system

Abstract

Provide a system. [Solution] a means for registering map data including location information data and a plurality of pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; a means for analyzing received search queries based on natural language processing to understand the intent of the queries; a means for searching a database based on the analysis results to obtain related map data and attribute information; means for formatting the acquired information into a format that is easy for the user to understand and transmitting the format to the terminal; means for displaying the received information to a user; 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 recent years, the frequency of disasters has increased, making it essential to quickly gather information, such as information on evacuation shelters and traffic restrictions. Conventional systems require special infrastructure and software to register and search map data and related information in a database, resulting in a lack of responsiveness. Another issue is that it is difficult for users to obtain information in natural language. The present invention aims to solve these problems and provide a system that allows users to quickly and intuitively obtain necessary information in the event of a disaster. [Means for solving the problem]

[0005] The present invention includes a means for registering map data including location information data and multiple attribute information related to the map data in a database, a means for receiving a search query input from a terminal, a means for analyzing the received search query using natural language processing to understand the intent of the query, a means for searching the database based on the analysis result and acquiring related map data and attribute information, and a means for formatting the acquired information in a format that is easy for a user to understand and transmitting it to the terminal. The device also includes a means for displaying the information received by the terminal to the user, allowing the user to quickly and intuitively obtain necessary information based on a search query entered in natural language. Furthermore, the device includes a means for acquiring search results including attribute information such as the location information, address, telephone number, and capacity of the shelter in the case of a search query related to danger level information on a hazard map, and a means for acquiring search results including danger level information for the corresponding area, thereby quickly providing specific disaster response information.

[0006] "Location information data" is information such as longitude and latitude that indicates a specific point on a map.

[0007] "Map data" refers to digital data containing geographical information, including location information for roads, buildings, natural landforms, and the like.

[0008] "Attribute information" is detailed information associated with map data, such as addresses, danger levels on hazard maps, and disaster response information for evacuation shelters.

[0009] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[0010] A "terminal" is a device used by a user that provides an interface for inputting and displaying search queries.

[0011] A "search query" refers to a question or request that a user enters to obtain the information they need.

[0012] "Natural language processing" is a technology that uses computers to analyze and understand human language.

[0013] "Analysis" is the act of breaking down the entered search query to understand its meaning and structure.

[0014] "Intent" refers to the information or goal a user is trying to obtain through a search query.

[0015] "Retrieval" is the act of receiving search results from a database.

[0016] "Formatting" refers to converting acquired data into a format that is easy for the user to understand.

[0017] "Display" is the act of outputting formatted information to a terminal screen.

[0018] An "evacuation shelter" is a place where people gather to temporarily ensure safety during a disaster.

[0019] A "hazard map" is a map that shows the risk of natural disasters occurring.

[0020] "Danger level information" is information that indicates the probability of occurrence of a natural disaster and the degree of danger in a specific location. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] This invention relates to a system that allows users to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. Specifically, map data and multiple related attribute information are registered in a database, and the search query is analyzed using natural language processing to retrieve and display related information, enabling the rapid provision of information in the event of a disaster.

[0043] Overview of the system's programs and their processing

[0044] Server Roles and Operations

[0045] Registering map data and attribute information:

[0046] The server registers map data and related attribute information (address, hazard map danger level, evacuation shelter disaster response information, etc.) in a database, enabling quick responses to search queries.

[0047] Receiving and parsing search queries:

[0048] The server receives the search query entered from the device. The received query is passed to a natural language processing engine for analysis. In this analysis step, the intent of the query and important keywords are extracted.

[0049] Searching the database and retrieving information:

[0050] Based on the parsed query, the server searches for relevant map data and attribute information in the database. For example, for a query requesting information on "nearby shelters," the server retrieves details such as the location, address, phone number, and capacity of the nearest shelter.

[0051] Formatting and sending information:

[0052] The acquired information is formatted in a way that is easy for the user to understand, and the formatted information is sent to the terminal as an HTTP response.

[0053] Terminal roles and processing

[0054] Getting and sending user input:

[0055] The device receives a search query from the user. For example, the user types, "Where is the nearest evacuation shelter?" The device sends this query to the server.

[0056] Receiving and displaying search results:

[0057] The terminal receives the HTTP response from the server. The received search results are displayed in the user interface. For example, a list of evacuation shelters is displayed, and their details (addresses, phone numbers, etc.) are provided to the user.

[0058] User operation example

[0059] Entering and sending a query: The user enters "Where is the nearest shelter?" into the device and sends it.

[0060] Check the results: Check the shelter information displayed on the device. For example, details such as "Shelter: XX Park, Address: XX City XX Town, Phone Number: 012-345-6789" will be displayed.

[0061] This system quickly and efficiently retrieves and provides relevant information based on natural language queries, demonstrating exceptional effectiveness in gathering information during disasters. Such a system allows users to intuitively and quickly obtain the information they need, enabling them to make quick decisions and take action in emergencies.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] A user enters a search query.

[0065] A user types a search query into a device, for example, "Where are the nearest evacuation centers?"

[0066] Step 2:

[0067] A user submits a search query.

[0068] The user presses the submit button to send the query to the server.

[0069] Step 3:

[0070] The device sends a search query to the server.

[0071] The device generates an HTTP POST request containing the user's input and sends it to the specified endpoint on the server.

[0072] Step 4:

[0073] A server receives a search query.

[0074] The server receives an HTTP POST request from the terminal and obtains the query.

[0075] Step 5:

[0076] The server parses the search query.

[0077] The server passes the received search query to a natural language processing engine, which analyzes the query's intent, extracting important keywords and user intent.

[0078] Step 6:

[0079] The server searches the database.

[0080] The server searches the database based on the analysis results. For example, if the analysis results indicate that the user is searching for a nearby shelter, the server retrieves information about the shelter from the database.

[0081] Step 7:

[0082] The server formats the search results.

[0083] The server formats the data it acquires into a format that is easy for users to understand. For example, it formats information such as the name, address, telephone number, and capacity of the evacuation shelter into a list.

[0084] Step 8:

[0085] The server sends the search results to the terminal.

[0086] The server sends the formatted information to the terminal as an HTTP response.

[0087] Step 9:

[0088] The terminal receives the search results.

[0089] The terminal receives an HTTP response from the server.

[0090] Step 10:

[0091] Your device will display the search results.

[0092] The terminal displays the received search results on a user interface, for example, a list of evacuation shelters is displayed and their details (addresses, telephone numbers, etc.) are provided to the user.

[0093] Step 11:

[0094] The user reviews the search results.

[0095] The user checks the search results displayed on the device and decides on the next action, for example, preparing to go to the nearest evacuation shelter.

[0096] Example 1

[0097] 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."

[0098] There is a lack of means to quickly and intuitively obtain map information and its related attribute information, which is a problem especially in times of disaster, where users are unable to immediately obtain the information they need.There is a need for a system that efficiently provides information necessary in emergencies, such as information on evacuation shelters and hazards.

[0099] 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.

[0100] In this invention, the server includes means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database, means for receiving a search query input from a terminal, means for analyzing the received search query using natural language processing and understanding the intent of the query, means for searching the database based on the analysis result and acquiring related map data and attribute information, means for formatting the acquired information in a format that is easy for the user to understand and transmitting it to the terminal, means for displaying the information received by the terminal to the user, and means for formatting and transmitting data that is effective for quickly providing map information incorporating evacuation shelter information. This enables a user to quickly and intuitively obtain the necessary map data and its attribute information based on a query input in natural language.

[0101] "Location information data" is data that indicates a specific point or area on a map, and includes coordinate information such as latitude and longitude.

[0102] "Map data" is digital data that visually represents geographical information, and includes information on roads, buildings, natural topography, and the like.

[0103] "Attribute information" is additional information related to map data, and includes additional information such as addresses, telephone numbers, facility features and functions, and disaster response information.

[0104] A "database" is a structured electronic file system that systematically stores map data and its associated attribute information, making it easy to search and retrieve.

[0105] A "search query" is a question or keyword that a user inputs into a terminal to obtain the information they need.

[0106] "Means for receiving" refers to the function or method by which the server receives the search query sent from the terminal.

[0107] "Natural language processing" is a technology that allows computers to understand and process human language, and includes text analysis, keyword extraction, and context understanding.

[0108] "Means for analyzing" refers to a method of analyzing the content of a received search query using natural language processing technology and extracting the intent of the query and important keywords.

[0109] "Means for obtaining" refers to the method or function for searching and extracting related map data and attribute information from the database based on the analysis results.

[0110] "Formatting" refers to a method for converting acquired information into a format that is easy for users to understand, such as converting into HTML or JSON format.

[0111] "Means for sending" refers to the function or method by which the server sends formatted information to the terminal.

[0112] The "means for displaying" refers to a method for displaying the information received by the terminal on the user interface and visually providing it to the user.

[0113] "Shelter information" refers to information about places to evacuate to in the event of a disaster, and includes data such as location information, addresses, telephone numbers, and capacity.

[0114] A "hazard map" is a map that visually shows the risk of natural disasters in a specific area, and includes risk information such as floods, earthquakes, and tsunamis.

[0115] This invention relates to a system that quickly and intuitively provides necessary map data and related attribute information based on a search query entered by a user in natural language. Specifically, this system registers map data and related attribute information in a database, analyzes the search query using natural language processing technology, and retrieves and displays related information, enabling the rapid provision of information, particularly in the event of a disaster.

[0116] The server registers map data and related attribute information (e.g., addresses, danger levels on hazard maps, disaster response information for evacuation centers, etc.) in a database. This database is constructed using a database management system such as MySQL (registered trademark) or PostgreSQL.

[0117] A device (e.g., a smartphone or PC) receives a search query from a user. For example, if a user types "Where is the nearest evacuation shelter?" into the device, this query is sent from the device to the server as an HTTP request.

[0118] The server passes the received search query to a natural language processing engine (e.g., NLTK or SpaCy) to analyze the query's intent and important keywords. For example, the keyword "nearby shelter" is extracted.

[0119] Based on the analysis results, the server searches the database to retrieve relevant map data and attribute information. For example, the server uses the user's current location information to retrieve details such as the location, address, phone number, and capacity of the nearest evacuation shelter.

[0120] The acquired information is formatted into a user-friendly format. During this formatting process, the information is converted into HTML or JSON format, and the information is converted into a user-friendly format. For example, the formatting might be "Evacuation shelter: XX Park, Address: XX City XX Town, Phone number: 012-345-6789."

[0121] The formatted information is sent from the server to the device as an HTTP response. The device receives the HTTP response from the server and displays it in a user interface. As a specific example, a list of shelters and detailed information is displayed on the screen using UI components in a browser or native app.

[0122] Users can check the information displayed on their device screen and take the necessary action. For example, they can refer to detailed information about a shelter displayed on their device, open a map app like Google Maps, and start navigation. In this way, the system provides users with information quickly and intuitively.

[0123] An example of a prompt might be:

[0124] Please explain in natural language the processing flow when the following search query is entered: Example query: A user types "Where is the nearest evacuation center?" into their device and submits it.

[0125] As such, the present invention is a system that enables the rapid and efficient acquisition and provision of relevant information based on natural language queries, and is particularly effective in gathering information during disasters.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1: The user enters a search query in natural language into the device.

[0128] A user enters a search query such as "Where is the nearest evacuation shelter?" into a browser on their smartphone or PC, or into a dedicated app. The entered query is saved in text format on the device.

[0129] Input: Natural language input by the user (e.g., "Where is the nearest evacuation center?")

[0130] Output: Search query in plain text

[0131] Specific action: The user types a query using the keyboard or voice input, and presses the Enter key in the input box or clicks the submit button.

[0132] Step 2: The device sends the search query to the server

[0133] The device sends the entered search query to the server as an HTTP request, which includes the query text and the user's current location information.

[0134] Input: Text search query, user location

[0135] Output: HTTP request (including search query and current location information)

[0136] What it does: Your browser or app packages the query and your current location information to create an HTTP POST request, which is then sent to the server by pressing the submit button.

[0137] Step 3: The server receives the search query

[0138] The server receives the HTTP request sent from the device and extracts the search query and current location information from the received request.

[0139] Input: HTTP request (including search query and current location information)

[0140] Output: Extracted search query and current location information

[0141] What happens: The server's API endpoint receives the HTTP request and parses and extracts the search query and current location information from the request body.

[0142] Step 4: The server analyzes the search query using a natural language processing engine

[0143] The server passes the extracted search query to a natural language processing engine (e.g., NLTK or SpaCy) to analyze the query's intent and important keywords.

[0144] Input: Search query

[0145] Output: Analysis results (intent and important keywords)

[0146] Specific operation: The server calls the natural language processing library and passes the search query as input data to the analysis function. For example, the keyword "nearby shelter" is extracted as the analysis result.

[0147] Step 5: The server searches the database

[0148] The server searches a database (e.g., MySQL or PostgreSQL) based on the analysis results to retrieve relevant map data and attribute information.

[0149] Input: Analysis results (important keywords), user's current location information

[0150] Output: Related map data and attribute information (e.g., shelter location, address, phone number, capacity)

[0151] Specific operation: The server generates an SQL query and executes a search against the database. For example, it issues a SELECT statement to retrieve data about "nearby shelters" and retrieves information about the nearest shelter.

[0152] Step 6: Format the information retrieved by the server

[0153] The server formats the map data and attribute information it has acquired into a format that is easy for users to understand. In this process, the data is converted into HTML or JSON format.

[0154] Input: Relevant map data and attribute information

[0155] Output: Formatted information (e.g., shelter information in HTML or JSON format)

[0156] What happens: The server uses a template engine (e.g. Jinja2) to embed data into templates and convert them into user-friendly HTML or JSON format.

[0157] Step 7: The server sends the formatted information to the device

[0158] The server sends the formatted information to the terminal as an HTTP response.

[0159] Input: Formatted information (e.g., shelter information in HTML or JSON format)

[0160] Output: HTTP response (including formatted information)

[0161] Specific operation: The server sets the HTTP response header, inserts formatted information into the response body, and sends it to the terminal.

[0162] Step 8: Your device receives the search results

[0163] The terminal receives the HTTP response from the server and extracts the formatted information from the response body.

[0164] Input: HTTP response (including formatted information)

[0165] Output: Extracted formatting information

[0166] What happens: The browser or app receives the HTTP response, parses the response data, and extracts information in HTML or JSON format.

[0167] Step 9: The device displays the search results to the user

[0168] The device displays the extracted information on the user interface, specifically a list of evacuation shelters and detailed information.

[0169] Input: Extracted formatting information

[0170] Output: Display on the user interface

[0171] What happens: The browser or app adds information to the DOM tree and redraws to visually provide the evacuation information to the user.

[0172] Step 10: User confirms the results

[0173] The user checks the information displayed on the device and takes the necessary action. For example, they open a map app and start navigation based on the detailed information about the evacuation shelter displayed.

[0174] Input: what is displayed on the user interface

[0175] Output: User action (e.g., opening a map app, heading to a shelter)

[0176] Specific actions: The user looks at the device screen, checks the displayed evacuation shelter information, and decides on the next action. They tap the map app to start navigation.

[0177] (Application example 1)

[0178] 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."

[0179] Conventional map information systems are required to provide fast and accurate information during disasters and emergencies, but they often lack the precision to display information on device screens and analyze users' vague search queries. Furthermore, information display methods adapted to new devices such as smart glasses are inadequate, creating a need for a system that provides information to users in an intuitive and visually easy-to-understand format. Given this background, a system is needed that can analyze user queries in natural language and quickly retrieve and display relevant information.

[0180] 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.

[0181] In this invention, the server includes: means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; means for analyzing the received search query based on natural language processing and understanding the intent of the query; means for searching the database based on the analysis result and acquiring related map data and attribute information; means for formatting the acquired information in a format easily understandable by the user and transmitting it to the terminal; means for displaying the information received by the terminal to the user; an application installed on the smart glasses; means for analyzing the query using a natural language processing engine and extracting keywords; means for sending a request to the server based on the extracted keywords and receiving related information; and means for displaying the received information on a display of the smart glasses. This allows a user to intuitively and quickly check security-related map information and attribute information through the smart glasses.

[0182] "Location data" is digital information about a geographic location, and is data used to indicate a particular point on a map.

[0183] "Map data" refers to digital map data that visually represents geographical information about the Earth or a region, and includes information on roads, buildings, topography, and so on.

[0184] "Attribute information" is additional information related to map data, and refers to detailed data about a specific point or area (for example, address, telephone number, danger level, etc.).

[0185] A "database" is a structured collection of information, a store of digital information that is organized and managed for a specific purpose.

[0186] A "search query" is a phrase or sentence that a user enters into a device to search for information.

[0187] "Natural language processing" is a technology that allows computers to understand and analyze the language (natural language) that humans use on a daily basis.

[0188] "Query intent" refers to the purpose and content of the information a user wants to know or seek through a search query.

[0189] A "server" is a computer system that provides data or services in response to requests from other computers (clients).

[0190] "Smart glasses" are a type of wearable device that incorporates a display and sensors into the glasses and has the function of visually displaying information.

[0191] A "natural language processing engine" is software for performing natural language processing, and is a tool for analyzing text data to understand its meaning and intent.

[0192] "Keywords" are important phrases or terms extracted from a search query.

[0193] An "HTTP request" is a type of communication protocol used by a web browser or client to request data or services from a server.

[0194] A "display" is a display device for visually displaying information, including smart glasses and computer monitors.

[0195] To implement this invention, several major components are required. The configuration and operation of a specific system are described in detail below.

[0196] Server Roles and Processes

[0197] 1. Register the database:

[0198] The server registers map data and related attribute information (addresses, telephone numbers, risk levels, etc.) in a database. This database is a structured collection of information that is organized and managed according to specific purposes.

[0199] 2. Receiving and parsing search queries:

[0200] The server receives the search query sent from the device, which is then analyzed using a natural language processing engine (e.g., the spacy library) to extract important keywords.

[0201] 3. Searching the database and retrieving information:

[0202] Based on the parsed query, the server searches the database to retrieve relevant map data and attribute information. For example, for a query requesting information on the "nearest police station," the server retrieves details such as the location, address, and phone number of the nearest police station.

[0203] 4. Formatting and sending information:

[0204] The acquired information is formatted in a way that is easy for the user to understand, and the formatted information is sent to the terminal as an HTTP response.

[0205] Terminal roles and processing

[0206] 1. Getting and sending user input:

[0207] The device receives a search query from the user, for example, "Where is the nearest police station?", and sends the query to the server.

[0208] 2. Receiving and Displaying Search Results:

[0209] The device receives the HTTP response from the server and displays the search results to the user. For example, the smart glasses display briefly displays information such as "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789."

[0210] The role of smart glasses

[0211] 1. Install the application:

[0212] The smart glasses are installed with an application that requests information based on the parsed query and displays the obtained information.

[0213] 2. Parse the prompt:

[0214] A natural language processing engine is used to analyze the query and extract important keywords, for example using the spacy library.

[0215] 3. Display information:

[0216] Based on the extracted keywords, a request is sent to the server, relevant information is received, and it is displayed on the display of the smart glasses.

[0217] Examples and prompts

[0218] Specific examples

[0219] The user puts on the smart glasses and speaks to ask, "What is the nearest police station from here?" The application analyzes the query and presents information about the nearest police station.

[0220] Prompt Sentence Examples

[0221] User Query: "What is the nearest police station?"

[0222] Analyzed keywords: ["Police Station"]

[0223] Information obtained: {"name": "XX Police Station", "address": "XX City XX Town", "phone": "012-345-6789"}

[0224] In this way, the system allows users to intuitively and quickly view security-related map information and attribute information through smart glasses.

[0225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0226] Step 1:

[0227] A user puts on the smart glasses and uses voice or text input to enter a query, such as "Where is the nearest police station from here?"

[0228] Input: User query (e.g., "Where is the nearest police station?")

[0229] Output: User query data (text format)

[0230] Step 2:

[0231] The device (smart glasses) receives a search query from the user and sends it to the server in the form of an HTTP request, which is how the query reaches the server.

[0232] Input: User query data

[0233] Output: HTTP request to the server

[0234] Step 3:

[0235] The server passes the received search query to a natural language processing engine, which parses the query and extracts important keywords, for example, using the spacy library.

[0236] Input: User query as an HTTP request

[0237] Output: Extracted keywords (e.g. "police station")

[0238] Step 4:

[0239] The server searches the database based on the analysis results and obtains relevant map data and attribute information (e.g., location information, address, telephone number, etc. of the nearest police station).

[0240] Input: Extracted keywords

[0241] Output: Associated map data and attribute information

[0242] Step 5:

[0243] The server formats the information it retrieves into a user-friendly format, which may include, for example, converting JSON-formatted data into human-readable text.

[0244] Input: Relevant map data and attribute information

[0245] Output: Formatted information (e.g., "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789")

[0246] Step 6:

[0247] The server sends the formatted information to the device as an HTTP response, and the device (smart glasses) receives this response.

[0248] Input: Formatted information

[0249] Output: HTTP response to the device

[0250] Step 7:

[0251] The device displays the received information on the user interface. Detailed information (e.g., "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789") is displayed on the smart glasses display.

[0252] Input: Formatted information as an HTTP response

[0253] Output: Information displayed on the smart glasses display

[0254] This step allows users to intuitively and quickly check the information they need through the smart glasses.

[0255] 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.

[0256] The present invention relates to a system that enables users to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. Furthermore, the present invention aims to provide users with the information they need more accurately and effectively by combining it with an emotion recognition engine that recognizes the user's emotions.

[0257] Overview of the system's programs and their processing

[0258] Server Roles and Operations

[0259] Registering map data and attribute information:

[0260] The server registers the map data and related attribute information (address, danger level on the hazard map, disaster response information for evacuation shelters, etc.) in a database. This registration is expected to enable quick search responses.

[0261] Receiving and parsing search queries:

[0262] The server receives the search query entered from the device. The received query is passed to a natural language processing engine for analysis. In this analysis step, the intent of the query and important keywords are extracted.

[0263] Emotion recognition:

[0264] When the server analyzes the search query, it also analyzes the user's emotional state using an emotion recognition engine, for example, to determine whether the user is in an emergency situation based on the content and wording of the query.

[0265] Searching the database and retrieving information:

[0266] The server searches the database based on the analysis results and the user's emotional state. For example, if the analysis results indicate a search for a nearby evacuation shelter and the user is in an emergency, the server will prioritize detailed information such as the location of the evacuation shelter and safe routes.

[0267] Formatting and sending information:

[0268] The acquired information is formatted into a form that is easy for the user to understand. Depending on the user's emotional state indicated by the emotion recognition engine, the way the information is presented (for example, by providing clearer instructions or including emergency contact information) is adjusted. The formatted information is then sent to the device.

[0269] Terminal roles and processing

[0270] Getting and sending user input:

[0271] The device receives a search query from the user. For example, the user types, "Where is the nearest evacuation shelter?" The device sends this query to the server.

[0272] Receiving and displaying search results:

[0273] The device receives the HTTP response from the server. The received search results are displayed in the user interface. For example, a list of evacuation shelters is displayed, and their details (addresses, phone numbers, etc.) are provided to the user.

[0274] User operation example

[0275] Enter and submit a query:

[0276] The user types "Where is the nearest evacuation shelter?" into the device and sends it.

[0277] Emotion recognition and display of results:

[0278] If the server analyzes the query and determines that the user is in an emergency, it quickly sends information about the best evacuation shelters, along with safe routes and other important contact information, to the device, which then displays it to the user.

[0279] This system combines natural language query input with emotion recognition to quickly and accurately provide users with the information they need. Especially in times of disaster, providing appropriate information based on the user's emotional state can encourage quick decisions and actions. In this way, the present invention can significantly improve the quality and speed of information provision.

[0280] The processing flow will be explained below.

[0281] Step 1:

[0282] A user enters a search query.

[0283] A user types a search query into the device interface, for example, "Where are the nearest evacuation centers?"

[0284] Step 2:

[0285] A user submits a search query.

[0286] The user presses the submit button to send the entered search query to the server.

[0287] Step 3:

[0288] The device sends a search query to the server.

[0289] The device generates an HTTP POST request containing the user-entered search query and sends it to the specified endpoint on the server.

[0290] Step 4:

[0291] A server receives a search query.

[0292] The server receives the HTTP POST request from the device and retrieves the query data for analysis.

[0293] Step 5:

[0294] The server parses the search query.

[0295] The server passes the received search query to a natural language processing engine, which extracts the query's intent and key keywords. This analysis identifies the information the user is looking for.

[0296] Step 6:

[0297] The server analyzes the user's emotions.

[0298] The server uses an emotion recognition engine to analyze the user's emotional state from the search query, for example, determining whether the user is experiencing an emergency based on the content of the query and the language used.

[0299] Step 7:

[0300] The server searches the database.

[0301] The server searches the database for relevant map data and attribute information based on the analysis of the search query and the user's emotional state, such as the location, address, phone number, and capacity of the evacuation shelter.

[0302] Step 8:

[0303] The server formats the search results.

[0304] The server formats the information it obtains into a format that is easy for the user to understand. The display format and content of the information are adjusted based on the user's emotional state indicated by the emotion recognition engine. For example, if the emergency is high, information on the shortest route to an evacuation shelter is added.

[0305] Step 9:

[0306] The server sends the search results to the terminal.

[0307] The server sends the formatted information to the terminal as an HTTP response.

[0308] Step 10:

[0309] The terminal receives the search results.

[0310] The terminal receives an HTTP response from the server.

[0311] Step 11:

[0312] Your device will display the search results.

[0313] The device displays the search results it receives in a user interface, such as a list of evacuation shelters with detailed information (e.g., address, phone number, capacity, etc.), and additional information (e.g., safe routes and emergency contacts) depending on the user's emotional state.

[0314] Step 12:

[0315] The user reviews the search results.

[0316] The user checks the search results displayed on the device and obtains the necessary information, for example, checking the route to the nearest evacuation shelter and preparing for emergency evacuation.

[0317] Example 2

[0318] 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."

[0319] Conventional map data systems simply provide location information, and have the problem of low response accuracy to user search queries. Furthermore, in emergencies such as disasters, it is difficult for users to quickly obtain the information they need, and information provision does not take into account the user's emotional state. This can result in delayed responses by users in emergencies.

[0320] 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.

[0321] In this invention, the server includes means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database, means for receiving a search query input from a terminal, means for analyzing the received search query based on natural language processing and understanding the intent of the query, means for performing emotion recognition during the analysis and determining the user's emotional state, means for searching the database based on the analysis result and the emotion recognition result and acquiring related map data and attribute information, means for formatting the acquired information into a format that is easy for the user to understand, adjusting the information presentation method according to the user's emotional state, and transmitting the information to the terminal, and means for displaying the information received by the terminal on a user interface. This makes it possible to respond quickly and accurately to a user's search query and provide information that takes the user's emotional state into consideration, particularly in an emergency.

[0322] "Location data" refers to data relating to a specific geographic location, including latitude and longitude.

[0323] "Map data" is data that visually represents geographical information, including roads, buildings, and natural topography.

[0324] "Attribute information" is additional information related to map data, and is data that includes specific characteristics such as addresses, telephone numbers, and seating capacity.

[0325] A "database" is a system for efficiently managing information and storing it in a form that can be searched and manipulated.

[0326] A "search query" is text data that expresses a question or request that a user inputs to a system.

[0327] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0328] "Emotion recognition" is a technology that determines a user's emotional state based on their input and behavior.

[0329] A "user interface" is an interface that allows interaction between a system and a user, and includes means for displaying and inputting information.

[0330] "Analysis results" refers to the conclusions or data obtained through processing search queries and emotion recognition.

[0331] "Information presentation method" refers to the format or means by which information is provided to the user, and includes text, images, audio, and the like.

[0332] The present invention is a system that enables a user to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. The system includes a server that registers map data including location information data and multiple attribute information related to the map data in a database, a server that receives and analyzes the search query entered from a terminal, a server that performs emotion recognition, a server that searches the database and obtains information based on the analysis and emotion recognition results, a server that formats the obtained information, adjusts the information presentation method according to the user's emotional state, and transmits the information to the terminal, and a user interface that displays the information received by the terminal.

[0333] Specifically, the server uses a GIS (geographic information system) to register map data and associated attribute information in a database. It uses OpenStreetMap data and its API, and stores the information in a PostgreSQL database. It also passes search queries entered from the device to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. It then analyzes the user's emotional state using an emotion recognition engine (e.g., IBM Watson (registered trademark) Tone Analyzer). It searches the database using an SQL query based on the analysis and emotion recognition results to obtain the necessary map data and attribute information. The obtained information is formatted in HTML and organized as data to be displayed on a map using the Google Maps API. Finally, the formatted information is converted to JSON format and sent to the device as an HTTP response.

[0334] The device receives the search query from the user and sends it to the server as an HTTP request. The received search query is sent to the server in JSON format, for example, "query": "Where is the nearest evacuation shelter?". The device then receives an HTTP response from the server and displays the received data on the user interface. An example of the display would be information such as "The nearest evacuation shelter is on Third Street. What is the safe route?"

[0335] A user enters a search query into their device and clicks the send button, which sends the query to the server. If the server analyzes the query and determines that the user is in an emergency, it can quickly provide information on the best evacuation shelter, as well as safe routes and other important contact information.

[0336] Example prompt for a generative AI model:

[0337] If a user types "Where are the nearest shelters?", how would the server perform emotion recognition and provide information about the appropriate shelters?

[0338] This system combines natural language query input with emotion recognition to quickly and accurately provide users with the information they need. Especially in times of disaster, providing appropriate information based on the user's emotional state can encourage quick decisions and actions. In this way, the present invention can significantly improve the quality and speed of information provision.

[0339] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0340] Step 1:

[0341] Registering map data and attribute information

[0342] The server acquires map data using a GIS (geographic information system) and registers multiple related attribute information (addresses, danger levels on hazard maps, disaster response information for evacuation centers, etc.) in a database. This registration process is carried out using OpenStreetMap data and its API. The server stores the acquired map data and attribute information in a PostgreSQL database. It receives GIS data and attribute information as input and generates the information registered in the database as output.

[0343] Step 2:

[0344] Getting User Input

[0345] A user inputs a search query into a device. For example, the query "Where is the nearest evacuation center?" is entered into an input field. The system receives a natural language search query as input and captures the query on the client side. The output is the query data sent to the server.

[0346] Step 3:

[0347] Sending User Input

[0348] The device sends the search query entered by the user to the server as an HTTP request. It receives the search query as input and sends JSON format data (e.g., "query": "Where is the nearest evacuation center?") as output to the server.

[0349] Step 4:

[0350] Receiving and parsing search queries

[0351] The server receives the search query sent from the device. It passes the received query to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. It processes the data to extract the intent of the query and key keywords. It receives the search query as input and obtains the analyzed keywords and intent as output.

[0352] Step 5:

[0353] emotion recognition

[0354] The server passes the parsed query to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotional state. This analysis involves performing data calculations to determine whether the user is in an emergency situation. It receives the parsed query as input and obtains the user's emotional state as output.

[0355] Step 6:

[0356] Searching the database

[0357] The server generates an SQL query based on the analysis results and emotion recognition results, searches the database, and retrieves related map data and attribute information. It receives the analysis results and emotional state as input, and obtains the necessary map data and attribute information as output.

[0358] Step 7:

[0359] Formatting and sending information

[0360] The server formats the information it acquires into a format that is easy for the user to understand, and adjusts the way the information is presented based on the user's emotional state. Specifically, it formats the information in HTML format and prepares the data for display on a map using the Google Maps API. It converts this information into JSON format and sends it to the device as an HTTP response. It receives the acquired map data and attribute information as input, generates formatted information as output, and sends it to the device.

[0361] Step 8:

[0362] Receiving and displaying search results

[0363] The device receives the HTTP response from the server and displays the received data on the user interface. It receives the information sent from the server as input and generates search results that are displayed to the user as output. Specifically, information is displayed in a format such as, "The nearest evacuation shelter is on Third Street. The safe route is on which street."

[0364] (Application example 2)

[0365] 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."

[0366] In modern society, it is important to provide users with the information they desire quickly and accurately. However, conventional information search systems simply provide results based on the query without considering the user's emotional state, making it difficult to provide appropriate information based on the user's emotions and situation. In particular, when it comes to dining, a user's emotional state has a significant impact on satisfaction, so there is a need for restaurant selection and menu suggestions that reflect emotions.

[0367] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; means for analyzing the received search query using natural language processing and understanding the intent of the query; means for analyzing the user's emotional state using emotion recognition technology; means for searching the database based on the analysis result and the emotional state and acquiring related map data and attribute information; means for formatting the acquired information in a format that is easy for the user to understand and transmitting it to the terminal; and means for displaying the information received by the terminal to the user. This makes it possible to provide information that takes the user's emotional state into consideration, and particularly when selecting a dining facility, it is possible to suggest restaurants and menus that suit the user's emotions, thereby improving user satisfaction.

[0368] "Location information data" refers to data that indicates a geographical location, and includes coordinate information such as latitude and longitude.

[0369] "Map data" is data that visually represents geographical locations, and includes information on roads, buildings, landmarks, and the like.

[0370] "Attribute information" is additional information associated with a particular geographic location, including address, phone number, ratings, menu information, and the like.

[0371] "Means of registering in a database" refers to the processes and technologies for registering map data and attribute information in a database that can be centrally managed.

[0372] A "terminal" is a device that allows a user to input or receive information, and includes smartphones, tablets, head-mounted displays, etc.

[0373] A "search query" refers to a natural language sentence or phrase entered by a user to search for information.

[0374] "Natural language processing" refers to the technology that enables computers to understand and analyze natural human language.

[0375] "Emotion recognition technology" refers to technology that analyzes and recognizes a user's emotional state from their input and behavior.

[0376] "Analysis Results" refers to the information and data obtained using search query analysis and emotion recognition technology.

[0377] "Means of formatting the information in a format that is easy for the user to understand and sending it to the terminal" refers to the technology and processing for processing the acquired information so that it can be easily understood by the user and sending it to the terminal.

[0378] "Means for displaying" refers to the technology or method for visually displaying the information received on the terminal.

[0379] "Food and beverage establishments" are establishments that serve food and beverages, including restaurants, cafes, and fast food restaurants.

[0380] "Ratings" refers to user ratings and reviews of dining establishments and services provided.

[0381] "Business status" refers to the status of a food and beverage establishment, such as whether it is open or closed.

[0382] "Menu Information" means the list and details of the food and beverages served at a Food and Beverage Establishment.

[0383] "Emotion analysis results" refers to the results of analyzing a user's emotional state using emotion recognition technology.

[0384] A "recommended menu" refers to a list of food and drink suggestions based on the user's emotional state and preferences.

[0385] This invention relates to a system that quickly and intuitively acquires necessary map data and its attribute information based on a search query entered by a user in natural language, and further combines emotion recognition technology to provide information more accurately and effectively. As an application example, consider a restaurant recommendation system.

[0386] System Overview

[0387] The system of the present invention is mainly composed of a server and a user terminal. A user inputs a search query using a terminal such as a smartphone or a head-mounted display, and the server analyzes the query and provides appropriate information.

[0388] Hardware and software used

[0389] Hardware

[0390] Smartphone or head-mounted display

[0391] GPS function

[0392] microphone

[0393] software

[0394] Natural language processing engine (e.g. Google NLP API)

[0395] Emotion recognition engine (e.g., Microsoft® Azure® Emotion API)

[0396] Map API (e.g. Google Maps API)

[0397] Business management system (e.g., Firebase Realtime Database)

[0398] System Operation

[0399] 1. Getting User Input

[0400] A user uses a terminal to input a query in natural language about the food they want to eat or their mood, such as "I want to eat some delicious pizza nearby."

[0401] 2. Search Query Analysis

[0402] The device sends the user's query to the server, which then uses a natural language processing engine to analyze the query and extract its intent and keywords. For example, keywords such as "pizza" and "nearby" are extracted.

[0403] 3. Emotion Recognition Implementation

[0404] The server uses an emotion recognition engine to analyze the user's emotional state, recognizing emotions such as "tired" or "in a hurry" from search queries and vocabulary.

[0405] 4. Acquisition of Information

[0406] The server searches a map database based on the analysis results and the user's emotional state. For example, it obtains information such as the location, ratings, business hours, and menu information of nearby pizza restaurants. It also prioritizes the search results and provides the most suitable restaurants based on the user's emotional state.

[0407] 5. Formatting and sending information

[0408] The acquired information is formatted in a way that is easy for the user to understand. For example, if the emotion recognition engine determines that the user is in a hurry, restaurant information that can serve food quickly will be prioritized.

[0409] 6. Display of search results

[0410] The formatted information is sent to the terminal, which displays it to the user, who can then select the most suitable dining establishment based on the information provided.

[0411] Specific examples

[0412] If a user inputs a prompt such as "I've been tired since yesterday, so I want to eat some delicious pizza right now," the system will analyze the user's emotional state, such as "tired" or "right now," and search for pizza restaurants that can serve food quickly. The retrieved restaurant information is displayed on the device in an easy-to-understand format, allowing the user to easily find a suitable dining establishment.

[0413] The system of the present invention makes it possible to provide information that takes into account the user's emotional state, and can suggest restaurants and menus that best suit the user's needs, particularly when selecting a dining establishment, thereby providing a comfortable and satisfying experience.

[0414] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0415] Step 1:

[0416] A user uses a smartphone or a head-mounted display to input queries about the food they want to eat or their mood in natural language. For example, if a user inputs a query such as "I want to eat good pizza nearby," the input format is text or voice. The device receives this input and sends it to the server. The input data is the query text, and the output is the data to be sent to the server.

[0417] Step 2:

[0418] The server passes the search query received from the device to a natural language processing engine for analysis. The input is the search query text, and the output is the analysis results and extracted keywords. Specifically, it uses the Google NLP API to extract important keywords from the text (e.g., "pizza" or "nearby") and the intent of the query.

[0419] Step 3:

[0420] The server uses an emotion recognition engine to analyze the user's emotional state from the search query text. The input is the search query text, and the output is the emotion recognition result. Specifically, it uses the Microsoft Azure Emotion API to determine the user's emotional state (e.g., "I'm in a hurry" or "I'm tired") from the content and wording of the query.

[0421] Step 4:

[0422] The server searches the map database based on the query analysis results and emotion recognition results. The input is the analysis results and emotion recognition results, and the output is related map data and attribute information. Specifically, it uses the Google Maps API to obtain location information and attribute information (e.g., ratings, business status, menu information) of the restaurant that best suits the user.

[0423] Step 5:

[0424] The server formats the map data and attribute information it obtains into a format that is easy for the user to understand. The input is search result data, and the output is the formatted data. Specific operations include adjusting the way information is presented depending on the user's emotional state (e.g., if the user is "in a hurry," prioritize displaying restaurant information that allows quick ordering).

[0425] Step 6:

[0426] The server sends the formatted information to the terminal. The input is the formatted data, and the output is the data sent to the terminal. Specifically, the server sends the necessary information to the user as an HTTP response.

[0427] Step 7:

[0428] The terminal displays the information it receives to the user. The input is the data received from the server, and the output is the content displayed on the user interface. Specifically, it displays restaurant information and menu information suitable for the user on the screen, allowing the user to easily refer to that information.

[0429] The above processing steps enable users to quickly and accurately obtain information on appropriate dining establishments. Because this system takes into account the user's emotional state, it can provide information that is more satisfying.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] [Second embodiment]

[0434] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0445] 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."

[0446] This invention relates to a system that allows users to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. Specifically, map data and multiple related attribute information are registered in a database, and the search query is analyzed using natural language processing to retrieve and display related information, enabling the rapid provision of information in the event of a disaster.

[0447] Overview of the system's programs and their processing

[0448] Server Roles and Operations

[0449] Registering map data and attribute information:

[0450] The server registers map data and related attribute information (address, hazard map danger level, evacuation shelter disaster response information, etc.) in a database, enabling quick responses to search queries.

[0451] Receiving and parsing search queries:

[0452] The server receives the search query entered from the device. The received query is passed to a natural language processing engine for analysis. In this analysis step, the intent of the query and important keywords are extracted.

[0453] Searching the database and retrieving information:

[0454] Based on the parsed query, the server searches for relevant map data and attribute information in the database. For example, for a query requesting information on "nearby shelters," the server retrieves details such as the location, address, phone number, and capacity of the nearest shelter.

[0455] Formatting and sending information:

[0456] The acquired information is formatted in a way that is easy for the user to understand, and the formatted information is sent to the terminal as an HTTP response.

[0457] Terminal roles and processing

[0458] Getting and sending user input:

[0459] The device receives a search query from the user. For example, the user types, "Where is the nearest evacuation shelter?" The device sends this query to the server.

[0460] Receiving and displaying search results:

[0461] The terminal receives the HTTP response from the server. The received search results are displayed in the user interface. For example, a list of evacuation shelters is displayed, and their details (addresses, phone numbers, etc.) are provided to the user.

[0462] User operation example

[0463] Entering and sending a query: The user enters "Where is the nearest shelter?" into the device and sends it.

[0464] Check the results: Check the shelter information displayed on the device. For example, details such as "Shelter: XX Park, Address: XX City XX Town, Phone Number: 012-345-6789" will be displayed.

[0465] This system quickly and efficiently retrieves and provides relevant information based on natural language queries, demonstrating exceptional effectiveness in gathering information during disasters. Such a system allows users to intuitively and quickly obtain the information they need, enabling them to make quick decisions and take action in emergencies.

[0466] The processing flow will be explained below.

[0467] Step 1:

[0468] A user enters a search query.

[0469] A user types a search query into a device, for example, "Where are the nearest evacuation centers?"

[0470] Step 2:

[0471] A user submits a search query.

[0472] The user presses the submit button to send the query to the server.

[0473] Step 3:

[0474] The device sends a search query to the server.

[0475] The device generates an HTTP POST request containing the user's input and sends it to the specified endpoint on the server.

[0476] Step 4:

[0477] A server receives a search query.

[0478] The server receives an HTTP POST request from the terminal and obtains the query.

[0479] Step 5:

[0480] The server parses the search query.

[0481] The server passes the received search query to a natural language processing engine, which analyzes the query's intent, extracting important keywords and user intent.

[0482] Step 6:

[0483] The server searches the database.

[0484] The server searches the database based on the analysis results. For example, if the analysis results indicate that the user is searching for a nearby shelter, the server retrieves information about the shelter from the database.

[0485] Step 7:

[0486] The server formats the search results.

[0487] The server formats the data it acquires into a format that is easy for users to understand. For example, it formats information such as the name, address, telephone number, and capacity of the evacuation shelter into a list.

[0488] Step 8:

[0489] The server sends the search results to the terminal.

[0490] The server sends the formatted information to the terminal as an HTTP response.

[0491] Step 9:

[0492] The terminal receives the search results.

[0493] The terminal receives an HTTP response from the server.

[0494] Step 10:

[0495] Your device will display the search results.

[0496] The terminal displays the received search results on a user interface, for example, a list of evacuation shelters is displayed and their details (addresses, telephone numbers, etc.) are provided to the user.

[0497] Step 11:

[0498] The user reviews the search results.

[0499] The user checks the search results displayed on the device and decides on the next action, for example, preparing to go to the nearest evacuation shelter.

[0500] Example 1

[0501] 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."

[0502] There is a lack of means to quickly and intuitively obtain map information and its related attribute information, which is a problem especially in times of disaster, where users are unable to immediately obtain the information they need.There is a need for a system that efficiently provides information necessary in emergencies, such as information on evacuation shelters and hazards.

[0503] 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.

[0504] In this invention, the server includes means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database, means for receiving a search query input from a terminal, means for analyzing the received search query using natural language processing and understanding the intent of the query, means for searching the database based on the analysis result and acquiring related map data and attribute information, means for formatting the acquired information in a format that is easy for the user to understand and transmitting it to the terminal, means for displaying the information received by the terminal to the user, and means for formatting and transmitting data that is effective for quickly providing map information incorporating evacuation shelter information. This enables a user to quickly and intuitively obtain the necessary map data and its attribute information based on a query input in natural language.

[0505] "Location information data" is data that indicates a specific point or area on a map, and includes coordinate information such as latitude and longitude.

[0506] "Map data" is digital data that visually represents geographical information, and includes information on roads, buildings, natural topography, and the like.

[0507] "Attribute information" is additional information related to map data, and includes additional information such as addresses, telephone numbers, facility features and functions, and disaster response information.

[0508] A "database" is a structured electronic file system that systematically stores map data and its associated attribute information, making it easy to search and retrieve.

[0509] A "search query" is a question or keyword that a user inputs into a terminal to obtain the information they need.

[0510] "Means for receiving" refers to the function or method by which the server receives the search query sent from the terminal.

[0511] "Natural language processing" is a technology that allows computers to understand and process human language, and includes text analysis, keyword extraction, and context understanding.

[0512] "Means for analyzing" refers to a method of analyzing the content of a received search query using natural language processing technology and extracting the intent of the query and important keywords.

[0513] "Means for obtaining" refers to the method or function for searching and extracting related map data and attribute information from the database based on the analysis results.

[0514] "Formatting" refers to a method for converting acquired information into a format that is easy for users to understand, such as converting into HTML or JSON format.

[0515] "Means for sending" refers to the function or method by which the server sends formatted information to the terminal.

[0516] The "means for displaying" refers to a method for displaying the information received by the terminal on the user interface and visually providing it to the user.

[0517] "Shelter information" refers to information about places to evacuate to in the event of a disaster, and includes data such as location information, addresses, telephone numbers, and capacity.

[0518] A "hazard map" is a map that visually shows the risk of natural disasters in a specific area, and includes risk information such as floods, earthquakes, and tsunamis.

[0519] This invention relates to a system that quickly and intuitively provides necessary map data and related attribute information based on a search query entered by a user in natural language. Specifically, this system registers map data and related attribute information in a database, analyzes the search query using natural language processing technology, and retrieves and displays related information, enabling the rapid provision of information, particularly in the event of a disaster.

[0520] The server registers map data and related attribute information (e.g., addresses, risk levels on hazard maps, disaster response information for evacuation centers, etc.) in a database. This database is constructed using a database management system such as MySQL or PostgreSQL.

[0521] A device (e.g., a smartphone or PC) receives a search query from a user. For example, if a user types "Where is the nearest evacuation shelter?" into the device, this query is sent from the device to the server as an HTTP request.

[0522] The server passes the received search query to a natural language processing engine (e.g., NLTK or SpaCy) to analyze the query's intent and important keywords. For example, the keyword "nearby shelter" is extracted.

[0523] Based on the analysis results, the server searches the database to retrieve relevant map data and attribute information. For example, the server uses the user's current location information to retrieve details such as the location, address, phone number, and capacity of the nearest evacuation shelter.

[0524] The acquired information is formatted into a user-friendly format. During this formatting process, the information is converted into HTML or JSON format, and the information is converted into a user-friendly format. For example, the formatting might be "Evacuation shelter: XX Park, Address: XX City XX Town, Phone number: 012-345-6789."

[0525] The formatted information is sent from the server to the device as an HTTP response. The device receives the HTTP response from the server and displays it in a user interface. As a specific example, a list of shelters and detailed information is displayed on the screen using UI components in a browser or native app.

[0526] Users can check the information displayed on their device screen and take necessary actions. For example, they can refer to the detailed information of the evacuation shelter displayed on their device, open a map app such as Google Maps, and start navigation. In this way, the system provides users with information quickly and intuitively.

[0527] An example of a prompt might be:

[0528] Please explain in natural language the processing flow when the following search query is entered: Example query: A user types "Where is the nearest evacuation center?" into their device and submits it.

[0529] As such, the present invention is a system that enables the rapid and efficient acquisition and provision of relevant information based on natural language queries, and is particularly effective in gathering information during disasters.

[0530] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0531] Step 1: The user enters a search query in natural language into the device.

[0532] A user enters a search query such as "Where is the nearest evacuation shelter?" into a browser on their smartphone or PC, or into a dedicated app. The entered query is saved in text format on the device.

[0533] Input: Natural language input by the user (e.g., "Where is the nearest evacuation center?")

[0534] Output: Search query in plain text

[0535] Specific action: The user types a query using the keyboard or voice input, and presses the Enter key in the input box or clicks the submit button.

[0536] Step 2: The device sends the search query to the server

[0537] The device sends the entered search query to the server as an HTTP request, which includes the query text and the user's current location information.

[0538] Input: Text search query, user location

[0539] Output: HTTP request (including search query and current location information)

[0540] What it does: Your browser or app packages the query and your current location information to create an HTTP POST request, which is then sent to the server by pressing the submit button.

[0541] Step 3: The server receives the search query

[0542] The server receives the HTTP request sent from the device and extracts the search query and current location information from the received request.

[0543] Input: HTTP request (including search query and current location information)

[0544] Output: Extracted search query and current location information

[0545] What happens: The server's API endpoint receives the HTTP request and parses and extracts the search query and current location information from the request body.

[0546] Step 4: The server analyzes the search query using a natural language processing engine

[0547] The server passes the extracted search query to a natural language processing engine (e.g., NLTK or SpaCy) to analyze the query's intent and important keywords.

[0548] Input: Search query

[0549] Output: Analysis results (intent and important keywords)

[0550] Specific operation: The server calls the natural language processing library and passes the search query as input data to the analysis function. For example, the keyword "nearby shelter" is extracted as the analysis result.

[0551] Step 5: The server searches the database

[0552] The server searches a database (e.g., MySQL or PostgreSQL) based on the analysis results to retrieve relevant map data and attribute information.

[0553] Input: Analysis results (important keywords), user's current location information

[0554] Output: Related map data and attribute information (e.g., shelter location, address, phone number, capacity)

[0555] Specific operation: The server generates an SQL query and executes a search against the database. For example, it issues a SELECT statement to retrieve data about "nearby shelters" and retrieves information about the nearest shelter.

[0556] Step 6: Format the information retrieved by the server

[0557] The server formats the map data and attribute information it has acquired into a format that is easy for users to understand. In this process, the data is converted into HTML or JSON format.

[0558] Input: Relevant map data and attribute information

[0559] Output: Formatted information (e.g., shelter information in HTML or JSON format)

[0560] What happens: The server uses a template engine (e.g. Jinja2) to embed data into templates and convert them into user-friendly HTML or JSON format.

[0561] Step 7: The server sends the formatted information to the device

[0562] The server sends the formatted information to the terminal as an HTTP response.

[0563] Input: Formatted information (e.g., shelter information in HTML or JSON format)

[0564] Output: HTTP response (including formatted information)

[0565] Specific operation: The server sets the HTTP response header, inserts formatted information into the response body, and sends it to the terminal.

[0566] Step 8: Your device receives the search results

[0567] The terminal receives the HTTP response from the server and extracts the formatted information from the response body.

[0568] Input: HTTP response (including formatted information)

[0569] Output: Extracted formatting information

[0570] What happens: The browser or app receives the HTTP response, parses the response data, and extracts information in HTML or JSON format.

[0571] Step 9: The device displays the search results to the user

[0572] The device displays the extracted information on the user interface, specifically a list of evacuation shelters and detailed information.

[0573] Input: Extracted formatting information

[0574] Output: Display on the user interface

[0575] What happens: The browser or app adds information to the DOM tree and redraws to visually provide the evacuation information to the user.

[0576] Step 10: User confirms the results

[0577] The user checks the information displayed on the device and takes the necessary action. For example, they open a map app and start navigation based on the detailed information about the evacuation shelter displayed.

[0578] Input: what is displayed on the user interface

[0579] Output: User action (e.g., opening a map app, heading to a shelter)

[0580] Specific actions: The user looks at the device screen, checks the displayed evacuation shelter information, and decides on the next action. They tap the map app to start navigation.

[0581] (Application example 1)

[0582] 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."

[0583] Conventional map information systems are required to provide fast and accurate information during disasters and emergencies, but they often lack the precision to display information on device screens and analyze users' vague search queries. Furthermore, information display methods adapted to new devices such as smart glasses are inadequate, creating a need for a system that provides information to users in an intuitive and visually easy-to-understand format. Given this background, a system is needed that can analyze user queries in natural language and quickly retrieve and display relevant information.

[0584] 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.

[0585] In this invention, the server includes: means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; means for analyzing the received search query based on natural language processing and understanding the intent of the query; means for searching the database based on the analysis result and acquiring related map data and attribute information; means for formatting the acquired information in a format easily understandable by the user and transmitting it to the terminal; means for displaying the information received by the terminal to the user; an application installed on the smart glasses; means for analyzing the query using a natural language processing engine and extracting keywords; means for sending a request to the server based on the extracted keywords and receiving related information; and means for displaying the received information on a display of the smart glasses. This allows a user to intuitively and quickly check security-related map information and attribute information through the smart glasses.

[0586] "Location data" is digital information about a geographic location, and is data used to indicate a particular point on a map.

[0587] "Map data" refers to digital map data that visually represents geographical information about the Earth or a region, and includes information on roads, buildings, topography, and so on.

[0588] "Attribute information" is additional information related to map data, and refers to detailed data about a specific point or area (for example, address, telephone number, danger level, etc.).

[0589] A "database" is a structured collection of information, a store of digital information that is organized and managed for a specific purpose.

[0590] A "search query" is a phrase or sentence that a user enters into a device to search for information.

[0591] "Natural language processing" is a technology that allows computers to understand and analyze the language (natural language) that humans use on a daily basis.

[0592] "Query intent" refers to the purpose and content of the information a user wants to know or seek through a search query.

[0593] A "server" is a computer system that provides data or services in response to requests from other computers (clients).

[0594] "Smart glasses" are a type of wearable device that incorporates a display and sensors into the glasses and has the function of visually displaying information.

[0595] A "natural language processing engine" is software for performing natural language processing, and is a tool for analyzing text data to understand its meaning and intent.

[0596] "Keywords" are important phrases or terms extracted from a search query.

[0597] An "HTTP request" is a type of communication protocol used by a web browser or client to request data or services from a server.

[0598] A "display" is a display device for visually displaying information, including smart glasses and computer monitors.

[0599] To implement this invention, several major components are required. The configuration and operation of a specific system are described in detail below.

[0600] Server Roles and Processes

[0601] 1. Register the database:

[0602] The server registers map data and related attribute information (addresses, telephone numbers, risk levels, etc.) in a database. This database is a structured collection of information that is organized and managed according to specific purposes.

[0603] 2. Receiving and parsing search queries:

[0604] The server receives the search query sent from the device, which is then analyzed using a natural language processing engine (e.g., the spacy library) to extract important keywords.

[0605] 3. Searching the database and retrieving information:

[0606] Based on the parsed query, the server searches the database to retrieve relevant map data and attribute information. For example, for a query requesting information on the "nearest police station," the server retrieves details such as the location, address, and phone number of the nearest police station.

[0607] 4. Formatting and sending information:

[0608] The acquired information is formatted in a way that is easy for the user to understand, and the formatted information is sent to the terminal as an HTTP response.

[0609] Terminal roles and processing

[0610] 1. Getting and sending user input:

[0611] The device receives a search query from the user, for example, "Where is the nearest police station?", and sends the query to the server.

[0612] 2. Receiving and Displaying Search Results:

[0613] The device receives the HTTP response from the server and displays the search results to the user. For example, the smart glasses display briefly displays information such as "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789."

[0614] The role of smart glasses

[0615] 1. Install the application:

[0616] The smart glasses are installed with an application that requests information based on the parsed query and displays the obtained information.

[0617] 2. Parse the prompt:

[0618] A natural language processing engine is used to analyze the query and extract important keywords, for example using the spacy library.

[0619] 3. Display information:

[0620] Based on the extracted keywords, a request is sent to the server, relevant information is received, and it is displayed on the display of the smart glasses.

[0621] Examples and prompts

[0622] Specific examples

[0623] The user puts on the smart glasses and speaks to ask, "What is the nearest police station from here?" The application analyzes the query and presents information about the nearest police station.

[0624] Prompt Sentence Examples

[0625] User Query: "What is the nearest police station?"

[0626] Analyzed keywords: ["Police Station"]

[0627] Information obtained: {"name": "XX Police Station", "address": "XX City XX Town", "phone": "012-345-6789"}

[0628] In this way, the system allows users to intuitively and quickly view security-related map information and attribute information through smart glasses.

[0629] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0630] Step 1:

[0631] A user puts on the smart glasses and uses voice or text input to enter a query, such as "Where is the nearest police station from here?"

[0632] Input: User query (e.g., "Where is the nearest police station?")

[0633] Output: User query data (text format)

[0634] Step 2:

[0635] The device (smart glasses) receives a search query from the user and sends it to the server in the form of an HTTP request, which is how the query reaches the server.

[0636] Input: User query data

[0637] Output: HTTP request to the server

[0638] Step 3:

[0639] The server passes the received search query to a natural language processing engine, which parses the query and extracts important keywords, for example, using the spacy library.

[0640] Input: User query as an HTTP request

[0641] Output: Extracted keywords (e.g. "police station")

[0642] Step 4:

[0643] The server searches the database based on the analysis results and obtains relevant map data and attribute information (e.g., location information, address, telephone number, etc. of the nearest police station).

[0644] Input: Extracted keywords

[0645] Output: Associated map data and attribute information

[0646] Step 5:

[0647] The server formats the information it retrieves into a user-friendly format, which may include, for example, converting JSON-formatted data into human-readable text.

[0648] Input: Relevant map data and attribute information

[0649] Output: Formatted information (e.g., "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789")

[0650] Step 6:

[0651] The server sends the formatted information to the device as an HTTP response, and the device (smart glasses) receives this response.

[0652] Input: Formatted information

[0653] Output: HTTP response to the device

[0654] Step 7:

[0655] The device displays the received information on the user interface. Detailed information (e.g., "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789") is displayed on the smart glasses display.

[0656] Input: Formatted information as an HTTP response

[0657] Output: Information displayed on the smart glasses display

[0658] This step allows users to intuitively and quickly check the information they need through the smart glasses.

[0659] 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.

[0660] The present invention relates to a system that enables users to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. Furthermore, the present invention aims to provide users with the information they need more accurately and effectively by combining it with an emotion recognition engine that recognizes the user's emotions.

[0661] Overview of the system's programs and their processing

[0662] Server Roles and Operations

[0663] Registering map data and attribute information:

[0664] The server registers the map data and related attribute information (address, danger level on the hazard map, disaster response information for evacuation shelters, etc.) in a database. This registration is expected to enable quick search responses.

[0665] Receiving and parsing search queries:

[0666] The server receives the search query entered from the device. The received query is passed to a natural language processing engine for analysis. In this analysis step, the intent of the query and important keywords are extracted.

[0667] Emotion recognition:

[0668] When the server analyzes the search query, it also analyzes the user's emotional state using an emotion recognition engine, for example, to determine whether the user is in an emergency situation based on the content and wording of the query.

[0669] Searching the database and retrieving information:

[0670] The server searches the database based on the analysis results and the user's emotional state. For example, if the analysis results indicate a search for a nearby evacuation shelter and the user is in an emergency, the server will prioritize detailed information such as the location of the evacuation shelter and safe routes.

[0671] Formatting and sending information:

[0672] The acquired information is formatted into a form that is easy for the user to understand. Depending on the user's emotional state indicated by the emotion recognition engine, the way the information is presented (for example, by providing clearer instructions or including emergency contact information) is adjusted. The formatted information is then sent to the device.

[0673] Terminal roles and processing

[0674] Getting and sending user input:

[0675] The device receives a search query from the user. For example, the user types, "Where is the nearest evacuation shelter?" The device sends this query to the server.

[0676] Receiving and displaying search results:

[0677] The device receives the HTTP response from the server. The received search results are displayed in the user interface. For example, a list of evacuation shelters is displayed, and their details (addresses, phone numbers, etc.) are provided to the user.

[0678] User operation example

[0679] Enter and submit a query:

[0680] The user types "Where is the nearest evacuation shelter?" into the device and sends it.

[0681] Emotion recognition and display of results:

[0682] If the server analyzes the query and determines that the user is in an emergency, it quickly sends information about the best evacuation shelters, along with safe routes and other important contact information, to the device, which then displays it to the user.

[0683] This system combines natural language query input with emotion recognition to quickly and accurately provide users with the information they need. Especially in times of disaster, providing appropriate information based on the user's emotional state can encourage quick decisions and actions. In this way, the present invention can significantly improve the quality and speed of information provision.

[0684] The processing flow will be explained below.

[0685] Step 1:

[0686] A user enters a search query.

[0687] A user types a search query into the device interface, for example, "Where are the nearest evacuation centers?"

[0688] Step 2:

[0689] A user submits a search query.

[0690] The user presses the submit button to send the entered search query to the server.

[0691] Step 3:

[0692] The device sends a search query to the server.

[0693] The device generates an HTTP POST request containing the user-entered search query and sends it to the specified endpoint on the server.

[0694] Step 4:

[0695] A server receives a search query.

[0696] The server receives the HTTP POST request from the device and retrieves the query data for analysis.

[0697] Step 5:

[0698] The server parses the search query.

[0699] The server passes the received search query to a natural language processing engine, which extracts the query's intent and key keywords. This analysis identifies the information the user is looking for.

[0700] Step 6:

[0701] The server analyzes the user's emotions.

[0702] The server uses an emotion recognition engine to analyze the user's emotional state from the search query, for example, determining whether the user is experiencing an emergency based on the content of the query and the language used.

[0703] Step 7:

[0704] The server searches the database.

[0705] The server searches the database for relevant map data and attribute information based on the analysis of the search query and the user's emotional state, such as the location, address, phone number, and capacity of the evacuation shelter.

[0706] Step 8:

[0707] The server formats the search results.

[0708] The server formats the information it obtains into a format that is easy for the user to understand. The display format and content of the information are adjusted based on the user's emotional state indicated by the emotion recognition engine. For example, if the emergency is high, information on the shortest route to an evacuation shelter is added.

[0709] Step 9:

[0710] The server sends the search results to the terminal.

[0711] The server sends the formatted information to the terminal as an HTTP response.

[0712] Step 10:

[0713] The terminal receives the search results.

[0714] The terminal receives an HTTP response from the server.

[0715] Step 11:

[0716] Your device will display the search results.

[0717] The device displays the search results it receives in a user interface, such as a list of evacuation shelters with detailed information (e.g., address, phone number, capacity, etc.), and additional information (e.g., safe routes and emergency contacts) depending on the user's emotional state.

[0718] Step 12:

[0719] The user reviews the search results.

[0720] The user checks the search results displayed on the device and obtains the necessary information, for example, checking the route to the nearest evacuation shelter and preparing for emergency evacuation.

[0721] Example 2

[0722] 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."

[0723] Conventional map data systems simply provide location information, and have the problem of low response accuracy to user search queries. Furthermore, in emergencies such as disasters, it is difficult for users to quickly obtain the information they need, and information provision does not take into account the user's emotional state. This can result in delayed responses by users in emergencies.

[0724] 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.

[0725] In this invention, the server includes means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database, means for receiving a search query input from a terminal, means for analyzing the received search query based on natural language processing and understanding the intent of the query, means for performing emotion recognition during the analysis and determining the user's emotional state, means for searching the database based on the analysis result and the emotion recognition result and acquiring related map data and attribute information, means for formatting the acquired information into a format that is easy for the user to understand, adjusting the information presentation method according to the user's emotional state, and transmitting the information to the terminal, and means for displaying the information received by the terminal on a user interface. This makes it possible to respond quickly and accurately to a user's search query and provide information that takes the user's emotional state into consideration, particularly in an emergency.

[0726] "Location data" refers to data relating to a specific geographic location, including latitude and longitude.

[0727] "Map data" is data that visually represents geographical information, including roads, buildings, and natural topography.

[0728] "Attribute information" is additional information related to map data, and is data that includes specific characteristics such as addresses, telephone numbers, and seating capacity.

[0729] A "database" is a system for efficiently managing information and storing it in a form that can be searched and manipulated.

[0730] A "search query" is text data that expresses a question or request that a user inputs to a system.

[0731] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0732] "Emotion recognition" is a technology that determines a user's emotional state based on their input and behavior.

[0733] A "user interface" is an interface that allows interaction between a system and a user, and includes means for displaying and inputting information.

[0734] "Analysis results" refers to the conclusions or data obtained through processing search queries and emotion recognition.

[0735] "Information presentation method" refers to the format or means by which information is provided to the user, and includes text, images, audio, and the like.

[0736] The present invention is a system that enables a user to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. The system includes a server that registers map data including location information data and multiple attribute information related to the map data in a database, a server that receives and analyzes the search query entered from a terminal, a server that performs emotion recognition, a server that searches the database and obtains information based on the analysis and emotion recognition results, a server that formats the obtained information, adjusts the information presentation method according to the user's emotional state, and transmits the information to the terminal, and a user interface that displays the information received by the terminal.

[0737] Specifically, the server uses a GIS (geographic information system) to register map data and associated attribute information in a database. It uses OpenStreetMap data and its API as software, storing the information in a PostgreSQL database. It also passes search queries entered from the device to a natural language processing engine (for example, Google Cloud Natural Language API) for analysis. It then analyzes the user's emotional state using an emotion recognition engine (for example, IBM Watson Tone Analyzer). It searches the database using an SQL query based on the analysis and emotion recognition results to obtain the necessary map data and attribute information. The obtained information is formatted in HTML and organized as data to be displayed on a map using the Google Maps API. Finally, the formatted information is converted to JSON format and sent to the device as an HTTP response.

[0738] The device receives the search query from the user and sends it to the server as an HTTP request. The received search query is sent to the server in JSON format, for example, "query": "Where is the nearest evacuation shelter?". The device then receives an HTTP response from the server and displays the received data on the user interface. An example of the display would be information such as "The nearest evacuation shelter is on Third Street. What is the safe route?"

[0739] A user enters a search query into their device and clicks the send button, which sends the query to the server. If the server analyzes the query and determines that the user is in an emergency, it can quickly provide information on the best evacuation shelter, as well as safe routes and other important contact information.

[0740] Example prompt for a generative AI model:

[0741] If a user types "Where are the nearest shelters?", how would the server perform emotion recognition and provide information about the appropriate shelters?

[0742] This system combines natural language query input with emotion recognition to quickly and accurately provide users with the information they need. Especially in times of disaster, providing appropriate information based on the user's emotional state can encourage quick decisions and actions. In this way, the present invention can significantly improve the quality and speed of information provision.

[0743] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0744] Step 1:

[0745] Registering map data and attribute information

[0746] The server acquires map data using a GIS (geographic information system) and registers multiple related attribute information (addresses, danger levels on hazard maps, disaster response information for evacuation centers, etc.) in a database. This registration process is carried out using OpenStreetMap data and its API. The server stores the acquired map data and attribute information in a PostgreSQL database. It receives GIS data and attribute information as input and generates the information registered in the database as output.

[0747] Step 2:

[0748] Getting User Input

[0749] A user inputs a search query into a device. For example, the query "Where is the nearest evacuation center?" is entered into an input field. The system receives a natural language search query as input and captures the query on the client side. The output is the query data sent to the server.

[0750] Step 3:

[0751] Sending User Input

[0752] The device sends the search query entered by the user to the server as an HTTP request. It receives the search query as input and sends JSON format data (e.g., "query": "Where is the nearest evacuation center?") as output to the server.

[0753] Step 4:

[0754] Receiving and parsing search queries

[0755] The server receives the search query sent from the device. It passes the received query to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. It processes the data to extract the intent of the query and key keywords. It receives the search query as input and obtains the analyzed keywords and intent as output.

[0756] Step 5:

[0757] emotion recognition

[0758] The server passes the parsed query to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotional state. This analysis involves performing data calculations to determine whether the user is in an emergency situation. It receives the parsed query as input and obtains the user's emotional state as output.

[0759] Step 6:

[0760] Searching the database

[0761] The server generates an SQL query based on the analysis results and emotion recognition results, searches the database, and retrieves related map data and attribute information. It receives the analysis results and emotional state as input, and obtains the necessary map data and attribute information as output.

[0762] Step 7:

[0763] Formatting and sending information

[0764] The server formats the information it acquires into a format that is easy for the user to understand, and adjusts the way the information is presented based on the user's emotional state. Specifically, it formats the information in HTML format and prepares the data for display on a map using the Google Maps API. It converts this information into JSON format and sends it to the device as an HTTP response. It receives the acquired map data and attribute information as input, generates formatted information as output, and sends it to the device.

[0765] Step 8:

[0766] Receiving and displaying search results

[0767] The device receives the HTTP response from the server and displays the received data on the user interface. It receives the information sent from the server as input and generates search results that are displayed to the user as output. Specifically, information is displayed in a format such as, "The nearest evacuation shelter is on Third Street. The safe route is on which street."

[0768] (Application example 2)

[0769] 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."

[0770] In modern society, it is important to provide users with the information they desire quickly and accurately. However, conventional information search systems simply provide results based on the query without considering the user's emotional state, making it difficult to provide appropriate information based on the user's emotions and situation. In particular, when it comes to dining, a user's emotional state has a significant impact on satisfaction, so there is a need for restaurant selection and menu suggestions that reflect emotions.

[0771] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; means for analyzing the received search query using natural language processing and understanding the intent of the query; means for analyzing the user's emotional state using emotion recognition technology; means for searching the database based on the analysis result and the emotional state and acquiring related map data and attribute information; means for formatting the acquired information in a format that is easy for the user to understand and transmitting it to the terminal; and means for displaying the information received by the terminal to the user. This makes it possible to provide information that takes the user's emotional state into consideration, and particularly when selecting a dining facility, it is possible to suggest restaurants and menus that suit the user's emotions, thereby improving user satisfaction.

[0772] "Location information data" refers to data that indicates a geographical location, and includes coordinate information such as latitude and longitude.

[0773] "Map data" is data that visually represents geographical locations, and includes information on roads, buildings, landmarks, and the like.

[0774] "Attribute information" is additional information associated with a particular geographic location, including address, phone number, ratings, menu information, and the like.

[0775] "Means of registering in a database" refers to the processes and technologies for registering map data and attribute information in a database that can be centrally managed.

[0776] A "terminal" is a device that allows a user to input or receive information, and includes smartphones, tablets, head-mounted displays, etc.

[0777] A "search query" refers to a natural language sentence or phrase entered by a user to search for information.

[0778] "Natural language processing" refers to the technology that enables computers to understand and analyze natural human language.

[0779] "Emotion recognition technology" refers to technology that analyzes and recognizes a user's emotional state from their input and behavior.

[0780] "Analysis Results" refers to the information and data obtained using search query analysis and emotion recognition technology.

[0781] "Means of formatting the information in a format that is easy for the user to understand and sending it to the terminal" refers to the technology and processing for processing the acquired information so that it can be easily understood by the user and sending it to the terminal.

[0782] "Means for displaying" refers to the technology or method for visually displaying the information received on the terminal.

[0783] "Food and beverage establishments" are establishments that serve food and beverages, including restaurants, cafes, and fast food restaurants.

[0784] "Ratings" refers to user ratings and reviews of dining establishments and services provided.

[0785] "Business status" refers to the status of a food and beverage establishment, such as whether it is open or closed.

[0786] "Menu Information" means the list and details of the food and beverages served at a Food and Beverage Establishment.

[0787] "Emotion analysis results" refers to the results of analyzing a user's emotional state using emotion recognition technology.

[0788] A "recommended menu" refers to a list of food and drink suggestions based on the user's emotional state and preferences.

[0789] This invention relates to a system that quickly and intuitively acquires necessary map data and its attribute information based on a search query entered by a user in natural language, and further combines emotion recognition technology to provide information more accurately and effectively. As an application example, consider a restaurant recommendation system.

[0790] System Overview

[0791] The system of the present invention is mainly composed of a server and a user terminal. A user inputs a search query using a terminal such as a smartphone or a head-mounted display, and the server analyzes the query and provides appropriate information.

[0792] Hardware and software used

[0793] Hardware

[0794] Smartphone or head-mounted display

[0795] GPS function

[0796] microphone

[0797] software

[0798] Natural language processing engine (e.g. Google NLP API)

[0799] Emotion recognition engine (e.g. Microsoft Azure Emotion API)

[0800] Map API (e.g. Google Maps API)

[0801] Business management system (e.g., Firebase Realtime Database)

[0802] System Operation

[0803] 1. Getting User Input

[0804] A user uses a terminal to input a query in natural language about the food they want to eat or their mood, such as "I want to eat some delicious pizza nearby."

[0805] 2. Search Query Analysis

[0806] The device sends the user's query to the server, which then uses a natural language processing engine to analyze the query and extract its intent and keywords. For example, keywords such as "pizza" and "nearby" are extracted.

[0807] 3. Emotion Recognition Implementation

[0808] The server uses an emotion recognition engine to analyze the user's emotional state, recognizing emotions such as "tired" or "in a hurry" from search queries and vocabulary.

[0809] 4. Acquisition of Information

[0810] The server searches a map database based on the analysis results and the user's emotional state. For example, it obtains information such as the location, ratings, business hours, and menu information of nearby pizza restaurants. It also prioritizes the search results and provides the most suitable restaurants based on the user's emotional state.

[0811] 5. Formatting and sending information

[0812] The acquired information is formatted in a way that is easy for the user to understand. For example, if the emotion recognition engine determines that the user is in a hurry, restaurant information that can serve food quickly will be prioritized.

[0813] 6. Display of search results

[0814] The formatted information is sent to the terminal, which displays it to the user, who can then select the most suitable dining establishment based on the information provided.

[0815] Specific examples

[0816] If a user inputs a prompt such as "I've been tired since yesterday, so I want to eat some delicious pizza right now," the system will analyze the user's emotional state, such as "tired" or "right now," and search for pizza restaurants that can serve food quickly. The retrieved restaurant information is displayed on the device in an easy-to-understand format, allowing the user to easily find a suitable dining establishment.

[0817] The system of the present invention makes it possible to provide information that takes into account the user's emotional state, and can suggest restaurants and menus that best suit the user's needs, particularly when selecting a dining establishment, thereby providing a comfortable and satisfying experience.

[0818] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0819] Step 1:

[0820] A user uses a smartphone or a head-mounted display to input queries about the food they want to eat or their mood in natural language. For example, if a user inputs a query such as "I want to eat good pizza nearby," the input format is text or voice. The device receives this input and sends it to the server. The input data is the query text, and the output is the data to be sent to the server.

[0821] Step 2:

[0822] The server passes the search query received from the device to a natural language processing engine for analysis. The input is the search query text, and the output is the analysis results and extracted keywords. Specifically, it uses the Google NLP API to extract important keywords from the text (e.g., "pizza" or "nearby") and the intent of the query.

[0823] Step 3:

[0824] The server uses an emotion recognition engine to analyze the user's emotional state from the search query text. The input is the search query text, and the output is the emotion recognition result. Specifically, it uses the Microsoft Azure Emotion API to determine the user's emotional state (e.g., "I'm in a hurry" or "I'm tired") from the content and wording of the query.

[0825] Step 4:

[0826] The server searches the map database based on the query analysis results and emotion recognition results. The input is the analysis results and emotion recognition results, and the output is related map data and attribute information. Specifically, it uses the Google Maps API to obtain location information and attribute information (e.g., ratings, business status, menu information) of the restaurant that best suits the user.

[0827] Step 5:

[0828] The server formats the map data and attribute information it obtains into a format that is easy for the user to understand. The input is search result data, and the output is the formatted data. Specific operations include adjusting the way information is presented depending on the user's emotional state (e.g., if the user is "in a hurry," prioritize displaying restaurant information that allows quick ordering).

[0829] Step 6:

[0830] The server sends the formatted information to the terminal. The input is the formatted data, and the output is the data sent to the terminal. Specifically, the server sends the necessary information to the user as an HTTP response.

[0831] Step 7:

[0832] The terminal displays the information it receives to the user. The input is the data received from the server, and the output is the content displayed on the user interface. Specifically, it displays restaurant information and menu information suitable for the user on the screen, allowing the user to easily refer to that information.

[0833] The above processing steps enable users to quickly and accurately obtain information on appropriate dining establishments. Because this system takes into account the user's emotional state, it can provide information that is more satisfying.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] [Third embodiment]

[0838] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0839] 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.

[0840] 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).

[0841] 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.

[0842] 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.

[0843] 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).

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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."

[0850] This invention relates to a system that allows users to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. Specifically, map data and multiple related attribute information are registered in a database, and the search query is analyzed using natural language processing to retrieve and display related information, enabling the rapid provision of information in the event of a disaster.

[0851] Overview of the system's programs and their processing

[0852] Server Roles and Operations

[0853] Registering map data and attribute information:

[0854] The server registers map data and related attribute information (address, hazard map danger level, evacuation shelter disaster response information, etc.) in a database, enabling quick responses to search queries.

[0855] Receiving and parsing search queries:

[0856] The server receives the search query entered from the device. The received query is passed to a natural language processing engine for analysis. In this analysis step, the intent of the query and important keywords are extracted.

[0857] Searching the database and retrieving information:

[0858] Based on the parsed query, the server searches for relevant map data and attribute information in the database. For example, for a query requesting information on "nearby shelters," the server retrieves details such as the location, address, phone number, and capacity of the nearest shelter.

[0859] Formatting and sending information:

[0860] The acquired information is formatted in a way that is easy for the user to understand, and the formatted information is sent to the terminal as an HTTP response.

[0861] Terminal roles and processing

[0862] Getting and sending user input:

[0863] The device receives a search query from the user. For example, the user types, "Where is the nearest evacuation shelter?" The device sends this query to the server.

[0864] Receiving and displaying search results:

[0865] The terminal receives the HTTP response from the server. The received search results are displayed in the user interface. For example, a list of evacuation shelters is displayed, and their details (addresses, phone numbers, etc.) are provided to the user.

[0866] User operation example

[0867] Entering and sending a query: The user enters "Where is the nearest shelter?" into the device and sends it.

[0868] Check the results: Check the shelter information displayed on the device. For example, details such as "Shelter: XX Park, Address: XX City XX Town, Phone Number: 012-345-6789" will be displayed.

[0869] This system quickly and efficiently retrieves and provides relevant information based on natural language queries, demonstrating exceptional effectiveness in gathering information during disasters. Such a system allows users to intuitively and quickly obtain the information they need, enabling them to make quick decisions and take action in emergencies.

[0870] The processing flow will be explained below.

[0871] Step 1:

[0872] A user enters a search query.

[0873] A user types a search query into a device, for example, "Where are the nearest evacuation centers?"

[0874] Step 2:

[0875] A user submits a search query.

[0876] The user presses the submit button to send the query to the server.

[0877] Step 3:

[0878] The device sends a search query to the server.

[0879] The device generates an HTTP POST request containing the user's input and sends it to the specified endpoint on the server.

[0880] Step 4:

[0881] A server receives a search query.

[0882] The server receives an HTTP POST request from the terminal and obtains the query.

[0883] Step 5:

[0884] The server parses the search query.

[0885] The server passes the received search query to a natural language processing engine, which analyzes the query's intent, extracting important keywords and user intent.

[0886] Step 6:

[0887] The server searches the database.

[0888] The server searches the database based on the analysis results. For example, if the analysis results indicate that the user is searching for a nearby shelter, the server retrieves information about the shelter from the database.

[0889] Step 7:

[0890] The server formats the search results.

[0891] The server formats the data it acquires into a format that is easy for users to understand. For example, it formats information such as the name, address, telephone number, and capacity of the evacuation shelter into a list.

[0892] Step 8:

[0893] The server sends the search results to the terminal.

[0894] The server sends the formatted information to the terminal as an HTTP response.

[0895] Step 9:

[0896] The terminal receives the search results.

[0897] The terminal receives an HTTP response from the server.

[0898] Step 10:

[0899] Your device will display the search results.

[0900] The terminal displays the received search results on a user interface, for example, a list of evacuation shelters is displayed and their details (addresses, telephone numbers, etc.) are provided to the user.

[0901] Step 11:

[0902] The user reviews the search results.

[0903] The user checks the search results displayed on the device and decides on the next action, for example, preparing to go to the nearest evacuation shelter.

[0904] Example 1

[0905] 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."

[0906] There is a lack of means to quickly and intuitively obtain map information and its related attribute information, which is a problem especially in times of disaster, where users are unable to immediately obtain the information they need.There is a need for a system that efficiently provides information necessary in emergencies, such as information on evacuation shelters and hazards.

[0907] 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.

[0908] In this invention, the server includes means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database, means for receiving a search query input from a terminal, means for analyzing the received search query using natural language processing and understanding the intent of the query, means for searching the database based on the analysis result and acquiring related map data and attribute information, means for formatting the acquired information in a format that is easy for the user to understand and transmitting it to the terminal, means for displaying the information received by the terminal to the user, and means for formatting and transmitting data that is effective for quickly providing map information incorporating evacuation shelter information. This enables a user to quickly and intuitively obtain the necessary map data and its attribute information based on a query input in natural language.

[0909] "Location information data" is data that indicates a specific point or area on a map, and includes coordinate information such as latitude and longitude.

[0910] "Map data" is digital data that visually represents geographical information, and includes information on roads, buildings, natural topography, and the like.

[0911] "Attribute information" is additional information related to map data, and includes additional information such as addresses, telephone numbers, facility features and functions, and disaster response information.

[0912] A "database" is a structured electronic file system that systematically stores map data and its associated attribute information, making it easy to search and retrieve.

[0913] A "search query" is a question or keyword that a user inputs into a terminal to obtain the information they need.

[0914] "Means for receiving" refers to the function or method by which the server receives the search query sent from the terminal.

[0915] "Natural language processing" is a technology that allows computers to understand and process human language, and includes text analysis, keyword extraction, and context understanding.

[0916] "Means for analyzing" refers to a method of analyzing the content of a received search query using natural language processing technology and extracting the intent of the query and important keywords.

[0917] "Means for obtaining" refers to the method or function for searching and extracting related map data and attribute information from the database based on the analysis results.

[0918] "Formatting" refers to a method for converting acquired information into a format that is easy for users to understand, such as converting into HTML or JSON format.

[0919] "Means for sending" refers to the function or method by which the server sends formatted information to the terminal.

[0920] The "means for displaying" refers to a method for displaying the information received by the terminal on the user interface and visually providing it to the user.

[0921] "Shelter information" refers to information about places to evacuate to in the event of a disaster, and includes data such as location information, addresses, telephone numbers, and capacity.

[0922] A "hazard map" is a map that visually shows the risk of natural disasters in a specific area, and includes risk information such as floods, earthquakes, and tsunamis.

[0923] This invention relates to a system that quickly and intuitively provides necessary map data and related attribute information based on a search query entered by a user in natural language. Specifically, this system registers map data and related attribute information in a database, analyzes the search query using natural language processing technology, and retrieves and displays related information, enabling the rapid provision of information, particularly in the event of a disaster.

[0924] The server registers map data and related attribute information (e.g., addresses, risk levels on hazard maps, disaster response information for evacuation centers, etc.) in a database. This database is constructed using a database management system such as MySQL or PostgreSQL.

[0925] A device (e.g., a smartphone or PC) receives a search query from a user. For example, if a user types "Where is the nearest evacuation shelter?" into the device, this query is sent from the device to the server as an HTTP request.

[0926] The server passes the received search query to a natural language processing engine (e.g., NLTK or SpaCy) to analyze the query's intent and important keywords. For example, the keyword "nearby shelter" is extracted.

[0927] Based on the analysis results, the server searches the database to retrieve relevant map data and attribute information. For example, the server uses the user's current location information to retrieve details such as the location, address, phone number, and capacity of the nearest evacuation shelter.

[0928] The acquired information is formatted into a user-friendly format. During this formatting process, the information is converted into HTML or JSON format, and the information is converted into a user-friendly format. For example, the formatting might be "Evacuation shelter: XX Park, Address: XX City XX Town, Phone number: 012-345-6789."

[0929] The formatted information is sent from the server to the device as an HTTP response. The device receives the HTTP response from the server and displays it in a user interface. As a specific example, a list of shelters and detailed information is displayed on the screen using UI components in a browser or native app.

[0930] Users can check the information displayed on their device screen and take necessary actions. For example, they can refer to the detailed information of the evacuation shelter displayed on their device, open a map app such as Google Maps, and start navigation. In this way, the system provides users with information quickly and intuitively.

[0931] An example of a prompt might be:

[0932] Please explain in natural language the processing flow when the following search query is entered: Example query: A user types "Where is the nearest evacuation center?" into their device and submits it.

[0933] As such, the present invention is a system that enables the rapid and efficient acquisition and provision of relevant information based on natural language queries, and is particularly effective in gathering information during disasters.

[0934] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0935] Step 1: The user enters a search query in natural language into the device.

[0936] A user enters a search query such as "Where is the nearest evacuation shelter?" into a browser on their smartphone or PC, or into a dedicated app. The entered query is saved in text format on the device.

[0937] Input: Natural language input by the user (e.g., "Where is the nearest evacuation center?")

[0938] Output: Search query in plain text

[0939] Specific action: The user types a query using the keyboard or voice input, and presses the Enter key in the input box or clicks the submit button.

[0940] Step 2: The device sends the search query to the server

[0941] The device sends the entered search query to the server as an HTTP request, which includes the query text and the user's current location information.

[0942] Input: Text search query, user location

[0943] Output: HTTP request (including search query and current location information)

[0944] What it does: Your browser or app packages the query and your current location information to create an HTTP POST request, which is then sent to the server by pressing the submit button.

[0945] Step 3: The server receives the search query

[0946] The server receives the HTTP request sent from the device and extracts the search query and current location information from the received request.

[0947] Input: HTTP request (including search query and current location information)

[0948] Output: Extracted search query and current location information

[0949] What happens: The server's API endpoint receives the HTTP request and parses and extracts the search query and current location information from the request body.

[0950] Step 4: The server analyzes the search query using a natural language processing engine

[0951] The server passes the extracted search query to a natural language processing engine (e.g., NLTK or SpaCy) to analyze the query's intent and important keywords.

[0952] Input: Search query

[0953] Output: Analysis results (intent and important keywords)

[0954] Specific operation: The server calls the natural language processing library and passes the search query as input data to the analysis function. For example, the keyword "nearby shelter" is extracted as the analysis result.

[0955] Step 5: The server searches the database

[0956] The server searches a database (e.g., MySQL or PostgreSQL) based on the analysis results to retrieve relevant map data and attribute information.

[0957] Input: Analysis results (important keywords), user's current location information

[0958] Output: Related map data and attribute information (e.g., shelter location, address, phone number, capacity)

[0959] Specific operation: The server generates an SQL query and executes a search against the database. For example, it issues a SELECT statement to retrieve data about "nearby shelters" and retrieves information about the nearest shelter.

[0960] Step 6: Format the information retrieved by the server

[0961] The server formats the map data and attribute information it has acquired into a format that is easy for users to understand. In this process, the data is converted into HTML or JSON format.

[0962] Input: Relevant map data and attribute information

[0963] Output: Formatted information (e.g., shelter information in HTML or JSON format)

[0964] What happens: The server uses a template engine (e.g. Jinja2) to embed data into templates and convert them into user-friendly HTML or JSON format.

[0965] Step 7: The server sends the formatted information to the device

[0966] The server sends the formatted information to the terminal as an HTTP response.

[0967] Input: Formatted information (e.g., shelter information in HTML or JSON format)

[0968] Output: HTTP response (including formatted information)

[0969] Specific operation: The server sets the HTTP response header, inserts formatted information into the response body, and sends it to the terminal.

[0970] Step 8: Your device receives the search results

[0971] The terminal receives the HTTP response from the server and extracts the formatted information from the response body.

[0972] Input: HTTP response (including formatted information)

[0973] Output: Extracted formatting information

[0974] What happens: The browser or app receives the HTTP response, parses the response data, and extracts information in HTML or JSON format.

[0975] Step 9: The device displays the search results to the user

[0976] The device displays the extracted information on the user interface, specifically a list of evacuation shelters and detailed information.

[0977] Input: Extracted formatting information

[0978] Output: Display on the user interface

[0979] What happens: The browser or app adds information to the DOM tree and redraws to visually provide the evacuation information to the user.

[0980] Step 10: User confirms the results

[0981] The user checks the information displayed on the device and takes the necessary action. For example, they open a map app and start navigation based on the detailed information about the evacuation shelter displayed.

[0982] Input: what is displayed on the user interface

[0983] Output: User action (e.g., opening a map app, heading to a shelter)

[0984] Specific actions: The user looks at the device screen, checks the displayed evacuation shelter information, and decides on the next action. They tap the map app to start navigation.

[0985] (Application example 1)

[0986] 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."

[0987] Conventional map information systems are required to provide fast and accurate information during disasters and emergencies, but they often lack the precision to display information on device screens and analyze users' vague search queries. Furthermore, information display methods adapted to new devices such as smart glasses are inadequate, creating a need for a system that provides information to users in an intuitive and visually easy-to-understand format. Given this background, a system is needed that can analyze user queries in natural language and quickly retrieve and display relevant information.

[0988] 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.

[0989] In this invention, the server includes: means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; means for analyzing the received search query based on natural language processing and understanding the intent of the query; means for searching the database based on the analysis result and acquiring related map data and attribute information; means for formatting the acquired information in a format easily understandable by the user and transmitting it to the terminal; means for displaying the information received by the terminal to the user; an application installed on the smart glasses; means for analyzing the query using a natural language processing engine and extracting keywords; means for sending a request to the server based on the extracted keywords and receiving related information; and means for displaying the received information on a display of the smart glasses. This allows a user to intuitively and quickly check security-related map information and attribute information through the smart glasses.

[0990] "Location data" is digital information about a geographic location, and is data used to indicate a particular point on a map.

[0991] "Map data" refers to digital map data that visually represents geographical information about the Earth or a region, and includes information on roads, buildings, topography, and so on.

[0992] "Attribute information" is additional information related to map data, and refers to detailed data about a specific point or area (for example, address, telephone number, danger level, etc.).

[0993] A "database" is a structured collection of information, a store of digital information that is organized and managed for a specific purpose.

[0994] A "search query" is a phrase or sentence that a user enters into a device to search for information.

[0995] "Natural language processing" is a technology that allows computers to understand and analyze the language (natural language) that humans use on a daily basis.

[0996] "Query intent" refers to the purpose and content of the information a user wants to know or seek through a search query.

[0997] A "server" is a computer system that provides data or services in response to requests from other computers (clients).

[0998] "Smart glasses" are a type of wearable device that incorporates a display and sensors into the glasses and has the function of visually displaying information.

[0999] A "natural language processing engine" is software for performing natural language processing, and is a tool for analyzing text data to understand its meaning and intent.

[1000] "Keywords" are important phrases or terms extracted from a search query.

[1001] An "HTTP request" is a type of communication protocol used by a web browser or client to request data or services from a server.

[1002] A "display" is a display device for visually displaying information, including smart glasses and computer monitors.

[1003] To implement this invention, several major components are required. The configuration and operation of a specific system are described in detail below.

[1004] Server Roles and Processes

[1005] 1. Register the database:

[1006] The server registers map data and related attribute information (addresses, telephone numbers, risk levels, etc.) in a database. This database is a structured collection of information that is organized and managed according to specific purposes.

[1007] 2. Receiving and parsing search queries:

[1008] The server receives the search query sent from the device, which is then analyzed using a natural language processing engine (e.g., the spacy library) to extract important keywords.

[1009] 3. Searching the database and retrieving information:

[1010] Based on the parsed query, the server searches the database to retrieve relevant map data and attribute information. For example, for a query requesting information on the "nearest police station," the server retrieves details such as the location, address, and phone number of the nearest police station.

[1011] 4. Formatting and sending information:

[1012] The acquired information is formatted in a way that is easy for the user to understand, and the formatted information is sent to the terminal as an HTTP response.

[1013] Terminal roles and processing

[1014] 1. Getting and sending user input:

[1015] The device receives a search query from the user, for example, "Where is the nearest police station?", and sends the query to the server.

[1016] 2. Receiving and Displaying Search Results:

[1017] The device receives the HTTP response from the server and displays the search results to the user. For example, the smart glasses display briefly displays information such as "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789."

[1018] The role of smart glasses

[1019] 1. Install the application:

[1020] The smart glasses are installed with an application that requests information based on the parsed query and displays the obtained information.

[1021] 2. Parse the prompt:

[1022] A natural language processing engine is used to analyze the query and extract important keywords, for example using the spacy library.

[1023] 3. Display information:

[1024] Based on the extracted keywords, a request is sent to the server, relevant information is received, and it is displayed on the display of the smart glasses.

[1025] Examples and prompts

[1026] Specific examples

[1027] The user puts on the smart glasses and speaks to ask, "What is the nearest police station from here?" The application analyzes the query and presents information about the nearest police station.

[1028] Prompt Sentence Examples

[1029] User Query: "What is the nearest police station?"

[1030] Analyzed keywords: ["Police Station"]

[1031] Information obtained: {"name": "XX Police Station", "address": "XX City XX Town", "phone": "012-345-6789"}

[1032] In this way, the system allows users to intuitively and quickly view security-related map information and attribute information through smart glasses.

[1033] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1034] Step 1:

[1035] A user puts on the smart glasses and uses voice or text input to enter a query, such as "Where is the nearest police station from here?"

[1036] Input: User query (e.g., "Where is the nearest police station?")

[1037] Output: User query data (text format)

[1038] Step 2:

[1039] The device (smart glasses) receives a search query from the user and sends it to the server in the form of an HTTP request, which is how the query reaches the server.

[1040] Input: User query data

[1041] Output: HTTP request to the server

[1042] Step 3:

[1043] The server passes the received search query to a natural language processing engine, which parses the query and extracts important keywords, for example, using the spacy library.

[1044] Input: User query as an HTTP request

[1045] Output: Extracted keywords (e.g. "police station")

[1046] Step 4:

[1047] The server searches the database based on the analysis results and obtains relevant map data and attribute information (e.g., location information, address, telephone number, etc. of the nearest police station).

[1048] Input: Extracted keywords

[1049] Output: Associated map data and attribute information

[1050] Step 5:

[1051] The server formats the information it retrieves into a user-friendly format, which may include, for example, converting JSON-formatted data into human-readable text.

[1052] Input: Relevant map data and attribute information

[1053] Output: Formatted information (e.g., "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789")

[1054] Step 6:

[1055] The server sends the formatted information to the device as an HTTP response, and the device (smart glasses) receives this response.

[1056] Input: Formatted information

[1057] Output: HTTP response to the device

[1058] Step 7:

[1059] The device displays the received information on the user interface. Detailed information (e.g., "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789") is displayed on the smart glasses display.

[1060] Input: Formatted information as an HTTP response

[1061] Output: Information displayed on the smart glasses display

[1062] This step allows users to intuitively and quickly check the information they need through the smart glasses.

[1063] 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.

[1064] The present invention relates to a system that enables users to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. Furthermore, the present invention aims to provide users with the information they need more accurately and effectively by combining it with an emotion recognition engine that recognizes the user's emotions.

[1065] Overview of the system's programs and their processing

[1066] Server Roles and Operations

[1067] Registering map data and attribute information:

[1068] The server registers the map data and related attribute information (address, danger level on the hazard map, disaster response information for evacuation shelters, etc.) in a database. This registration is expected to enable quick search responses.

[1069] Receiving and parsing search queries:

[1070] The server receives the search query entered from the device. The received query is passed to a natural language processing engine for analysis. In this analysis step, the intent of the query and important keywords are extracted.

[1071] Emotion recognition:

[1072] When the server analyzes the search query, it also analyzes the user's emotional state using an emotion recognition engine, for example, to determine whether the user is in an emergency situation based on the content and wording of the query.

[1073] Searching the database and retrieving information:

[1074] The server searches the database based on the analysis results and the user's emotional state. For example, if the analysis results indicate a search for a nearby evacuation shelter and the user is in an emergency, the server will prioritize detailed information such as the location of the evacuation shelter and safe routes.

[1075] Formatting and sending information:

[1076] The acquired information is formatted into a form that is easy for the user to understand. Depending on the user's emotional state indicated by the emotion recognition engine, the way the information is presented (for example, by providing clearer instructions or including emergency contact information) is adjusted. The formatted information is then sent to the device.

[1077] Terminal roles and processing

[1078] Getting and sending user input:

[1079] The device receives a search query from the user. For example, the user types, "Where is the nearest evacuation shelter?" The device sends this query to the server.

[1080] Receiving and displaying search results:

[1081] The device receives the HTTP response from the server. The received search results are displayed in the user interface. For example, a list of evacuation shelters is displayed, and their details (addresses, phone numbers, etc.) are provided to the user.

[1082] User operation example

[1083] Enter and submit a query:

[1084] The user types "Where is the nearest evacuation shelter?" into the device and sends it.

[1085] Emotion recognition and display of results:

[1086] If the server analyzes the query and determines that the user is in an emergency, it quickly sends information about the best evacuation shelters, along with safe routes and other important contact information, to the device, which then displays it to the user.

[1087] This system combines natural language query input with emotion recognition to quickly and accurately provide users with the information they need. Especially in times of disaster, providing appropriate information based on the user's emotional state can encourage quick decisions and actions. In this way, the present invention can significantly improve the quality and speed of information provision.

[1088] The processing flow will be explained below.

[1089] Step 1:

[1090] A user enters a search query.

[1091] A user types a search query into the device interface, for example, "Where are the nearest evacuation centers?"

[1092] Step 2:

[1093] A user submits a search query.

[1094] The user presses the submit button to send the entered search query to the server.

[1095] Step 3:

[1096] The device sends a search query to the server.

[1097] The device generates an HTTP POST request containing the user-entered search query and sends it to the specified endpoint on the server.

[1098] Step 4:

[1099] A server receives a search query.

[1100] The server receives the HTTP POST request from the device and retrieves the query data for analysis.

[1101] Step 5:

[1102] The server parses the search query.

[1103] The server passes the received search query to a natural language processing engine, which extracts the query's intent and key keywords. This analysis identifies the information the user is looking for.

[1104] Step 6:

[1105] The server analyzes the user's emotions.

[1106] The server uses an emotion recognition engine to analyze the user's emotional state from the search query, for example, determining whether the user is experiencing an emergency based on the content of the query and the language used.

[1107] Step 7:

[1108] The server searches the database.

[1109] The server searches the database for relevant map data and attribute information based on the analysis of the search query and the user's emotional state, such as the location, address, phone number, and capacity of the evacuation shelter.

[1110] Step 8:

[1111] The server formats the search results.

[1112] The server formats the information it obtains into a format that is easy for the user to understand. The display format and content of the information are adjusted based on the user's emotional state indicated by the emotion recognition engine. For example, if the emergency is high, information on the shortest route to an evacuation shelter is added.

[1113] Step 9:

[1114] The server sends the search results to the terminal.

[1115] The server sends the formatted information to the terminal as an HTTP response.

[1116] Step 10:

[1117] The terminal receives the search results.

[1118] The terminal receives an HTTP response from the server.

[1119] Step 11:

[1120] Your device will display the search results.

[1121] The device displays the search results it receives in a user interface, such as a list of evacuation shelters with detailed information (e.g., address, phone number, capacity, etc.), and additional information (e.g., safe routes and emergency contacts) depending on the user's emotional state.

[1122] Step 12:

[1123] The user reviews the search results.

[1124] The user checks the search results displayed on the device and obtains the necessary information, for example, checking the route to the nearest evacuation shelter and preparing for emergency evacuation.

[1125] Example 2

[1126] 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."

[1127] Conventional map data systems simply provide location information, and have the problem of low response accuracy to user search queries. Furthermore, in emergencies such as disasters, it is difficult for users to quickly obtain the information they need, and information provision does not take into account the user's emotional state. This can result in delayed responses by users in emergencies.

[1128] 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.

[1129] In this invention, the server includes means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database, means for receiving a search query input from a terminal, means for analyzing the received search query based on natural language processing and understanding the intent of the query, means for performing emotion recognition during the analysis and determining the user's emotional state, means for searching the database based on the analysis result and the emotion recognition result and acquiring related map data and attribute information, means for formatting the acquired information into a format that is easy for the user to understand, adjusting the information presentation method according to the user's emotional state, and transmitting the information to the terminal, and means for displaying the information received by the terminal on a user interface. This makes it possible to respond quickly and accurately to a user's search query and provide information that takes the user's emotional state into consideration, particularly in an emergency.

[1130] "Location data" refers to data relating to a specific geographic location, including latitude and longitude.

[1131] "Map data" is data that visually represents geographical information, including roads, buildings, and natural topography.

[1132] "Attribute information" is additional information related to map data, and is data that includes specific characteristics such as addresses, telephone numbers, and seating capacity.

[1133] A "database" is a system for efficiently managing information and storing it in a form that can be searched and manipulated.

[1134] A "search query" is text data that expresses a question or request that a user inputs to a system.

[1135] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1136] "Emotion recognition" is a technology that determines a user's emotional state based on their input and behavior.

[1137] A "user interface" is an interface that allows interaction between a system and a user, and includes means for displaying and inputting information.

[1138] "Analysis results" refers to the conclusions or data obtained through processing search queries and emotion recognition.

[1139] "Information presentation method" refers to the format or means by which information is provided to the user, and includes text, images, audio, and the like.

[1140] The present invention is a system that enables a user to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. The system includes a server that registers map data including location information data and multiple attribute information related to the map data in a database, a server that receives and analyzes the search query entered from a terminal, a server that performs emotion recognition, a server that searches the database and obtains information based on the analysis and emotion recognition results, a server that formats the obtained information, adjusts the information presentation method according to the user's emotional state, and transmits the information to the terminal, and a user interface that displays the information received by the terminal.

[1141] Specifically, the server uses a GIS (geographic information system) to register map data and associated attribute information in a database. It uses OpenStreetMap data and its API as software, storing the information in a PostgreSQL database. It also passes search queries entered from the device to a natural language processing engine (for example, Google Cloud Natural Language API) for analysis. It then analyzes the user's emotional state using an emotion recognition engine (for example, IBM Watson Tone Analyzer). It searches the database using an SQL query based on the analysis and emotion recognition results to obtain the necessary map data and attribute information. The obtained information is formatted in HTML and organized as data to be displayed on a map using the Google Maps API. Finally, the formatted information is converted to JSON format and sent to the device as an HTTP response.

[1142] The device receives the search query from the user and sends it to the server as an HTTP request. The received search query is sent to the server in JSON format, for example, "query": "Where is the nearest evacuation shelter?". The device then receives an HTTP response from the server and displays the received data on the user interface. An example of the display would be information such as "The nearest evacuation shelter is on Third Street. What is the safe route?"

[1143] A user enters a search query into their device and clicks the send button, which sends the query to the server. If the server analyzes the query and determines that the user is in an emergency, it can quickly provide information on the best evacuation shelter, as well as safe routes and other important contact information.

[1144] Example prompt for a generative AI model:

[1145] If a user types "Where are the nearest shelters?", how would the server perform emotion recognition and provide information about the appropriate shelters?

[1146] This system combines natural language query input with emotion recognition to quickly and accurately provide users with the information they need. Especially in times of disaster, providing appropriate information based on the user's emotional state can encourage quick decisions and actions. In this way, the present invention can significantly improve the quality and speed of information provision.

[1147] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1148] Step 1:

[1149] Registering map data and attribute information

[1150] The server acquires map data using a GIS (geographic information system) and registers multiple related attribute information (addresses, danger levels on hazard maps, disaster response information for evacuation centers, etc.) in a database. This registration process is carried out using OpenStreetMap data and its API. The server stores the acquired map data and attribute information in a PostgreSQL database. It receives GIS data and attribute information as input and generates the information registered in the database as output.

[1151] Step 2:

[1152] Getting User Input

[1153] A user inputs a search query into a device. For example, the query "Where is the nearest evacuation center?" is entered into an input field. The system receives a natural language search query as input and captures the query on the client side. The output is the query data sent to the server.

[1154] Step 3:

[1155] Sending User Input

[1156] The device sends the search query entered by the user to the server as an HTTP request. It receives the search query as input and sends JSON format data (e.g., "query": "Where is the nearest evacuation center?") as output to the server.

[1157] Step 4:

[1158] Receiving and parsing search queries

[1159] The server receives the search query sent from the device. It passes the received query to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. It processes the data to extract the intent of the query and key keywords. It receives the search query as input and obtains the analyzed keywords and intent as output.

[1160] Step 5:

[1161] emotion recognition

[1162] The server passes the parsed query to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotional state. This analysis involves performing data calculations to determine whether the user is in an emergency situation. It receives the parsed query as input and obtains the user's emotional state as output.

[1163] Step 6:

[1164] Searching the database

[1165] The server generates an SQL query based on the analysis results and emotion recognition results, searches the database, and retrieves related map data and attribute information. It receives the analysis results and emotional state as input, and obtains the necessary map data and attribute information as output.

[1166] Step 7:

[1167] Formatting and sending information

[1168] The server formats the information it acquires into a format that is easy for the user to understand, and adjusts the way the information is presented based on the user's emotional state. Specifically, it formats the information in HTML format and prepares the data for display on a map using the Google Maps API. It converts this information into JSON format and sends it to the device as an HTTP response. It receives the acquired map data and attribute information as input, generates formatted information as output, and sends it to the device.

[1169] Step 8:

[1170] Receiving and displaying search results

[1171] The device receives the HTTP response from the server and displays the received data on the user interface. It receives the information sent from the server as input and generates search results that are displayed to the user as output. Specifically, information is displayed in a format such as, "The nearest evacuation shelter is on Third Street. The safe route is on which street."

[1172] (Application example 2)

[1173] 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."

[1174] In modern society, it is important to provide users with the information they desire quickly and accurately. However, conventional information search systems simply provide results based on the query without considering the user's emotional state, making it difficult to provide appropriate information based on the user's emotions and situation. In particular, when it comes to dining, a user's emotional state has a significant impact on satisfaction, so there is a need for restaurant selection and menu suggestions that reflect emotions.

[1175] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; means for analyzing the received search query using natural language processing and understanding the intent of the query; means for analyzing the user's emotional state using emotion recognition technology; means for searching the database based on the analysis result and the emotional state and acquiring related map data and attribute information; means for formatting the acquired information in a format that is easy for the user to understand and transmitting it to the terminal; and means for displaying the information received by the terminal to the user. This makes it possible to provide information that takes the user's emotional state into consideration, and particularly when selecting a dining facility, it is possible to suggest restaurants and menus that suit the user's emotions, thereby improving user satisfaction.

[1176] "Location information data" refers to data that indicates a geographical location, and includes coordinate information such as latitude and longitude.

[1177] "Map data" is data that visually represents geographical locations, and includes information on roads, buildings, landmarks, and the like.

[1178] "Attribute information" is additional information associated with a particular geographic location, including address, phone number, ratings, menu information, and the like.

[1179] "Means of registering in a database" refers to the processes and technologies for registering map data and attribute information in a database that can be centrally managed.

[1180] A "terminal" is a device that allows a user to input or receive information, and includes smartphones, tablets, head-mounted displays, etc.

[1181] A "search query" refers to a natural language sentence or phrase entered by a user to search for information.

[1182] "Natural language processing" refers to the technology that enables computers to understand and analyze natural human language.

[1183] "Emotion recognition technology" refers to technology that analyzes and recognizes a user's emotional state from their input and behavior.

[1184] "Analysis Results" refers to the information and data obtained using search query analysis and emotion recognition technology.

[1185] "Means of formatting the information in a format that is easy for the user to understand and sending it to the terminal" refers to the technology and processing for processing the acquired information so that it can be easily understood by the user and sending it to the terminal.

[1186] "Means for displaying" refers to the technology or method for visually displaying the information received on the terminal.

[1187] "Food and beverage establishments" are establishments that serve food and beverages, including restaurants, cafes, and fast food restaurants.

[1188] "Ratings" refers to user ratings and reviews of dining establishments and services provided.

[1189] "Business status" refers to the status of a food and beverage establishment, such as whether it is open or closed.

[1190] "Menu Information" means the list and details of the food and beverages served at a Food and Beverage Establishment.

[1191] "Emotion analysis results" refers to the results of analyzing a user's emotional state using emotion recognition technology.

[1192] A "recommended menu" refers to a list of food and drink suggestions based on the user's emotional state and preferences.

[1193] This invention relates to a system that quickly and intuitively acquires necessary map data and its attribute information based on a search query entered by a user in natural language, and further combines emotion recognition technology to provide information more accurately and effectively. As an application example, consider a restaurant recommendation system.

[1194] System Overview

[1195] The system of the present invention is mainly composed of a server and a user terminal. A user inputs a search query using a terminal such as a smartphone or a head-mounted display, and the server analyzes the query and provides appropriate information.

[1196] Hardware and software used

[1197] Hardware

[1198] Smartphone or head-mounted display

[1199] GPS function

[1200] microphone

[1201] software

[1202] Natural language processing engine (e.g. Google NLP API)

[1203] Emotion recognition engine (e.g. Microsoft Azure Emotion API)

[1204] Map API (e.g. Google Maps API)

[1205] Business management system (e.g., Firebase Realtime Database)

[1206] System Operation

[1207] 1. Getting User Input

[1208] A user uses a terminal to input a query in natural language about the food they want to eat or their mood, such as "I want to eat some delicious pizza nearby."

[1209] 2. Search Query Analysis

[1210] The device sends the user's query to the server, which then uses a natural language processing engine to analyze the query and extract its intent and keywords. For example, keywords such as "pizza" and "nearby" are extracted.

[1211] 3. Emotion Recognition Implementation

[1212] The server uses an emotion recognition engine to analyze the user's emotional state, recognizing emotions such as "tired" or "in a hurry" from search queries and vocabulary.

[1213] 4. Acquisition of Information

[1214] The server searches a map database based on the analysis results and the user's emotional state. For example, it obtains information such as the location, ratings, business hours, and menu information of nearby pizza restaurants. It also prioritizes the search results and provides the most suitable restaurants based on the user's emotional state.

[1215] 5. Formatting and sending information

[1216] The acquired information is formatted in a way that is easy for the user to understand. For example, if the emotion recognition engine determines that the user is in a hurry, restaurant information that can serve food quickly will be prioritized.

[1217] 6. Display of search results

[1218] The formatted information is sent to the terminal, which displays it to the user, who can then select the most suitable dining establishment based on the information provided.

[1219] Specific examples

[1220] If a user inputs a prompt such as "I've been tired since yesterday, so I want to eat some delicious pizza right now," the system will analyze the user's emotional state, such as "tired" or "right now," and search for pizza restaurants that can serve food quickly. The retrieved restaurant information is displayed on the device in an easy-to-understand format, allowing the user to easily find a suitable dining establishment.

[1221] The system of the present invention makes it possible to provide information that takes into account the user's emotional state, and can suggest restaurants and menus that best suit the user's needs, particularly when selecting a dining establishment, thereby providing a comfortable and satisfying experience.

[1222] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1223] Step 1:

[1224] A user uses a smartphone or a head-mounted display to input queries about the food they want to eat or their mood in natural language. For example, if a user inputs a query such as "I want to eat good pizza nearby," the input format is text or voice. The device receives this input and sends it to the server. The input data is the query text, and the output is the data to be sent to the server.

[1225] Step 2:

[1226] The server passes the search query received from the device to a natural language processing engine for analysis. The input is the search query text, and the output is the analysis results and extracted keywords. Specifically, it uses the Google NLP API to extract important keywords from the text (e.g., "pizza" or "nearby") and the intent of the query.

[1227] Step 3:

[1228] The server uses an emotion recognition engine to analyze the user's emotional state from the search query text. The input is the search query text, and the output is the emotion recognition result. Specifically, it uses the Microsoft Azure Emotion API to determine the user's emotional state (e.g., "I'm in a hurry" or "I'm tired") from the content and wording of the query.

[1229] Step 4:

[1230] The server searches the map database based on the query analysis results and emotion recognition results. The input is the analysis results and emotion recognition results, and the output is related map data and attribute information. Specifically, it uses the Google Maps API to obtain location information and attribute information (e.g., ratings, business status, menu information) of the restaurant that best suits the user.

[1231] Step 5:

[1232] The server formats the map data and attribute information it obtains into a format that is easy for the user to understand. The input is search result data, and the output is the formatted data. Specific operations include adjusting the way information is presented depending on the user's emotional state (e.g., if the user is "in a hurry," prioritize displaying restaurant information that allows quick ordering).

[1233] Step 6:

[1234] The server sends the formatted information to the terminal. The input is the formatted data, and the output is the data sent to the terminal. Specifically, the server sends the necessary information to the user as an HTTP response.

[1235] Step 7:

[1236] The terminal displays the information it receives to the user. The input is the data received from the server, and the output is the content displayed on the user interface. Specifically, it displays restaurant information and menu information suitable for the user on the screen, allowing the user to easily refer to that information.

[1237] The above processing steps enable users to quickly and accurately obtain information on appropriate dining establishments. Because this system takes into account the user's emotional state, it can provide information that is more satisfying.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] [Fourth embodiment]

[1242] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1243] 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.

[1244] 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).

[1245] 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.

[1246] 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.

[1247] 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).

[1248] 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.

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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."

[1255] This invention relates to a system that allows users to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. Specifically, map data and multiple related attribute information are registered in a database, and the search query is analyzed using natural language processing to retrieve and display related information, enabling the rapid provision of information in the event of a disaster.

[1256] Overview of the system's programs and their processing

[1257] Server Roles and Operations

[1258] Registering map data and attribute information:

[1259] The server registers map data and related attribute information (address, hazard map danger level, evacuation shelter disaster response information, etc.) in a database, enabling quick responses to search queries.

[1260] Receiving and parsing search queries:

[1261] The server receives the search query entered from the device. The received query is passed to a natural language processing engine for analysis. In this analysis step, the intent of the query and important keywords are extracted.

[1262] Searching the database and retrieving information:

[1263] Based on the parsed query, the server searches for relevant map data and attribute information in the database. For example, for a query requesting information on "nearby shelters," the server retrieves details such as the location, address, phone number, and capacity of the nearest shelter.

[1264] Formatting and sending information:

[1265] The acquired information is formatted in a way that is easy for the user to understand, and the formatted information is sent to the terminal as an HTTP response.

[1266] Terminal roles and processing

[1267] Getting and sending user input:

[1268] The device receives a search query from the user. For example, the user types, "Where is the nearest evacuation shelter?" The device sends this query to the server.

[1269] Receiving and displaying search results:

[1270] The terminal receives the HTTP response from the server. The received search results are displayed in the user interface. For example, a list of evacuation shelters is displayed, and their details (addresses, phone numbers, etc.) are provided to the user.

[1271] User operation example

[1272] Entering and sending a query: The user enters "Where is the nearest shelter?" into the device and sends it.

[1273] Check the results: Check the shelter information displayed on the device. For example, details such as "Shelter: XX Park, Address: XX City XX Town, Phone Number: 012-345-6789" will be displayed.

[1274] This system quickly and efficiently retrieves and provides relevant information based on natural language queries, demonstrating exceptional effectiveness in gathering information during disasters. Such a system allows users to intuitively and quickly obtain the information they need, enabling them to make quick decisions and take action in emergencies.

[1275] The processing flow will be explained below.

[1276] Step 1:

[1277] A user enters a search query.

[1278] A user types a search query into a device, for example, "Where are the nearest evacuation centers?"

[1279] Step 2:

[1280] A user submits a search query.

[1281] The user presses the submit button to send the query to the server.

[1282] Step 3:

[1283] The device sends a search query to the server.

[1284] The device generates an HTTP POST request containing the user's input and sends it to the specified endpoint on the server.

[1285] Step 4:

[1286] A server receives a search query.

[1287] The server receives an HTTP POST request from the terminal and obtains the query.

[1288] Step 5:

[1289] The server parses the search query.

[1290] The server passes the received search query to a natural language processing engine, which analyzes the query's intent, extracting important keywords and user intent.

[1291] Step 6:

[1292] The server searches the database.

[1293] The server searches the database based on the analysis results. For example, if the analysis results indicate that the user is searching for a nearby shelter, the server retrieves information about the shelter from the database.

[1294] Step 7:

[1295] The server formats the search results.

[1296] The server formats the data it acquires into a format that is easy for users to understand. For example, it formats information such as the name, address, telephone number, and capacity of the evacuation shelter into a list.

[1297] Step 8:

[1298] The server sends the search results to the terminal.

[1299] The server sends the formatted information to the terminal as an HTTP response.

[1300] Step 9:

[1301] The terminal receives the search results.

[1302] The terminal receives an HTTP response from the server.

[1303] Step 10:

[1304] Your device will display the search results.

[1305] The terminal displays the received search results on a user interface, for example, a list of evacuation shelters is displayed and their details (addresses, telephone numbers, etc.) are provided to the user.

[1306] Step 11:

[1307] The user reviews the search results.

[1308] The user checks the search results displayed on the device and decides on the next action, for example, preparing to go to the nearest evacuation shelter.

[1309] Example 1

[1310] 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."

[1311] There is a lack of means to quickly and intuitively obtain map information and its related attribute information, which is a problem especially in times of disaster, where users are unable to immediately obtain the information they need.There is a need for a system that efficiently provides information necessary in emergencies, such as information on evacuation shelters and hazards.

[1312] 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.

[1313] In this invention, the server includes means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database, means for receiving a search query input from a terminal, means for analyzing the received search query using natural language processing and understanding the intent of the query, means for searching the database based on the analysis result and acquiring related map data and attribute information, means for formatting the acquired information in a format that is easy for the user to understand and transmitting it to the terminal, means for displaying the information received by the terminal to the user, and means for formatting and transmitting data that is effective for quickly providing map information incorporating evacuation shelter information. This enables a user to quickly and intuitively obtain the necessary map data and its attribute information based on a query input in natural language.

[1314] "Location information data" is data that indicates a specific point or area on a map, and includes coordinate information such as latitude and longitude.

[1315] "Map data" is digital data that visually represents geographical information, and includes information on roads, buildings, natural topography, and the like.

[1316] "Attribute information" is additional information related to map data, and includes additional information such as addresses, telephone numbers, facility features and functions, and disaster response information.

[1317] A "database" is a structured electronic file system that systematically stores map data and its associated attribute information, making it easy to search and retrieve.

[1318] A "search query" is a question or keyword that a user inputs into a terminal to obtain the information they need.

[1319] "Means for receiving" refers to the function or method by which the server receives the search query sent from the terminal.

[1320] "Natural language processing" is a technology that allows computers to understand and process human language, and includes text analysis, keyword extraction, and context understanding.

[1321] "Means for analyzing" refers to a method of analyzing the content of a received search query using natural language processing technology and extracting the intent of the query and important keywords.

[1322] "Means for obtaining" refers to the method or function for searching and extracting related map data and attribute information from the database based on the analysis results.

[1323] "Formatting" refers to a method for converting acquired information into a format that is easy for users to understand, such as converting into HTML or JSON format.

[1324] "Means for sending" refers to the function or method by which the server sends formatted information to the terminal.

[1325] The "means for displaying" refers to a method for displaying the information received by the terminal on the user interface and visually providing it to the user.

[1326] "Shelter information" refers to information about places to evacuate to in the event of a disaster, and includes data such as location information, addresses, telephone numbers, and capacity.

[1327] A "hazard map" is a map that visually shows the risk of natural disasters in a specific area, and includes risk information such as floods, earthquakes, and tsunamis.

[1328] This invention relates to a system that quickly and intuitively provides necessary map data and related attribute information based on a search query entered by a user in natural language. Specifically, this system registers map data and related attribute information in a database, analyzes the search query using natural language processing technology, and retrieves and displays related information, enabling the rapid provision of information, particularly in the event of a disaster.

[1329] The server registers map data and related attribute information (e.g., addresses, risk levels on hazard maps, disaster response information for evacuation centers, etc.) in a database. This database is constructed using a database management system such as MySQL or PostgreSQL.

[1330] A device (e.g., a smartphone or PC) receives a search query from a user. For example, if a user types "Where is the nearest evacuation shelter?" into the device, this query is sent from the device to the server as an HTTP request.

[1331] The server passes the received search query to a natural language processing engine (e.g., NLTK or SpaCy) to analyze the query's intent and important keywords. For example, the keyword "nearby shelter" is extracted.

[1332] Based on the analysis results, the server searches the database to retrieve relevant map data and attribute information. For example, the server uses the user's current location information to retrieve details such as the location, address, phone number, and capacity of the nearest evacuation shelter.

[1333] The acquired information is formatted into a user-friendly format. During this formatting process, the information is converted into HTML or JSON format, and the information is converted into a user-friendly format. For example, the formatting might be "Evacuation shelter: XX Park, Address: XX City XX Town, Phone number: 012-345-6789."

[1334] The formatted information is sent from the server to the device as an HTTP response. The device receives the HTTP response from the server and displays it in a user interface. As a specific example, a list of shelters and detailed information is displayed on the screen using UI components in a browser or native app.

[1335] Users can check the information displayed on their device screen and take necessary actions. For example, they can refer to the detailed information of the evacuation shelter displayed on their device, open a map app such as Google Maps, and start navigation. In this way, the system provides users with information quickly and intuitively.

[1336] An example of a prompt might be:

[1337] Please explain in natural language the processing flow when the following search query is entered: Example query: A user types "Where is the nearest evacuation center?" into their device and submits it.

[1338] As such, the present invention is a system that enables the rapid and efficient acquisition and provision of relevant information based on natural language queries, and is particularly effective in gathering information during disasters.

[1339] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1340] Step 1: The user enters a search query in natural language into the device.

[1341] A user enters a search query such as "Where is the nearest evacuation shelter?" into a browser on their smartphone or PC, or into a dedicated app. The entered query is saved in text format on the device.

[1342] Input: Natural language input by the user (e.g., "Where is the nearest evacuation center?")

[1343] Output: Search query in plain text

[1344] Specific action: The user types a query using the keyboard or voice input, and presses the Enter key in the input box or clicks the submit button.

[1345] Step 2: The device sends the search query to the server

[1346] The device sends the entered search query to the server as an HTTP request, which includes the query text and the user's current location information.

[1347] Input: Text search query, user location

[1348] Output: HTTP request (including search query and current location information)

[1349] What it does: Your browser or app packages the query and your current location information to create an HTTP POST request, which is then sent to the server by pressing the submit button.

[1350] Step 3: The server receives the search query

[1351] The server receives the HTTP request sent from the device and extracts the search query and current location information from the received request.

[1352] Input: HTTP request (including search query and current location information)

[1353] Output: Extracted search query and current location information

[1354] What happens: The server's API endpoint receives the HTTP request and parses and extracts the search query and current location information from the request body.

[1355] Step 4: The server analyzes the search query using a natural language processing engine

[1356] The server passes the extracted search query to a natural language processing engine (e.g., NLTK or SpaCy) to analyze the query's intent and important keywords.

[1357] Input: Search query

[1358] Output: Analysis results (intent and important keywords)

[1359] Specific operation: The server calls the natural language processing library and passes the search query as input data to the analysis function. For example, the keyword "nearby shelter" is extracted as the analysis result.

[1360] Step 5: The server searches the database

[1361] The server searches a database (e.g., MySQL or PostgreSQL) based on the analysis results to retrieve relevant map data and attribute information.

[1362] Input: Analysis results (important keywords), user's current location information

[1363] Output: Related map data and attribute information (e.g., shelter location, address, phone number, capacity)

[1364] Specific operation: The server generates an SQL query and executes a search against the database. For example, it issues a SELECT statement to retrieve data about "nearby shelters" and retrieves information about the nearest shelter.

[1365] Step 6: Format the information retrieved by the server

[1366] The server formats the map data and attribute information it has acquired into a format that is easy for users to understand. In this process, the data is converted into HTML or JSON format.

[1367] Input: Relevant map data and attribute information

[1368] Output: Formatted information (e.g., shelter information in HTML or JSON format)

[1369] What happens: The server uses a template engine (e.g. Jinja2) to embed data into templates and convert them into user-friendly HTML or JSON format.

[1370] Step 7: The server sends the formatted information to the device

[1371] The server sends the formatted information to the terminal as an HTTP response.

[1372] Input: Formatted information (e.g., shelter information in HTML or JSON format)

[1373] Output: HTTP response (including formatted information)

[1374] Specific operation: The server sets the HTTP response header, inserts formatted information into the response body, and sends it to the terminal.

[1375] Step 8: Your device receives the search results

[1376] The terminal receives the HTTP response from the server and extracts the formatted information from the response body.

[1377] Input: HTTP response (including formatted information)

[1378] Output: Extracted formatting information

[1379] What happens: The browser or app receives the HTTP response, parses the response data, and extracts information in HTML or JSON format.

[1380] Step 9: The device displays the search results to the user

[1381] The device displays the extracted information on the user interface, specifically a list of evacuation shelters and detailed information.

[1382] Input: Extracted formatting information

[1383] Output: Display on the user interface

[1384] What happens: The browser or app adds information to the DOM tree and redraws to visually provide the evacuation information to the user.

[1385] Step 10: User confirms the results

[1386] The user checks the information displayed on the device and takes the necessary action. For example, they open a map app and start navigation based on the detailed information about the evacuation shelter displayed.

[1387] Input: what is displayed on the user interface

[1388] Output: User action (e.g., opening a map app, heading to a shelter)

[1389] Specific actions: The user looks at the device screen, checks the displayed evacuation shelter information, and decides on the next action. They tap the map app to start navigation.

[1390] (Application example 1)

[1391] 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."

[1392] Conventional map information systems are required to provide fast and accurate information during disasters and emergencies, but they often lack the precision to display information on device screens and analyze users' vague search queries. Furthermore, information display methods adapted to new devices such as smart glasses are inadequate, creating a need for a system that provides information to users in an intuitive and visually easy-to-understand format. Given this background, a system is needed that can analyze user queries in natural language and quickly retrieve and display relevant information.

[1393] 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.

[1394] In this invention, the server includes: means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; means for analyzing the received search query based on natural language processing and understanding the intent of the query; means for searching the database based on the analysis result and acquiring related map data and attribute information; means for formatting the acquired information in a format easily understandable by the user and transmitting it to the terminal; means for displaying the information received by the terminal to the user; an application installed on the smart glasses; means for analyzing the query using a natural language processing engine and extracting keywords; means for sending a request to the server based on the extracted keywords and receiving related information; and means for displaying the received information on a display of the smart glasses. This allows a user to intuitively and quickly check security-related map information and attribute information through the smart glasses.

[1395] "Location data" is digital information about a geographic location, and is data used to indicate a particular point on a map.

[1396] "Map data" refers to digital map data that visually represents geographical information about the Earth or a region, and includes information on roads, buildings, topography, and so on.

[1397] "Attribute information" is additional information related to map data, and refers to detailed data about a specific point or area (for example, address, telephone number, danger level, etc.).

[1398] A "database" is a structured collection of information, a store of digital information that is organized and managed for a specific purpose.

[1399] A "search query" is a phrase or sentence that a user enters into a device to search for information.

[1400] "Natural language processing" is a technology that allows computers to understand and analyze the language (natural language) that humans use on a daily basis.

[1401] "Query intent" refers to the purpose and content of the information a user wants to know or seek through a search query.

[1402] A "server" is a computer system that provides data or services in response to requests from other computers (clients).

[1403] "Smart glasses" are a type of wearable device that incorporates a display and sensors into the glasses and has the function of visually displaying information.

[1404] A "natural language processing engine" is software for performing natural language processing, and is a tool for analyzing text data to understand its meaning and intent.

[1405] "Keywords" are important phrases or terms extracted from a search query.

[1406] An "HTTP request" is a type of communication protocol used by a web browser or client to request data or services from a server.

[1407] A "display" is a display device for visually displaying information, including smart glasses and computer monitors.

[1408] To implement this invention, several major components are required. The configuration and operation of a specific system are described in detail below.

[1409] Server Roles and Processes

[1410] 1. Register the database:

[1411] The server registers map data and related attribute information (addresses, telephone numbers, risk levels, etc.) in a database. This database is a structured collection of information that is organized and managed according to specific purposes.

[1412] 2. Receiving and parsing search queries:

[1413] The server receives the search query sent from the device, which is then analyzed using a natural language processing engine (e.g., the spacy library) to extract important keywords.

[1414] 3. Searching the database and retrieving information:

[1415] Based on the parsed query, the server searches the database to retrieve relevant map data and attribute information. For example, for a query requesting information on the "nearest police station," the server retrieves details such as the location, address, and phone number of the nearest police station.

[1416] 4. Formatting and sending information:

[1417] The acquired information is formatted in a way that is easy for the user to understand, and the formatted information is sent to the terminal as an HTTP response.

[1418] Terminal roles and processing

[1419] 1. Getting and sending user input:

[1420] The device receives a search query from the user, for example, "Where is the nearest police station?", and sends the query to the server.

[1421] 2. Receiving and Displaying Search Results:

[1422] The device receives the HTTP response from the server and displays the search results to the user. For example, the smart glasses display briefly displays information such as "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789."

[1423] The role of smart glasses

[1424] 1. Install the application:

[1425] The smart glasses are installed with an application that requests information based on the parsed query and displays the obtained information.

[1426] 2. Parse the prompt:

[1427] A natural language processing engine is used to analyze the query and extract important keywords, for example using the spacy library.

[1428] 3. Display information:

[1429] Based on the extracted keywords, a request is sent to the server, relevant information is received, and it is displayed on the display of the smart glasses.

[1430] Examples and prompts

[1431] Specific examples

[1432] The user puts on the smart glasses and speaks to ask, "What is the nearest police station from here?" The application analyzes the query and presents information about the nearest police station.

[1433] Prompt Sentence Examples

[1434] User Query: "What is the nearest police station?"

[1435] Analyzed keywords: ["Police Station"]

[1436] Information obtained: {"name": "XX Police Station", "address": "XX City XX Town", "phone": "012-345-6789"}

[1437] In this way, the system allows users to intuitively and quickly view security-related map information and attribute information through smart glasses.

[1438] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1439] Step 1:

[1440] A user puts on the smart glasses and uses voice or text input to enter a query, such as "Where is the nearest police station from here?"

[1441] Input: User query (e.g., "Where is the nearest police station?")

[1442] Output: User query data (text format)

[1443] Step 2:

[1444] The device (smart glasses) receives a search query from the user and sends it to the server in the form of an HTTP request, which is how the query reaches the server.

[1445] Input: User query data

[1446] Output: HTTP request to the server

[1447] Step 3:

[1448] The server passes the received search query to a natural language processing engine, which parses the query and extracts important keywords, for example, using the spacy library.

[1449] Input: User query as an HTTP request

[1450] Output: Extracted keywords (e.g. "police station")

[1451] Step 4:

[1452] The server searches the database based on the analysis results and obtains relevant map data and attribute information (e.g., location information, address, telephone number, etc. of the nearest police station).

[1453] Input: Extracted keywords

[1454] Output: Associated map data and attribute information

[1455] Step 5:

[1456] The server formats the information it retrieves into a user-friendly format, which may include, for example, converting JSON-formatted data into human-readable text.

[1457] Input: Relevant map data and attribute information

[1458] Output: Formatted information (e.g., "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789")

[1459] Step 6:

[1460] The server sends the formatted information to the device as an HTTP response, and the device (smart glasses) receives this response.

[1461] Input: Formatted information

[1462] Output: HTTP response to the device

[1463] Step 7:

[1464] The device displays the received information on the user interface. Detailed information (e.g., "Name: XX Police Station, Address: XX City XX Town, Phone Number: 012-345-6789") is displayed on the smart glasses display.

[1465] Input: Formatted information as an HTTP response

[1466] Output: Information displayed on the smart glasses display

[1467] This step allows users to intuitively and quickly check the information they need through the smart glasses.

[1468] 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.

[1469] The present invention relates to a system that enables users to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. Furthermore, the present invention aims to provide users with the information they need more accurately and effectively by combining it with an emotion recognition engine that recognizes the user's emotions.

[1470] Overview of the system's programs and their processing

[1471] Server Roles and Operations

[1472] Registering map data and attribute information:

[1473] The server registers the map data and related attribute information (address, danger level on the hazard map, disaster response information for evacuation shelters, etc.) in a database. This registration is expected to enable quick search responses.

[1474] Receiving and parsing search queries:

[1475] The server receives the search query entered from the device. The received query is passed to a natural language processing engine for analysis. In this analysis step, the intent of the query and important keywords are extracted.

[1476] Emotion recognition:

[1477] When the server analyzes the search query, it also analyzes the user's emotional state using an emotion recognition engine, for example, to determine whether the user is in an emergency situation based on the content and wording of the query.

[1478] Searching the database and retrieving information:

[1479] The server searches the database based on the analysis results and the user's emotional state. For example, if the analysis results indicate a search for a nearby evacuation shelter and the user is in an emergency, the server will prioritize detailed information such as the location of the evacuation shelter and safe routes.

[1480] Formatting and sending information:

[1481] The acquired information is formatted into a form that is easy for the user to understand. Depending on the user's emotional state indicated by the emotion recognition engine, the way the information is presented (for example, by providing clearer instructions or including emergency contact information) is adjusted. The formatted information is then sent to the device.

[1482] Terminal roles and processing

[1483] Getting and sending user input:

[1484] The device receives a search query from the user. For example, the user types, "Where is the nearest evacuation shelter?" The device sends this query to the server.

[1485] Receiving and displaying search results:

[1486] The device receives the HTTP response from the server. The received search results are displayed in the user interface. For example, a list of evacuation shelters is displayed, and their details (addresses, phone numbers, etc.) are provided to the user.

[1487] User operation example

[1488] Enter and submit a query:

[1489] The user types "Where is the nearest evacuation shelter?" into the device and sends it.

[1490] Emotion recognition and display of results:

[1491] If the server analyzes the query and determines that the user is in an emergency, it quickly sends information about the best evacuation shelters, along with safe routes and other important contact information, to the device, which then displays it to the user.

[1492] This system combines natural language query input with emotion recognition to quickly and accurately provide users with the information they need. Especially in times of disaster, providing appropriate information based on the user's emotional state can encourage quick decisions and actions. In this way, the present invention can significantly improve the quality and speed of information provision.

[1493] The processing flow will be explained below.

[1494] Step 1:

[1495] A user enters a search query.

[1496] A user types a search query into the device interface, for example, "Where are the nearest evacuation centers?"

[1497] Step 2:

[1498] A user submits a search query.

[1499] The user presses the submit button to send the entered search query to the server.

[1500] Step 3:

[1501] The device sends a search query to the server.

[1502] The device generates an HTTP POST request containing the user-entered search query and sends it to the specified endpoint on the server.

[1503] Step 4:

[1504] A server receives a search query.

[1505] The server receives the HTTP POST request from the device and retrieves the query data for analysis.

[1506] Step 5:

[1507] The server parses the search query.

[1508] The server passes the received search query to a natural language processing engine, which extracts the query's intent and key keywords. This analysis identifies the information the user is looking for.

[1509] Step 6:

[1510] The server analyzes the user's emotions.

[1511] The server uses an emotion recognition engine to analyze the user's emotional state from the search query, for example, determining whether the user is experiencing an emergency based on the content of the query and the language used.

[1512] Step 7:

[1513] The server searches the database.

[1514] The server searches the database for relevant map data and attribute information based on the analysis of the search query and the user's emotional state, such as the location, address, phone number, and capacity of the evacuation shelter.

[1515] Step 8:

[1516] The server formats the search results.

[1517] The server formats the information it obtains into a format that is easy for the user to understand. The display format and content of the information are adjusted based on the user's emotional state indicated by the emotion recognition engine. For example, if the emergency is high, information on the shortest route to an evacuation shelter is added.

[1518] Step 9:

[1519] The server sends the search results to the terminal.

[1520] The server sends the formatted information to the terminal as an HTTP response.

[1521] Step 10:

[1522] The terminal receives the search results.

[1523] The terminal receives an HTTP response from the server.

[1524] Step 11:

[1525] Your device will display the search results.

[1526] The device displays the search results it receives in a user interface, such as a list of evacuation shelters with detailed information (e.g., address, phone number, capacity, etc.), and additional information (e.g., safe routes and emergency contacts) depending on the user's emotional state.

[1527] Step 12:

[1528] The user reviews the search results.

[1529] The user checks the search results displayed on the device and obtains the necessary information, for example, checking the route to the nearest evacuation shelter and preparing for emergency evacuation.

[1530] Example 2

[1531] 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."

[1532] Conventional map data systems simply provide location information, and have the problem of low response accuracy to user search queries. Furthermore, in emergencies such as disasters, it is difficult for users to quickly obtain the information they need, and information provision does not take into account the user's emotional state. This can result in delayed responses by users in emergencies.

[1533] 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.

[1534] In this invention, the server includes means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database, means for receiving a search query input from a terminal, means for analyzing the received search query based on natural language processing and understanding the intent of the query, means for performing emotion recognition during the analysis and determining the user's emotional state, means for searching the database based on the analysis result and the emotion recognition result and acquiring related map data and attribute information, means for formatting the acquired information into a format that is easy for the user to understand, adjusting the information presentation method according to the user's emotional state, and transmitting the information to the terminal, and means for displaying the information received by the terminal on a user interface. This makes it possible to respond quickly and accurately to a user's search query and provide information that takes the user's emotional state into consideration, particularly in an emergency.

[1535] "Location data" refers to data relating to a specific geographic location, including latitude and longitude.

[1536] "Map data" is data that visually represents geographical information, including roads, buildings, and natural topography.

[1537] "Attribute information" is additional information related to map data, and is data that includes specific characteristics such as addresses, telephone numbers, and seating capacity.

[1538] A "database" is a system for efficiently managing information and storing it in a form that can be searched and manipulated.

[1539] A "search query" is text data that expresses a question or request that a user inputs to a system.

[1540] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1541] "Emotion recognition" is a technology that determines a user's emotional state based on their input and behavior.

[1542] A "user interface" is an interface that allows interaction between a system and a user, and includes means for displaying and inputting information.

[1543] "Analysis results" refers to the conclusions or data obtained through processing search queries and emotion recognition.

[1544] "Information presentation method" refers to the format or means by which information is provided to the user, and includes text, images, audio, and the like.

[1545] The present invention is a system that enables a user to quickly and intuitively obtain necessary map data and its attribute information based on a search query entered in natural language. The system includes a server that registers map data including location information data and multiple attribute information related to the map data in a database, a server that receives and analyzes the search query entered from a terminal, a server that performs emotion recognition, a server that searches the database and obtains information based on the analysis and emotion recognition results, a server that formats the obtained information, adjusts the information presentation method according to the user's emotional state, and transmits the information to the terminal, and a user interface that displays the information received by the terminal.

[1546] Specifically, the server uses a GIS (geographic information system) to register map data and associated attribute information in a database. It uses OpenStreetMap data and its API as software, storing the information in a PostgreSQL database. It also passes search queries entered from the device to a natural language processing engine (for example, Google Cloud Natural Language API) for analysis. It then analyzes the user's emotional state using an emotion recognition engine (for example, IBM Watson Tone Analyzer). It searches the database using an SQL query based on the analysis and emotion recognition results to obtain the necessary map data and attribute information. The obtained information is formatted in HTML and organized as data to be displayed on a map using the Google Maps API. Finally, the formatted information is converted to JSON format and sent to the device as an HTTP response.

[1547] The device receives the search query from the user and sends it to the server as an HTTP request. The received search query is sent to the server in JSON format, for example, "query": "Where is the nearest evacuation shelter?". The device then receives an HTTP response from the server and displays the received data on the user interface. An example of the display would be information such as "The nearest evacuation shelter is on Third Street. What is the safe route?"

[1548] A user enters a search query into their device and clicks the send button, which sends the query to the server. If the server analyzes the query and determines that the user is in an emergency, it can quickly provide information on the best evacuation shelter, as well as safe routes and other important contact information.

[1549] Example prompt for a generative AI model:

[1550] If a user types "Where are the nearest shelters?", how would the server perform emotion recognition and provide information about the appropriate shelters?

[1551] This system combines natural language query input with emotion recognition to quickly and accurately provide users with the information they need. Especially in times of disaster, providing appropriate information based on the user's emotional state can encourage quick decisions and actions. In this way, the present invention can significantly improve the quality and speed of information provision.

[1552] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1553] Step 1:

[1554] Registering map data and attribute information

[1555] The server acquires map data using a GIS (geographic information system) and registers multiple related attribute information (addresses, danger levels on hazard maps, disaster response information for evacuation centers, etc.) in a database. This registration process is carried out using OpenStreetMap data and its API. The server stores the acquired map data and attribute information in a PostgreSQL database. It receives GIS data and attribute information as input and generates the information registered in the database as output.

[1556] Step 2:

[1557] Getting User Input

[1558] A user inputs a search query into a device. For example, the query "Where is the nearest evacuation center?" is entered into an input field. The system receives a natural language search query as input and captures the query on the client side. The output is the query data sent to the server.

[1559] Step 3:

[1560] Sending User Input

[1561] The device sends the search query entered by the user to the server as an HTTP request. It receives the search query as input and sends JSON format data (e.g., "query": "Where is the nearest evacuation center?") as output to the server.

[1562] Step 4:

[1563] Receiving and parsing search queries

[1564] The server receives the search query sent from the device. It passes the received query to a natural language processing engine (e.g., Google Cloud Natural Language API) for analysis. It processes the data to extract the intent of the query and key keywords. It receives the search query as input and obtains the analyzed keywords and intent as output.

[1565] Step 5:

[1566] emotion recognition

[1567] The server passes the parsed query to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotional state. This analysis involves performing data calculations to determine whether the user is in an emergency situation. It receives the parsed query as input and obtains the user's emotional state as output.

[1568] Step 6:

[1569] Searching the database

[1570] The server generates an SQL query based on the analysis results and emotion recognition results, searches the database, and retrieves related map data and attribute information. It receives the analysis results and emotional state as input, and obtains the necessary map data and attribute information as output.

[1571] Step 7:

[1572] Formatting and sending information

[1573] The server formats the information it acquires into a format that is easy for the user to understand, and adjusts the way the information is presented based on the user's emotional state. Specifically, it formats the information in HTML format and prepares the data for display on a map using the Google Maps API. It converts this information into JSON format and sends it to the device as an HTTP response. It receives the acquired map data and attribute information as input, generates formatted information as output, and sends it to the device.

[1574] Step 8:

[1575] Receiving and displaying search results

[1576] The device receives the HTTP response from the server and displays the received data on the user interface. It receives the information sent from the server as input and generates search results that are displayed to the user as output. Specifically, information is displayed in a format such as, "The nearest evacuation shelter is on Third Street. The safe route is on which street."

[1577] (Application example 2)

[1578] 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."

[1579] In modern society, it is important to provide users with the information they desire quickly and accurately. However, conventional information search systems simply provide results based on the query without considering the user's emotional state, making it difficult to provide appropriate information based on the user's emotions and situation. In particular, when it comes to dining, a user's emotional state has a significant impact on satisfaction, so there is a need for restaurant selection and menu suggestions that reflect emotions.

[1580] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for registering map data including location information data and multiple pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; means for analyzing the received search query using natural language processing and understanding the intent of the query; means for analyzing the user's emotional state using emotion recognition technology; means for searching the database based on the analysis result and the emotional state and acquiring related map data and attribute information; means for formatting the acquired information in a format that is easy for the user to understand and transmitting it to the terminal; and means for displaying the information received by the terminal to the user. This makes it possible to provide information that takes the user's emotional state into consideration, and particularly when selecting a dining facility, it is possible to suggest restaurants and menus that suit the user's emotions, thereby improving user satisfaction.

[1581] "Location information data" refers to data that indicates a geographical location, and includes coordinate information such as latitude and longitude.

[1582] "Map data" is data that visually represents geographical locations, and includes information on roads, buildings, landmarks, and the like.

[1583] "Attribute information" is additional information associated with a particular geographic location, including address, phone number, ratings, menu information, and the like.

[1584] "Means of registering in a database" refers to the processes and technologies for registering map data and attribute information in a database that can be centrally managed.

[1585] A "terminal" is a device that allows a user to input or receive information, and includes smartphones, tablets, head-mounted displays, etc.

[1586] A "search query" refers to a natural language sentence or phrase entered by a user to search for information.

[1587] "Natural language processing" refers to the technology that enables computers to understand and analyze natural human language.

[1588] "Emotion recognition technology" refers to technology that analyzes and recognizes a user's emotional state from their input and behavior.

[1589] "Analysis Results" refers to the information and data obtained using search query analysis and emotion recognition technology.

[1590] "Means of formatting the information in a format that is easy for the user to understand and sending it to the terminal" refers to the technology and processing for processing the acquired information so that it can be easily understood by the user and sending it to the terminal.

[1591] "Means for displaying" refers to the technology or method for visually displaying the information received on the terminal.

[1592] "Food and beverage establishments" are establishments that serve food and beverages, including restaurants, cafes, and fast food restaurants.

[1593] "Ratings" refers to user ratings and reviews of dining establishments and services provided.

[1594] "Business status" refers to the status of a food and beverage establishment, such as whether it is open or closed.

[1595] "Menu Information" means the list and details of the food and beverages served at a Food and Beverage Establishment.

[1596] "Emotion analysis results" refers to the results of analyzing a user's emotional state using emotion recognition technology.

[1597] A "recommended menu" refers to a list of food and drink suggestions based on the user's emotional state and preferences.

[1598] This invention relates to a system that quickly and intuitively acquires necessary map data and its attribute information based on a search query entered by a user in natural language, and further combines emotion recognition technology to provide information more accurately and effectively. As an application example, consider a restaurant recommendation system.

[1599] System Overview

[1600] The system of the present invention is mainly composed of a server and a user terminal. A user inputs a search query using a terminal such as a smartphone or a head-mounted display, and the server analyzes the query and provides appropriate information.

[1601] Hardware and software used

[1602] Hardware

[1603] Smartphone or head-mounted display

[1604] GPS function

[1605] microphone

[1606] software

[1607] Natural language processing engine (e.g. Google NLP API)

[1608] Emotion recognition engine (e.g. Microsoft Azure Emotion API)

[1609] Map API (e.g. Google Maps API)

[1610] Business management system (e.g., Firebase Realtime Database)

[1611] System Operation

[1612] 1. Getting User Input

[1613] A user uses a terminal to input a query in natural language about the food they want to eat or their mood, such as "I want to eat some delicious pizza nearby."

[1614] 2. Search Query Analysis

[1615] The device sends the user's query to the server, which then uses a natural language processing engine to analyze the query and extract its intent and keywords. For example, keywords such as "pizza" and "nearby" are extracted.

[1616] 3. Emotion Recognition Implementation

[1617] The server uses an emotion recognition engine to analyze the user's emotional state, recognizing emotions such as "tired" or "in a hurry" from search queries and vocabulary.

[1618] 4. Acquisition of Information

[1619] The server searches a map database based on the analysis results and the user's emotional state. For example, it obtains information such as the location, ratings, business hours, and menu information of nearby pizza restaurants. It also prioritizes the search results and provides the most suitable restaurants based on the user's emotional state.

[1620] 5. Formatting and sending information

[1621] The acquired information is formatted in a way that is easy for the user to understand. For example, if the emotion recognition engine determines that the user is in a hurry, restaurant information that can serve food quickly will be prioritized.

[1622] 6. Display of search results

[1623] The formatted information is sent to the terminal, which displays it to the user, who can then select the most suitable dining establishment based on the information provided.

[1624] Specific examples

[1625] If a user inputs a prompt such as "I've been tired since yesterday, so I want to eat some delicious pizza right now," the system will analyze the user's emotional state, such as "tired" or "right now," and search for pizza restaurants that can serve food quickly. The retrieved restaurant information is displayed on the device in an easy-to-understand format, allowing the user to easily find a suitable dining establishment.

[1626] The system of the present invention makes it possible to provide information that takes into account the user's emotional state, and can suggest restaurants and menus that best suit the user's needs, particularly when selecting a dining establishment, thereby providing a comfortable and satisfying experience.

[1627] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1628] Step 1:

[1629] A user uses a smartphone or a head-mounted display to input queries about the food they want to eat or their mood in natural language. For example, if a user inputs a query such as "I want to eat good pizza nearby," the input format is text or voice. The device receives this input and sends it to the server. The input data is the query text, and the output is the data to be sent to the server.

[1630] Step 2:

[1631] The server passes the search query received from the device to a natural language processing engine for analysis. The input is the search query text, and the output is the analysis results and extracted keywords. Specifically, it uses the Google NLP API to extract important keywords from the text (e.g., "pizza" or "nearby") and the intent of the query.

[1632] Step 3:

[1633] The server uses an emotion recognition engine to analyze the user's emotional state from the search query text. The input is the search query text, and the output is the emotion recognition result. Specifically, it uses the Microsoft Azure Emotion API to determine the user's emotional state (e.g., "I'm in a hurry" or "I'm tired") from the content and wording of the query.

[1634] Step 4:

[1635] The server searches the map database based on the query analysis results and emotion recognition results. The input is the analysis results and emotion recognition results, and the output is related map data and attribute information. Specifically, it uses the Google Maps API to obtain location information and attribute information (e.g., ratings, business status, menu information) of the restaurant that best suits the user.

[1636] Step 5:

[1637] The server formats the map data and attribute information it obtains into a format that is easy for the user to understand. The input is search result data, and the output is the formatted data. Specific operations include adjusting the way information is presented depending on the user's emotional state (e.g., if the user is "in a hurry," prioritize displaying restaurant information that allows quick ordering).

[1638] Step 6:

[1639] The server sends the formatted information to the terminal. The input is the formatted data, and the output is the data sent to the terminal. Specifically, the server sends the necessary information to the user as an HTTP response.

[1640] Step 7:

[1641] The terminal displays the information it receives to the user. The input is the data received from the server, and the output is the content displayed on the user interface. Specifically, it displays restaurant information and menu information suitable for the user on the screen, allowing the user to easily refer to that information.

[1642] The above processing steps enable users to quickly and accurately obtain information on appropriate dining establishments. Because this system takes into account the user's emotional state, it can provide information that is more satisfying.

[1643] 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.

[1644] 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.

[1645] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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).

[1650] 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.

[1651] 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."

[1652] 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.

[1653] 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).

[1654] 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.

[1655] 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.

[1656] 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.

[1657] 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.

[1658] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] The following is further disclosed regarding the above embodiment.

[1665] (Claim 1)

[1666] a means for registering map data including location information data and a plurality of pieces of attribute information related to the map data in a database;

[1667] means for receiving a search query input from a terminal;

[1668] a means for analyzing received search queries based on natural language processing to understand the intent of the queries;

[1669] a means for searching a database based on the analysis results to obtain related map data and attribute information;

[1670] means for formatting the acquired information into a format that is easy for the user to understand and transmitting the format to the terminal;

[1671] means for displaying the received information to a user;

[1672] A system including:

[1673] (Claim 2)

[1674] The system of claim 1 further comprising means for obtaining search results including attribute information of the evacuation shelter, such as its location, address, telephone number, and capacity, if the received search query is related to the evacuation shelter.

[1675] (Claim 3)

[1676] 2. The system according to claim 1, further comprising means for, when the received search query relates to risk level information of a hazard map, obtaining search results including risk level information of a corresponding area.

[1677] "Example 1"

[1678] (Claim 1)

[1679] a means for registering map data including location information data and a plurality of pieces of attribute information related to the map data in a database;

[1680] means for receiving a search query input from a terminal;

[1681] a means for analyzing received search queries based on natural language processing to understand the intent of the queries;

[1682] a means for searching a database based on the analysis results to obtain related map data and attribute information;

[1683] means for formatting the acquired information into a format that is easy for the user to understand and transmitting the format to the terminal;

[1684] means for displaying the received information to a user;

[1685] An effective data formatting and transmission method for quickly providing map information incorporating evacuation shelter information;

[1686] A system including:

[1687] (Claim 2)

[1688] The system of claim 1 further comprising means for obtaining search results including attribute information of the evacuation shelter, such as its location, address, telephone number, and capacity, if the received search query is related to the evacuation shelter.

[1689] (Claim 3)

[1690] 2. The system according to claim 1, further comprising means for, when the received search query relates to risk level information of a hazard map, obtaining search results including risk level information of a corresponding area.

[1691] "Application Example 1"

[1692] (Claim 1)

[1693] a means for registering map data including location information data and a plurality of pieces of attribute information related to the map data in a database;

[1694] means for receiving a search query input from a terminal;

[1695] a means for analyzing received search queries based on natural language processing to understand the intent of the queries;

[1696] a means for searching a database based on the analysis results to obtain related map data and attribute information;

[1697] means for formatting the acquired information into a format that is easy for the user to understand and transmitting the format to the terminal;

[1698] means for displaying the received information to a user;

[1699] an application installed on the smart glasses;

[1700] a means for parsing the query and extracting keywords using a natural language processing engine;

[1701] means for sending a request to a server based on the extracted keywords and receiving related information;

[1702] means for displaying the received information on a display of the smart glasses;

[1703] A system including:

[1704] (Claim 2)

[1705] The system of claim 1 further comprising means for obtaining search results including attribute information of the evacuation shelter, such as its location, address, telephone number, and capacity, if the received search query is related to the evacuation shelter.

[1706] (Claim 3)

[1707] 2. The system according to claim 1, further comprising means for, when the received search query relates to risk level information of a hazard map, obtaining search results including risk level information of a corresponding area.

[1708] "Example 2: Combining Emotion Engines"

[1709] (Claim 1)

[1710] a means for registering map data including location information data and a plurality of pieces of attribute information related to the map data in a database;

[1711] means for receiving a search query input from a terminal;

[1712] a means for analyzing received search queries based on natural language processing to understand the intent of the queries;

[1713] means for performing emotion recognition during analysis to determine the user's emotional state;

[1714] a means for searching a database based on the analysis result and the emotion recognition result to obtain related map data and attribute information;

[1715] means for arranging the acquired information into a format that is easy for the user to understand, adjusting the information presentation method according to the user's emotional state, and transmitting the information to the terminal;

[1716] means for displaying the information received by the terminal on a user interface;

[1717] A system including:

[1718] (Claim 2)

[1719] The system of claim 1 further comprising means for obtaining search results including attribute information of the evacuation shelter, such as its location, address, telephone number, and capacity, if the received search query is related to the evacuation shelter.

[1720] (Claim 3)

[1721] 2. The system according to claim 1, further comprising means for, when the received search query relates to risk level information of a hazard map, obtaining search results including risk level information of a corresponding area.

[1722] "Application example 2 when combining emotion engines"

[1723] (Claim 1)

[1724] a means for registering map data including location information data and a plurality of pieces of attribute information related to the map data in a database;

[1725] means for receiving a search query input from a terminal;

[1726] a means for analyzing received search queries based on natural language processing to understand the intent of the queries;

[1727] means for analyzing a user's emotional state using emotion recognition technology;

[1728] means for searching a database based on the analysis result and the emotional state to obtain relevant map data and attribute information;

[1729] means for formatting the acquired information into a format that is easy for the user to understand and transmitting the format to the terminal;

[1730] means for displaying the received information to a user;

[1731] A system including:

[1732] (Claim 2)

[1733] The system of claim 1, further comprising means for obtaining search results including attribute information of the restaurant, such as location information, ratings, business status, and menu information, if the received search query is related to the restaurant.

[1734] (Claim 3)

[1735] 2. The system according to claim 1, further comprising means for providing, as search results, restaurants and recommended menus suited to the user's emotional state based on the emotion analysis results. [Explanation of symbols]

[1736] 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 registering map data including location information data and a plurality of pieces of attribute information related to the map data in a database; means for receiving a search query input from a terminal; a means for analyzing received search queries based on natural language processing to understand the intent of the queries; a means for searching a database based on the analysis results to obtain related map data and attribute information; means for formatting the acquired information into a format that is easy for the user to understand and transmitting the format to the terminal; means for displaying the received information to a user; A system including:

2. The system of claim 1 further comprising means for obtaining search results including attribute information of the evacuation shelter, such as its location, address, telephone number, and capacity, if the received search query is related to the evacuation shelter.

3. The system according to claim 1 , further comprising means for, when the received search query relates to risk level information of a hazard map, obtaining search results including risk level information of a corresponding area.

Images