system

Abstract

Provide a system. A method for a user to input a search query; means for analyzing the search query and extracting keywords; a means for searching for related information using the extracted keywords; means for collecting and filtering highly relevant information from the search results; means for generating summary information based on the collected information; means for notifying a user of the summary information; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern society, there is a wide variety of information about government services, making it extremely difficult to search for and understand. This requires a great deal of effort on the part of users to find the information they need. Furthermore, much of the information on the Internet is unreliable, making it difficult for users to quickly and accurately obtain the information they need. There is a need to solve these problems and provide a means for users to easily and quickly obtain reliable information about government services. [Means for solving the problem]

[0005] The present invention solves the above problems by using the following means.

[0006] a means for a user to input a search query;

[0007] means for analyzing the search query and extracting keywords;

[0008] a means for searching for related information using the extracted keywords;

[0009] means for collecting and filtering highly relevant information from the search results;

[0010] means for generating summary information based on the collected information;

[0011] A system is provided that includes means for notifying a user of the summary information.

[0012] Furthermore, by using the reliability and freshness of information as criteria when filtering the search results and by using natural language generation technology when generating summaries of the information, users can easily obtain highly reliable information, enabling them to quickly obtain accurate information about government services.

[0013] A "search query" is a string of data that a user inputs to the system to search for information.

[0014] "Analysis" is the process of breaking down the entered search query and understanding its meaning.

[0015] "Keyword extraction" is the process of extracting important words and phrases from a search query.

[0016] "Related information" is data obtained based on a search query that is directly related to the query content.

[0017] "Collection" is the act of gathering the necessary data from multiple sources obtained through a search.

[0018] "Filtering" is the act of removing unnecessary information from collected information and selecting only the necessary information.

[0019] "Summary information" is data that extracts important points from collected information and reconstructs them in a concise and clear format.

[0020] "Notification" refers to the act of delivering the generated summary information to the user.

[0021] "Natural language generation technology" is a technology that enables computers to understand and generate human language.

[0022] "Reliability" is a criterion for assessing the accuracy of information.

[0023] "Freshness" is a criterion for assessing whether information is up-to-date. [Brief explanation of the drawings]

[0024] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0025] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0026] First, the terms used in the following description will be explained.

[0027] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0028] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0029] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0030] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0031] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0032] [First embodiment]

[0033] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0034] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0035] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0036] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0037] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0038] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0039] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0040] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0041] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0042] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0043] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0044] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0045] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. The program processing of this system is explained below with specific examples.

[0046] Enter and submit a search query

[0047] A user inputs a question about a government service into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures this query and sends it to the server.

[0048] Query Analysis

[0049] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text.

[0050] Search for related information

[0051] The server uses the extracted keywords to search for information in multiple government service databases and related websites, and uses APIs and web scraping technology to collect data from reliable sources.

[0052] Information collection and filtering

[0053] The server analyzes the acquired information and collects highly relevant information. The filtering process removes unnecessary information based on the reliability and freshness of the information.

[0054] Generate summary information

[0055] Based on the filtered information, the server generates a summary. It uses natural language generation technology to extract important information and present it in an easy-to-understand format. For example, the following summary is generated for the input "How do I get a resident registration card?"

[0056] Required documents: Identification documents (driver's license, passport, etc.)

[0057] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0058] Fee: Average 300-500 yen (may vary if applying online)

[0059] Other: Reception hours, location of the counter, etc.

[0060] Summary information notification

[0061] The server sends the generated summary information to the terminal, which then displays it to the user, allowing the user to quickly obtain the necessary information about government services related to the input query.

[0062] Specific examples

[0063] For example:

[0064] User operations

[0065] The user types "Please tell me how to obtain a resident registration card" into the terminal.

[0066] Server-side processing

[0067] 1. The server analyzes the query and extracts the keywords "resident registration card" and "how to obtain."

[0068] 2. The server uses these keywords to search for information from multiple trusted databases and websites.

[0069] 3. The server collects relevant information from the search results and filters out unnecessary information.

[0070] 4. The server summarizes the collected information and presents it in a concise and easy-to-understand format.

[0071] Device behavior

[0072] The terminal displays the summary information sent from the server to the user. The user receives a summary like this:

[0073] How to obtain a resident certificate:

[0074] Required documents: Identification documents (driver's license, passport, etc.)

[0075] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0076] Fee: Average 300-500 yen (may vary if applying online)

[0077] Other: Reception hours, location of the counter, etc.

[0078] In this way, users can obtain accurate information about government services in a short time.

[0079] The processing flow will be explained below.

[0080] Step 1:

[0081] The user inputs a search query into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card."

[0082] Step 2:

[0083] The device sends the entered search query to the server, which passes the query to the server via the Internet.

[0084] Step 3:

[0085] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain it."

[0086] Step 4:

[0087] The server uses the extracted keywords to access databases related to government services and related official websites to search for information, using APIs and web scraping technology.

[0088] Step 5:

[0089] The server collects the search results, gathering data from multiple sources and verifying their contents.

[0090] Step 6:

[0091] The server filters the collected information, eliminating unnecessary or unreliable information based on its reliability and freshness.

[0092] Step 7:

[0093] The server summarizes the filtered information, using natural language generation techniques to extract key points and present them in a concise, easy-to-understand format.

[0094] Step 8:

[0095] The server sends the generated summary information to the terminal, and data security is ensured using encrypted communication.

[0096] Step 9:

[0097] The terminal displays the received summary information to the user in an easily viewable and organized format using a GUI.

[0098] Step 10:

[0099] Users can quickly understand the information they need by checking the displayed summary, such as the documents, procedures, and fees required to obtain a resident registration card.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] Existing information search systems for government services often have information scattered across multiple systems, making it difficult for users to efficiently obtain the information they need, making it difficult to make quick decisions. Furthermore, when there is too much information, it takes a long time for users to extract the information they need.

[0103] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0104] In this invention, the server includes means for a user to input a search query, means for analyzing the search query and extracting keywords, means for searching databases and websites for related information using the extracted keywords, means for collecting highly relevant information from the search results and filtering the information based on reliability and freshness, and means for generating summary information based on the filtered related information, thereby enabling users to centrally search distributed administrative service information and efficiently obtain reliable and up-to-date information.

[0105] A "search query" refers to a question or keyword that a user enters into a system to obtain information.

[0106] "Keywords" refers to important words or phrases extracted from a search query and used to retrieve related information.

[0107] A "database" refers to a collection of information that is systematically organized and made available for efficient search and reference.

[0108] "Website" means a collection of information pages on the Internet that provide information on a particular subject.

[0109] "Filtering" refers to the process of removing unnecessary information from collected information based on criteria such as reliability and freshness.

[0110] A "generative AI model" refers to an algorithm or program that uses artificial intelligence techniques to generate new information based on input data.

[0111] "Summary information" refers to information that has been filtered and concisely summarized by extracting only the important points.

[0112] "Notification" refers to the process of presenting system-generated summary information to the user.

[0113] The system according to the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. A specific embodiment of this system will be described below.

[0114] Enter and submit a search query

[0115] A user uses their own device (PC, smartphone, tablet, etc.) to input a question about a government service. For example, they input a query such as "Please tell me how to obtain a resident registration card" into the input field of the device. The device captures this input query and sends it to a server via the Internet.

[0116] Receiving and parsing queries

[0117] The server passes the received query to a natural language processing engine (e.g., SpaCy, NLTK) for morphological analysis. As a result, keywords such as "resident registration card" and "how to obtain" are extracted from the query. At the same time, contextual analysis is performed to determine the type of information the user is looking for.

[0118] Examples:

[0119] User: "Please tell me how to obtain a resident registration card."

[0120] Terminal: Sends query to server

[0121] Server: Extract the keywords "resident certificate" and "acquisition method"

[0122] Search for related information

[0123] The server searches for information from multiple government service databases and related websites based on the extracted keywords, by querying the database using RESTful APIs and by using web scraping techniques (e.g., BeautifulSoup) to collect data from websites.

[0124] Examples:

[0125] Server: Sends a query "How to obtain a resident registration card" to the administrative service database API

[0126] Server: Uses web scrapers to gather information from trusted sites

[0127] Information collection and filtering

[0128] The server filters the information collected from the search results, evaluating the information based on its reliability, freshness, and relevance, and removing unnecessary information. This filtering process includes evaluating the reliability of the source and checking the most recent update date.

[0129] Examples:

[0130] Server: Classifies the data obtained from the search results and extracts only the most up-to-date and reliable information

[0131] Server: Remove unnecessary information (duplicates and old information)

[0132] Generate summary information

[0133] The server generates summary information based on the filtered information using a generative AI model (e.g., OpenAI's GPT-3®), writes summary instructions in a prompt, and analyzes and verifies the generated summary.

[0134] Examples:

[0135] Server: Send the summary of "Please tell me how to obtain a resident registration card" as a prompt to the generative AI model

[0136] Generative AI model: Generates summary text. Required documents: Personal identification (driver's license, passport, etc.); Acquisition method: Application at city hall, by mail, or online application; Fee: Average 300 to 500 yen.

[0137] Server: Validate the generated summary and adjust it if necessary

[0138] Summary information notification

[0139] The server then sends the generated summary information to the terminal, which then displays it to the user. This allows the user to quickly and centrally search for dispersed administrative service information and efficiently obtain the most reliable and up-to-date information.

[0140] Examples:

[0141] Server: Sends summary information to the terminal

[0142] Terminal: Display the received summary information to the user. "How to obtain a resident registration certificate: Required documents: Personal identification document (driver's license, passport, etc.); How to obtain: Apply at the city hall, by mail, or online; Fee: Average 300 to 500 yen."

[0143] In this way, the system can quickly provide reliable, up-to-date information on government services based on the search query entered by the user.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1:

[0146] A user uses their own terminal to input a question about a government service. For example, they might input, "Please tell me how to obtain a resident registration card." The input data is a text query. The terminal captures this input query and sends it to a server via the Internet. The output is a text query received by the server.

[0147] Step 2:

[0148] The server passes the received query to a natural language processing engine (e.g., SpaCy, NLTK) for morphological and contextual analysis. At this stage, the input query is broken down into keywords such as "resident registration card" and "how to obtain it." The input is the text data of the query, and the output is a set of extracted keywords.

[0149] Step 3:

[0150] The server searches for information from multiple government service databases and related websites based on the extracted keywords. This is done using RESTful API calls and web scraping techniques (e.g., BeautifulSoup). The input is a set of keywords, and the output is a dataset of related information obtained as search results.

[0151] Step 4:

[0152] The server filters the information collected from the search results. At this stage, the reliability, freshness, and relevance of the information are evaluated, and unnecessary information is removed. For example, if the same information appears multiple times or if the information is outdated, it is filtered. The input is a dataset of search results, and the output is filtered, highly reliable information data.

[0153] Step 5:

[0154] The server generates summary information using a generative AI model (e.g., OpenAI's GPT-3) based on the filtered information. The server writes summary instructions in a prompt and passes it to the generative AI model. The input is the filtered information and the prompt, and the output is the generated summary.

[0155] Step 6:

[0156] The server sends the generated summary information to the terminal, which displays this information to the user. This allows the user to quickly and centrally search for dispersed administrative service information and efficiently obtain reliable, up-to-date information. The input is summary information, and the output is the information displayed to the user.

[0157] In this way, each processing step works together with specific operations, realizing efficient and highly reliable information provision.

[0158] (Application example 1)

[0159] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0160] In conventional shopping, users must browse multiple online shopping sites to obtain information about the product they want to purchase, checking the information on each site. This takes time and effort, placing a particular burden on beginners and the elderly. Furthermore, the reliability and freshness of the information available varies, making it difficult to determine which information is the most up-to-date and trustworthy. To solve these problems, a system is needed that provides highly reliable and up-to-date summary information in a unified manner.

[0161] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0162] In this invention, the server includes means for a user to input a shopping search query, means for analyzing the shopping search query and extracting product-related keywords, means for searching for product information from online shopping sites using the extracted product-related keywords, means for collecting and filtering product information details and price information from the search results, and means for generating summary information based on the collected product information and price information, thereby enabling a user to obtain reliable and up-to-date product summary information in a short amount of time.

[0163] A "means for a user to enter a search query" is a device or interface through which a user can enter a question about a product they wish to purchase.

[0164] The "means for analyzing the search query and extracting keywords" refers to a technology or algorithm that extracts important words or phrases from the search query entered by the user.

[0165] The "means for searching for related information using the extracted keywords" refers to algorithms or techniques that use the extracted important words or phrases to find related information from various sources.

[0166] The "means for collecting and filtering highly relevant information from the search results" refers to a method or technology for selecting particularly relevant information from the search results and eliminating unnecessary information.

[0167] The "means for generating summary information based on the collected information" refers to a method or technology for concisely summarizing the collected information and providing it to the user in an easily understandable format.

[0168] The "means for notifying the user of the summary information" refers to an interface or technology for transmitting the generated summary information to the user's device and displaying it.

[0169] A "means for a user to enter a shopping search query" is a device or interface through which a user can enter a question about a product they wish to purchase.

[0170] The "means for analyzing the shopping-related search query and extracting product-related keywords" refers to a method or technology for extracting important product-related words and phrases from shopping-related questions entered by users.

[0171] "Means for searching for product information from online shopping sites using keywords related to the extracted products" refers to a technology that uses important words and phrases related to the extracted products to find relevant product information from multiple online shopping sites.

[0172] "Means for collecting and filtering detailed product information and price information from the search results" refers to a method or technology for collecting detailed product information and price information from the search results and removing unnecessary information.

[0173] The "means for generating summary information based on the collected product information and price information" refers to a method or technology for concisely summarizing the collected product-related details and price information and providing it to the user in an easy-to-understand format.

[0174] The system according to the present invention allows users to input shopping search queries and provides related product information in a unified manner. The processing of the program of this system will be explained using specific examples.

[0175] System configuration

[0176] The system consists of a terminal used by the user, a server that processes the data, and various software components that collect, filter, and summarize the information.

[0177] Program processing overview

[0178] The system consists of the following main steps:

[0179] User operations and device behavior

[0180] The user types a shopping question into the device, for example, "How do I buy a Nintendo Switch?" This query is captured by the device and sent to the server.

[0181] Query Analysis

[0182] The server analyzes the received query and uses natural language processing technology to extract keywords such as "Nintendo Switch" and "how to purchase" from the input text. The specific software used includes transformers, a Python natural language processing library.

[0183] Search for product information

[0184] The server uses the extracted keywords to search for product information on multiple online shopping sites. It uses APIs and web scraping techniques, such as BeautifulSoup and requests, to collect data from reliable sources.

[0185] Information collection and filtering

[0186] The server analyzes the acquired information and collects relevant product and price information. The filtering process eliminates unnecessary information based on the reliability and freshness of the information.

[0187] Generate summary information

[0188] Based on the filtered information, the server generates summary information. It uses a generative AI model to concisely summarize the extracted important information. Specifically, it uses the transformers library.

[0189] Summary information notification

[0190] The server sends the generated summary information to the terminal, which displays it to the user, allowing the user to quickly obtain important information about the product they want to purchase.

[0191] Specific examples

[0192] User actions and query input

[0193] The user types "How do I purchase a Nintendo Switch?" into the device. Based on this query, the system starts a series of processes.

[0194] Query analysis and product search

[0195] The server analyzes the query and extracts the keywords "Nintendo Switch" and "purchase method," then collects product information from multiple online shopping sites.

[0196] Collecting and summarizing information

[0197] Based on the collected product and price information, important data is extracted and a summary is generated. For example, the following summary is generated:

[0198] Information on purchasing the Nintendo Switch: The Nintendo Switch console is available for purchase for 32,978 yen, and the Nintendo Switch Lite is available for purchase for 21,970 yen. You can purchase them from the links below.

[0199] Summary information notification

[0200] The generated summary information is sent to the terminal and displayed to the user. The user receives a summary that looks like this:

[0201] Information on purchasing the Nintendo Switch: The Nintendo Switch console is available for purchase for 32,978 yen, and the Nintendo Switch Lite is available for purchase for 21,970 yen. You can purchase them from the links below.

[0202] In this way, users can easily obtain reliable product information in a short time.

[0203] With the above-described configuration and method, the system of the present invention can quickly provide accurate information in response to user queries regarding shopping.

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1:

[0206] A user enters a shopping-related search query into their device, for example, "How do I buy a Nintendo Switch?" This query becomes input to the system.

[0207] Step 2:

[0208] The terminal captures the entered query and sends it to the server, where the input is the user's query and the output is the query sent to the server.

[0209] Step 3:

[0210] The server analyzes the received query. It uses natural language processing technology to extract keywords such as "Nintendo Switch" and "how to purchase" from the input query. For example, it uses transformers, a Python natural language processing library, to perform the analysis.

[0211] Step 4:

[0212] The server uses the extracted keywords to search for product information from multiple online shopping sites. For example, it uses requests to retrieve pages from online shopping sites, analyzes them with BeautifulSoup, and collects product and price information. The input here is the extracted keywords, and the output is a list of the collected product information.

[0213] Step 5:

[0214] The server filters the collected product information, eliminating unnecessary information based on reliability and freshness. For example, reliability is evaluated based on collected product reviews and update dates, and only the necessary data is extracted. The input is the collected product information, and the output is the filtered product information.

[0215] Step 6:

[0216] The server generates summary information based on the filtered information. Here, a generative AI model is used to concisely summarize important information. For example, the transformers library is used to generate the summary information. The input is the filtered product information, and the output is the summarized information.

[0217] Step 7:

[0218] The server sends the generated summary information to the terminal. The input is the summarized information, and the output is the summary information sent to the terminal.

[0219] Step 8:

[0220] The terminal displays the received summary information to the user, allowing the user to quickly obtain important information about the product they are planning to purchase. The input is the summary information sent from the server, and the output is the content displayed to the user.

[0221] This allows the system to provide a summary of reliable and up-to-date information in response to a user's shopping search query through a series of processes.

[0222] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0223] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions and optimizes the information provided based on those emotions. The program processing of this system is explained below with specific examples.

[0224] Enter and submit a search query

[0225] A user inputs a question about a government service into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures this query and recognizes the user's emotion using an emotion engine. The device then transmits the query and emotion information to the server.

[0226] Query Analysis

[0227] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text. It also uses an emotion engine to analyze the user's emotions and recognize their current emotional state.

[0228] Search for related information

[0229] The server then uses the extracted keywords to access databases related to government services and related official websites to search for information, using APIs and web scraping technology. Furthermore, it adjusts the filtering criteria for search results based on the user's emotions. For example, if the user appears anxious, it will prioritize detailed and reassuring information.

[0230] Information collection and filtering

[0231] The server collects the search results. In doing so, it gathers data from multiple sources and checks their contents. When filtering the collected information, it eliminates unnecessary information based on its reliability and freshness. It also sets filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes information that is concise and can be understood quickly.

[0232] Generate summary information

[0233] The server generates a summary based on the filtered information. It uses natural language generation technology to extract key points and present them in an easy-to-understand format. The server also adjusts the presentation and format of the summary, taking into account the user's emotional state, as recognized by the emotion engine. For example, if the user is anxious, the server generates a summary in a gentle tone that provides a sense of security.

[0234] Summary information notification

[0235] The server sends the generated summary information to the terminal. Data security is ensured using encrypted communication. The terminal displays this information to the user. Furthermore, the display method is also adjusted according to the user's emotional state.

[0236] Specific examples

[0237] For example:

[0238] User operations

[0239] The user types into the terminal, "Please tell me how to obtain a resident registration card." At this time, the emotion engine recognizes that the user looks anxious.

[0240] Server-side processing

[0241] 1. The server analyzes the query and extracts the keywords "resident registration card" and "how to obtain."

[0242] 2. The server recognizes that the user is anxious based on the emotional information from the emotion engine.

[0243] 3. The server uses these keywords to search for information from multiple trusted databases and websites, prioritizing detailed and reassuring information to allay concerns.

[0244] 4. The server collects reliable information from the search results and filters out unnecessary information.

[0245] 5. The server summarizes the collected information and generates a summary in a warm tone to ease anxiety.

[0246] Device behavior

[0247] The terminal displays the summary information sent from the server to the user. To ease the user's anxiety, the information is organized in an easy-to-read format and presented in a reassuring manner. The user receives a summary like this:

[0248] How to obtain a resident certificate:

[0249] Required documents: Identification documents (driver's license, passport, etc.)

[0250] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0251] Fee: Average 300-500 yen (may vary if applying online)

[0252] Other: Reception hours, location of the counter, etc.

[0253] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[0254] In this way, users can obtain accurate and reassuring information about government services in a short amount of time.

[0255] The processing flow will be explained below.

[0256] Step 1:

[0257] The user inputs a search query into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures the input query.

[0258] Step 2:

[0259] The emotion engine recognizes the user's emotions from their voice, facial expressions, etc. The device then sends the recognized emotion information along with the query to the server.

[0260] Step 3:

[0261] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text. At the same time, it analyzes the user's emotions, which are recognized by an emotion engine.

[0262] Step 4:

[0263] The server then searches for information by accessing databases related to government services and related official websites based on the extracted keywords, using APIs and web scraping technology to obtain relevant information.

[0264] Step 5:

[0265] The server collects the search results, gathers reliable data from multiple sources, and verifies their contents.

[0266] Step 6:

[0267] The server filters the collected information. The filtering process eliminates unnecessary information based on the reliability and freshness of the information. It also adjusts the filtering criteria based on the user's emotional state. For example, if the user seems anxious, it will prioritize detailed and reassuring information.

[0268] Step 7:

[0269] The server generates a summary based on the filtered information. It uses natural language generation technology to extract key points and present them in an easy-to-understand format. The server adjusts the presentation of the summary based on the user's emotional state, as recognized by the emotion engine. For example, if the user appears anxious, it uses a calm, reassuring tone.

[0270] Step 8:

[0271] The server sends the generated summary information to the terminal, and uses encrypted communication to ensure data security.

[0272] Step 9:

[0273] The device then displays the summary information to the user. The display method is also adjusted according to the user's emotions. For example, if a user is feeling anxious, a design and color scheme that visually conveys a sense of security is used.

[0274] Step 10:

[0275] Users can quickly understand the information they need by checking the summary displayed. Information on necessary procedures and documents is concisely explained, allowing them to act with confidence.

[0276] Examples:

[0277] For example, if a user says, "Please tell me how to obtain a resident registration card," and looks anxious, this emotion is recognized. Based on this information, the server prioritizes collecting detailed and reassuring information on how to obtain a resident registration card, and generates summary information in a calm manner. The user can then reassure themselves by checking the information displayed on the device and following the instructions to proceed with the procedure.

[0278] Example 2

[0279] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0280] Conventional information search systems provide relevant information in response to a user's search query, but lack the ability to recognize the user's emotional state and provide optimal information based on that emotion. This makes it difficult for users to quickly and confidently obtain the information they need. Another issue is the insufficient filtering of information based on its reliability and freshness. The present invention aims to solve these problems and provide a system that provides optimal information based on the user's emotions.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0282] In this invention, the server includes a means for recognizing a user's emotion and optimizing information to be provided based on the emotion, a means for analyzing a search query and extracting keywords, and a means for searching for related information using the extracted keywords, thereby enabling the provision of optimal information according to the user's emotion.

[0283] "User" refers to a person who utilizes the System to enter a search query and retrieve information.

[0284] A "search query" refers to a question or keyword that a user enters to obtain information.

[0285] "Terminal" refers to an electronic device through which a user enters search queries and receives information.

[0286] "Server" means a central processing unit for analyzing search queries and providing relevant information.

[0287] An "emotion engine" is a technology that recognizes a user's emotions and optimizes the information provided based on that emotional information.

[0288] "Natural language processing technology" refers to the technology that allows a computer to understand and analyze input text data.

[0289] "Keywords" refer to important words in information retrieval extracted from a search query.

[0290] "Relevant information" refers to information that is relevant to the purpose a user is trying to obtain through a search query.

[0291] "Filtering" refers to the process of removing unnecessary parts from acquired information, leaving only useful information.

[0292] "Natural language generation technology" refers to the technology of generating sentences in a natural way based on large amounts of data.

[0293] "Summary information" refers to information that extracts important points from collected information and summarizes them concisely.

[0294] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions and optimizes the information provided based on the user's emotions.

[0295] Enter and submit a search query

[0296] A user inputs a question about a government service into their own device. A specific example is the query "Please tell me how to obtain a resident registration card." The device captures this query and recognizes the user's emotions using an emotion engine. Emotion analysis technology, for example, can be used as the emotion engine. The captured query and emotion information are sent to the server.

[0297] Query Analysis

[0298] The server analyzes the received query using natural language processing techniques (e.g., BERT and spaCy) to extract keywords such as "resident registration card" and "how to obtain" from the input text. It also analyzes the user's emotional state using an emotion engine and recognizes the current emotional state as a cyclic variable.

[0299] Search for related information

[0300] The server then uses the extracted keywords to access databases of government services and related official websites to retrieve information. It uses APIs and web scraping technologies (e.g., BeautifulSoup and Scrapy). It also adjusts the filtering criteria for search results based on the user's emotional state. For example, if the user appears anxious, it prioritizes detailed and reassuring information.

[0301] Information collection and filtering

[0302] The server organizes the search results and integrates data from multiple sources. It filters information based on reliability and freshness. It also flexibly adjusts the filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes concise and easy-to-understand information.

[0303] Generate summary information

[0304] The server generates a summary based on the filtered information. It uses natural language generation technology (e.g., GPT-3) to extract key points and translate them into an easy-to-understand format. The generated summary takes into account the user's emotional state and adjusts its expression and tone accordingly. For example, a summary may be written in a gentler tone to alleviate anxiety.

[0305] Summary information notification

[0306] The server sends the generated summary information to the device. Data security is ensured using encryption technologies such as SSL / TLS for communication. The device then displays the received summary information to the user, displaying it according to their emotional state.

[0307] Specific examples

[0308] For example, if a user types "Please tell me how to get a resident registration card" into the terminal, the emotion engine will recognize that the user looks anxious. The following process will be performed on the server side:

[0309] 1. The server analyzes and extracts the keywords "resident registration card" and "how to obtain."

[0310] 2. Based on the user's emotional information, prioritize collecting detailed information to alleviate anxiety.

[0311] 3. Filter reliable information and filter out unnecessary information.

[0312] 4. Generate summary information in a gentle tone and add a reassuring message.

[0313] The terminal will display the generated summary information to the user as follows:

[0314] How to obtain a resident certificate:

[0315] Required documents: Identification documents (driver's license, passport, etc.)

[0316] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0317] Fee: Average 300-500 yen (may vary if applying online)

[0318] Other: Reception hours, location of the counter, etc.

[0319] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[0320] This allows users to quickly obtain accurate and reliable information about government services.

[0321] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0322] Step 1: Enter and submit a search query

[0323] The user inputs a question about government services into the terminal. Specifically, the terminal receives the text data entered by the user, "Please tell me how to obtain a resident registration card." The terminal captures this query. The emotion engine analyzes the input query and recognizes the user's emotional state (e.g., anxiety). The captured query and emotion information are sent to the server. The input is the search query and the user's emotional state, and the output is the data sent to the server.

[0324] Step 2: Parsing the query

[0325] The server analyzes the query based on the received data. Specifically, it analyzes the query using natural language processing technology (e.g., BERT) to extract keywords such as "resident registration card" and "how to obtain it." The server also analyzes the emotional information provided by the emotion engine to recognize the current emotional state. The input is the search query and emotional information, and the output is the extracted keywords and the recognition result of the emotional state.

[0326] Step 3: Find related information

[0327] The server accesses databases related to government services and related official websites based on keywords to obtain information. Specifically, it uses APIs and web scraping technologies (e.g., BeautifulSoup and Scrapy) to collect relevant information. It adjusts search criteria based on the user's emotions, and prioritizes detailed and reassuring information for anxious users. The input is the extracted keywords and emotional state, and the output is the obtained related information.

[0328] Step 4: Collecting and filtering information

[0329] The server organizes the collected search results. Specifically, it integrates data from multiple sources and filters them based on reliability and freshness. Furthermore, it flexibly adjusts the filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes concise and easy-to-understand information. The input is the retrieved relevant information and the user's emotional state, and the output is the filtered information.

[0330] Step 5: Generate summary information

[0331] The server generates summary information based on the filtered information. Specifically, it uses natural language generation technology (e.g., GPT-3) to extract key points and convert them into an easy-to-understand format. The generated summary adjusts its expression and tone to take into account the user's emotions. For anxious users, it generates a summary that includes reassuring words. The input is the filtered information and emotional state, and the output is the generated summary information.

[0332] Step 6: Notification of summary information

[0333] The server sends the generated summary information to the terminal. Specifically, encryption technology such as SSL / TLS is used for communication to ensure data security. The terminal displays the received summary information to the user and selects a display method based on the user's emotional state. The input is the generated summary information, and the output is the screen display viewed by the user.

[0334] (Application example 2)

[0335] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0336] When searching for information about government services, it is difficult to provide optimal information based on the user's emotions. Specifically, if a user is feeling anxious or impatient, it is necessary to obtain and provide information in a manner that corresponds to that emotion. However, many conventional systems provide information uniformly without considering the user's emotions, which results in the problem of not being able to obtain optimal information for the user. Furthermore, there is no established method for easily obtaining information in an in-car environment, such as through voice input.

[0337] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0338] In this invention, the server includes: a means for a user to input a search query; a means for analyzing the search query and extracting keywords; a means for searching for related information using the extracted keywords; a means for collecting and filtering highly relevant information from the search results; a means for generating summary information based on the collected information; a means for notifying the user of the summary information; an emotion engine means for recognizing the user's emotions; and a means for optimizing the filtering criteria for the information and the expression of the summary information based on the emotion information recognized by the emotion engine means. This makes it possible to provide information in an optimal form according to the user's emotional state. For example, in an in-vehicle environment of an autonomous vehicle, voice input can be accepted through smart glasses, and appropriate information can be provided quickly and reassuringly.

[0339] - "Means by which a user enters a search query" refers to an interface through which a user can enter a question about a government service, including a voice input device, keyboard, or touchscreen.

[0340] The "means for analyzing the search query and extracting keywords" is a mechanism for analyzing the input search query using natural language processing technology and identifying important keywords.

[0341] The "means for searching for related information using the extracted keywords" is a system for obtaining information from databases and official websites related to administrative services based on the extracted keywords.

[0342] The "means for collecting and filtering highly relevant information from the search results" refers to a procedure for excluding unnecessary information from the acquired information based on its reliability and freshness, and selecting highly relevant information.

[0343] The "means for generating summary information based on the collected information" refers to a method for extracting important points from filtered information and summarizing them in an easy-to-understand manner using natural language generation technology.

[0344] The "means for notifying the user of the summary information" is a mechanism for displaying the generated summary information on the user's terminal, and is provided visually through smart glasses or a smartphone.

[0345] The "emotion engine means for recognizing the user's emotions" is an engine for analyzing the emotional state from the input query or the user's voice and acquiring emotional information.

[0346] The "means for optimizing the filtering criteria for the information and the expression of summary information based on the emotional information recognized by the emotion engine means" refers to a system for adjusting the method and content of information provision in accordance with the emotional information, and providing information in a form that is optimal for the user.

[0347] "System" refers to the overall mechanism that is made up of a combination of multiple technological elements, and in this case refers to the infrastructure for providing users with information about government services in the most optimal way.

[0348] MODE FOR CARRYING OUT THE INVENTION

[0349] This invention relates to a system for enabling a user in an autonomous vehicle to obtain information about government services through voice input and optimize that information using an emotion recognition engine. The system includes a voice input device, an emotion recognition engine, natural language processing technology, an information search engine, a filtering system, and a user notification device.

[0350] System Overview

[0351] In this system, when a user uses smart glasses or other voice input devices to ask a question about government services, the voice input is converted into text and sent to a server. The server analyzes the input text and extracts important keywords. Based on the extracted keywords, it searches for related information from government service databases and websites. In addition, an emotion recognition engine recognizes the user's emotions and optimizes the information filtering criteria and summary information presentation based on those emotions.

[0352] Hardware and software details

[0353] The server uses the following software and hardware:

[0354] Speech Recognition: Use the speech_recognition library to capture voice input from a microphone, such as smart glasses, and convert it to text.

[0355] Emotion recognition: Uses the emotion recognition model (pipeline('sentiment-analysis')) from the transformers library.

[0356] Information retrieval: Using APIs and web scraping technology, information is retrieved from government service databases and websites.

[0357] Information filtering: Filter information based on reliability and freshness, and prioritize information based on emotional information.

[0358] Summary Generation: Summarize the filtered information using a summary generation model from the transformers library.

[0359] After receiving voice input from the user, the server performs the following actions:

[0360] Speech recognition and text conversion

[0361] The server captures the voice input from the user through the smart glasses and converts it into text using the speech_recognition library. For example, when a user inputs "Please tell me how to obtain a resident registration card," the voice is converted into text.

[0362] emotion recognition

[0363] The converted text is sent to an emotion recognition engine, where the emotional state is analyzed using emotion recognition models from the transformers library. For example, if the user is feeling anxious, it is recognized as "anxious."

[0364] Information Search and Filtering

[0365] Based on the extracted keywords, the server retrieves information from government service databases and official websites. Based on emotional information, priority is given to information that gives a sense of security and can be quickly understood. For example, information such as "how to obtain a resident registration card," "required documents," "how to obtain it," and "fees" is searched.

[0366] Summary generation and notification

[0367] The acquired information is summarized using the transformers library, and the representation is optimized based on the emotion, and then displayed on the smart glasses. For example, the following summary is generated:

[0368] How to obtain a resident certificate:

[0369] Required documents: Identification documents (driver's license, passport, etc.)

[0370] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0371] Fee: Average 300-500 yen (may vary if applying online)

[0372] Other: Reception hours, location of the counter, etc.

[0373] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[0374] Prompt Sentence Examples

[0375] Here are some examples of emotion recognition prompts for input queries:

[0376] Identify the emotions in the following sentences:

[0377] I would like to go to the local government office in my area to get a resident registration certificate. What documents and procedures are required?

[0378] This system allows users to easily obtain information about government services while on the move, and provides reassuring information that is optimized according to their emotions.

[0379] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0380] Program processing steps

[0381] Step 1:

[0382] The user inputs voice through the smart glasses. For example, the user might ask, "Please tell me how to obtain a resident registration card." The smart glasses capture this voice and send it to the server. The input is the user's voice data, and the output is the voice data sent to the server.

[0383] Step 2:

[0384] The server converts the received voice data into text using the speech_recognition library. In this step, the voice data is converted into text data. Specifically, the voice recognition model analyzes the voice waveform and outputs the corresponding text, "Please tell me how to obtain a resident registration card."

[0385] Step 3:

[0386] The server sends the text data to the emotion recognition engine, which analyzes the user's emotions using the emotion recognition model in the Transformers library. The input is text data, and the output is emotional information (e.g., "anxiety"). Specifically, the emotion recognition model analyzes the user's emotional state from the text content and assigns an emotion label.

[0387] Step 4:

[0388] The server uses natural language processing technology to extract important keywords from the input text data. For example, the keywords "resident registration card" and "how to obtain" are extracted. The input is emotional information and text data, and the output is a keyword list. Specifically, the keyword extraction model analyzes the text and lists important words.

[0389] Step 5:

[0390] The server uses the extracted keywords to search for relevant information from government service databases and official websites. The input is a list of keywords, and the output is search results. Specifically, APIs and web scraping technologies are used to obtain data from sources.

[0391] Step 6:

[0392] The server filters the search results based on reliability and freshness, as well as on recognized emotional information. The input is the search results and emotional information, and the output is the filtered information. Specifically, the filtering algorithm eliminates unreliable information and prioritizes it according to its emotions.

[0393] Step 7:

[0394] The server generates a summary based on the filtered information. The summary generation model from the transformers library is used to generate the summary. The input is the filtered information, and the output is the summary information. Specifically, the summary generation model extracts important information and summarizes it using emotion-based expressions.

[0395] Step 8:

[0396] The summary information is sent to the user's smart glasses using encrypted communication. The input is the summary information, and the output is the text displayed on the smart glasses. Specifically, the server encrypts the summary and sends it to the smart glasses through a communication protocol.

[0397] Step 9:

[0398] The smart glasses display summary information to the user. The display method is also adjusted according to the user's emotional state. The input is summary information received from the server, and the output is visual information provided to the user. Specifically, the smart glasses display the information with appropriate font size, color, and layout.

[0399] In this way, users can easily obtain information about government services while on the move, and can obtain reassuring information that is optimized according to their emotions.

[0400] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0401] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0402] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0403] [Second embodiment]

[0404] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0405] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0406] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0407] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0408] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0409] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0410] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0411] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0412] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0413] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0414] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0415] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0416] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. The program processing of this system is explained below with specific examples.

[0417] Enter and submit a search query

[0418] A user inputs a question about a government service into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures this query and sends it to the server.

[0419] Query Analysis

[0420] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text.

[0421] Search for related information

[0422] The server uses the extracted keywords to search for information in multiple government service databases and related websites, and uses APIs and web scraping technology to collect data from reliable sources.

[0423] Information collection and filtering

[0424] The server analyzes the acquired information and collects highly relevant information. The filtering process removes unnecessary information based on the reliability and freshness of the information.

[0425] Generate summary information

[0426] Based on the filtered information, the server generates a summary. It uses natural language generation technology to extract important information and present it in an easy-to-understand format. For example, the following summary is generated for the input "How do I get a resident registration card?"

[0427] Required documents: Identification documents (driver's license, passport, etc.)

[0428] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0429] Fee: Average 300-500 yen (may vary if applying online)

[0430] Other: Reception hours, location of the counter, etc.

[0431] Summary information notification

[0432] The server sends the generated summary information to the terminal, which then displays it to the user, allowing the user to quickly obtain the necessary information about government services related to the input query.

[0433] Specific examples

[0434] For example:

[0435] User operations

[0436] The user types "Please tell me how to obtain a resident registration card" into the terminal.

[0437] Server-side processing

[0438] 1. The server analyzes the query and extracts the keywords "resident registration card" and "how to obtain."

[0439] 2. The server uses these keywords to search for information from multiple trusted databases and websites.

[0440] 3. The server collects relevant information from the search results and filters out unnecessary information.

[0441] 4. The server summarizes the collected information and presents it in a concise and easy-to-understand format.

[0442] Device behavior

[0443] The terminal displays the summary information sent from the server to the user. The user receives a summary like this:

[0444] How to obtain a resident certificate:

[0445] Required documents: Identification documents (driver's license, passport, etc.)

[0446] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0447] Fee: Average 300-500 yen (may vary if applying online)

[0448] Other: Reception hours, location of the counter, etc.

[0449] In this way, users can obtain accurate information about government services in a short time.

[0450] The processing flow will be explained below.

[0451] Step 1:

[0452] The user inputs a search query into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card."

[0453] Step 2:

[0454] The device sends the entered search query to the server, which passes the query to the server via the Internet.

[0455] Step 3:

[0456] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain it."

[0457] Step 4:

[0458] The server uses the extracted keywords to access databases related to government services and related official websites to search for information, using APIs and web scraping technology.

[0459] Step 5:

[0460] The server collects the search results, gathering data from multiple sources and verifying their contents.

[0461] Step 6:

[0462] The server filters the collected information, eliminating unnecessary or unreliable information based on its reliability and freshness.

[0463] Step 7:

[0464] The server summarizes the filtered information, using natural language generation techniques to extract key points and present them in a concise, easy-to-understand format.

[0465] Step 8:

[0466] The server sends the generated summary information to the terminal, and data security is ensured using encrypted communication.

[0467] Step 9:

[0468] The terminal displays the received summary information to the user in an easily viewable and organized format using a GUI.

[0469] Step 10:

[0470] Users can quickly understand the information they need by checking the displayed summary, such as the documents, procedures, and fees required to obtain a resident registration card.

[0471] Example 1

[0472] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0473] Existing information search systems for government services often have information scattered across multiple systems, making it difficult for users to efficiently obtain the information they need, making it difficult to make quick decisions. Furthermore, when there is too much information, it takes a long time for users to extract the information they need.

[0474] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0475] In this invention, the server includes means for a user to input a search query, means for analyzing the search query and extracting keywords, means for searching databases and websites for related information using the extracted keywords, means for collecting highly relevant information from the search results and filtering the information based on reliability and freshness, and means for generating summary information based on the filtered related information, thereby enabling users to centrally search distributed administrative service information and efficiently obtain reliable and up-to-date information.

[0476] A "search query" refers to a question or keyword that a user enters into a system to obtain information.

[0477] "Keywords" refers to important words or phrases extracted from a search query and used to retrieve related information.

[0478] A "database" refers to a collection of information that is systematically organized and made available for efficient search and reference.

[0479] "Website" means a collection of information pages on the Internet that provide information on a particular subject.

[0480] "Filtering" refers to the process of removing unnecessary information from collected information based on criteria such as reliability and freshness.

[0481] A "generative AI model" refers to an algorithm or program that uses artificial intelligence techniques to generate new information based on input data.

[0482] "Summary information" refers to information that has been filtered and concisely summarized by extracting only the important points.

[0483] "Notification" refers to the process of presenting system-generated summary information to the user.

[0484] The system according to the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. A specific embodiment of this system will be described below.

[0485] Enter and submit a search query

[0486] A user uses their own device (PC, smartphone, tablet, etc.) to input a question about a government service. For example, they input a query such as "Please tell me how to obtain a resident registration card" into the input field of the device. The device captures this input query and sends it to a server via the Internet.

[0487] Receiving and parsing queries

[0488] The server passes the received query to a natural language processing engine (e.g., SpaCy, NLTK) for morphological analysis. As a result, keywords such as "resident registration card" and "how to obtain" are extracted from the query. At the same time, contextual analysis is performed to determine the type of information the user is looking for.

[0489] Examples:

[0490] User: "Please tell me how to obtain a resident registration card."

[0491] Terminal: Sends query to server

[0492] Server: Extract the keywords "resident certificate" and "acquisition method"

[0493] Search for related information

[0494] The server searches for information from multiple government service databases and related websites based on the extracted keywords, by querying the database using RESTful APIs and by using web scraping techniques (e.g., BeautifulSoup) to collect data from websites.

[0495] Examples:

[0496] Server: Sends a query "How to obtain a resident registration card" to the administrative service database API

[0497] Server: Uses web scrapers to gather information from trusted sites

[0498] Information collection and filtering

[0499] The server filters the information collected from the search results, evaluating the information based on its reliability, freshness, and relevance, and removing unnecessary information. This filtering process includes evaluating the reliability of the source and checking the most recent update date.

[0500] Examples:

[0501] Server: Classifies the data obtained from the search results and extracts only the most up-to-date and reliable information

[0502] Server: Remove unnecessary information (duplicates and old information)

[0503] Generate summary information

[0504] The server generates summary information based on the filtered information using a generative AI model (e.g., OpenAI's GPT-3), writes summary instructions in a prompt, and analyzes and verifies the generated summary.

[0505] Examples:

[0506] Server: Send the summary of "Please tell me how to obtain a resident registration card" as a prompt to the generative AI model

[0507] Generative AI model: Generates summary text. Required documents: Personal identification (driver's license, passport, etc.); Acquisition method: Application at city hall, by mail, or online application; Fee: Average 300 to 500 yen.

[0508] Server: Validate the generated summary and adjust it if necessary

[0509] Summary information notification

[0510] The server then sends the generated summary information to the terminal, which then displays it to the user. This allows the user to quickly and centrally search for dispersed administrative service information and efficiently obtain the most reliable and up-to-date information.

[0511] Examples:

[0512] Server: Sends summary information to the terminal

[0513] Terminal: Display the received summary information to the user. "How to obtain a resident registration certificate: Required documents: Personal identification document (driver's license, passport, etc.); How to obtain: Apply at the city hall, by mail, or online; Fee: Average 300 to 500 yen."

[0514] In this way, the system can quickly provide reliable, up-to-date information on government services based on the search query entered by the user.

[0515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0516] Step 1:

[0517] A user uses their own terminal to input a question about a government service. For example, they might input, "Please tell me how to obtain a resident registration card." The input data is a text query. The terminal captures this input query and sends it to a server via the Internet. The output is a text query received by the server.

[0518] Step 2:

[0519] The server passes the received query to a natural language processing engine (e.g., SpaCy, NLTK) for morphological and contextual analysis. At this stage, the input query is broken down into keywords such as "resident registration card" and "how to obtain it." The input is the text data of the query, and the output is a set of extracted keywords.

[0520] Step 3:

[0521] The server searches for information from multiple government service databases and related websites based on the extracted keywords. This is done using RESTful API calls and web scraping techniques (e.g., BeautifulSoup). The input is a set of keywords, and the output is a dataset of related information obtained as search results.

[0522] Step 4:

[0523] The server filters the information collected from the search results. At this stage, the reliability, freshness, and relevance of the information are evaluated, and unnecessary information is removed. For example, if the same information appears multiple times or if the information is outdated, it is filtered. The input is a dataset of search results, and the output is filtered, highly reliable information data.

[0524] Step 5:

[0525] The server generates summary information using a generative AI model (e.g., OpenAI's GPT-3) based on the filtered information. The server writes summary instructions in a prompt and passes it to the generative AI model. The input is the filtered information and the prompt, and the output is the generated summary.

[0526] Step 6:

[0527] The server sends the generated summary information to the terminal, which displays this information to the user. This allows the user to quickly and centrally search for dispersed administrative service information and efficiently obtain reliable, up-to-date information. The input is summary information, and the output is the information displayed to the user.

[0528] In this way, each processing step works together with specific operations, realizing efficient and highly reliable information provision.

[0529] (Application example 1)

[0530] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0531] In conventional shopping, users must browse multiple online shopping sites to obtain information about the product they want to purchase, checking the information on each site. This takes time and effort, placing a particular burden on beginners and the elderly. Furthermore, the reliability and freshness of the information available varies, making it difficult to determine which information is the most up-to-date and trustworthy. To solve these problems, a system is needed that provides highly reliable and up-to-date summary information in a unified manner.

[0532] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0533] In this invention, the server includes means for a user to input a shopping search query, means for analyzing the shopping search query and extracting product-related keywords, means for searching for product information from online shopping sites using the extracted product-related keywords, means for collecting and filtering product information details and price information from the search results, and means for generating summary information based on the collected product information and price information, thereby enabling a user to obtain reliable and up-to-date product summary information in a short amount of time.

[0534] A "means for a user to enter a search query" is a device or interface through which a user can enter a question about a product they wish to purchase.

[0535] The "means for analyzing the search query and extracting keywords" refers to a technology or algorithm that extracts important words or phrases from the search query entered by the user.

[0536] The "means for searching for related information using the extracted keywords" refers to algorithms or techniques that use the extracted important words or phrases to find related information from various sources.

[0537] The "means for collecting and filtering highly relevant information from the search results" refers to a method or technology for selecting particularly relevant information from the search results and eliminating unnecessary information.

[0538] The "means for generating summary information based on the collected information" refers to a method or technology for concisely summarizing the collected information and providing it to the user in an easily understandable format.

[0539] The "means for notifying the user of the summary information" refers to an interface or technology for transmitting the generated summary information to the user's device and displaying it.

[0540] A "means for a user to enter a shopping search query" is a device or interface through which a user can enter a question about a product they wish to purchase.

[0541] The "means for analyzing the shopping-related search query and extracting product-related keywords" refers to a method or technology for extracting important product-related words and phrases from shopping-related questions entered by users.

[0542] "Means for searching for product information from online shopping sites using keywords related to the extracted products" refers to a technology that uses important words and phrases related to the extracted products to find relevant product information from multiple online shopping sites.

[0543] "Means for collecting and filtering detailed product information and price information from the search results" refers to a method or technology for collecting detailed product information and price information from the search results and removing unnecessary information.

[0544] The "means for generating summary information based on the collected product information and price information" refers to a method or technology for concisely summarizing the collected product-related details and price information and providing it to the user in an easy-to-understand format.

[0545] The system according to the present invention allows users to input shopping search queries and provides related product information in a unified manner. The processing of the program of this system will be explained using specific examples.

[0546] System configuration

[0547] The system consists of a terminal used by the user, a server that processes the data, and various software components that collect, filter, and summarize the information.

[0548] Program processing overview

[0549] The system consists of the following main steps:

[0550] User operations and device behavior

[0551] The user types a shopping question into the device, for example, "How do I buy a Nintendo Switch?" This query is captured by the device and sent to the server.

[0552] Query Analysis

[0553] The server analyzes the received query and uses natural language processing technology to extract keywords such as "Nintendo Switch" and "how to purchase" from the input text. The specific software used includes transformers, a Python natural language processing library.

[0554] Search for product information

[0555] The server uses the extracted keywords to search for product information on multiple online shopping sites. It uses APIs and web scraping techniques, such as BeautifulSoup and requests, to collect data from reliable sources.

[0556] Information collection and filtering

[0557] The server analyzes the acquired information and collects relevant product and price information. The filtering process eliminates unnecessary information based on the reliability and freshness of the information.

[0558] Generate summary information

[0559] Based on the filtered information, the server generates summary information. It uses a generative AI model to concisely summarize the extracted important information. Specifically, it uses the transformers library.

[0560] Summary information notification

[0561] The server sends the generated summary information to the terminal, which displays it to the user, allowing the user to quickly obtain important information about the product they want to purchase.

[0562] Specific examples

[0563] User actions and query input

[0564] The user types "How do I purchase a Nintendo Switch?" into the device. Based on this query, the system starts a series of processes.

[0565] Query analysis and product search

[0566] The server analyzes the query and extracts the keywords "Nintendo Switch" and "purchase method," then collects product information from multiple online shopping sites.

[0567] Collecting and summarizing information

[0568] Based on the collected product and price information, important data is extracted and a summary is generated. For example, the following summary is generated:

[0569] Information on purchasing the Nintendo Switch: The Nintendo Switch console is available for purchase for 32,978 yen, and the Nintendo Switch Lite is available for purchase for 21,970 yen. You can purchase them from the links below.

[0570] Summary information notification

[0571] The generated summary information is sent to the terminal and displayed to the user. The user receives a summary that looks like this:

[0572] Information on purchasing the Nintendo Switch: The Nintendo Switch console is available for purchase for 32,978 yen, and the Nintendo Switch Lite is available for purchase for 21,970 yen. You can purchase them from the links below.

[0573] In this way, users can easily obtain reliable product information in a short time.

[0574] With the above-described configuration and method, the system of the present invention can quickly provide accurate information in response to user queries regarding shopping.

[0575] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0576] Step 1:

[0577] A user enters a shopping-related search query into their device, for example, "How do I buy a Nintendo Switch?" This query becomes input to the system.

[0578] Step 2:

[0579] The terminal captures the entered query and sends it to the server, where the input is the user's query and the output is the query sent to the server.

[0580] Step 3:

[0581] The server analyzes the received query. It uses natural language processing technology to extract keywords such as "Nintendo Switch" and "how to purchase" from the input query. For example, it uses transformers, a Python natural language processing library, to perform the analysis.

[0582] Step 4:

[0583] The server uses the extracted keywords to search for product information from multiple online shopping sites. For example, it uses requests to retrieve pages from online shopping sites, analyzes them with BeautifulSoup, and collects product and price information. The input here is the extracted keywords, and the output is a list of the collected product information.

[0584] Step 5:

[0585] The server filters the collected product information, eliminating unnecessary information based on reliability and freshness. For example, reliability is evaluated based on collected product reviews and update dates, and only the necessary data is extracted. The input is the collected product information, and the output is the filtered product information.

[0586] Step 6:

[0587] The server generates summary information based on the filtered information. Here, a generative AI model is used to concisely summarize important information. For example, the transformers library is used to generate the summary information. The input is the filtered product information, and the output is the summarized information.

[0588] Step 7:

[0589] The server sends the generated summary information to the terminal. The input is the summarized information, and the output is the summary information sent to the terminal.

[0590] Step 8:

[0591] The terminal displays the received summary information to the user, allowing the user to quickly obtain important information about the product they are planning to purchase. The input is the summary information sent from the server, and the output is the content displayed to the user.

[0592] This allows the system to provide a summary of reliable and up-to-date information in response to a user's shopping search query through a series of processes.

[0593] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0594] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions and optimizes the information provided based on those emotions. The program processing of this system is explained below with specific examples.

[0595] Enter and submit a search query

[0596] A user inputs a question about a government service into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures this query and recognizes the user's emotion using an emotion engine. The device then transmits the query and emotion information to the server.

[0597] Query Analysis

[0598] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text. It also uses an emotion engine to analyze the user's emotions and recognize their current emotional state.

[0599] Search for related information

[0600] The server then uses the extracted keywords to access databases related to government services and related official websites to search for information, using APIs and web scraping technology. Furthermore, it adjusts the filtering criteria for search results based on the user's emotions. For example, if the user appears anxious, it will prioritize detailed and reassuring information.

[0601] Information collection and filtering

[0602] The server collects the search results. In doing so, it gathers data from multiple sources and checks their contents. When filtering the collected information, it eliminates unnecessary information based on its reliability and freshness. It also sets filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes information that is concise and can be understood quickly.

[0603] Generate summary information

[0604] The server generates a summary based on the filtered information. It uses natural language generation technology to extract key points and present them in an easy-to-understand format. The server also adjusts the presentation and format of the summary, taking into account the user's emotional state, as recognized by the emotion engine. For example, if the user is anxious, the server generates a summary in a gentle tone that provides a sense of security.

[0605] Summary information notification

[0606] The server sends the generated summary information to the terminal. Data security is ensured using encrypted communication. The terminal displays this information to the user. Furthermore, the display method is also adjusted according to the user's emotional state.

[0607] Specific examples

[0608] For example:

[0609] User operations

[0610] The user types into the terminal, "Please tell me how to obtain a resident registration card." At this time, the emotion engine recognizes that the user looks anxious.

[0611] Server-side processing

[0612] 1. The server analyzes the query and extracts the keywords "resident registration card" and "how to obtain."

[0613] 2. The server recognizes that the user is anxious based on the emotional information from the emotion engine.

[0614] 3. The server uses these keywords to search for information from multiple trusted databases and websites, prioritizing detailed and reassuring information to allay concerns.

[0615] 4. The server collects reliable information from the search results and filters out unnecessary information.

[0616] 5. The server summarizes the collected information and generates a summary in a warm tone to ease anxiety.

[0617] Device behavior

[0618] The terminal displays the summary information sent from the server to the user. To ease the user's anxiety, the information is organized in an easy-to-read format and presented in a reassuring manner. The user receives a summary like this:

[0619] How to obtain a resident certificate:

[0620] Required documents: Identification documents (driver's license, passport, etc.)

[0621] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0622] Fee: Average 300-500 yen (may vary if applying online)

[0623] Other: Reception hours, location of the counter, etc.

[0624] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[0625] In this way, users can obtain accurate and reassuring information about government services in a short amount of time.

[0626] The processing flow will be explained below.

[0627] Step 1:

[0628] The user inputs a search query into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures the input query.

[0629] Step 2:

[0630] The emotion engine recognizes the user's emotions from their voice, facial expressions, etc. The device then sends the recognized emotion information along with the query to the server.

[0631] Step 3:

[0632] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text. At the same time, it analyzes the user's emotions, which are recognized by an emotion engine.

[0633] Step 4:

[0634] The server then searches for information by accessing databases related to government services and related official websites based on the extracted keywords, using APIs and web scraping technology to obtain relevant information.

[0635] Step 5:

[0636] The server collects the search results, gathers reliable data from multiple sources, and verifies their contents.

[0637] Step 6:

[0638] The server filters the collected information. The filtering process eliminates unnecessary information based on the reliability and freshness of the information. It also adjusts the filtering criteria based on the user's emotional state. For example, if the user seems anxious, it will prioritize detailed and reassuring information.

[0639] Step 7:

[0640] The server generates a summary based on the filtered information. It uses natural language generation technology to extract key points and present them in an easy-to-understand format. The server adjusts the presentation of the summary based on the user's emotional state, as recognized by the emotion engine. For example, if the user appears anxious, it uses a calm, reassuring tone.

[0641] Step 8:

[0642] The server sends the generated summary information to the terminal, and uses encrypted communication to ensure data security.

[0643] Step 9:

[0644] The device then displays the summary information to the user. The display method is also adjusted according to the user's emotions. For example, if a user is feeling anxious, a design and color scheme that visually conveys a sense of security is used.

[0645] Step 10:

[0646] Users can quickly understand the information they need by checking the summary displayed. Information on necessary procedures and documents is concisely explained, allowing them to act with confidence.

[0647] Examples:

[0648] For example, if a user says, "Please tell me how to obtain a resident registration card," and looks anxious, this emotion is recognized. Based on this information, the server prioritizes collecting detailed and reassuring information on how to obtain a resident registration card, and generates summary information in a calm manner. The user can then reassure themselves by checking the information displayed on the device and following the instructions to proceed with the procedure.

[0649] Example 2

[0650] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0651] Conventional information search systems provide relevant information in response to a user's search query, but lack the ability to recognize the user's emotional state and provide optimal information based on that emotion. This makes it difficult for users to quickly and confidently obtain the information they need. Another issue is the insufficient filtering of information based on its reliability and freshness. The present invention aims to solve these problems and provide a system that provides optimal information based on the user's emotions.

[0652] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0653] In this invention, the server includes a means for recognizing a user's emotion and optimizing information to be provided based on the emotion, a means for analyzing a search query and extracting keywords, and a means for searching for related information using the extracted keywords, thereby enabling the provision of optimal information according to the user's emotion.

[0654] "User" refers to a person who utilizes the System to enter a search query and retrieve information.

[0655] A "search query" refers to a question or keyword that a user enters to obtain information.

[0656] "Terminal" refers to an electronic device through which a user enters search queries and receives information.

[0657] "Server" means a central processing unit for analyzing search queries and providing relevant information.

[0658] An "emotion engine" is a technology that recognizes a user's emotions and optimizes the information provided based on that emotional information.

[0659] "Natural language processing technology" refers to the technology that allows a computer to understand and analyze input text data.

[0660] "Keywords" refer to important words in information retrieval extracted from a search query.

[0661] "Relevant information" refers to information that is relevant to the purpose a user is trying to obtain through a search query.

[0662] "Filtering" refers to the process of removing unnecessary parts from acquired information, leaving only useful information.

[0663] "Natural language generation technology" refers to the technology of generating sentences in a natural way based on large amounts of data.

[0664] "Summary information" refers to information that extracts important points from collected information and summarizes them concisely.

[0665] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions and optimizes the information provided based on the user's emotions.

[0666] Enter and submit a search query

[0667] A user inputs a question about a government service into their own device. A specific example is the query "Please tell me how to obtain a resident registration card." The device captures this query and recognizes the user's emotions using an emotion engine. Emotion analysis technology, for example, can be used as the emotion engine. The captured query and emotion information are sent to the server.

[0668] Query Analysis

[0669] The server analyzes the received query using natural language processing techniques (e.g., BERT and spaCy) to extract keywords such as "resident registration card" and "how to obtain" from the input text. It also analyzes the user's emotional state using an emotion engine and recognizes the current emotional state as a cyclic variable.

[0670] Search for related information

[0671] The server then uses the extracted keywords to access databases of government services and related official websites to retrieve information. It uses APIs and web scraping technologies (e.g., BeautifulSoup and Scrapy). It also adjusts the filtering criteria for search results based on the user's emotional state. For example, if the user appears anxious, it prioritizes detailed and reassuring information.

[0672] Information collection and filtering

[0673] The server organizes the search results and integrates data from multiple sources. It filters information based on reliability and freshness. It also flexibly adjusts the filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes concise and easy-to-understand information.

[0674] Generate summary information

[0675] The server generates a summary based on the filtered information. It uses natural language generation technology (e.g., GPT-3) to extract key points and translate them into an easy-to-understand format. The generated summary takes into account the user's emotional state and adjusts its expression and tone accordingly. For example, a summary may be written in a gentler tone to alleviate anxiety.

[0676] Summary information notification

[0677] The server sends the generated summary information to the device. Data security is ensured using encryption technologies such as SSL / TLS for communication. The device then displays the received summary information to the user, displaying it according to their emotional state.

[0678] Specific examples

[0679] For example, if a user types "Please tell me how to get a resident registration card" into the terminal, the emotion engine will recognize that the user looks anxious. The following process will be performed on the server side:

[0680] 1. The server analyzes and extracts the keywords "resident registration card" and "how to obtain."

[0681] 2. Based on the user's emotional information, prioritize collecting detailed information to alleviate anxiety.

[0682] 3. Filter reliable information and filter out unnecessary information.

[0683] 4. Generate summary information in a gentle tone and add a reassuring message.

[0684] The terminal will display the generated summary information to the user as follows:

[0685] How to obtain a resident certificate:

[0686] Required documents: Identification documents (driver's license, passport, etc.)

[0687] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0688] Fee: Average 300-500 yen (may vary if applying online)

[0689] Other: Reception hours, location of the counter, etc.

[0690] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[0691] This allows users to quickly obtain accurate and reliable information about government services.

[0692] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0693] Step 1: Enter and submit a search query

[0694] The user inputs a question about government services into the terminal. Specifically, the terminal receives the text data entered by the user, "Please tell me how to obtain a resident registration card." The terminal captures this query. The emotion engine analyzes the input query and recognizes the user's emotional state (e.g., anxiety). The captured query and emotion information are sent to the server. The input is the search query and the user's emotional state, and the output is the data sent to the server.

[0695] Step 2: Parsing the query

[0696] The server analyzes the query based on the received data. Specifically, it analyzes the query using natural language processing technology (e.g., BERT) to extract keywords such as "resident registration card" and "how to obtain it." The server also analyzes the emotional information provided by the emotion engine to recognize the current emotional state. The input is the search query and emotional information, and the output is the extracted keywords and the recognition result of the emotional state.

[0697] Step 3: Find related information

[0698] The server accesses databases related to government services and related official websites based on keywords to obtain information. Specifically, it uses APIs and web scraping technologies (e.g., BeautifulSoup and Scrapy) to collect relevant information. It adjusts search criteria based on the user's emotions, and prioritizes detailed and reassuring information for anxious users. The input is the extracted keywords and emotional state, and the output is the obtained related information.

[0699] Step 4: Collecting and filtering information

[0700] The server organizes the collected search results. Specifically, it integrates data from multiple sources and filters them based on reliability and freshness. Furthermore, it flexibly adjusts the filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes concise and easy-to-understand information. The input is the retrieved relevant information and the user's emotional state, and the output is the filtered information.

[0701] Step 5: Generate summary information

[0702] The server generates summary information based on the filtered information. Specifically, it uses natural language generation technology (e.g., GPT-3) to extract key points and convert them into an easy-to-understand format. The generated summary adjusts its expression and tone to take into account the user's emotions. For anxious users, it generates a summary that includes reassuring words. The input is the filtered information and emotional state, and the output is the generated summary information.

[0703] Step 6: Notification of summary information

[0704] The server sends the generated summary information to the terminal. Specifically, encryption technology such as SSL / TLS is used for communication to ensure data security. The terminal displays the received summary information to the user and selects a display method based on the user's emotional state. The input is the generated summary information, and the output is the screen display viewed by the user.

[0705] (Application example 2)

[0706] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0707] When searching for information about government services, it is difficult to provide optimal information based on the user's emotions. Specifically, if a user is feeling anxious or impatient, it is necessary to obtain and provide information in a manner that corresponds to that emotion. However, many conventional systems provide information uniformly without considering the user's emotions, which results in the problem of not being able to obtain optimal information for the user. Furthermore, there is no established method for easily obtaining information in an in-car environment, such as through voice input.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0709] In this invention, the server includes: a means for a user to input a search query; a means for analyzing the search query and extracting keywords; a means for searching for related information using the extracted keywords; a means for collecting and filtering highly relevant information from the search results; a means for generating summary information based on the collected information; a means for notifying the user of the summary information; an emotion engine means for recognizing the user's emotions; and a means for optimizing the filtering criteria for the information and the expression of the summary information based on the emotion information recognized by the emotion engine means. This makes it possible to provide information in an optimal form according to the user's emotional state. For example, in an in-vehicle environment of an autonomous vehicle, voice input can be accepted through smart glasses, and appropriate information can be provided quickly and reassuringly.

[0710] - "Means by which a user enters a search query" refers to an interface through which a user can enter a question about a government service, including a voice input device, keyboard, or touchscreen.

[0711] The "means for analyzing the search query and extracting keywords" is a mechanism for analyzing the input search query using natural language processing technology and identifying important keywords.

[0712] The "means for searching for related information using the extracted keywords" is a system for obtaining information from databases and official websites related to administrative services based on the extracted keywords.

[0713] The "means for collecting and filtering highly relevant information from the search results" refers to a procedure for excluding unnecessary information from the acquired information based on its reliability and freshness, and selecting highly relevant information.

[0714] The "means for generating summary information based on the collected information" refers to a method for extracting important points from filtered information and summarizing them in an easy-to-understand manner using natural language generation technology.

[0715] The "means for notifying the user of the summary information" is a mechanism for displaying the generated summary information on the user's terminal, and is provided visually through smart glasses or a smartphone.

[0716] The "emotion engine means for recognizing the user's emotions" is an engine for analyzing the emotional state from the input query or the user's voice and acquiring emotional information.

[0717] The "means for optimizing the filtering criteria for the information and the expression of summary information based on the emotional information recognized by the emotion engine means" refers to a system for adjusting the method and content of information provision in accordance with the emotional information, and providing information in a form that is optimal for the user.

[0718] "System" refers to the overall mechanism that is made up of a combination of multiple technological elements, and in this case refers to the infrastructure for providing users with information about government services in the most optimal way.

[0719] MODE FOR CARRYING OUT THE INVENTION

[0720] This invention relates to a system for enabling a user in an autonomous vehicle to obtain information about government services through voice input and optimize that information using an emotion recognition engine. The system includes a voice input device, an emotion recognition engine, natural language processing technology, an information search engine, a filtering system, and a user notification device.

[0721] System Overview

[0722] In this system, when a user uses smart glasses or other voice input devices to ask a question about government services, the voice input is converted into text and sent to a server. The server analyzes the input text and extracts important keywords. Based on the extracted keywords, it searches for related information from government service databases and websites. In addition, an emotion recognition engine recognizes the user's emotions and optimizes the information filtering criteria and summary information presentation based on those emotions.

[0723] Hardware and software details

[0724] The server uses the following software and hardware:

[0725] Speech Recognition: Use the speech_recognition library to capture voice input from a microphone, such as smart glasses, and convert it to text.

[0726] Emotion recognition: Uses the emotion recognition model (pipeline('sentiment-analysis')) from the transformers library.

[0727] Information retrieval: Using APIs and web scraping technology, information is retrieved from government service databases and websites.

[0728] Information filtering: Filter information based on reliability and freshness, and prioritize information based on emotional information.

[0729] Summary Generation: Summarize the filtered information using a summary generation model from the transformers library.

[0730] After receiving voice input from the user, the server performs the following actions:

[0731] Speech recognition and text conversion

[0732] The server captures the voice input from the user through the smart glasses and converts it into text using the speech_recognition library. For example, when a user inputs "Please tell me how to obtain a resident registration card," the voice is converted into text.

[0733] emotion recognition

[0734] The converted text is sent to an emotion recognition engine, where the emotional state is analyzed using emotion recognition models from the transformers library. For example, if the user is feeling anxious, it is recognized as "anxious."

[0735] Information Search and Filtering

[0736] Based on the extracted keywords, the server retrieves information from government service databases and official websites. Based on emotional information, priority is given to information that gives a sense of security and can be quickly understood. For example, information such as "how to obtain a resident registration card," "required documents," "how to obtain it," and "fees" is searched.

[0737] Summary generation and notification

[0738] The acquired information is summarized using the transformers library, and the representation is optimized based on the emotion, and then displayed on the smart glasses. For example, the following summary is generated:

[0739] How to obtain a resident certificate:

[0740] Required documents: Identification documents (driver's license, passport, etc.)

[0741] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0742] Fee: Average 300-500 yen (may vary if applying online)

[0743] Other: Reception hours, location of the counter, etc.

[0744] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[0745] Prompt Sentence Examples

[0746] Here are some examples of emotion recognition prompts for input queries:

[0747] Identify the emotions in the following sentences:

[0748] I would like to go to the local government office in my area to get a resident registration certificate. What documents and procedures are required?

[0749] This system allows users to easily obtain information about government services while on the move, and provides reassuring information that is optimized according to their emotions.

[0750] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0751] Program processing steps

[0752] Step 1:

[0753] The user inputs voice through the smart glasses. For example, the user might ask, "Please tell me how to obtain a resident registration card." The smart glasses capture this voice and send it to the server. The input is the user's voice data, and the output is the voice data sent to the server.

[0754] Step 2:

[0755] The server converts the received voice data into text using the speech_recognition library. In this step, the voice data is converted into text data. Specifically, the voice recognition model analyzes the voice waveform and outputs the corresponding text, "Please tell me how to obtain a resident registration card."

[0756] Step 3:

[0757] The server sends the text data to the emotion recognition engine, which analyzes the user's emotions using the emotion recognition model in the Transformers library. The input is text data, and the output is emotional information (e.g., "anxiety"). Specifically, the emotion recognition model analyzes the user's emotional state from the text content and assigns an emotion label.

[0758] Step 4:

[0759] The server uses natural language processing technology to extract important keywords from the input text data. For example, the keywords "resident registration card" and "how to obtain" are extracted. The input is emotional information and text data, and the output is a keyword list. Specifically, the keyword extraction model analyzes the text and lists important words.

[0760] Step 5:

[0761] The server uses the extracted keywords to search for relevant information from government service databases and official websites. The input is a list of keywords, and the output is search results. Specifically, APIs and web scraping technologies are used to obtain data from sources.

[0762] Step 6:

[0763] The server filters the search results based on reliability and freshness, as well as on recognized emotional information. The input is the search results and emotional information, and the output is the filtered information. Specifically, the filtering algorithm eliminates unreliable information and prioritizes it according to its emotions.

[0764] Step 7:

[0765] The server generates a summary based on the filtered information. The summary generation model from the transformers library is used to generate the summary. The input is the filtered information, and the output is the summary information. Specifically, the summary generation model extracts important information and summarizes it using emotion-based expressions.

[0766] Step 8:

[0767] The summary information is sent to the user's smart glasses using encrypted communication. The input is the summary information, and the output is the text displayed on the smart glasses. Specifically, the server encrypts the summary and sends it to the smart glasses through a communication protocol.

[0768] Step 9:

[0769] The smart glasses display summary information to the user. The display method is also adjusted according to the user's emotional state. The input is summary information received from the server, and the output is visual information provided to the user. Specifically, the smart glasses display the information with appropriate font size, color, and layout.

[0770] In this way, users can easily obtain information about government services while on the move, and can obtain reassuring information that is optimized according to their emotions.

[0771] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0772] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0773] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0774] [Third embodiment]

[0775] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0776] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0777] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0778] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0779] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0780] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0781] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0782] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0783] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0784] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0785] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0786] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0787] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. The program processing of this system is explained below with specific examples.

[0788] Enter and submit a search query

[0789] A user inputs a question about a government service into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures this query and sends it to the server.

[0790] Query Analysis

[0791] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text.

[0792] Search for related information

[0793] The server uses the extracted keywords to search for information in multiple government service databases and related websites, and uses APIs and web scraping technology to collect data from reliable sources.

[0794] Information collection and filtering

[0795] The server analyzes the acquired information and collects highly relevant information. The filtering process removes unnecessary information based on the reliability and freshness of the information.

[0796] Generate summary information

[0797] Based on the filtered information, the server generates a summary. It uses natural language generation technology to extract important information and present it in an easy-to-understand format. For example, the following summary is generated for the input "How do I get a resident registration card?"

[0798] Required documents: Identification documents (driver's license, passport, etc.)

[0799] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0800] Fee: Average 300-500 yen (may vary if applying online)

[0801] Other: Reception hours, location of the counter, etc.

[0802] Summary information notification

[0803] The server sends the generated summary information to the terminal, which then displays it to the user, allowing the user to quickly obtain the necessary information about government services related to the input query.

[0804] Specific examples

[0805] For example:

[0806] User operations

[0807] The user types "Please tell me how to obtain a resident registration card" into the terminal.

[0808] Server-side processing

[0809] 1. The server analyzes the query and extracts the keywords "resident registration card" and "how to obtain."

[0810] 2. The server uses these keywords to search for information from multiple trusted databases and websites.

[0811] 3. The server collects relevant information from the search results and filters out unnecessary information.

[0812] 4. The server summarizes the collected information and presents it in a concise and easy-to-understand format.

[0813] Device behavior

[0814] The terminal displays the summary information sent from the server to the user. The user receives a summary like this:

[0815] How to obtain a resident certificate:

[0816] Required documents: Identification documents (driver's license, passport, etc.)

[0817] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0818] Fee: Average 300-500 yen (may vary if applying online)

[0819] Other: Reception hours, location of the counter, etc.

[0820] In this way, users can obtain accurate information about government services in a short time.

[0821] The processing flow will be explained below.

[0822] Step 1:

[0823] The user inputs a search query into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card."

[0824] Step 2:

[0825] The device sends the entered search query to the server, which passes the query to the server via the Internet.

[0826] Step 3:

[0827] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain it."

[0828] Step 4:

[0829] The server uses the extracted keywords to access databases related to government services and related official websites to search for information, using APIs and web scraping technology.

[0830] Step 5:

[0831] The server collects the search results, gathering data from multiple sources and verifying their contents.

[0832] Step 6:

[0833] The server filters the collected information, eliminating unnecessary or unreliable information based on its reliability and freshness.

[0834] Step 7:

[0835] The server summarizes the filtered information, using natural language generation techniques to extract key points and present them in a concise, easy-to-understand format.

[0836] Step 8:

[0837] The server sends the generated summary information to the terminal, and data security is ensured using encrypted communication.

[0838] Step 9:

[0839] The terminal displays the received summary information to the user in an easily viewable and organized format using a GUI.

[0840] Step 10:

[0841] Users can quickly understand the information they need by checking the displayed summary, such as the documents, procedures, and fees required to obtain a resident registration card.

[0842] Example 1

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

[0844] Existing information search systems for government services often have information scattered across multiple systems, making it difficult for users to efficiently obtain the information they need, making it difficult to make quick decisions. Furthermore, when there is too much information, it takes a long time for users to extract the information they need.

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

[0846] In this invention, the server includes means for a user to input a search query, means for analyzing the search query and extracting keywords, means for searching databases and websites for related information using the extracted keywords, means for collecting highly relevant information from the search results and filtering the information based on reliability and freshness, and means for generating summary information based on the filtered related information, thereby enabling users to centrally search distributed administrative service information and efficiently obtain reliable and up-to-date information.

[0847] A "search query" refers to a question or keyword that a user enters into a system to obtain information.

[0848] "Keywords" refers to important words or phrases extracted from a search query and used to retrieve related information.

[0849] A "database" refers to a collection of information that is systematically organized and made available for efficient search and reference.

[0850] "Website" means a collection of information pages on the Internet that provide information on a particular subject.

[0851] "Filtering" refers to the process of removing unnecessary information from collected information based on criteria such as reliability and freshness.

[0852] A "generative AI model" refers to an algorithm or program that uses artificial intelligence techniques to generate new information based on input data.

[0853] "Summary information" refers to information that has been filtered and concisely summarized by extracting only the important points.

[0854] "Notification" refers to the process of presenting system-generated summary information to the user.

[0855] The system according to the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. A specific embodiment of this system will be described below.

[0856] Enter and submit a search query

[0857] A user uses their own device (PC, smartphone, tablet, etc.) to input a question about a government service. For example, they input a query such as "Please tell me how to obtain a resident registration card" into the input field of the device. The device captures this input query and sends it to a server via the Internet.

[0858] Receiving and parsing queries

[0859] The server passes the received query to a natural language processing engine (e.g., SpaCy, NLTK) for morphological analysis. As a result, keywords such as "resident registration card" and "how to obtain" are extracted from the query. At the same time, contextual analysis is performed to determine the type of information the user is looking for.

[0860] Examples:

[0861] User: "Please tell me how to obtain a resident registration card."

[0862] Terminal: Sends query to server

[0863] Server: Extract the keywords "resident certificate" and "acquisition method"

[0864] Search for related information

[0865] The server searches for information from multiple government service databases and related websites based on the extracted keywords, by querying the database using RESTful APIs and by using web scraping techniques (e.g., BeautifulSoup) to collect data from websites.

[0866] Examples:

[0867] Server: Sends a query "How to obtain a resident registration card" to the administrative service database API

[0868] Server: Uses web scrapers to gather information from trusted sites

[0869] Information collection and filtering

[0870] The server filters the information collected from the search results, evaluating the information based on its reliability, freshness, and relevance, and removing unnecessary information. This filtering process includes evaluating the reliability of the source and checking the most recent update date.

[0871] Examples:

[0872] Server: Classifies the data obtained from the search results and extracts only the most up-to-date and reliable information

[0873] Server: Remove unnecessary information (duplicates and old information)

[0874] Generate summary information

[0875] The server generates summary information based on the filtered information using a generative AI model (e.g., OpenAI's GPT-3), writes summary instructions in a prompt, and analyzes and verifies the generated summary.

[0876] Examples:

[0877] Server: Send the summary of "Please tell me how to obtain a resident registration card" as a prompt to the generative AI model

[0878] Generative AI model: Generates summary text. Required documents: Personal identification (driver's license, passport, etc.); Acquisition method: Application at city hall, by mail, or online application; Fee: Average 300 to 500 yen.

[0879] Server: Validate the generated summary and adjust it if necessary

[0880] Summary information notification

[0881] The server then sends the generated summary information to the terminal, which then displays it to the user. This allows the user to quickly and centrally search for dispersed administrative service information and efficiently obtain the most reliable and up-to-date information.

[0882] Examples:

[0883] Server: Sends summary information to the terminal

[0884] Terminal: Display the received summary information to the user. "How to obtain a resident registration certificate: Required documents: Personal identification document (driver's license, passport, etc.); How to obtain: Apply at the city hall, by mail, or online; Fee: Average 300 to 500 yen."

[0885] In this way, the system can quickly provide reliable, up-to-date information on government services based on the search query entered by the user.

[0886] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0887] Step 1:

[0888] A user uses their own terminal to input a question about a government service. For example, they might input, "Please tell me how to obtain a resident registration card." The input data is a text query. The terminal captures this input query and sends it to a server via the Internet. The output is a text query received by the server.

[0889] Step 2:

[0890] The server passes the received query to a natural language processing engine (e.g., SpaCy, NLTK) for morphological and contextual analysis. At this stage, the input query is broken down into keywords such as "resident registration card" and "how to obtain it." The input is the text data of the query, and the output is a set of extracted keywords.

[0891] Step 3:

[0892] The server searches for information from multiple government service databases and related websites based on the extracted keywords. This is done using RESTful API calls and web scraping techniques (e.g., BeautifulSoup). The input is a set of keywords, and the output is a dataset of related information obtained as search results.

[0893] Step 4:

[0894] The server filters the information collected from the search results. At this stage, the reliability, freshness, and relevance of the information are evaluated, and unnecessary information is removed. For example, if the same information appears multiple times or if the information is outdated, it is filtered. The input is a dataset of search results, and the output is filtered, highly reliable information data.

[0895] Step 5:

[0896] The server generates summary information using a generative AI model (e.g., OpenAI's GPT-3) based on the filtered information. The server writes summary instructions in a prompt and passes it to the generative AI model. The input is the filtered information and the prompt, and the output is the generated summary.

[0897] Step 6:

[0898] The server sends the generated summary information to the terminal, which displays this information to the user. This allows the user to quickly and centrally search for dispersed administrative service information and efficiently obtain reliable, up-to-date information. The input is summary information, and the output is the information displayed to the user.

[0899] In this way, each processing step works together with specific operations, realizing efficient and highly reliable information provision.

[0900] (Application example 1)

[0901] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0902] In conventional shopping, users must browse multiple online shopping sites to obtain information about the product they want to purchase, checking the information on each site. This takes time and effort, placing a particular burden on beginners and the elderly. Furthermore, the reliability and freshness of the information available varies, making it difficult to determine which information is the most up-to-date and trustworthy. To solve these problems, a system is needed that provides highly reliable and up-to-date summary information in a unified manner.

[0903] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0904] In this invention, the server includes means for a user to input a shopping search query, means for analyzing the shopping search query and extracting product-related keywords, means for searching for product information from online shopping sites using the extracted product-related keywords, means for collecting and filtering product information details and price information from the search results, and means for generating summary information based on the collected product information and price information, thereby enabling a user to obtain reliable and up-to-date product summary information in a short amount of time.

[0905] A "means for a user to enter a search query" is a device or interface through which a user can enter a question about a product they wish to purchase.

[0906] The "means for analyzing the search query and extracting keywords" refers to a technology or algorithm that extracts important words or phrases from the search query entered by the user.

[0907] The "means for searching for related information using the extracted keywords" refers to algorithms or techniques that use the extracted important words or phrases to find related information from various sources.

[0908] The "means for collecting and filtering highly relevant information from the search results" refers to a method or technology for selecting particularly relevant information from the search results and eliminating unnecessary information.

[0909] The "means for generating summary information based on the collected information" refers to a method or technology for concisely summarizing the collected information and providing it to the user in an easily understandable format.

[0910] The "means for notifying the user of the summary information" refers to an interface or technology for transmitting the generated summary information to the user's device and displaying it.

[0911] A "means for a user to enter a shopping search query" is a device or interface through which a user can enter a question about a product they wish to purchase.

[0912] The "means for analyzing the shopping-related search query and extracting product-related keywords" refers to a method or technology for extracting important product-related words and phrases from shopping-related questions entered by users.

[0913] "Means for searching for product information from online shopping sites using keywords related to the extracted products" refers to a technology that uses important words and phrases related to the extracted products to find relevant product information from multiple online shopping sites.

[0914] "Means for collecting and filtering detailed product information and price information from the search results" refers to a method or technology for collecting detailed product information and price information from the search results and removing unnecessary information.

[0915] The "means for generating summary information based on the collected product information and price information" refers to a method or technology for concisely summarizing the collected product-related details and price information and providing it to the user in an easy-to-understand format.

[0916] The system according to the present invention allows users to input shopping search queries and provides related product information in a unified manner. The processing of the program of this system will be explained using specific examples.

[0917] System configuration

[0918] The system consists of a terminal used by the user, a server that processes the data, and various software components that collect, filter, and summarize the information.

[0919] Program processing overview

[0920] The system consists of the following main steps:

[0921] User operations and device behavior

[0922] The user types a shopping question into the device, for example, "How do I buy a Nintendo Switch?" This query is captured by the device and sent to the server.

[0923] Query Analysis

[0924] The server analyzes the received query and uses natural language processing technology to extract keywords such as "Nintendo Switch" and "how to purchase" from the input text. The specific software used includes transformers, a Python natural language processing library.

[0925] Search for product information

[0926] The server uses the extracted keywords to search for product information on multiple online shopping sites. It uses APIs and web scraping techniques, such as BeautifulSoup and requests, to collect data from reliable sources.

[0927] Information collection and filtering

[0928] The server analyzes the acquired information and collects relevant product and price information. The filtering process eliminates unnecessary information based on the reliability and freshness of the information.

[0929] Generate summary information

[0930] Based on the filtered information, the server generates summary information. It uses a generative AI model to concisely summarize the extracted important information. Specifically, it uses the transformers library.

[0931] Summary information notification

[0932] The server sends the generated summary information to the terminal, which displays it to the user, allowing the user to quickly obtain important information about the product they want to purchase.

[0933] Specific examples

[0934] User actions and query input

[0935] The user types "How do I purchase a Nintendo Switch?" into the device. Based on this query, the system starts a series of processes.

[0936] Query analysis and product search

[0937] The server analyzes the query and extracts the keywords "Nintendo Switch" and "purchase method," then collects product information from multiple online shopping sites.

[0938] Collecting and summarizing information

[0939] Based on the collected product and price information, important data is extracted and a summary is generated. For example, the following summary is generated:

[0940] Information on purchasing the Nintendo Switch: The Nintendo Switch console is available for purchase for 32,978 yen, and the Nintendo Switch Lite is available for purchase for 21,970 yen. You can purchase them from the links below.

[0941] Summary information notification

[0942] The generated summary information is sent to the terminal and displayed to the user. The user receives a summary that looks like this:

[0943] Information on purchasing the Nintendo Switch: The Nintendo Switch console is available for purchase for 32,978 yen, and the Nintendo Switch Lite is available for purchase for 21,970 yen. You can purchase them from the links below.

[0944] In this way, users can easily obtain reliable product information in a short time.

[0945] With the above-described configuration and method, the system of the present invention can quickly provide accurate information in response to user queries regarding shopping.

[0946] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0947] Step 1:

[0948] A user enters a shopping-related search query into their device, for example, "How do I buy a Nintendo Switch?" This query becomes input to the system.

[0949] Step 2:

[0950] The terminal captures the entered query and sends it to the server, where the input is the user's query and the output is the query sent to the server.

[0951] Step 3:

[0952] The server analyzes the received query. It uses natural language processing technology to extract keywords such as "Nintendo Switch" and "how to purchase" from the input query. For example, it uses transformers, a Python natural language processing library, to perform the analysis.

[0953] Step 4:

[0954] The server uses the extracted keywords to search for product information from multiple online shopping sites. For example, it uses requests to retrieve pages from online shopping sites, analyzes them with BeautifulSoup, and collects product and price information. The input here is the extracted keywords, and the output is a list of the collected product information.

[0955] Step 5:

[0956] The server filters the collected product information, eliminating unnecessary information based on reliability and freshness. For example, reliability is evaluated based on collected product reviews and update dates, and only the necessary data is extracted. The input is the collected product information, and the output is the filtered product information.

[0957] Step 6:

[0958] The server generates summary information based on the filtered information. Here, a generative AI model is used to concisely summarize important information. For example, the transformers library is used to generate the summary information. The input is the filtered product information, and the output is the summarized information.

[0959] Step 7:

[0960] The server sends the generated summary information to the terminal. The input is the summarized information, and the output is the summary information sent to the terminal.

[0961] Step 8:

[0962] The terminal displays the received summary information to the user, allowing the user to quickly obtain important information about the product they are planning to purchase. The input is the summary information sent from the server, and the output is the content displayed to the user.

[0963] This allows the system to provide a summary of reliable and up-to-date information in response to a user's shopping search query through a series of processes.

[0964] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0965] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions and optimizes the information provided based on those emotions. The program processing of this system is explained below with specific examples.

[0966] Enter and submit a search query

[0967] A user inputs a question about a government service into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures this query and recognizes the user's emotion using an emotion engine. The device then transmits the query and emotion information to the server.

[0968] Query Analysis

[0969] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text. It also uses an emotion engine to analyze the user's emotions and recognize their current emotional state.

[0970] Search for related information

[0971] The server then uses the extracted keywords to access databases related to government services and related official websites to search for information, using APIs and web scraping technology. Furthermore, it adjusts the filtering criteria for search results based on the user's emotions. For example, if the user appears anxious, it will prioritize detailed and reassuring information.

[0972] Information collection and filtering

[0973] The server collects the search results. In doing so, it gathers data from multiple sources and checks their contents. When filtering the collected information, it eliminates unnecessary information based on its reliability and freshness. It also sets filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes information that is concise and can be understood quickly.

[0974] Generate summary information

[0975] The server generates a summary based on the filtered information. It uses natural language generation technology to extract key points and present them in an easy-to-understand format. The server also adjusts the presentation and format of the summary, taking into account the user's emotional state, as recognized by the emotion engine. For example, if the user is anxious, the server generates a summary in a gentle tone that provides a sense of security.

[0976] Summary information notification

[0977] The server sends the generated summary information to the terminal. Data security is ensured using encrypted communication. The terminal displays this information to the user. Furthermore, the display method is also adjusted according to the user's emotional state.

[0978] Specific examples

[0979] For example:

[0980] User operations

[0981] The user types into the terminal, "Please tell me how to obtain a resident registration card." At this time, the emotion engine recognizes that the user looks anxious.

[0982] Server-side processing

[0983] 1. The server analyzes the query and extracts the keywords "resident registration card" and "how to obtain."

[0984] 2. The server recognizes that the user is anxious based on the emotional information from the emotion engine.

[0985] 3. The server uses these keywords to search for information from multiple trusted databases and websites, prioritizing detailed and reassuring information to allay concerns.

[0986] 4. The server collects reliable information from the search results and filters out unnecessary information.

[0987] 5. The server summarizes the collected information and generates a summary in a warm tone to ease anxiety.

[0988] Device behavior

[0989] The terminal displays the summary information sent from the server to the user. To ease the user's anxiety, the information is organized in an easy-to-read format and presented in a reassuring manner. The user receives a summary like this:

[0990] How to obtain a resident certificate:

[0991] Required documents: Identification documents (driver's license, passport, etc.)

[0992] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[0993] Fee: Average 300-500 yen (may vary if applying online)

[0994] Other: Reception hours, location of the counter, etc.

[0995] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[0996] In this way, users can obtain accurate and reassuring information about government services in a short amount of time.

[0997] The processing flow will be explained below.

[0998] Step 1:

[0999] The user inputs a search query into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures the input query.

[1000] Step 2:

[1001] The emotion engine recognizes the user's emotions from their voice, facial expressions, etc. The device then sends the recognized emotion information along with the query to the server.

[1002] Step 3:

[1003] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text. At the same time, it analyzes the user's emotions, which are recognized by an emotion engine.

[1004] Step 4:

[1005] The server then searches for information by accessing databases related to government services and related official websites based on the extracted keywords, using APIs and web scraping technology to obtain relevant information.

[1006] Step 5:

[1007] The server collects the search results, gathers reliable data from multiple sources, and verifies their contents.

[1008] Step 6:

[1009] The server filters the collected information. The filtering process eliminates unnecessary information based on the reliability and freshness of the information. It also adjusts the filtering criteria based on the user's emotional state. For example, if the user seems anxious, it will prioritize detailed and reassuring information.

[1010] Step 7:

[1011] The server generates a summary based on the filtered information. It uses natural language generation technology to extract key points and present them in an easy-to-understand format. The server adjusts the presentation of the summary based on the user's emotional state, as recognized by the emotion engine. For example, if the user appears anxious, it uses a calm, reassuring tone.

[1012] Step 8:

[1013] The server sends the generated summary information to the terminal, and uses encrypted communication to ensure data security.

[1014] Step 9:

[1015] The device then displays the summary information to the user. The display method is also adjusted according to the user's emotions. For example, if a user is feeling anxious, a design and color scheme that visually conveys a sense of security is used.

[1016] Step 10:

[1017] Users can quickly understand the information they need by checking the summary displayed. Information on necessary procedures and documents is concisely explained, allowing them to act with confidence.

[1018] Examples:

[1019] For example, if a user says, "Please tell me how to obtain a resident registration card," and looks anxious, this emotion is recognized. Based on this information, the server prioritizes collecting detailed and reassuring information on how to obtain a resident registration card, and generates summary information in a calm manner. The user can then reassure themselves by checking the information displayed on the device and following the instructions to proceed with the procedure.

[1020] Example 2

[1021] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1022] Conventional information search systems provide relevant information in response to a user's search query, but lack the ability to recognize the user's emotional state and provide optimal information based on that emotion. This makes it difficult for users to quickly and confidently obtain the information they need. Another issue is the insufficient filtering of information based on its reliability and freshness. The present invention aims to solve these problems and provide a system that provides optimal information based on the user's emotions.

[1023] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1024] In this invention, the server includes a means for recognizing a user's emotion and optimizing information to be provided based on the emotion, a means for analyzing a search query and extracting keywords, and a means for searching for related information using the extracted keywords, thereby enabling the provision of optimal information according to the user's emotion.

[1025] "User" refers to a person who utilizes the System to enter a search query and retrieve information.

[1026] A "search query" refers to a question or keyword that a user enters to obtain information.

[1027] "Terminal" refers to an electronic device through which a user enters search queries and receives information.

[1028] "Server" means a central processing unit for analyzing search queries and providing relevant information.

[1029] An "emotion engine" is a technology that recognizes a user's emotions and optimizes the information provided based on that emotional information.

[1030] "Natural language processing technology" refers to the technology that allows a computer to understand and analyze input text data.

[1031] "Keywords" refer to important words in information retrieval extracted from a search query.

[1032] "Relevant information" refers to information that is relevant to the purpose a user is trying to obtain through a search query.

[1033] "Filtering" refers to the process of removing unnecessary parts from acquired information, leaving only useful information.

[1034] "Natural language generation technology" refers to the technology of generating sentences in a natural way based on large amounts of data.

[1035] "Summary information" refers to information that extracts important points from collected information and summarizes them concisely.

[1036] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions and optimizes the information provided based on the user's emotions.

[1037] Enter and submit a search query

[1038] A user inputs a question about a government service into their own device. A specific example is the query "Please tell me how to obtain a resident registration card." The device captures this query and recognizes the user's emotions using an emotion engine. Emotion analysis technology, for example, can be used as the emotion engine. The captured query and emotion information are sent to the server.

[1039] Query Analysis

[1040] The server analyzes the received query using natural language processing techniques (e.g., BERT and spaCy) to extract keywords such as "resident registration card" and "how to obtain" from the input text. It also analyzes the user's emotional state using an emotion engine and recognizes the current emotional state as a cyclic variable.

[1041] Search for related information

[1042] The server then uses the extracted keywords to access databases of government services and related official websites to retrieve information. It uses APIs and web scraping technologies (e.g., BeautifulSoup and Scrapy). It also adjusts the filtering criteria for search results based on the user's emotional state. For example, if the user appears anxious, it prioritizes detailed and reassuring information.

[1043] Information collection and filtering

[1044] The server organizes the search results and integrates data from multiple sources. It filters information based on reliability and freshness. It also flexibly adjusts the filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes concise and easy-to-understand information.

[1045] Generate summary information

[1046] The server generates a summary based on the filtered information. It uses natural language generation technology (e.g., GPT-3) to extract key points and translate them into an easy-to-understand format. The generated summary takes into account the user's emotional state and adjusts its expression and tone accordingly. For example, a summary may be written in a gentler tone to alleviate anxiety.

[1047] Summary information notification

[1048] The server sends the generated summary information to the device. Data security is ensured using encryption technologies such as SSL / TLS for communication. The device then displays the received summary information to the user, displaying it according to their emotional state.

[1049] Specific examples

[1050] For example, if a user types "Please tell me how to get a resident registration card" into the terminal, the emotion engine will recognize that the user looks anxious. The following process will be performed on the server side:

[1051] 1. The server analyzes and extracts the keywords "resident registration card" and "how to obtain."

[1052] 2. Based on the user's emotional information, prioritize collecting detailed information to alleviate anxiety.

[1053] 3. Filter reliable information and filter out unnecessary information.

[1054] 4. Generate summary information in a gentle tone and add a reassuring message.

[1055] The terminal will display the generated summary information to the user as follows:

[1056] How to obtain a resident certificate:

[1057] Required documents: Identification documents (driver's license, passport, etc.)

[1058] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[1059] Fee: Average 300-500 yen (may vary if applying online)

[1060] Other: Reception hours, location of the counter, etc.

[1061] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[1062] This allows users to quickly obtain accurate and reliable information about government services.

[1063] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1064] Step 1: Enter and submit a search query

[1065] The user inputs a question about government services into the terminal. Specifically, the terminal receives the text data entered by the user, "Please tell me how to obtain a resident registration card." The terminal captures this query. The emotion engine analyzes the input query and recognizes the user's emotional state (e.g., anxiety). The captured query and emotion information are sent to the server. The input is the search query and the user's emotional state, and the output is the data sent to the server.

[1066] Step 2: Parsing the query

[1067] The server analyzes the query based on the received data. Specifically, it analyzes the query using natural language processing technology (e.g., BERT) to extract keywords such as "resident registration card" and "how to obtain it." The server also analyzes the emotional information provided by the emotion engine to recognize the current emotional state. The input is the search query and emotional information, and the output is the extracted keywords and the recognition result of the emotional state.

[1068] Step 3: Find related information

[1069] The server accesses databases related to government services and related official websites based on keywords to obtain information. Specifically, it uses APIs and web scraping technologies (e.g., BeautifulSoup and Scrapy) to collect relevant information. It adjusts search criteria based on the user's emotions, and prioritizes detailed and reassuring information for anxious users. The input is the extracted keywords and emotional state, and the output is the obtained related information.

[1070] Step 4: Collecting and filtering information

[1071] The server organizes the collected search results. Specifically, it integrates data from multiple sources and filters them based on reliability and freshness. Furthermore, it flexibly adjusts the filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes concise and easy-to-understand information. The input is the retrieved relevant information and the user's emotional state, and the output is the filtered information.

[1072] Step 5: Generate summary information

[1073] The server generates summary information based on the filtered information. Specifically, it uses natural language generation technology (e.g., GPT-3) to extract key points and convert them into an easy-to-understand format. The generated summary adjusts its expression and tone to take into account the user's emotions. For anxious users, it generates a summary that includes reassuring words. The input is the filtered information and emotional state, and the output is the generated summary information.

[1074] Step 6: Notification of summary information

[1075] The server sends the generated summary information to the terminal. Specifically, encryption technology such as SSL / TLS is used for communication to ensure data security. The terminal displays the received summary information to the user and selects a display method based on the user's emotional state. The input is the generated summary information, and the output is the screen display viewed by the user.

[1076] (Application example 2)

[1077] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1078] When searching for information about government services, it is difficult to provide optimal information based on the user's emotions. Specifically, if a user is feeling anxious or impatient, it is necessary to obtain and provide information in a manner that corresponds to that emotion. However, many conventional systems provide information uniformly without considering the user's emotions, which results in the problem of not being able to obtain optimal information for the user. Furthermore, there is no established method for easily obtaining information in an in-car environment, such as through voice input.

[1079] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1080] In this invention, the server includes: a means for a user to input a search query; a means for analyzing the search query and extracting keywords; a means for searching for related information using the extracted keywords; a means for collecting and filtering highly relevant information from the search results; a means for generating summary information based on the collected information; a means for notifying the user of the summary information; an emotion engine means for recognizing the user's emotions; and a means for optimizing the filtering criteria for the information and the expression of the summary information based on the emotion information recognized by the emotion engine means. This makes it possible to provide information in an optimal form according to the user's emotional state. For example, in an in-vehicle environment of an autonomous vehicle, voice input can be accepted through smart glasses, and appropriate information can be provided quickly and reassuringly.

[1081] - "Means by which a user enters a search query" refers to an interface through which a user can enter a question about a government service, including a voice input device, keyboard, or touchscreen.

[1082] The "means for analyzing the search query and extracting keywords" is a mechanism for analyzing the input search query using natural language processing technology and identifying important keywords.

[1083] The "means for searching for related information using the extracted keywords" is a system for obtaining information from databases and official websites related to administrative services based on the extracted keywords.

[1084] The "means for collecting and filtering highly relevant information from the search results" refers to a procedure for excluding unnecessary information from the acquired information based on its reliability and freshness, and selecting highly relevant information.

[1085] The "means for generating summary information based on the collected information" refers to a method for extracting important points from filtered information and summarizing them in an easy-to-understand manner using natural language generation technology.

[1086] The "means for notifying the user of the summary information" is a mechanism for displaying the generated summary information on the user's terminal, and is provided visually through smart glasses or a smartphone.

[1087] The "emotion engine means for recognizing the user's emotions" is an engine for analyzing the emotional state from the input query or the user's voice and acquiring emotional information.

[1088] The "means for optimizing the filtering criteria for the information and the expression of summary information based on the emotional information recognized by the emotion engine means" refers to a system for adjusting the method and content of information provision in accordance with the emotional information, and providing information in a form that is optimal for the user.

[1089] "System" refers to the overall mechanism that is made up of a combination of multiple technological elements, and in this case refers to the infrastructure for providing users with information about government services in the most optimal way.

[1090] MODE FOR CARRYING OUT THE INVENTION

[1091] This invention relates to a system for enabling a user in an autonomous vehicle to obtain information about government services through voice input and optimize that information using an emotion recognition engine. The system includes a voice input device, an emotion recognition engine, natural language processing technology, an information search engine, a filtering system, and a user notification device.

[1092] System Overview

[1093] In this system, when a user uses smart glasses or other voice input devices to ask a question about government services, the voice input is converted into text and sent to a server. The server analyzes the input text and extracts important keywords. Based on the extracted keywords, it searches for related information from government service databases and websites. In addition, an emotion recognition engine recognizes the user's emotions and optimizes the information filtering criteria and summary information presentation based on those emotions.

[1094] Hardware and software details

[1095] The server uses the following software and hardware:

[1096] Speech Recognition: Use the speech_recognition library to capture voice input from a microphone, such as smart glasses, and convert it to text.

[1097] Emotion recognition: Uses the emotion recognition model (pipeline('sentiment-analysis')) from the transformers library.

[1098] Information retrieval: Using APIs and web scraping technology, information is retrieved from government service databases and websites.

[1099] Information filtering: Filter information based on reliability and freshness, and prioritize information based on emotional information.

[1100] Summary Generation: Summarize the filtered information using a summary generation model from the transformers library.

[1101] After receiving voice input from the user, the server performs the following actions:

[1102] Speech recognition and text conversion

[1103] The server captures the voice input from the user through the smart glasses and converts it into text using the speech_recognition library. For example, when a user inputs "Please tell me how to obtain a resident registration card," the voice is converted into text.

[1104] emotion recognition

[1105] The converted text is sent to an emotion recognition engine, where the emotional state is analyzed using emotion recognition models from the transformers library. For example, if the user is feeling anxious, it is recognized as "anxious."

[1106] Information Search and Filtering

[1107] Based on the extracted keywords, the server retrieves information from government service databases and official websites. Based on emotional information, priority is given to information that gives a sense of security and can be quickly understood. For example, information such as "how to obtain a resident registration card," "required documents," "how to obtain it," and "fees" is searched.

[1108] Summary generation and notification

[1109] The acquired information is summarized using the transformers library, and the representation is optimized based on the emotion, and then displayed on the smart glasses. For example, the following summary is generated:

[1110] How to obtain a resident certificate:

[1111] Required documents: Identification documents (driver's license, passport, etc.)

[1112] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[1113] Fee: Average 300-500 yen (may vary if applying online)

[1114] Other: Reception hours, location of the counter, etc.

[1115] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[1116] Prompt Sentence Examples

[1117] Here are some examples of emotion recognition prompts for input queries:

[1118] Identify the emotions in the following sentences:

[1119] I would like to go to the local government office in my area to get a resident registration certificate. What documents and procedures are required?

[1120] This system allows users to easily obtain information about government services while on the move, and provides reassuring information that is optimized according to their emotions.

[1121] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1122] Program processing steps

[1123] Step 1:

[1124] The user inputs voice through the smart glasses. For example, the user might ask, "Please tell me how to obtain a resident registration card." The smart glasses capture this voice and send it to the server. The input is the user's voice data, and the output is the voice data sent to the server.

[1125] Step 2:

[1126] The server converts the received voice data into text using the speech_recognition library. In this step, the voice data is converted into text data. Specifically, the voice recognition model analyzes the voice waveform and outputs the corresponding text, "Please tell me how to obtain a resident registration card."

[1127] Step 3:

[1128] The server sends the text data to the emotion recognition engine, which analyzes the user's emotions using the emotion recognition model in the Transformers library. The input is text data, and the output is emotional information (e.g., "anxiety"). Specifically, the emotion recognition model analyzes the user's emotional state from the text content and assigns an emotion label.

[1129] Step 4:

[1130] The server uses natural language processing technology to extract important keywords from the input text data. For example, the keywords "resident registration card" and "how to obtain" are extracted. The input is emotional information and text data, and the output is a keyword list. Specifically, the keyword extraction model analyzes the text and lists important words.

[1131] Step 5:

[1132] The server uses the extracted keywords to search for relevant information from government service databases and official websites. The input is a list of keywords, and the output is search results. Specifically, APIs and web scraping technologies are used to obtain data from sources.

[1133] Step 6:

[1134] The server filters the search results based on reliability and freshness, as well as on recognized emotional information. The input is the search results and emotional information, and the output is the filtered information. Specifically, the filtering algorithm eliminates unreliable information and prioritizes it according to its emotions.

[1135] Step 7:

[1136] The server generates a summary based on the filtered information. The summary generation model from the transformers library is used to generate the summary. The input is the filtered information, and the output is the summary information. Specifically, the summary generation model extracts important information and summarizes it using emotion-based expressions.

[1137] Step 8:

[1138] The summary information is sent to the user's smart glasses using encrypted communication. The input is the summary information, and the output is the text displayed on the smart glasses. Specifically, the server encrypts the summary and sends it to the smart glasses through a communication protocol.

[1139] Step 9:

[1140] The smart glasses display summary information to the user. The display method is also adjusted according to the user's emotional state. The input is summary information received from the server, and the output is visual information provided to the user. Specifically, the smart glasses display the information with appropriate font size, color, and layout.

[1141] In this way, users can easily obtain information about government services while on the move, and can obtain reassuring information that is optimized according to their emotions.

[1142] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1143] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1144] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1145] [Fourth embodiment]

[1146] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1147] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1150] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1153] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1155] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1157] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1158] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1159] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. The program processing of this system is explained below with specific examples.

[1160] Enter and submit a search query

[1161] A user inputs a question about a government service into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures this query and sends it to the server.

[1162] Query Analysis

[1163] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text.

[1164] Search for related information

[1165] The server uses the extracted keywords to search for information in multiple government service databases and related websites, and uses APIs and web scraping technology to collect data from reliable sources.

[1166] Information collection and filtering

[1167] The server analyzes the acquired information and collects highly relevant information. The filtering process removes unnecessary information based on the reliability and freshness of the information.

[1168] Generate summary information

[1169] Based on the filtered information, the server generates a summary. It uses natural language generation technology to extract important information and present it in an easy-to-understand format. For example, the following summary is generated for the input "How do I get a resident registration card?"

[1170] Required documents: Identification documents (driver's license, passport, etc.)

[1171] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[1172] Fee: Average 300-500 yen (may vary if applying online)

[1173] Other: Reception hours, location of the counter, etc.

[1174] Summary information notification

[1175] The server sends the generated summary information to the terminal, which then displays it to the user, allowing the user to quickly obtain the necessary information about government services related to the input query.

[1176] Specific examples

[1177] For example:

[1178] User operations

[1179] The user types "Please tell me how to obtain a resident registration card" into the terminal.

[1180] Server-side processing

[1181] 1. The server analyzes the query and extracts the keywords "resident registration card" and "how to obtain."

[1182] 2. The server uses these keywords to search for information from multiple trusted databases and websites.

[1183] 3. The server collects relevant information from the search results and filters out unnecessary information.

[1184] 4. The server summarizes the collected information and presents it in a concise and easy-to-understand format.

[1185] Device behavior

[1186] The terminal displays the summary information sent from the server to the user. The user receives a summary like this:

[1187] How to obtain a resident certificate:

[1188] Required documents: Identification documents (driver's license, passport, etc.)

[1189] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[1190] Fee: Average 300-500 yen (may vary if applying online)

[1191] Other: Reception hours, location of the counter, etc.

[1192] In this way, users can obtain accurate information about government services in a short time.

[1193] The processing flow will be explained below.

[1194] Step 1:

[1195] The user inputs a search query into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card."

[1196] Step 2:

[1197] The device sends the entered search query to the server, which passes the query to the server via the Internet.

[1198] Step 3:

[1199] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain it."

[1200] Step 4:

[1201] The server uses the extracted keywords to access databases related to government services and related official websites to search for information, using APIs and web scraping technology.

[1202] Step 5:

[1203] The server collects the search results, gathering data from multiple sources and verifying their contents.

[1204] Step 6:

[1205] The server filters the collected information, eliminating unnecessary or unreliable information based on its reliability and freshness.

[1206] Step 7:

[1207] The server summarizes the filtered information, using natural language generation techniques to extract key points and present them in a concise, easy-to-understand format.

[1208] Step 8:

[1209] The server sends the generated summary information to the terminal, and data security is ensured using encrypted communication.

[1210] Step 9:

[1211] The terminal displays the received summary information to the user in an easily viewable and organized format using a GUI.

[1212] Step 10:

[1213] Users can quickly understand the information they need by checking the displayed summary, such as the documents, procedures, and fees required to obtain a resident registration card.

[1214] Example 1

[1215] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1216] Existing information search systems for government services often have information scattered across multiple systems, making it difficult for users to efficiently obtain the information they need, making it difficult to make quick decisions. Furthermore, when there is too much information, it takes a long time for users to extract the information they need.

[1217] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1218] In this invention, the server includes means for a user to input a search query, means for analyzing the search query and extracting keywords, means for searching databases and websites for related information using the extracted keywords, means for collecting highly relevant information from the search results and filtering the information based on reliability and freshness, and means for generating summary information based on the filtered related information, thereby enabling users to centrally search distributed administrative service information and efficiently obtain reliable and up-to-date information.

[1219] A "search query" refers to a question or keyword that a user enters into a system to obtain information.

[1220] "Keywords" refers to important words or phrases extracted from a search query and used to retrieve related information.

[1221] A "database" refers to a collection of information that is systematically organized and made available for efficient search and reference.

[1222] "Website" means a collection of information pages on the Internet that provide information on a particular subject.

[1223] "Filtering" refers to the process of removing unnecessary information from collected information based on criteria such as reliability and freshness.

[1224] A "generative AI model" refers to an algorithm or program that uses artificial intelligence techniques to generate new information based on input data.

[1225] "Summary information" refers to information that has been filtered and concisely summarized by extracting only the important points.

[1226] "Notification" refers to the process of presenting system-generated summary information to the user.

[1227] The system according to the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. A specific embodiment of this system will be described below.

[1228] Enter and submit a search query

[1229] A user uses their own device (PC, smartphone, tablet, etc.) to input a question about a government service. For example, they input a query such as "Please tell me how to obtain a resident registration card" into the input field of the device. The device captures this input query and sends it to a server via the Internet.

[1230] Receiving and parsing queries

[1231] The server passes the received query to a natural language processing engine (e.g., SpaCy, NLTK) for morphological analysis. As a result, keywords such as "resident registration card" and "how to obtain" are extracted from the query. At the same time, contextual analysis is performed to determine the type of information the user is looking for.

[1232] Examples:

[1233] User: "Please tell me how to obtain a resident registration card."

[1234] Terminal: Sends query to server

[1235] Server: Extract the keywords "resident certificate" and "acquisition method"

[1236] Search for related information

[1237] The server searches for information from multiple government service databases and related websites based on the extracted keywords, by querying the database using RESTful APIs and by using web scraping techniques (e.g., BeautifulSoup) to collect data from websites.

[1238] Examples:

[1239] Server: Sends a query "How to obtain a resident registration card" to the administrative service database API

[1240] Server: Uses web scrapers to gather information from trusted sites

[1241] Information collection and filtering

[1242] The server filters the information collected from the search results, evaluating the information based on its reliability, freshness, and relevance, and removing unnecessary information. This filtering process includes evaluating the reliability of the source and checking the most recent update date.

[1243] Examples:

[1244] Server: Classifies the data obtained from the search results and extracts only the most up-to-date and reliable information

[1245] Server: Remove unnecessary information (duplicates and old information)

[1246] Generate summary information

[1247] The server generates summary information based on the filtered information using a generative AI model (e.g., OpenAI's GPT-3), writes summary instructions in a prompt, and analyzes and verifies the generated summary.

[1248] Examples:

[1249] Server: Send the summary of "Please tell me how to obtain a resident registration card" as a prompt to the generative AI model

[1250] Generative AI model: Generates summary text. Required documents: Personal identification (driver's license, passport, etc.); Acquisition method: Application at city hall, by mail, or online application; Fee: Average 300 to 500 yen.

[1251] Server: Validate the generated summary and adjust it if necessary

[1252] Summary information notification

[1253] The server then sends the generated summary information to the terminal, which then displays it to the user. This allows the user to quickly and centrally search for dispersed administrative service information and efficiently obtain the most reliable and up-to-date information.

[1254] Examples:

[1255] Server: Sends summary information to the terminal

[1256] Terminal: Display the received summary information to the user. "How to obtain a resident registration certificate: Required documents: Personal identification document (driver's license, passport, etc.); How to obtain: Apply at the city hall, by mail, or online; Fee: Average 300 to 500 yen."

[1257] In this way, the system can quickly provide reliable, up-to-date information on government services based on the search query entered by the user.

[1258] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1259] Step 1:

[1260] A user uses their own terminal to input a question about a government service. For example, they might input, "Please tell me how to obtain a resident registration card." The input data is a text query. The terminal captures this input query and sends it to a server via the Internet. The output is a text query received by the server.

[1261] Step 2:

[1262] The server passes the received query to a natural language processing engine (e.g., SpaCy, NLTK) for morphological and contextual analysis. At this stage, the input query is broken down into keywords such as "resident registration card" and "how to obtain it." The input is the text data of the query, and the output is a set of extracted keywords.

[1263] Step 3:

[1264] The server searches for information from multiple government service databases and related websites based on the extracted keywords. This is done using RESTful API calls and web scraping techniques (e.g., BeautifulSoup). The input is a set of keywords, and the output is a dataset of related information obtained as search results.

[1265] Step 4:

[1266] The server filters the information collected from the search results. At this stage, the reliability, freshness, and relevance of the information are evaluated, and unnecessary information is removed. For example, if the same information appears multiple times or if the information is outdated, it is filtered. The input is a dataset of search results, and the output is filtered, highly reliable information data.

[1267] Step 5:

[1268] The server generates summary information using a generative AI model (e.g., OpenAI's GPT-3) based on the filtered information. The server writes summary instructions in a prompt and passes it to the generative AI model. The input is the filtered information and the prompt, and the output is the generated summary.

[1269] Step 6:

[1270] The server sends the generated summary information to the terminal, which displays this information to the user. This allows the user to quickly and centrally search for dispersed administrative service information and efficiently obtain reliable, up-to-date information. The input is summary information, and the output is the information displayed to the user.

[1271] In this way, each processing step works together with specific operations, realizing efficient and highly reliable information provision.

[1272] (Application example 1)

[1273] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1274] In conventional shopping, users must browse multiple online shopping sites to obtain information about the product they want to purchase, checking the information on each site. This takes time and effort, placing a particular burden on beginners and the elderly. Furthermore, the reliability and freshness of the information available varies, making it difficult to determine which information is the most up-to-date and trustworthy. To solve these problems, a system is needed that provides highly reliable and up-to-date summary information in a unified manner.

[1275] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1276] In this invention, the server includes means for a user to input a shopping search query, means for analyzing the shopping search query and extracting product-related keywords, means for searching for product information from online shopping sites using the extracted product-related keywords, means for collecting and filtering product information details and price information from the search results, and means for generating summary information based on the collected product information and price information, thereby enabling a user to obtain reliable and up-to-date product summary information in a short amount of time.

[1277] A "means for a user to enter a search query" is a device or interface through which a user can enter a question about a product they wish to purchase.

[1278] The "means for analyzing the search query and extracting keywords" refers to a technology or algorithm that extracts important words or phrases from the search query entered by the user.

[1279] The "means for searching for related information using the extracted keywords" refers to algorithms or techniques that use the extracted important words or phrases to find related information from various sources.

[1280] The "means for collecting and filtering highly relevant information from the search results" refers to a method or technology for selecting particularly relevant information from the search results and eliminating unnecessary information.

[1281] The "means for generating summary information based on the collected information" refers to a method or technology for concisely summarizing the collected information and providing it to the user in an easily understandable format.

[1282] The "means for notifying the user of the summary information" refers to an interface or technology for transmitting the generated summary information to the user's device and displaying it.

[1283] A "means for a user to enter a shopping search query" is a device or interface through which a user can enter a question about a product they wish to purchase.

[1284] The "means for analyzing the shopping-related search query and extracting product-related keywords" refers to a method or technology for extracting important product-related words and phrases from shopping-related questions entered by users.

[1285] "Means for searching for product information from online shopping sites using keywords related to the extracted products" refers to a technology that uses important words and phrases related to the extracted products to find relevant product information from multiple online shopping sites.

[1286] "Means for collecting and filtering detailed product information and price information from the search results" refers to a method or technology for collecting detailed product information and price information from the search results and removing unnecessary information.

[1287] The "means for generating summary information based on the collected product information and price information" refers to a method or technology for concisely summarizing the collected product-related details and price information and providing it to the user in an easy-to-understand format.

[1288] The system according to the present invention allows users to input shopping search queries and provides related product information in a unified manner. The processing of the program of this system will be explained using specific examples.

[1289] System configuration

[1290] The system consists of a terminal used by the user, a server that processes the data, and various software components that collect, filter, and summarize the information.

[1291] Program processing overview

[1292] The system consists of the following main steps:

[1293] User operations and device behavior

[1294] The user types a shopping question into the device, for example, "How do I buy a Nintendo Switch?" This query is captured by the device and sent to the server.

[1295] Query Analysis

[1296] The server analyzes the received query and uses natural language processing technology to extract keywords such as "Nintendo Switch" and "how to purchase" from the input text. The specific software used includes transformers, a Python natural language processing library.

[1297] Search for product information

[1298] The server uses the extracted keywords to search for product information on multiple online shopping sites. It uses APIs and web scraping techniques, such as BeautifulSoup and requests, to collect data from reliable sources.

[1299] Information collection and filtering

[1300] The server analyzes the acquired information and collects relevant product and price information. The filtering process eliminates unnecessary information based on the reliability and freshness of the information.

[1301] Generate summary information

[1302] Based on the filtered information, the server generates summary information. It uses a generative AI model to concisely summarize the extracted important information. Specifically, it uses the transformers library.

[1303] Summary information notification

[1304] The server sends the generated summary information to the terminal, which displays it to the user, allowing the user to quickly obtain important information about the product they want to purchase.

[1305] Specific examples

[1306] User actions and query input

[1307] The user types "How do I purchase a Nintendo Switch?" into the device. Based on this query, the system starts a series of processes.

[1308] Query analysis and product search

[1309] The server analyzes the query and extracts the keywords "Nintendo Switch" and "purchase method," then collects product information from multiple online shopping sites.

[1310] Collecting and summarizing information

[1311] Based on the collected product and price information, important data is extracted and a summary is generated. For example, the following summary is generated:

[1312] Information on purchasing the Nintendo Switch: The Nintendo Switch console is available for purchase for 32,978 yen, and the Nintendo Switch Lite is available for purchase for 21,970 yen. You can purchase them from the links below.

[1313] Summary information notification

[1314] The generated summary information is sent to the terminal and displayed to the user. The user receives a summary that looks like this:

[1315] Information on purchasing the Nintendo Switch: The Nintendo Switch console is available for purchase for 32,978 yen, and the Nintendo Switch Lite is available for purchase for 21,970 yen. You can purchase them from the links below.

[1316] In this way, users can easily obtain reliable product information in a short time.

[1317] With the above-described configuration and method, the system of the present invention can quickly provide accurate information in response to user queries regarding shopping.

[1318] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1319] Step 1:

[1320] A user enters a shopping-related search query into their device, for example, "How do I buy a Nintendo Switch?" This query becomes input to the system.

[1321] Step 2:

[1322] The terminal captures the entered query and sends it to the server, where the input is the user's query and the output is the query sent to the server.

[1323] Step 3:

[1324] The server analyzes the received query. It uses natural language processing technology to extract keywords such as "Nintendo Switch" and "how to purchase" from the input query. For example, it uses transformers, a Python natural language processing library, to perform the analysis.

[1325] Step 4:

[1326] The server uses the extracted keywords to search for product information from multiple online shopping sites. For example, it uses requests to retrieve pages from online shopping sites, analyzes them with BeautifulSoup, and collects product and price information. The input here is the extracted keywords, and the output is a list of the collected product information.

[1327] Step 5:

[1328] The server filters the collected product information, eliminating unnecessary information based on reliability and freshness. For example, reliability is evaluated based on collected product reviews and update dates, and only the necessary data is extracted. The input is the collected product information, and the output is the filtered product information.

[1329] Step 6:

[1330] The server generates summary information based on the filtered information. Here, a generative AI model is used to concisely summarize important information. For example, the transformers library is used to generate the summary information. The input is the filtered product information, and the output is the summarized information.

[1331] Step 7:

[1332] The server sends the generated summary information to the terminal. The input is the summarized information, and the output is the summary information sent to the terminal.

[1333] Step 8:

[1334] The terminal displays the received summary information to the user, allowing the user to quickly obtain important information about the product they are planning to purchase. The input is the summary information sent from the server, and the output is the content displayed to the user.

[1335] This allows the system to provide a summary of reliable and up-to-date information in response to a user's shopping search query through a series of processes.

[1336] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1337] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions and optimizes the information provided based on those emotions. The program processing of this system is explained below with specific examples.

[1338] Enter and submit a search query

[1339] A user inputs a question about a government service into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures this query and recognizes the user's emotion using an emotion engine. The device then transmits the query and emotion information to the server.

[1340] Query Analysis

[1341] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text. It also uses an emotion engine to analyze the user's emotions and recognize their current emotional state.

[1342] Search for related information

[1343] The server then uses the extracted keywords to access databases related to government services and related official websites to search for information, using APIs and web scraping technology. Furthermore, it adjusts the filtering criteria for search results based on the user's emotions. For example, if the user appears anxious, it will prioritize detailed and reassuring information.

[1344] Information collection and filtering

[1345] The server collects the search results. In doing so, it gathers data from multiple sources and checks their contents. When filtering the collected information, it eliminates unnecessary information based on its reliability and freshness. It also sets filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes information that is concise and can be understood quickly.

[1346] Generate summary information

[1347] The server generates a summary based on the filtered information. It uses natural language generation technology to extract key points and present them in an easy-to-understand format. The server also adjusts the presentation and format of the summary, taking into account the user's emotional state, as recognized by the emotion engine. For example, if the user is anxious, the server generates a summary in a gentle tone that provides a sense of security.

[1348] Summary information notification

[1349] The server sends the generated summary information to the terminal. Data security is ensured using encrypted communication. The terminal displays this information to the user. Furthermore, the display method is also adjusted according to the user's emotional state.

[1350] Specific examples

[1351] For example:

[1352] User operations

[1353] The user types into the terminal, "Please tell me how to obtain a resident registration card." At this time, the emotion engine recognizes that the user looks anxious.

[1354] Server-side processing

[1355] 1. The server analyzes the query and extracts the keywords "resident registration card" and "how to obtain."

[1356] 2. The server recognizes that the user is anxious based on the emotional information from the emotion engine.

[1357] 3. The server uses these keywords to search for information from multiple trusted databases and websites, prioritizing detailed and reassuring information to allay concerns.

[1358] 4. The server collects reliable information from the search results and filters out unnecessary information.

[1359] 5. The server summarizes the collected information and generates a summary in a warm tone to ease anxiety.

[1360] Device behavior

[1361] The terminal displays the summary information sent from the server to the user. To ease the user's anxiety, the information is organized in an easy-to-read format and presented in a reassuring manner. The user receives a summary like this:

[1362] How to obtain a resident certificate:

[1363] Required documents: Identification documents (driver's license, passport, etc.)

[1364] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[1365] Fee: Average 300-500 yen (may vary if applying online)

[1366] Other: Reception hours, location of the counter, etc.

[1367] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[1368] In this way, users can obtain accurate and reassuring information about government services in a short amount of time.

[1369] The processing flow will be explained below.

[1370] Step 1:

[1371] The user inputs a search query into their device. For example, they input a query such as "Please tell me how to obtain a resident registration card." The device captures the input query.

[1372] Step 2:

[1373] The emotion engine recognizes the user's emotions from their voice, facial expressions, etc. The device then sends the recognized emotion information along with the query to the server.

[1374] Step 3:

[1375] The server analyzes the received query and uses natural language processing technology to extract keywords such as "resident registration card" and "how to obtain" from the input text. At the same time, it analyzes the user's emotions, which are recognized by an emotion engine.

[1376] Step 4:

[1377] The server then searches for information by accessing databases related to government services and related official websites based on the extracted keywords, using APIs and web scraping technology to obtain relevant information.

[1378] Step 5:

[1379] The server collects the search results, gathers reliable data from multiple sources, and verifies their contents.

[1380] Step 6:

[1381] The server filters the collected information. The filtering process eliminates unnecessary information based on the reliability and freshness of the information. It also adjusts the filtering criteria based on the user's emotional state. For example, if the user seems anxious, it will prioritize detailed and reassuring information.

[1382] Step 7:

[1383] The server generates a summary based on the filtered information. It uses natural language generation technology to extract key points and present them in an easy-to-understand format. The server adjusts the presentation of the summary based on the user's emotional state, as recognized by the emotion engine. For example, if the user appears anxious, it uses a calm, reassuring tone.

[1384] Step 8:

[1385] The server sends the generated summary information to the terminal, and uses encrypted communication to ensure data security.

[1386] Step 9:

[1387] The device then displays the summary information to the user. The display method is also adjusted according to the user's emotions. For example, if a user is feeling anxious, a design and color scheme that visually conveys a sense of security is used.

[1388] Step 10:

[1389] Users can quickly understand the information they need by checking the summary displayed. Information on necessary procedures and documents is concisely explained, allowing them to act with confidence.

[1390] Examples:

[1391] For example, if a user says, "Please tell me how to obtain a resident registration card," and looks anxious, this emotion is recognized. Based on this information, the server prioritizes collecting detailed and reassuring information on how to obtain a resident registration card, and generates summary information in a calm manner. The user can then reassure themselves by checking the information displayed on the device and following the instructions to proceed with the procedure.

[1392] Example 2

[1393] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1394] Conventional information search systems provide relevant information in response to a user's search query, but lack the ability to recognize the user's emotional state and provide optimal information based on that emotion. This makes it difficult for users to quickly and confidently obtain the information they need. Another issue is the insufficient filtering of information based on its reliability and freshness. The present invention aims to solve these problems and provide a system that provides optimal information based on the user's emotions.

[1395] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1396] In this invention, the server includes a means for recognizing a user's emotion and optimizing information to be provided based on the emotion, a means for analyzing a search query and extracting keywords, and a means for searching for related information using the extracted keywords, thereby enabling the provision of optimal information according to the user's emotion.

[1397] "User" refers to a person who utilizes the System to enter a search query and retrieve information.

[1398] A "search query" refers to a question or keyword that a user enters to obtain information.

[1399] "Terminal" refers to an electronic device through which a user enters search queries and receives information.

[1400] "Server" means a central processing unit for analyzing search queries and providing relevant information.

[1401] An "emotion engine" is a technology that recognizes a user's emotions and optimizes the information provided based on that emotional information.

[1402] "Natural language processing technology" refers to the technology that allows a computer to understand and analyze input text data.

[1403] "Keywords" refer to important words in information retrieval extracted from a search query.

[1404] "Relevant information" refers to information that is relevant to the purpose a user is trying to obtain through a search query.

[1405] "Filtering" refers to the process of removing unnecessary parts from acquired information, leaving only useful information.

[1406] "Natural language generation technology" refers to the technology of generating sentences in a natural way based on large amounts of data.

[1407] "Summary information" refers to information that extracts important points from collected information and summarizes them concisely.

[1408] The system of the present invention searches for information about government services based on a search query entered by a user, filters and summarizes the information, and provides it to the user. Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions and optimizes the information provided based on the user's emotions.

[1409] Enter and submit a search query

[1410] A user inputs a question about a government service into their own device. A specific example is the query "Please tell me how to obtain a resident registration card." The device captures this query and recognizes the user's emotions using an emotion engine. Emotion analysis technology, for example, can be used as the emotion engine. The captured query and emotion information are sent to the server.

[1411] Query Analysis

[1412] The server analyzes the received query using natural language processing techniques (e.g., BERT and spaCy) to extract keywords such as "resident registration card" and "how to obtain" from the input text. It also analyzes the user's emotional state using an emotion engine and recognizes the current emotional state as a cyclic variable.

[1413] Search for related information

[1414] The server then uses the extracted keywords to access databases of government services and related official websites to retrieve information. It uses APIs and web scraping technologies (e.g., BeautifulSoup and Scrapy). It also adjusts the filtering criteria for search results based on the user's emotional state. For example, if the user appears anxious, it prioritizes detailed and reassuring information.

[1415] Information collection and filtering

[1416] The server organizes the search results and integrates data from multiple sources. It filters information based on reliability and freshness. It also flexibly adjusts the filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes concise and easy-to-understand information.

[1417] Generate summary information

[1418] The server generates a summary based on the filtered information. It uses natural language generation technology (e.g., GPT-3) to extract key points and translate them into an easy-to-understand format. The generated summary takes into account the user's emotional state and adjusts its expression and tone accordingly. For example, a summary may be written in a gentler tone to alleviate anxiety.

[1419] Summary information notification

[1420] The server sends the generated summary information to the device. Data security is ensured using encryption technologies such as SSL / TLS for communication. The device then displays the received summary information to the user, displaying it according to their emotional state.

[1421] Specific examples

[1422] For example, if a user types "Please tell me how to get a resident registration card" into the terminal, the emotion engine will recognize that the user looks anxious. The following process will be performed on the server side:

[1423] 1. The server analyzes and extracts the keywords "resident registration card" and "how to obtain."

[1424] 2. Based on the user's emotional information, prioritize collecting detailed information to alleviate anxiety.

[1425] 3. Filter reliable information and filter out unnecessary information.

[1426] 4. Generate summary information in a gentle tone and add a reassuring message.

[1427] The terminal will display the generated summary information to the user as follows:

[1428] How to obtain a resident certificate:

[1429] Required documents: Identification documents (driver's license, passport, etc.)

[1430] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[1431] Fee: Average 300-500 yen (may vary if applying online)

[1432] Other: Reception hours, location of the counter, etc.

[1433] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[1434] This allows users to quickly obtain accurate and reliable information about government services.

[1435] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1436] Step 1: Enter and submit a search query

[1437] The user inputs a question about government services into the terminal. Specifically, the terminal receives the text data entered by the user, "Please tell me how to obtain a resident registration card." The terminal captures this query. The emotion engine analyzes the input query and recognizes the user's emotional state (e.g., anxiety). The captured query and emotion information are sent to the server. The input is the search query and the user's emotional state, and the output is the data sent to the server.

[1438] Step 2: Parsing the query

[1439] The server analyzes the query based on the received data. Specifically, it analyzes the query using natural language processing technology (e.g., BERT) to extract keywords such as "resident registration card" and "how to obtain it." The server also analyzes the emotional information provided by the emotion engine to recognize the current emotional state. The input is the search query and emotional information, and the output is the extracted keywords and the recognition result of the emotional state.

[1440] Step 3: Find related information

[1441] The server accesses databases related to government services and related official websites based on keywords to obtain information. Specifically, it uses APIs and web scraping technologies (e.g., BeautifulSoup and Scrapy) to collect relevant information. It adjusts search criteria based on the user's emotions, and prioritizes detailed and reassuring information for anxious users. The input is the extracted keywords and emotional state, and the output is the obtained related information.

[1442] Step 4: Collecting and filtering information

[1443] The server organizes the collected search results. Specifically, it integrates data from multiple sources and filters them based on reliability and freshness. Furthermore, it flexibly adjusts the filtering criteria according to the user's emotional state. For example, if the user is in a hurry, it prioritizes concise and easy-to-understand information. The input is the retrieved relevant information and the user's emotional state, and the output is the filtered information.

[1444] Step 5: Generate summary information

[1445] The server generates summary information based on the filtered information. Specifically, it uses natural language generation technology (e.g., GPT-3) to extract key points and convert them into an easy-to-understand format. The generated summary adjusts its expression and tone to take into account the user's emotions. For anxious users, it generates a summary that includes reassuring words. The input is the filtered information and emotional state, and the output is the generated summary information.

[1446] Step 6: Notification of summary information

[1447] The server sends the generated summary information to the terminal. Specifically, encryption technology such as SSL / TLS is used for communication to ensure data security. The terminal displays the received summary information to the user and selects a display method based on the user's emotional state. The input is the generated summary information, and the output is the screen display viewed by the user.

[1448] (Application example 2)

[1449] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1450] When searching for information about government services, it is difficult to provide optimal information based on the user's emotions. Specifically, if a user is feeling anxious or impatient, it is necessary to obtain and provide information in a manner that corresponds to that emotion. However, many conventional systems provide information uniformly without considering the user's emotions, which results in the problem of not being able to obtain optimal information for the user. Furthermore, there is no established method for easily obtaining information in an in-car environment, such as through voice input.

[1451] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1452] In this invention, the server includes: a means for a user to input a search query; a means for analyzing the search query and extracting keywords; a means for searching for related information using the extracted keywords; a means for collecting and filtering highly relevant information from the search results; a means for generating summary information based on the collected information; a means for notifying the user of the summary information; an emotion engine means for recognizing the user's emotions; and a means for optimizing the filtering criteria for the information and the expression of the summary information based on the emotion information recognized by the emotion engine means. This makes it possible to provide information in an optimal form according to the user's emotional state. For example, in an in-vehicle environment of an autonomous vehicle, voice input can be accepted through smart glasses, and appropriate information can be provided quickly and reassuringly.

[1453] - "Means by which a user enters a search query" refers to an interface through which a user can enter a question about a government service, including a voice input device, keyboard, or touchscreen.

[1454] The "means for analyzing the search query and extracting keywords" is a mechanism for analyzing the input search query using natural language processing technology and identifying important keywords.

[1455] The "means for searching for related information using the extracted keywords" is a system for obtaining information from databases and official websites related to administrative services based on the extracted keywords.

[1456] The "means for collecting and filtering highly relevant information from the search results" refers to a procedure for excluding unnecessary information from the acquired information based on its reliability and freshness, and selecting highly relevant information.

[1457] The "means for generating summary information based on the collected information" refers to a method for extracting important points from filtered information and summarizing them in an easy-to-understand manner using natural language generation technology.

[1458] The "means for notifying the user of the summary information" is a mechanism for displaying the generated summary information on the user's terminal, and is provided visually through smart glasses or a smartphone.

[1459] The "emotion engine means for recognizing the user's emotions" is an engine for analyzing the emotional state from the input query or the user's voice and acquiring emotional information.

[1460] The "means for optimizing the filtering criteria for the information and the expression of summary information based on the emotional information recognized by the emotion engine means" refers to a system for adjusting the method and content of information provision in accordance with the emotional information, and providing information in a form that is optimal for the user.

[1461] "System" refers to the overall mechanism that is made up of a combination of multiple technological elements, and in this case refers to the infrastructure for providing users with information about government services in the most optimal way.

[1462] MODE FOR CARRYING OUT THE INVENTION

[1463] This invention relates to a system for enabling a user in an autonomous vehicle to obtain information about government services through voice input and optimize that information using an emotion recognition engine. The system includes a voice input device, an emotion recognition engine, natural language processing technology, an information search engine, a filtering system, and a user notification device.

[1464] System Overview

[1465] In this system, when a user uses smart glasses or other voice input devices to ask a question about government services, the voice input is converted into text and sent to a server. The server analyzes the input text and extracts important keywords. Based on the extracted keywords, it searches for related information from government service databases and websites. In addition, an emotion recognition engine recognizes the user's emotions and optimizes the information filtering criteria and summary information presentation based on those emotions.

[1466] Hardware and software details

[1467] The server uses the following software and hardware:

[1468] Speech Recognition: Use the speech_recognition library to capture voice input from a microphone, such as smart glasses, and convert it to text.

[1469] Emotion recognition: Uses the emotion recognition model (pipeline('sentiment-analysis')) from the transformers library.

[1470] Information retrieval: Using APIs and web scraping technology, information is retrieved from government service databases and websites.

[1471] Information filtering: Filter information based on reliability and freshness, and prioritize information based on emotional information.

[1472] Summary Generation: Summarize the filtered information using a summary generation model from the transformers library.

[1473] After receiving voice input from the user, the server performs the following actions:

[1474] Speech recognition and text conversion

[1475] The server captures the voice input from the user through the smart glasses and converts it into text using the speech_recognition library. For example, when a user inputs "Please tell me how to obtain a resident registration card," the voice is converted into text.

[1476] emotion recognition

[1477] The converted text is sent to an emotion recognition engine, where the emotional state is analyzed using emotion recognition models from the transformers library. For example, if the user is feeling anxious, it is recognized as "anxious."

[1478] Information Search and Filtering

[1479] Based on the extracted keywords, the server retrieves information from government service databases and official websites. Based on emotional information, priority is given to information that gives a sense of security and can be quickly understood. For example, information such as "how to obtain a resident registration card," "required documents," "how to obtain it," and "fees" is searched.

[1480] Summary generation and notification

[1481] The acquired information is summarized using the transformers library, and the representation is optimized based on the emotion, and then displayed on the smart glasses. For example, the following summary is generated:

[1482] How to obtain a resident certificate:

[1483] Required documents: Identification documents (driver's license, passport, etc.)

[1484] How to obtain: Apply at your local municipal office, apply by mail, or apply online

[1485] Fee: Average 300-500 yen (may vary if applying online)

[1486] Other: Reception hours, location of the counter, etc.

[1487] Please go without worry. If you have any concerns, please contact the consultation desk at your local government office.

[1488] Prompt Sentence Examples

[1489] Here are some examples of emotion recognition prompts for input queries:

[1490] Identify the emotions in the following sentences:

[1491] I would like to go to the local government office in my area to get a resident registration certificate. What documents and procedures are required?

[1492] This system allows users to easily obtain information about government services while on the move, and provides reassuring information that is optimized according to their emotions.

[1493] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1494] Program processing steps

[1495] Step 1:

[1496] The user inputs voice through the smart glasses. For example, the user might ask, "Please tell me how to obtain a resident registration card." The smart glasses capture this voice and send it to the server. The input is the user's voice data, and the output is the voice data sent to the server.

[1497] Step 2:

[1498] The server converts the received voice data into text using the speech_recognition library. In this step, the voice data is converted into text data. Specifically, the voice recognition model analyzes the voice waveform and outputs the corresponding text, "Please tell me how to obtain a resident registration card."

[1499] Step 3:

[1500] The server sends the text data to the emotion recognition engine, which analyzes the user's emotions using the emotion recognition model in the Transformers library. The input is text data, and the output is emotional information (e.g., "anxiety"). Specifically, the emotion recognition model analyzes the user's emotional state from the text content and assigns an emotion label.

[1501] Step 4:

[1502] The server uses natural language processing technology to extract important keywords from the input text data. For example, the keywords "resident registration card" and "how to obtain" are extracted. The input is emotional information and text data, and the output is a keyword list. Specifically, the keyword extraction model analyzes the text and lists important words.

[1503] Step 5:

[1504] The server uses the extracted keywords to search for relevant information from government service databases and official websites. The input is a list of keywords, and the output is search results. Specifically, APIs and web scraping technologies are used to obtain data from sources.

[1505] Step 6:

[1506] The server filters the search results based on reliability and freshness, as well as on recognized emotional information. The input is the search results and emotional information, and the output is the filtered information. Specifically, the filtering algorithm eliminates unreliable information and prioritizes it according to its emotions.

[1507] Step 7:

[1508] The server generates a summary based on the filtered information. The summary generation model from the transformers library is used to generate the summary. The input is the filtered information, and the output is the summary information. Specifically, the summary generation model extracts important information and summarizes it using emotion-based expressions.

[1509] Step 8:

[1510] The summary information is sent to the user's smart glasses using encrypted communication. The input is the summary information, and the output is the text displayed on the smart glasses. Specifically, the server encrypts the summary and sends it to the smart glasses through a communication protocol.

[1511] Step 9:

[1512] The smart glasses display summary information to the user. The display method is also adjusted according to the user's emotional state. The input is summary information received from the server, and the output is visual information provided to the user. Specifically, the smart glasses display the information with appropriate font size, color, and layout.

[1513] In this way, users can easily obtain information about government services while on the move, and can obtain reassuring information that is optimized according to their emotions.

[1514] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1515] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1516] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1517] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1518] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1519] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1520] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1521] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1522] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1523] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1524] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1525] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1526] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1527] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1528] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1529] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1530] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1531] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1532] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1533] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1534] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1535] The following is further disclosed regarding the above embodiment.

[1536] (Claim 1)

[1537] a means for a user to input a search query;

[1538] means for analyzing the search query and extracting keywords;

[1539] a means for searching for related information using the extracted keywords;

[1540] means for collecting and filtering highly relevant information from the search results;

[1541] means for generating summary information based on the collected information;

[1542] means for notifying a user of the summary information;

[1543] A system including:

[1544] (Claim 2)

[1545] The system according to claim 1, wherein the reliability and freshness of information are used as criteria when filtering the search results.

[1546] (Claim 3)

[1547] 10. The system of claim 1, wherein natural language generation techniques are used to generate the summary of the information.

[1548] "Example 1"

[1549] (Claim 1)

[1550] a means for a user to input a search query;

[1551] means for analyzing the search query and extracting keywords;

[1552] a means for searching for related information from a database or a website using the extracted keywords;

[1553] means for collecting highly relevant information from the search results and filtering the information based on reliability and freshness;

[1554] means for generating summary information based on the filtered related information;

[1555] means for notifying a user of the summary information;

[1556] A system including:

[1557] (Claim 2)

[1558] The system according to claim 1, wherein the reliability and freshness of information are used as criteria when filtering the search results.

[1559] (Claim 3)

[1560] The system according to claim 1, wherein the summary information is generated using a generative AI model when generating the summary of the information.

[1561] "Application Example 1"

[1562] (Claim 1)

[1563] a means for a user to input a search query;

[1564] means for analyzing the search query and extracting keywords;

[1565] a means for searching for related information using the extracted keywords;

[1566] means for collecting and filtering highly relevant information from the search results;

[1567] means for generating summary information based on the collected information;

[1568] means for notifying a user of the summary information;

[1569] a means for a user to input a shopping search query;

[1570] means for analyzing the shopping-related search query and extracting keywords related to products;

[1571] a means for searching for product information from an online shopping site using keywords related to the extracted product;

[1572] means for collecting and filtering product details and price information from the search results;

[1573] means for generating summary information based on the collected product information and price information;

[1574] A system including:

[1575] (Claim 2)

[1576] The system according to claim 1, wherein the reliability and freshness of information are used as criteria when filtering the search results.

[1577] (Claim 3)

[1578] 10. The system of claim 1, wherein natural language generation techniques are used to generate the summary of the information.

[1579] "Example 2: Combining Emotion Engines"

[1580] (Claim 1)

[1581] a means for a user to input a search query;

[1582] means for analyzing the search query and extracting keywords;

[1583] a means for searching for related information using the extracted keywords;

[1584] means for collecting and filtering highly relevant information from the search results;

[1585] means for generating summary information based on the collected information;

[1586] A means for recognizing a user's emotion and optimizing information provided based on the emotion;

[1587] means for notifying a user of the summary information;

[1588] A system including:

[1589] (Claim 2)

[1590] The system according to claim 1, wherein the reliability and freshness of information are used as criteria when filtering the search results.

[1591] (Claim 3)

[1592] 10. The system of claim 1, wherein natural language generation techniques are used to generate the summary of the information.

[1593] "Application example 2 when combining emotion engines"

[1594] (Claim 1)

[1595] a means for a user to input a search query;

[1596] means for analyzing the search query and extracting keywords;

[1597] a means for searching for related information using the extracted keywords;

[1598] means for collecting and filtering highly relevant information from the search results;

[1599] means for generating summary information based on the collected information;

[1600] means for notifying a user of the summary information;

[1601] emotion engine means for recognizing the emotion of a user;

[1602] means for optimizing the filtering criteria of the information and the expression of the summary information based on the emotion information recognized by the emotion engine means;

[1603] A system including:

[1604] (Claim 2)

[1605] The system according to claim 1, wherein the reliability and freshness of information are used as criteria when filtering the search results.

[1606] (Claim 3)

[1607] 10. The system of claim 1, wherein natural language generation techniques are used to generate the summary of the information. [Explanation of symbols]

[1608] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input a search query; means for analyzing the search query and extracting keywords; a means for searching for related information using the extracted keywords; means for collecting and filtering highly relevant information from the search results; means for generating summary information based on the collected information; means for notifying a user of the summary information; A system including:

2. The system according to claim 1 , wherein the reliability and freshness of information are used as criteria when filtering the search results.

3. 10. The system of claim 1, wherein natural language generation techniques are used to generate the summary of the information.

Images