system

Abstract

We provide the system. [Solution] A means for collecting and managing past proposals and specifications in a database, A means for the user to input the task details and receive the task details, A method for analyzing received tasks using natural language processing technology and extracting keywords, A means of searching for past cases and solutions in the database based on extracted keywords, A means of generating and displaying recommended solutions to the user based on the searched cases, A means of receiving user feedback and updating the database, A system that includes this.

Description

Technical Field

[0004] , , ,

[0005] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Local governments lack information exchange for efficiently solving common problems. In particular, local governments in rural areas have limited interactions with external vendors, resulting in few inputs of diverse solutions. Also, since the information exchange between local governments is personal, there are situations where optimal solutions are not implemented in a timely manner. Therefore, there is a need for solution proposals in an efficient and standardized manner.

Means for Solving the Problems

[0005] The present invention solves the above problem with a system that includes means for collecting and managing past proposals and specifications in a database, means for users to input and receive problem details, means for analyzing the received problems using natural language processing technology and extracting keywords, means for searching past cases and solutions in the database based on the extracted keywords, means for generating recommended solutions based on the searched cases and displaying them to the user, and means for receiving user feedback and updating the database. Furthermore, the present invention improves security and analysis accuracy by including means for authenticating users using two-factor authentication and means for using morphological and syntactic analysis for keyword extraction.

[0006] A "database" is a collection of information that centrally manages and makes searchable past proposals, specifications, related case studies, and solutions.

[0007] A "proposal" is a written proposal for a specific issue or project, and its contents include the objectives, methods, budget, schedule, and so on.

[0008] A "specification document" is a document that describes the detailed requirements and design of a project or system, and it specifically defines the progress of the work and the final form.

[0009] A "user" is someone who accesses the system, inputs problems, and uses it to obtain solutions. In this context, it specifically refers to a local government official.

[0010] "Natural language processing technology" refers to technologies that enable computers to understand and analyze natural language used by humans in everyday life, and includes morphological analysis and syntactic analysis.

[0011] "Keywords" are important words or phrases extracted from the entered tasks and are used to search for related cases within the database.

[0012] "Searching" is the act of examining information within a database based on specific keywords or conditions to find relevant data.

[0013] A "recommended solution" is an optimal solution or proposal for a specific problem, generated based on past cases and success stories.

[0014] Two-factor authentication is a security technology that uses two different authentication factors to verify a user's identity when they access a system.

[0015] Morphological analysis is a technique that breaks down the words and phrases that make up a sentence into their basic forms and analyzes their roles and meanings within the sentence.

[0016] "Syntactic analysis" is a technique that analyzes the structure of a sentence and how each word and phrase relates to the rest of the sentence.

[0017] "Feedback" is the act of returning evaluations and comments about the results and problems obtained from a system or solution after its implementation. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6]It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example​​​​​​​​​​​​​​​​​​In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

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

[0028] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] System Overview

[0040] This invention is a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on problems entered by users. This system consists of multiple means for data collection, user authentication, problem analysis, proposal generation, and feedback collection, thereby improving the efficiency of information exchange and solution proposals among local governments.

[0041] Explain the program's processing in natural language.

[0042] 1. Data collection:

[0043] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0044] 2. User registration and authentication:

[0045] Users create an account with their local government and enter their basic information. After registration, the system requests two-factor authentication and sends an authentication code to the user's email address. Users enter this code to complete the login process.

[0046] 3. Input the problem:

[0047] After logging in, the terminal displays a task input form to the user. The user enters the specific project name, overview, requirements, budget, deadline, etc., and then presses the "Submit" button to send it to the server.

[0048] 4. Problem Analysis:

[0049] The server analyzes the received assignment text using natural language processing technology. First, it performs morphological analysis, and then syntactic analysis to extract important keywords. For example, if the input is "The bus service needs to be made more efficient," the server will extract the keywords "bus service" and "efficiency."

[0050] 5. Search past cases:

[0051] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0052] 6. Generating Recommended Solutions:

[0053] The server automatically generates the most effective and similar solutions based on the searched cases. The recommended solutions include the solution itself, the necessary resources, the expected effects, and implementation steps.

[0054] 7. Display of proposal:

[0055] The device displays the generated recommended solutions to the user. The user can review these, make corrections, or ask additional questions.

[0056] 8. Gathering feedback:

[0057] After implementing the proposed solution, the user sends the results and any additional feedback to the system. The server updates the database to reflect the received feedback and improve future search accuracy.

[0058] Specific example

[0059] Improvement of public transportation

[0060] 1. Data collection:

[0061] The server collects past proposals and specifications related to public transportation into a database.

[0062] 2. User registration and authentication:

[0063] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[0064] 3. Input the problem:

[0065] Users input challenges related to "improving the efficiency of bus operations" and describe the current operation plan and the challenges in detail.

[0066] 4. Problem Analysis:

[0067] The server extracts keywords such as "bus operation" and "efficiency."

[0068] 5. Search past cases:

[0069] The server searches for relevant data and discovers systems such as "bus route optimization systems" and "real-time operation information provision systems" in other municipalities.

[0070] 6. Generating Recommended Solutions:

[0071] The server recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system."

[0072] 7. Display of proposal:

[0073] The terminal displays the generated proposal to the user, including the implementation steps and expected effects.

[0074] 8. Gathering feedback:

[0075] Users implement the suggested solutions and provide feedback on the results and their impressions to the system. The server incorporates this feedback into its database to improve the accuracy of future suggestions.

[0076] As described above, by using the system of the present invention, local governments can efficiently solve common problems and quickly obtain optimal solutions.

[0077] The following describes the processing flow.

[0078] Step 1:

[0079] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0080] Step 2:

[0081] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[0082] Step 3:

[0083] Users enter basic information (such as the name of their local government, the name of the person in charge, and their email address) to create an account for their local government.

[0084] Step 4:

[0085] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[0086] Step 5:

[0087] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form.

[0088] Step 6:

[0089] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[0090] Step 7:

[0091] The server performs morphological analysis, dividing the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships between elements within the sentence.

[0092] Step 8:

[0093] The server extracts key keywords and uses those keywords to search for past cases and solutions in the database.

[0094] Step 9:

[0095] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions. These recommended solutions include the solution itself, the resources required, and the expected effects.

[0096] Step 10:

[0097] The terminal displays the generated recommended solution to the user. The user can review it and ask additional questions or make corrections as needed.

[0098] Step 11:

[0099] The user implements the proposed solution and inputs the results and any additional feedback into the system.

[0100] Step 12:

[0101] The server receives feedback from users, reflects it in the database, and improves future search accuracy.

[0102] The above outlines the specific processing steps of the program. This system enables local governments to efficiently solve problems and quickly obtain optimal solutions.

[0103] (Example 1)

[0104] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0105] To efficiently solve common challenges faced by public institutions such as local governments, it is necessary to quickly find the optimal solution from past success stories and proposals. However, manual searching and analysis are time-consuming and labor-intensive, and are prone to information bias and omissions. As a result, it is difficult to quickly find effective solutions.

[0106] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0107] In this invention, the server includes means for collecting and managing past proposals and specifications in a database using a document processing device; means for receiving and inputting task details from users; means for analyzing the received task details using natural language processing technology and extracting important keywords; means for searching past cases and solutions from the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and presenting them to the user; and means for receiving feedback information from the user and updating the database. This enables users to efficiently and quickly find the optimal solution based on past cases.

[0108] A "document processing device" is a device that reads documents stored on paper or electronic media and converts them into digital data.

[0109] A "proposal" is a document that details solutions and implementation plans for a specific problem.

[0110] A "specification document" is a document that describes the specific requirements, functions, and technical details of a system or project.

[0111] A "database" is a system that organizes, stores, and manages collected data so that it can be efficiently searched and used.

[0112] "Users" refer to officials from local governments and public institutions who use this system to solve problems.

[0113] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0114] A "keyword" is an important term or phrase that represents the content of an issue or document.

[0115] A "recommended solution" is a proposed solution that is considered optimal for solving the current problem, generated based on past cases found through searches.

[0116] "Feedback information" refers to information that users provide to the system after implementing a proposed solution, including the results, impressions, and problems encountered.

[0117] Modes for carrying out the invention

[0118] The present invention aims to efficiently solve common challenges faced by local governments. This system collects past proposals and specifications, stores them in a database, and automatically generates optimal solutions for challenges entered by users. The system includes a document processing device, natural language processing technology, a database management system, and a generative AI model.

[0119] Hardware and software usage

[0120] 1. Document processing equipment:

[0121] The server uses a scanning device to digitize past paper-based proposals and specifications. After scanning, OCR software (such as Tesseract) is used to convert the PDF documents into text data, which is then stored in a database.

[0122] 2. Natural Language Processing Techniques:

[0123] The server analyzes the received task content using a morphological analysis engine (e.g., MeCab) and a syntactic analysis engine. It extracts important keywords from the analyzed data and uses these keywords to perform a database search.

[0124] 3. Database Management:

[0125] The server stores and maintains the accessibility of collected digitized proposals and specifications using a database management system. The database uses a SQL (Structured Query Language) based database management system to provide efficient searching and high reliability.

[0126] 4. Generative AI Models:

[0127] The server uses a generative AI model to generate the optimal solution from past cases. This model is trained to generate the best solution for the given problem.

[0128] Instructions for use and operating procedures

[0129] 1. User registration and authentication:

[0130] Users access the system's web interface and enter basic information such as the name of the municipality, email address, and name into the new account creation form. After registration, the server saves the entered information to a database and sends a two-factor authentication code to the user's email address. The user enters this code to complete account verification.

[0131] 2. Inputting the assignment:

[0132] After logging in, the terminal displays a task input form to the user. The user enters detailed information such as project name, overview, requirements, budget, and deadline, and then presses the "Submit" button to send it to the server.

[0133] 3. Problem analysis and keyword extraction:

[0134] The server analyzes the received task content using natural language processing technology and extracts important keywords. For example, if the input is "Road maintenance needs to be made more efficient," the server will extract the keywords "road maintenance" and "efficiency."

[0135] 4. Search past cases:

[0136] The server searches the database for relevant past cases and solutions based on the extracted keywords, and identifies highly relevant documents.

[0137] 5. Generating and displaying recommended solutions:

[0138] The server automatically generates the most effective solution using an AI model based on the searched cases. The generated recommended solution includes specific solutions, required resources, expected effects, and implementation steps.

[0139] The terminal displays the generated solution to the user. The user can review the displayed solution and make corrections or ask additional questions as needed.

[0140] 6. Gathering feedback and updating the database:

[0141] Users implement the proposed solutions and send the results and feedback to the system. The server incorporates the received feedback into its database and uses it to improve future search and suggestion accuracy.

[0142] Specific example

[0143] 1. Improvement of public transport:

[0144] Users input challenges related to "improving the efficiency of bus operations" and describe the current operation plan and the challenges in detail.

[0145] The server uses natural language processing technology to extract keywords such as "bus operation" and "efficiency."

[0146] The server searches for relevant data and identifies examples of "bus route optimization systems" and "real-time operation information provision systems" in other municipalities.

[0147] The server generates a solution that recommends the implementation of a "bus route optimization algorithm" and an "operation monitoring system."

[0148] The terminal displays the generated proposal to the user and explains the implementation steps and expected effects.

[0149] The user implements the proposed solution and returns the results and feedback to the system. The server incorporates this feedback into the database to improve the accuracy of future suggestions.

[0150] Examples of prompts for generative AI models

[0151] "Local governments are seeking to improve the efficiency of bus operations. Please propose the best solution based on past examples."

[0152] "We are seeking proposals for improving IT education in elementary schools. Please refer to past successful examples and provide specific suggestions."

[0153] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0154] Step 1: Data Collection

[0155] The server collects data from past proposals and specifications provided by local governments nationwide and internationally. Input is document data from external storage or online repositories, and output is digitized text data.

[0156] The server retrieves documents using APIs from Google Drive and Dropbox, and digitizes the physical documents through a scanning device. The digitized documents are saved in PDF format.

[0157] The server uses OCR software (such as Tesseract) to convert PDF documents into text data and stores that text in a database.

[0158] Step 2: User Registration and Authentication

[0159] Users access the system's web interface and enter basic information such as the name of the local government, email address, and name into the new account creation form. The input is account information, and the output is a registration completion notification.

[0160] The server receives the entered information and saves it to the database. After registration is complete, an authentication code for two-factor authentication is sent to the user's email address.

[0161] The user enters the authentication code sent to them into the form to complete two-factor authentication. This allows the user to log in.

[0162] Step 3: Enter the problem

[0163] The terminal displays an assignment input form to the logged-in user. The input consists of detailed assignment information (project name, overview, requirements, budget, deadline, etc.), and the output is a confirmation of submission to the server.

[0164] The user enters the details of the issue into the form and presses the "Submit" button to send the information to the server.

[0165] Step 4: Problem Analysis

[0166] The server analyzes the received text data of the assignment content using natural language processing technology. The input is the assignment text, and the output is a set of extracted keywords.

[0167] The server uses a morphological analysis engine (such as MeCab) to break down the text into words, and then performs syntactic analysis to extract important keywords. For example, if the input is "Road maintenance needs to be made more efficient," the keywords "road maintenance" and "efficiency" will be extracted.

[0168] Step 5: Search past cases

[0169] The server searches the database for past cases and solutions based on the extracted keywords. The input is the extracted keywords, and the output is a list of relevant past cases.

[0170] The server uses TF-IDF (Term Frequency-Inverse Document Frequency) and vectorization techniques (e.g., Word2Vec) to search for highly relevant documents.

[0171] Step 6: Generating Recommended Solutions

[0172] The server automatically generates the most effective solutions using an AI model based on searched past cases. The input is data from relevant cases, and the output is a document of the recommended solution.

[0173] The server generates the optimal solution tailored to the problem to be solved, including the necessary resources, expected effects, and implementation procedures.

[0174] Step 7: Display the proposal

[0175] The terminal displays the generated recommended solution to the user. The input is the document for the recommended solution, and the output is a confirmation of the display to the user.

[0176] The user reviews the displayed solution and makes corrections or asks additional questions as needed.

[0177] The device also provides an interface for receiving user feedback.

[0178] Step 8: Gathering Feedback and Updating the Database

[0179] The user implements the proposed solution and sends the results and additional feedback to the system. The input is feedback information, and the output is a confirmation of database updates.

[0180] The server updates its database based on the feedback it receives, thereby improving the accuracy of future suggestions.

[0181] The above outlines the specific processing steps of this system.

[0182] (Application Example 1)

[0183] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0184] Store owners and managers face a wide range of operational challenges, including inventory management, improving customer service, and optimizing working hours. Traditional methods have made it difficult to efficiently find solutions to these challenges and quickly obtain concrete implementation procedures. Furthermore, there is a lack of databases for referencing past success stories, and no system exists to automatically suggest optimal solutions. Therefore, there is a need for more efficient store operations and a unified solution proposal system.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0186] In this invention, the server includes means for collecting and managing past proposals and specifications in a database; means for receiving and inputting problem details from users; means for analyzing the received problems using natural language processing technology and extracting keywords; means for searching past cases and solutions in the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for receiving user feedback and updating the database; and means for searching past cases based on keywords extracted using natural language processing technology and then generating recommended solutions using an API of a generation AI model. This makes it possible to automatically provide optimal solutions for efficiently and quickly resolving operational challenges in physical stores.

[0187] A "database" is a collection of information that structures and stores data such as past proposals and specifications, allowing for efficient searching and management.

[0188] A "proposal" is a written proposal or plan submitted to address a specific issue or problem.

[0189] A "specification document" is a document that describes the detailed requirements, design, and procedures for a particular project or system.

[0190] A "user" is an individual or group that uses the system to input a problem and receive a solution proposal.

[0191] "Problem description" refers to the specific problems or requirements that the user wants to solve.

[0192] "Means of receiving" refers to the method by which the system receives and processes data entered by the user.

[0193] "Natural language processing technology" is a technology that analyzes text data entered by a user and uses computers to understand and process human language.

[0194] "Keywords" are important words or phrases extracted from a task or document.

[0195] A "search method" is a way of finding information within a database based on specified conditions.

[0196] A "recommended solution" refers to a suggestion to the user of the most suitable solution based on past cases and data that have been searched.

[0197] A "generative AI model" is a learning model that uses artificial intelligence to generate new solutions based on specified data and conditions.

[0198] "API" stands for Application Programming Interface, and it is an interface for exchanging functions and data between different software programs.

[0199] "Feedback" refers to information returned to the system by users regarding the results and impressions of implementing the suggested solutions.

[0200] "Means of updating" refers to the methods by which a system adds new information and revises or modifies existing data.

[0201] System Overview

[0202] This invention is a system for efficiently solving common challenges in store operations for owners and managers of physical stores. It collects past proposals and specifications in a database, generates optimal solutions based on user-inputted challenges, and collects feedback. This system consists of the following main components:

[0203] Hardware and software

[0204] Database Server: The server collects and manages past proposals and specifications in the database. Python's `beautifulsoup` and `requests` libraries are used for data collection.

[0205] Authentication system: Implement user registration and two-factor authentication using Firebase Authentication.

[0206] User Interface: The frontend is built with Flutter® and provides a form for users to input tasks.

[0207] Natural Language Processing: spaCy will be used for text analysis to extract keywords from the assignment content.

[0208] Search engine: Uses TF-IDF (Inverse Document Frequency) and ElasticSearch (registered trademark) to search for similar cases within the database.

[0209] Generative AI Model: Using the GPT-4 (registered trademark) API, it generates solutions based on searched case studies.

[0210] Database: Use Firebase Firestore to store feedback data and update the database.

[0211] Specific steps of the invention

[0212] 1. Data Collection: The server scrapes past proposals and specifications from the web and stores them in a database. For example, proposals can be retrieved using Python with requests.get("http: / / example.com / proposals").

[0213] 2. User Authentication: Users create an account using Firebase Authentication and log in after two-factor authentication. An authentication code is sent via email, and authentication is completed by entering this code.

[0214] 3. Problem Input: The user interface is built with Flutter, and users input specific store operation challenges here. For example, a form is provided for inputting "improvement of inventory management."

[0215] 4. Problem Analysis: The server uses spaCy to analyze the received problem and extract keywords. The model is loaded with nlp = spacy.load("en_core_web_sm") and keywords are extracted with doc = nlp("Improved inventory management").

[0216] 5. Searching past cases: The server uses TF-IDF or Elasticsearch to search for similar cases in the database. The search is performed using es.search(index="proposals", body={"query": {"match": {"content": "Inventory Management"}}}).

[0217] 6. Generating Recommended Solutions: Use the GPT-4 API to generate solutions based on the searched cases. An example of a prompt would be: "Please propose the best solution to achieve efficient inventory management. Please also describe the implementation method in detail, referencing past success stories."

[0218] 7. Solution Display: Review the suggestions generated in the user interface and make modifications or ask additional questions as needed.

[0219] 8. Feedback Collection: Users submit their results and feedback on trying out the suggested solutions back to the system and store them in Firebase Firestore.

[0220] Through this series of processes, it becomes possible to solve operational challenges in physical stores efficiently and quickly.

[0221] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0222] Step 1: Data Collection

[0223] The server collects past proposals and specifications from national and international sources. Specifically, it uses the Python libraries beautifulsoup and requests to scrape data from websites and stores the retrieved document data in a database. For example, it retrieves proposals using requests.get("http: / / example.com / proposals") and parses them with beautifulsoup. The input is the URL of the website, and the output is the document data stored in the database.

[0224] Step 2: User Authentication

[0225] The device provides an authentication system for users to create accounts and log in. It implements user registration and two-factor authentication using Firebase Authentication. Specifically, the user enters their email address and password, and the system sends an authentication code via email. The user enters this code to complete authentication. The input is the user's email address and password, and the output is a message indicating authentication success or failure.

[0226] Step 3: Enter the assignment

[0227] Users access a form via their device to input specific store operation challenges. Using a Flutter-based interface, they enter the project name, overview, requirements, budget, deadline, etc., and then press the "Submit" button to send the information to the server. The input is detailed information about the challenge provided by the user, and the output is the challenge data stored on the server.

[0228] Step 4: Problem Analysis

[0229] The server analyzes the received task data using natural language processing technology (spaCy). First, it performs morphological analysis, and then syntactic analysis to extract important keywords. Specifically, it loads the model using `nlp = spacy.load("en_core_web_sm")` and extracts keywords using `doc = nlp("Improved inventory management")`. The input is the text data of the task, and the output is the extracted keywords.

[0230] Step 5: Search past cases

[0231] The server searches past cases in the database based on the extracted keywords. It uses TF-IDF and Elasticsearch to identify the most relevant documents in the database. Specifically, it performs a search using es.search(index="proposals", body={"query": {"match": {"content": "Inventory Management"}}}). The input is the extracted keywords, and the output is a list of search results.

[0232] Step 6: Generating Recommended Solutions

[0233] The server generates appropriate solutions using a generative AI model (GPT-4 API) based on the search results. A prompt is provided as input, and the AI ​​generates a detailed solution based on that prompt. An example prompt is: "Please propose the optimal solution for achieving efficient inventory management. Please also describe the implementation method in detail, referencing past success stories." The input consists of the prompt and search results, and the output is the generated solution.

[0234] Step 7: Display Solution

[0235] The terminal displays the generated solution to the user. The user interface shows detailed suggestions, along with the necessary resources and expected effects. The user can review this and ask additional questions or make modifications. The input is the generated solution, and the output is the suggestions displayed to the user.

[0236] Step 8: Gathering Feedback

[0237] Users provide feedback and results from implementing the proposed solution to the system via their device. The server collects this feedback and stores it in Firebase Firestore. This feedback is used when generating the next solution. The input is the user's feedback information, and the output is the updated database.

[0238] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0239] System Overview

[0240] This invention provides a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on user-inputted problems. Furthermore, by incorporating an emotion engine that recognizes user emotions during problem input and feedback, the system can provide more personalized solution suggestions. This system consists of multiple means for data collection, user authentication, problem analysis, emotion recognition, proposal generation, and feedback collection, thereby improving the efficiency of information exchange and solution proposals among local governments.

[0241] Explain the program's processing in natural language.

[0242] 1. Data collection:

[0243] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0244] 2. Importing data:

[0245] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[0246] 3. User registration and authentication:

[0247] Users enter basic information (such as the name of their local government, the name of the person in charge, and their email address) to create an account for their local government.

[0248] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[0249] 4. Inputting the assignment:

[0250] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form.

[0251] During input, the server uses an emotion engine to analyze the user's input speed, patterns, and facial expression data (for example, if a webcam is used) to identify the user's emotional state.

[0252] 5. Problem Analysis:

[0253] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[0254] The server performs morphological analysis, dividing the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships within the text and extract important keywords.

[0255] 6. Search past cases:

[0256] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0257] 7. Generating Recommended Solutions:

[0258] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions that take into account the user's emotional state using an emotion engine. These recommended solutions include the means of resolution, the resources required, and the expected effects. For example, if the user is stressed, the suggestions will be concise and include step-by-step implementation instructions.

[0259] 8. Display of proposals:

[0260] The device displays the generated recommended solutions to the user. It helps the user understand the suggestions by customizing them based on the user's emotional state. The user can review these suggestions and ask additional questions or make modifications as needed.

[0261] 9. Gathering feedback:

[0262] The user implements the proposed solution and inputs the results and any additional feedback into the system.

[0263] When feedback is received, the emotion engine re-analyzes the user's emotional state and adjusts the system's responsiveness and friendliness.

[0264] The server receives user feedback, incorporates it into the database, and uses it to improve search accuracy and the system in the future.

[0265] Specific example

[0266] Improvement of public transportation

[0267] 1. Data collection:

[0268] The server collects past proposals and specifications related to public transportation into a database.

[0269] 2. User registration and authentication:

[0270] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[0271] 3. Task input and emotion recognition:

[0272] When users input challenges related to "improving the efficiency of bus operations," the emotion engine analyzes input speed, patterns, and facial expressions via webcam to recognize when the user is experiencing stress.

[0273] 4. Problem analysis:

[0274] The server extracts keywords such as "bus operation" and "efficiency improvement", and searches for relevant past cases.

[0275] 5. Search for past cases:

[0276] The server identifies relevant cases such as "bus route optimization system" and "real-time operation information providing system" from the database.

[0277] 6. Generation of recommended solutions:

[0278] The server recommends the introduction of a "bus route optimization algorithm" and an "operation monitoring system" including step-by-step execution procedures, considering the user's stress state by the emotion engine.

[0279] 7. Display of proposals:

[0280] The terminal displays the generated proposals to the user in a concise and step-by-step manner, presenting the implementation procedures and expected effects as well.

[0281] 8. Collection of feedback:

[0282] The user implements the proposed solution and inputs the results and additional feedback into the system. When inputting feedback, the emotion engine analyzes the user's emotion and the responsiveness of the system is adjusted.

[0283] As described above, by using the system of the present invention, local governments can efficiently solve problems and quickly obtain optimal solutions. Also, by considering the user's emotional state, more personalized solution proposals are realized.

[0284] The following describes the processing flow.

[0285] Step 1:

[0286] The server collects past proposals and specifications from local governments across the country and internationally to build a database. This process includes document scanning and text conversion using OCR (Optical Character Recognition).

[0287] Step 2:

[0288] The server imports the collected documents into the database and properly categorizes the document metadata (creation date, local government name, project name, etc.).

[0289] Step 3:

[0290] The user inputs basic information (local government name, person in charge name, email address, etc.) to create an account for their local government. After registration, the system requests two-factor authentication.

[0291] Step 4:

[0292] The server sends an authentication code to the email address entered by the user, and the user enters the code to complete two-factor authentication.

[0293] Step 5:

[0294] After logging in, the user enters information such as the specific project name, summary, requirements specification, budget, deadline, etc. into the issue input form. At this time, the emotion engine monitors the speed and pattern of the webcam and keyboard input.

[0295] Step 6:

[0296] The emotion engine analyzes the user's input data and facial expression data to identify the user's emotional state (stress, anxiety, joy, etc.). This enables the determination of the user's emotional state during input.

[0297] Step 7:

[0298] When the user sends a problem, the server receives its content and analyzes the text using natural language processing technology.

[0299] Step 8:

[0300] The server performs morphological analysis to divide the problem sentence into words and phrases. Then, it performs syntactic analysis to analyze the relationships within the sentence and extracts important keywords. For example, when "Improving bus operation efficiency" is input, the keywords "bus operation" and "efficiency improvement" are extracted.

[0301] Step 9:

[0302] Based on the extracted keywords, the server searches for relevant past cases and solutions in the database. At this time, TF-IDF and vectorization techniques are used to identify highly relevant documents.

[0303] <00,00956>Step 10:

[0304] The server extracts highly relevant cases and solutions as search results and generates recommended solutions considering the user's emotional state by the emotion engine. For example, when the user is in a stressed state, the proposed content is made concise and includes step-by-step execution procedures.

[0305] Step 11:

[0306] The terminal displays the generated recommended solutions to the user. By customizing the proposed content according to the user's emotional state, it helps the user's understanding. The user can confirm this and make additional questions or corrections if necessary. <,

[0307] Step 12:

[0308] The user implements the proposed solution and inputs the results and additional feedback into the system. At this time, the emotion engine analyzes the user's emotional state again.

[0309] Step 13:

[0310] The server receives user feedback, reflects it in the database, and uses it to improve future search accuracy and the system. It adjusts the system's responsiveness and friendliness based on the analysis results of the emotion engine.

[0311] The above outlines the specific processing steps of a system that incorporates user emotion recognition capabilities. This system enables local governments to efficiently solve problems and quickly obtain optimal solutions that take emotions into consideration.

[0312] (Example 2)

[0313] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0314] Local governments often struggle to quickly find appropriate solutions to efficiently address common challenges. Furthermore, current systems struggle to automatically generate personalized suggestions that take into account user emotional states. Additionally, there's a lack of mechanisms for efficiently incorporating feedback and improving the system. This frequently leads to delays in information sharing and effective solution proposals among local governments.

[0315] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0316] In this invention, the server includes means for collecting and managing past proposals and specifications in a database; means for users to input and receive problem details; means for analyzing the received problems using natural language processing technology and extracting keywords; means for searching past cases and solutions in the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for receiving user feedback and updating the database; means for analyzing the user's emotional state using an emotion recognition engine; and means for optimizing recommended solutions based on the user's emotional state. This enables local governments to efficiently solve problems and quickly obtain personalized suggestions based on the user's emotional state.

[0317] A "database" is an information storage system that accumulates information such as past proposals and specifications, and allows for searching and management of that information.

[0318] A "proposal" is a document that outlines solutions to a particular project or problem.

[0319] A "specification document" is a document that summarizes the detailed requirements and specifications of a particular project or product.

[0320] A "user" is a local government official who uses this system to input tasks and provide feedback.

[0321] "Natural language processing technology" refers to the technology used to analyze, understand, and generate human language.

[0322] "Keywords" are important words or phrases extracted from texts or documents.

[0323] An "emotion recognition engine" is a technology that analyzes the user's input speed, keystroke patterns, facial expression data, and other factors to identify the user's emotional state.

[0324] A "solution" is a specific means or method for solving a particular problem or issue.

[0325] "Feedback" refers to the results, evaluations, and additional comments that a user provides after implementing a suggested solution.

[0326] Morphological analysis is a technique that breaks down text into words and phrases for analysis.

[0327] "Syntactic analysis" is a technique for analyzing the relationships between words and phrases within a text.

[0328] Two-factor authentication is an authentication process that uses two different authentication methods to enhance user authentication.

[0329] System Overview

[0330] This invention is a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on problems entered by users. Furthermore, by combining it with an emotion recognition engine, it becomes possible to make suggestions that take into account the user's emotional state. This system consists of multiple means for data collection, user authentication, problem analysis, emotion recognition, suggestion generation, and feedback collection.

[0331] Data collection

[0332] The server collects past proposals and specifications from local governments across Japan and internationally. This collection uses web crawling technology and scanners, and converts paper-based documents into text data using OCR (Optical Character Recognition) technology.

[0333] Import data

[0334] The server imports the collected documents into a database, extracts the document metadata (creation date, municipality name, project name, etc.), and categorizes them appropriately. This allows for a smoother subsequent search process.

[0335] User registration and authentication

[0336] Users create their own municipal account to gain access to the system. Registration is completed by entering the necessary basic information (municipality name, contact person's name, email address, etc.).

[0337] The server sends an authentication code to the email address entered by the user, and the user is granted access to the system after entering that code to complete two-factor authentication.

[0338] Task input and emotion recognition

[0339] After logging in, users enter detailed information such as project name, overview, requirements, budget, and deadline into the task input form.

[0340] The server operates an emotion recognition engine that analyzes the user's input speed, keystroke patterns, and facial expression data using a webcam to identify the user's emotional state.

[0341] Problem analysis

[0342] The server analyzes the task text received from the user using natural language processing technology. Specifically, it performs morphological analysis to break down the task text into words and phrases, then performs syntactic analysis to analyze the relationships between them and extract important keywords.

[0343] Search past cases

[0344] The server searches the database for past cases and solutions based on the extracted keywords. It uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0345] Generating Recommended Solutions

[0346] The server generates the most suitable recommended solution for the user based on highly relevant examples and solutions obtained from the search results. Considering the user's emotional state, as provided by the emotion recognition engine, it offers concise and step-by-step suggestions to users experiencing stress.

[0347] Display of proposals

[0348] The device displays the generated recommended solutions to the user. The suggestions are customized according to the user's emotional state, and the user can review them and ask additional questions or make modifications as needed.

[0349] Gathering feedback

[0350] The user implements the proposed solution and inputs the results and additional feedback into the system. During this process, the emotion recognition engine analyzes the user's emotional state and adjusts the system's responsiveness accordingly.

[0351] The server receives user feedback and reflects it in the database. This will lead to improvements in search accuracy and system performance in the future.

[0352] Specific example

[0353] Improvement of public transportation

[0354] 1. Data Collection

[0355] The server collects past proposals and specifications related to public transportation.

[0356] 2. User Registration and Authentication

[0357] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[0358] 3. Task input and emotion recognition

[0359] When a user inputs a problem related to "improving the efficiency of bus operations," the emotion recognition engine analyzes the input speed, keystroke patterns, and facial expressions via the webcam to recognize if the user is experiencing stress.

[0360] 4. Problem Analysis

[0361] The server extracts keywords such as "bus operation" and "efficiency improvements" and searches for related past cases.

[0362] 5. Searching for past cases

[0363] The server identifies relevant cases from the database, such as "bus route optimization systems" and "real-time operation information provision systems."

[0364] 6. Generating Recommended Solutions

[0365] The server, taking into account the user's stress level as assessed by the emotion recognition engine, recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system" that include step-by-step execution procedures.

[0366] 7. Display of Proposal

[0367] The terminal displays the generated proposal to the user in a concise and step-by-step manner, including the implementation procedures and expected effects.

[0368] 8. Gathering Feedback

[0369] The user implements the proposed solution and inputs the results and additional feedback into the system. As feedback is entered, the emotion recognition engine analyzes the user's emotions, and the system's responsiveness is adjusted accordingly.

[0370] This invention enables local governments to efficiently solve problems and quickly obtain personalized suggestions based on users' emotional states.

[0371] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0372] Step 1: Data Collection and Import

[0373] Input: Past proposals and specifications provided by local governments nationwide and internationally.

[0374] The server uses web crawling technology to collect proposals and specifications from online sources. Furthermore, paper-based documents are digitized using a scanner and converted into text data using OCR (optical character recognition) technology.

[0375] Output: A dataset of digitized proposals and specifications.

[0376] Step 2: Import into database

[0377] Input: Digitized proposals and specifications.

[0378] The server imports the collected documents into a database. It extracts the document metadata (creation date and time, name of providing municipality, project name, etc.) and classifies each into the appropriate category.

[0379] Output: Structured database entries.

[0380] Step 3: User Registration and Authentication

[0381] Input: Basic information entered by the user (name of local government, name of contact person, email address, etc.).

[0382] The user creates their own municipal account to gain access to the system. The server sends an authentication code to the entered email address.

[0383] Output: User authentication was successful, and access rights to the system were granted.

[0384] Step 4: Task Input and Emotion Recognition

[0385] Input: Issue information entered by the user (project name, overview, requirements, budget, deadline, etc.).

[0386] The user fills in detailed information on the task input form. The server acquires data on input speed, keystroke patterns, and, if necessary, facial expression data using a webcam, and uses an emotion recognition engine to identify the user's emotional state.

[0387] Output: Task information with analyzed emotional states.

[0388] Step 5: Problem Analysis

[0389] Input: Task information with analyzed emotional states.

[0390] The server analyzes the given text using natural language processing technology. Morphological analysis breaks down the text into words and phrases, and syntactic analysis analyzes the relationships between them to extract important keywords.

[0391] Output: Issue information with keywords extracted.

[0392] Step 6: Search past cases

[0393] Input: Issue information from which keywords have been extracted.

[0394] The server searches the database for past cases and solutions based on the extracted keywords. It uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0395] Output: A list of relevant past cases and solutions.

[0396] Step 7: Generating Recommended Solutions

[0397] Input: A list of relevant past cases and solutions, and the user's emotional state.

[0398] The server generates recommended solutions based on highly relevant cases and solutions. Considering the results of the emotion recognition engine, it provides concise and step-by-step suggestions if the user is experiencing stress.

[0399] Output: Recommended solutions optimized for the user.

[0400] Step 8: Display the proposal

[0401] Input: Recommended solutions optimized for the user.

[0402] The device displays the generated recommended solutions to the user. The suggestions are customized according to the user's emotional state.

[0403] Output: Proposed solutions confirmed by the user.

[0404] Step 9: Gathering Feedback

[0405] Input: User feedback after solution implementation.

[0406] The user implements the proposed solution and inputs the results and additional feedback into the system. The server uses an emotion recognition engine to analyze the user's emotional state when providing feedback.

[0407] Output: Database entries where feedback was collected.

[0408] The above explains the system's program processing in concrete steps. Based on this, you should gain a deeper understanding of input, data processing, and output in each processing step.

[0409] (Application Example 2)

[0410] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0411] To efficiently solve the common challenges faced by local governments, a system is needed that effectively utilizes past solutions and proposals to quickly suggest optimal solutions. However, current systems lack a personalization function that takes emotional states into account, resulting in a significant burden on users. Furthermore, it is expected that more appropriate solutions can be provided by adjusting the method of presenting solutions based on emotional states. This invention aims to solve the above problems.

[0412] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting and managing past proposals and design documents in a database; means for receiving and inputting the content of a problem from the user; means for analyzing the received problem using natural language processing technology and extracting important keywords; means for searching past cases and solutions in the database based on the extracted important keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for analyzing the user's emotional state; means for personalizing the recommended solutions based on the emotional analysis results; and means for receiving user feedback and updating the database. This enables the rapid generation of optimal solutions based on past cases and the provision of personalized solutions that take into account the user's emotional state.

[0413] A "database" is a system for collecting and managing information, including past proposals and design documents.

[0414] A "user" refers to a local government official or related party who inputs their own problems and receives solutions from the system.

[0415] "Problem description" refers to information that includes the specific problems and requirements that the user seeks to solve.

[0416] "Natural language processing technology" is a technology that analyzes text data entered by a user and understands important words and context.

[0417] "Key terms" are specific words or phrases extracted using natural language processing technology, and are elements considered important for solving the problem.

[0418] A "case study" refers to a record of proposals or solutions that have been made to similar problems in the past.

[0419] A "solution" is a specific means or method proposed to solve a problem.

[0420] "Emotional state" refers to the psychological state a user is in when entering information into a task or providing feedback.

[0421] "Emotional analysis" is a technology that analyzes user input data and behavioral patterns to identify the user's emotional state.

[0422] "Personalization" refers to adjusting the solutions provided according to the user's emotional state and individual needs.

[0423] "Feedback" refers to users inputting the results of implementing the proposed solutions, new insights, and other relevant information into the system.

[0424] Two-factor authentication is a method of strengthening user authentication by using multiple authentication methods (e.g., password and email verification).

[0425] Morphological analysis is a technique that divides a sentence into words and analyzes their parts of speech and base forms.

[0426] "Syntactic analysis" is a technique that analyzes the structure of a text and reveals the interrelationships between individual words and phrases.

[0427] "Presentation method" refers to the way or format in which a solution is visually displayed to the user.

[0428] A "step-by-step implementation procedure" is a description that includes a series of specific steps for implementing a solution.

[0429] System Configuration

[0430] This invention is a system for local governments to efficiently solve problems, and consists of a database, server, terminals, and users. The purpose of this system is to analyze the emotional state of users based on the problems they input and to automatically generate the optimal solution.

[0431] Hardware and software to be used

[0432] Database: SQLite is used to collect and manage past proposals and design documents.

[0433] Server: Receives task input from users and functions as a platform for natural language processing and sentiment analysis.

[0434] Natural language processing techniques: For document analysis, we use Python libraries such as TextBlob, as well as morphological and syntactic analysis tools.

[0435] Emotion Analysis Model: Using the Hugging Face transformers library, the emotional state of the user is analyzed from their text data.

[0436] TF-IDF Vectorizer: Used to calculate the relevance of past cases and recommended solutions.

[0437] Device: A device used by the user to input a problem and view suggested solutions. This includes PCs, tablets, and smartphones.

[0438] Program processing details

[0439] 1. Database Setup and Data Collection: The server collects past proposals and design documents from local governments nationwide and internationally, and imports them into the database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0440] 2. User task input: The user uses a terminal to input information such as the specific project name, overview, requirements, budget, and deadline into the task input form. The server receives this information and analyzes it using natural language processing technology.

[0441] 3. Emotional State Analysis: Based on the text data entered by the user, the server uses an emotional analysis model to identify the user's emotional state. This allows the server to understand the user's psychological situation, such as whether they are experiencing stress.

[0442] 4. Generating Recommended Solutions: The server extracts key keywords and searches the database for relevant past cases and solutions. Based on the sentiment analysis results, it generates recommended solutions from highly relevant cases and provides personalized solutions according to the user's emotional state.

[0443] 5. Gathering Feedback and Updating the Database: Users implement the solutions provided and input the results and feedback into the system. The server receives this and updates the database to use it for future search accuracy and system improvements.

[0444] Specific example

[0445] Let's take an example where a city's transportation official inputs a problem regarding traffic congestion around a major train station. When the official inputs the problem, "Traffic volume around the city's major train station has increased excessively, causing frequent congestion," the system uses an emotion analysis model to identify the official's stress level. As a result, it proposes phased solutions such as "introducing dedicated bus lanes" and "optimizing traffic signals," and provides detailed implementation procedures and expected effects.

[0446] Example of a prompt

[0447] Prompt: "Please provide effective solutions to alleviate traffic congestion in the city."

[0448] Expected answer: "Past examples have shown that introducing dedicated bus lanes and optimizing traffic signals are effective. The implementation procedure is as follows: First..."

[0449] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0450] Step 1:

[0451] The server collects and manages past proposals and design documents in a database. Data collection is performed from local governments nationwide and internationally, involving document scanning and text conversion using OCR (Optical Character Recognition). Scanned documents are received as input and imported into the database as text data. The output is managed text data.

[0452] Step 2:

[0453] The user enters the task details using a terminal. They enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form and send it to the server. The entered task details are received by the server. The input is the task details entered by the user on the terminal, and the output is the received task details data.

[0454] Step 3:

[0455] The server analyzes the received assignment content using natural language processing techniques. This process involves morphological and syntactic analysis to extract key terms. The server receives the assignment content text data as input and outputs a list of extracted key terms.

[0456] Step 4:

[0457] The server searches the database for past cases and solutions based on the extracted key keywords. It uses a TF-IDF vectorizer to calculate relevance and identify the most relevant past cases and solutions. The input is a list of key keywords and a database of past proposals, and the output is a list of highly relevant cases and solutions.

[0458] Step 5:

[0459] The server analyzes the user's emotional state. It inputs the text data entered by the user into an emotional analysis model to identify the emotional state. The input consists of the task description text and the user's input data, while the output is the evaluation result of the emotional state.

[0460] Step 6:

[0461] The server generates recommended solutions based on searched cases and personalizes them based on sentiment analysis results. Specifically, if the user is experiencing stress, it presents a solution that includes concise, step-by-step instructions. The input is a list of relevant cases and the results of the sentiment state assessment, and the output is a personalized solution.

[0462] Step 7:

[0463] The terminal displays the generated recommended solution to the user. The user reviews it and asks additional questions or makes modifications as needed. The input is the personalized solution, and the output is a visual presentation of the solution displayed to the user.

[0464] Step 8:

[0465] The user implements the proposed solution and inputs the results and feedback into the system. The server receives this information and uses an emotion analysis model to re-analyze the user's emotional state at the time of feedback. The input is the feedback content, and the output is the updated evaluation result of the emotional state.

[0466] Step 9:

[0467] The server incorporates the feedback into the database, using it to improve future search accuracy and the system. The input consists of feedback content and emotional state evaluation results, while the output is the updated database.

[0468] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0469] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0470] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0471] [Second Embodiment]

[0472] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0473] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0474] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0475] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0476] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0477] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0478] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0479] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0480] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0481] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0482] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0483] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0484] System Overview

[0485] This invention is a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on problems entered by users. This system consists of multiple means for data collection, user authentication, problem analysis, proposal generation, and feedback collection, thereby improving the efficiency of information exchange and solution proposals among local governments.

[0486] Explain the program's processing in natural language.

[0487] 1. Data collection:

[0488] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0489] 2. User registration and authentication:

[0490] Users create an account with their local government and enter their basic information. After registration, the system requests two-factor authentication and sends an authentication code to the user's email address. Users enter this code to complete the login process.

[0491] 3. Input the problem:

[0492] After logging in, the terminal displays a task input form to the user. The user enters the specific project name, overview, requirements, budget, deadline, etc., and then presses the "Submit" button to send it to the server.

[0493] 4. Problem Analysis:

[0494] The server analyzes the received assignment text using natural language processing technology. First, it performs morphological analysis, and then syntactic analysis to extract important keywords. For example, if the input is "The bus service needs to be made more efficient," the server will extract the keywords "bus service" and "efficiency."

[0495] 5. Search past cases:

[0496] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0497] 6. Generating Recommended Solutions:

[0498] The server automatically generates the most effective and similar solutions based on the searched cases. The recommended solutions include the solution itself, the necessary resources, the expected effects, and implementation steps.

[0499] 7. Display of proposal:

[0500] The device displays the generated recommended solutions to the user. The user can review these, make corrections, or ask additional questions.

[0501] 8. Gathering feedback:

[0502] After implementing the proposed solution, the user sends the results and any additional feedback to the system. The server updates the database to reflect the received feedback and improve future search accuracy.

[0503] Specific example

[0504] Improvement of public transportation

[0505] 1. Data collection:

[0506] The server collects past proposals and specifications related to public transportation into a database.

[0507] 2. User registration and authentication:

[0508] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[0509] 3. Input the problem:

[0510] Users input challenges related to "improving the efficiency of bus operations" and describe the current operation plan and the challenges in detail.

[0511] 4. Problem Analysis:

[0512] The server extracts keywords such as "bus operation" and "efficiency."

[0513] 5. Search past cases:

[0514] The server searches for relevant data and discovers systems such as "bus route optimization systems" and "real-time operation information provision systems" in other municipalities.

[0515] 6. Generating Recommended Solutions:

[0516] The server recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system."

[0517] 7. Display of proposal:

[0518] The terminal displays the generated proposal to the user, including the implementation steps and expected effects.

[0519] 8. Gathering feedback:

[0520] Users implement the suggested solutions and provide feedback on the results and their impressions to the system. The server incorporates this feedback into its database to improve the accuracy of future suggestions.

[0521] As described above, by using the system of the present invention, local governments can efficiently solve common problems and quickly obtain optimal solutions.

[0522] The following describes the processing flow.

[0523] Step 1:

[0524] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0525] Step 2:

[0526] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[0527] Step 3:

[0528] Users enter basic information (such as the name of their local government, the name of the person in charge, and their email address) to create an account for their local government.

[0529] Step 4:

[0530] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[0531] Step 5:

[0532] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form.

[0533] Step 6:

[0534] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[0535] Step 7:

[0536] The server performs morphological analysis, dividing the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships between elements within the sentence.

[0537] Step 8:

[0538] The server extracts key keywords and uses those keywords to search for past cases and solutions in the database.

[0539] Step 9:

[0540] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions. These recommended solutions include the solution itself, the resources required, and the expected effects.

[0541] Step 10:

[0542] The terminal displays the generated recommended solution to the user. The user can review it and ask additional questions or make corrections as needed.

[0543] Step 11:

[0544] The user implements the proposed solution and inputs the results and any additional feedback into the system.

[0545] Step 12:

[0546] The server receives feedback from users, reflects it in the database, and improves future search accuracy.

[0547] The above outlines the specific processing steps of the program. This system enables local governments to efficiently solve problems and quickly obtain optimal solutions.

[0548] (Example 1)

[0549] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0550] To efficiently solve common challenges faced by public institutions such as local governments, it is necessary to quickly find the optimal solution from past success stories and proposals. However, manual searching and analysis are time-consuming and labor-intensive, and are prone to information bias and omissions. As a result, it is difficult to quickly find effective solutions.

[0551] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0552] In this invention, the server includes means for collecting and managing past proposals and specifications in a database using a document processing device; means for receiving and inputting task details from users; means for analyzing the received task details using natural language processing technology and extracting important keywords; means for searching past cases and solutions from the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and presenting them to the user; and means for receiving feedback information from the user and updating the database. This enables users to efficiently and quickly find the optimal solution based on past cases.

[0553] A "document processing device" is a device that reads documents stored on paper or electronic media and converts them into digital data.

[0554] A "proposal" is a document that details solutions and implementation plans for a specific problem.

[0555] A "specification document" is a document that describes the specific requirements, functions, and technical details of a system or project.

[0556] A "database" is a system that organizes, stores, and manages collected data so that it can be efficiently searched and used.

[0557] "Users" refer to officials from local governments and public institutions who use this system to solve problems.

[0558] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0559] A "keyword" is an important term or phrase that represents the content of an issue or document.

[0560] A "recommended solution" is a proposed solution that is considered optimal for solving the current problem, generated based on past cases found through searches.

[0561] "Feedback information" refers to information that users provide to the system after implementing a proposed solution, including the results, impressions, and problems encountered.

[0562] Modes for carrying out the invention

[0563] The present invention aims to efficiently solve common challenges faced by local governments. This system collects past proposals and specifications, stores them in a database, and automatically generates optimal solutions for challenges entered by users. The system includes a document processing device, natural language processing technology, a database management system, and a generative AI model.

[0564] Hardware and software usage

[0565] 1. Document processing equipment:

[0566] The server uses a scanning device to digitize past paper-based proposals and specifications. After scanning, OCR software (such as Tesseract) is used to convert the PDF documents into text data, which is then stored in a database.

[0567] 2. Natural Language Processing Techniques:

[0568] The server analyzes the received task content using a morphological analysis engine (e.g., MeCab) and a syntactic analysis engine. It extracts important keywords from the analyzed data and uses these keywords to perform a database search.

[0569] 3. Database Management:

[0570] The server stores and maintains the accessibility of collected digitized proposals and specifications using a database management system. The database uses a SQL (Structured Query Language) based database management system to provide efficient searching and high reliability.

[0571] 4. Generative AI Models:

[0572] The server uses a generative AI model to generate the optimal solution from past cases. This model is trained to generate the best solution for the given problem.

[0573] Instructions for use and operating procedures

[0574] 1. User registration and authentication:

[0575] Users access the system's web interface and enter basic information such as the name of the municipality, email address, and name into the new account creation form. After registration, the server saves the entered information to a database and sends a two-factor authentication code to the user's email address. The user enters this code to complete account verification.

[0576] 2. Inputting the assignment:

[0577] After logging in, the terminal displays a task input form to the user. The user enters detailed information such as project name, overview, requirements, budget, and deadline, and then presses the "Submit" button to send it to the server.

[0578] 3. Problem analysis and keyword extraction:

[0579] The server analyzes the received task content using natural language processing technology and extracts important keywords. For example, if the input is "Road maintenance needs to be made more efficient," the server will extract the keywords "road maintenance" and "efficiency."

[0580] 4. Search past cases:

[0581] The server searches the database for relevant past cases and solutions based on the extracted keywords, and identifies highly relevant documents.

[0582] 5. Generating and displaying recommended solutions:

[0583] The server automatically generates the most effective solution using an AI model based on the searched cases. The generated recommended solution includes specific solutions, required resources, expected effects, and implementation steps.

[0584] The terminal displays the generated solution to the user. The user can review the displayed solution and make corrections or ask additional questions as needed.

[0585] 6. Gathering feedback and updating the database:

[0586] Users implement the proposed solutions and send the results and feedback to the system. The server incorporates the received feedback into its database and uses it to improve future search and suggestion accuracy.

[0587] Specific example

[0588] 1. Improvement of public transport:

[0589] Users input challenges related to "improving the efficiency of bus operations" and describe the current operation plan and the challenges in detail.

[0590] The server uses natural language processing technology to extract keywords such as "bus operation" and "efficiency."

[0591] The server searches for relevant data and identifies examples of "bus route optimization systems" and "real-time operation information provision systems" in other municipalities.

[0592] The server generates a solution that recommends the implementation of a "bus route optimization algorithm" and an "operation monitoring system."

[0593] The terminal displays the generated proposal to the user and explains the implementation steps and expected effects.

[0594] The user implements the proposed solution and returns the results and feedback to the system. The server incorporates this feedback into the database to improve the accuracy of future suggestions.

[0595] Examples of prompts for generative AI models

[0596] "Local governments are seeking to improve the efficiency of bus operations. Please propose the best solution based on past examples."

[0597] "We are seeking proposals for improving IT education in elementary schools. Please refer to past successful examples and provide specific suggestions."

[0598] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0599] Step 1: Data Collection

[0600] The server collects data from past proposals and specifications provided by local governments nationwide and internationally. Input is document data from external storage or online repositories, and output is digitized text data.

[0601] The server retrieves documents using APIs from Google Drive and Dropbox, and digitizes the physical documents through a scanning device. The digitized documents are saved in PDF format.

[0602] The server uses OCR software (such as Tesseract) to convert PDF documents into text data and stores that text in a database.

[0603] Step 2: User Registration and Authentication

[0604] Users access the system's web interface and enter basic information such as the name of the local government, email address, and name into the new account creation form. The input is account information, and the output is a registration completion notification.

[0605] The server receives the entered information and saves it to the database. After registration is complete, an authentication code for two-factor authentication is sent to the user's email address.

[0606] The user enters the authentication code sent to them into the form to complete two-factor authentication. This allows the user to log in.

[0607] Step 3: Enter the problem

[0608] The terminal displays an assignment input form to the logged-in user. The input consists of detailed assignment information (project name, overview, requirements, budget, deadline, etc.), and the output is a confirmation of submission to the server.

[0609] The user enters the details of the issue into the form and presses the "Submit" button to send the information to the server.

[0610] Step 4: Problem Analysis

[0611] The server analyzes the received text data of the assignment content using natural language processing technology. The input is the assignment text, and the output is a set of extracted keywords.

[0612] The server uses a morphological analysis engine (such as MeCab) to break down the text into words, and then performs syntactic analysis to extract important keywords. For example, if the input is "Road maintenance needs to be made more efficient," the keywords "road maintenance" and "efficiency" will be extracted.

[0613] Step 5: Search past cases

[0614] The server searches the database for past cases and solutions based on the extracted keywords. The input is the extracted keywords, and the output is a list of relevant past cases.

[0615] The server uses TF-IDF (Term Frequency-Inverse Document Frequency) and vectorization techniques (e.g., Word2Vec) to search for highly relevant documents.

[0616] Step 6: Generating Recommended Solutions

[0617] The server automatically generates the most effective solutions using an AI model based on searched past cases. The input is data from relevant cases, and the output is a document of the recommended solution.

[0618] The server generates the optimal solution tailored to the problem to be solved, including the necessary resources, expected effects, and implementation procedures.

[0619] Step 7: Display the proposal

[0620] The terminal displays the generated recommended solution to the user. The input is the document for the recommended solution, and the output is a confirmation of the display to the user.

[0621] The user reviews the displayed solution and makes corrections or asks additional questions as needed.

[0622] The device also provides an interface for receiving user feedback.

[0623] Step 8: Gathering Feedback and Updating the Database

[0624] The user implements the proposed solution and sends the results and additional feedback to the system. The input is feedback information, and the output is a confirmation of database updates.

[0625] The server updates its database based on the feedback it receives, thereby improving the accuracy of future suggestions.

[0626] The above outlines the specific processing steps of this system.

[0627] (Application Example 1)

[0628] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0629] Store owners and managers face a wide range of operational challenges, including inventory management, improving customer service, and optimizing working hours. Traditional methods have made it difficult to efficiently find solutions to these challenges and quickly obtain concrete implementation procedures. Furthermore, there is a lack of databases for referencing past success stories, and no system exists to automatically suggest optimal solutions. Therefore, there is a need for more efficient store operations and a unified solution proposal system.

[0630] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0631] In this invention, the server includes means for collecting and managing past proposals and specifications in a database; means for receiving and inputting problem details from users; means for analyzing the received problems using natural language processing technology and extracting keywords; means for searching past cases and solutions in the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for receiving user feedback and updating the database; and means for searching past cases based on keywords extracted using natural language processing technology and then generating recommended solutions using an API of a generation AI model. This makes it possible to automatically provide optimal solutions for efficiently and quickly resolving operational challenges in physical stores.

[0632] A "database" is a collection of information that structures and stores data such as past proposals and specifications, allowing for efficient searching and management.

[0633] A "proposal" is a written proposal or plan submitted to address a specific issue or problem.

[0634] A "specification document" is a document that describes the detailed requirements, design, and procedures for a particular project or system.

[0635] A "user" is an individual or group that uses the system to input a problem and receive a solution proposal.

[0636] "Problem description" refers to the specific problems or requirements that the user wants to solve.

[0637] "Means of receiving" refers to the method by which the system receives and processes data entered by the user.

[0638] "Natural language processing technology" is a technology that analyzes text data entered by a user and uses computers to understand and process human language.

[0639] "Keywords" are important words or phrases extracted from a task or document.

[0640] A "search method" is a way of finding information within a database based on specified conditions.

[0641] A "recommended solution" refers to a suggestion to the user of the most suitable solution based on past cases and data that have been searched.

[0642] A "generative AI model" is a learning model that uses artificial intelligence to generate new solutions based on specified data and conditions.

[0643] "API" stands for Application Programming Interface, and it is an interface for exchanging functions and data between different software programs.

[0644] "Feedback" refers to information returned to the system by users regarding the results and impressions of implementing the suggested solutions.

[0645] "Means of updating" refers to the methods by which a system adds new information and revises or modifies existing data.

[0646] System Overview

[0647] This invention is a system for efficiently solving common challenges in store operations for owners and managers of physical stores. It collects past proposals and specifications in a database, generates optimal solutions based on user-inputted challenges, and collects feedback. This system consists of the following main components:

[0648] Hardware and software

[0649] Database Server: The server collects and manages past proposals and specifications in the database. Python's `beautifulsoup` and `requests` libraries are used for data collection.

[0650] Authentication system: Implement user registration and two-factor authentication using Firebase Authentication.

[0651] User Interface: The frontend is built with Flutter and provides a form for users to input their tasks.

[0652] Natural Language Processing: spaCy will be used for text analysis to extract keywords from the assignment content.

[0653] Search engine: Uses TF-IDF (Inverse Document Frequency) and Elasticsearch to search for similar cases within the database.

[0654] Generative AI Model: Uses the GPT-4 API to generate solutions based on searched case studies.

[0655] Database: Use Firebase Firestore to store feedback data and update the database.

[0656] Specific steps of the invention

[0657] 1. Data Collection: The server scrapes past proposals and specifications from the web and stores them in a database. For example, proposals can be retrieved using Python with requests.get("http: / / example.com / proposals").

[0658] 2. User Authentication: Users create an account using Firebase Authentication and log in after two-factor authentication. An authentication code is sent via email, and authentication is completed by entering this code.

[0659] 3. Problem Input: The user interface is built with Flutter, and users input specific store operation challenges here. For example, a form is provided for inputting "improvement of inventory management."

[0660] 4. Problem Analysis: The server uses spaCy to analyze the received problem and extract keywords. The model is loaded with nlp = spacy.load("en_core_web_sm") and keywords are extracted with doc = nlp("Improved inventory management").

[0661] 5. Searching past cases: The server uses TF-IDF or Elasticsearch to search for similar cases in the database. The search is performed using es.search(index="proposals", body={"query": {"match": {"content": "Inventory Management"}}}).

[0662] 6. Generating Recommended Solutions: Use the GPT-4 API to generate solutions based on the searched cases. An example of a prompt would be: "Please propose the best solution to achieve efficient inventory management. Please also describe the implementation method in detail, referencing past success stories."

[0663] 7. Solution Display: Review the suggestions generated in the user interface and make modifications or ask additional questions as needed.

[0664] 8. Feedback Collection: Users submit their results and feedback on trying out the suggested solutions back to the system and store them in Firebase Firestore.

[0665] Through this series of processes, it becomes possible to solve operational challenges in physical stores efficiently and quickly.

[0666] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0667] Step 1: Data Collection

[0668] The server collects past proposals and specifications from national and international sources. Specifically, it uses the Python libraries beautifulsoup and requests to scrape data from websites and stores the retrieved document data in a database. For example, it retrieves proposals using requests.get("http: / / example.com / proposals") and parses them with beautifulsoup. The input is the URL of the website, and the output is the document data stored in the database.

[0669] Step 2: User Authentication

[0670] The device provides an authentication system for users to create accounts and log in. It implements user registration and two-factor authentication using Firebase Authentication. Specifically, the user enters their email address and password, and the system sends an authentication code via email. The user enters this code to complete authentication. The input is the user's email address and password, and the output is a message indicating authentication success or failure.

[0671] Step 3: Enter the assignment

[0672] Users access a form via their device to input specific store operation challenges. Using a Flutter-based interface, they enter the project name, overview, requirements, budget, deadline, etc., and then press the "Submit" button to send the information to the server. The input is detailed information about the challenge provided by the user, and the output is the challenge data stored on the server.

[0673] Step 4: Problem Analysis

[0674] The server analyzes the received task data using natural language processing technology (spaCy). First, it performs morphological analysis, and then syntactic analysis to extract important keywords. Specifically, it loads the model using `nlp = spacy.load("en_core_web_sm")` and extracts keywords using `doc = nlp("Improved inventory management")`. The input is the text data of the task, and the output is the extracted keywords.

[0675] Step 5: Search past cases

[0676] The server searches past cases in the database based on the extracted keywords. It uses TF-IDF and Elasticsearch to identify the most relevant documents in the database. Specifically, it performs a search using es.search(index="proposals", body={"query": {"match": {"content": "Inventory Management"}}}). The input is the extracted keywords, and the output is a list of search results.

[0677] Step 6: Generating Recommended Solutions

[0678] The server generates appropriate solutions using a generative AI model (GPT-4 API) based on the search results. A prompt is provided as input, and the AI ​​generates a detailed solution based on that prompt. An example prompt is: "Please propose the optimal solution for achieving efficient inventory management. Please also describe the implementation method in detail, referencing past success stories." The input consists of the prompt and search results, and the output is the generated solution.

[0679] Step 7: Display Solution

[0680] The terminal displays the generated solution to the user. The user interface shows detailed suggestions, along with the necessary resources and expected effects. The user can review this and ask additional questions or make modifications. The input is the generated solution, and the output is the suggestions displayed to the user.

[0681] Step 8: Gathering Feedback

[0682] Users provide feedback and results from implementing the proposed solution to the system via their device. The server collects this feedback and stores it in Firebase Firestore. This feedback is used when generating the next solution. The input is the user's feedback information, and the output is the updated database.

[0683] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0684] System Overview

[0685] This invention provides a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on user-inputted problems. Furthermore, by incorporating an emotion engine that recognizes user emotions during problem input and feedback, the system can provide more personalized solution suggestions. This system consists of multiple means for data collection, user authentication, problem analysis, emotion recognition, proposal generation, and feedback collection, thereby improving the efficiency of information exchange and solution proposals among local governments.

[0686] Explain the program's processing in natural language.

[0687] 1. Data collection:

[0688] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0689] 2. Importing data:

[0690] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[0691] 3. User registration and authentication:

[0692] Users enter basic information (such as the name of their local government, the name of the person in charge, and their email address) to create an account for their local government.

[0693] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[0694] 4. Inputting the assignment:

[0695] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form.

[0696] During input, the server uses an emotion engine to analyze the user's input speed, patterns, and facial expression data (for example, if a webcam is used) to identify the user's emotional state.

[0697] 5. Problem Analysis:

[0698] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[0699] The server performs morphological analysis, dividing the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships within the text and extract important keywords.

[0700] 6. Search past cases:

[0701] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0702] 7. Generating Recommended Solutions:

[0703] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions that take into account the user's emotional state using an emotion engine. These recommended solutions include the means of resolution, the resources required, and the expected effects. For example, if the user is stressed, the suggestions will be concise and include step-by-step implementation instructions.

[0704] 8. Display of proposals:

[0705] The device displays the generated recommended solutions to the user. It helps the user understand the suggestions by customizing them based on the user's emotional state. The user can review these suggestions and ask additional questions or make modifications as needed.

[0706] 9. Gathering feedback:

[0707] The user implements the proposed solution and inputs the results and any additional feedback into the system.

[0708] When feedback is received, the emotion engine re-analyzes the user's emotional state and adjusts the system's responsiveness and friendliness.

[0709] The server receives user feedback, incorporates it into the database, and uses it to improve search accuracy and the system in the future.

[0710] Specific example

[0711] Improvement of public transportation

[0712] 1. Data collection:

[0713] The server collects past proposals and specifications related to public transportation into a database.

[0714] 2. User registration and authentication:

[0715] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[0716] 3. Task input and emotion recognition:

[0717] When users input challenges related to "improving the efficiency of bus operations," the emotion engine analyzes input speed, patterns, and facial expressions via webcam to recognize when the user is experiencing stress.

[0718] 4. Problem Analysis:

[0719] The server extracts keywords such as "bus operation" and "efficiency improvements" and searches for related past cases.

[0720] 5. Search past cases:

[0721] The server identifies relevant cases from the database, such as "bus route optimization systems" and "real-time operation information provision systems."

[0722] 6. Generating Recommended Solutions:

[0723] The server, taking into account the user's stress level as determined by the emotion engine, recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system" that include step-by-step execution procedures.

[0724] 7. Display of proposal:

[0725] The terminal displays the generated proposal to the user in a concise and step-by-step manner, including the implementation procedures and expected effects.

[0726] 8. Gathering feedback:

[0727] The user implements the proposed solution and inputs the results and additional feedback into the system. As feedback is entered, the emotion engine analyzes the user's emotions and adjusts the system's responsiveness accordingly.

[0728] As described above, by using the system of the present invention, local governments can efficiently solve problems and quickly obtain optimal solutions. Furthermore, by taking into account the user's emotional state, more personalized solution proposals can be realized.

[0729] The following describes the processing flow.

[0730] Step 1:

[0731] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0732] Step 2:

[0733] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[0734] Step 3:

[0735] Users enter basic information (such as the name of their local government, the name of the contact person, and their email address) to create an account for their local government. After registration, the system requests two-factor authentication.

[0736] Step 4:

[0737] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[0738] Step 5:

[0739] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form. During this process, the emotion engine monitors the speed and patterns of webcam and keyboard input.

[0740] Step 6:

[0741] The emotion engine analyzes user input data and facial expression data to identify the user's emotional state (stress, anxiety, joy, etc.). This allows it to determine the user's emotional state at the time of input.

[0742] Step 7:

[0743] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[0744] Step 8:

[0745] The server performs morphological analysis to break down the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships within the text and extract important keywords. For example, if the input is "improving the efficiency of bus operations," the server will extract the keywords "bus operations" and "efficiency."

[0746] Step 9:

[0747] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0748] Step 10:

[0749] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions considering the user's emotional state using an emotion engine. For example, if the user is stressed, the suggestions will be concise and include step-by-step implementation instructions.

[0750] Step 11:

[0751] The device displays the generated recommended solutions to the user. It helps the user understand the suggestions by customizing them based on the user's emotional state. The user can review these suggestions and ask additional questions or make modifications as needed.

[0752] Step 12:

[0753] The user implements the proposed solution and inputs the results and additional feedback into the system. At this time, the emotion engine re-analyzes the user's emotional state.

[0754] Step 13:

[0755] The server receives user feedback, reflects it in the database, and uses it to improve future search accuracy and the system. It adjusts the system's responsiveness and friendliness based on the analysis results of the emotion engine.

[0756] The above outlines the specific processing steps of a system that incorporates user emotion recognition capabilities. This system enables local governments to efficiently solve problems and quickly obtain optimal solutions that take emotions into consideration.

[0757] (Example 2)

[0758] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0759] Local governments often struggle to quickly find appropriate solutions to efficiently address common challenges. Furthermore, current systems struggle to automatically generate personalized suggestions that take into account user emotional states. Additionally, there's a lack of mechanisms for efficiently incorporating feedback and improving the system. This frequently leads to delays in information sharing and effective solution proposals among local governments.

[0760] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0761] In this invention, the server includes means for collecting and managing past proposals and specifications in a database; means for users to input and receive problem details; means for analyzing the received problems using natural language processing technology and extracting keywords; means for searching past cases and solutions in the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for receiving user feedback and updating the database; means for analyzing the user's emotional state using an emotion recognition engine; and means for optimizing recommended solutions based on the user's emotional state. This enables local governments to efficiently solve problems and quickly obtain personalized suggestions based on the user's emotional state.

[0762] A "database" is an information storage system that accumulates information such as past proposals and specifications, and allows for searching and management of that information.

[0763] A "proposal" is a document that outlines solutions to a particular project or problem.

[0764] A "specification document" is a document that summarizes the detailed requirements and specifications of a particular project or product.

[0765] A "user" is a local government official who uses this system to input tasks and provide feedback.

[0766] "Natural language processing technology" refers to the technology used to analyze, understand, and generate human language.

[0767] "Keywords" are important words or phrases extracted from texts or documents.

[0768] An "emotion recognition engine" is a technology that analyzes the user's input speed, keystroke patterns, facial expression data, and other factors to identify the user's emotional state.

[0769] A "solution" is a specific means or method for solving a particular problem or issue.

[0770] "Feedback" refers to the results, evaluations, and additional comments that a user provides after implementing a suggested solution.

[0771] Morphological analysis is a technique that breaks down text into words and phrases for analysis.

[0772] "Syntactic analysis" is a technique for analyzing the relationships between words and phrases within a text.

[0773] Two-factor authentication is an authentication process that uses two different authentication methods to enhance user authentication.

[0774] System Overview

[0775] This invention is a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on problems entered by users. Furthermore, by combining it with an emotion recognition engine, it becomes possible to make suggestions that take into account the user's emotional state. This system consists of multiple means for data collection, user authentication, problem analysis, emotion recognition, suggestion generation, and feedback collection.

[0776] Data collection

[0777] The server collects past proposals and specifications from local governments across Japan and internationally. This collection uses web crawling technology and scanners, and converts paper-based documents into text data using OCR (Optical Character Recognition) technology.

[0778] Import data

[0779] The server imports the collected documents into a database, extracts the document metadata (creation date, municipality name, project name, etc.), and categorizes them appropriately. This allows for a smoother subsequent search process.

[0780] User registration and authentication

[0781] Users create their own municipal account to gain access to the system. Registration is completed by entering the necessary basic information (municipality name, contact person's name, email address, etc.).

[0782] The server sends an authentication code to the email address entered by the user, and the user is granted access to the system after entering that code to complete two-factor authentication.

[0783] Task input and emotion recognition

[0784] After logging in, users enter detailed information such as project name, overview, requirements, budget, and deadline into the task input form.

[0785] The server operates an emotion recognition engine that analyzes the user's input speed, keystroke patterns, and facial expression data using a webcam to identify the user's emotional state.

[0786] Problem analysis

[0787] The server analyzes the task text received from the user using natural language processing technology. Specifically, it performs morphological analysis to break down the task text into words and phrases, then performs syntactic analysis to analyze the relationships between them and extract important keywords.

[0788] Search past cases

[0789] The server searches the database for past cases and solutions based on the extracted keywords. It uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0790] Generating Recommended Solutions

[0791] The server generates the most suitable recommended solution for the user based on highly relevant examples and solutions obtained from the search results. Considering the user's emotional state, as provided by the emotion recognition engine, it offers concise and step-by-step suggestions to users experiencing stress.

[0792] Display of proposals

[0793] The device displays the generated recommended solutions to the user. The suggestions are customized according to the user's emotional state, and the user can review them and ask additional questions or make modifications as needed.

[0794] Gathering feedback

[0795] The user implements the proposed solution and inputs the results and additional feedback into the system. During this process, the emotion recognition engine analyzes the user's emotional state and adjusts the system's responsiveness accordingly.

[0796] The server receives user feedback and reflects it in the database. This will lead to improvements in search accuracy and system performance in the future.

[0797] Specific example

[0798] Improvement of public transportation

[0799] 1. Data Collection

[0800] The server collects past proposals and specifications related to public transportation.

[0801] 2. User Registration and Authentication

[0802] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[0803] 3. Task input and emotion recognition

[0804] When a user inputs a problem related to "improving the efficiency of bus operations," the emotion recognition engine analyzes the input speed, keystroke patterns, and facial expressions via the webcam to recognize if the user is experiencing stress.

[0805] 4. Problem Analysis

[0806] The server extracts keywords such as "bus operation" and "efficiency improvements" and searches for related past cases.

[0807] 5. Searching for past cases

[0808] The server identifies relevant cases from the database, such as "bus route optimization systems" and "real-time operation information provision systems."

[0809] 6. Generating Recommended Solutions

[0810] The server, taking into account the user's stress level as assessed by the emotion recognition engine, recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system" that include step-by-step execution procedures.

[0811] 7. Display of Proposal

[0812] The terminal displays the generated proposal to the user in a concise and step-by-step manner, including the implementation procedures and expected effects.

[0813] 8. Gathering Feedback

[0814] The user implements the proposed solution and inputs the results and additional feedback into the system. As feedback is entered, the emotion recognition engine analyzes the user's emotions, and the system's responsiveness is adjusted accordingly.

[0815] This invention enables local governments to efficiently solve problems and quickly obtain personalized suggestions based on users' emotional states.

[0816] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0817] Step 1: Data Collection and Import

[0818] Input: Past proposals and specifications provided by local governments nationwide and internationally.

[0819] The server uses web crawling technology to collect proposals and specifications from online sources. Furthermore, paper-based documents are digitized using a scanner and converted into text data using OCR (optical character recognition) technology.

[0820] Output: A dataset of digitized proposals and specifications.

[0821] Step 2: Import into database

[0822] Input: Digitized proposals and specifications.

[0823] The server imports the collected documents into a database. It extracts the document metadata (creation date and time, name of providing municipality, project name, etc.) and classifies each into the appropriate category.

[0824] Output: Structured database entries.

[0825] Step 3: User Registration and Authentication

[0826] Input: Basic information entered by the user (name of local government, name of contact person, email address, etc.).

[0827] The user creates their own municipal account to gain access to the system. The server sends an authentication code to the entered email address.

[0828] Output: User authentication was successful, and access rights to the system were granted.

[0829] Step 4: Task Input and Emotion Recognition

[0830] Input: Issue information entered by the user (project name, overview, requirements, budget, deadline, etc.).

[0831] The user fills in detailed information on the task input form. The server acquires data on input speed, keystroke patterns, and, if necessary, facial expression data using a webcam, and uses an emotion recognition engine to identify the user's emotional state.

[0832] Output: Task information with analyzed emotional states.

[0833] Step 5: Problem Analysis

[0834] Input: Task information with analyzed emotional states.

[0835] The server analyzes the given text using natural language processing technology. Morphological analysis breaks down the text into words and phrases, and syntactic analysis analyzes the relationships between them to extract important keywords.

[0836] Output: Issue information with keywords extracted.

[0837] Step 6: Search past cases

[0838] Input: Issue information from which keywords have been extracted.

[0839] The server searches the database for past cases and solutions based on the extracted keywords. It uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0840] Output: A list of relevant past cases and solutions.

[0841] Step 7: Generating Recommended Solutions

[0842] Input: A list of relevant past cases and solutions, and the user's emotional state.

[0843] The server generates recommended solutions based on highly relevant cases and solutions. Considering the results of the emotion recognition engine, it provides concise and step-by-step suggestions if the user is experiencing stress.

[0844] Output: Recommended solutions optimized for the user.

[0845] Step 8: Display the proposal

[0846] Input: Recommended solutions optimized for the user.

[0847] The device displays the generated recommended solutions to the user. The suggestions are customized according to the user's emotional state.

[0848] Output: Proposed solutions confirmed by the user.

[0849] Step 9: Gathering Feedback

[0850] Input: User feedback after solution implementation.

[0851] The user implements the proposed solution and inputs the results and additional feedback into the system. The server uses an emotion recognition engine to analyze the user's emotional state when providing feedback.

[0852] Output: Database entries where feedback was collected.

[0853] The above explains the system's program processing in concrete steps. Based on this, you should gain a deeper understanding of input, data processing, and output in each processing step.

[0854] (Application Example 2)

[0855] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0856] To efficiently solve the common challenges faced by local governments, a system is needed that effectively utilizes past solutions and proposals to quickly suggest optimal solutions. However, current systems lack a personalization function that takes emotional states into account, resulting in a significant burden on users. Furthermore, it is expected that more appropriate solutions can be provided by adjusting the method of presenting solutions based on emotional states. This invention aims to solve the above problems.

[0857] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting and managing past proposals and design documents in a database; means for receiving and inputting the content of a problem from the user; means for analyzing the received problem using natural language processing technology and extracting important keywords; means for searching past cases and solutions in the database based on the extracted important keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for analyzing the user's emotional state; means for personalizing the recommended solutions based on the emotional analysis results; and means for receiving user feedback and updating the database. This enables the rapid generation of optimal solutions based on past cases and the provision of personalized solutions that take into account the user's emotional state.

[0858] A "database" is a system for collecting and managing information, including past proposals and design documents.

[0859] A "user" refers to a local government official or related party who inputs their own problems and receives solutions from the system.

[0860] "Problem description" refers to information that includes the specific problems and requirements that the user seeks to solve.

[0861] "Natural language processing technology" is a technology that analyzes text data entered by a user and understands important words and context.

[0862] "Key terms" are specific words or phrases extracted using natural language processing technology, and are elements considered important for solving the problem.

[0863] A "case study" refers to a record of proposals or solutions that have been made to similar problems in the past.

[0864] A "solution" is a specific means or method proposed to solve a problem.

[0865] "Emotional state" refers to the psychological state a user is in when entering information into a task or providing feedback.

[0866] "Emotional analysis" is a technology that analyzes user input data and behavioral patterns to identify the user's emotional state.

[0867] "Personalization" refers to adjusting the solutions provided according to the user's emotional state and individual needs.

[0868] "Feedback" refers to users inputting the results of implementing the proposed solutions, new insights, and other relevant information into the system.

[0869] Two-factor authentication is a method of strengthening user authentication by using multiple authentication methods (e.g., password and email verification).

[0870] Morphological analysis is a technique that divides a sentence into words and analyzes their parts of speech and base forms.

[0871] "Syntactic analysis" is a technique that analyzes the structure of a text and reveals the interrelationships between individual words and phrases.

[0872] "Presentation method" refers to the way or format in which a solution is visually displayed to the user.

[0873] A "step-by-step implementation procedure" is a description that includes a series of specific steps for implementing a solution.

[0874] System Configuration

[0875] This invention is a system for local governments to efficiently solve problems, and consists of a database, server, terminals, and users. The purpose of this system is to analyze the emotional state of users based on the problems they input and to automatically generate the optimal solution.

[0876] Hardware and software to be used

[0877] Database: SQLite is used to collect and manage past proposals and design documents.

[0878] Server: Receives task input from users and functions as a platform for natural language processing and sentiment analysis.

[0879] Natural language processing techniques: For document analysis, we use Python libraries such as TextBlob, as well as morphological and syntactic analysis tools.

[0880] Emotion Analysis Model: Using the Hugging Face transformers library, the emotional state of the user is analyzed from their text data.

[0881] TF-IDF Vectorizer: Used to calculate the relevance of past cases and recommended solutions.

[0882] Device: A device used by the user to input a problem and view suggested solutions. This includes PCs, tablets, and smartphones.

[0883] Program processing details

[0884] 1. Database Setup and Data Collection: The server collects past proposals and design documents from local governments nationwide and internationally, and imports them into the database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0885] 2. User task input: The user uses a terminal to input information such as the specific project name, overview, requirements, budget, and deadline into the task input form. The server receives this information and analyzes it using natural language processing technology.

[0886] 3. Emotional State Analysis: Based on the text data entered by the user, the server uses an emotional analysis model to identify the user's emotional state. This allows the server to understand the user's psychological situation, such as whether they are experiencing stress.

[0887] 4. Generating Recommended Solutions: The server extracts key keywords and searches the database for relevant past cases and solutions. Based on the sentiment analysis results, it generates recommended solutions from highly relevant cases and provides personalized solutions according to the user's emotional state.

[0888] 5. Gathering Feedback and Updating the Database: Users implement the solutions provided and input the results and feedback into the system. The server receives this and updates the database to use it for future search accuracy and system improvements.

[0889] Specific example

[0890] Let's take an example where a city's transportation official inputs a problem regarding traffic congestion around a major train station. When the official inputs the problem, "Traffic volume around the city's major train station has increased excessively, causing frequent congestion," the system uses an emotion analysis model to identify the official's stress level. As a result, it proposes phased solutions such as "introducing dedicated bus lanes" and "optimizing traffic signals," and provides detailed implementation procedures and expected effects.

[0891] Example of a prompt

[0892] Prompt: "Please provide effective solutions to alleviate traffic congestion in the city."

[0893] Expected answer: "Past examples have shown that introducing dedicated bus lanes and optimizing traffic signals are effective. The implementation procedure is as follows: First..."

[0894] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0895] Step 1:

[0896] The server collects and manages past proposals and design documents in a database. Data collection is performed from local governments nationwide and internationally, involving document scanning and text conversion using OCR (Optical Character Recognition). Scanned documents are received as input and imported into the database as text data. The output is managed text data.

[0897] Step 2:

[0898] The user enters the task details using a terminal. They enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form and send it to the server. The entered task details are received by the server. The input is the task details entered by the user on the terminal, and the output is the received task details data.

[0899] Step 3:

[0900] The server analyzes the received assignment content using natural language processing techniques. This process involves morphological and syntactic analysis to extract key terms. The server receives the assignment content text data as input and outputs a list of extracted key terms.

[0901] Step 4:

[0902] The server searches the database for past cases and solutions based on the extracted key keywords. It uses a TF-IDF vectorizer to calculate relevance and identify the most relevant past cases and solutions. The input is a list of key keywords and a database of past proposals, and the output is a list of highly relevant cases and solutions.

[0903] Step 5:

[0904] The server analyzes the user's emotional state. It inputs the text data entered by the user into an emotional analysis model to identify the emotional state. The input consists of the task description text and the user's input data, while the output is the evaluation result of the emotional state.

[0905] Step 6:

[0906] The server generates recommended solutions based on searched cases and personalizes them based on sentiment analysis results. Specifically, if the user is experiencing stress, it presents a solution that includes concise, step-by-step instructions. The input is a list of relevant cases and the results of the sentiment state assessment, and the output is a personalized solution.

[0907] Step 7:

[0908] The terminal displays the generated recommended solution to the user. The user reviews it and asks additional questions or makes modifications as needed. The input is the personalized solution, and the output is a visual presentation of the solution displayed to the user.

[0909] Step 8:

[0910] The user implements the proposed solution and inputs the results and feedback into the system. The server receives this information and uses an emotion analysis model to re-analyze the user's emotional state at the time of feedback. The input is the feedback content, and the output is the updated evaluation result of the emotional state.

[0911] Step 9:

[0912] The server incorporates the feedback into the database, using it to improve future search accuracy and the system. The input consists of feedback content and emotional state evaluation results, while the output is the updated database.

[0913] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0914] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0915] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0916] [Third Embodiment]

[0917] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0918] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0919] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0920] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0921] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0922] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0923] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0924] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0925] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0926] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0927] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0928] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0929] System Overview

[0930] This invention is a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on problems entered by users. This system consists of multiple means for data collection, user authentication, problem analysis, proposal generation, and feedback collection, thereby improving the efficiency of information exchange and solution proposals among local governments.

[0931] Explain the program's processing in natural language.

[0932] 1. Data collection:

[0933] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0934] 2. User registration and authentication:

[0935] Users create an account with their local government and enter their basic information. After registration, the system requests two-factor authentication and sends an authentication code to the user's email address. Users enter this code to complete the login process.

[0936] 3. Input the problem:

[0937] After logging in, the terminal displays a task input form to the user. The user enters the specific project name, overview, requirements, budget, deadline, etc., and then presses the "Submit" button to send it to the server.

[0938] 4. Problem Analysis:

[0939] The server analyzes the received assignment text using natural language processing technology. First, it performs morphological analysis, and then syntactic analysis to extract important keywords. For example, if the input is "The bus service needs to be made more efficient," the server will extract the keywords "bus service" and "efficiency."

[0940] 5. Search past cases:

[0941] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[0942] 6. Generating Recommended Solutions:

[0943] The server automatically generates the most effective and similar solutions based on the searched cases. The recommended solutions include the solution itself, the necessary resources, the expected effects, and implementation steps.

[0944] 7. Display of proposal:

[0945] The device displays the generated recommended solutions to the user. The user can review these, make corrections, or ask additional questions.

[0946] 8. Gathering feedback:

[0947] After implementing the proposed solution, the user sends the results and any additional feedback to the system. The server updates the database to reflect the received feedback and improve future search accuracy.

[0948] Specific example

[0949] Improvement of public transportation

[0950] 1. Data collection:

[0951] The server collects past proposals and specifications related to public transportation into a database.

[0952] 2. User registration and authentication:

[0953] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[0954] 3. Input the problem:

[0955] Users input challenges related to "improving the efficiency of bus operations" and describe the current operation plan and the challenges in detail.

[0956] 4. Problem Analysis:

[0957] The server extracts keywords such as "bus operation" and "efficiency."

[0958] 5. Search past cases:

[0959] The server searches for relevant data and discovers systems such as "bus route optimization systems" and "real-time operation information provision systems" in other municipalities.

[0960] 6. Generating Recommended Solutions:

[0961] The server recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system."

[0962] 7. Display of proposal:

[0963] The terminal displays the generated proposal to the user, including the implementation steps and expected effects.

[0964] 8. Gathering feedback:

[0965] Users implement the suggested solutions and provide feedback on the results and their impressions to the system. The server incorporates this feedback into its database to improve the accuracy of future suggestions.

[0966] As described above, by using the system of the present invention, local governments can efficiently solve common problems and quickly obtain optimal solutions.

[0967] The following describes the processing flow.

[0968] Step 1:

[0969] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[0970] Step 2:

[0971] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[0972] Step 3:

[0973] Users enter basic information (such as the name of their local government, the name of the person in charge, and their email address) to create an account for their local government.

[0974] Step 4:

[0975] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[0976] Step 5:

[0977] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form.

[0978] Step 6:

[0979] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[0980] Step 7:

[0981] The server performs morphological analysis, dividing the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships between elements within the sentence.

[0982] Step 8:

[0983] The server extracts key keywords and uses those keywords to search for past cases and solutions in the database.

[0984] Step 9:

[0985] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions. These recommended solutions include the solution itself, the resources required, and the expected effects.

[0986] Step 10:

[0987] The terminal displays the generated recommended solution to the user. The user can review it and ask additional questions or make corrections as needed.

[0988] Step 11:

[0989] The user implements the proposed solution and inputs the results and any additional feedback into the system.

[0990] Step 12:

[0991] The server receives feedback from users, reflects it in the database, and improves future search accuracy.

[0992] The above outlines the specific processing steps of the program. This system enables local governments to efficiently solve problems and quickly obtain optimal solutions.

[0993] (Example 1)

[0994] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0995] To efficiently solve common challenges faced by public institutions such as local governments, it is necessary to quickly find the optimal solution from past success stories and proposals. However, manual searching and analysis are time-consuming and labor-intensive, and are prone to information bias and omissions. As a result, it is difficult to quickly find effective solutions.

[0996] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0997] In this invention, the server includes means for collecting and managing past proposals and specifications in a database using a document processing device; means for receiving and inputting task details from users; means for analyzing the received task details using natural language processing technology and extracting important keywords; means for searching past cases and solutions from the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and presenting them to the user; and means for receiving feedback information from the user and updating the database. This enables users to efficiently and quickly find the optimal solution based on past cases.

[0998] A "document processing device" is a device that reads documents stored on paper or electronic media and converts them into digital data.

[0999] A "proposal" is a document that details solutions and implementation plans for a specific problem.

[1000] A "specification document" is a document that describes the specific requirements, functions, and technical details of a system or project.

[1001] A "database" is a system that organizes, stores, and manages collected data so that it can be efficiently searched and used.

[1002] "Users" refer to officials from local governments and public institutions who use this system to solve problems.

[1003] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1004] A "keyword" is an important term or phrase that represents the content of an issue or document.

[1005] A "recommended solution" is a proposed solution that is considered optimal for solving the current problem, generated based on past cases found through searches.

[1006] "Feedback information" refers to information that users provide to the system after implementing a proposed solution, including the results, impressions, and problems encountered.

[1007] Modes for carrying out the invention

[1008] The present invention aims to efficiently solve common challenges faced by local governments. This system collects past proposals and specifications, stores them in a database, and automatically generates optimal solutions for challenges entered by users. The system includes a document processing device, natural language processing technology, a database management system, and a generative AI model.

[1009] Hardware and software usage

[1010] 1. Document processing equipment:

[1011] The server uses a scanning device to digitize past paper-based proposals and specifications. After scanning, OCR software (such as Tesseract) is used to convert the PDF documents into text data, which is then stored in a database.

[1012] 2. Natural Language Processing Techniques:

[1013] The server analyzes the received task content using a morphological analysis engine (e.g., MeCab) and a syntactic analysis engine. It extracts important keywords from the analyzed data and uses these keywords to perform a database search.

[1014] 3. Database Management:

[1015] The server stores and maintains the accessibility of collected digitized proposals and specifications using a database management system. The database uses a SQL (Structured Query Language) based database management system to provide efficient searching and high reliability.

[1016] 4. Generative AI Models:

[1017] The server uses a generative AI model to generate the optimal solution from past cases. This model is trained to generate the best solution for the given problem.

[1018] Instructions for use and operating procedures

[1019] 1. User registration and authentication:

[1020] Users access the system's web interface and enter basic information such as the name of the municipality, email address, and name into the new account creation form. After registration, the server saves the entered information to a database and sends a two-factor authentication code to the user's email address. The user enters this code to complete account verification.

[1021] 2. Inputting the assignment:

[1022] After logging in, the terminal displays a task input form to the user. The user enters detailed information such as project name, overview, requirements, budget, and deadline, and then presses the "Submit" button to send it to the server.

[1023] 3. Problem analysis and keyword extraction:

[1024] The server analyzes the received task content using natural language processing technology and extracts important keywords. For example, if the input is "Road maintenance needs to be made more efficient," the server will extract the keywords "road maintenance" and "efficiency."

[1025] 4. Search past cases:

[1026] The server searches the database for relevant past cases and solutions based on the extracted keywords, and identifies highly relevant documents.

[1027] 5. Generating and displaying recommended solutions:

[1028] The server automatically generates the most effective solution using an AI model based on the searched cases. The generated recommended solution includes specific solutions, required resources, expected effects, and implementation steps.

[1029] The terminal displays the generated solution to the user. The user can review the displayed solution and make corrections or ask additional questions as needed.

[1030] 6. Gathering feedback and updating the database:

[1031] Users implement the proposed solutions and send the results and feedback to the system. The server incorporates the received feedback into its database and uses it to improve future search and suggestion accuracy.

[1032] Specific example

[1033] 1. Improvement of public transport:

[1034] Users input challenges related to "improving the efficiency of bus operations" and describe the current operation plan and the challenges in detail.

[1035] The server uses natural language processing technology to extract keywords such as "bus operation" and "efficiency."

[1036] The server searches for relevant data and identifies examples of "bus route optimization systems" and "real-time operation information provision systems" in other municipalities.

[1037] The server generates a solution that recommends the implementation of a "bus route optimization algorithm" and an "operation monitoring system."

[1038] The terminal displays the generated proposal to the user and explains the implementation steps and expected effects.

[1039] The user implements the proposed solution and returns the results and feedback to the system. The server incorporates this feedback into the database to improve the accuracy of future suggestions.

[1040] Examples of prompts for generative AI models

[1041] "Local governments are seeking to improve the efficiency of bus operations. Please propose the best solution based on past examples."

[1042] "We are seeking proposals for improving IT education in elementary schools. Please refer to past successful examples and provide specific suggestions."

[1043] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1044] Step 1: Data Collection

[1045] The server collects data from past proposals and specifications provided by local governments nationwide and internationally. Input is document data from external storage or online repositories, and output is digitized text data.

[1046] The server retrieves documents using APIs from Google Drive and Dropbox, and digitizes the physical documents through a scanning device. The digitized documents are saved in PDF format.

[1047] The server uses OCR software (such as Tesseract) to convert PDF documents into text data and stores that text in a database.

[1048] Step 2: User Registration and Authentication

[1049] Users access the system's web interface and enter basic information such as the name of the local government, email address, and name into the new account creation form. The input is account information, and the output is a registration completion notification.

[1050] The server receives the entered information and saves it to the database. After registration is complete, an authentication code for two-factor authentication is sent to the user's email address.

[1051] The user enters the authentication code sent to them into the form to complete two-factor authentication. This allows the user to log in.

[1052] Step 3: Enter the problem

[1053] The terminal displays an assignment input form to the logged-in user. The input consists of detailed assignment information (project name, overview, requirements, budget, deadline, etc.), and the output is a confirmation of submission to the server.

[1054] The user enters the details of the issue into the form and presses the "Submit" button to send the information to the server.

[1055] Step 4: Problem Analysis

[1056] The server analyzes the received text data of the assignment content using natural language processing technology. The input is the assignment text, and the output is a set of extracted keywords.

[1057] The server uses a morphological analysis engine (such as MeCab) to break down the text into words, and then performs syntactic analysis to extract important keywords. For example, if the input is "Road maintenance needs to be made more efficient," the keywords "road maintenance" and "efficiency" will be extracted.

[1058] Step 5: Search past cases

[1059] The server searches the database for past cases and solutions based on the extracted keywords. The input is the extracted keywords, and the output is a list of relevant past cases.

[1060] The server uses TF-IDF (Term Frequency-Inverse Document Frequency) and vectorization techniques (e.g., Word2Vec) to search for highly relevant documents.

[1061] Step 6: Generating Recommended Solutions

[1062] The server automatically generates the most effective solutions using an AI model based on searched past cases. The input is data from relevant cases, and the output is a document of the recommended solution.

[1063] The server generates the optimal solution tailored to the problem to be solved, including the necessary resources, expected effects, and implementation procedures.

[1064] Step 7: Display the proposal

[1065] The terminal displays the generated recommended solution to the user. The input is the document for the recommended solution, and the output is a confirmation of the display to the user.

[1066] The user reviews the displayed solution and makes corrections or asks additional questions as needed.

[1067] The device also provides an interface for receiving user feedback.

[1068] Step 8: Gathering Feedback and Updating the Database

[1069] The user implements the proposed solution and sends the results and additional feedback to the system. The input is feedback information, and the output is a confirmation of database updates.

[1070] The server updates its database based on the feedback it receives, thereby improving the accuracy of future suggestions.

[1071] The above outlines the specific processing steps of this system.

[1072] (Application Example 1)

[1073] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1074] Store owners and managers face a wide range of operational challenges, including inventory management, improving customer service, and optimizing working hours. Traditional methods have made it difficult to efficiently find solutions to these challenges and quickly obtain concrete implementation procedures. Furthermore, there is a lack of databases for referencing past success stories, and no system exists to automatically suggest optimal solutions. Therefore, there is a need for more efficient store operations and a unified solution proposal system.

[1075] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1076] In this invention, the server includes means for collecting and managing past proposals and specifications in a database; means for receiving and inputting problem details from users; means for analyzing the received problems using natural language processing technology and extracting keywords; means for searching past cases and solutions in the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for receiving user feedback and updating the database; and means for searching past cases based on keywords extracted using natural language processing technology and then generating recommended solutions using an API of a generation AI model. This makes it possible to automatically provide optimal solutions for efficiently and quickly resolving operational challenges in physical stores.

[1077] A "database" is a collection of information that structures and stores data such as past proposals and specifications, allowing for efficient searching and management.

[1078] A "proposal" is a written proposal or plan submitted to address a specific issue or problem.

[1079] A "specification document" is a document that describes the detailed requirements, design, and procedures for a particular project or system.

[1080] A "user" is an individual or group that uses the system to input a problem and receive a solution proposal.

[1081] "Problem description" refers to the specific problems or requirements that the user wants to solve.

[1082] "Means of receiving" refers to the method by which the system receives and processes data entered by the user.

[1083] "Natural language processing technology" is a technology that analyzes text data entered by a user and uses computers to understand and process human language.

[1084] "Keywords" are important words or phrases extracted from a task or document.

[1085] A "search method" is a way of finding information within a database based on specified conditions.

[1086] A "recommended solution" refers to a suggestion to the user of the most suitable solution based on past cases and data that have been searched.

[1087] A "generative AI model" is a learning model that uses artificial intelligence to generate new solutions based on specified data and conditions.

[1088] "API" stands for Application Programming Interface, and it is an interface for exchanging functions and data between different software programs.

[1089] "Feedback" refers to information returned to the system by users regarding the results and impressions of implementing the suggested solutions.

[1090] "Means of updating" refers to the methods by which a system adds new information and revises or modifies existing data.

[1091] System Overview

[1092] This invention is a system for efficiently solving common challenges in store operations for owners and managers of physical stores. It collects past proposals and specifications in a database, generates optimal solutions based on user-inputted challenges, and collects feedback. This system consists of the following main components:

[1093] Hardware and software

[1094] Database Server: The server collects and manages past proposals and specifications in the database. Python's `beautifulsoup` and `requests` libraries are used for data collection.

[1095] Authentication system: Implement user registration and two-factor authentication using Firebase Authentication.

[1096] User Interface: The frontend is built with Flutter and provides a form for users to input their tasks.

[1097] Natural Language Processing: spaCy will be used for text analysis to extract keywords from the assignment content.

[1098] Search engine: Uses TF-IDF (Inverse Document Frequency) and Elasticsearch to search for similar cases within the database.

[1099] Generative AI Model: Uses the GPT-4 API to generate solutions based on searched case studies.

[1100] Database: Use Firebase Firestore to store feedback data and update the database.

[1101] Specific steps of the invention

[1102] 1. Data Collection: The server scrapes past proposals and specifications from the web and stores them in a database. For example, proposals can be retrieved using Python with requests.get("http: / / example.com / proposals").

[1103] 2. User Authentication: Users create an account using Firebase Authentication and log in after two-factor authentication. An authentication code is sent via email, and authentication is completed by entering this code.

[1104] 3. Problem Input: The user interface is built with Flutter, and users input specific store operation challenges here. For example, a form is provided for inputting "improvement of inventory management."

[1105] 4. Problem Analysis: The server uses spaCy to analyze the received problem and extract keywords. The model is loaded with nlp = spacy.load("en_core_web_sm") and keywords are extracted with doc = nlp("Improved inventory management").

[1106] 5. Searching past cases: The server uses TF-IDF or Elasticsearch to search for similar cases in the database. The search is performed using es.search(index="proposals", body={"query": {"match": {"content": "Inventory Management"}}}).

[1107] 6. Generating Recommended Solutions: Use the GPT-4 API to generate solutions based on the searched cases. An example of a prompt would be: "Please propose the best solution to achieve efficient inventory management. Please also describe the implementation method in detail, referencing past success stories."

[1108] 7. Solution Display: Review the suggestions generated in the user interface and make modifications or ask additional questions as needed.

[1109] 8. Feedback Collection: Users submit their results and feedback on trying out the suggested solutions back to the system and store them in Firebase Firestore.

[1110] Through this series of processes, it becomes possible to solve operational challenges in physical stores efficiently and quickly.

[1111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1112] Step 1: Data Collection

[1113] The server collects past proposals and specifications from national and international sources. Specifically, it uses the Python libraries beautifulsoup and requests to scrape data from websites and stores the retrieved document data in a database. For example, it retrieves proposals using requests.get("http: / / example.com / proposals") and parses them with beautifulsoup. The input is the URL of the website, and the output is the document data stored in the database.

[1114] Step 2: User Authentication

[1115] The device provides an authentication system for users to create accounts and log in. It implements user registration and two-factor authentication using Firebase Authentication. Specifically, the user enters their email address and password, and the system sends an authentication code via email. The user enters this code to complete authentication. The input is the user's email address and password, and the output is a message indicating authentication success or failure.

[1116] Step 3: Enter the assignment

[1117] Users access a form via their device to input specific store operation challenges. Using a Flutter-based interface, they enter the project name, overview, requirements, budget, deadline, etc., and then press the "Submit" button to send the information to the server. The input is detailed information about the challenge provided by the user, and the output is the challenge data stored on the server.

[1118] Step 4: Problem Analysis

[1119] The server analyzes the received task data using natural language processing technology (spaCy). First, it performs morphological analysis, and then syntactic analysis to extract important keywords. Specifically, it loads the model using `nlp = spacy.load("en_core_web_sm")` and extracts keywords using `doc = nlp("Improved inventory management")`. The input is the text data of the task, and the output is the extracted keywords.

[1120] Step 5: Search past cases

[1121] The server searches past cases in the database based on the extracted keywords. It uses TF-IDF and Elasticsearch to identify the most relevant documents in the database. Specifically, it performs a search using es.search(index="proposals", body={"query": {"match": {"content": "Inventory Management"}}}). The input is the extracted keywords, and the output is a list of search results.

[1122] Step 6: Generating Recommended Solutions

[1123] The server generates appropriate solutions using a generative AI model (GPT-4 API) based on the search results. A prompt is provided as input, and the AI ​​generates a detailed solution based on that prompt. An example prompt is: "Please propose the optimal solution for achieving efficient inventory management. Please also describe the implementation method in detail, referencing past success stories." The input consists of the prompt and search results, and the output is the generated solution.

[1124] Step 7: Display Solution

[1125] The terminal displays the generated solution to the user. The user interface shows detailed suggestions, along with the necessary resources and expected effects. The user can review this and ask additional questions or make modifications. The input is the generated solution, and the output is the suggestions displayed to the user.

[1126] Step 8: Gathering Feedback

[1127] Users provide feedback and results from implementing the proposed solution to the system via their device. The server collects this feedback and stores it in Firebase Firestore. This feedback is used when generating the next solution. The input is the user's feedback information, and the output is the updated database.

[1128] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1129] System Overview

[1130] This invention provides a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on user-inputted problems. Furthermore, by incorporating an emotion engine that recognizes user emotions during problem input and feedback, the system can provide more personalized solution suggestions. This system consists of multiple means for data collection, user authentication, problem analysis, emotion recognition, proposal generation, and feedback collection, thereby improving the efficiency of information exchange and solution proposals among local governments.

[1131] Explain the program's processing in natural language.

[1132] 1. Data collection:

[1133] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[1134] 2. Importing data:

[1135] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[1136] 3. User registration and authentication:

[1137] Users enter basic information (such as the name of their local government, the name of the person in charge, and their email address) to create an account for their local government.

[1138] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[1139] 4. Inputting the assignment:

[1140] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form.

[1141] During input, the server uses an emotion engine to analyze the user's input speed, patterns, and facial expression data (for example, if a webcam is used) to identify the user's emotional state.

[1142] 5. Problem Analysis:

[1143] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[1144] The server performs morphological analysis, dividing the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships within the text and extract important keywords.

[1145] 6. Search past cases:

[1146] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[1147] 7. Generating Recommended Solutions:

[1148] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions that take into account the user's emotional state using an emotion engine. These recommended solutions include the means of resolution, the resources required, and the expected effects. For example, if the user is stressed, the suggestions will be concise and include step-by-step implementation instructions.

[1149] 8. Display of proposals:

[1150] The device displays the generated recommended solutions to the user. It helps the user understand the suggestions by customizing them based on the user's emotional state. The user can review these suggestions and ask additional questions or make modifications as needed.

[1151] 9. Gathering feedback:

[1152] The user implements the proposed solution and inputs the results and any additional feedback into the system.

[1153] When feedback is received, the emotion engine re-analyzes the user's emotional state and adjusts the system's responsiveness and friendliness.

[1154] The server receives user feedback, incorporates it into the database, and uses it to improve search accuracy and the system in the future.

[1155] Specific example

[1156] Improvement of public transportation

[1157] 1. Data collection:

[1158] The server collects past proposals and specifications related to public transportation into a database.

[1159] 2. User registration and authentication:

[1160] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[1161] 3. Task input and emotion recognition:

[1162] When users input challenges related to "improving the efficiency of bus operations," the emotion engine analyzes input speed, patterns, and facial expressions via webcam to recognize when the user is experiencing stress.

[1163] 4. Problem Analysis:

[1164] The server extracts keywords such as "bus operation" and "efficiency improvements" and searches for related past cases.

[1165] 5. Search past cases:

[1166] The server identifies relevant cases from the database, such as "bus route optimization systems" and "real-time operation information provision systems."

[1167] 6. Generating Recommended Solutions:

[1168] The server, taking into account the user's stress level as determined by the emotion engine, recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system" that include step-by-step execution procedures.

[1169] 7. Display of proposal:

[1170] The terminal displays the generated proposal to the user in a concise and step-by-step manner, including the implementation procedures and expected effects.

[1171] 8. Gathering feedback:

[1172] The user implements the proposed solution and inputs the results and additional feedback into the system. As feedback is entered, the emotion engine analyzes the user's emotions and adjusts the system's responsiveness accordingly.

[1173] As described above, by using the system of the present invention, local governments can efficiently solve problems and quickly obtain optimal solutions. Furthermore, by taking into account the user's emotional state, more personalized solution proposals can be realized.

[1174] The following describes the processing flow.

[1175] Step 1:

[1176] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[1177] Step 2:

[1178] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[1179] Step 3:

[1180] Users enter basic information (such as the name of their local government, the name of the contact person, and their email address) to create an account for their local government. After registration, the system requests two-factor authentication.

[1181] Step 4:

[1182] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[1183] Step 5:

[1184] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form. During this process, the emotion engine monitors the speed and patterns of webcam and keyboard input.

[1185] Step 6:

[1186] The emotion engine analyzes user input data and facial expression data to identify the user's emotional state (stress, anxiety, joy, etc.). This allows it to determine the user's emotional state at the time of input.

[1187] Step 7:

[1188] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[1189] Step 8:

[1190] The server performs morphological analysis to break down the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships within the text and extract important keywords. For example, if the input is "improving the efficiency of bus operations," the server will extract the keywords "bus operations" and "efficiency."

[1191] Step 9:

[1192] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[1193] Step 10:

[1194] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions considering the user's emotional state using an emotion engine. For example, if the user is stressed, the suggestions will be concise and include step-by-step implementation instructions.

[1195] Step 11:

[1196] The device displays the generated recommended solutions to the user. It helps the user understand the suggestions by customizing them based on the user's emotional state. The user can review these suggestions and ask additional questions or make modifications as needed.

[1197] Step 12:

[1198] The user implements the proposed solution and inputs the results and additional feedback into the system. At this time, the emotion engine re-analyzes the user's emotional state.

[1199] Step 13:

[1200] The server receives user feedback, reflects it in the database, and uses it to improve future search accuracy and the system. It adjusts the system's responsiveness and friendliness based on the analysis results of the emotion engine.

[1201] The above outlines the specific processing steps of a system that incorporates user emotion recognition capabilities. This system enables local governments to efficiently solve problems and quickly obtain optimal solutions that take emotions into consideration.

[1202] (Example 2)

[1203] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1204] Local governments often struggle to quickly find appropriate solutions to efficiently address common challenges. Furthermore, current systems struggle to automatically generate personalized suggestions that take into account user emotional states. Additionally, there's a lack of mechanisms for efficiently incorporating feedback and improving the system. This frequently leads to delays in information sharing and effective solution proposals among local governments.

[1205] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1206] In this invention, the server includes means for collecting and managing past proposals and specifications in a database; means for users to input and receive problem details; means for analyzing the received problems using natural language processing technology and extracting keywords; means for searching past cases and solutions in the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for receiving user feedback and updating the database; means for analyzing the user's emotional state using an emotion recognition engine; and means for optimizing recommended solutions based on the user's emotional state. This enables local governments to efficiently solve problems and quickly obtain personalized suggestions based on the user's emotional state.

[1207] A "database" is an information storage system that accumulates information such as past proposals and specifications, and allows for searching and management of that information.

[1208] A "proposal" is a document that outlines solutions to a particular project or problem.

[1209] A "specification document" is a document that summarizes the detailed requirements and specifications of a particular project or product.

[1210] A "user" is a local government official who uses this system to input tasks and provide feedback.

[1211] "Natural language processing technology" refers to the technology used to analyze, understand, and generate human language.

[1212] "Keywords" are important words or phrases extracted from texts or documents.

[1213] An "emotion recognition engine" is a technology that analyzes the user's input speed, keystroke patterns, facial expression data, and other factors to identify the user's emotional state.

[1214] A "solution" is a specific means or method for solving a particular problem or issue.

[1215] "Feedback" refers to the results, evaluations, and additional comments that a user provides after implementing a suggested solution.

[1216] Morphological analysis is a technique that breaks down text into words and phrases for analysis.

[1217] "Syntactic analysis" is a technique for analyzing the relationships between words and phrases within a text.

[1218] Two-factor authentication is an authentication process that uses two different authentication methods to enhance user authentication.

[1219] System Overview

[1220] This invention is a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on problems entered by users. Furthermore, by combining it with an emotion recognition engine, it becomes possible to make suggestions that take into account the user's emotional state. This system consists of multiple means for data collection, user authentication, problem analysis, emotion recognition, suggestion generation, and feedback collection.

[1221] Data collection

[1222] The server collects past proposals and specifications from local governments across Japan and internationally. This collection uses web crawling technology and scanners, and converts paper-based documents into text data using OCR (Optical Character Recognition) technology.

[1223] Import data

[1224] The server imports the collected documents into a database, extracts the document metadata (creation date, municipality name, project name, etc.), and categorizes them appropriately. This allows for a smoother subsequent search process.

[1225] User registration and authentication

[1226] Users create their own municipal account to gain access to the system. Registration is completed by entering the necessary basic information (municipality name, contact person's name, email address, etc.).

[1227] The server sends an authentication code to the email address entered by the user, and the user is granted access to the system after entering that code to complete two-factor authentication.

[1228] Task input and emotion recognition

[1229] After logging in, users enter detailed information such as project name, overview, requirements, budget, and deadline into the task input form.

[1230] The server operates an emotion recognition engine that analyzes the user's input speed, keystroke patterns, and facial expression data using a webcam to identify the user's emotional state.

[1231] Problem analysis

[1232] The server analyzes the task text received from the user using natural language processing technology. Specifically, it performs morphological analysis to break down the task text into words and phrases, then performs syntactic analysis to analyze the relationships between them and extract important keywords.

[1233] Search past cases

[1234] The server searches the database for past cases and solutions based on the extracted keywords. It uses TF-IDF and vectorization techniques to identify highly relevant documents.

[1235] Generating Recommended Solutions

[1236] The server generates the most suitable recommended solution for the user based on highly relevant examples and solutions obtained from the search results. Considering the user's emotional state, as provided by the emotion recognition engine, it offers concise and step-by-step suggestions to users experiencing stress.

[1237] Display of proposals

[1238] The device displays the generated recommended solutions to the user. The suggestions are customized according to the user's emotional state, and the user can review them and ask additional questions or make modifications as needed.

[1239] Gathering feedback

[1240] The user implements the proposed solution and inputs the results and additional feedback into the system. During this process, the emotion recognition engine analyzes the user's emotional state and adjusts the system's responsiveness accordingly.

[1241] The server receives user feedback and reflects it in the database. This will lead to improvements in search accuracy and system performance in the future.

[1242] Specific example

[1243] Improvement of public transportation

[1244] 1. Data Collection

[1245] The server collects past proposals and specifications related to public transportation.

[1246] 2. User Registration and Authentication

[1247] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[1248] 3. Task input and emotion recognition

[1249] When a user inputs a problem related to "improving the efficiency of bus operations," the emotion recognition engine analyzes the input speed, keystroke patterns, and facial expressions via the webcam to recognize if the user is experiencing stress.

[1250] 4. Problem Analysis

[1251] The server extracts keywords such as "bus operation" and "efficiency improvements" and searches for related past cases.

[1252] 5. Searching for past cases

[1253] The server identifies relevant cases from the database, such as "bus route optimization systems" and "real-time operation information provision systems."

[1254] 6. Generating Recommended Solutions

[1255] The server, taking into account the user's stress level as assessed by the emotion recognition engine, recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system" that include step-by-step execution procedures.

[1256] 7. Display of Proposal

[1257] The terminal displays the generated proposal to the user in a concise and step-by-step manner, including the implementation procedures and expected effects.

[1258] 8. Gathering Feedback

[1259] The user implements the proposed solution and inputs the results and additional feedback into the system. As feedback is entered, the emotion recognition engine analyzes the user's emotions, and the system's responsiveness is adjusted accordingly.

[1260] This invention enables local governments to efficiently solve problems and quickly obtain personalized suggestions based on users' emotional states.

[1261] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1262] Step 1: Data Collection and Import

[1263] Input: Past proposals and specifications provided by local governments nationwide and internationally.

[1264] The server uses web crawling technology to collect proposals and specifications from online sources. Furthermore, paper-based documents are digitized using a scanner and converted into text data using OCR (optical character recognition) technology.

[1265] Output: A dataset of digitized proposals and specifications.

[1266] Step 2: Import into database

[1267] Input: Digitized proposals and specifications.

[1268] The server imports the collected documents into a database. It extracts the document metadata (creation date and time, name of providing municipality, project name, etc.) and classifies each into the appropriate category.

[1269] Output: Structured database entries.

[1270] Step 3: User Registration and Authentication

[1271] Input: Basic information entered by the user (name of local government, name of contact person, email address, etc.).

[1272] The user creates their own municipal account to gain access to the system. The server sends an authentication code to the entered email address.

[1273] Output: User authentication was successful, and access rights to the system were granted.

[1274] Step 4: Task Input and Emotion Recognition

[1275] Input: Issue information entered by the user (project name, overview, requirements, budget, deadline, etc.).

[1276] The user fills in detailed information on the task input form. The server acquires data on input speed, keystroke patterns, and, if necessary, facial expression data using a webcam, and uses an emotion recognition engine to identify the user's emotional state.

[1277] Output: Task information with analyzed emotional states.

[1278] Step 5: Problem Analysis

[1279] Input: Task information with analyzed emotional states.

[1280] The server analyzes the given text using natural language processing technology. Morphological analysis breaks down the text into words and phrases, and syntactic analysis analyzes the relationships between them to extract important keywords.

[1281] Output: Issue information with keywords extracted.

[1282] Step 6: Search past cases

[1283] Input: Issue information from which keywords have been extracted.

[1284] The server searches the database for past cases and solutions based on the extracted keywords. It uses TF-IDF and vectorization techniques to identify highly relevant documents.

[1285] Output: A list of relevant past cases and solutions.

[1286] Step 7: Generating Recommended Solutions

[1287] Input: A list of relevant past cases and solutions, and the user's emotional state.

[1288] The server generates recommended solutions based on highly relevant cases and solutions. Considering the results of the emotion recognition engine, it provides concise and step-by-step suggestions if the user is experiencing stress.

[1289] Output: Recommended solutions optimized for the user.

[1290] Step 8: Display the proposal

[1291] Input: Recommended solutions optimized for the user.

[1292] The device displays the generated recommended solutions to the user. The suggestions are customized according to the user's emotional state.

[1293] Output: Proposed solutions confirmed by the user.

[1294] Step 9: Gathering Feedback

[1295] Input: User feedback after solution implementation.

[1296] The user implements the proposed solution and inputs the results and additional feedback into the system. The server uses an emotion recognition engine to analyze the user's emotional state when providing feedback.

[1297] Output: Database entries where feedback was collected.

[1298] The above explains the system's program processing in concrete steps. Based on this, you should gain a deeper understanding of input, data processing, and output in each processing step.

[1299] (Application Example 2)

[1300] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1301] To efficiently solve the common challenges faced by local governments, a system is needed that effectively utilizes past solutions and proposals to quickly suggest optimal solutions. However, current systems lack a personalization function that takes emotional states into account, resulting in a significant burden on users. Furthermore, it is expected that more appropriate solutions can be provided by adjusting the method of presenting solutions based on emotional states. This invention aims to solve the above problems.

[1302] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting and managing past proposals and design documents in a database; means for receiving and inputting the content of a problem from the user; means for analyzing the received problem using natural language processing technology and extracting important keywords; means for searching past cases and solutions in the database based on the extracted important keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for analyzing the user's emotional state; means for personalizing the recommended solutions based on the emotional analysis results; and means for receiving user feedback and updating the database. This enables the rapid generation of optimal solutions based on past cases and the provision of personalized solutions that take into account the user's emotional state.

[1303] A "database" is a system for collecting and managing information, including past proposals and design documents.

[1304] A "user" refers to a local government official or related party who inputs their own problems and receives solutions from the system.

[1305] "Problem description" refers to information that includes the specific problems and requirements that the user seeks to solve.

[1306] "Natural language processing technology" is a technology that analyzes text data entered by a user and understands important words and context.

[1307] "Key terms" are specific words or phrases extracted using natural language processing technology, and are elements considered important for solving the problem.

[1308] A "case study" refers to a record of proposals or solutions that have been made to similar problems in the past.

[1309] A "solution" is a specific means or method proposed to solve a problem.

[1310] "Emotional state" refers to the psychological state a user is in when entering information into a task or providing feedback.

[1311] "Emotional analysis" is a technology that analyzes user input data and behavioral patterns to identify the user's emotional state.

[1312] "Personalization" refers to adjusting the solutions provided according to the user's emotional state and individual needs.

[1313] "Feedback" refers to users inputting the results of implementing the proposed solutions, new insights, and other relevant information into the system.

[1314] Two-factor authentication is a method of strengthening user authentication by using multiple authentication methods (e.g., password and email verification).

[1315] Morphological analysis is a technique that divides a sentence into words and analyzes their parts of speech and base forms.

[1316] "Syntactic analysis" is a technique that analyzes the structure of a text and reveals the interrelationships between individual words and phrases.

[1317] "Presentation method" refers to the way or format in which a solution is visually displayed to the user.

[1318] A "step-by-step implementation procedure" is a description that includes a series of specific steps for implementing a solution.

[1319] System Configuration

[1320] This invention is a system for local governments to efficiently solve problems, and consists of a database, server, terminals, and users. The purpose of this system is to analyze the emotional state of users based on the problems they input and to automatically generate the optimal solution.

[1321] Hardware and software to be used

[1322] Database: SQLite is used to collect and manage past proposals and design documents.

[1323] Server: Receives task input from users and functions as a platform for natural language processing and sentiment analysis.

[1324] Natural language processing techniques: For document analysis, we use Python libraries such as TextBlob, as well as morphological and syntactic analysis tools.

[1325] Emotion Analysis Model: Using the Hugging Face transformers library, the emotional state of the user is analyzed from their text data.

[1326] TF-IDF Vectorizer: Used to calculate the relevance of past cases and recommended solutions.

[1327] Device: A device used by the user to input a problem and view suggested solutions. This includes PCs, tablets, and smartphones.

[1328] Program processing details

[1329] 1. Database Setup and Data Collection: The server collects past proposals and design documents from local governments nationwide and internationally, and imports them into the database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[1330] 2. User task input: The user uses a terminal to input information such as the specific project name, overview, requirements, budget, and deadline into the task input form. The server receives this information and analyzes it using natural language processing technology.

[1331] 3. Emotional State Analysis: Based on the text data entered by the user, the server uses an emotional analysis model to identify the user's emotional state. This allows the server to understand the user's psychological situation, such as whether they are experiencing stress.

[1332] 4. Generating Recommended Solutions: The server extracts key keywords and searches the database for relevant past cases and solutions. Based on the sentiment analysis results, it generates recommended solutions from highly relevant cases and provides personalized solutions according to the user's emotional state.

[1333] 5. Gathering Feedback and Updating the Database: Users implement the solutions provided and input the results and feedback into the system. The server receives this and updates the database to use it for future search accuracy and system improvements.

[1334] Specific example

[1335] Let's take an example where a city's transportation official inputs a problem regarding traffic congestion around a major train station. When the official inputs the problem, "Traffic volume around the city's major train station has increased excessively, causing frequent congestion," the system uses an emotion analysis model to identify the official's stress level. As a result, it proposes phased solutions such as "introducing dedicated bus lanes" and "optimizing traffic signals," and provides detailed implementation procedures and expected effects.

[1336] Example of a prompt

[1337] Prompt: "Please provide effective solutions to alleviate traffic congestion in the city."

[1338] Expected answer: "Past examples have shown that introducing dedicated bus lanes and optimizing traffic signals are effective. The implementation procedure is as follows: First..."

[1339] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1340] Step 1:

[1341] The server collects and manages past proposals and design documents in a database. Data collection is performed from local governments nationwide and internationally, involving document scanning and text conversion using OCR (Optical Character Recognition). Scanned documents are received as input and imported into the database as text data. The output is managed text data.

[1342] Step 2:

[1343] The user enters the task details using a terminal. They enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form and send it to the server. The entered task details are received by the server. The input is the task details entered by the user on the terminal, and the output is the received task details data.

[1344] Step 3:

[1345] The server analyzes the received assignment content using natural language processing techniques. This process involves morphological and syntactic analysis to extract key terms. The server receives the assignment content text data as input and outputs a list of extracted key terms.

[1346] Step 4:

[1347] The server searches the database for past cases and solutions based on the extracted key keywords. It uses a TF-IDF vectorizer to calculate relevance and identify the most relevant past cases and solutions. The input is a list of key keywords and a database of past proposals, and the output is a list of highly relevant cases and solutions.

[1348] Step 5:

[1349] The server analyzes the user's emotional state. It inputs the text data entered by the user into an emotional analysis model to identify the emotional state. The input consists of the task description text and the user's input data, while the output is the evaluation result of the emotional state.

[1350] Step 6:

[1351] The server generates recommended solutions based on searched cases and personalizes them based on sentiment analysis results. Specifically, if the user is experiencing stress, it presents a solution that includes concise, step-by-step instructions. The input is a list of relevant cases and the results of the sentiment state assessment, and the output is a personalized solution.

[1352] Step 7:

[1353] The terminal displays the generated recommended solution to the user. The user reviews it and asks additional questions or makes modifications as needed. The input is the personalized solution, and the output is a visual presentation of the solution displayed to the user.

[1354] Step 8:

[1355] The user implements the proposed solution and inputs the results and feedback into the system. The server receives this information and uses an emotion analysis model to re-analyze the user's emotional state at the time of feedback. The input is the feedback content, and the output is the updated evaluation result of the emotional state.

[1356] Step 9:

[1357] The server incorporates the feedback into the database, using it to improve future search accuracy and the system. The input consists of feedback content and emotional state evaluation results, while the output is the updated database.

[1358] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1359] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1360] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1361] [Fourth Embodiment]

[1362] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1363] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1364] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1365] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1366] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1367] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1368] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1369] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1370] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1371] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1372] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1373] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1374] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1375] System Overview

[1376] This invention is a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on problems entered by users. This system consists of multiple means for data collection, user authentication, problem analysis, proposal generation, and feedback collection, thereby improving the efficiency of information exchange and solution proposals among local governments.

[1377] Explain the program's processing in natural language.

[1378] 1. Data collection:

[1379] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[1380] 2. User registration and authentication:

[1381] Users create an account with their local government and enter their basic information. After registration, the system requests two-factor authentication and sends an authentication code to the user's email address. Users enter this code to complete the login process.

[1382] 3. Input the problem:

[1383] After logging in, the terminal displays a task input form to the user. The user enters the specific project name, overview, requirements, budget, deadline, etc., and then presses the "Submit" button to send it to the server.

[1384] 4. Problem Analysis:

[1385] The server analyzes the received assignment text using natural language processing technology. First, it performs morphological analysis, and then syntactic analysis to extract important keywords. For example, if the input is "The bus service needs to be made more efficient," the server will extract the keywords "bus service" and "efficiency."

[1386] 5. Search past cases:

[1387] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[1388] 6. Generating Recommended Solutions:

[1389] The server automatically generates the most effective and similar solutions based on the searched cases. The recommended solutions include the solution itself, the necessary resources, the expected effects, and implementation steps.

[1390] 7. Display of proposal:

[1391] The device displays the generated recommended solutions to the user. The user can review these, make corrections, or ask additional questions.

[1392] 8. Gathering feedback:

[1393] After implementing the proposed solution, the user sends the results and any additional feedback to the system. The server updates the database to reflect the received feedback and improve future search accuracy.

[1394] Specific example

[1395] Improvement of public transportation

[1396] 1. Data collection:

[1397] The server collects past proposals and specifications related to public transportation into a database.

[1398] 2. User registration and authentication:

[1399] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[1400] 3. Input the problem:

[1401] Users input challenges related to "improving the efficiency of bus operations" and describe the current operation plan and the challenges in detail.

[1402] 4. Problem Analysis:

[1403] The server extracts keywords such as "bus operation" and "efficiency."

[1404] 5. Search past cases:

[1405] The server searches for relevant data and discovers systems such as "bus route optimization systems" and "real-time operation information provision systems" in other municipalities.

[1406] 6. Generating Recommended Solutions:

[1407] The server recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system."

[1408] 7. Display of proposal:

[1409] The terminal displays the generated proposal to the user, including the implementation steps and expected effects.

[1410] 8. Gathering feedback:

[1411] Users implement the suggested solutions and provide feedback on the results and their impressions to the system. The server incorporates this feedback into its database to improve the accuracy of future suggestions.

[1412] As described above, by using the system of the present invention, local governments can efficiently solve common problems and quickly obtain optimal solutions.

[1413] The following describes the processing flow.

[1414] Step 1:

[1415] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[1416] Step 2:

[1417] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[1418] Step 3:

[1419] Users enter basic information (such as the name of their local government, the name of the person in charge, and their email address) to create an account for their local government.

[1420] Step 4:

[1421] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[1422] Step 5:

[1423] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form.

[1424] Step 6:

[1425] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[1426] Step 7:

[1427] The server performs morphological analysis, dividing the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships between elements within the sentence.

[1428] Step 8:

[1429] The server extracts key keywords and uses those keywords to search for past cases and solutions in the database.

[1430] Step 9:

[1431] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions. These recommended solutions include the solution itself, the resources required, and the expected effects.

[1432] Step 10:

[1433] The terminal displays the generated recommended solution to the user. The user can review it and ask additional questions or make corrections as needed.

[1434] Step 11:

[1435] The user implements the proposed solution and inputs the results and any additional feedback into the system.

[1436] Step 12:

[1437] The server receives feedback from users, reflects it in the database, and improves future search accuracy.

[1438] The above outlines the specific processing steps of the program. This system enables local governments to efficiently solve problems and quickly obtain optimal solutions.

[1439] (Example 1)

[1440] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1441] To efficiently solve common challenges faced by public institutions such as local governments, it is necessary to quickly find the optimal solution from past success stories and proposals. However, manual searching and analysis are time-consuming and labor-intensive, and are prone to information bias and omissions. As a result, it is difficult to quickly find effective solutions.

[1442] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1443] In this invention, the server includes means for collecting and managing past proposals and specifications in a database using a document processing device; means for receiving and inputting task details from users; means for analyzing the received task details using natural language processing technology and extracting important keywords; means for searching past cases and solutions from the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and presenting them to the user; and means for receiving feedback information from the user and updating the database. This enables users to efficiently and quickly find the optimal solution based on past cases.

[1444] A "document processing device" is a device that reads documents stored on paper or electronic media and converts them into digital data.

[1445] A "proposal" is a document that details solutions and implementation plans for a specific problem.

[1446] A "specification document" is a document that describes the specific requirements, functions, and technical details of a system or project.

[1447] A "database" is a system that organizes, stores, and manages collected data so that it can be efficiently searched and used.

[1448] "Users" refer to officials from local governments and public institutions who use this system to solve problems.

[1449] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1450] A "keyword" is an important term or phrase that represents the content of an issue or document.

[1451] A "recommended solution" is a proposed solution that is considered optimal for solving the current problem, generated based on past cases found through searches.

[1452] "Feedback information" refers to information that users provide to the system after implementing a proposed solution, including the results, impressions, and problems encountered.

[1453] Modes for carrying out the invention

[1454] The present invention aims to efficiently solve common challenges faced by local governments. This system collects past proposals and specifications, stores them in a database, and automatically generates optimal solutions for challenges entered by users. The system includes a document processing device, natural language processing technology, a database management system, and a generative AI model.

[1455] Hardware and software usage

[1456] 1. Document processing equipment:

[1457] The server uses a scanning device to digitize past paper-based proposals and specifications. After scanning, OCR software (such as Tesseract) is used to convert the PDF documents into text data, which is then stored in a database.

[1458] 2. Natural Language Processing Techniques:

[1459] The server analyzes the received task content using a morphological analysis engine (e.g., MeCab) and a syntactic analysis engine. It extracts important keywords from the analyzed data and uses these keywords to perform a database search.

[1460] 3. Database Management:

[1461] The server stores and maintains the accessibility of collected digitized proposals and specifications using a database management system. The database uses a SQL (Structured Query Language) based database management system to provide efficient searching and high reliability.

[1462] 4. Generative AI Models:

[1463] The server uses a generative AI model to generate the optimal solution from past cases. This model is trained to generate the best solution for the given problem.

[1464] Instructions for use and operating procedures

[1465] 1. User registration and authentication:

[1466] Users access the system's web interface and enter basic information such as the name of the municipality, email address, and name into the new account creation form. After registration, the server saves the entered information to a database and sends a two-factor authentication code to the user's email address. The user enters this code to complete account verification.

[1467] 2. Inputting the assignment:

[1468] After logging in, the terminal displays a task input form to the user. The user enters detailed information such as project name, overview, requirements, budget, and deadline, and then presses the "Submit" button to send it to the server.

[1469] 3. Problem analysis and keyword extraction:

[1470] The server analyzes the received task content using natural language processing technology and extracts important keywords. For example, if the input is "Road maintenance needs to be made more efficient," the server will extract the keywords "road maintenance" and "efficiency."

[1471] 4. Search past cases:

[1472] The server searches the database for relevant past cases and solutions based on the extracted keywords, and identifies highly relevant documents.

[1473] 5. Generating and displaying recommended solutions:

[1474] The server automatically generates the most effective solution using an AI model based on the searched cases. The generated recommended solution includes specific solutions, required resources, expected effects, and implementation steps.

[1475] The terminal displays the generated solution to the user. The user can review the displayed solution and make corrections or ask additional questions as needed.

[1476] 6. Gathering feedback and updating the database:

[1477] Users implement the proposed solutions and send the results and feedback to the system. The server incorporates the received feedback into its database and uses it to improve future search and suggestion accuracy.

[1478] Specific example

[1479] 1. Improvement of public transport:

[1480] Users input challenges related to "improving the efficiency of bus operations" and describe the current operation plan and the challenges in detail.

[1481] The server uses natural language processing technology to extract keywords such as "bus operation" and "efficiency."

[1482] The server searches for relevant data and identifies examples of "bus route optimization systems" and "real-time operation information provision systems" in other municipalities.

[1483] The server generates a solution that recommends the implementation of a "bus route optimization algorithm" and an "operation monitoring system."

[1484] The terminal displays the generated proposal to the user and explains the implementation steps and expected effects.

[1485] The user implements the proposed solution and returns the results and feedback to the system. The server incorporates this feedback into the database to improve the accuracy of future suggestions.

[1486] Examples of prompts for generative AI models

[1487] "Local governments are seeking to improve the efficiency of bus operations. Please propose the best solution based on past examples."

[1488] "We are seeking proposals for improving IT education in elementary schools. Please refer to past successful examples and provide specific suggestions."

[1489] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1490] Step 1: Data Collection

[1491] The server collects data from past proposals and specifications provided by local governments nationwide and internationally. Input is document data from external storage or online repositories, and output is digitized text data.

[1492] The server retrieves documents using APIs from Google Drive and Dropbox, and digitizes the physical documents through a scanning device. The digitized documents are saved in PDF format.

[1493] The server uses OCR software (such as Tesseract) to convert PDF documents into text data and stores that text in a database.

[1494] Step 2: User Registration and Authentication

[1495] Users access the system's web interface and enter basic information such as the name of the local government, email address, and name into the new account creation form. The input is account information, and the output is a registration completion notification.

[1496] The server receives the entered information and saves it to the database. After registration is complete, an authentication code for two-factor authentication is sent to the user's email address.

[1497] The user enters the authentication code sent to them into the form to complete two-factor authentication. This allows the user to log in.

[1498] Step 3: Enter the problem

[1499] The terminal displays an assignment input form to the logged-in user. The input consists of detailed assignment information (project name, overview, requirements, budget, deadline, etc.), and the output is a confirmation of submission to the server.

[1500] The user enters the details of the issue into the form and presses the "Submit" button to send the information to the server.

[1501] Step 4: Problem Analysis

[1502] The server analyzes the received text data of the assignment content using natural language processing technology. The input is the assignment text, and the output is a set of extracted keywords.

[1503] The server uses a morphological analysis engine (such as MeCab) to break down the text into words, and then performs syntactic analysis to extract important keywords. For example, if the input is "Road maintenance needs to be made more efficient," the keywords "road maintenance" and "efficiency" will be extracted.

[1504] Step 5: Search past cases

[1505] The server searches the database for past cases and solutions based on the extracted keywords. The input is the extracted keywords, and the output is a list of relevant past cases.

[1506] The server uses TF-IDF (Term Frequency-Inverse Document Frequency) and vectorization techniques (e.g., Word2Vec) to search for highly relevant documents.

[1507] Step 6: Generating Recommended Solutions

[1508] The server automatically generates the most effective solutions using an AI model based on searched past cases. The input is data from relevant cases, and the output is a document of the recommended solution.

[1509] The server generates the optimal solution tailored to the problem to be solved, including the necessary resources, expected effects, and implementation procedures.

[1510] Step 7: Display the proposal

[1511] The terminal displays the generated recommended solution to the user. The input is the document for the recommended solution, and the output is a confirmation of the display to the user.

[1512] The user reviews the displayed solution and makes corrections or asks additional questions as needed.

[1513] The device also provides an interface for receiving user feedback.

[1514] Step 8: Gathering Feedback and Updating the Database

[1515] The user implements the proposed solution and sends the results and additional feedback to the system. The input is feedback information, and the output is a confirmation of database updates.

[1516] The server updates its database based on the feedback it receives, thereby improving the accuracy of future suggestions.

[1517] The above outlines the specific processing steps of this system.

[1518] (Application Example 1)

[1519] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1520] Store owners and managers face a wide range of operational challenges, including inventory management, improving customer service, and optimizing working hours. Traditional methods have made it difficult to efficiently find solutions to these challenges and quickly obtain concrete implementation procedures. Furthermore, there is a lack of databases for referencing past success stories, and no system exists to automatically suggest optimal solutions. Therefore, there is a need for more efficient store operations and a unified solution proposal system.

[1521] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1522] In this invention, the server includes means for collecting and managing past proposals and specifications in a database; means for receiving and inputting problem details from users; means for analyzing the received problems using natural language processing technology and extracting keywords; means for searching past cases and solutions in the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for receiving user feedback and updating the database; and means for searching past cases based on keywords extracted using natural language processing technology and then generating recommended solutions using an API of a generation AI model. This makes it possible to automatically provide optimal solutions for efficiently and quickly resolving operational challenges in physical stores.

[1523] A "database" is a collection of information that structures and stores data such as past proposals and specifications, allowing for efficient searching and management.

[1524] A "proposal" is a written proposal or plan submitted to address a specific issue or problem.

[1525] A "specification document" is a document that describes the detailed requirements, design, and procedures for a particular project or system.

[1526] A "user" is an individual or group that uses the system to input a problem and receive a solution proposal.

[1527] "Problem description" refers to the specific problems or requirements that the user wants to solve.

[1528] "Means of receiving" refers to the method by which the system receives and processes data entered by the user.

[1529] "Natural language processing technology" is a technology that analyzes text data entered by a user and uses computers to understand and process human language.

[1530] "Keywords" are important words or phrases extracted from a task or document.

[1531] A "search method" is a way of finding information within a database based on specified conditions.

[1532] A "recommended solution" refers to a suggestion to the user of the most suitable solution based on past cases and data that have been searched.

[1533] A "generative AI model" is a learning model that uses artificial intelligence to generate new solutions based on specified data and conditions.

[1534] "API" stands for Application Programming Interface, and it is an interface for exchanging functions and data between different software programs.

[1535] "Feedback" refers to information returned to the system by users regarding the results and impressions of implementing the suggested solutions.

[1536] "Means of updating" refers to the methods by which a system adds new information and revises or modifies existing data.

[1537] System Overview

[1538] This invention is a system for efficiently solving common challenges in store operations for owners and managers of physical stores. It collects past proposals and specifications in a database, generates optimal solutions based on user-inputted challenges, and collects feedback. This system consists of the following main components:

[1539] Hardware and software

[1540] Database Server: The server collects and manages past proposals and specifications in the database. Python's `beautifulsoup` and `requests` libraries are used for data collection.

[1541] Authentication system: Implement user registration and two-factor authentication using Firebase Authentication.

[1542] User Interface: The frontend is built with Flutter and provides a form for users to input their tasks.

[1543] Natural Language Processing: spaCy will be used for text analysis to extract keywords from the assignment content.

[1544] Search engine: Uses TF-IDF (Inverse Document Frequency) and Elasticsearch to search for similar cases within the database.

[1545] Generative AI Model: Uses the GPT-4 API to generate solutions based on searched case studies.

[1546] Database: Use Firebase Firestore to store feedback data and update the database.

[1547] Specific steps of the invention

[1548] 1. Data Collection: The server scrapes past proposals and specifications from the web and stores them in a database. For example, proposals can be retrieved using Python with requests.get("http: / / example.com / proposals").

[1549] 2. User Authentication: Users create an account using Firebase Authentication and log in after two-factor authentication. An authentication code is sent via email, and authentication is completed by entering this code.

[1550] 3. Problem Input: The user interface is built with Flutter, and users input specific store operation challenges here. For example, a form is provided for inputting "improvement of inventory management."

[1551] 4. Problem Analysis: The server uses spaCy to analyze the received problem and extract keywords. The model is loaded with nlp = spacy.load("en_core_web_sm") and keywords are extracted with doc = nlp("Improved inventory management").

[1552] 5. Searching past cases: The server uses TF-IDF or Elasticsearch to search for similar cases in the database. The search is performed using es.search(index="proposals", body={"query": {"match": {"content": "Inventory Management"}}}).

[1553] 6. Generating Recommended Solutions: Use the GPT-4 API to generate solutions based on the searched cases. An example of a prompt would be: "Please propose the best solution to achieve efficient inventory management. Please also describe the implementation method in detail, referencing past success stories."

[1554] 7. Solution Display: Review the suggestions generated in the user interface and make modifications or ask additional questions as needed.

[1555] 8. Feedback Collection: Users submit their results and feedback on trying out the suggested solutions back to the system and store them in Firebase Firestore.

[1556] Through this series of processes, it becomes possible to solve operational challenges in physical stores efficiently and quickly.

[1557] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1558] Step 1: Data Collection

[1559] The server collects past proposals and specifications from national and international sources. Specifically, it uses the Python libraries beautifulsoup and requests to scrape data from websites and stores the retrieved document data in a database. For example, it retrieves proposals using requests.get("http: / / example.com / proposals") and parses them with beautifulsoup. The input is the URL of the website, and the output is the document data stored in the database.

[1560] Step 2: User Authentication

[1561] The device provides an authentication system for users to create accounts and log in. It implements user registration and two-factor authentication using Firebase Authentication. Specifically, the user enters their email address and password, and the system sends an authentication code via email. The user enters this code to complete authentication. The input is the user's email address and password, and the output is a message indicating authentication success or failure.

[1562] Step 3: Enter the assignment

[1563] Users access a form via their device to input specific store operation challenges. Using a Flutter-based interface, they enter the project name, overview, requirements, budget, deadline, etc., and then press the "Submit" button to send the information to the server. The input is detailed information about the challenge provided by the user, and the output is the challenge data stored on the server.

[1564] Step 4: Problem Analysis

[1565] The server analyzes the received task data using natural language processing technology (spaCy). First, it performs morphological analysis, and then syntactic analysis to extract important keywords. Specifically, it loads the model using `nlp = spacy.load("en_core_web_sm")` and extracts keywords using `doc = nlp("Improved inventory management")`. The input is the text data of the task, and the output is the extracted keywords.

[1566] Step 5: Search past cases

[1567] The server searches past cases in the database based on the extracted keywords. It uses TF-IDF and Elasticsearch to identify the most relevant documents in the database. Specifically, it performs a search using es.search(index="proposals", body={"query": {"match": {"content": "Inventory Management"}}}). The input is the extracted keywords, and the output is a list of search results.

[1568] Step 6: Generating Recommended Solutions

[1569] The server generates appropriate solutions using a generative AI model (GPT-4 API) based on the search results. A prompt is provided as input, and the AI ​​generates a detailed solution based on that prompt. An example prompt is: "Please propose the optimal solution for achieving efficient inventory management. Please also describe the implementation method in detail, referencing past success stories." The input consists of the prompt and search results, and the output is the generated solution.

[1570] Step 7: Display Solution

[1571] The terminal displays the generated solution to the user. The user interface shows detailed suggestions, along with the necessary resources and expected effects. The user can review this and ask additional questions or make modifications. The input is the generated solution, and the output is the suggestions displayed to the user.

[1572] Step 8: Gathering Feedback

[1573] Users provide feedback and results from implementing the proposed solution to the system via their device. The server collects this feedback and stores it in Firebase Firestore. This feedback is used when generating the next solution. The input is the user's feedback information, and the output is the updated database.

[1574] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1575] System Overview

[1576] This invention provides a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on user-inputted problems. Furthermore, by incorporating an emotion engine that recognizes user emotions during problem input and feedback, the system can provide more personalized solution suggestions. This system consists of multiple means for data collection, user authentication, problem analysis, emotion recognition, proposal generation, and feedback collection, thereby improving the efficiency of information exchange and solution proposals among local governments.

[1577] Explain the program's processing in natural language.

[1578] 1. Data collection:

[1579] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[1580] 2. Importing data:

[1581] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[1582] 3. User registration and authentication:

[1583] Users enter basic information (such as the name of their local government, the name of the person in charge, and their email address) to create an account for their local government.

[1584] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[1585] 4. Inputting the assignment:

[1586] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form.

[1587] During input, the server uses an emotion engine to analyze the user's input speed, patterns, and facial expression data (for example, if a webcam is used) to identify the user's emotional state.

[1588] 5. Problem Analysis:

[1589] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[1590] The server performs morphological analysis, dividing the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships within the text and extract important keywords.

[1591] 6. Search past cases:

[1592] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[1593] 7. Generating Recommended Solutions:

[1594] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions that take into account the user's emotional state using an emotion engine. These recommended solutions include the means of resolution, the resources required, and the expected effects. For example, if the user is stressed, the suggestions will be concise and include step-by-step implementation instructions.

[1595] 8. Display of proposals:

[1596] The device displays the generated recommended solutions to the user. It helps the user understand the suggestions by customizing them based on the user's emotional state. The user can review these suggestions and ask additional questions or make modifications as needed.

[1597] 9. Gathering feedback:

[1598] The user implements the proposed solution and inputs the results and any additional feedback into the system.

[1599] When feedback is received, the emotion engine re-analyzes the user's emotional state and adjusts the system's responsiveness and friendliness.

[1600] The server receives user feedback, incorporates it into the database, and uses it to improve search accuracy and the system in the future.

[1601] Specific example

[1602] Improvement of public transportation

[1603] 1. Data collection:

[1604] The server collects past proposals and specifications related to public transportation into a database.

[1605] 2. User registration and authentication:

[1606] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[1607] 3. Task input and emotion recognition:

[1608] When users input challenges related to "improving the efficiency of bus operations," the emotion engine analyzes input speed, patterns, and facial expressions via webcam to recognize when the user is experiencing stress.

[1609] 4. Problem Analysis:

[1610] The server extracts keywords such as "bus operation" and "efficiency improvements" and searches for related past cases.

[1611] 5. Search past cases:

[1612] The server identifies relevant cases from the database, such as "bus route optimization systems" and "real-time operation information provision systems."

[1613] 6. Generating Recommended Solutions:

[1614] The server, taking into account the user's stress level as determined by the emotion engine, recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system" that include step-by-step execution procedures.

[1615] 7. Display of proposal:

[1616] The terminal displays the generated proposal to the user in a concise and step-by-step manner, including the implementation procedures and expected effects.

[1617] 8. Gathering feedback:

[1618] The user implements the proposed solution and inputs the results and additional feedback into the system. As feedback is entered, the emotion engine analyzes the user's emotions and adjusts the system's responsiveness accordingly.

[1619] As described above, by using the system of the present invention, local governments can efficiently solve problems and quickly obtain optimal solutions. Furthermore, by taking into account the user's emotional state, more personalized solution proposals can be realized.

[1620] The following describes the processing flow.

[1621] Step 1:

[1622] The server collects past proposals and specifications from local governments across Japan and internationally to build a database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[1623] Step 2:

[1624] The server imports the collected documents into a database and appropriately categorizes the document metadata (creation date, name of local government, project name, etc.).

[1625] Step 3:

[1626] Users enter basic information (such as the name of their local government, the name of the contact person, and their email address) to create an account for their local government. After registration, the system requests two-factor authentication.

[1627] Step 4:

[1628] The server sends an authentication code to the email address entered by the user, and the user enters that code to complete two-factor authentication.

[1629] Step 5:

[1630] After logging in, users enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form. During this process, the emotion engine monitors the speed and patterns of webcam and keyboard input.

[1631] Step 6:

[1632] The emotion engine analyzes user input data and facial expression data to identify the user's emotional state (stress, anxiety, joy, etc.). This allows it to determine the user's emotional state at the time of input.

[1633] Step 7:

[1634] When a user submits an assignment, the server receives the content and analyzes the text using natural language processing technology.

[1635] Step 8:

[1636] The server performs morphological analysis to break down the given text into words and phrases. Then, it performs syntactic analysis to analyze the relationships within the text and extract important keywords. For example, if the input is "improving the efficiency of bus operations," the server will extract the keywords "bus operations" and "efficiency."

[1637] Step 9:

[1638] The server searches the database for relevant past cases and solutions based on the extracted keywords. During this process, it uses TF-IDF and vectorization techniques to identify highly relevant documents.

[1639] Step 10:

[1640] The server extracts highly relevant cases and solutions from the search results and generates recommended solutions considering the user's emotional state using an emotion engine. For example, if the user is stressed, the suggestions will be concise and include step-by-step implementation instructions.

[1641] Step 11:

[1642] The device displays the generated recommended solutions to the user. It helps the user understand the suggestions by customizing them based on the user's emotional state. The user can review these suggestions and ask additional questions or make modifications as needed.

[1643] Step 12:

[1644] The user implements the proposed solution and inputs the results and additional feedback into the system. At this time, the emotion engine re-analyzes the user's emotional state.

[1645] Step 13:

[1646] The server receives user feedback, reflects it in the database, and uses it to improve future search accuracy and the system. It adjusts the system's responsiveness and friendliness based on the analysis results of the emotion engine.

[1647] The above outlines the specific processing steps of a system that incorporates user emotion recognition capabilities. This system enables local governments to efficiently solve problems and quickly obtain optimal solutions that take emotions into consideration.

[1648] (Example 2)

[1649] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1650] Local governments often struggle to quickly find appropriate solutions to efficiently address common challenges. Furthermore, current systems struggle to automatically generate personalized suggestions that take into account user emotional states. Additionally, there's a lack of mechanisms for efficiently incorporating feedback and improving the system. This frequently leads to delays in information sharing and effective solution proposals among local governments.

[1651] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1652] In this invention, the server includes means for collecting and managing past proposals and specifications in a database; means for users to input and receive problem details; means for analyzing the received problems using natural language processing technology and extracting keywords; means for searching past cases and solutions in the database based on the extracted keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for receiving user feedback and updating the database; means for analyzing the user's emotional state using an emotion recognition engine; and means for optimizing recommended solutions based on the user's emotional state. This enables local governments to efficiently solve problems and quickly obtain personalized suggestions based on the user's emotional state.

[1653] A "database" is an information storage system that accumulates information such as past proposals and specifications, and allows for searching and management of that information.

[1654] A "proposal" is a document that outlines solutions to a particular project or problem.

[1655] A "specification document" is a document that summarizes the detailed requirements and specifications of a particular project or product.

[1656] A "user" is a local government official who uses this system to input tasks and provide feedback.

[1657] "Natural language processing technology" refers to the technology used to analyze, understand, and generate human language.

[1658] "Keywords" are important words or phrases extracted from texts or documents.

[1659] An "emotion recognition engine" is a technology that analyzes the user's input speed, keystroke patterns, facial expression data, and other factors to identify the user's emotional state.

[1660] A "solution" is a specific means or method for solving a particular problem or issue.

[1661] "Feedback" refers to the results, evaluations, and additional comments that a user provides after implementing a suggested solution.

[1662] Morphological analysis is a technique that breaks down text into words and phrases for analysis.

[1663] "Syntactic analysis" is a technique for analyzing the relationships between words and phrases within a text.

[1664] Two-factor authentication is an authentication process that uses two different authentication methods to enhance user authentication.

[1665] System Overview

[1666] This invention is a system for local governments to efficiently solve common problems. It builds a database of past proposals and specifications and automatically generates optimal solutions based on problems entered by users. Furthermore, by combining it with an emotion recognition engine, it becomes possible to make suggestions that take into account the user's emotional state. This system consists of multiple means for data collection, user authentication, problem analysis, emotion recognition, suggestion generation, and feedback collection.

[1667] Data collection

[1668] The server collects past proposals and specifications from local governments across Japan and internationally. This collection uses web crawling technology and scanners, and converts paper-based documents into text data using OCR (Optical Character Recognition) technology.

[1669] Import data

[1670] The server imports the collected documents into a database, extracts the document metadata (creation date, municipality name, project name, etc.), and categorizes them appropriately. This allows for a smoother subsequent search process.

[1671] User registration and authentication

[1672] Users create their own municipal account to gain access to the system. Registration is completed by entering the necessary basic information (municipality name, contact person's name, email address, etc.).

[1673] The server sends an authentication code to the email address entered by the user, and the user is granted access to the system after entering that code to complete two-factor authentication.

[1674] Task input and emotion recognition

[1675] After logging in, users enter detailed information such as project name, overview, requirements, budget, and deadline into the task input form.

[1676] The server operates an emotion recognition engine that analyzes the user's input speed, keystroke patterns, and facial expression data using a webcam to identify the user's emotional state.

[1677] Problem analysis

[1678] The server analyzes the task text received from the user using natural language processing technology. Specifically, it performs morphological analysis to break down the task text into words and phrases, then performs syntactic analysis to analyze the relationships between them and extract important keywords.

[1679] Search past cases

[1680] The server searches the database for past cases and solutions based on the extracted keywords. It uses TF-IDF and vectorization techniques to identify highly relevant documents.

[1681] Generating Recommended Solutions

[1682] The server generates the most suitable recommended solution for the user based on highly relevant examples and solutions obtained from the search results. Considering the user's emotional state, as provided by the emotion recognition engine, it offers concise and step-by-step suggestions to users experiencing stress.

[1683] Display of proposals

[1684] The device displays the generated recommended solutions to the user. The suggestions are customized according to the user's emotional state, and the user can review them and ask additional questions or make modifications as needed.

[1685] Gathering feedback

[1686] The user implements the proposed solution and inputs the results and additional feedback into the system. During this process, the emotion recognition engine analyzes the user's emotional state and adjusts the system's responsiveness accordingly.

[1687] The server receives user feedback and reflects it in the database. This will lead to improvements in search accuracy and system performance in the future.

[1688] Specific example

[1689] Improvement of public transportation

[1690] 1. Data Collection

[1691] The server collects past proposals and specifications related to public transportation.

[1692] 2. User Registration and Authentication

[1693] The user (a local government official) creates an account and logs in after completing two-factor authentication.

[1694] 3. Task input and emotion recognition

[1695] When a user inputs a problem related to "improving the efficiency of bus operations," the emotion recognition engine analyzes the input speed, keystroke patterns, and facial expressions via the webcam to recognize if the user is experiencing stress.

[1696] 4. Problem Analysis

[1697] The server extracts keywords such as "bus operation" and "efficiency improvements" and searches for related past cases.

[1698] 5. Searching for past cases

[1699] The server identifies relevant cases from the database, such as "bus route optimization systems" and "real-time operation information provision systems."

[1700] 6. Generating Recommended Solutions

[1701] The server, taking into account the user's stress level as assessed by the emotion recognition engine, recommends the implementation of a "bus route optimization algorithm" and a "operation monitoring system" that include step-by-step execution procedures.

[1702] 7. Display of Proposal

[1703] The terminal displays the generated proposal to the user in a concise and step-by-step manner, including the implementation procedures and expected effects.

[1704] 8. Gathering Feedback

[1705] The user implements the proposed solution and inputs the results and additional feedback into the system. As feedback is entered, the emotion recognition engine analyzes the user's emotions, and the system's responsiveness is adjusted accordingly.

[1706] This invention enables local governments to efficiently solve problems and quickly obtain personalized suggestions based on users' emotional states.

[1707] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1708] Step 1: Data Collection and Import

[1709] Input: Past proposals and specifications provided by local governments nationwide and internationally.

[1710] The server uses web crawling technology to collect proposals and specifications from online sources. Furthermore, paper-based documents are digitized using a scanner and converted into text data using OCR (optical character recognition) technology.

[1711] Output: A dataset of digitized proposals and specifications.

[1712] Step 2: Import into database

[1713] Input: Digitized proposals and specifications.

[1714] The server imports the collected documents into a database. It extracts the document metadata (creation date and time, name of providing municipality, project name, etc.) and classifies each into the appropriate category.

[1715] Output: Structured database entries.

[1716] Step 3: User Registration and Authentication

[1717] Input: Basic information entered by the user (name of local government, name of contact person, email address, etc.).

[1718] The user creates their own municipal account to gain access to the system. The server sends an authentication code to the entered email address.

[1719] Output: User authentication was successful, and access rights to the system were granted.

[1720] Step 4: Task Input and Emotion Recognition

[1721] Input: Issue information entered by the user (project name, overview, requirements, budget, deadline, etc.).

[1722] The user fills in detailed information on the task input form. The server acquires data on input speed, keystroke patterns, and, if necessary, facial expression data using a webcam, and uses an emotion recognition engine to identify the user's emotional state.

[1723] Output: Task information with analyzed emotional states.

[1724] Step 5: Problem Analysis

[1725] Input: Task information with analyzed emotional states.

[1726] The server analyzes the given text using natural language processing technology. Morphological analysis breaks down the text into words and phrases, and syntactic analysis analyzes the relationships between them to extract important keywords.

[1727] Output: Issue information with keywords extracted.

[1728] Step 6: Search past cases

[1729] Input: Issue information from which keywords have been extracted.

[1730] The server searches the database for past cases and solutions based on the extracted keywords. It uses TF-IDF and vectorization techniques to identify highly relevant documents.

[1731] Output: A list of relevant past cases and solutions.

[1732] Step 7: Generating Recommended Solutions

[1733] Input: A list of relevant past cases and solutions, and the user's emotional state.

[1734] The server generates recommended solutions based on highly relevant cases and solutions. Considering the results of the emotion recognition engine, it provides concise and step-by-step suggestions if the user is experiencing stress.

[1735] Output: Recommended solutions optimized for the user.

[1736] Step 8: Display the proposal

[1737] Input: Recommended solutions optimized for the user.

[1738] The device displays the generated recommended solutions to the user. The suggestions are customized according to the user's emotional state.

[1739] Output: Proposed solutions confirmed by the user.

[1740] Step 9: Gathering Feedback

[1741] Input: User feedback after solution implementation.

[1742] The user implements the proposed solution and inputs the results and additional feedback into the system. The server uses an emotion recognition engine to analyze the user's emotional state when providing feedback.

[1743] Output: Database entries where feedback was collected.

[1744] The above explains the system's program processing in concrete steps. Based on this, you should gain a deeper understanding of input, data processing, and output in each processing step.

[1745] (Application Example 2)

[1746] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1747] To efficiently solve the common challenges faced by local governments, a system is needed that effectively utilizes past solutions and proposals to quickly suggest optimal solutions. However, current systems lack a personalization function that takes emotional states into account, resulting in a significant burden on users. Furthermore, it is expected that more appropriate solutions can be provided by adjusting the method of presenting solutions based on emotional states. This invention aims to solve the above problems.

[1748] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting and managing past proposals and design documents in a database; means for receiving and inputting the content of a problem from the user; means for analyzing the received problem using natural language processing technology and extracting important keywords; means for searching past cases and solutions in the database based on the extracted important keywords; means for generating recommended solutions based on the searched cases and displaying them to the user; means for analyzing the user's emotional state; means for personalizing the recommended solutions based on the emotional analysis results; and means for receiving user feedback and updating the database. This enables the rapid generation of optimal solutions based on past cases and the provision of personalized solutions that take into account the user's emotional state.

[1749] A "database" is a system for collecting and managing information, including past proposals and design documents.

[1750] A "user" refers to a local government official or related party who inputs their own problems and receives solutions from the system.

[1751] "Problem description" refers to information that includes the specific problems and requirements that the user seeks to solve.

[1752] "Natural language processing technology" is a technology that analyzes text data entered by a user and understands important words and context.

[1753] "Key terms" are specific words or phrases extracted using natural language processing technology, and are elements considered important for solving the problem.

[1754] A "case study" refers to a record of proposals or solutions that have been made to similar problems in the past.

[1755] A "solution" is a specific means or method proposed to solve a problem.

[1756] "Emotional state" refers to the psychological state a user is in when entering information into a task or providing feedback.

[1757] "Emotional analysis" is a technology that analyzes user input data and behavioral patterns to identify the user's emotional state.

[1758] "Personalization" refers to adjusting the solutions provided according to the user's emotional state and individual needs.

[1759] "Feedback" refers to users inputting the results of implementing the proposed solutions, new insights, and other relevant information into the system.

[1760] Two-factor authentication is a method of strengthening user authentication by using multiple authentication methods (e.g., password and email verification).

[1761] Morphological analysis is a technique that divides a sentence into words and analyzes their parts of speech and base forms.

[1762] "Syntactic analysis" is a technique that analyzes the structure of a text and reveals the interrelationships between individual words and phrases.

[1763] "Presentation method" refers to the way or format in which a solution is visually displayed to the user.

[1764] A "step-by-step implementation procedure" is a description that includes a series of specific steps for implementing a solution.

[1765] System Configuration

[1766] This invention is a system for local governments to efficiently solve problems, and consists of a database, server, terminals, and users. The purpose of this system is to analyze the emotional state of users based on the problems they input and to automatically generate the optimal solution.

[1767] Hardware and software to be used

[1768] Database: SQLite is used to collect and manage past proposals and design documents.

[1769] Server: Receives task input from users and functions as a platform for natural language processing and sentiment analysis.

[1770] Natural language processing techniques: For document analysis, we use Python libraries such as TextBlob, as well as morphological and syntactic analysis tools.

[1771] Emotion Analysis Model: Using the Hugging Face transformers library, the emotional state of the user is analyzed from their text data.

[1772] TF-IDF Vectorizer: Used to calculate the relevance of past cases and recommended solutions.

[1773] Device: A device used by the user to input a problem and view suggested solutions. This includes PCs, tablets, and smartphones.

[1774] Program processing details

[1775] 1. Database Setup and Data Collection: The server collects past proposals and design documents from local governments nationwide and internationally, and imports them into the database. This process includes scanning documents and converting them to text using OCR (Optical Character Recognition).

[1776] 2. User task input: The user uses a terminal to input information such as the specific project name, overview, requirements, budget, and deadline into the task input form. The server receives this information and analyzes it using natural language processing technology.

[1777] 3. Emotional State Analysis: Based on the text data entered by the user, the server uses an emotional analysis model to identify the user's emotional state. This allows the server to understand the user's psychological situation, such as whether they are experiencing stress.

[1778] 4. Generating Recommended Solutions: The server extracts key keywords and searches the database for relevant past cases and solutions. Based on the sentiment analysis results, it generates recommended solutions from highly relevant cases and provides personalized solutions according to the user's emotional state.

[1779] 5. Gathering Feedback and Updating the Database: Users implement the solutions provided and input the results and feedback into the system. The server receives this and updates the database to use it for future search accuracy and system improvements.

[1780] Specific example

[1781] Let's take an example where a city's transportation official inputs a problem regarding traffic congestion around a major train station. When the official inputs the problem, "Traffic volume around the city's major train station has increased excessively, causing frequent congestion," the system uses an emotion analysis model to identify the official's stress level. As a result, it proposes phased solutions such as "introducing dedicated bus lanes" and "optimizing traffic signals," and provides detailed implementation procedures and expected effects.

[1782] Example of a prompt

[1783] Prompt: "Please provide effective solutions to alleviate traffic congestion in the city."

[1784] Expected answer: "Past examples have shown that introducing dedicated bus lanes and optimizing traffic signals are effective. The implementation procedure is as follows: First..."

[1785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1786] Step 1:

[1787] The server collects and manages past proposals and design documents in a database. Data collection is performed from local governments nationwide and internationally, involving document scanning and text conversion using OCR (Optical Character Recognition). Scanned documents are received as input and imported into the database as text data. The output is managed text data.

[1788] Step 2:

[1789] The user enters the task details using a terminal. They enter information such as the specific project name, overview, requirements, budget, and deadline into the task input form and send it to the server. The entered task details are received by the server. The input is the task details entered by the user on the terminal, and the output is the received task details data.

[1790] Step 3:

[1791] The server analyzes the received assignment content using natural language processing techniques. This process involves morphological and syntactic analysis to extract key terms. The server receives the assignment content text data as input and outputs a list of extracted key terms.

[1792] Step 4:

[1793] The server searches the database for past cases and solutions based on the extracted key keywords. It uses a TF-IDF vectorizer to calculate relevance and identify the most relevant past cases and solutions. The input is a list of key keywords and a database of past proposals, and the output is a list of highly relevant cases and solutions.

[1794] Step 5:

[1795] The server analyzes the user's emotional state. It inputs the text data entered by the user into an emotional analysis model to identify the emotional state. The input consists of the task description text and the user's input data, while the output is the evaluation result of the emotional state.

[1796] Step 6:

[1797] The server generates recommended solutions based on searched cases and personalizes them based on sentiment analysis results. Specifically, if the user is experiencing stress, it presents a solution that includes concise, step-by-step instructions. The input is a list of relevant cases and the results of the sentiment state assessment, and the output is a personalized solution.

[1798] Step 7:

[1799] The terminal displays the generated recommended solution to the user. The user reviews it and asks additional questions or makes modifications as needed. The input is the personalized solution, and the output is a visual presentation of the solution displayed to the user.

[1800] Step 8:

[1801] The user implements the proposed solution and inputs the results and feedback into the system. The server receives this information and uses an emotion analysis model to re-analyze the user's emotional state at the time of feedback. The input is the feedback content, and the output is the updated evaluation result of the emotional state.

[1802] Step 9:

[1803] The server incorporates the feedback into the database, using it to improve future search accuracy and the system. The input consists of feedback content and emotional state evaluation results, while the output is the updated database.

[1804] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1805] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1806] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1807] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1808] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1809] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1810] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1811] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1812] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1813] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1814] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1815] I...

Claims

1. A means of collecting and managing past proposals and specifications in a database, A means for the user to input the task details and receive the task details, A method for analyzing received tasks using natural language processing technology and extracting keywords, A means of searching for past cases and solutions in the database based on extracted keywords, A means of generating and displaying recommended solutions to the user based on the searched cases, A means of receiving user feedback and updating the database, A system that includes this.

2. The system according to claim 1, further comprising means for authenticating a user using two-factor authentication.

3. The system according to claim 1, further comprising means for using morphological analysis and syntactic analysis for keyword extraction.

Images