system

Abstract

Provide a system. The system collects digital transformation cases related to local government operations and presents relevant cases in response to user queries, A means to automatically collect digital transformation case studies related to municipal operations from a variety of sources; A means to analyze the collected cases, classify them by keyword, and store them in a database; means for analyzing a question received from a user and extracting related keywords; A means for searching a database based on the extracted keywords and extracting related cases; A system that includes a means for generating and presenting a response in a user-friendly format based on the extracted cases.

Description

[Technical Field]

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

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

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

[0004] When promoting digital transformation (DX) in local government operations, there is a need to quickly learn about specific examples. However, with current systems, it is difficult to provide relevant examples in real time at the time of proposal, and prior research and reporting often require a great deal of time. This results in a lack of efficiency in proposals and makes it difficult to make quick decisions. [Means for solving the problem]

[0005] This invention relates to a system for rapidly providing digital transformation case studies related to municipal operations. Specifically, the system includes a means for automatically collecting digital transformation case studies related to municipal operations from a variety of sources, a means for analyzing the collected case studies, categorizing them by keyword, and storing them in a database, a means for analyzing questions received from users and extracting relevant keywords, a means for searching the database based on the extracted keywords and extracting relevant case studies, and a means for generating and presenting responses based on the extracted case studies in a format that is easy for users to understand. The system also includes a means for collecting user feedback and improving the search algorithm based on the feedback. This system is expected to improve the efficiency of proposals and enable rapid decision-making, thereby facilitating the digital transformation of municipal operations.

[0006] "Municipal affairs" refers to all administrative activities carried out by local governments for citizen services and regional development.

[0007] "Digital transformation (DX)" refers to efforts to fundamentally change business processes, culture, and service offerings using digital technology in order to increase efficiency and value.

[0008] "Case studies" refer to information showing past achievements and specific examples of use, and are samples that can be used as reference for others.

[0009] A "database" refers to a structured collection of information that allows for efficient searching, management, and updating of large amounts of data.

[0010] A "query" refers to a question or request sent to a database to retrieve specific information.

[0011] "Natural Language Processing (NLP)" refers to the techniques and methods that enable computers to understand, interpret, and generate human language.

[0012] "Feedback" refers to evaluations and opinions on the output and results of a system, and refers to information that can be used to improve the system.

[0013] A "search algorithm" refers to a computational procedure or method for efficiently and effectively finding relevant information from databases or other sources.

[0014] "Analysis" refers to the process of examining data or information in detail and identifying its components and characteristics.

[0015] "Response generation" refers to the process of creating the system-provided answers to user questions or requests. [Brief explanation of the drawings]

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

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

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

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

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

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

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0037] The present invention relates to a system for quickly providing examples of digital transformation (DX) related to local government operations. The system is specifically implemented using the following means.

[0038] First, the server collects digital transformation case studies related to local government operations from a variety of sources, including the internet, specialized news sites, and public reports from local governments. The collected data is then analyzed using text mining technology to extract keywords.

[0039] The server then categorizes the collected case data by keyword and stores it in a database. This database is used to efficiently manage various cases of local government work and provides a quick response to subsequent search processing.

[0040] When a user inputs a question, they enter a query into the terminal, such as "I would like to know about examples of AI being used in local governments." The terminal then sends this query to the query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords "local government," "AI," and "examples."

[0041] The server then searches the database based on the extracted keywords. The search results might include examples such as "Fukuoka City's AI-based snow removal management system" or "Osaka City's AI-based tourist information system." This search process uses a keyword-matching algorithm to prioritize the most relevant examples.

[0042] The server then generates a response based on the search results. The generated response is formatted to be easily understood by the user. For example, a response might be created in the form of, "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work."

[0043] Finally, the device displays the generated response to the user. The user can then obtain specific information based on the response. The user can also provide feedback on the response, for example, by typing "This information is useful" into the device. The device then sends this feedback to the server, which analyzes it and uses it to improve the search algorithm. Repeating this process improves the accuracy of the entire system.

[0044] In this way, digital transformation case studies for municipal operations can be provided quickly, and support will be provided to municipal employees and staff to efficiently advance proposals.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The server automatically collects data on digital transformation cases from the internet, news sites, official local government websites, etc. This collection activity is carried out periodically, and new cases are added to the database.

[0048] Step 2:

[0049] The server analyzes the collected data using text mining technology. This analysis extracts key keywords for each case study, such as "AI," "IoT," and "smart city."

[0050] Step 3:

[0051] The server categorizes the case data by keyword based on the extracted keywords. This categorization is used to create a database. The database organizes and stores cases related to each keyword.

[0052] Step 4:

[0053] The user inputs a question about a specific case into the terminal. For example, a question such as, "I would like to know about cases where AI has been used in local governments."

[0054] Step 5:

[0055] The device sends the user's question to the query analysis module, which uses natural language processing technology to analyze the question and extract key keywords such as "local government," "AI," and "case study."

[0056] Step 6:

[0057] The server searches the database based on the analyzed keywords. Using a keyword matching algorithm, it prioritizes the most relevant cases. For example, search results might include "Fukuoka City's AI-based snow removal management system."

[0058] Step 7:

[0059] The server generates a response to present to the user based on the search results. This response is formatted using natural language processing technology in a format that is easy for the user to understand. For example, a response such as "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work" may be created.

[0060] Step 8:

[0061] The terminal displays the generated response to the user, who can review the provided response and obtain any required details.

[0062] Step 9:

[0063] The user inputs feedback on the response into the terminal, for example, "This information is useful."

[0064] Step 10:

[0065] The device sends user feedback to the server, which analyzes it and refines the search algorithm and how the database is organized. This self-improvement process improves the accuracy of responses to the next query.

[0066] Example 1

[0067] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0068] There is a need for a system that can quickly collect, classify, and search examples of digital transformation (DX) related to local government operations and provide appropriate information in response to user requests. Current systems have the problem of taking time to collect, analyze, and search information, preventing users from quickly accessing the information they need. Furthermore, there is no well-established method for effectively utilizing user feedback, making it difficult to improve the accuracy of the entire system.

[0069] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0070] In this invention, the server includes means for automatically collecting digital transformation cases related to local government operations from a variety of sources, means for analyzing the collected data using natural language processing technology to extract keywords, and means for categorizing the analyzed data by keyword and storing it in a database, thereby enabling users to quickly and accurately access the DX cases they need.

[0071] "Municipal business" refers to all business activities carried out by local governments, such as administrative services and public works.

[0072] "Digital transformation (DX)" is an initiative that utilizes digital technology to reform business processes and improve efficiency and service quality.

[0073] "Means of collection" refers to the technical methods and tools used to automatically obtain the required information from various sources.

[0074] "Natural language processing technology" is a general term for algorithms and methods that enable computers to understand, process, and generate human language.

[0075] "Means of analysis" refers to the technical process of analyzing collected data using machine learning and statistical methods to extract meaningful information.

[0076] "Keywords" refer to important words or phrases related to a particular theme or topic.

[0077] "Classification" refers to the process of grouping analyzed information based on specific criteria and organizing it into a more manageable form.

[0078] A "database" is a data storage system that is an organized collection of data stored in a form that allows for efficient retrieval and processing.

[0079] "User" refers to a person who uses the system to input information and obtain output.

[0080] A "query" refers to a question or search phrase that a user enters to request information from a system.

[0081] A "search algorithm" refers to a computational method or rule for efficiently finding information in a database based on specific criteria.

[0082] The "means of generating a response" refers to the process of formatting and outputting the information so that the search results are displayed in a way that is easy for the user to understand.

[0083] "Display means" refers to a technology for visually presenting the generated information on the user's terminal.

[0084] "Feedback" refers to the evaluation and opinion information that users give to the system.

[0085] MODE FOR CARRYING OUT THE INVENTION

[0086] This invention relates to a system for quickly providing examples of digital transformation (DX) related to local government operations. Specific embodiments of this system are described below.

[0087] First, the server collects digital transformation case studies related to municipal operations from various sources. Specifically, it uses web scraping tools such as Python's BeautifulSoup and Scrapy to obtain information from the Internet, specialized news sites, and public reports published by the municipality. The collected data is temporarily stored in local storage.

[0088] The server then analyzes the collected data using natural language processing technologies such as Python's NLTK (Natural Language Toolkit) and spaCy to extract important keywords from the text data. For example, keywords such as "Fukuoka City," "AI," and "snow removal management system" are extracted.

[0089] The analyzed data is classified by keyword, using, for example, the k-means clustering algorithm to group related data, and then stored in a MySQL® database to provide quick responses for subsequent searches.

[0090] When a user inputs information they want to know into a device, they enter a query such as, "I want to know about cases where AI is being used in local governments." The device then sends this query to the server's query analysis module. The server then uses natural language processing (NLP) to analyze the query and extract key keywords such as "local government," "AI," and "case studies."

[0091] Based on the extracted keywords, the server searches the MySQL database using ElasticSearch (registered trademark). This search process finds related cases, such as "Fukuoka City's AI-based snow removal management system" and "Osaka City's AI-based tourist information system."

[0092] The server generates a response based on the search results. This response is generated using Python's Jinja2 template engine, providing information that is easy for the user to understand. For example, the generated response might be expressed in a format such as, "Fukuoka City has introduced a snow removal management system using AI, enabling efficient snow removal work."

[0093] Finally, the device generates and displays the response to the user, using HTML and CSS to present it in a visually friendly format.

[0094] Users can also provide feedback on the information provided. For example, they can input feedback such as "This information is useful" into the device. The device then sends this feedback to the server, which analyzes it and uses it to improve the search algorithm. The feedback is analyzed using Python's Pandas library, which updates the machine learning model to improve the system's accuracy.

[0095] For example, a user may enter a prompt such as, "Please tell me more about examples of how AI has been used in local governments." In response to this prompt, the system can quickly and accurately generate and provide a response through the steps described above.

[0096] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0097] System program processing flow

[0098] Step 1:

[0099] Data collection

[0100] The server collects digital transformation case studies related to municipal operations from a variety of sources, including the internet, specialized news sites, and public reports from municipalities. Specifically, it performs web scraping using Python's BeautifulSoup and Scrapy to obtain the necessary text data.

[0101] Input: Request URL

[0102] Output: Collected text data

[0103] Step 2:

[0104] Data analysis

[0105] The server analyzes the collected text data using natural language processing libraries such as Python's NLTK and spaCy to extract important keywords from the text content. For example, keywords such as "Fukuoka City," "AI," and "snow removal management system" are extracted.

[0106] Input: Collected text data

[0107] Output: Extracted keyword list

[0108] Step 3:

[0109] Data classification and storage

[0110] The server categorizes the data based on the extracted keywords, using the k-means clustering algorithm to group related data, and then stores the categorized data in a MySQL database for efficient management.

[0111] Input: Extracted keyword list

[0112] Output: Classified data, stored database records

[0113] Step 4:

[0114] Entering a query

[0115] The user inputs the information they want to know into the device. For example, they input a query such as, "I want to know about cases where AI is being used in local governments."

[0116] Input: User query

[0117] Output: The device sends a query to the server

[0118] Step 5:

[0119] Query Analysis

[0120] The device sends the user's query to the server's query analysis module, which then uses natural language processing technology to analyze the query and extract key keywords such as "local government," "AI," and "case study."

[0121] Input: User query

[0122] Output: Extracted query keywords

[0123] Step 6:

[0124] Searching the database

[0125] The server uses Elasticsearch to search the MySQL database based on the extracted keywords. This search process finds related case studies. For example, case studies such as "Fukuoka City's AI-based snow removal management system" and "Osaka City's AI-based tourist information system" are listed.

[0126] Input: Extracted query keywords

[0127] Output: List of related cases

[0128] Step 7:

[0129] Generating a response

[0130] The server uses Python's Jinja2 template engine to generate a response based on the search results. To provide users with easy-to-understand information, the generated response is expressed in a format such as, "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work."

[0131] Input: List of related cases

[0132] Output: The generated response

[0133] Step 8:

[0134] Viewing the response

[0135] The terminal then displays the generated response to the user, formatting it using HTML and CSS to make the information visually appealing.

[0136] Input: Generated response

[0137] Output: Displayed response

[0138] Step 9:

[0139] Gathering feedback

[0140] The user provides feedback on the provided information. For example, they input feedback such as "This information is useful" into the terminal. The terminal sends this feedback to the server, which analyzes it using the Python Pandas library and improves the search algorithm based on this feedback.

[0141] Input: User feedback

[0142] Output: Improved search algorithm

[0143] This will enable the entire system to quickly provide examples of digital transformation related to local government operations and appropriately present information that meets users' needs.

[0144] (Application example 1)

[0145] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] Customer service in modern brick-and-mortar stores requires the provision of fast and accurate information, but it is difficult for store staff to efficiently utilize the vast amount of information available to answer customers. Responses are often delayed, particularly when providing similar questions or information about specific products. Therefore, in order to improve service in brick-and-mortar stores, a system that can provide fast and accurate information is needed.

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

[0148] In this invention, the server includes means for automatically collecting digital transformation case studies related to local government operations from a variety of sources, means for analyzing the collected case studies and categorizing them by keyword and storing them in a database, means for analyzing questions received from users and extracting related keywords, means for searching the database based on the extracted keywords and extracting related case studies, means for generating and presenting responses in a user-friendly format based on the extracted case studies, and means for providing optimal responses to customer questions within a smartphone application. This enables fast and accurate customer service in physical stores.

[0149] Definitions of important terms contained in the claims

[0150] "Municipal Affairs"

[0151] It refers to a series of administrative and service activities carried out by local governments.

[0152] "Digital Transformation Case Studies"

[0153] This refers to concrete examples of how digital technology has improved and transformed business processes and services.

[0154] "sauce"

[0155] It refers to the source or reference from which information or data is obtained.

[0156] "means"

[0157] refers to the methods or technical elements used to achieve a specific purpose.

[0158] "analysis"

[0159] It refers to the detailed examination of data and information to clarify its meaning and content.

[0160] "keyword"

[0161] refers to important words or terms to use as search and classification criteria.

[0162] Database

[0163] It refers to a collection of data that is organized in an organized manner, and a system for efficiently searching and manipulating specific data.

[0164] "User"

[0165] refers to the individuals or organizations that use the system or application.

[0166] "question"

[0167] It refers to the linguistic expression of the information a user wants to know or the problem they want to solve.

[0168] "response"

[0169] refers to information provided in response to a question or question.

[0170] "Smartphone"

[0171] refers to a portable electronic device that combines mobile communication and computer functions.

[0172] "application"

[0173] refers to a software program designed for a specific purpose.

[0174] "customer"

[0175] refers to the person or entity that purchases or uses a product or service.

[0176] "Natural language processing technology"

[0177] refers to computer technology for understanding and processing human language.

[0178] MODE FOR CARRYING OUT THE INVENTION

[0179] The system of the present invention collects examples of digital transformation related to local government operations and presents relevant examples in response to queries from users. Specific embodiments of the system will be described below.

[0180] Hardware and software used

[0181] Hardware: Standard servers, smartphones

[0182] Software: Python, requests (for data collection), BeautifulSoup (for HTML analysis), spaCy (natural language processing)

[0183] System processing flow

[0184] The server first automatically collects digital transformation case studies related to local government operations from a variety of sources, including online news sites and public reports from local governments.

[0185] The collected cases are analyzed using text mining technology and classified by keyword. During this process, important keywords are extracted from the text data using spaCy. The extracted keywords are stored in a database, allowing for quick response to subsequent search processing.

[0186] When a user accesses the application using a smartphone and enters a question, the question is first received by the device, then sent to the server where it is analyzed using natural language processing technology. This analysis extracts the main keywords contained in the question.

[0187] The server then searches the database based on the extracted keywords. The search results yield relevant cases, which are then presented to the customer within the smartphone application. For example, in response to the question, "What products are popular these days?", a response such as, "The most popular product over the past six months is the new smartphone model" is generated.

[0188] The generated response is displayed to the user in a user-friendly format, and the user can provide feedback on the response, which is then sent back to the server to help refine the search algorithm, thereby improving the accuracy of the entire system.

[0189] Examples and prompts

[0190] For example, if a user asks the following question:

[0191] What products are popular these days?

[0192] The system uses a generative AI model to generate a response using the following prompt:

[0193] Question: "What are the most popular products these days?"

[0194] Prompt: Please provide examples related to the following keywords: "popular" and "product"

[0195] In response to this,

[0196] "The most popular products over the past six months have been new smartphone models. This was confirmed based on sales data in specific regions."

[0197] The information is provided to the user in this format.

[0198] In this way, customer service can be provided quickly and accurately in physical stores.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Detailed program processing flow

[0201] Step 1: Data collection

[0202] The server first automatically collects digital transformation case studies related to municipal operations from a variety of sources, such as online news sites and public reports from municipalities. This collection process uses the Python requests library to obtain the contents of web pages. The obtained HTML data is then analyzed using the BeautifulSoup library and extracted as text data.

[0203] Enter: Website URL

[0204] Output: Extract text data from HTML content

[0205] Specific operation: The server sends an HTTP request to the specified URL, analyzes the received HTML data, and saves it as text.

[0206] Step 2: Text mining

[0207] The collected text data is analyzed using text mining techniques. The server uses the spaCy library to extract important keywords from the text data, which makes the data more organized and streamlines the subsequent search process.

[0208] Input: Text data

[0209] Output: Extracted keyword list

[0210] What it does: The server feeds the text data into a natural language processing library to extract noun phrases and other important keywords.

[0211] Step 3: Database storage

[0212] The extracted keywords and their corresponding examples are stored in a database that is designed to enable rapid response to subsequent search processes.

[0213] Input: A list of keywords and their corresponding examples

[0214] Output: Structured data stored in a database

[0215] Specific operation: The server stores keywords and their related cases in a database and sets up an index to enable efficient searches.

[0216] Step 4: Receiving and parsing user queries

[0217] A user accesses the application using a smartphone and enters a question. This question is received by the device and sent to the server, which uses natural language processing techniques to analyze the question and extract key keywords, again using the spaCy library.

[0218] Input: User's question (in text format)

[0219] Output: Extracted keywords

[0220] How it works: The device receives user input and sends it to the server, which then uses NLP technology to analyze the question and extract key keywords.

[0221] Step 5: Database Search

[0222] The server searches the database based on the extracted keywords and extracts relevant cases using a keyword matching search algorithm.

[0223] Input: Extracted keywords

[0224] Output: List of related cases

[0225] Specific operation: The server searches the database and extracts cases that match the keywords.

[0226] Step 6: Response generation and presentation

[0227] Based on the extracted cases, the server generates a response in a user-friendly format and sends it to the terminal, which then displays the response to the user.

[0228] Input: List of related cases

[0229] Output: The response that is presented to the user

[0230] Specific operation: The server generates an easy-to-understand response based on the case data and sends it to the terminal, which then displays the response on the user's screen.

[0231] Step 7: Gather feedback and improve the algorithm

[0232] Users can provide feedback on the responses provided, which is sent back to the server to help improve the search algorithm.

[0233] Input: User feedback (text format)

[0234] Output: Improved search algorithm

[0235] How it works: The device receives feedback and sends it to the server, which analyzes it and uses it to improve the algorithm.

[0236] This will enable quick and accurate customer service in physical stores.

[0237] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0238] This invention combines an emotion engine with a system for quickly providing examples of digital transformation (DX) related to local government operations. Specifically, this invention is implemented using the following means.

[0239] First, the server collects digital transformation case studies related to local government operations from a variety of sources, including the internet, news sites, and official local government websites, and then analyzes the collected data using text mining technology.

[0240] The server then extracts keywords from the analyzed data and stores the collected cases in a database, categorizing them by keyword. This database neatly stores cases related to keywords such as "AI," "IoT," and "smart city."

[0241] When a user inputs a question about a specific case into the device, a query such as "I would like to know about cases where AI has been used in local governments" is sent to the device. The device then sends this query to a query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords "local government," "AI," and "case study."

[0242] The server then searches the database based on the extracted keywords, using a keyword matching algorithm to prioritize the most relevant cases, such as "Fukuoka City's AI-based snow removal management system."

[0243] Furthermore, the present invention incorporates an emotion engine. When a user inputs a question or receives search results, the device analyzes the user's facial expression, tone of voice, etc., and recognizes the user's emotional state through the emotion engine. For example, if the user is feeling dissatisfied, the device will prioritize providing examples and answers that correspond to that emotional state.

[0244] The server generates a response based on the detected emotional state. This response is generated using natural language processing technology with a tone and content that reflects the user's emotional state. For example, a response could be created that reads, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work and has received high praise from citizens."

[0245] Finally, the device displays the generated response to the user, who can review the provided response and obtain necessary information. If the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[0246] In this way, not only can digital transformation examples related to municipal operations be provided quickly, but the content and tone of the response can be adjusted depending on the user's emotional state, resulting in more personalized information provision.

[0247] The processing flow will be explained below.

[0248] Step 1:

[0249] The server automatically collects examples of digital transformation related to local government operations from the internet, news sites, official local government websites, etc. This collection is set to occur periodically, and new examples are added to the database.

[0250] Step 2:

[0251] The server analyzes the collected data using text mining technology to extract key keywords for each case study, which are then categorized into categories such as "AI," "IoT," and "smart city."

[0252] Step 3:

[0253] The server categorizes the case data based on the extracted keywords and stores them in a structured database, where related cases are stored in a searchable format for each keyword.

[0254] Step 4:

[0255] The user inputs a question about a specific case into the terminal. For example, a question might be input such as, "I would like to know about cases where AI has been used in local governments."

[0256] Step 5:

[0257] The device sends the entered question to the query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords: "municipal government," "AI," and "case study."

[0258] Step 6:

[0259] During query analysis, the device analyzes the user's facial expressions and tone of voice using an emotion engine, which recognizes the user's emotional state (e.g., frustration, interest, joy, etc.) and sends that information to the query analysis module.

[0260] Step 7:

[0261] The server searches the database based on the extracted keywords and emotional state. Using a keyword matching algorithm, it prioritizes and extracts highly relevant cases. Specifically, it finds cases such as "Fukuoka City's AI-based snow removal management system."

[0262] Step 8:

[0263] When generating a response based on the search results, the server takes into account the user's emotional state obtained from the emotion engine. For example, if the user is dissatisfied, the tone of the response will be more considerate. The response is generated using natural language processing technology and formatted as, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work. It has received high praise from citizens."

[0264] Step 9:

[0265] The terminal displays the generated response to the user, who can obtain specific information based on the provided response.

[0266] Step 10:

[0267] The user inputs feedback on the response into the terminal, such as "This information is useful" or "I'd like to know more specific examples."

[0268] Step 11:

[0269] The device sends the collected feedback to the server, which analyzes it and uses it to refine the search algorithm and response generation process. This self-improvement process improves the accuracy of the response to the next query.

[0270] In this way, it is possible to quickly provide examples of digital transformation for municipal operations and generate responses that reflect the user's emotional state.

[0271] Example 2

[0272] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0273] Currently, there are problems with collecting examples of digital transformation in municipal operations and with responding quickly and specifically to user questions. There is also a lack of systems that generate personalized responses based on user sentiment. This makes it difficult for municipal employees and residents to obtain the information they need in a timely manner. Furthermore, there is an insufficient mechanism for improving the accuracy of the system based on feedback.

[0274] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0275] In this invention, the server includes means for automatically collecting digital transformation case studies related to local government operations from a variety of sources, means for analyzing the collected case studies and categorizing them by keyword and storing them in a database, means for analyzing questions received from users and extracting related keywords, means for searching the database based on the extracted keywords and extracting related case studies, means for generating and presenting a response in a format easy for the user to understand based on the extracted case studies, means for analyzing the user's emotional state and adjusting the content of the response, means for generating a response personalized for the user, and means for collecting feedback from users and improving the search algorithm based on the feedback, thereby making it possible to provide necessary information quickly and appropriately.

[0276] "Municipal services" is a general term for the various services and administrative procedures that local governments and regional administrative agencies provide to local residents.

[0277] "Digital transformation" refers to the use of information technology to innovate business processes and service delivery methods in order to improve efficiency and optimization.

[0278] "DX cases" refer to examples of specific results and initiatives that have been implemented through digital transformation.

[0279] "Source" refers to the source of information or the source of data.

[0280] "Collection means" refers to the specific methods or devices used to collect information or data.

[0281] "Analysis tools" refers to methods and software used to analyze collected data and understand and classify its contents.

[0282] "Keywords" refer to important words or phrases in the data or question.

[0283] A "database" refers to an information management system for systematically organizing and storing data.

[0284] A "question" refers to a query entered by a user to ask for information or an example they want to know.

[0285] "Extraction means" refers to the methods and techniques for extracting the necessary information from the analyzed data and keywords.

[0286] "Search methods" refer to methods and techniques for investigating and verifying information in a database.

[0287] "Response methods" refers to the methods and techniques used to provide information to users based on search results.

[0288] "Emotional state" refers to a user's current psychological state or feelings.

[0289] "Emotion analysis means" refers to methods or techniques for analyzing a user's facial expressions and tone of voice to determine their emotional state.

[0290] "Personalized responses" refer to providing specific information tailored to a user's individual needs and emotions.

[0291] "Feedback" refers to opinions and ratings provided by users.

[0292] A "search algorithm" refers to a procedure or calculation method for efficiently searching for information in a database.

[0293] The present invention is a system for quickly providing examples of digital transformation (DX) related to local government operations, and is combined with an emotion engine. This system is specifically implemented using the following means.

[0294] The server automatically collects digital transformation case studies related to local government operations from a variety of sources, including online news sites and official local government websites. This collection is performed using web crawler tools such as Apache (registered trademark) Nutch. The collected data is then analyzed using text mining techniques such as Apache OpenNLP.

[0295] The server extracts key keywords from the analyzed data and categorizes them by case, for example, into categories such as "AI," "IoT," and "smart city," and stores them in a MySQL or PostgreSQL database.

[0296] When a user enters a specific question into the device (e.g., "I would like to know about examples of AI use in local governments"), the device sends the question to a query analysis module (e.g., NLTK or SpaCy), which uses natural language processing technology to extract key keywords. The analysis results are then sent to the server.

[0297] The server then searches the database based on the extracted keywords and uses a keyword matching algorithm such as Elasticsearch to extract the most relevant examples, such as a specific example like "Fukuoka City's AI-based snow removal management system."

[0298] The present invention also incorporates an emotion engine. When a user enters a question or receives search results, the device uses a webcam and microphone to capture the user's facial expressions and tone of voice. Emotion analysis tools such as OpenFace and IBM Watson® Tone Analyzer are used to recognize the user's emotional state. For example, if the user is dissatisfied, the relevant examples and responses are tailored to that emotional state.

[0299] The server generates a response based on the emotion-analyzed data. This response is generated using natural language processing technology with a generative AI model (e.g., OpenAI® GPT-3®) that uses tone and content that reflects the user's emotional state. For example, a response such as "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work and has been well-received by citizens" may be generated.

[0300] The device displays the generated response to the user, who can review the provided information and gain the necessary knowledge. When the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[0301] Specific examples

[0302] Example 1:

[0303] User: "I want to know about examples of smart city development."

[0304] The server searches for relevant cases and finds "City X's Smart City Project." The device analyzes the user's emotions and generates a response in a reassuring tone: "City X's Smart City Project has been a success, and the quality of life for its residents has improved significantly."

[0305] Example prompt sentence:

[0306] "I'd like to know more about the AI-based snow removal management system in Fukuoka City."

[0307] "Please tell us some examples of successful smart city projects."

[0308] "Please introduce some examples of IoT implementation in local governments."

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Step 1: Collect data

[0311] The server automatically collects digital transformation examples related to local government operations from a variety of sources, specifically by periodically collecting data from online news sites and official local government websites using web crawler tools such as Apache Nutch.

[0312] Input: URL list of various internet sources

[0313] How it works: The web crawler visits pages from a set list of URLs at a specified interval and collects text data.

[0314] Output: raw collected data (text)

[0315] Step 2: Data analysis and keyword extraction

[0316] The server analyzes the collected raw data and uses text mining techniques such as Apache OpenNLP to extract keywords, tokenizing sentences and extracting key keywords such as nouns and verbs.

[0317] Input: Collected raw data (text)

[0318] How it works: The text analysis module tokenizes the data and runs it through analysis algorithms to extract keywords.

[0319] Output: Parsed data and extracted keyword list

[0320] Step 3: Classify and store data

[0321] The server categorizes the analyzed data based on the extracted keywords and stores it in a database such as MySQL or PostgreSQL. The categorized data is then organized for later searches and queries.

[0322] Input: Parsed data and extracted keyword list

[0323] How it works: The data classification module categorizes data based on a list of keywords and connects to a database to store the information.

[0324] Output: A database containing data sorted by category

[0325] Step 4: Receiving a query

[0326] The user inputs a specific question into the device. For example, a query such as "I would like to know about examples of how local governments have used AI" is entered.

[0327] Input: The question (query) entered by the user

[0328] Operation: The terminal receives input from the user through the query receiving module.

[0329] Output: Received query

[0330] Step 5: Query analysis and keyword extraction

[0331] The device analyzes the received query and uses natural language processing techniques (e.g., NLTK or SpaCy) to extract key keywords. The analysis results are sent to the server.

[0332] Input: Received query

[0333] How it works: The query analysis module tokenizes the query and extracts the main keywords.

[0334] Output: Extracted keyword list

[0335] Step 6: Search the database

[0336] The server searches the database based on the extracted keywords and extracts the most relevant cases using a keyword matching algorithm such as Elasticsearch.

[0337] Input: Extracted keyword list

[0338] How it works: The database search module generates a search query based on the keywords and queries the database.

[0339] Output: A list of the most relevant cases

[0340] Step 7: Sentiment Analysis

[0341] The device collects data using a webcam and microphone to analyze the user's facial expressions and tone of voice, using tools such as OpenFace and IBM Watson Tone Analyzer to recognize the user's emotional state.

[0342] Input: User facial expression images and voice data

[0343] How it works: The emotion analysis module analyzes facial expression images and audio data to recognize the user's emotional state.

[0344] Output: Recognized emotion data

[0345] Step 8: Generate a response

[0346] The server generates personalized responses based on the recognized emotion data, using a generative AI model (e.g., OpenAI GPT-3) to create responses appropriate for the user through natural language processing techniques.

[0347] Input: A list of the most relevant cases and recognized emotion data

[0348] How it works: The response generation module uses a generative AI model to generate a response based on relevant examples and sentiment data.

[0349] Output: The generated personalized response

[0350] Step 9: View the response

[0351] The terminal displays the generated response to the user, who reviews the information provided and optionally enters feedback into the terminal.

[0352] Input: The generated personalized response

[0353] Action: The device displays the response on the screen and receives user feedback.

[0354] Output: The response displayed to the user and any feedback entered

[0355] Step 10: Analyze feedback and refine the system

[0356] The server analyzes user feedback and uses the results to improve the search algorithm and response generation process.

[0357] Input: User feedback

[0358] How it works: The feedback analysis module analyzes the feedback and identifies areas for improvement in the search algorithm and response generation process.

[0359] Output: Improved search algorithm and response generation process

[0360] (Application example 2)

[0361] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0362] Conventional systems providing examples of digital transformation for local government operations only present relevant examples in response to user queries, and have the problem of being unable to provide personalized responses according to the user's emotional state. This is particularly difficult in situations where an optimal response according to the user's emotional state is required, such as when the user is feeling stressed or in a hurry, so it was necessary to improve the quality of the responses.

[0363] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting digital transformation case studies related to local government operations from various sources; means for analyzing the collected case studies, classifying them by keyword, and storing them in a database; means for analyzing questions received from users and extracting related keywords; means for searching the database based on the extracted keywords and extracting related case studies; means for generating and presenting a response in a format easy for the user to understand based on the extracted case studies; and means for analyzing the user's emotions and generating a response based on the emotions. This makes it possible to provide an optimal response according to the user's emotional state, improving the quality of the response.

[0364] "Municipal affairs" refers to all activities and operations carried out by local governments to manage their communities and provide public services.

[0365] "Digital transformation cases" refer to specific examples of improvements and innovations that utilize digital technology to improve the efficiency and quality of business operations and services.

[0366] "Diverse sources" refers to different information sources such as the internet, news sites, and official websites.

[0367] "Automatic collection means" refers to methods of collecting information using programs or systems without human intervention.

[0368] "Methods for analyzing collected cases" refers to methods for organizing the information obtained and analyzing it to make its content easier to understand.

[0369] "Keyword categorization" refers to categorizing information based on important words or phrases.

[0370] "Means for storing in a database" refers to the method for storing classified information in a database.

[0371] "Means for analyzing a question received from a user" refers to a method for understanding the content of an inquiry entered by a user and extracting key elements.

[0372] "Means for extracting relevant keywords" refers to a method for finding important words and phrases from the content of a user's question.

[0373] "Means for searching a database and extracting relevant cases" refers to a method of searching a database based on keywords and retrieving relevant information.

[0374] "Means for generating and presenting a response in a user-friendly format" refers to a method for displaying search results in a format that is easy for the user to understand.

[0375] "Means for analyzing user emotions" refers to a method for reading and understanding emotions from user input and behavior.

[0376] The "means for generating a response based on emotions" refers to a method for creating a response with optimal content according to the analyzed emotional state.

[0377] This invention is a system that quickly provides examples of digital transformation related to local government operations and adjusts the content and tone of the response based on the user's emotional state. The invention is implemented through a series of processes consisting of a server, a terminal, and a user.

[0378] The server automatically collects examples of digital transformation in local government operations from various sources, such as the internet and official websites. The collected data is analyzed using text mining technology, and the results are then categorized and stored by keyword. This database stores examples related to keywords such as "AI," "IoT," and "smart city."

[0379] Users input questions about specific cases from their devices. For example, when a query such as "Please tell me about an example of digital transformation in production management using the latest automation technology" is sent to the device, the device sends the query to the query analysis module. The query analysis module, which uses natural language processing technology, analyzes the question and extracts key keywords. An example of a natural language processing library used here is "nlp_library."

[0380] The server searches the database based on the extracted keywords and uses a keyword matching algorithm to prioritize and extract the most relevant cases, such as "the latest case studies using AI for production management."

[0381] Furthermore, the present invention incorporates an emotion engine. When a user inputs a question or receives search results, the device analyzes the user's facial expression, tone of voice, etc., and recognizes the user's emotional state through the emotion engine. For example, "emotion_engine" is used.

[0382] Based on the detected emotional state, the server generates an appropriate response. This response is generated using natural language generation technology with a tone and content that reflects the user's emotional state. For example, if the user is feeling stressed, the server may generate a response such as, "A case study on a production management system using automation technology is effective in not only improving efficiency but also reducing employee stress," allowing the user to receive the information with peace of mind.

[0383] Finally, the device displays the generated response to the user, who can review the provided response and obtain the necessary information. If the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[0384] As a concrete example, consider the following prompt sentence: If a user types, "Please tell me about an example of digital transformation in production management using the latest automation technology," the system can detect the user's stress level from the tone of their voice and generate a response such as, "Here is an example that is effective in both improving efficiency and reducing employee stress." In this way, it is possible to provide the optimal response tailored to the user's emotional state.

[0385] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0386] Step 1:

[0387] The server collects digital transformation case studies related to local government operations from various sources. Specifically, the server scrapes information from the internet, news sites, official websites, etc. It receives the source URL as input and saves the collected data in text format as output.

[0388] Step 2:

[0389] The server analyzes the collected data. Specifically, it uses text mining technology to extract important information. For example, it uses the natural language processing library "nlp_library" to tokenize the data and extract keywords. The input is the collected text data, and the output is keywords and important phrases.

[0390] Step 3:

[0391] The server classifies the analyzed data by keyword and stores it in a database. Specifically, it categorizes the data based on the extracted keywords and stores related information systematically. The input is the analyzed keywords, and the output is a database entry organized by keyword.

[0392] Step 4:

[0393] The user inputs a question about a specific case study from the terminal. The user inputs a query such as, "Please tell me about an example of digital transformation of production management using the latest automation technology." The input is the user's text query, and the output is the query sent to the terminal.

[0394] Step 5:

[0395] The device analyzes the user's question and extracts relevant keywords. Specifically, it uses natural language processing technology to analyze the query and extract key keywords. For example, it uses "nlp_library" to obtain keywords such as "automation," "production management," and "digital transformation" from the question's text data. The user's text query is sent as input, and the extracted keywords are sent as output to the server.

[0396] Step 6:

[0397] The server searches the database based on the extracted keywords and extracts relevant cases. Specifically, it uses a keyword matching algorithm to find relevant cases. The input is the keywords, and the output is a list of highly relevant cases.

[0398] Step 7:

[0399] The device analyzes the user's emotions. Specifically, the device's camera and microphone are used to analyze the user's facial expressions and tone of voice using the emotion engine "emotion_engine." The input is the user's voice and video data, and the output is the user's emotional state, which is sent to the server.

[0400] Step 8:

[0401] The server generates a response based on the user's emotional state. Specifically, it uses natural language generation technology to create a response that reflects the user's emotional state. For example, if the user is feeling stressed, it generates a response with a relaxing tone. The input is the relevant case and the user's emotional state, and the output is the generated response text, which is sent to the terminal.

[0402] Step 9:

[0403] The device displays the generated response to the user, either by displaying the text on the screen or, if necessary, by using speech synthesis technology to read it aloud. The input is the generated response text, and the output is information provided to the user in a format that is easy to understand.

[0404] Step 10:

[0405] The user provides feedback, such as the satisfaction with the search results or the response content. The input is the user's feedback, and the output is the feedback sent to the server.

[0406] Step 11:

[0407] The server analyzes the feedback and improves the search algorithm and response generation process. The input is user feedback data, and the output is an improved algorithm or generation process. This improves the overall performance of the system and provides more personalized information.

[0408] This series of steps enables the system that is the subject of the invention to quickly and accurately provide an appropriate response that takes into account the user's emotional state.

[0409] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0410] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0411] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0412] [Second embodiment]

[0413] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0414] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0415] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0416] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0417] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0418] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0419] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0420] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0421] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0422] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0423] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0424] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0425] The present invention relates to a system for quickly providing examples of digital transformation (DX) related to local government operations. The system is specifically implemented using the following means.

[0426] First, the server collects digital transformation case studies related to local government operations from a variety of sources, including the internet, specialized news sites, and public reports from local governments. The collected data is then analyzed using text mining technology to extract keywords.

[0427] The server then categorizes the collected case data by keyword and stores it in a database. This database is used to efficiently manage various cases of local government work and provides a quick response to subsequent search processing.

[0428] When a user inputs a question, they enter a query into the terminal, such as "I would like to know about examples of AI being used in local governments." The terminal then sends this query to the query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords "local government," "AI," and "examples."

[0429] The server then searches the database based on the extracted keywords. The search results might include examples such as "Fukuoka City's AI-based snow removal management system" or "Osaka City's AI-based tourist information system." This search process uses a keyword-matching algorithm to prioritize the most relevant examples.

[0430] The server then generates a response based on the search results. The generated response is formatted to be easily understood by the user. For example, a response might be created in the form of, "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work."

[0431] Finally, the device displays the generated response to the user. The user can then obtain specific information based on the response. The user can also provide feedback on the response, for example, by typing "This information is useful" into the device. The device then sends this feedback to the server, which analyzes it and uses it to improve the search algorithm. Repeating this process improves the accuracy of the entire system.

[0432] In this way, digital transformation case studies for municipal operations can be provided quickly, and support will be provided to municipal employees and staff to efficiently advance proposals.

[0433] The processing flow will be explained below.

[0434] Step 1:

[0435] The server automatically collects data on digital transformation cases from the internet, news sites, official local government websites, etc. This collection activity is carried out periodically, and new cases are added to the database.

[0436] Step 2:

[0437] The server analyzes the collected data using text mining technology. This analysis extracts key keywords for each case study, such as "AI," "IoT," and "smart city."

[0438] Step 3:

[0439] The server categorizes the case data by keyword based on the extracted keywords. This categorization is used to create a database. The database organizes and stores cases related to each keyword.

[0440] Step 4:

[0441] The user inputs a question about a specific case into the terminal. For example, a question such as, "I would like to know about cases where AI has been used in local governments."

[0442] Step 5:

[0443] The device sends the user's question to the query analysis module, which uses natural language processing technology to analyze the question and extract key keywords such as "local government," "AI," and "case study."

[0444] Step 6:

[0445] The server searches the database based on the analyzed keywords. Using a keyword matching algorithm, it prioritizes the most relevant cases. For example, search results might include "Fukuoka City's AI-based snow removal management system."

[0446] Step 7:

[0447] The server generates a response to present to the user based on the search results. This response is formatted using natural language processing technology in a format that is easy for the user to understand. For example, a response such as "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work" may be created.

[0448] Step 8:

[0449] The terminal displays the generated response to the user, who can review the provided response and obtain any required details.

[0450] Step 9:

[0451] The user inputs feedback on the response into the terminal, for example, "This information is useful."

[0452] Step 10:

[0453] The device sends user feedback to the server, which analyzes it and refines the search algorithm and how the database is organized. This self-improvement process improves the accuracy of responses to the next query.

[0454] Example 1

[0455] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0456] There is a need for a system that can quickly collect, classify, and search examples of digital transformation (DX) related to local government operations and provide appropriate information in response to user requests. Current systems have the problem of taking time to collect, analyze, and search information, preventing users from quickly accessing the information they need. Furthermore, there is no well-established method for effectively utilizing user feedback, making it difficult to improve the accuracy of the entire system.

[0457] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0458] In this invention, the server includes means for automatically collecting digital transformation cases related to local government operations from a variety of sources, means for analyzing the collected data using natural language processing technology to extract keywords, and means for categorizing the analyzed data by keyword and storing it in a database, thereby enabling users to quickly and accurately access the DX cases they need.

[0459] "Municipal business" refers to all business activities carried out by local governments, such as administrative services and public works.

[0460] "Digital transformation (DX)" is an initiative that utilizes digital technology to reform business processes and improve efficiency and service quality.

[0461] "Means of collection" refers to the technical methods and tools used to automatically obtain the required information from various sources.

[0462] "Natural language processing technology" is a general term for algorithms and methods that enable computers to understand, process, and generate human language.

[0463] "Means of analysis" refers to the technical process of analyzing collected data using machine learning and statistical methods to extract meaningful information.

[0464] "Keywords" refer to important words or phrases related to a particular theme or topic.

[0465] "Classification" refers to the process of grouping analyzed information based on specific criteria and organizing it into a more manageable form.

[0466] A "database" is a data storage system that is an organized collection of data stored in a form that allows for efficient retrieval and processing.

[0467] "User" refers to a person who uses the system to input information and obtain output.

[0468] A "query" refers to a question or search phrase that a user enters to request information from a system.

[0469] A "search algorithm" refers to a computational method or rule for efficiently finding information in a database based on specific criteria.

[0470] The "means of generating a response" refers to the process of formatting and outputting the information so that the search results are displayed in a way that is easy for the user to understand.

[0471] "Display means" refers to a technology for visually presenting the generated information on the user's terminal.

[0472] "Feedback" refers to the evaluation and opinion information that users give to the system.

[0473] MODE FOR CARRYING OUT THE INVENTION

[0474] This invention relates to a system for quickly providing examples of digital transformation (DX) related to local government operations. Specific embodiments of this system are described below.

[0475] First, the server collects digital transformation case studies related to municipal operations from various sources. Specifically, it uses web scraping tools such as Python's BeautifulSoup and Scrapy to obtain information from the Internet, specialized news sites, and public reports published by the municipality. The collected data is temporarily stored in local storage.

[0476] The server then analyzes the collected data using natural language processing technologies such as Python's NLTK (Natural Language Toolkit) and spaCy to extract important keywords from the text data. For example, keywords such as "Fukuoka City," "AI," and "snow removal management system" are extracted.

[0477] The analyzed data is classified by keywords, for example using the k-means clustering algorithm to group related data, and then stored in a MySQL database to provide fast responses for subsequent searches.

[0478] When a user inputs information they want to know into a device, they enter a query such as, "I want to know about cases where AI is being used in local governments." The device then sends this query to the server's query analysis module. The server then uses natural language processing (NLP) to analyze the query and extract key keywords such as "local government," "AI," and "case studies."

[0479] Based on the extracted keywords, the server uses Elasticsearch to search the MySQL database, finding related cases such as "Fukuoka City's AI-based snow removal management system" and "Osaka City's AI-based tourist information system."

[0480] The server generates a response based on the search results. This response is generated using Python's Jinja2 template engine, providing information that is easy for the user to understand. For example, the generated response might be expressed in a format such as, "Fukuoka City has introduced a snow removal management system using AI, enabling efficient snow removal work."

[0481] Finally, the device generates and displays the response to the user, using HTML and CSS to present it in a visually friendly format.

[0482] Users can also provide feedback on the information provided. For example, they can input feedback such as "This information is useful" into the device. The device then sends this feedback to the server, which analyzes it and uses it to improve the search algorithm. The feedback is analyzed using Python's Pandas library, which updates the machine learning model to improve the system's accuracy.

[0483] For example, a user may enter a prompt such as, "Please tell me more about examples of how AI has been used in local governments." In response to this prompt, the system can quickly and accurately generate and provide a response through the steps described above.

[0484] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0485] System program processing flow

[0486] Step 1:

[0487] Data collection

[0488] The server collects digital transformation case studies related to municipal operations from a variety of sources, including the internet, specialized news sites, and public reports from municipalities. Specifically, it performs web scraping using Python's BeautifulSoup and Scrapy to obtain the necessary text data.

[0489] Input: Request URL

[0490] Output: Collected text data

[0491] Step 2:

[0492] Data analysis

[0493] The server analyzes the collected text data using natural language processing libraries such as Python's NLTK and spaCy to extract important keywords from the text content. For example, keywords such as "Fukuoka City," "AI," and "snow removal management system" are extracted.

[0494] Input: Collected text data

[0495] Output: Extracted keyword list

[0496] Step 3:

[0497] Data classification and storage

[0498] The server categorizes the data based on the extracted keywords, using the k-means clustering algorithm to group related data, and then stores the categorized data in a MySQL database for efficient management.

[0499] Input: Extracted keyword list

[0500] Output: Classified data, stored database records

[0501] Step 4:

[0502] Entering a query

[0503] The user inputs the information they want to know into the device. For example, they input a query such as, "I want to know about cases where AI is being used in local governments."

[0504] Input: User query

[0505] Output: The device sends a query to the server

[0506] Step 5:

[0507] Query Analysis

[0508] The device sends the user's query to the server's query analysis module, which then uses natural language processing technology to analyze the query and extract key keywords such as "local government," "AI," and "case study."

[0509] Input: User query

[0510] Output: Extracted query keywords

[0511] Step 6:

[0512] Searching the database

[0513] The server uses Elasticsearch to search the MySQL database based on the extracted keywords. This search process finds related case studies. For example, case studies such as "Fukuoka City's AI-based snow removal management system" and "Osaka City's AI-based tourist information system" are listed.

[0514] Input: Extracted query keywords

[0515] Output: List of related cases

[0516] Step 7:

[0517] Generating a response

[0518] The server uses Python's Jinja2 template engine to generate a response based on the search results. To provide users with easy-to-understand information, the generated response is expressed in a format such as, "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work."

[0519] Input: List of related cases

[0520] Output: The generated response

[0521] Step 8:

[0522] Viewing the response

[0523] The terminal then displays the generated response to the user, formatting it using HTML and CSS to make the information visually appealing.

[0524] Input: Generated response

[0525] Output: Displayed response

[0526] Step 9:

[0527] Gathering feedback

[0528] The user provides feedback on the provided information. For example, they input feedback such as "This information is useful" into the terminal. The terminal sends this feedback to the server, which analyzes it using the Python Pandas library and improves the search algorithm based on this feedback.

[0529] Input: User feedback

[0530] Output: Improved search algorithm

[0531] This will enable the entire system to quickly provide examples of digital transformation related to local government operations and appropriately present information that meets users' needs.

[0532] (Application example 1)

[0533] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0534] Customer service in modern brick-and-mortar stores requires the provision of fast and accurate information, but it is difficult for store staff to efficiently utilize the vast amount of information available to answer customers. Responses are often delayed, particularly when providing similar questions or information about specific products. Therefore, in order to improve service in brick-and-mortar stores, a system that can provide fast and accurate information is needed.

[0535] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0536] In this invention, the server includes means for automatically collecting digital transformation case studies related to local government operations from a variety of sources, means for analyzing the collected case studies and categorizing them by keyword and storing them in a database, means for analyzing questions received from users and extracting related keywords, means for searching the database based on the extracted keywords and extracting related case studies, means for generating and presenting responses in a user-friendly format based on the extracted case studies, and means for providing optimal responses to customer questions within a smartphone application. This enables fast and accurate customer service in physical stores.

[0537] Definitions of important terms contained in the claims

[0538] "Municipal Affairs"

[0539] It refers to a series of administrative and service activities carried out by local governments.

[0540] "Digital Transformation Case Studies"

[0541] This refers to concrete examples of how digital technology has improved and transformed business processes and services.

[0542] "sauce"

[0543] It refers to the source or reference from which information or data is obtained.

[0544] "means"

[0545] refers to the methods or technical elements used to achieve a specific purpose.

[0546] "analysis"

[0547] It refers to the detailed examination of data and information to clarify its meaning and content.

[0548] "keyword"

[0549] refers to important words or terms to use as search and classification criteria.

[0550] Database

[0551] It refers to a collection of data that is organized in an organized manner, and a system for efficiently searching and manipulating specific data.

[0552] "User"

[0553] refers to the individuals or organizations that use the system or application.

[0554] "question"

[0555] It refers to the linguistic expression of the information a user wants to know or the problem they want to solve.

[0556] "response"

[0557] refers to information provided in response to a question or question.

[0558] "Smartphone"

[0559] refers to a portable electronic device that combines mobile communication and computer functions.

[0560] "application"

[0561] refers to a software program designed for a specific purpose.

[0562] "customer"

[0563] refers to the person or entity that purchases or uses a product or service.

[0564] "Natural language processing technology"

[0565] refers to computer technology for understanding and processing human language.

[0566] MODE FOR CARRYING OUT THE INVENTION

[0567] The system of the present invention collects examples of digital transformation related to local government operations and presents relevant examples in response to queries from users. Specific embodiments of the system will be described below.

[0568] Hardware and software used

[0569] Hardware: Standard servers, smartphones

[0570] Software: Python, requests (for data collection), BeautifulSoup (for HTML analysis), spaCy (natural language processing)

[0571] System processing flow

[0572] The server first automatically collects digital transformation case studies related to local government operations from a variety of sources, including online news sites and public reports from local governments.

[0573] The collected cases are analyzed using text mining technology and classified by keyword. During this process, important keywords are extracted from the text data using spaCy. The extracted keywords are stored in a database, allowing for quick response to subsequent search processing.

[0574] When a user accesses the application using a smartphone and enters a question, the question is first received by the device, then sent to the server where it is analyzed using natural language processing technology. This analysis extracts the main keywords contained in the question.

[0575] The server then searches the database based on the extracted keywords. The search results yield relevant cases, which are then presented to the customer within the smartphone application. For example, in response to the question, "What products are popular these days?", a response such as, "The most popular product over the past six months is the new smartphone model" is generated.

[0576] The generated response is displayed to the user in a user-friendly format, and the user can provide feedback on the response, which is then sent back to the server to help refine the search algorithm, thereby improving the accuracy of the entire system.

[0577] Examples and prompts

[0578] For example, if a user asks the following question:

[0579] What products are popular these days?

[0580] The system uses a generative AI model to generate a response using the following prompt:

[0581] Question: "What are the most popular products these days?"

[0582] Prompt: Please provide examples related to the following keywords: "popular" and "product"

[0583] In response to this,

[0584] "The most popular products over the past six months have been new smartphone models. This was confirmed based on sales data in specific regions."

[0585] The information is provided to the user in this format.

[0586] In this way, customer service can be provided quickly and accurately in physical stores.

[0587] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0588] Detailed program processing flow

[0589] Step 1: Data collection

[0590] The server first automatically collects digital transformation case studies related to municipal operations from a variety of sources, such as online news sites and public reports from municipalities. This collection process uses the Python requests library to obtain the contents of web pages. The obtained HTML data is then analyzed using the BeautifulSoup library and extracted as text data.

[0591] Enter: Website URL

[0592] Output: Extract text data from HTML content

[0593] Specific operation: The server sends an HTTP request to the specified URL, analyzes the received HTML data, and saves it as text.

[0594] Step 2: Text mining

[0595] The collected text data is analyzed using text mining techniques. The server uses the spaCy library to extract important keywords from the text data, which makes the data more organized and streamlines the subsequent search process.

[0596] Input: Text data

[0597] Output: Extracted keyword list

[0598] What it does: The server feeds the text data into a natural language processing library to extract noun phrases and other important keywords.

[0599] Step 3: Database storage

[0600] The extracted keywords and their corresponding examples are stored in a database that is designed to enable rapid response to subsequent search processes.

[0601] Input: A list of keywords and their corresponding examples

[0602] Output: Structured data stored in a database

[0603] Specific operation: The server stores keywords and their related cases in a database and sets up an index to enable efficient searches.

[0604] Step 4: Receiving and parsing user queries

[0605] A user accesses the application using a smartphone and enters a question. This question is received by the device and sent to the server, which uses natural language processing techniques to analyze the question and extract key keywords, again using the spaCy library.

[0606] Input: User's question (in text format)

[0607] Output: Extracted keywords

[0608] How it works: The device receives user input and sends it to the server, which then uses NLP technology to analyze the question and extract key keywords.

[0609] Step 5: Database Search

[0610] The server searches the database based on the extracted keywords and extracts relevant cases using a keyword matching search algorithm.

[0611] Input: Extracted keywords

[0612] Output: List of related cases

[0613] Specific operation: The server searches the database and extracts cases that match the keywords.

[0614] Step 6: Response generation and presentation

[0615] Based on the extracted cases, the server generates a response in a user-friendly format and sends it to the terminal, which then displays the response to the user.

[0616] Input: List of related cases

[0617] Output: The response that is presented to the user

[0618] Specific operation: The server generates an easy-to-understand response based on the case data and sends it to the terminal, which then displays the response on the user's screen.

[0619] Step 7: Gather feedback and improve the algorithm

[0620] Users can provide feedback on the responses provided, which is sent back to the server to help improve the search algorithm.

[0621] Input: User feedback (text format)

[0622] Output: Improved search algorithm

[0623] How it works: The device receives feedback and sends it to the server, which analyzes it and uses it to improve the algorithm.

[0624] This will enable quick and accurate customer service in physical stores.

[0625] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0626] This invention combines an emotion engine with a system for quickly providing examples of digital transformation (DX) related to local government operations. Specifically, this invention is implemented using the following means.

[0627] First, the server collects digital transformation case studies related to local government operations from a variety of sources, including the internet, news sites, and official local government websites, and then analyzes the collected data using text mining technology.

[0628] The server then extracts keywords from the analyzed data and stores the collected cases in a database, categorizing them by keyword. This database neatly stores cases related to keywords such as "AI," "IoT," and "smart city."

[0629] When a user inputs a question about a specific case into the device, a query such as "I would like to know about cases where AI has been used in local governments" is sent to the device. The device then sends this query to a query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords "local government," "AI," and "case study."

[0630] The server then searches the database based on the extracted keywords, using a keyword matching algorithm to prioritize the most relevant cases, such as "Fukuoka City's AI-based snow removal management system."

[0631] Furthermore, the present invention incorporates an emotion engine. When a user inputs a question or receives search results, the device analyzes the user's facial expression, tone of voice, etc., and recognizes the user's emotional state through the emotion engine. For example, if the user is feeling dissatisfied, the device will prioritize providing examples and answers that correspond to that emotional state.

[0632] The server generates a response based on the detected emotional state. This response is generated using natural language processing technology with a tone and content that reflects the user's emotional state. For example, a response could be created that reads, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work and has received high praise from citizens."

[0633] Finally, the device displays the generated response to the user, who can review the provided response and obtain necessary information. If the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[0634] In this way, not only can digital transformation examples related to municipal operations be provided quickly, but the content and tone of the response can be adjusted depending on the user's emotional state, resulting in more personalized information provision.

[0635] The processing flow will be explained below.

[0636] Step 1:

[0637] The server automatically collects examples of digital transformation related to local government operations from the internet, news sites, official local government websites, etc. This collection is set to occur periodically, and new examples are added to the database.

[0638] Step 2:

[0639] The server analyzes the collected data using text mining technology to extract key keywords for each case study, which are then categorized into categories such as "AI," "IoT," and "smart city."

[0640] Step 3:

[0641] The server categorizes the case data based on the extracted keywords and stores them in a structured database, where related cases are stored in a searchable format for each keyword.

[0642] Step 4:

[0643] The user inputs a question about a specific case into the terminal. For example, a question might be input such as, "I would like to know about cases where AI has been used in local governments."

[0644] Step 5:

[0645] The device sends the entered question to the query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords: "municipal government," "AI," and "case study."

[0646] Step 6:

[0647] During query analysis, the device analyzes the user's facial expressions and tone of voice using an emotion engine, which recognizes the user's emotional state (e.g., frustration, interest, joy, etc.) and sends that information to the query analysis module.

[0648] Step 7:

[0649] The server searches the database based on the extracted keywords and emotional state. Using a keyword matching algorithm, it prioritizes and extracts highly relevant cases. Specifically, it finds cases such as "Fukuoka City's AI-based snow removal management system."

[0650] Step 8:

[0651] When generating a response based on the search results, the server takes into account the user's emotional state obtained from the emotion engine. For example, if the user is dissatisfied, the tone of the response will be more considerate. The response is generated using natural language processing technology and formatted as, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work. It has received high praise from citizens."

[0652] Step 9:

[0653] The terminal displays the generated response to the user, who can obtain specific information based on the provided response.

[0654] Step 10:

[0655] The user inputs feedback on the response into the terminal, such as "This information is useful" or "I'd like to know more specific examples."

[0656] Step 11:

[0657] The device sends the collected feedback to the server, which analyzes it and uses it to refine the search algorithm and response generation process. This self-improvement process improves the accuracy of the response to the next query.

[0658] In this way, it is possible to quickly provide examples of digital transformation for municipal operations and generate responses that reflect the user's emotional state.

[0659] Example 2

[0660] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0661] Currently, there are problems with collecting examples of digital transformation in municipal operations and with responding quickly and specifically to user questions. There is also a lack of systems that generate personalized responses based on user sentiment. This makes it difficult for municipal employees and residents to obtain the information they need in a timely manner. Furthermore, there is an insufficient mechanism for improving the accuracy of the system based on feedback.

[0662] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0663] In this invention, the server includes means for automatically collecting digital transformation case studies related to local government operations from a variety of sources, means for analyzing the collected case studies and categorizing them by keyword and storing them in a database, means for analyzing questions received from users and extracting related keywords, means for searching the database based on the extracted keywords and extracting related case studies, means for generating and presenting a response in a format easy for the user to understand based on the extracted case studies, means for analyzing the user's emotional state and adjusting the content of the response, means for generating a response personalized for the user, and means for collecting feedback from users and improving the search algorithm based on the feedback, thereby making it possible to provide necessary information quickly and appropriately.

[0664] "Municipal services" is a general term for the various services and administrative procedures that local governments and regional administrative agencies provide to local residents.

[0665] "Digital transformation" refers to the use of information technology to innovate business processes and service delivery methods in order to improve efficiency and optimization.

[0666] "DX cases" refer to examples of specific results and initiatives that have been implemented through digital transformation.

[0667] "Source" refers to the source of information or the source of data.

[0668] "Collection means" refers to the specific methods or devices used to collect information or data.

[0669] "Analysis tools" refers to methods and software used to analyze collected data and understand and classify its contents.

[0670] "Keywords" refer to important words or phrases in the data or question.

[0671] A "database" refers to an information management system for systematically organizing and storing data.

[0672] A "question" refers to a query entered by a user to ask for information or an example they want to know.

[0673] "Extraction means" refers to the methods and techniques for extracting the necessary information from the analyzed data and keywords.

[0674] "Search methods" refer to methods and techniques for investigating and verifying information in a database.

[0675] "Response methods" refers to the methods and techniques used to provide information to users based on search results.

[0676] "Emotional state" refers to a user's current psychological state or feelings.

[0677] "Emotion analysis means" refers to methods or techniques for analyzing a user's facial expressions and tone of voice to determine their emotional state.

[0678] "Personalized responses" refer to providing specific information tailored to a user's individual needs and emotions.

[0679] "Feedback" refers to opinions and ratings provided by users.

[0680] A "search algorithm" refers to a procedure or calculation method for efficiently searching for information in a database.

[0681] The present invention is a system for quickly providing examples of digital transformation (DX) related to local government operations, and is combined with an emotion engine. This system is specifically implemented using the following means.

[0682] The server automatically collects digital transformation case studies related to local government operations from a variety of sources, including online news sites and official local government websites. This collection is performed using web crawler tools such as Apache Nutch. The collected data is then analyzed using text mining techniques such as Apache OpenNLP.

[0683] The server extracts key keywords from the analyzed data and categorizes them by case, for example, into categories such as "AI," "IoT," and "smart city," and stores them in a MySQL or PostgreSQL database.

[0684] When a user enters a specific question into the device (e.g., "I would like to know about examples of AI use in local governments"), the device sends the question to a query analysis module (e.g., NLTK or SpaCy), which uses natural language processing technology to extract key keywords. The analysis results are then sent to the server.

[0685] The server then searches the database based on the extracted keywords and uses a keyword matching algorithm such as Elasticsearch to extract the most relevant examples, such as a specific example like "Fukuoka City's AI-based snow removal management system."

[0686] The present invention also incorporates an emotion engine. When a user enters a question or receives search results, the device uses a webcam and microphone to collect the user's facial expressions and tone of voice. Using emotion analysis tools such as OpenFace and IBM Watson Tone Analyzer, the device recognizes the user's emotional state. For example, if the user is dissatisfied, the relevant examples and response content are adjusted based on that emotional state.

[0687] The server generates a response based on the emotion-analyzed data. This response is generated using natural language processing technology with a generative AI model (e.g., OpenAI GPT-3) and its tone and content reflect the user's emotional state. For example, a response such as, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work and has been well received by citizens" may be generated.

[0688] The device displays the generated response to the user, who can review the provided information and gain the necessary knowledge. When the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[0689] Specific examples

[0690] Example 1:

[0691] User: "I want to know about examples of smart city development."

[0692] The server searches for relevant cases and finds "City X's Smart City Project." The device analyzes the user's emotions and generates a response in a reassuring tone: "City X's Smart City Project has been a success, and the quality of life for its residents has improved significantly."

[0693] Example prompt sentence:

[0694] "I'd like to know more about the AI-based snow removal management system in Fukuoka City."

[0695] "Please tell us some examples of successful smart city projects."

[0696] "Please introduce some examples of IoT implementation in local governments."

[0697] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0698] Step 1: Collect data

[0699] The server automatically collects digital transformation examples related to local government operations from a variety of sources, specifically by periodically collecting data from online news sites and official local government websites using web crawler tools such as Apache Nutch.

[0700] Input: URL list of various internet sources

[0701] How it works: The web crawler visits pages from a set list of URLs at a specified interval and collects text data.

[0702] Output: raw collected data (text)

[0703] Step 2: Data analysis and keyword extraction

[0704] The server analyzes the collected raw data and uses text mining techniques such as Apache OpenNLP to extract keywords, tokenizing sentences and extracting key keywords such as nouns and verbs.

[0705] Input: Collected raw data (text)

[0706] How it works: The text analysis module tokenizes the data and runs it through analysis algorithms to extract keywords.

[0707] Output: Parsed data and extracted keyword list

[0708] Step 3: Classify and store data

[0709] The server categorizes the analyzed data based on the extracted keywords and stores it in a database such as MySQL or PostgreSQL. The categorized data is then organized for later searches and queries.

[0710] Input: Parsed data and extracted keyword list

[0711] How it works: The data classification module categorizes data based on a list of keywords and connects to a database to store the information.

[0712] Output: A database containing data sorted by category

[0713] Step 4: Receiving a query

[0714] The user inputs a specific question into the device. For example, a query such as "I would like to know about examples of how local governments have used AI" is entered.

[0715] Input: The question (query) entered by the user

[0716] Operation: The terminal receives input from the user through the query receiving module.

[0717] Output: Received query

[0718] Step 5: Query analysis and keyword extraction

[0719] The device analyzes the received query and uses natural language processing techniques (e.g., NLTK or SpaCy) to extract key keywords. The analysis results are sent to the server.

[0720] Input: Received query

[0721] How it works: The query analysis module tokenizes the query and extracts the main keywords.

[0722] Output: Extracted keyword list

[0723] Step 6: Search the database

[0724] The server searches the database based on the extracted keywords and extracts the most relevant cases using a keyword matching algorithm such as Elasticsearch.

[0725] Input: Extracted keyword list

[0726] How it works: The database search module generates a search query based on the keywords and queries the database.

[0727] Output: A list of the most relevant cases

[0728] Step 7: Sentiment Analysis

[0729] The device collects data using a webcam and microphone to analyze the user's facial expressions and tone of voice, using tools such as OpenFace and IBM Watson Tone Analyzer to recognize the user's emotional state.

[0730] Input: User facial expression images and voice data

[0731] How it works: The emotion analysis module analyzes facial expression images and audio data to recognize the user's emotional state.

[0732] Output: Recognized emotion data

[0733] Step 8: Generate a response

[0734] The server generates personalized responses based on the recognized emotion data, using a generative AI model (e.g., OpenAI GPT-3) to create responses appropriate for the user through natural language processing techniques.

[0735] Input: A list of the most relevant cases and recognized emotion data

[0736] How it works: The response generation module uses a generative AI model to generate a response based on relevant examples and sentiment data.

[0737] Output: The generated personalized response

[0738] Step 9: View the response

[0739] The terminal displays the generated response to the user, who reviews the information provided and optionally enters feedback into the terminal.

[0740] Input: The generated personalized response

[0741] Action: The device displays the response on the screen and receives user feedback.

[0742] Output: The response displayed to the user and any feedback entered

[0743] Step 10: Analyze feedback and refine the system

[0744] The server analyzes user feedback and uses the results to improve the search algorithm and response generation process.

[0745] Input: User feedback

[0746] How it works: The feedback analysis module analyzes the feedback and identifies areas for improvement in the search algorithm and response generation process.

[0747] Output: Improved search algorithm and response generation process

[0748] (Application example 2)

[0749] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0750] Conventional systems providing examples of digital transformation for local government operations only present relevant examples in response to user queries, and have the problem of being unable to provide personalized responses according to the user's emotional state. This is particularly difficult in situations where an optimal response according to the user's emotional state is required, such as when the user is feeling stressed or in a hurry, so it was necessary to improve the quality of the responses.

[0751] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting digital transformation case studies related to local government operations from various sources; means for analyzing the collected case studies, classifying them by keyword, and storing them in a database; means for analyzing questions received from users and extracting related keywords; means for searching the database based on the extracted keywords and extracting related case studies; means for generating and presenting a response in a format easy for the user to understand based on the extracted case studies; and means for analyzing the user's emotions and generating a response based on the emotions. This makes it possible to provide an optimal response according to the user's emotional state, improving the quality of the response.

[0752] "Municipal affairs" refers to all activities and operations carried out by local governments to manage their communities and provide public services.

[0753] "Digital transformation cases" refer to specific examples of improvements and innovations that utilize digital technology to improve the efficiency and quality of business operations and services.

[0754] "Diverse sources" refers to different information sources such as the internet, news sites, and official websites.

[0755] "Automatic collection means" refers to methods of collecting information using programs or systems without human intervention.

[0756] "Methods for analyzing collected cases" refers to methods for organizing the information obtained and analyzing it to make its content easier to understand.

[0757] "Keyword categorization" refers to categorizing information based on important words or phrases.

[0758] "Means for storing in a database" refers to the method for storing classified information in a database.

[0759] "Means for analyzing a question received from a user" refers to a method for understanding the content of an inquiry entered by a user and extracting key elements.

[0760] "Means for extracting relevant keywords" refers to a method for finding important words and phrases from the content of a user's question.

[0761] "Means for searching a database and extracting relevant cases" refers to a method of searching a database based on keywords and retrieving relevant information.

[0762] "Means for generating and presenting a response in a user-friendly format" refers to a method for displaying search results in a format that is easy for the user to understand.

[0763] "Means for analyzing user emotions" refers to a method for reading and understanding emotions from user input and behavior.

[0764] The "means for generating a response based on emotions" refers to a method for creating a response with optimal content according to the analyzed emotional state.

[0765] This invention is a system that quickly provides examples of digital transformation related to local government operations and adjusts the content and tone of the response based on the user's emotional state. The invention is implemented through a series of processes consisting of a server, a terminal, and a user.

[0766] The server automatically collects examples of digital transformation in local government operations from various sources, such as the internet and official websites. The collected data is analyzed using text mining technology, and the results are then categorized and stored by keyword. This database stores examples related to keywords such as "AI," "IoT," and "smart city."

[0767] Users input questions about specific cases from their devices. For example, when a query such as "Please tell me about an example of digital transformation in production management using the latest automation technology" is sent to the device, the device sends the query to the query analysis module. The query analysis module, which uses natural language processing technology, analyzes the question and extracts key keywords. An example of a natural language processing library used here is "nlp_library."

[0768] The server searches the database based on the extracted keywords and uses a keyword matching algorithm to prioritize and extract the most relevant cases, such as "the latest case studies using AI for production management."

[0769] Furthermore, the present invention incorporates an emotion engine. When a user inputs a question or receives search results, the device analyzes the user's facial expression, tone of voice, etc., and recognizes the user's emotional state through the emotion engine. For example, "emotion_engine" is used.

[0770] Based on the detected emotional state, the server generates an appropriate response. This response is generated using natural language generation technology with a tone and content that reflects the user's emotional state. For example, if the user is feeling stressed, the server may generate a response such as, "A case study on a production management system using automation technology is effective in not only improving efficiency but also reducing employee stress," allowing the user to receive the information with peace of mind.

[0771] Finally, the device displays the generated response to the user, who can review the provided response and obtain the necessary information. If the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[0772] As a concrete example, consider the following prompt sentence: If a user types, "Please tell me about an example of digital transformation in production management using the latest automation technology," the system can detect the user's stress level from the tone of their voice and generate a response such as, "Here is an example that is effective in both improving efficiency and reducing employee stress." In this way, it is possible to provide the optimal response tailored to the user's emotional state.

[0773] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0774] Step 1:

[0775] The server collects digital transformation case studies related to local government operations from various sources. Specifically, the server scrapes information from the internet, news sites, official websites, etc. It receives the source URL as input and saves the collected data in text format as output.

[0776] Step 2:

[0777] The server analyzes the collected data. Specifically, it uses text mining technology to extract important information. For example, it uses the natural language processing library "nlp_library" to tokenize the data and extract keywords. The input is the collected text data, and the output is keywords and important phrases.

[0778] Step 3:

[0779] The server classifies the analyzed data by keyword and stores it in a database. Specifically, it categorizes the data based on the extracted keywords and stores related information systematically. The input is the analyzed keywords, and the output is a database entry organized by keyword.

[0780] Step 4:

[0781] The user inputs a question about a specific case study from the terminal. The user inputs a query such as, "Please tell me about an example of digital transformation of production management using the latest automation technology." The input is the user's text query, and the output is the query sent to the terminal.

[0782] Step 5:

[0783] The device analyzes the user's question and extracts relevant keywords. Specifically, it uses natural language processing technology to analyze the query and extract key keywords. For example, it uses "nlp_library" to obtain keywords such as "automation," "production management," and "digital transformation" from the question's text data. The user's text query is sent as input, and the extracted keywords are sent as output to the server.

[0784] Step 6:

[0785] The server searches the database based on the extracted keywords and extracts relevant cases. Specifically, it uses a keyword matching algorithm to find relevant cases. The input is the keywords, and the output is a list of highly relevant cases.

[0786] Step 7:

[0787] The device analyzes the user's emotions. Specifically, the device's camera and microphone are used to analyze the user's facial expressions and tone of voice using the emotion engine "emotion_engine." The input is the user's voice and video data, and the output is the user's emotional state, which is sent to the server.

[0788] Step 8:

[0789] The server generates a response based on the user's emotional state. Specifically, it uses natural language generation technology to create a response that reflects the user's emotional state. For example, if the user is feeling stressed, it generates a response with a relaxing tone. The input is the relevant case and the user's emotional state, and the output is the generated response text, which is sent to the terminal.

[0790] Step 9:

[0791] The device displays the generated response to the user, either by displaying the text on the screen or, if necessary, by using speech synthesis technology to read it aloud. The input is the generated response text, and the output is information provided to the user in a format that is easy to understand.

[0792] Step 10:

[0793] The user provides feedback, such as the satisfaction with the search results or the response content. The input is the user's feedback, and the output is the feedback sent to the server.

[0794] Step 11:

[0795] The server analyzes the feedback and improves the search algorithm and response generation process. The input is user feedback data, and the output is an improved algorithm or generation process. This improves the overall performance of the system and provides more personalized information.

[0796] This series of steps enables the system that is the subject of the invention to quickly and accurately provide an appropriate response that takes into account the user's emotional state.

[0797] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0798] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0799] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0800] [Third embodiment]

[0801] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0802] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0803] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0804] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0805] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0806] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0807] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0808] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0809] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0810] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0811] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0812] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0813] The present invention relates to a system for quickly providing examples of digital transformation (DX) related to local government operations. The system is specifically implemented using the following means.

[0814] First, the server collects digital transformation case studies related to local government operations from a variety of sources, including the internet, specialized news sites, and public reports from local governments. The collected data is then analyzed using text mining technology to extract keywords.

[0815] The server then categorizes the collected case data by keyword and stores it in a database. This database is used to efficiently manage various cases of local government work and provides a quick response to subsequent search processing.

[0816] When a user inputs a question, they enter a query into the terminal, such as "I would like to know about examples of AI being used in local governments." The terminal then sends this query to the query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords "local government," "AI," and "examples."

[0817] The server then searches the database based on the extracted keywords. The search results might include examples such as "Fukuoka City's AI-based snow removal management system" or "Osaka City's AI-based tourist information system." This search process uses a keyword-matching algorithm to prioritize the most relevant examples.

[0818] The server then generates a response based on the search results. The generated response is formatted to be easily understood by the user. For example, a response might be created in the form of, "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work."

[0819] Finally, the device displays the generated response to the user. The user can then obtain specific information based on the response. The user can also provide feedback on the response, for example, by typing "This information is useful" into the device. The device then sends this feedback to the server, which analyzes it and uses it to improve the search algorithm. Repeating this process improves the accuracy of the entire system.

[0820] In this way, digital transformation case studies for municipal operations can be provided quickly, and support will be provided to municipal employees and staff to efficiently advance proposals.

[0821] The processing flow will be explained below.

[0822] Step 1:

[0823] The server automatically collects data on digital transformation cases from the internet, news sites, official local government websites, etc. This collection activity is carried out periodically, and new cases are added to the database.

[0824] Step 2:

[0825] The server analyzes the collected data using text mining technology. This analysis extracts key keywords for each case study, such as "AI," "IoT," and "smart city."

[0826] Step 3:

[0827] The server categorizes the case data by keyword based on the extracted keywords. This categorization is used to create a database. The database organizes and stores cases related to each keyword.

[0828] Step 4:

[0829] The user inputs a question about a specific case into the terminal. For example, a question such as, "I would like to know about cases where AI has been used in local governments."

[0830] Step 5:

[0831] The device sends the user's question to the query analysis module, which uses natural language processing technology to analyze the question and extract key keywords such as "local government," "AI," and "case study."

[0832] Step 6:

[0833] The server searches the database based on the analyzed keywords. Using a keyword matching algorithm, it prioritizes the most relevant cases. For example, search results might include "Fukuoka City's AI-based snow removal management system."

[0834] Step 7:

[0835] The server generates a response to present to the user based on the search results. This response is formatted using natural language processing technology in a format that is easy for the user to understand. For example, a response such as "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work" may be created.

[0836] Step 8:

[0837] The terminal displays the generated response to the user, who can review the provided response and obtain any required details.

[0838] Step 9:

[0839] The user inputs feedback on the response into the terminal, for example, "This information is useful."

[0840] Step 10:

[0841] The device sends user feedback to the server, which analyzes it and refines the search algorithm and how the database is organized. This self-improvement process improves the accuracy of responses to the next query.

[0842] Example 1

[0843] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0844] There is a need for a system that can quickly collect, classify, and search examples of digital transformation (DX) related to local government operations and provide appropriate information in response to user requests. Current systems have the problem of taking time to collect, analyze, and search information, preventing users from quickly accessing the information they need. Furthermore, there is no well-established method for effectively utilizing user feedback, making it difficult to improve the accuracy of the entire system.

[0845] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0846] In this invention, the server includes means for automatically collecting digital transformation cases related to local government operations from a variety of sources, means for analyzing the collected data using natural language processing technology to extract keywords, and means for categorizing the analyzed data by keyword and storing it in a database, thereby enabling users to quickly and accurately access the DX cases they need.

[0847] "Municipal business" refers to all business activities carried out by local governments, such as administrative services and public works.

[0848] "Digital transformation (DX)" is an initiative that utilizes digital technology to reform business processes and improve efficiency and service quality.

[0849] "Means of collection" refers to the technical methods and tools used to automatically obtain the required information from various sources.

[0850] "Natural language processing technology" is a general term for algorithms and methods that enable computers to understand, process, and generate human language.

[0851] "Means of analysis" refers to the technical process of analyzing collected data using machine learning and statistical methods to extract meaningful information.

[0852] "Keywords" refer to important words or phrases related to a particular theme or topic.

[0853] "Classification" refers to the process of grouping analyzed information based on specific criteria and organizing it into a more manageable form.

[0854] A "database" is a data storage system that is an organized collection of data stored in a form that allows for efficient retrieval and processing.

[0855] "User" refers to a person who uses the system to input information and obtain output.

[0856] A "query" refers to a question or search phrase that a user enters to request information from a system.

[0857] A "search algorithm" refers to a computational method or rule for efficiently finding information in a database based on specific criteria.

[0858] The "means of generating a response" refers to the process of formatting and outputting the information so that the search results are displayed in a way that is easy for the user to understand.

[0859] "Display means" refers to a technology for visually presenting the generated information on the user's terminal.

[0860] "Feedback" refers to the evaluation and opinion information that users give to the system.

[0861] MODE FOR CARRYING OUT THE INVENTION

[0862] This invention relates to a system for quickly providing examples of digital transformation (DX) related to local government operations. Specific embodiments of this system are described below.

[0863] First, the server collects digital transformation case studies related to municipal operations from various sources. Specifically, it uses web scraping tools such as Python's BeautifulSoup and Scrapy to obtain information from the Internet, specialized news sites, and public reports published by the municipality. The collected data is temporarily stored in local storage.

[0864] The server then analyzes the collected data using natural language processing technologies such as Python's NLTK (Natural Language Toolkit) and spaCy to extract important keywords from the text data. For example, keywords such as "Fukuoka City," "AI," and "snow removal management system" are extracted.

[0865] The analyzed data is classified by keywords, for example using the k-means clustering algorithm to group related data, and then stored in a MySQL database to provide fast responses for subsequent searches.

[0866] When a user inputs information they want to know into a device, they enter a query such as, "I want to know about cases where AI is being used in local governments." The device then sends this query to the server's query analysis module. The server then uses natural language processing (NLP) to analyze the query and extract key keywords such as "local government," "AI," and "case studies."

[0867] Based on the extracted keywords, the server uses Elasticsearch to search the MySQL database, finding related cases such as "Fukuoka City's AI-based snow removal management system" and "Osaka City's AI-based tourist information system."

[0868] The server generates a response based on the search results. This response is generated using Python's Jinja2 template engine, providing information that is easy for the user to understand. For example, the generated response might be expressed in a format such as, "Fukuoka City has introduced a snow removal management system using AI, enabling efficient snow removal work."

[0869] Finally, the device generates and displays the response to the user, using HTML and CSS to present it in a visually friendly format.

[0870] Users can also provide feedback on the information provided. For example, they can input feedback such as "This information is useful" into the device. The device then sends this feedback to the server, which analyzes it and uses it to improve the search algorithm. The feedback is analyzed using Python's Pandas library, which updates the machine learning model to improve the system's accuracy.

[0871] For example, a user may enter a prompt such as, "Please tell me more about examples of how AI has been used in local governments." In response to this prompt, the system can quickly and accurately generate and provide a response through the steps described above.

[0872] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0873] System program processing flow

[0874] Step 1:

[0875] Data collection

[0876] The server collects digital transformation case studies related to municipal operations from a variety of sources, including the internet, specialized news sites, and public reports from municipalities. Specifically, it performs web scraping using Python's BeautifulSoup and Scrapy to obtain the necessary text data.

[0877] Input: Request URL

[0878] Output: Collected text data

[0879] Step 2:

[0880] Data analysis

[0881] The server analyzes the collected text data using natural language processing libraries such as Python's NLTK and spaCy to extract important keywords from the text content. For example, keywords such as "Fukuoka City," "AI," and "snow removal management system" are extracted.

[0882] Input: Collected text data

[0883] Output: Extracted keyword list

[0884] Step 3:

[0885] Data classification and storage

[0886] The server categorizes the data based on the extracted keywords, using the k-means clustering algorithm to group related data, and then stores the categorized data in a MySQL database for efficient management.

[0887] Input: Extracted keyword list

[0888] Output: Classified data, stored database records

[0889] Step 4:

[0890] Entering a query

[0891] The user inputs the information they want to know into the device. For example, they input a query such as, "I want to know about cases where AI is being used in local governments."

[0892] Input: User query

[0893] Output: The device sends a query to the server

[0894] Step 5:

[0895] Query Analysis

[0896] The device sends the user's query to the server's query analysis module, which then uses natural language processing technology to analyze the query and extract key keywords such as "local government," "AI," and "case study."

[0897] Input: User query

[0898] Output: Extracted query keywords

[0899] Step 6:

[0900] Searching the database

[0901] The server uses Elasticsearch to search the MySQL database based on the extracted keywords. This search process finds related case studies. For example, case studies such as "Fukuoka City's AI-based snow removal management system" and "Osaka City's AI-based tourist information system" are listed.

[0902] Input: Extracted query keywords

[0903] Output: List of related cases

[0904] Step 7:

[0905] Generating a response

[0906] The server uses Python's Jinja2 template engine to generate a response based on the search results. To provide users with easy-to-understand information, the generated response is expressed in a format such as, "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work."

[0907] Input: List of related cases

[0908] Output: The generated response

[0909] Step 8:

[0910] Viewing the response

[0911] The terminal then displays the generated response to the user, formatting it using HTML and CSS to make the information visually appealing.

[0912] Input: Generated response

[0913] Output: Displayed response

[0914] Step 9:

[0915] Gathering feedback

[0916] The user provides feedback on the provided information. For example, they input feedback such as "This information is useful" into the terminal. The terminal sends this feedback to the server, which analyzes it using the Python Pandas library and improves the search algorithm based on this feedback.

[0917] Input: User feedback

[0918] Output: Improved search algorithm

[0919] This will enable the entire system to quickly provide examples of digital transformation related to local government operations and appropriately present information that meets users' needs.

[0920] (Application example 1)

[0921] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0922] Customer service in modern brick-and-mortar stores requires the provision of fast and accurate information, but it is difficult for store staff to efficiently utilize the vast amount of information available to answer customers. Responses are often delayed, particularly when providing similar questions or information about specific products. Therefore, in order to improve service in brick-and-mortar stores, a system that can provide fast and accurate information is needed.

[0923] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0924] In this invention, the server includes means for automatically collecting digital transformation case studies related to local government operations from a variety of sources, means for analyzing the collected case studies and categorizing them by keyword and storing them in a database, means for analyzing questions received from users and extracting related keywords, means for searching the database based on the extracted keywords and extracting related case studies, means for generating and presenting responses in a user-friendly format based on the extracted case studies, and means for providing optimal responses to customer questions within a smartphone application. This enables fast and accurate customer service in physical stores.

[0925] Definitions of important terms contained in the claims

[0926] "Municipal Affairs"

[0927] It refers to a series of administrative and service activities carried out by local governments.

[0928] "Digital Transformation Case Studies"

[0929] This refers to concrete examples of how digital technology has improved and transformed business processes and services.

[0930] "sauce"

[0931] It refers to the source or reference from which information or data is obtained.

[0932] "means"

[0933] refers to the methods or technical elements used to achieve a specific purpose.

[0934] "analysis"

[0935] It refers to the detailed examination of data and information to clarify its meaning and content.

[0936] "keyword"

[0937] refers to important words or terms to use as search and classification criteria.

[0938] Database

[0939] It refers to a collection of data that is organized in an organized manner, and a system for efficiently searching and manipulating specific data.

[0940] "User"

[0941] refers to the individuals or organizations that use the system or application.

[0942] "question"

[0943] It refers to the linguistic expression of the information a user wants to know or the problem they want to solve.

[0944] "response"

[0945] refers to information provided in response to a question or question.

[0946] "Smartphone"

[0947] refers to a portable electronic device that combines mobile communication and computer functions.

[0948] "application"

[0949] refers to a software program designed for a specific purpose.

[0950] "customer"

[0951] refers to the person or entity that purchases or uses a product or service.

[0952] "Natural language processing technology"

[0953] refers to computer technology for understanding and processing human language.

[0954] MODE FOR CARRYING OUT THE INVENTION

[0955] The system of the present invention collects examples of digital transformation related to local government operations and presents relevant examples in response to queries from users. Specific embodiments of the system will be described below.

[0956] Hardware and software used

[0957] Hardware: Standard servers, smartphones

[0958] Software: Python, requests (for data collection), BeautifulSoup (for HTML analysis), spaCy (natural language processing)

[0959] System processing flow

[0960] The server first automatically collects digital transformation case studies related to local government operations from a variety of sources, including online news sites and public reports from local governments.

[0961] The collected cases are analyzed using text mining technology and classified by keyword. During this process, important keywords are extracted from the text data using spaCy. The extracted keywords are stored in a database, allowing for quick response to subsequent search processing.

[0962] When a user accesses the application using a smartphone and enters a question, the question is first received by the device, then sent to the server where it is analyzed using natural language processing technology. This analysis extracts the main keywords contained in the question.

[0963] The server then searches the database based on the extracted keywords. The search results yield relevant cases, which are then presented to the customer within the smartphone application. For example, in response to the question, "What products are popular these days?", a response such as, "The most popular product over the past six months is the new smartphone model" is generated.

[0964] The generated response is displayed to the user in a user-friendly format, and the user can provide feedback on the response, which is then sent back to the server to help refine the search algorithm, thereby improving the accuracy of the entire system.

[0965] Examples and prompts

[0966] For example, if a user asks the following question:

[0967] What products are popular these days?

[0968] The system uses a generative AI model to generate a response using the following prompt:

[0969] Question: "What are the most popular products these days?"

[0970] Prompt: Please provide examples related to the following keywords: "popular" and "product"

[0971] In response to this,

[0972] "The most popular products over the past six months have been new smartphone models. This was confirmed based on sales data in specific regions."

[0973] The information is provided to the user in this format.

[0974] In this way, customer service can be provided quickly and accurately in physical stores.

[0975] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0976] Detailed program processing flow

[0977] Step 1: Data collection

[0978] The server first automatically collects digital transformation case studies related to municipal operations from a variety of sources, such as online news sites and public reports from municipalities. This collection process uses the Python requests library to obtain the contents of web pages. The obtained HTML data is then analyzed using the BeautifulSoup library and extracted as text data.

[0979] Enter: Website URL

[0980] Output: Extract text data from HTML content

[0981] Specific operation: The server sends an HTTP request to the specified URL, analyzes the received HTML data, and saves it as text.

[0982] Step 2: Text mining

[0983] The collected text data is analyzed using text mining techniques. The server uses the spaCy library to extract important keywords from the text data, which makes the data more organized and streamlines the subsequent search process.

[0984] Input: Text data

[0985] Output: Extracted keyword list

[0986] What it does: The server feeds the text data into a natural language processing library to extract noun phrases and other important keywords.

[0987] Step 3: Database storage

[0988] The extracted keywords and their corresponding examples are stored in a database that is designed to enable rapid response to subsequent search processes.

[0989] Input: A list of keywords and their corresponding examples

[0990] Output: Structured data stored in a database

[0991] Specific operation: The server stores keywords and their related cases in a database and sets up an index to enable efficient searches.

[0992] Step 4: Receiving and parsing user queries

[0993] A user accesses the application using a smartphone and enters a question. This question is received by the device and sent to the server, which uses natural language processing techniques to analyze the question and extract key keywords, again using the spaCy library.

[0994] Input: User's question (in text format)

[0995] Output: Extracted keywords

[0996] How it works: The device receives user input and sends it to the server, which then uses NLP technology to analyze the question and extract key keywords.

[0997] Step 5: Database Search

[0998] The server searches the database based on the extracted keywords and extracts relevant cases using a keyword matching search algorithm.

[0999] Input: Extracted keywords

[1000] Output: List of related cases

[1001] Specific operation: The server searches the database and extracts cases that match the keywords.

[1002] Step 6: Response generation and presentation

[1003] Based on the extracted cases, the server generates a response in a user-friendly format and sends it to the terminal, which then displays the response to the user.

[1004] Input: List of related cases

[1005] Output: The response that is presented to the user

[1006] Specific operation: The server generates an easy-to-understand response based on the case data and sends it to the terminal, which then displays the response on the user's screen.

[1007] Step 7: Gather feedback and improve the algorithm

[1008] Users can provide feedback on the responses provided, which is sent back to the server to help improve the search algorithm.

[1009] Input: User feedback (text format)

[1010] Output: Improved search algorithm

[1011] How it works: The device receives feedback and sends it to the server, which analyzes it and uses it to improve the algorithm.

[1012] This will enable quick and accurate customer service in physical stores.

[1013] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1014] This invention combines an emotion engine with a system for quickly providing examples of digital transformation (DX) related to local government operations. Specifically, this invention is implemented using the following means.

[1015] First, the server collects digital transformation case studies related to local government operations from a variety of sources, including the internet, news sites, and official local government websites, and then analyzes the collected data using text mining technology.

[1016] The server then extracts keywords from the analyzed data and stores the collected cases in a database, categorizing them by keyword. This database neatly stores cases related to keywords such as "AI," "IoT," and "smart city."

[1017] When a user inputs a question about a specific case into the device, a query such as "I would like to know about cases where AI has been used in local governments" is sent to the device. The device then sends this query to a query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords "local government," "AI," and "case study."

[1018] The server then searches the database based on the extracted keywords, using a keyword matching algorithm to prioritize the most relevant cases, such as "Fukuoka City's AI-based snow removal management system."

[1019] Furthermore, the present invention incorporates an emotion engine. When a user inputs a question or receives search results, the device analyzes the user's facial expression, tone of voice, etc., and recognizes the user's emotional state through the emotion engine. For example, if the user is feeling dissatisfied, the device will prioritize providing examples and answers that correspond to that emotional state.

[1020] The server generates a response based on the detected emotional state. This response is generated using natural language processing technology with a tone and content that reflects the user's emotional state. For example, a response could be created that reads, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work and has received high praise from citizens."

[1021] Finally, the device displays the generated response to the user, who can review the provided response and obtain necessary information. If the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[1022] In this way, not only can digital transformation examples related to municipal operations be provided quickly, but the content and tone of the response can be adjusted depending on the user's emotional state, resulting in more personalized information provision.

[1023] The processing flow will be explained below.

[1024] Step 1:

[1025] The server automatically collects examples of digital transformation related to local government operations from the internet, news sites, official local government websites, etc. This collection is set to occur periodically, and new examples are added to the database.

[1026] Step 2:

[1027] The server analyzes the collected data using text mining technology to extract key keywords for each case study, which are then categorized into categories such as "AI," "IoT," and "smart city."

[1028] Step 3:

[1029] The server categorizes the case data based on the extracted keywords and stores them in a structured database, where related cases are stored in a searchable format for each keyword.

[1030] Step 4:

[1031] The user inputs a question about a specific case into the terminal. For example, a question might be input such as, "I would like to know about cases where AI has been used in local governments."

[1032] Step 5:

[1033] The device sends the entered question to the query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords: "municipal government," "AI," and "case study."

[1034] Step 6:

[1035] During query analysis, the device analyzes the user's facial expressions and tone of voice using an emotion engine, which recognizes the user's emotional state (e.g., frustration, interest, joy, etc.) and sends that information to the query analysis module.

[1036] Step 7:

[1037] The server searches the database based on the extracted keywords and emotional state. Using a keyword matching algorithm, it prioritizes and extracts highly relevant cases. Specifically, it finds cases such as "Fukuoka City's AI-based snow removal management system."

[1038] Step 8:

[1039] When generating a response based on the search results, the server takes into account the user's emotional state obtained from the emotion engine. For example, if the user is dissatisfied, the tone of the response will be more considerate. The response is generated using natural language processing technology and formatted as, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work. It has received high praise from citizens."

[1040] Step 9:

[1041] The terminal displays the generated response to the user, who can obtain specific information based on the provided response.

[1042] Step 10:

[1043] The user inputs feedback on the response into the terminal, such as "This information is useful" or "I'd like to know more specific examples."

[1044] Step 11:

[1045] The device sends the collected feedback to the server, which analyzes it and uses it to refine the search algorithm and response generation process. This self-improvement process improves the accuracy of the response to the next query.

[1046] In this way, it is possible to quickly provide examples of digital transformation for municipal operations and generate responses that reflect the user's emotional state.

[1047] Example 2

[1048] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1049] Currently, there are problems with collecting examples of digital transformation in municipal operations and with responding quickly and specifically to user questions. There is also a lack of systems that generate personalized responses based on user sentiment. This makes it difficult for municipal employees and residents to obtain the information they need in a timely manner. Furthermore, there is an insufficient mechanism for improving the accuracy of the system based on feedback.

[1050] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1051] In this invention, the server includes means for automatically collecting digital transformation case studies related to local government operations from a variety of sources, means for analyzing the collected case studies and categorizing them by keyword and storing them in a database, means for analyzing questions received from users and extracting related keywords, means for searching the database based on the extracted keywords and extracting related case studies, means for generating and presenting a response in a format easy for the user to understand based on the extracted case studies, means for analyzing the user's emotional state and adjusting the content of the response, means for generating a response personalized for the user, and means for collecting feedback from users and improving the search algorithm based on the feedback, thereby making it possible to provide necessary information quickly and appropriately.

[1052] "Municipal services" is a general term for the various services and administrative procedures that local governments and regional administrative agencies provide to local residents.

[1053] "Digital transformation" refers to the use of information technology to innovate business processes and service delivery methods in order to improve efficiency and optimization.

[1054] "DX cases" refer to examples of specific results and initiatives that have been implemented through digital transformation.

[1055] "Source" refers to the source of information or the source of data.

[1056] "Collection means" refers to the specific methods or devices used to collect information or data.

[1057] "Analysis tools" refers to methods and software used to analyze collected data and understand and classify its contents.

[1058] "Keywords" refer to important words or phrases in the data or question.

[1059] A "database" refers to an information management system for systematically organizing and storing data.

[1060] A "question" refers to a query entered by a user to ask for information or an example they want to know.

[1061] "Extraction means" refers to the methods and techniques for extracting the necessary information from the analyzed data and keywords.

[1062] "Search methods" refer to methods and techniques for investigating and verifying information in a database.

[1063] "Response methods" refers to the methods and techniques used to provide information to users based on search results.

[1064] "Emotional state" refers to a user's current psychological state or feelings.

[1065] "Emotion analysis means" refers to methods or techniques for analyzing a user's facial expressions and tone of voice to determine their emotional state.

[1066] "Personalized responses" refer to providing specific information tailored to a user's individual needs and emotions.

[1067] "Feedback" refers to opinions and ratings provided by users.

[1068] A "search algorithm" refers to a procedure or calculation method for efficiently searching for information in a database.

[1069] The present invention is a system for quickly providing examples of digital transformation (DX) related to local government operations, and is combined with an emotion engine. This system is specifically implemented using the following means.

[1070] The server automatically collects digital transformation case studies related to local government operations from a variety of sources, including online news sites and official local government websites. This collection is performed using web crawler tools such as Apache Nutch. The collected data is then analyzed using text mining techniques such as Apache OpenNLP.

[1071] The server extracts key keywords from the analyzed data and categorizes them by case, for example, into categories such as "AI," "IoT," and "smart city," and stores them in a MySQL or PostgreSQL database.

[1072] When a user enters a specific question into the device (e.g., "I would like to know about examples of AI use in local governments"), the device sends the question to a query analysis module (e.g., NLTK or SpaCy), which uses natural language processing technology to extract key keywords. The analysis results are then sent to the server.

[1073] The server then searches the database based on the extracted keywords and uses a keyword matching algorithm such as Elasticsearch to extract the most relevant examples, such as a specific example like "Fukuoka City's AI-based snow removal management system."

[1074] The present invention also incorporates an emotion engine. When a user enters a question or receives search results, the device uses a webcam and microphone to collect the user's facial expressions and tone of voice. Using emotion analysis tools such as OpenFace and IBM Watson Tone Analyzer, the device recognizes the user's emotional state. For example, if the user is dissatisfied, the relevant examples and response content are adjusted based on that emotional state.

[1075] The server generates a response based on the emotion-analyzed data. This response is generated using natural language processing technology with a generative AI model (e.g., OpenAI GPT-3) and its tone and content reflect the user's emotional state. For example, a response such as, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work and has been well received by citizens" may be generated.

[1076] The device displays the generated response to the user, who can review the provided information and gain the necessary knowledge. When the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[1077] Specific examples

[1078] Example 1:

[1079] User: "I want to know about examples of smart city development."

[1080] The server searches for relevant cases and finds "City X's Smart City Project." The device analyzes the user's emotions and generates a response in a reassuring tone: "City X's Smart City Project has been a success, and the quality of life for its residents has improved significantly."

[1081] Example prompt sentence:

[1082] "I'd like to know more about the AI-based snow removal management system in Fukuoka City."

[1083] "Please tell us some examples of successful smart city projects."

[1084] "Please introduce some examples of IoT implementation in local governments."

[1085] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1086] Step 1: Collect data

[1087] The server automatically collects digital transformation examples related to local government operations from a variety of sources, specifically by periodically collecting data from online news sites and official local government websites using web crawler tools such as Apache Nutch.

[1088] Input: URL list of various internet sources

[1089] How it works: The web crawler visits pages from a set list of URLs at a specified interval and collects text data.

[1090] Output: raw collected data (text)

[1091] Step 2: Data analysis and keyword extraction

[1092] The server analyzes the collected raw data and uses text mining techniques such as Apache OpenNLP to extract keywords, tokenizing sentences and extracting key keywords such as nouns and verbs.

[1093] Input: Collected raw data (text)

[1094] How it works: The text analysis module tokenizes the data and runs it through analysis algorithms to extract keywords.

[1095] Output: Parsed data and extracted keyword list

[1096] Step 3: Classify and store data

[1097] The server categorizes the analyzed data based on the extracted keywords and stores it in a database such as MySQL or PostgreSQL. The categorized data is then organized for later searches and queries.

[1098] Input: Parsed data and extracted keyword list

[1099] How it works: The data classification module categorizes data based on a list of keywords and connects to a database to store the information.

[1100] Output: A database containing data sorted by category

[1101] Step 4: Receiving a query

[1102] The user inputs a specific question into the device. For example, a query such as "I would like to know about examples of how local governments have used AI" is entered.

[1103] Input: The question (query) entered by the user

[1104] Operation: The terminal receives input from the user through the query receiving module.

[1105] Output: Received query

[1106] Step 5: Query analysis and keyword extraction

[1107] The device analyzes the received query and uses natural language processing techniques (e.g., NLTK or SpaCy) to extract key keywords. The analysis results are sent to the server.

[1108] Input: Received query

[1109] How it works: The query analysis module tokenizes the query and extracts the main keywords.

[1110] Output: Extracted keyword list

[1111] Step 6: Search the database

[1112] The server searches the database based on the extracted keywords and extracts the most relevant cases using a keyword matching algorithm such as Elasticsearch.

[1113] Input: Extracted keyword list

[1114] How it works: The database search module generates a search query based on the keywords and queries the database.

[1115] Output: A list of the most relevant cases

[1116] Step 7: Sentiment Analysis

[1117] The device collects data using a webcam and microphone to analyze the user's facial expressions and tone of voice, using tools such as OpenFace and IBM Watson Tone Analyzer to recognize the user's emotional state.

[1118] Input: User facial expression images and voice data

[1119] How it works: The emotion analysis module analyzes facial expression images and audio data to recognize the user's emotional state.

[1120] Output: Recognized emotion data

[1121] Step 8: Generate a response

[1122] The server generates personalized responses based on the recognized emotion data, using a generative AI model (e.g., OpenAI GPT-3) to create responses appropriate for the user through natural language processing techniques.

[1123] Input: A list of the most relevant cases and recognized emotion data

[1124] How it works: The response generation module uses a generative AI model to generate a response based on relevant examples and sentiment data.

[1125] Output: The generated personalized response

[1126] Step 9: View the response

[1127] The terminal displays the generated response to the user, who reviews the information provided and optionally enters feedback into the terminal.

[1128] Input: The generated personalized response

[1129] Action: The device displays the response on the screen and receives user feedback.

[1130] Output: The response displayed to the user and any feedback entered

[1131] Step 10: Analyze feedback and refine the system

[1132] The server analyzes user feedback and uses the results to improve the search algorithm and response generation process.

[1133] Input: User feedback

[1134] How it works: The feedback analysis module analyzes the feedback and identifies areas for improvement in the search algorithm and response generation process.

[1135] Output: Improved search algorithm and response generation process

[1136] (Application example 2)

[1137] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1138] Conventional systems providing examples of digital transformation for local government operations only present relevant examples in response to user queries, and have the problem of being unable to provide personalized responses according to the user's emotional state. This is particularly difficult in situations where an optimal response according to the user's emotional state is required, such as when the user is feeling stressed or in a hurry, so it was necessary to improve the quality of the responses.

[1139] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting digital transformation case studies related to local government operations from various sources; means for analyzing the collected case studies, classifying them by keyword, and storing them in a database; means for analyzing questions received from users and extracting related keywords; means for searching the database based on the extracted keywords and extracting related case studies; means for generating and presenting a response in a format easy for the user to understand based on the extracted case studies; and means for analyzing the user's emotions and generating a response based on the emotions. This makes it possible to provide an optimal response according to the user's emotional state, improving the quality of the response.

[1140] "Municipal affairs" refers to all activities and operations carried out by local governments to manage their communities and provide public services.

[1141] "Digital transformation cases" refer to specific examples of improvements and innovations that utilize digital technology to improve the efficiency and quality of business operations and services.

[1142] "Diverse sources" refers to different information sources such as the internet, news sites, and official websites.

[1143] "Automatic collection means" refers to methods of collecting information using programs or systems without human intervention.

[1144] "Methods for analyzing collected cases" refers to methods for organizing the information obtained and analyzing it to make its content easier to understand.

[1145] "Keyword categorization" refers to categorizing information based on important words or phrases.

[1146] "Means for storing in a database" refers to the method for storing classified information in a database.

[1147] "Means for analyzing a question received from a user" refers to a method for understanding the content of an inquiry entered by a user and extracting key elements.

[1148] "Means for extracting relevant keywords" refers to a method for finding important words and phrases from the content of a user's question.

[1149] "Means for searching a database and extracting relevant cases" refers to a method of searching a database based on keywords and retrieving relevant information.

[1150] "Means for generating and presenting a response in a user-friendly format" refers to a method for displaying search results in a format that is easy for the user to understand.

[1151] "Means for analyzing user emotions" refers to a method for reading and understanding emotions from user input and behavior.

[1152] The "means for generating a response based on emotions" refers to a method for creating a response with optimal content according to the analyzed emotional state.

[1153] This invention is a system that quickly provides examples of digital transformation related to local government operations and adjusts the content and tone of the response based on the user's emotional state. The invention is implemented through a series of processes consisting of a server, a terminal, and a user.

[1154] The server automatically collects examples of digital transformation in local government operations from various sources, such as the internet and official websites. The collected data is analyzed using text mining technology, and the results are then categorized and stored by keyword. This database stores examples related to keywords such as "AI," "IoT," and "smart city."

[1155] Users input questions about specific cases from their devices. For example, when a query such as "Please tell me about an example of digital transformation in production management using the latest automation technology" is sent to the device, the device sends the query to the query analysis module. The query analysis module, which uses natural language processing technology, analyzes the question and extracts key keywords. An example of a natural language processing library used here is "nlp_library."

[1156] The server searches the database based on the extracted keywords and uses a keyword matching algorithm to prioritize and extract the most relevant cases, such as "the latest case studies using AI for production management."

[1157] Furthermore, the present invention incorporates an emotion engine. When a user inputs a question or receives search results, the device analyzes the user's facial expression, tone of voice, etc., and recognizes the user's emotional state through the emotion engine. For example, "emotion_engine" is used.

[1158] Based on the detected emotional state, the server generates an appropriate response. This response is generated using natural language generation technology with a tone and content that reflects the user's emotional state. For example, if the user is feeling stressed, the server may generate a response such as, "A case study on a production management system using automation technology is effective in not only improving efficiency but also reducing employee stress," allowing the user to receive the information with peace of mind.

[1159] Finally, the device displays the generated response to the user, who can review the provided response and obtain the necessary information. If the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[1160] As a concrete example, consider the following prompt sentence: If a user types, "Please tell me about an example of digital transformation in production management using the latest automation technology," the system can detect the user's stress level from the tone of their voice and generate a response such as, "Here is an example that is effective in both improving efficiency and reducing employee stress." In this way, it is possible to provide the optimal response tailored to the user's emotional state.

[1161] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1162] Step 1:

[1163] The server collects digital transformation case studies related to local government operations from various sources. Specifically, the server scrapes information from the internet, news sites, official websites, etc. It receives the source URL as input and saves the collected data in text format as output.

[1164] Step 2:

[1165] The server analyzes the collected data. Specifically, it uses text mining technology to extract important information. For example, it uses the natural language processing library "nlp_library" to tokenize the data and extract keywords. The input is the collected text data, and the output is keywords and important phrases.

[1166] Step 3:

[1167] The server classifies the analyzed data by keyword and stores it in a database. Specifically, it categorizes the data based on the extracted keywords and stores related information systematically. The input is the analyzed keywords, and the output is a database entry organized by keyword.

[1168] Step 4:

[1169] The user inputs a question about a specific case study from the terminal. The user inputs a query such as, "Please tell me about an example of digital transformation of production management using the latest automation technology." The input is the user's text query, and the output is the query sent to the terminal.

[1170] Step 5:

[1171] The device analyzes the user's question and extracts relevant keywords. Specifically, it uses natural language processing technology to analyze the query and extract key keywords. For example, it uses "nlp_library" to obtain keywords such as "automation," "production management," and "digital transformation" from the question's text data. The user's text query is sent as input, and the extracted keywords are sent as output to the server.

[1172] Step 6:

[1173] The server searches the database based on the extracted keywords and extracts relevant cases. Specifically, it uses a keyword matching algorithm to find relevant cases. The input is the keywords, and the output is a list of highly relevant cases.

[1174] Step 7:

[1175] The device analyzes the user's emotions. Specifically, the device's camera and microphone are used to analyze the user's facial expressions and tone of voice using the emotion engine "emotion_engine." The input is the user's voice and video data, and the output is the user's emotional state, which is sent to the server.

[1176] Step 8:

[1177] The server generates a response based on the user's emotional state. Specifically, it uses natural language generation technology to create a response that reflects the user's emotional state. For example, if the user is feeling stressed, it generates a response with a relaxing tone. The input is the relevant case and the user's emotional state, and the output is the generated response text, which is sent to the terminal.

[1178] Step 9:

[1179] The device displays the generated response to the user, either by displaying the text on the screen or, if necessary, by using speech synthesis technology to read it aloud. The input is the generated response text, and the output is information provided to the user in a format that is easy to understand.

[1180] Step 10:

[1181] The user provides feedback, such as the satisfaction with the search results or the response content. The input is the user's feedback, and the output is the feedback sent to the server.

[1182] Step 11:

[1183] The server analyzes the feedback and improves the search algorithm and response generation process. The input is user feedback data, and the output is an improved algorithm or generation process. This improves the overall performance of the system and provides more personalized information.

[1184] This series of steps enables the system that is the subject of the invention to quickly and accurately provide an appropriate response that takes into account the user's emotional state.

[1185] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1186] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1187] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1188] [Fourth embodiment]

[1189] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1190] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1191] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1192] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1193] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1194] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1195] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1196] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1197] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1198] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1199] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1200] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1201] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1202] The present invention relates to a system for quickly providing examples of digital transformation (DX) related to local government operations. The system is specifically implemented using the following means.

[1203] First, the server collects digital transformation case studies related to local government operations from a variety of sources, including the internet, specialized news sites, and public reports from local governments. The collected data is then analyzed using text mining technology to extract keywords.

[1204] The server then categorizes the collected case data by keyword and stores it in a database. This database is used to efficiently manage various cases of local government work and provides a quick response to subsequent search processing.

[1205] When a user inputs a question, they enter a query into the terminal, such as "I would like to know about examples of AI being used in local governments." The terminal then sends this query to the query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords "local government," "AI," and "examples."

[1206] The server then searches the database based on the extracted keywords. The search results might include examples such as "Fukuoka City's AI-based snow removal management system" or "Osaka City's AI-based tourist information system." This search process uses a keyword-matching algorithm to prioritize the most relevant examples.

[1207] The server then generates a response based on the search results. The generated response is formatted to be easily understood by the user. For example, a response might be created in the form of, "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work."

[1208] Finally, the device displays the generated response to the user. The user can then obtain specific information based on the response. The user can also provide feedback on the response, for example, by typing "This information is useful" into the device. The device then sends this feedback to the server, which analyzes it and uses it to improve the search algorithm. Repeating this process improves the accuracy of the entire system.

[1209] In this way, digital transformation case studies for municipal operations can be provided quickly, and support will be provided to municipal employees and staff to efficiently advance proposals.

[1210] The processing flow will be explained below.

[1211] Step 1:

[1212] The server automatically collects data on digital transformation cases from the internet, news sites, official local government websites, etc. This collection activity is carried out periodically, and new cases are added to the database.

[1213] Step 2:

[1214] The server analyzes the collected data using text mining technology. This analysis extracts key keywords for each case study, such as "AI," "IoT," and "smart city."

[1215] Step 3:

[1216] The server categorizes the case data by keyword based on the extracted keywords. This categorization is used to create a database. The database organizes and stores cases related to each keyword.

[1217] Step 4:

[1218] The user inputs a question about a specific case into the terminal. For example, a question such as, "I would like to know about cases where AI has been used in local governments."

[1219] Step 5:

[1220] The device sends the user's question to the query analysis module, which uses natural language processing technology to analyze the question and extract key keywords such as "local government," "AI," and "case study."

[1221] Step 6:

[1222] The server searches the database based on the analyzed keywords. Using a keyword matching algorithm, it prioritizes the most relevant cases. For example, search results might include "Fukuoka City's AI-based snow removal management system."

[1223] Step 7:

[1224] The server generates a response to present to the user based on the search results. This response is formatted using natural language processing technology in a format that is easy for the user to understand. For example, a response such as "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work" may be created.

[1225] Step 8:

[1226] The terminal displays the generated response to the user, who can review the provided response and obtain any required details.

[1227] Step 9:

[1228] The user inputs feedback on the response into the terminal, for example, "This information is useful."

[1229] Step 10:

[1230] The device sends user feedback to the server, which analyzes it and refines the search algorithm and how the database is organized. This self-improvement process improves the accuracy of responses to the next query.

[1231] Example 1

[1232] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1233] There is a need for a system that can quickly collect, classify, and search examples of digital transformation (DX) related to local government operations and provide appropriate information in response to user requests. Current systems have the problem of taking time to collect, analyze, and search information, preventing users from quickly accessing the information they need. Furthermore, there is no well-established method for effectively utilizing user feedback, making it difficult to improve the accuracy of the entire system.

[1234] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1235] In this invention, the server includes means for automatically collecting digital transformation cases related to local government operations from a variety of sources, means for analyzing the collected data using natural language processing technology to extract keywords, and means for categorizing the analyzed data by keyword and storing it in a database, thereby enabling users to quickly and accurately access the DX cases they need.

[1236] "Municipal business" refers to all business activities carried out by local governments, such as administrative services and public works.

[1237] "Digital transformation (DX)" is an initiative that utilizes digital technology to reform business processes and improve efficiency and service quality.

[1238] "Means of collection" refers to the technical methods and tools used to automatically obtain the required information from various sources.

[1239] "Natural language processing technology" is a general term for algorithms and methods that enable computers to understand, process, and generate human language.

[1240] "Means of analysis" refers to the technical process of analyzing collected data using machine learning and statistical methods to extract meaningful information.

[1241] "Keywords" refer to important words or phrases related to a particular theme or topic.

[1242] "Classification" refers to the process of grouping analyzed information based on specific criteria and organizing it into a more manageable form.

[1243] A "database" is a data storage system that is an organized collection of data stored in a form that allows for efficient retrieval and processing.

[1244] "User" refers to a person who uses the system to input information and obtain output.

[1245] A "query" refers to a question or search phrase that a user enters to request information from a system.

[1246] A "search algorithm" refers to a computational method or rule for efficiently finding information in a database based on specific criteria.

[1247] The "means of generating a response" refers to the process of formatting and outputting the information so that the search results are displayed in a way that is easy for the user to understand.

[1248] "Display means" refers to a technology for visually presenting the generated information on the user's terminal.

[1249] "Feedback" refers to the evaluation and opinion information that users give to the system.

[1250] MODE FOR CARRYING OUT THE INVENTION

[1251] This invention relates to a system for quickly providing examples of digital transformation (DX) related to local government operations. Specific embodiments of this system are described below.

[1252] First, the server collects digital transformation case studies related to municipal operations from various sources. Specifically, it uses web scraping tools such as Python's BeautifulSoup and Scrapy to obtain information from the Internet, specialized news sites, and public reports published by the municipality. The collected data is temporarily stored in local storage.

[1253] The server then analyzes the collected data using natural language processing technologies such as Python's NLTK (Natural Language Toolkit) and spaCy to extract important keywords from the text data. For example, keywords such as "Fukuoka City," "AI," and "snow removal management system" are extracted.

[1254] The analyzed data is classified by keywords, for example using the k-means clustering algorithm to group related data, and then stored in a MySQL database to provide fast responses for subsequent searches.

[1255] When a user inputs information they want to know into a device, they enter a query such as, "I want to know about cases where AI is being used in local governments." The device then sends this query to the server's query analysis module. The server then uses natural language processing (NLP) to analyze the query and extract key keywords such as "local government," "AI," and "case studies."

[1256] Based on the extracted keywords, the server uses Elasticsearch to search the MySQL database, finding related cases such as "Fukuoka City's AI-based snow removal management system" and "Osaka City's AI-based tourist information system."

[1257] The server generates a response based on the search results. This response is generated using Python's Jinja2 template engine, providing information that is easy for the user to understand. For example, the generated response might be expressed in a format such as, "Fukuoka City has introduced a snow removal management system using AI, enabling efficient snow removal work."

[1258] Finally, the device generates and displays the response to the user, using HTML and CSS to present it in a visually friendly format.

[1259] Users can also provide feedback on the information provided. For example, they can input feedback such as "This information is useful" into the device. The device then sends this feedback to the server, which analyzes it and uses it to improve the search algorithm. The feedback is analyzed using Python's Pandas library, which updates the machine learning model to improve the system's accuracy.

[1260] For example, a user may enter a prompt such as, "Please tell me more about examples of how AI has been used in local governments." In response to this prompt, the system can quickly and accurately generate and provide a response through the steps described above.

[1261] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1262] System program processing flow

[1263] Step 1:

[1264] Data collection

[1265] The server collects digital transformation case studies related to municipal operations from a variety of sources, including the internet, specialized news sites, and public reports from municipalities. Specifically, it performs web scraping using Python's BeautifulSoup and Scrapy to obtain the necessary text data.

[1266] Input: Request URL

[1267] Output: Collected text data

[1268] Step 2:

[1269] Data analysis

[1270] The server analyzes the collected text data using natural language processing libraries such as Python's NLTK and spaCy to extract important keywords from the text content. For example, keywords such as "Fukuoka City," "AI," and "snow removal management system" are extracted.

[1271] Input: Collected text data

[1272] Output: Extracted keyword list

[1273] Step 3:

[1274] Data classification and storage

[1275] The server categorizes the data based on the extracted keywords, using the k-means clustering algorithm to group related data, and then stores the categorized data in a MySQL database for efficient management.

[1276] Input: Extracted keyword list

[1277] Output: Classified data, stored database records

[1278] Step 4:

[1279] Entering a query

[1280] The user inputs the information they want to know into the device. For example, they input a query such as, "I want to know about cases where AI is being used in local governments."

[1281] Input: User query

[1282] Output: The device sends a query to the server

[1283] Step 5:

[1284] Query Analysis

[1285] The device sends the user's query to the server's query analysis module, which then uses natural language processing technology to analyze the query and extract key keywords such as "local government," "AI," and "case study."

[1286] Input: User query

[1287] Output: Extracted query keywords

[1288] Step 6:

[1289] Searching the database

[1290] The server uses Elasticsearch to search the MySQL database based on the extracted keywords. This search process finds related case studies. For example, case studies such as "Fukuoka City's AI-based snow removal management system" and "Osaka City's AI-based tourist information system" are listed.

[1291] Input: Extracted query keywords

[1292] Output: List of related cases

[1293] Step 7:

[1294] Generating a response

[1295] The server uses Python's Jinja2 template engine to generate a response based on the search results. To provide users with easy-to-understand information, the generated response is expressed in a format such as, "Fukuoka City has introduced a snow removal management system using AI to achieve efficient snow removal work."

[1296] Input: List of related cases

[1297] Output: The generated response

[1298] Step 8:

[1299] Viewing the response

[1300] The terminal then displays the generated response to the user, formatting it using HTML and CSS to make the information visually appealing.

[1301] Input: Generated response

[1302] Output: Displayed response

[1303] Step 9:

[1304] Gathering feedback

[1305] The user provides feedback on the provided information. For example, they input feedback such as "This information is useful" into the terminal. The terminal sends this feedback to the server, which analyzes it using the Python Pandas library and improves the search algorithm based on this feedback.

[1306] Input: User feedback

[1307] Output: Improved search algorithm

[1308] This will enable the entire system to quickly provide examples of digital transformation related to local government operations and appropriately present information that meets users' needs.

[1309] (Application example 1)

[1310] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1311] Customer service in modern brick-and-mortar stores requires the provision of fast and accurate information, but it is difficult for store staff to efficiently utilize the vast amount of information available to answer customers. Responses are often delayed, particularly when providing similar questions or information about specific products. Therefore, in order to improve service in brick-and-mortar stores, a system that can provide fast and accurate information is needed.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1313] In this invention, the server includes means for automatically collecting digital transformation case studies related to local government operations from a variety of sources, means for analyzing the collected case studies and categorizing them by keyword and storing them in a database, means for analyzing questions received from users and extracting related keywords, means for searching the database based on the extracted keywords and extracting related case studies, means for generating and presenting responses in a user-friendly format based on the extracted case studies, and means for providing optimal responses to customer questions within a smartphone application. This enables fast and accurate customer service in physical stores.

[1314] Definitions of important terms contained in the claims

[1315] "Municipal Affairs"

[1316] It refers to a series of administrative and service activities carried out by local governments.

[1317] "Digital Transformation Case Studies"

[1318] This refers to concrete examples of how digital technology has improved and transformed business processes and services.

[1319] "sauce"

[1320] It refers to the source or reference from which information or data is obtained.

[1321] "means"

[1322] refers to the methods or technical elements used to achieve a specific purpose.

[1323] "analysis"

[1324] It refers to the detailed examination of data and information to clarify its meaning and content.

[1325] "keyword"

[1326] refers to important words or terms to use as search and classification criteria.

[1327] Database

[1328] It refers to a collection of data that is organized in an organized manner, and a system for efficiently searching and manipulating specific data.

[1329] "User"

[1330] refers to the individuals or organizations that use the system or application.

[1331] "question"

[1332] It refers to the linguistic expression of the information a user wants to know or the problem they want to solve.

[1333] "response"

[1334] refers to information provided in response to a question or question.

[1335] "Smartphone"

[1336] refers to a portable electronic device that combines mobile communication and computer functions.

[1337] "application"

[1338] refers to a software program designed for a specific purpose.

[1339] "customer"

[1340] refers to the person or entity that purchases or uses a product or service.

[1341] "Natural language processing technology"

[1342] refers to computer technology for understanding and processing human language.

[1343] MODE FOR CARRYING OUT THE INVENTION

[1344] The system of the present invention collects examples of digital transformation related to local government operations and presents relevant examples in response to queries from users. Specific embodiments of the system will be described below.

[1345] Hardware and software used

[1346] Hardware: Standard servers, smartphones

[1347] Software: Python, requests (for data collection), BeautifulSoup (for HTML analysis), spaCy (natural language processing)

[1348] System processing flow

[1349] The server first automatically collects digital transformation case studies related to local government operations from a variety of sources, including online news sites and public reports from local governments.

[1350] The collected cases are analyzed using text mining technology and classified by keyword. During this process, important keywords are extracted from the text data using spaCy. The extracted keywords are stored in a database, allowing for quick response to subsequent search processing.

[1351] When a user accesses the application using a smartphone and enters a question, the question is first received by the device, then sent to the server where it is analyzed using natural language processing technology. This analysis extracts the main keywords contained in the question.

[1352] The server then searches the database based on the extracted keywords. The search results yield relevant cases, which are then presented to the customer within the smartphone application. For example, in response to the question, "What products are popular these days?", a response such as, "The most popular product over the past six months is the new smartphone model" is generated.

[1353] The generated response is displayed to the user in a user-friendly format, and the user can provide feedback on the response, which is then sent back to the server to help refine the search algorithm, thereby improving the accuracy of the entire system.

[1354] Examples and prompts

[1355] For example, if a user asks the following question:

[1356] What products are popular these days?

[1357] The system uses a generative AI model to generate a response using the following prompt:

[1358] Question: "What are the most popular products these days?"

[1359] Prompt: Please provide examples related to the following keywords: "popular" and "product"

[1360] In response to this,

[1361] "The most popular products over the past six months have been new smartphone models. This was confirmed based on sales data in specific regions."

[1362] The information is provided to the user in this format.

[1363] In this way, customer service can be provided quickly and accurately in physical stores.

[1364] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1365] Detailed program processing flow

[1366] Step 1: Data collection

[1367] The server first automatically collects digital transformation case studies related to municipal operations from a variety of sources, such as online news sites and public reports from municipalities. This collection process uses the Python requests library to obtain the contents of web pages. The obtained HTML data is then analyzed using the BeautifulSoup library and extracted as text data.

[1368] Enter: Website URL

[1369] Output: Extract text data from HTML content

[1370] Specific operation: The server sends an HTTP request to the specified URL, analyzes the received HTML data, and saves it as text.

[1371] Step 2: Text mining

[1372] The collected text data is analyzed using text mining techniques. The server uses the spaCy library to extract important keywords from the text data, which makes the data more organized and streamlines the subsequent search process.

[1373] Input: Text data

[1374] Output: Extracted keyword list

[1375] What it does: The server feeds the text data into a natural language processing library to extract noun phrases and other important keywords.

[1376] Step 3: Database storage

[1377] The extracted keywords and their corresponding examples are stored in a database that is designed to enable rapid response to subsequent search processes.

[1378] Input: A list of keywords and their corresponding examples

[1379] Output: Structured data stored in a database

[1380] Specific operation: The server stores keywords and their related cases in a database and sets up an index to enable efficient searches.

[1381] Step 4: Receiving and parsing user queries

[1382] A user accesses the application using a smartphone and enters a question. This question is received by the device and sent to the server, which uses natural language processing techniques to analyze the question and extract key keywords, again using the spaCy library.

[1383] Input: User's question (in text format)

[1384] Output: Extracted keywords

[1385] How it works: The device receives user input and sends it to the server, which then uses NLP technology to analyze the question and extract key keywords.

[1386] Step 5: Database Search

[1387] The server searches the database based on the extracted keywords and extracts relevant cases using a keyword matching search algorithm.

[1388] Input: Extracted keywords

[1389] Output: List of related cases

[1390] Specific operation: The server searches the database and extracts cases that match the keywords.

[1391] Step 6: Response generation and presentation

[1392] Based on the extracted cases, the server generates a response in a user-friendly format and sends it to the terminal, which then displays the response to the user.

[1393] Input: List of related cases

[1394] Output: The response that is presented to the user

[1395] Specific operation: The server generates an easy-to-understand response based on the case data and sends it to the terminal, which then displays the response on the user's screen.

[1396] Step 7: Gather feedback and improve the algorithm

[1397] Users can provide feedback on the responses provided, which is sent back to the server to help improve the search algorithm.

[1398] Input: User feedback (text format)

[1399] Output: Improved search algorithm

[1400] How it works: The device receives feedback and sends it to the server, which analyzes it and uses it to improve the algorithm.

[1401] This will enable quick and accurate customer service in physical stores.

[1402] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1403] This invention combines an emotion engine with a system for quickly providing examples of digital transformation (DX) related to local government operations. Specifically, this invention is implemented using the following means.

[1404] First, the server collects digital transformation case studies related to local government operations from a variety of sources, including the internet, news sites, and official local government websites, and then analyzes the collected data using text mining technology.

[1405] The server then extracts keywords from the analyzed data and stores the collected cases in a database, categorizing them by keyword. This database neatly stores cases related to keywords such as "AI," "IoT," and "smart city."

[1406] When a user inputs a question about a specific case into the device, a query such as "I would like to know about cases where AI has been used in local governments" is sent to the device. The device then sends this query to a query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords "local government," "AI," and "case study."

[1407] The server then searches the database based on the extracted keywords, using a keyword matching algorithm to prioritize the most relevant cases, such as "Fukuoka City's AI-based snow removal management system."

[1408] Furthermore, the present invention incorporates an emotion engine. When a user inputs a question or receives search results, the device analyzes the user's facial expression, tone of voice, etc., and recognizes the user's emotional state through the emotion engine. For example, if the user is feeling dissatisfied, the device will prioritize providing examples and answers that correspond to that emotional state.

[1409] The server generates a response based on the detected emotional state. This response is generated using natural language processing technology with a tone and content that reflects the user's emotional state. For example, a response could be created that reads, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work and has received high praise from citizens."

[1410] Finally, the device displays the generated response to the user, who can review the provided response and obtain necessary information. If the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[1411] In this way, not only can digital transformation examples related to municipal operations be provided quickly, but the content and tone of the response can be adjusted depending on the user's emotional state, resulting in more personalized information provision.

[1412] The processing flow will be explained below.

[1413] Step 1:

[1414] The server automatically collects examples of digital transformation related to local government operations from the internet, news sites, official local government websites, etc. This collection is set to occur periodically, and new examples are added to the database.

[1415] Step 2:

[1416] The server analyzes the collected data using text mining technology to extract key keywords for each case study, which are then categorized into categories such as "AI," "IoT," and "smart city."

[1417] Step 3:

[1418] The server categorizes the case data based on the extracted keywords and stores them in a structured database, where related cases are stored in a searchable format for each keyword.

[1419] Step 4:

[1420] The user inputs a question about a specific case into the terminal. For example, a question might be input such as, "I would like to know about cases where AI has been used in local governments."

[1421] Step 5:

[1422] The device sends the entered question to the query analysis module, which uses natural language processing (NLP) technology to analyze the question and extract the main keywords: "municipal government," "AI," and "case study."

[1423] Step 6:

[1424] During query analysis, the device analyzes the user's facial expressions and tone of voice using an emotion engine, which recognizes the user's emotional state (e.g., frustration, interest, joy, etc.) and sends that information to the query analysis module.

[1425] Step 7:

[1426] The server searches the database based on the extracted keywords and emotional state. Using a keyword matching algorithm, it prioritizes and extracts highly relevant cases. Specifically, it finds cases such as "Fukuoka City's AI-based snow removal management system."

[1427] Step 8:

[1428] When generating a response based on the search results, the server takes into account the user's emotional state obtained from the emotion engine. For example, if the user is dissatisfied, the tone of the response will be more considerate. The response is generated using natural language processing technology and formatted as, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work. It has received high praise from citizens."

[1429] Step 9:

[1430] The terminal displays the generated response to the user, who can obtain specific information based on the provided response.

[1431] Step 10:

[1432] The user inputs feedback on the response into the terminal, such as "This information is useful" or "I'd like to know more specific examples."

[1433] Step 11:

[1434] The device sends the collected feedback to the server, which analyzes it and uses it to refine the search algorithm and response generation process. This self-improvement process improves the accuracy of the response to the next query.

[1435] In this way, it is possible to quickly provide examples of digital transformation for municipal operations and generate responses that reflect the user's emotional state.

[1436] Example 2

[1437] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1438] Currently, there are problems with collecting examples of digital transformation in municipal operations and with responding quickly and specifically to user questions. There is also a lack of systems that generate personalized responses based on user sentiment. This makes it difficult for municipal employees and residents to obtain the information they need in a timely manner. Furthermore, there is an insufficient mechanism for improving the accuracy of the system based on feedback.

[1439] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1440] In this invention, the server includes means for automatically collecting digital transformation case studies related to local government operations from a variety of sources, means for analyzing the collected case studies and categorizing them by keyword and storing them in a database, means for analyzing questions received from users and extracting related keywords, means for searching the database based on the extracted keywords and extracting related case studies, means for generating and presenting a response in a format easy for the user to understand based on the extracted case studies, means for analyzing the user's emotional state and adjusting the content of the response, means for generating a response personalized for the user, and means for collecting feedback from users and improving the search algorithm based on the feedback, thereby making it possible to provide necessary information quickly and appropriately.

[1441] "Municipal services" is a general term for the various services and administrative procedures that local governments and regional administrative agencies provide to local residents.

[1442] "Digital transformation" refers to the use of information technology to innovate business processes and service delivery methods in order to improve efficiency and optimization.

[1443] "DX cases" refer to examples of specific results and initiatives that have been implemented through digital transformation.

[1444] "Source" refers to the source of information or the source of data.

[1445] "Collection means" refers to the specific methods or devices used to collect information or data.

[1446] "Analysis tools" refers to methods and software used to analyze collected data and understand and classify its contents.

[1447] "Keywords" refer to important words or phrases in the data or question.

[1448] A "database" refers to an information management system for systematically organizing and storing data.

[1449] A "question" refers to a query entered by a user to ask for information or an example they want to know.

[1450] "Extraction means" refers to the methods and techniques for extracting the necessary information from the analyzed data and keywords.

[1451] "Search methods" refer to methods and techniques for investigating and verifying information in a database.

[1452] "Response methods" refers to the methods and techniques used to provide information to users based on search results.

[1453] "Emotional state" refers to a user's current psychological state or feelings.

[1454] "Emotion analysis means" refers to methods or techniques for analyzing a user's facial expressions and tone of voice to determine their emotional state.

[1455] "Personalized responses" refer to providing specific information tailored to a user's individual needs and emotions.

[1456] "Feedback" refers to opinions and ratings provided by users.

[1457] A "search algorithm" refers to a procedure or calculation method for efficiently searching for information in a database.

[1458] The present invention is a system for quickly providing examples of digital transformation (DX) related to local government operations, and is combined with an emotion engine. This system is specifically implemented using the following means.

[1459] The server automatically collects digital transformation case studies related to local government operations from a variety of sources, including online news sites and official local government websites. This collection is performed using web crawler tools such as Apache Nutch. The collected data is then analyzed using text mining techniques such as Apache OpenNLP.

[1460] The server extracts key keywords from the analyzed data and categorizes them by case, for example, into categories such as "AI," "IoT," and "smart city," and stores them in a MySQL or PostgreSQL database.

[1461] When a user enters a specific question into the device (e.g., "I would like to know about examples of AI use in local governments"), the device sends the question to a query analysis module (e.g., NLTK or SpaCy), which uses natural language processing technology to extract key keywords. The analysis results are then sent to the server.

[1462] The server then searches the database based on the extracted keywords and uses a keyword matching algorithm such as Elasticsearch to extract the most relevant examples, such as a specific example like "Fukuoka City's AI-based snow removal management system."

[1463] The present invention also incorporates an emotion engine. When a user enters a question or receives search results, the device uses a webcam and microphone to collect the user's facial expressions and tone of voice. Using emotion analysis tools such as OpenFace and IBM Watson Tone Analyzer, the device recognizes the user's emotional state. For example, if the user is dissatisfied, the relevant examples and response content are adjusted based on that emotional state.

[1464] The server generates a response based on the emotion-analyzed data. This response is generated using natural language processing technology with a generative AI model (e.g., OpenAI GPT-3) and its tone and content reflect the user's emotional state. For example, a response such as, "Fukuoka City has introduced a snow removal management system using AI, which has enabled efficient snow removal work and has been well received by citizens" may be generated.

[1465] The device displays the generated response to the user, who can review the provided information and gain the necessary knowledge. When the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[1466] Specific examples

[1467] Example 1:

[1468] User: "I want to know about examples of smart city development."

[1469] The server searches for relevant cases and finds "City X's Smart City Project." The device analyzes the user's emotions and generates a response in a reassuring tone: "City X's Smart City Project has been a success, and the quality of life for its residents has improved significantly."

[1470] Example prompt sentence:

[1471] "I'd like to know more about the AI-based snow removal management system in Fukuoka City."

[1472] "Please tell us some examples of successful smart city projects."

[1473] "Please introduce some examples of IoT implementation in local governments."

[1474] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1475] Step 1: Collect data

[1476] The server automatically collects digital transformation examples related to local government operations from a variety of sources, specifically by periodically collecting data from online news sites and official local government websites using web crawler tools such as Apache Nutch.

[1477] Input: URL list of various internet sources

[1478] How it works: The web crawler visits pages from a set list of URLs at a specified interval and collects text data.

[1479] Output: raw collected data (text)

[1480] Step 2: Data analysis and keyword extraction

[1481] The server analyzes the collected raw data and uses text mining techniques such as Apache OpenNLP to extract keywords, tokenizing sentences and extracting key keywords such as nouns and verbs.

[1482] Input: Collected raw data (text)

[1483] How it works: The text analysis module tokenizes the data and runs it through analysis algorithms to extract keywords.

[1484] Output: Parsed data and extracted keyword list

[1485] Step 3: Classify and store data

[1486] The server categorizes the analyzed data based on the extracted keywords and stores it in a database such as MySQL or PostgreSQL. The categorized data is then organized for later searches and queries.

[1487] Input: Parsed data and extracted keyword list

[1488] How it works: The data classification module categorizes data based on a list of keywords and connects to a database to store the information.

[1489] Output: A database containing data sorted by category

[1490] Step 4: Receiving a query

[1491] The user inputs a specific question into the device. For example, a query such as "I would like to know about examples of how local governments have used AI" is entered.

[1492] Input: The question (query) entered by the user

[1493] Operation: The terminal receives input from the user through the query receiving module.

[1494] Output: Received query

[1495] Step 5: Query analysis and keyword extraction

[1496] The device analyzes the received query and uses natural language processing techniques (e.g., NLTK or SpaCy) to extract key keywords. The analysis results are sent to the server.

[1497] Input: Received query

[1498] How it works: The query analysis module tokenizes the query and extracts the main keywords.

[1499] Output: Extracted keyword list

[1500] Step 6: Search the database

[1501] The server searches the database based on the extracted keywords and extracts the most relevant cases using a keyword matching algorithm such as Elasticsearch.

[1502] Input: Extracted keyword list

[1503] How it works: The database search module generates a search query based on the keywords and queries the database.

[1504] Output: A list of the most relevant cases

[1505] Step 7: Sentiment Analysis

[1506] The device collects data using a webcam and microphone to analyze the user's facial expressions and tone of voice, using tools such as OpenFace and IBM Watson Tone Analyzer to recognize the user's emotional state.

[1507] Input: User facial expression images and voice data

[1508] How it works: The emotion analysis module analyzes facial expression images and audio data to recognize the user's emotional state.

[1509] Output: Recognized emotion data

[1510] Step 8: Generate a response

[1511] The server generates personalized responses based on the recognized emotion data, using a generative AI model (e.g., OpenAI GPT-3) to create responses appropriate for the user through natural language processing techniques.

[1512] Input: A list of the most relevant cases and recognized emotion data

[1513] How it works: The response generation module uses a generative AI model to generate a response based on relevant examples and sentiment data.

[1514] Output: The generated personalized response

[1515] Step 9: View the response

[1516] The terminal displays the generated response to the user, who reviews the information provided and optionally enters feedback into the terminal.

[1517] Input: The generated personalized response

[1518] Action: The device displays the response on the screen and receives user feedback.

[1519] Output: The response displayed to the user and any feedback entered

[1520] Step 10: Analyze feedback and refine the system

[1521] The server analyzes user feedback and uses the results to improve the search algorithm and response generation process.

[1522] Input: User feedback

[1523] How it works: The feedback analysis module analyzes the feedback and identifies areas for improvement in the search algorithm and response generation process.

[1524] Output: Improved search algorithm and response generation process

[1525] (Application example 2)

[1526] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1527] Conventional systems providing examples of digital transformation for local government operations only present relevant examples in response to user queries, and have the problem of being unable to provide personalized responses according to the user's emotional state. This is particularly difficult in situations where an optimal response according to the user's emotional state is required, such as when the user is feeling stressed or in a hurry, so it was necessary to improve the quality of the responses.

[1528] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting digital transformation case studies related to local government operations from various sources; means for analyzing the collected case studies, classifying them by keyword, and storing them in a database; means for analyzing questions received from users and extracting related keywords; means for searching the database based on the extracted keywords and extracting related case studies; means for generating and presenting a response in a format easy for the user to understand based on the extracted case studies; and means for analyzing the user's emotions and generating a response based on the emotions. This makes it possible to provide an optimal response according to the user's emotional state, improving the quality of the response.

[1529] "Municipal affairs" refers to all activities and operations carried out by local governments to manage their communities and provide public services.

[1530] "Digital transformation cases" refer to specific examples of improvements and innovations that utilize digital technology to improve the efficiency and quality of business operations and services.

[1531] "Diverse sources" refers to different information sources such as the internet, news sites, and official websites.

[1532] "Automatic collection means" refers to methods of collecting information using programs or systems without human intervention.

[1533] "Methods for analyzing collected cases" refers to methods for organizing the information obtained and analyzing it to make its content easier to understand.

[1534] "Keyword categorization" refers to categorizing information based on important words or phrases.

[1535] "Means for storing in a database" refers to the method for storing classified information in a database.

[1536] "Means for analyzing a question received from a user" refers to a method for understanding the content of an inquiry entered by a user and extracting key elements.

[1537] "Means for extracting relevant keywords" refers to a method for finding important words and phrases from the content of a user's question.

[1538] "Means for searching a database and extracting relevant cases" refers to a method of searching a database based on keywords and retrieving relevant information.

[1539] "Means for generating and presenting a response in a user-friendly format" refers to a method for displaying search results in a format that is easy for the user to understand.

[1540] "Means for analyzing user emotions" refers to a method for reading and understanding emotions from user input and behavior.

[1541] The "means for generating a response based on emotions" refers to a method for creating a response with optimal content according to the analyzed emotional state.

[1542] This invention is a system that quickly provides examples of digital transformation related to local government operations and adjusts the content and tone of the response based on the user's emotional state. The invention is implemented through a series of processes consisting of a server, a terminal, and a user.

[1543] The server automatically collects examples of digital transformation in local government operations from various sources, such as the internet and official websites. The collected data is analyzed using text mining technology, and the results are then categorized and stored by keyword. This database stores examples related to keywords such as "AI," "IoT," and "smart city."

[1544] Users input questions about specific cases from their devices. For example, when a query such as "Please tell me about an example of digital transformation in production management using the latest automation technology" is sent to the device, the device sends the query to the query analysis module. The query analysis module, which uses natural language processing technology, analyzes the question and extracts key keywords. An example of a natural language processing library used here is "nlp_library."

[1545] The server searches the database based on the extracted keywords and uses a keyword matching algorithm to prioritize and extract the most relevant cases, such as "the latest case studies using AI for production management."

[1546] Furthermore, the present invention incorporates an emotion engine. When a user inputs a question or receives search results, the device analyzes the user's facial expression, tone of voice, etc., and recognizes the user's emotional state through the emotion engine. For example, "emotion_engine" is used.

[1547] Based on the detected emotional state, the server generates an appropriate response. This response is generated using natural language generation technology with a tone and content that reflects the user's emotional state. For example, if the user is feeling stressed, the server may generate a response such as, "A case study on a production management system using automation technology is effective in not only improving efficiency but also reducing employee stress," allowing the user to receive the information with peace of mind.

[1548] Finally, the device displays the generated response to the user, who can review the provided response and obtain the necessary information. If the user provides feedback, the device sends it to the server, which analyzes the feedback and uses it to improve the search algorithm and response generation process.

[1549] As a concrete example, consider the following prompt sentence: If a user types, "Please tell me about an example of digital transformation in production management using the latest automation technology," the system can detect the user's stress level from the tone of their voice and generate a response such as, "Here is an example that is effective in both improving efficiency and reducing employee stress." In this way, it is possible to provide the optimal response tailored to the user's emotional state.

[1550] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1551] Step 1:

[1552] The server collects digital transformation case studies related to local government operations from various sources. Specifically, the server scrapes information from the internet, news sites, official websites, etc. It receives the source URL as input and saves the collected data in text format as output.

[1553] Step 2:

[1554] The server analyzes the collected data. Specifically, it uses text mining technology to extract important information. For example, it uses the natural language processing library "nlp_library" to tokenize the data and extract keywords. The input is the collected text data, and the output is keywords and important phrases.

[1555] Step 3:

[1556] The server classifies the analyzed data by keyword and stores it in a database. Specifically, it categorizes the data based on the extracted keywords and stores related information systematically. The input is the analyzed keywords, and the output is a database entry organized by keyword.

[1557] Step 4:

[1558] The user inputs a question about a specific case study from the terminal. The user inputs a query such as, "Please tell me about an example of digital transformation of production management using the latest automation technology." The input is the user's text query, and the output is the query sent to the terminal.

[1559] Step 5:

[1560] The device analyzes the user's question and extracts relevant keywords. Specifically, it uses natural language processing technology to analyze the query and extract key keywords. For example, it uses "nlp_library" to obtain keywords such as "automation," "production management," and "digital transformation" from the question's text data. The user's text query is sent as input, and the extracted keywords are sent as output to the server.

[1561] Step 6:

[1562] The server searches the database based on the extracted keywords and extracts relevant cases. Specifically, it uses a keyword matching algorithm to find relevant cases. The input is the keywords, and the output is a list of highly relevant cases.

[1563] Step 7:

[1564] The device analyzes the user's emotions. Specifically, the device's camera and microphone are used to analyze the user's facial expressions and tone of voice using the emotion engine "emotion_engine." The input is the user's voice and video data, and the output is the user's emotional state, which is sent to the server.

[1565] Step 8:

[1566] The server generates a response based on the user's emotional state. Specifically, it uses natural language generation technology to create a response that reflects the user's emotional state. For example, if the user is feeling stressed, it generates a response with a relaxing tone. The input is the relevant case and the user's emotional state, and the output is the generated response text, which is sent to the terminal.

[1567] Step 9:

[1568] The device displays the generated response to the user, either by displaying the text on the screen or, if necessary, by using speech synthesis technology to read it aloud. The input is the generated response text, and the output is information provided to the user in a format that is easy to understand.

[1569] Step 10:

[1570] The user provides feedback, such as the satisfaction with the search results or the response content. The input is the user's feedback, and the output is the feedback sent to the server.

[1571] Step 11:

[1572] The server analyzes the feedback and improves the search algorithm and response generation process. The input is user feedback data, and the output is an improved algorithm or generation process. This improves the overall performance of the system and provides more personalized information.

[1573] This series of steps enables the system that is the subject of the invention to quickly and accurately provide an appropriate response that takes into account the user's emotional state.

[1574] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1575] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1576] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1577] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1578] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1579] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1580] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1581] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1582] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1583] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1584] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1585] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1586] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1587] 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.

[1588] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1589] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1590] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1591] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1592] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1593] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1594] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1595] The following is further disclosed regarding the above embodiment.

[1596] (Claim 1)

[1597] A system that collects digital transformation cases related to local government operations and presents related cases in response to user queries,

[1598] A means to automatically collect digital transformation case studies related to municipal operations from a variety of sources;

[1599] A means to analyze the collected cases, classify them by keyword, and store them in a database;

[1600] means for analyzing a question received from a user and extracting related keywords;

[1601] A means for searching a database based on the extracted keywords and extracting related cases;

[1602] A system that includes a means for generating and presenting a response in a user-friendly format based on the extracted cases.

[1603] (Claim 2)

[1604] 10. The system of claim 1, further comprising means for collecting feedback from users and improving the search algorithm based on the feedback.

[1605] (Claim 3)

[1606] 2. The system according to claim 1, further comprising means for analyzing a question from a user and extracting keywords using natural language processing technology.

[1607] "Example 1"

[1608] (Claim 1)

[1609] A system that collects digital transformation cases related to local government operations and presents related cases in response to user queries,

[1610] A means to automatically collect digital transformation case studies related to municipal operations from a variety of sources;

[1611] A means to analyze the collected cases, classify them by keyword, and store them in a database;

[1612] means for analyzing a question received from a user and extracting related keywords;

[1613] A means for searching a database based on the extracted keywords and extracting related cases;

[1614] A means for generating and presenting a response in a user-friendly format based on the extracted cases;

[1615] A means of analyzing the collected data using natural language processing technology and extracting keywords;

[1616] A classification algorithm to classify the analyzed data by keyword and store it in a database;

[1617] A means for analyzing user questions using a query analysis module and extracting key keywords;

[1618] A means of using search algorithms to prioritize and extract highly relevant cases;

[1619] means for collecting feedback from users and improving the search algorithm based on said feedback;

[1620] A display means for displaying the generated response

[1621] A system including:

[1622] (Claim 2)

[1623] 10. The system of claim 1, further comprising means for collecting feedback from users and improving the search algorithm based on the feedback.

[1624] (Claim 3)

[1625] 2. The system according to claim 1, further comprising means for analyzing a question from a user and extracting keywords using natural language processing technology.

[1626] "Application Example 1"

[1627] (Claim 1)

[1628] A system that collects digital transformation cases related to local government operations and presents related cases in response to user queries,

[1629] A means to automatically collect digital transformation case studies related to municipal operations from a variety of sources;

[1630] A means to analyze the collected cases, classify them by keyword, and store them in a database;

[1631] means for analyzing a question received from a user and extracting related keywords;

[1632] A means for searching a database based on the extracted keywords and extracting related cases;

[1633] A means for generating and presenting a response in a user-friendly format based on the extracted cases;

[1634] A means for providing optimal responses to customer questions within a smartphone application;

[1635] A system including:

[1636] (Claim 2)

[1637] 10. The system of claim 1, further comprising means for collecting feedback from users and improving the search algorithm based on the feedback.

[1638] (Claim 3)

[1639] 2. The system according to claim 1, further comprising means for analyzing a question from a user and extracting keywords using natural language processing technology.

[1640] "Example 2: Combining Emotion Engines"

[1641] (Claim 1)

[1642] A system that collects digital transformation cases related to local government operations and presents related cases in response to user queries,

[1643] A means to automatically collect digital transformation case studies related to municipal operations from a variety of sources;

[1644] A means to analyze the collected cases, classify them by keyword, and store them in a database;

[1645] means for analyzing a question received from a user and extracting related keywords;

[1646] A means for searching a database based on the extracted keywords and extracting related cases;

[1647] A means for generating and presenting a response in a user-friendly format based on the extracted cases;

[1648] means for analyzing the emotional state of the user and adjusting the response content;

[1649] A system including means for generating a personalized response to a user.

[1650] (Claim 2)

[1651] 10. The system of claim 1, further comprising means for collecting feedback from users and improving the search algorithm based on the feedback.

[1652] (Claim 3)

[1653] 2. The system according to claim 1, further comprising means for analyzing a question from a user and extracting keywords using natural language processing technology.

[1654] "Application example 2 when combining emotion engines"

[1655] (Claim 1)

[1656] A system that collects digital transformation cases related to local government operations and presents related cases in response to user queries,

[1657] A means to automatically collect digital transformation case studies related to municipal operations from a variety of sources;

[1658] A means to analyze the collected cases, classify them by keyword, and store them in a database;

[1659] means for analyzing a question received from a user and extracting related keywords;

[1660] A means for searching a database based on the extracted keywords and extracting related cases;

[1661] A means for generating and presenting a response in a user-friendly format based on the extracted cases;

[1662] A system including means for analyzing a user's emotions and generating a response based on the emotions.

[1663] (Claim 2)

[1664] 10. The system of claim 1, further comprising means for collecting feedback from users and improving the search algorithm based on the feedback.

[1665] (Claim 3)

[1666] 2. The system according to claim 1, further comprising means for analyzing a question from a user and extracting keywords using natural language processing technology. [Explanation of symbols]

[1667] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system that collects digital transformation cases related to local government operations and presents related cases in response to user queries, A means to automatically collect digital transformation case studies related to municipal operations from a variety of sources; A means to analyze the collected cases, classify them by keyword, and store them in a database; means for analyzing a question received from a user and extracting related keywords; A means for searching a database based on the extracted keywords and extracting related cases; A system that includes a means for generating and presenting a response in a user-friendly format based on the extracted cases.

2. 10. The system of claim 1, further comprising means for collecting feedback from users and improving the search algorithm based on the feedback.

3. 2. The system according to claim 1, further comprising means for analyzing a question from a user and extracting keywords using natural language processing technology.

Images