sentiment, the server generates a search query and sends it to the database. The relevant information is returned from the database and logged by the server.

[1918] Answer generation

[1919] The server generates responses based on information retrieved from the database. An emotion engine adjusts the tone and content according to the user's emotions. For example, if the emotion "anxiety" is recognized, the response will be adjusted to a tone such as, "Don't worry. Here's how to separate your trash into combustible waste, non-combustible waste, plastics, etc."

[1920] User notifications

[1921] The server checks the device type of the pre-registered user and notifies them of the response in the appropriate format (text or voice). Finally, the user receives the response through their device and confirms its contents.

[1922] Specific example

[1923] Consider a scenario where a user sends a message via smartphone asking, "Please tell me how to sort my trash." The user is anxious about incorrect sorting. The device sends this message to a server, which analyzes it and categorizes it as "trash disposal" and the user's emotion, "anxiety." Using this category and emotion information, the server queries a database to retrieve information on proper sorting methods. The server then generates a response, adjusting the tone according to the user's emotion, formatting it as, "Don't worry. Here's how to sort your trash: burnable, non-burnable, plastic, etc." Finally, the server verifies the pre-registered device type and sends the response to the user in text format. The user reviews the response on their smartphone, understands the trash sorting method, and their anxiety is relieved.

[1924] Examples of prompts for generative AI models

[1925] "Describe a system that uses a sentiment analysis engine and a natural language processing engine to categorize inquiries from citizens into categories and emotions, retrieves appropriate information from a database based on these categories, and provides it to the user's device in text or audio format."

[1926] By using this prompt, you can obtain detailed information about the specific operation and concepts of the system from the generating AI model.

[1927] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1928] Step 1: Inquiry Received

[1929] 1.1 A user makes an inquiry

[1930] Users enter inquiries using smartphones, computers, or voice devices. For example, a user might enter a message such as, "Please tell me how to sort my trash."

[1931] Input: The inquiry message sent from the user's device.

[1932] Output: Query data sent from the terminal to the server.

[1933] 1.2 The terminal sends the inquiry.

[1934] The terminal sends the query data to the server.

[1935] Specific operation: The terminal sends metadata to the server, including the query content and the user's device information (e.g., IP address, device ID).

[1936] Input: User inquiry message and metadata.

[1937] Output: Query data sent to the server.

[1938] 1.3 The server receives the query

[1939] The server receives the query data sent from the terminal and generates a unique user ID.

[1940] Specific operation: The server records the query details in the logging system and generates a user ID to associate with this log.

[1941] Input: Inquiry data sent from the terminal.

[1942] Output: Query data recorded in the log and the generated user ID.

[1943] Step 2: Content Analysis and Sentiment Analysis

[1944] 2.1 The server performs natural language processing.

[1945] The server uses a natural language processing engine to parse the query content.

[1946] Specific operation: The natural language processing engine analyzes the text data and classifies the query into categories such as "garbage disposal" based on keywords and context.

[1947] Input: Query data recorded on the server.

[1948] Output: Classified category information.

[1949] 2.2 The server performs sentiment analysis

[1950] The server uses an emotion analysis engine to determine the emotions contained in the query.

[1951] Specific operation: The emotion analysis engine analyzes the tone and expression of the text to detect emotions such as "anxiety," "anger," and "joy."

[1952] Input: Query data recorded on the server.

[1953] Output: Detected emotion information.

[1954] 2.3 The server records the analysis results.

[1955] The server integrates the results of natural language processing and sentiment analysis, and logs the categories and sentiments.

[1956] Input: Classified category information and detected sentiment information.

[1957] Output: Category and sentiment information recorded in the log.

[1958] Step 3: Database Search

[1959] 3.1 The server generates the search query

[1960] The server generates search queries based on category and sentiment.

[1961] Specific operation: The server generates database search queries, such as SQL queries, and sets conditions to search for specific information related to categories and sentiments.

[1962] Input: Category and sentiment information recorded in the log.

[1963] Output: The generated search query.

[1964] 3.2 The server sends a query to the database

[1965] The server sends a search query to the database and retrieves the information.

[1966] Specific operation: The server opens a database connection and executes the generated search query against the database.

[1967] Input: The generated search query.

[1968] Output: Search results returned from the database.

[1969] 3.3 The server receives the search results

[1970] The server receives the search results returned from the database and logs them.

[1971] Input: Search results from the database.

[1972] Output: Search results recorded in the log.

[1973] Step 4: Answer Generation

[1974] 4.1 The server generates the answer

[1975] The server generates an answer based on information retrieved from the database.

[1976] Specific operation: The server analyzes the acquired information and generates an appropriate response that aligns with the user's inquiry and sentiment.

[1977] Input: Search results from the database.

[1978] Output: The generated response.

[1979] 4.2 The server adjusts responses based on emotions.

[1980] The emotion engine adjusts the tone and content of responses according to the user's emotions.

[1981] Specific operation: The server modifies the wording and tone of the response based on the detected emotion. For example, if it determines that the user is "anxious," it will add phrases such as "don't worry."

[1982] Input: Generated response content and sentiment information.

[1983] Output: Adjusted response content.

[1984] 4.3 The server formats the response.

[1985] The server formats the adjusted responses into a user-friendly format.

[1986] Specific operation: The server converts the response into text or audio format, making it easy for the user to understand.

[1987] Input: Adjusted response content.

[1988] Output: Formatted response.

[1989] Step 5: User Notifications

[1990] 5.1 The server checks the user's device type.

[1991] The server checks the device type (smartphone, voice-enabled device) of the user who has been registered in advance.

[1992] Specific action: The server checks the device information listed in the user profile.

[1993] Input: User profile data.

[1994] Output: Device type information.

[1995] 5.2 The server sends the response

[1996] The server will send the response in either text or audio format, depending on the device type.

[1997] Specific operation: The server uses the corresponding communication protocol to send text messages and voice notifications to the user's device.

[1998] Input: Formatted response and device type information.

[1999] Output: The response sent to the user's device.

[2000] 5.3 The user receives the response

[2001] Users receive and review the responses via their smartphones or voice devices.

[2002] Specific actions: The user checks the device and views or listens to received messages.

[2003] Input: Response sent from the server.

[2004] Output: Confirmation of user responses.

[2005] (Application Example 2)

[2006] 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".

[2007] Traditional customer service in brick-and-mortar stores often involves providing the same service to all customers, making it difficult to respond flexibly to customers' emotions and circumstances. Furthermore, it placed a heavy burden on staff, and there was a demand for quick and efficient responses.

[2008] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[2009] In this invention, the server includes means for a user to make a query using an information processing device, means for classifying the user's query content into categories and emotions by performing natural language analysis and sentiment analysis, means for retrieving appropriate information from a database based on the categories and emotions, and means for providing the retrieved information in text or audio format in a tone appropriate to the user's emotions. This enables flexible and rapid responses that are appropriate to the customer's emotions and circumstances.

[2010] An "information processing device" is a device used by users to input or process information, such as a smartphone or a robot.

[2011] "Natural language processing" is a technology that uses computers to analyze the language that humans use on a daily basis, with the aim of understanding and structuring the content of user inquiries.

[2012] "Sentiment analysis" is a technology that analyzes the emotions contained in a user's statements and writings, and identifies emotional states such as interest, anxiety, and confusion.

[2013] A "category" is a subject or theme used to classify user inquiries, and examples include product information and return procedures.

[2014] "Tone" refers to the element of adjusting the tone and expression of a response according to the user's emotional state. This includes, for example, a gentle tone to encourage reassurance or lively expressions to pique interest.

[2015] A "database" is a collection of information in which multiple pieces of information are systematically organized and stored, and is used to retrieve appropriate information in response to a query.

[2016] To implement this invention, the following system configuration is necessary. The system provides information to customers when they make inquiries at physical stores, and optimizes the response by also considering the customer's emotions.

[2017] System Overview

[2018] 1. Inquiry reception

[2019] The server provides a means for users to make inquiries using information processing devices (e.g., smartphones or in-store robots). Inquiry data sent from these information processing devices is transmitted to the cloud server.

[2020] 2. Content Analysis and Sentiment Analysis

[2021] The server analyzes the query content using a natural language processing engine (e.g., Google Cloud Natural Language API) to extract the query content and category. It also uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions and determine their emotional state.

[2022] 3. Database Search

[2023] The server searches the database for appropriate information based on the analyzed categories and sentiments. This database contains product information, procedure instructions, store information, and more.

[2024] 4. Answer generation

[2025] The server generates a response based on the information it has acquired. It adjusts the tone and expression according to the user's emotional state. This process generates a response that makes the user feel at ease.

[2026] 5. User Notifications

[2027] The server verifies the device type of the pre-registered user (smartphone, voice-enabled device, etc.) and provides the response in the appropriate format. The user can receive and confirm the response through the information processing device.

[2028] Specific example

[2029] For example, if a user uses their smartphone in a physical store and asks, "How do I return this item?", the following process will occur:

[2030] 1. Inquiry reception

[2031] A user submits an inquiry using their smartphone. This inquiry is sent to a cloud server.

[2032] 2. Content Analysis and Sentiment Analysis

[2033] The server uses the Google Cloud Natural Language API to analyze the inquiry and categorize it as "product information." Simultaneously, it uses IBM Watson Tone Analyzer to analyze the user's emotion as "confused."

[2034] 3. Database Search

[2035] The server searches the database based on the "product information" category and the "confusion" emotion to retrieve information on appropriate return procedures.

[2036] 4. Answer generation

[2037] Based on the information it retrieves, the server generates a response with a adjusted tone, such as, "Please rest assured. For instructions on how to return this product, please see the following steps."

[2038] 5. User Notifications

[2039] The server sends the response to the user's smartphone in text format, and the user checks the response on their smartphone.

[2040] Example of a prompt

[2041] Specifically, use the following prompt statements:

[2042] "When a user inquires, 'I want to know how to return an item,' and their emotion is perceived as 'confused,' please provide specific steps on how to generate a response."

[2043] Implementing such a system will enable flexible and rapid responses tailored to the user's emotions and circumstances.

[2044] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2045] Step 1:

[2046] The user makes an inquiry using an information processing device. The user inputs an inquiry, such as "How do I return this product?", using a smartphone or an in-store robot. The input inquiry data is sent to a cloud server by the terminal. Here, the input is the user's inquiry, and the output is the data sent to the cloud server.

[2047] Step 2:

[2048] The server analyzes received query data using natural language processing and sentiment analysis. Specifically, it uses the Google Cloud Natural Language API to analyze the query content and extract categories (e.g., "product information"). It also uses IBM Watson Tone Analyzer to determine the sentiment contained in the query (e.g., "confused"). The input is the user's query data, and the output is the analyzed category and sentiment information.

[2049] Step 3:

[2050] The server searches the database for appropriate information based on the analyzed categories and sentiments. Here, the server generates a database search query and performs the search against the database. The input is category and sentiment information, and the output is the information retrieved from the database.

[2051] Step 4:

[2052] The server generates a response based on information retrieved from the database. During this process, it adjusts the tone and expression according to the analyzed emotion. For example, if the emotion "confusion" is recognized, it will generate a response in a tone such as, "Please rest assured. For instructions on how to return this product, please see the following steps." The input consists of information and emotion data retrieved from the database, while the output is the adjusted response.

[2053] Step 5:

[2054] The server pre-verifies the type of information processing device the user is using and provides the response in the appropriate format. For example, if the user is using a smartphone, the response will be sent in text format. The input consists of the response and the user's device information, and the output is a response notification in the appropriate format.

[2055] Step 6:

[2056] Users receive and confirm answers through an information processing device. Specifically, users can receive text messages on their smartphones and learn how to resolve their inquiries by reviewing their content. The input is the provided answer, and the output is the user's improved understanding and satisfaction.

[2057] 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.

[2058] 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.

[2059] 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.

[2060] 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.

[2061] 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.

[2062] 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.

[2063] 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.

[2064] 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.

[2065] 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."

[2066] 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.

[2067] 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.

[2068] 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.

[2069] 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.

[2070] 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.

[2071] 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.

[2072] 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.

[2073] 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.

[2074] 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.

[2075] 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.

[2076] 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.

[2077] 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.

[2078] The following is further disclosed regarding the embodiments described above.

[2079] (Claim 1)

[2080] A means for users to contact the city hall using their devices,

[2081] A means for classifying the user's inquiry content into categories by performing natural language analysis,

[2082] A means for searching for appropriate information from a database based on the aforementioned categories,

[2083] Means for providing the retrieved information to the user in text or audio format,

[2084] A system that includes this.

[2085] (Claim 2)

[2086] The system according to claim 1, further comprising means for calling for expert assistance if the database does not contain appropriate information.

[2087] (Claim 3)

[2088] The system according to claim 1, further comprising means for prior confirmation of the type of device to be used by the user and for notifying the user of the response in an appropriate format.

[2089] "Example 1"

[2090] (Claim 1)

[2091] A means for users to contact local governments using information terminals,

[2092] A means for analyzing the user's inquiry content using a natural language processing engine and classifying it into categories,

[2093] A means for searching for appropriate information from a database based on the aforementioned categories,

[2094] Means for providing the retrieved information to the user in text or audio format,

[2095] A system that includes this.

[2096] (Claim 2)

[2097] The system according to claim 1, further comprising means including the content of the inquiry and device information in the process by which the information terminal transmits inquiry data to the server.

[2098] (Claim 3)

[2099] The system according to claim 1, further comprising means for the server to receive query data, generate a unique user ID, and record it in a log.

[2100] (Claim 4)

[2101] The system according to claim 1, further comprising means for the server to store the analysis results in an internal system and record them in a log.

[2102] (Claim 5)

[2103] The system according to claim 1, further comprising means for the server to generate an SQL query based on category information and send it to a database.

[2104] (Claim 6)

[2105] The system according to claim 1, further comprising means for the server to format the generated response in text or audio format and log it.

[2106] (Claim 7)

[2107] The system according to claim 1, further comprising means for confirming the type of information terminal used by the user and notifying the user of the response in an appropriate format.

[2108] "Application Example 1"

[2109] (Claim 1)

[2110] A means for users to contact service facilities using electronic devices,

[2111] A means for classifying the user's inquiry content into categories by performing natural language analysis,

[2112] A means for searching for appropriate information from the information storage unit based on the aforementioned category,

[2113] Means for providing the retrieved information to the user in text or audio format,

[2114] A means of generating a unique user ID and logging it,

[2115] A system that includes this.

[2116] (Claim 2)

[2117] The system according to claim 1, further comprising means for calling for expert assistance when the information storage unit does not contain appropriate information.

[2118] (Claim 3)

[2119] The system according to claim 1, further comprising means for confirming in advance the type of electronic terminal to be used by the user and notifying the user of the response in an appropriate format.

[2120] "Example 2 of combining an emotion engine"

[2121] (Claim 1)

[2122] Means by which users can make inquiries using their devices,

[2123] A means for performing natural language analysis on the user's inquiry content and classifying it into categories and emotions,

[2124] A means for retrieving appropriate information from a database based on the aforementioned categories and emotions,

[2125] A means for adjusting the tone and content of the response according to the user's emotions,

[2126] Means for providing the retrieved information to the user in text or audio format,

[2127] A system that includes this.

[2128] (Claim 2)

[2129] The system according to claim 1, further comprising means for calling for expert assistance if the database does not contain appropriate information.

[2130] (Claim 3)

[2131] The system according to claim 1, further comprising means for prior confirmation of the type of device to be used by the user and for notifying the user of the response in an appropriate format.

[2132] "Application example 2 when combining with an emotional engine"

[2133] (Claim 1)

[2134] A means by which a user makes a query using an information processing device,

[2135] A means for classifying the user's inquiry content into categories and emotions by performing natural language analysis and sentiment analysis,

[2136] A means for retrieving appropriate information from a database based on the aforementioned categories and emotions,

[2137] A means for providing the retrieved information in text or audio format in a tone appropriate to the user's emotions,

[2138] A system that includes this.

[2139] (Claim 2)

[2140] The system according to claim 1, further comprising means for calling for expert assistance if the database does not contain appropriate information.

[2141] (Claim 3)

[2142] The system according to claim 1, further comprising means for confirming in advance the type of information processing device to be used by the user and notifying the user of the answer in an appropriate format. [Explanation of symbols]

[2143] 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 for users to contact the city hall using their devices, A means for classifying the user's inquiry content into categories by performing natural language analysis, A means for searching for appropriate information from a database based on the aforementioned categories, Means for providing the retrieved information to the user in text or audio format, A system that includes this.

2. The system according to claim 1, further comprising means for calling for expert assistance if the database does not contain appropriate information.

3. The system according to claim 1, further comprising means for confirming in advance the type of device to be used by the user and notifying the user of the response in an appropriate format.

Images