system

Abstract

A system is provided.SOLUTION: A system including means for collecting information related to food from a post on an SNS, means for analyzing a type of food and an atmosphere of a store from the collected information using an image recognition technique, means for analyzing a post content from the collected information using a natural language processing technique and extracting an evaluation of a user, means for analyzing quoted position information and specifying accurate geographic information, and means for displaying food information based on the analysis on a map.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When people are out and about looking for a place to eat, they often use search engines, gourmet sites, maps, and social media to find information, but they face challenges such as uncertainty about the accuracy of the information and the location of the location on the map. Another problem is that individual information sources are fragmented, making it time-consuming to gather information. Furthermore, the reliability of the collected data and the accuracy of the evaluations are uncertain, resulting in a lack of intuitive methods for effectively finding places to eat. [Means for solving the problem]

[0005] This invention solves these problems by providing a system that includes: a means for collecting information about food from posts on social media; a means for analyzing the type of food and the atmosphere of the restaurant from the collected information using image recognition technology; a means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings; a means for analyzing quoted location information to identify accurate geographic information; and a means for displaying food information based on the analysis on a map. Furthermore, by incorporating a means for scoring the reliability and recommendation level of posts based on the number of likes and comments, and filtering technology that takes into consideration the privacy of personal information, the system provides more accurate and user-friendly information.

[0006] "SNS" is an abbreviation for social networking service, a platform for users to share and interact with information and content via the Internet.

[0007] "Posting" refers to the act of a user uploading content such as images, videos, or text to a social networking site, or the content itself.

[0008] "Image recognition technology" is a technology in which a computer analyzes image data and identifies objects and scenes.

[0009] "Type of food" refers to the food category identified from the posted image or video (e.g., Japanese food, Western food, dessert).

[0010] "Store atmosphere" refers to the characteristics and mood of the store that can be sensed from elements such as the store's decoration, interior, lighting, and music.

[0011] "Natural language processing technology" is a technology that allows computers to analyze, understand, and generate human language (natural language).

[0012] "User ratings" are users' opinions and impressions expressed through comments, ratings, and reactions on SNS posts.

[0013] "Location information" is geographical data included in a post, and is information that indicates a specific location.

[0014] A "map display" is a plot on a map to visually present the analyzed information to the user.

[0015] "Credibility" is an indicator of how trustworthy the posted information or content is.

[0016] "Recommendation level" refers to the degree to which a certain piece of information or place is recommended to a user based on the analysis results.

[0017] "Filtering technology" is a technology that selects and displays only necessary information while protecting the user's privacy. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

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

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0033] 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.

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

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention provides a system for collecting and analyzing gourmet information from social networking site posts and displaying it intuitively on a map, with the aim of improving user convenience. Specific embodiments of this system will be described below.

[0040] Data collection

[0041] The server periodically collects food-related posts using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, location information, etc. For example, the server collects posts tagged with "food" and stores them in a database.

[0042] Image and video analysis

[0043] The server analyzes the collected images and videos using AI image recognition technology, which identifies characteristics such as the type of food, the atmosphere of the restaurant, and the price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[0044] Natural Language Processing (NLP)

[0045] The server uses NLP technology to analyze comments on posts and extract user ratings and impressions. It then scores the reliability and recommendation level of the post based on the number of likes and comments. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and a high recommendation level is assigned to posts with over 1,000 likes.

[0046] Adding location information

[0047] The server analyzes the location information in the post to determine its precise geographic location, using image metadata and any explicit location information provided by the poster, and cross-references it with other geographic databases.

[0048] Data Mapping and Visualization

[0049] The server plots the analyzed information on a map and provides it visually to the user. When a user accesses the application, restaurants are displayed on the map as pins, and clicking on them displays detailed information. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" displays detailed information about the restaurant and any posted images.

[0050] User Interface

[0051] Users can use the application to view and manipulate information on a map. They can use search filters to narrow down their search by their preferred genre (e.g., Japanese, Western, cafe) or price range. The application also provides information on nearby restaurants based on the user's current location. Users can also select the "sushi" tag to display highly rated sushi restaurants in Shinjuku Ward on the map.

[0052] Updates and Feedback

[0053] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[0054] In this way, this system collects and analyzes gourmet information from social media in real time, helping users choose dining locations in an intuitive and personalized way.

[0055] The processing flow will be explained below.

[0056] Step 1: Data collection

[0057] The server uses the SNS's public API to collect posts using specific hashtags or keywords (e.g., gourmet, restaurant).

[0058] The server stores the collected post data in a temporary database, including post IDs, image and video URLs, comments, number of likes, and location information.

[0059] Step 2: Image and video analysis

[0060] The server retrieves images and videos from a temporary database and uses an image recognition engine to analyze the type of food and the atmosphere of the restaurant.

[0061] The server extracts characteristics from the analysis results, such as the type of cuisine (e.g., Japanese, Western), the atmosphere of the restaurant (e.g., casual, high-end), and price range.

[0062] Step 3: Natural Language Processing (NLP)

[0063] The server retrieves the collected comments and uses NLP technology to analyze users' ratings and impressions.

[0064] The server scores the collected posts based on the number of likes and comments, assigning them a credibility and recommendation rating.

[0065] Step 4: Adding location information

[0066] The server retrieves the location information contained in the post and identifies the exact address from the extralocation data.

[0067] The server checks the location against other geographic databases to verify its accuracy.

[0068] Step 5: Data mapping and visualization

[0069] The data is plotted on a map based on the information analyzed by the server.

[0070] The server highlights information that interests the user and visually emphasizes it on the map.

[0071] Step 6: User Interface

[0072] The device obtains the user's current location information and displays it on a map.

[0073] The device accepts user operations and narrows down the information according to the filter conditions (e.g., Japanese food, Western food, cafes, etc.).

[0074] The user browses the restaurant information displayed as a search result and obtains detailed information.

[0075] Step 7: Updates and Feedback

[0076] The server periodically collects new data and updates the existing database with the latest information.

[0077] The server receives feedback from users to improve the accuracy and usability of the system.

[0078] Example 1

[0079] 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."

[0080] Conventional gourmet information systems were unreliable and it was difficult to obtain specific ratings and detailed information. Furthermore, it was time-consuming to manually collect and analyze information from individual posts, making it difficult to provide information intuitively to users. Furthermore, information was not updated in real time, making it difficult to reflect user feedback.

[0081] 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.

[0082] In this invention, the server includes means for collecting information about meals from posts on the SNS, means for analyzing the type of meal and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing location information from the collected information and identifying accurate geographic information, means for displaying the meal information based on the analysis on a map, means for users to check and manipulate the information on the map using an application, means for periodically collecting new data and updating the database, and means for collecting user feedback and improving the accuracy and usability of the analysis algorithm. This allows users to obtain reliable, detailed gourmet information in real time and intuitively check it on a map.

[0083] "SNS" is an abbreviation for social networking service, an online platform for people to share information and interact over the Internet.

[0084] A "server" refers to a computer system that accepts requests from clients over a network and provides data and services.

[0085] "Meal" refers to any food or drink consumed, including the act of consuming food.

[0086] "Information" refers to facts, data, knowledge, etc. about a subject, and is expressed through language, numbers, images, sounds, etc.

[0087] "Image recognition technology" is a technology that allows computers to identify and analyze objects and patterns contained in images and photographs.

[0088] "Natural language processing technology" is a technology that enables computers to understand and generate human language, and includes applications such as text analysis, translation, and dialogue systems.

[0089] A "database" is a collection of structured data, and is a system designed to enable efficient searching, adding, updating, and deleting.

[0090] "Location information" refers to geographical information about a specific point or place, and is represented by data such as latitude, longitude, and address.

[0091] A "map" is a visual representation of a particular portion of geographic space, depicting roads, buildings, natural features, etc.

[0092] "Feedback" refers to opinions and reactions provided by users regarding a system or service, which are used for improvement and adjustment.

[0093] An "analytical algorithm" is a computational procedure or method for analyzing data and finding patterns or regularities in it.

[0094] "Usability" refers to the ease of use and operation of a system or product, and is the characteristic that enables users to achieve their goals efficiently.

[0095] This invention is a system that collects and analyzes gourmet information from social networking sites and intuitively displays it on a map to improve user convenience. This system collects information about food from posts on social networking sites, analyzes it using image recognition technology and natural language processing technology, and plots geographical information based on the results to provide to users.

[0096] Hardware and software used

[0097] Hardware: Servers, user terminals

[0098] Software: Public APIs for social networking sites, image recognition technology (e.g., Google Cloud Vision API), natural language processing technology (e.g., spaCy, GPT-4), map display libraries (e.g., Leaflet.js), databases (e.g., MySQL)

[0099] Specific explanation of the process

[0100] 1. Data Collection

[0101] The server uses the public API of the SNS to collect posts with a specific hashtag (e.g., "gourmet"). For example, the server uses the Twitter API to periodically retrieve posts tagged with "gourmet" every day at 3:00 PM and store them in a database in JSON format.

[0102] 2. Image and video analysis

[0103] The server applies image recognition technology to the collected image data. For example, it uses the Google Cloud Vision API to extract features such as "sushi," "Japanese food," and "luxury" from the image, organizes them, and stores them in a database.

[0104] 3. Natural Language Processing (NLP)

[0105] The server analyzes the comments in the post using natural language processing technology. For example, it uses GPT-4 to extract "likes" from a comment like "The sushi at this restaurant was amazing!", and then scores the reliability of the comment based on the number of likes and comments, and stores the results in a database.

[0106] 4. Adding location information

[0107] The server analyzes the location information attached to the post and converts it into accurate geographic information. Specifically, it compares the metadata and explicit location information in the post with the Google Maps API and registers the coordinates in a database.

[0108] 5. Data Mapping and Visualization

[0109] The server plots the analysis results on a map and displays them in a format that is easy for users to understand. For example, Leaflet.js is used to display the analyzed information as pins on a map, and an interface is provided that allows users to click on the pins to view detailed information.

[0110] 6. User Interface

[0111] Users can use the application to search and manipulate information on a map. For example, if a user enters filter criteria such as "sushi" or "Shinjuku Ward," pins for restaurants that match the criteria will appear on the map.

[0112] 7. Updates and Feedback

[0113] The server periodically collects new data and updates the database with the latest information. It also collects user feedback and updates the analysis algorithm to improve the system's accuracy and usability. For example, if a user reports that "this restaurant information is not accurate," the system uses that feedback to improve the accuracy of location information and analysis results.

[0114] Examples of specific examples and prompts

[0115] Specific examples

[0116] The server uses the Twitter API to automatically collect posts tagged with "gourmet."

[0117] Image data is analyzed using the Google Cloud Vision API and feature tags are generated.

[0118] GPT-4 analyzes comments and calculates a rating score.

[0119] Use the Google Maps API to check geographic information.

[0120] The analysis results are plotted on a map using Leaflet.js, providing a visual presentation to the user.

[0121] Users can use search filters in the application to display information on the map that matches specific criteria.

[0122] The server updates the data based on user feedback to improve the accuracy of the system.

[0123] Prompt Sentence Examples

[0124] "Please explain in detail the process of the system that collects gourmet information from social media posts, analyzes ratings and characteristics, and displays them on a map."

[0125] "Please give me an example of how image recognition technology can be used to extract the type and characteristics of food."

[0126] "Please explain how you would improve the system based on user feedback."

[0127] In this way, this system collects and analyzes gourmet information from social media in real time, helping users choose dining locations in an intuitive and personalized way.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] Data collection

[0131] The server uses the SNS's public API to collect posts with the "gourmet" hashtag.

[0132] Input: A social networking site's public API and the hashtag "gourmet."

[0133] What it does: It periodically sends API requests and receives the posted data in response.

[0134] Output: Social media post data (images, videos, comments, likes, location information, etc.).

[0135] Step 2:

[0136] Data Storage

[0137] The server stores the collected post data in a database.

[0138] Input: Post data collected from social media.

[0139] What it does: Organizes submitted data by field and stores it in a database.

[0140] Output: Organized submission data in a database.

[0141] Step 3:

[0142] Image and video analysis

[0143] The server uses the Google Cloud Vision API to analyze the collected image data.

[0144] Input: Image data retrieved from a database.

[0145] How it works: Image data is sent to the Google Cloud Vision API, and the returned analysis results (e.g., characteristics such as "sushi," "Japanese food," and "luxury") are organized.

[0146] Output: Image data with extracted features.

[0147] Step 4:

[0148] Natural Language Processing (NLP)

[0149] The server analyzes the comment portion using natural language processing technology (e.g., spaCy, GPT-4).

[0150] Input: Comment data retrieved from the database.

[0151] How it works: Comment data is input into a natural language processing model, and the returned ratings and recommendation data is organized.

[0152] Output: Comment data with numerical ratings and recommendation levels.

[0153] Step 5:

[0154] Like and comment scoring

[0155] The server scores the credibility and recommendation of posts based on the number of likes and comments.

[0156] Input: Number of likes and comments retrieved from the database.

[0157] How it works: The acquired data is fed into an algorithm to calculate trustworthiness and recommendation score.

[0158] Output: Confidence and recommendation scores.

[0159] Step 6:

[0160] Adding location information

[0161] The server analyzes the location information contained in the collected posts and identifies precise geographic information.

[0162] Input: Post metadata and explicit location information.

[0163] What it does: Sends location information to the Google Maps API and organizes the coordinate data returned.

[0164] Output: Accurate geographic information.

[0165] Step 7:

[0166] Data Mapping and Visualization

[0167] The server plots the analyzed information on a map and provides it visually to the user.

[0168] Input: Analysis results stored in a database.

[0169] How it works: Using a map display library (e.g. Leaflet.js), the analysis results are displayed as pins on a map, and clicking on the pins displays more information.

[0170] Output: Map view with pins.

[0171] Step 8:

[0172] User Interface

[0173] Users use the application to search and manipulate information on the map.

[0174] Input: User's search filter criteria (e.g. cuisine type, price range, region, etc.).

[0175] How it works: Searches a database based on user input and displays information that matches the criteria on a map.

[0176] Output: Map display of restaurant information that matches the conditions.

[0177] Step 9:

[0178] Updates and Feedback

[0179] The server periodically collects new data and updates the database.

[0180] Input: Newly collected social media posting data and user feedback.

[0181] What it does: Adds new submissions to the database and improves the analysis algorithm based on feedback.

[0182] Output: Updated database and improved algorithms.

[0183] In this way, this system can collect and analyze gourmet information from SNS posts in real time, and provide users with intuitive and detailed information.

[0184] (Application example 1)

[0185] 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."

[0186] Conventional food delivery systems have the problem that it takes a huge amount of time and effort for users to find a restaurant that suits their preferences. Furthermore, there are not enough methods to utilize gourmet information on social media, and real-time updated rating information cannot be effectively utilized. Furthermore, users have to move between different platforms, which is inconvenient. There is a need for a system that can solve these issues and improve user convenience.

[0187] 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.

[0188] In this invention, the server includes means for collecting information about food from posts on the SNS, means for analyzing the type of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing the quoted location information and identifying accurate geographic information, means for displaying food information based on the analysis on a map, means for introducing restaurants recommended from the analyzed information based on keywords searched by the user and the user's current location, and means for directly ordering from the selected restaurant. This enables users to quickly find their favorite restaurant and easily order from it based on reliable gourmet information collected in real time from SNS posts.

[0189] "SNS posts" refers to information such as comments, images, and videos that users make public on social networking services.

[0190] "Food information" refers to data about the type of food and drink, its characteristics, price range, and the environment in which it is served.

[0191] "Image recognition technology" is a technology that extracts specific features and patterns from image data and performs identification and classification.

[0192] "Natural language processing technology" is a technology that mechanically analyzes, understands, and generates human language.

[0193] "Location Information" refers to geographic data including the latitude and longitude of a specific point.

[0194] "Map display" refers to a map for visually presenting geographic information.

[0195] "Search keywords" refer to words or phrases that users enter to retrieve content of interest.

[0196] "Current location" refers to geographic information about the user's current location.

[0197] "Restaurant" refers to a commercial establishment that serves food and beverages.

[0198] "Order" refers to the act of a User making a request to purchase a product or service.

[0199] "Credibility" refers to the property of indicating the accuracy and reliability of information.

[0200] System Overview

[0201] This invention is a food delivery system that collects and analyzes food information from social media posts, intuitively displays it on a map, and enables users to efficiently find their favorite restaurants and place orders directly with those restaurants. This system consists of social media data collection, image recognition, natural language processing, location information analysis, map display, search engine, and ordering functions.

[0202] Used technologies and data processing

[0203] 1. Data Collection

[0204] The system uses the public API of social media platforms to collect posts with specific hashtags (e.g., "food"). The specific software used is Python and social media APIs (e.g., Twitter API, Instagram API). The collected data is stored in MongoDB.

[0205] 2. Image and video analysis

[0206] The server analyzes the collected images and videos using AI image recognition technology such as Google Cloud Vision API. During the analysis process, characteristics such as the type of food and the atmosphere of the restaurant are identified. For example, from an image of sushi, characteristics such as "sushi," "Japanese food," and "high-end" are extracted.

[0207] 3. Natural Language Processing

[0208] Comments on posts are analyzed using NLP technology (e.g., spaCy and BERT). This extracts user ratings and impressions, and then scores the reliability and recommendation level based on the number of likes and comments. For example, a "high rating" is automatically extracted from a comment such as "The sushi at this restaurant was amazing!", and the recommendation level increases if there are multiple likes.

[0209] 4. Adding location information

[0210] Analyze the location information contained in SNS posts to identify accurate geographic information. Use geographic information services such as Geopy to analyze the location information. Based on the location information contained in the post, match it with other geographic databases (such as Google Maps API).

[0211] 5. Data Mapping and Visualization

[0212] The analyzed information is plotted on a map using map display libraries such as Leaflet.js and Google Maps API, and users can use search filters to narrow down their search by their preferred genre or price range.

[0213] 6. Order function

[0214] Based on the user's search keywords and current location, the app analyzes information and recommends restaurants, which are then displayed on a map. Users can easily check restaurant information and place orders directly from the app.

[0215] Specific examples

[0216] When a smartphone user searches for the keyword "sushi in Shibuya Ward," pins are displayed on a map showing restaurants with "sushi," "Shibuya Ward," and "highly rated" based on recent social media posting data. The user can then select a restaurant called "Sushimaru," check out the highly rated reviews and photos, and place an order within the app.

[0217] Prompt Sentence Examples

[0218] When a user types in the app, "Search for highly rated sushi restaurants in Shibuya Ward," the system retrieves the appropriate information from its internal database and displays the results on a map.

[0219] In this way, the present invention is a system that collects and analyzes SNS data in real time and provides users with useful information, allowing them to select restaurants and place orders easily and efficiently.

[0220] Specific examples of hardware and software used

[0221] SNS API (Twitter API, Instagram API)

[0222] Python

[0223] MongoDB

[0224] Google Cloud Vision API

[0225] spaCy, BERT

[0226] geopy, Google Maps API

[0227] Leaflet.js

[0228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0229] Step 1:

[0230] The server periodically collects posts with a specific hashtag (e.g., "food") using the public API of the social networking site (e.g., Twitter API, Instagram API). The collected data includes images, videos, comments, number of likes, and location information. This data is stored in MongoDB.

[0231] Input: SNS API

[0232] Output: Collected data stored in MongoDB

[0233] Specific operation: The server calls the SNS API, retrieves relevant posts based on the filter conditions, and saves them in the database.

[0234] Step 2:

[0235] The server analyzes the collected images and videos using the Google Cloud Vision API, identifying characteristics such as the type of food and the restaurant's atmosphere.

[0236] Input: Image data stored in MongoDB

[0237] Output: Analyzed features (e.g. "Sushi", "Japanese food", "High-end")

[0238] Specific operation: The server sends the image data to the Google Cloud Vision API and adds the returned feature information to the database.

[0239] Step 3:

[0240] The server uses NLP technology (e.g., spaCy or BERT) to analyze the collected comments, extract user ratings and impressions, and score the trustworthiness and recommendation level based on the number of likes and comments.

[0241] Input: Comment data stored in MongoDB

[0242] Output: Extracted ratings and recommendation scores

[0243] Specific operation: The server inputs the comment data into the NLP model, extracts ratings and opinions as analysis results, calculates the reliability and recommendation level, and stores them in a database.

[0244] Step 4:

[0245] The server uses the geopy library to analyze the location information contained in the post, identify precise geographic information, and further refine the location information by comparing it with other geographic databases (such as the Google Maps API).

[0246] Input: Geolocation data stored in MongoDB

[0247] Output: Precisely identified geographic location

[0248] What it does: The server inputs the location data into the geopy library and checks the returned latitude and longitude information against a geographic database to verify accuracy.

[0249] Step 5:

[0250] The server plots the analyzed information on a map using Leaflet.js and the Google Maps API. Users can view the information on the map through a smartphone or PC application and use search filters to narrow down the restaurants they find based on their preferences.

[0251] Input: Parsed feature and geographic information

[0252] Output: Restaurant information displayed on a map

[0253] Specific operation: The server inputs the analyzed feature information and location information into the map display library and provides it visually to the user.

[0254] Step 6:

[0255] Users input their search keywords and current location, and the server recommends restaurants based on that information. Users can then check the restaurant information and place an order directly through the application if necessary.

[0256] Input: Search keywords and current location information entered by the user

[0257] Output: Recommended restaurant information displayed as search results and order confirmation information

[0258] Specific operation: The user enters search keywords and current location, and the server retrieves and displays the corresponding information from the database and processes the order for the restaurant selected by the user.

[0259] 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.

[0260] The present invention provides a system for collecting and analyzing gourmet information and user emotion information from social networking site posts, and intuitively displaying the information on a map, with the aim of improving user convenience. Specific embodiments of this system are described below.

[0261] Data collection

[0262] The server periodically collects posts with specific hashtags or keywords (e.g., gourmet, restaurant) using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, location information, and sentiment analysis of comments. For example, the server collects posts tagged with "gourmet" and stores them in a database.

[0263] Image and video analysis

[0264] The server analyzes the collected images and videos using AI image recognition technology, which identifies characteristics such as the type of food, the atmosphere of the restaurant, and the price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[0265] Natural Language Processing (NLP)

[0266] The server uses NLP technology to analyze comments on posts and extract user ratings and impressions. It then scores the reliability and recommendation level of the post based on the number of likes and comments. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and a high recommendation level is assigned to posts with over 1,000 likes.

[0267] Emotion analysis using an emotion engine

[0268] The server analyzes the collected comments and their language data using an emotion engine to recognize the user's emotions. For example, it can extract "positive emotions" from a comment like "I love the atmosphere of this store!"

[0269] The server adjusts the recommendation level for food and restaurants based on the user's emotional data, giving a higher recommendation level to posts with positive emotions and a lower recommendation level to posts with negative emotions.

[0270] Adding location information

[0271] Our servers retrieve the location information contained in the post, use the extralocation data to determine the exact address, and verify the accuracy of the location information by cross-checking it with other geolocation databases.

[0272] Data Mapping and Visualization

[0273] The server plots the data on a map based on the information analyzed. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" will display detailed information about the restaurant and any posted images. The information displayed also takes into account the results of sentiment analysis.

[0274] User Interface

[0275] Users can use the application to view and manipulate information on a map. They can use search filters to narrow down their search by their preferred genre (e.g., Japanese, Western, cafe) or price range. The application also provides information on nearby restaurants based on the user's current location. Furthermore, users can select the "sushi" tag to display highly rated sushi restaurants in Shinjuku Ward on the map.

[0276] Updates and Feedback

[0277] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[0278] In this way, this system collects and analyzes gourmet information and user sentiment information from SNS in real time, helping users select dining locations in an intuitive and personalized way.

[0279] The processing flow will be explained below.

[0280] Step 1: Data collection

[0281] The server uses the SNS's public API to collect posts using specific hashtags or keywords (e.g., gourmet, restaurant).

[0282] The server stores the collected post data in a temporary database, including post IDs, image and video URLs, comments, number of likes, and location information.

[0283] Step 2: Image and video analysis

[0284] The server retrieves images and videos from a temporary database and uses an image recognition engine to analyze the type of food and the atmosphere of the restaurant.

[0285] The server extracts characteristics from the analysis results, such as the type of cuisine (e.g., Japanese, Western), the atmosphere of the restaurant (e.g., casual, high-end), and price range.

[0286] Step 3: Natural Language Processing (NLP)

[0287] The server retrieves the collected comments and uses NLP technology to analyze users' ratings and impressions.

[0288] The server scores the collected posts based on the number of likes and comments, assigning them a credibility and recommendation rating.

[0289] Step 4: Emotion analysis using the emotion engine

[0290] The server analyzes the collected comments and their language data using an emotion engine to recognize the user's emotions.

[0291] Based on the results of the emotion analysis, the server assigns a high recommendation level to positive emotions and a low recommendation level to negative emotions.

[0292] Step 5: Adding location information

[0293] The server retrieves the location information contained in the post and identifies the exact address from the extralocation data.

[0294] The server checks the location against other geographic databases to verify its accuracy.

[0295] Step 6: Data mapping and visualization

[0296] The data is plotted on a map based on the information analyzed by the server.

[0297] The server highlights information that interests the user and visually emphasizes it on the map.

[0298] Step 7: User Interface

[0299] The device obtains the user's current location information and displays it on a map.

[0300] The device accepts user operations and narrows down the information according to the filter conditions (e.g., Japanese food, Western food, cafes, etc.).

[0301] The user browses the restaurant information displayed as a search result and obtains detailed information.

[0302] Step 8: Updates and Feedback

[0303] The server periodically collects new data and updates the existing database with the latest information.

[0304] The server receives feedback from users to improve the accuracy and usability of the system.

[0305] Example 2

[0306] 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."

[0307] Conventional systems have difficulty accurately extracting information about food types, restaurant atmospheres, and user ratings when collecting and analyzing gourmet information on social media. Furthermore, the collected information lacks reliability, resulting in a poor user experience. Furthermore, intuitive map displays that take user emotions and ratings into account are lacking, creating a need for a user-friendly system.

[0308] 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.

[0309] In this invention, the server includes means for collecting information about food from posts on the SNS, means for analyzing the type of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing the sentiment of the collected comments using an emotion engine and adjusting the recommendation level based on the sentiment, means for analyzing quoted location information and identifying accurate geographic information, and means for displaying food information based on the analysis on a map. This allows users to intuitively grasp reliable gourmet information and easily find restaurants and dishes that suit their preferences.

[0310] "SNS posts" refer to content such as text, images, and videos that users make public on social networking services.

[0311] "Information about food" refers to food and related information such as the type of food, name, recipe, restaurant name, price, rating, image, video, and location information.

[0312] "Image recognition technology" is a technology that uses computer vision technology to identify objects in images and videos and analyze their features.

[0313] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language, and is a technology that analyzes text data and extracts emotions.

[0314] "User ratings" refers to user opinions and impressions contained in posts on social media, as well as rating scores based on them.

[0315] "Quoted location information" refers to data indicating geographic coordinates or locations contained in posts on social media.

[0316] An "emotion engine" refers to technology that analyzes emotions from text data and recognizes emotional categories such as positive, negative, and neutral.

[0317] "Recommendation level" is an index that indicates the degree to which a particular dish or restaurant is recommended based on analyzed information.

[0318] "Precise geographic information" is information that accurately identifies a specific address or location based on the location information contained in a post.

[0319] "Means for displaying on a map" refers to technology that uses a geographic information system to visualize the analyzed information on a map.

[0320] The present invention provides a system that collects and analyzes gourmet information and user emotion information from social networking site posts and intuitively displays the information on a map. Specific embodiments of this system will be described below.

[0321] Data collection

[0322] The server periodically collects posts containing specific hashtags or keywords (e.g., food, restaurant) using the public API of the social networking site. For example, it retrieves posts using Facebook's Graph API or Twitter's API. The server stores the collected post content, such as images, videos, comments, number of likes, and location information, in a database. The server searches for posts containing the "food" hashtag every hour and adds newly found posts to the database.

[0323] Image and video analysis

[0324] The server uses AI image recognition technologies such as Google Cloud Vision API and Amazon Rekognition to analyze the collected images and videos. This allows it to identify the type of food, the restaurant's atmosphere, price range, and other information. For example, it can detect the presence of sushi in a particular image and store characteristics such as "sushi," "Japanese food," and "high-end" in a database. Specifically, the server sequentially analyzes newly collected images and generates metadata about the type of food and the restaurant's atmosphere.

[0325] Natural Language Processing (NLP)

[0326] The server uses natural language processing technologies such as Google Cloud Natural Language API and OpenAI's GPT-3 to analyze comments on posts and extract user ratings and impressions. It also scores the reliability and recommendation level of posts based on the number of likes and comments. For example, it extracts a "high rating" from a comment like "The sushi at this restaurant was amazing!" and assigns a high recommendation level to posts with over 1,000 likes. Specifically, the server analyzes newly collected comments, calculates a reliability score, and stores it in a database.

[0327] Emotion analysis using an emotion engine

[0328] The server uses emotion engines such as Azure Text Analytics and IBM Watson to perform emotion analysis on the collected comments. This allows it to recognize positive, negative, and neutral emotions from the comments and adjust the recommendation level for a dish or restaurant accordingly. For example, a "positive emotion" is extracted from a comment like "I love the atmosphere of this restaurant!" The server calculates an emotion score for the collected comments and assigns a higher recommendation level to posts with a high percentage of positive emotions.

[0329] Adding location information

[0330] The server uses the location information contained in the post to identify the exact address using the Google Maps API or OpenStreetMap API. It also verifies the accuracy of the location information by comparing it with other geographic information databases. For example, it can identify the address of a specific restaurant from the location information. Specifically, the server sequentially analyzes posts with location information and stores the exact address information in a database.

[0331] Data Mapping and Visualization

[0332] Based on the analyzed information, the server plots the data on a map using Leaflet, Google Maps, etc. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" displays detailed information about the restaurant and any posted images. Specifically, the server displays data that meets the specified criteria as pins on the map, and clicking on the pin displays detailed information.

[0333] User Interface

[0334] Users can use applications (e.g., mobile apps or web apps) to view and manipulate information on a map. Users can use search filters to narrow down their search by their preferred genre and price range. The app also provides information about nearby restaurants based on the user's current location. For example, if a user selects the "sushi" tag, highly rated sushi restaurants in Shinjuku Ward are displayed on a map and detailed information about them is displayed.

[0335] Updates and Feedback

[0336] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[0337] Example prompt sentence:

[0338] Please explain the system that collects and analyzes gourmet information and user sentiment information from social media posts and displays it intuitively on a map.

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

[0340] Step 1:

[0341] Data collection

[0342] The server uses the public API of the social networking site to periodically collect posts containing specific hashtags or keywords (e.g., gourmet, restaurant). Specifically, it retrieves posts using Facebook's Graph API or Twitter's API. It receives the specified hashtag or keyword as input and searches for posts containing that hashtag. As output, it stores the content of the collected posts (images, videos, comments, number of likes, location information) in a database. The server searches for posts containing the hashtag "gourmet" every hour and adds new posts to the database.

[0343] Step 2:

[0344] Image and video analysis

[0345] The server analyzes the collected images and videos using AI image recognition technologies such as Google Cloud Vision API and Amazon Rekognition. It receives the collected image and video data as input and stores features such as the type of food, restaurant atmosphere, and price range as output in a database. Specifically, it detects the presence of sushi in a particular image and extracts features such as "sushi," "Japanese food," and "high-end." The server sequentially analyzes newly collected images and generates metadata related to the type of food and restaurant atmosphere.

[0346] Step 3:

[0347] Natural Language Processing (NLP)

[0348] The server uses natural language processing technologies such as Google Cloud Natural Language API and OpenAI's GPT-3 to analyze comments on posts. It receives collected comment data as input and extracts user ratings and impressions as output, calculating reliability scores and recommendation levels and storing them in a database. Specifically, it extracts "high ratings" from comments such as "The sushi at this restaurant was amazing!" and assigns a high recommendation level to posts with over 1,000 likes. The server analyzes the comments and calculates reliability scores.

[0349] Step 4:

[0350] Emotion analysis using an emotion engine

[0351] The server uses emotion engines such as Azure Text Analytics and IBM Watson to analyze the emotions of the collected comments. It receives the collected comment data as input and stores emotion scores such as positive, negative, and neutral as output in a database. For example, it extracts "positive emotion" from the comment "I love the atmosphere of this store!" The server inputs the collected comments into the emotion engine, calculates the emotion score, and assigns a high recommendation rating to posts with a high percentage of positive emotion.

[0352] Step 5:

[0353] Adding location information

[0354] The server analyzes the location information included in the post using the Google Maps API or OpenStreetMap API to identify the exact address. It receives the location information (coordinate data) included in the post as input and stores the specific address in a database as output. For example, it identifies the address of a specific restaurant from the location information. The server analyzes the post with location information and stores the exact address information in a database.

[0355] Step 6:

[0356] Data Mapping and Visualization

[0357] Based on the analyzed information, the server plots the data on a map using Leaflet, Google Maps, or similar. It receives the analyzed food information, user ratings, and sentiment scores as input, and provides visualized data (such as pins) on the map as output. For example, clicking on a pin labeled "Japanese food," "sushi," or "highly rated" displays detailed information about the restaurant and any posted images. The server displays data that meets the specified criteria as pins on the map, and clicking on the pins provides detailed information.

[0358] Step 7:

[0359] User Interface

[0360] Users use an application (mobile or web) to view and manipulate information on a map. The application receives the user's search criteria (e.g., genre, price range, tags) as input, and displays corresponding restaurant and cuisine information on the map as output. For example, if a user selects the tag "sushi," highly rated sushi restaurants in Shinjuku Ward are displayed on the map and detailed information can be viewed. Users can also receive information about nearby restaurants based on their current location.

[0361] Step 8:

[0362] Updates and Feedback

[0363] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. It receives the collected new data and user feedback as input, and provides an updated database and an analysis algorithm with adjusted accuracy as output. For example, if a user reports that "this restaurant information is not accurate," the accuracy of the location information and analysis results is adjusted based on that feedback.

[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 today's world, people increasingly have opportunities to obtain gourmet information through social media. However, it is not easy to efficiently find reliable information and restaurants and delivery services that suit one's preferences from the vast amount of information available. In particular, the lack of personalized information based on the user's preferences and current location is a challenge. Another issue is the lack of functionality to analyze emotional information and adjust the recommendation level, making it difficult for users to choose a service that will truly satisfy them.

[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 collecting information about food from posts on SNS, means for analyzing the types of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing quoted location information and identifying accurate geographic information, means for displaying food information based on the analysis on a map, and means for suggesting recommended delivery services based on the user's preferences and location information. This makes it possible to provide reliable, personalized gourmet information that is suitable for the user from a vast amount of information.

[0368] "SNS" is an abbreviation for social networking service, an online platform that allows users to share information and interact with each other via the Internet.

[0369] "Image recognition technology" is a technology in the field of computer vision that identifies and classifies objects and scenes in images and videos.

[0370] "Natural language processing technology" is a technology that enables computers to analyze and understand human language, and is used to analyze and automatically generate text data.

[0371] "Location information" is information for identifying a geographical location, and is mainly expressed in the form of latitude and longitude.

[0372] "Delivery service" refers to a service that delivers food, beverages, and merchandise directly to a location designated by the user.

[0373] "Personalization" refers to providing individually optimized experiences and services based on each user's preferences and behavior.

[0374] "Reliability" refers to the degree to which information or services are relevant, accurate, and consistent and can be relied upon by users.

[0375] "Emotional information" is data that reflects the user's emotions, such as positive, negative, or neutral, and is the analysis result based on that information.

[0376] This system collects information about food from social media posts and suggests optimal delivery services based on the user's preferences and location. This system mainly uses a server to perform the following processes:

[0377] First, the server periodically collects posts with specific hashtags or keywords (e.g., gourmet, delivery) using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, and location information. For example, the server periodically collects posts tagged with "delivery" and stores them in a database.

[0378] The server then analyzes the collected images and videos using AI image recognition technology, identifying characteristics such as the type of food, atmosphere, and price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[0379] The server then uses natural language processing (NLP) to analyze the collected comments and extract user ratings and impressions. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and the reliability and recommendation of the post are scored based on the number of likes and comments.

[0380] The server then uses an emotion engine to analyze the collected comments and their language data to recognize the user's emotions. For example, a "positive emotion" is extracted from a comment like "I love the atmosphere of this restaurant!" The recommendation level for the food or restaurant is adjusted based on this emotional data.

[0381] Additionally, the server captures the location information contained in the post, uses the extralocation data to determine the exact address, and verifies the accuracy of the location information by checking it against other geographic databases.

[0382] The server then uses the analysis results to suggest delivery services that take into account the user's preferences and location. For example, a user can select the tag "sushi" to display nearby highly rated sushi restaurants on a map. The server also suggests the best delivery options based on the user's current location.

[0383] The system runs on servers on AWS (Amazon Web Services) or Google Cloud Platform, with data stored in a PostgreSQL database. It uses TensorFlow or OpenCV for image recognition, Google Cloud Natural Language API for NLP, IBM Watson Tone Analyzer for sentiment analysis, and Google Maps API for accurate location information.

[0384] For example, consider the following prompt:

[0385] "Analyze the following image to identify the type of food and price range: Sushi image"

[0386] "Analyze the following comment with your sentiment engine to determine whether it's positive, negative, or neutral: 'The sushi at this place was amazing!'"

[0387] In this way, the system can provide users with reliable, personalized gourmet information from a vast amount of information.

[0388] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0389] Step 1:

[0390] The server periodically collects posts with specific hashtags or keywords (e.g., gourmet, delivery) using the public API of the social networking site. Here, it sends an API request and analyzes the returned JSON data to extract images, videos, comments, number of likes, location information, etc. The input is the keyword of the API request, and the output is the collected post data.

[0391] Step 2:

[0392] The server analyzes the collected images and videos using AI image recognition technology (e.g., TensorFlow or OpenCV). This identifies features such as the type of cuisine, the atmosphere of the restaurant, and the price range. Specifically, the image data is input into the model, and feature labels (e.g., "sushi," "Japanese cuisine," "high-end") are obtained as output. The input is the images and videos of the posted data, and the output is the analyzed feature information.

[0393] Step 3:

[0394] The server analyzes the collected comments on posts using natural language processing technology (e.g., Google Cloud Natural Language API) to extract user ratings and impressions. Here, text data is sent to the API, and rating information is extracted based on the returned analysis results. The input is the comments on the post data, and the output is the analyzed ratings and impressions.

[0395] Step 4:

[0396] The server analyzes the collected comments and their language data using an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. Specifically, the comment text is input into the emotion engine, and emotion labels such as positive, negative, and neutral are obtained as output. The input is the posted comments, and the output is the analyzed emotion information.

[0397] Step 5:

[0398] The server retrieves the location information contained in the post, identifies the exact address from the extrapolation data, and verifies the accuracy of the location information by checking it against other geographic information databases (e.g., Google Maps API). The input is the location information of the post data, and the output is the confirmed exact address information.

[0399] Step 6:

[0400] The server then proposes delivery services based on the analysis results, taking into account the user's preferences and location information. Specifically, it runs an algorithm that recommends optimal delivery options based on the user's current location and preferences. The input is the user's current location and preference data, and the output is the proposed delivery service information.

[0401] Step 7:

[0402] Users can check suggested delivery services and restaurant information on a map through their device. Users can manipulate the information on the map to view detailed information and posted images. The input is the suggested delivery service information, and the output is the map information and detailed data that the user can view.

[0403] In this way, the system performs individual processing at each step, providing delivery services and gourmet information that are suited to the user.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] [Second embodiment]

[0408] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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).

[0414] 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. 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.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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."

[0420] The present invention provides a system for collecting and analyzing gourmet information from social networking site posts and displaying it intuitively on a map, with the aim of improving user convenience. Specific embodiments of this system will be described below.

[0421] Data collection

[0422] The server periodically collects food-related posts using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, location information, etc. For example, the server collects posts tagged with "food" and stores them in a database.

[0423] Image and video analysis

[0424] The server analyzes the collected images and videos using AI image recognition technology, which identifies characteristics such as the type of food, the atmosphere of the restaurant, and the price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[0425] Natural Language Processing (NLP)

[0426] The server uses NLP technology to analyze comments on posts and extract user ratings and impressions. It then scores the reliability and recommendation level of the post based on the number of likes and comments. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and a high recommendation level is assigned to posts with over 1,000 likes.

[0427] Adding location information

[0428] The server analyzes the location information in the post to determine its precise geographic location, using image metadata and any explicit location information provided by the poster, and cross-references it with other geographic databases.

[0429] Data Mapping and Visualization

[0430] The server plots the analyzed information on a map and provides it visually to the user. When a user accesses the application, restaurants are displayed on the map as pins, and clicking on them displays detailed information. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" displays detailed information about the restaurant and any posted images.

[0431] User Interface

[0432] Users can use the application to view and manipulate information on a map. They can use search filters to narrow down their search by their preferred genre (e.g., Japanese, Western, cafe) or price range. The application also provides information on nearby restaurants based on the user's current location. Users can also select the "sushi" tag to display highly rated sushi restaurants in Shinjuku Ward on the map.

[0433] Updates and Feedback

[0434] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[0435] In this way, this system collects and analyzes gourmet information from social media in real time, helping users choose dining locations in an intuitive and personalized way.

[0436] The processing flow will be explained below.

[0437] Step 1: Data collection

[0438] The server uses the SNS's public API to collect posts using specific hashtags or keywords (e.g., gourmet, restaurant).

[0439] The server stores the collected post data in a temporary database, including post IDs, image and video URLs, comments, number of likes, and location information.

[0440] Step 2: Image and video analysis

[0441] The server retrieves images and videos from a temporary database and uses an image recognition engine to analyze the type of food and the atmosphere of the restaurant.

[0442] The server extracts characteristics from the analysis results, such as the type of cuisine (e.g., Japanese, Western), the atmosphere of the restaurant (e.g., casual, high-end), and price range.

[0443] Step 3: Natural Language Processing (NLP)

[0444] The server retrieves the collected comments and uses NLP technology to analyze users' ratings and impressions.

[0445] The server scores the collected posts based on the number of likes and comments, assigning them a credibility and recommendation rating.

[0446] Step 4: Adding location information

[0447] The server retrieves the location information contained in the post and identifies the exact address from the extralocation data.

[0448] The server checks the location against other geographic databases to verify its accuracy.

[0449] Step 5: Data mapping and visualization

[0450] The data is plotted on a map based on the information analyzed by the server.

[0451] The server highlights information that interests the user and visually emphasizes it on the map.

[0452] Step 6: User Interface

[0453] The device obtains the user's current location information and displays it on a map.

[0454] The device accepts user operations and narrows down the information according to the filter conditions (e.g., Japanese food, Western food, cafes, etc.).

[0455] The user browses the restaurant information displayed as a search result and obtains detailed information.

[0456] Step 7: Updates and Feedback

[0457] The server periodically collects new data and updates the existing database with the latest information.

[0458] The server receives feedback from users to improve the accuracy and usability of the system.

[0459] Example 1

[0460] 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."

[0461] Conventional gourmet information systems were unreliable and it was difficult to obtain specific ratings and detailed information. Furthermore, it was time-consuming to manually collect and analyze information from individual posts, making it difficult to provide information intuitively to users. Furthermore, information was not updated in real time, making it difficult to reflect user feedback.

[0462] 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.

[0463] In this invention, the server includes means for collecting information about meals from posts on the SNS, means for analyzing the type of meal and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing location information from the collected information and identifying accurate geographic information, means for displaying the meal information based on the analysis on a map, means for users to check and manipulate the information on the map using an application, means for periodically collecting new data and updating the database, and means for collecting user feedback and improving the accuracy and usability of the analysis algorithm. This allows users to obtain reliable, detailed gourmet information in real time and intuitively check it on a map.

[0464] "SNS" is an abbreviation for social networking service, an online platform for people to share information and interact over the Internet.

[0465] A "server" refers to a computer system that accepts requests from clients over a network and provides data and services.

[0466] "Meal" refers to any food or drink consumed, including the act of consuming food.

[0467] "Information" refers to facts, data, knowledge, etc. about a subject, and is expressed through language, numbers, images, sounds, etc.

[0468] "Image recognition technology" is a technology that allows computers to identify and analyze objects and patterns contained in images and photographs.

[0469] "Natural language processing technology" is a technology that enables computers to understand and generate human language, and includes applications such as text analysis, translation, and dialogue systems.

[0470] A "database" is a collection of structured data, and is a system designed to enable efficient searching, adding, updating, and deleting.

[0471] "Location information" refers to geographical information about a specific point or place, and is represented by data such as latitude, longitude, and address.

[0472] A "map" is a visual representation of a particular portion of geographic space, depicting roads, buildings, natural features, etc.

[0473] "Feedback" refers to opinions and reactions provided by users regarding a system or service, which are used for improvement and adjustment.

[0474] An "analytical algorithm" is a computational procedure or method for analyzing data and finding patterns or regularities in it.

[0475] "Usability" refers to the ease of use and operation of a system or product, and is the characteristic that enables users to achieve their goals efficiently.

[0476] This invention is a system that collects and analyzes gourmet information from social networking sites and intuitively displays it on a map to improve user convenience. This system collects information about food from posts on social networking sites, analyzes it using image recognition technology and natural language processing technology, and plots geographical information based on the results to provide to users.

[0477] Hardware and software used

[0478] Hardware: Servers, user terminals

[0479] Software: Public APIs for social networking sites, image recognition technology (e.g., Google Cloud Vision API), natural language processing technology (e.g., spaCy, GPT-4), map display libraries (e.g., Leaflet.js), databases (e.g., MySQL)

[0480] Specific explanation of the process

[0481] 1. Data Collection

[0482] The server uses the public API of the SNS to collect posts with a specific hashtag (e.g., "gourmet"). For example, the server uses the Twitter API to periodically retrieve posts tagged with "gourmet" every day at 3:00 PM and store them in a database in JSON format.

[0483] 2. Image and video analysis

[0484] The server applies image recognition technology to the collected image data. For example, it uses the Google Cloud Vision API to extract features such as "sushi," "Japanese food," and "luxury" from the image, organizes them, and stores them in a database.

[0485] 3. Natural Language Processing (NLP)

[0486] The server analyzes the comments in the post using natural language processing technology. For example, it uses GPT-4 to extract "likes" from a comment like "The sushi at this restaurant was amazing!", and then scores the reliability of the comment based on the number of likes and comments, and stores the results in a database.

[0487] 4. Adding location information

[0488] The server analyzes the location information attached to the post and converts it into accurate geographic information. Specifically, it compares the metadata and explicit location information in the post with the Google Maps API and registers the coordinates in a database.

[0489] 5. Data Mapping and Visualization

[0490] The server plots the analysis results on a map and displays them in a format that is easy for users to understand. For example, Leaflet.js is used to display the analyzed information as pins on a map, and an interface is provided that allows users to click on the pins to view detailed information.

[0491] 6. User Interface

[0492] Users can use the application to search and manipulate information on a map. For example, if a user enters filter criteria such as "sushi" or "Shinjuku Ward," pins for restaurants that match the criteria will appear on the map.

[0493] 7. Updates and Feedback

[0494] The server periodically collects new data and updates the database with the latest information. It also collects user feedback and updates the analysis algorithm to improve the system's accuracy and usability. For example, if a user reports that "this restaurant information is not accurate," the system uses that feedback to improve the accuracy of location information and analysis results.

[0495] Examples of specific examples and prompts

[0496] Specific examples

[0497] The server uses the Twitter API to automatically collect posts tagged with "gourmet."

[0498] Image data is analyzed using the Google Cloud Vision API and feature tags are generated.

[0499] GPT-4 analyzes comments and calculates a rating score.

[0500] Use the Google Maps API to check geographic information.

[0501] The analysis results are plotted on a map using Leaflet.js, providing a visual presentation to the user.

[0502] Users can use search filters in the application to display information on the map that matches specific criteria.

[0503] The server updates the data based on user feedback to improve the accuracy of the system.

[0504] Prompt Sentence Examples

[0505] "Please explain in detail the process of the system that collects gourmet information from social media posts, analyzes ratings and characteristics, and displays them on a map."

[0506] "Please give me an example of how image recognition technology can be used to extract the type and characteristics of food."

[0507] "Please explain how you would improve the system based on user feedback."

[0508] In this way, this system collects and analyzes gourmet information from social media in real time, helping users choose dining locations in an intuitive and personalized way.

[0509] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0510] Step 1:

[0511] Data collection

[0512] The server uses the SNS's public API to collect posts with the "gourmet" hashtag.

[0513] Input: A social networking site's public API and the hashtag "gourmet."

[0514] What it does: It periodically sends API requests and receives the posted data in response.

[0515] Output: Social media post data (images, videos, comments, likes, location information, etc.).

[0516] Step 2:

[0517] Data Storage

[0518] The server stores the collected post data in a database.

[0519] Input: Post data collected from social media.

[0520] What it does: Organizes submitted data by field and stores it in a database.

[0521] Output: Organized submission data in a database.

[0522] Step 3:

[0523] Image and video analysis

[0524] The server uses the Google Cloud Vision API to analyze the collected image data.

[0525] Input: Image data retrieved from a database.

[0526] How it works: Image data is sent to the Google Cloud Vision API, and the returned analysis results (e.g., characteristics such as "sushi," "Japanese food," and "luxury") are organized.

[0527] Output: Image data with extracted features.

[0528] Step 4:

[0529] Natural Language Processing (NLP)

[0530] The server analyzes the comment portion using natural language processing technology (e.g., spaCy, GPT-4).

[0531] Input: Comment data retrieved from the database.

[0532] How it works: Comment data is input into a natural language processing model, and the returned ratings and recommendation data is organized.

[0533] Output: Comment data with numerical ratings and recommendation levels.

[0534] Step 5:

[0535] Like and comment scoring

[0536] The server scores the credibility and recommendation of posts based on the number of likes and comments.

[0537] Input: Number of likes and comments retrieved from the database.

[0538] How it works: The acquired data is fed into an algorithm to calculate trustworthiness and recommendation score.

[0539] Output: Confidence and recommendation scores.

[0540] Step 6:

[0541] Adding location information

[0542] The server analyzes the location information contained in the collected posts and identifies precise geographic information.

[0543] Input: Post metadata and explicit location information.

[0544] What it does: Sends location information to the Google Maps API and organizes the coordinate data returned.

[0545] Output: Accurate geographic information.

[0546] Step 7:

[0547] Data Mapping and Visualization

[0548] The server plots the analyzed information on a map and provides it visually to the user.

[0549] Input: Analysis results stored in a database.

[0550] How it works: Using a map display library (e.g. Leaflet.js), the analysis results are displayed as pins on a map, and clicking on the pins displays more information.

[0551] Output: Map view with pins.

[0552] Step 8:

[0553] User Interface

[0554] Users use the application to search and manipulate information on the map.

[0555] Input: User's search filter criteria (e.g. cuisine type, price range, region, etc.).

[0556] How it works: Searches a database based on user input and displays information that matches the criteria on a map.

[0557] Output: Map display of restaurant information that matches the conditions.

[0558] Step 9:

[0559] Updates and Feedback

[0560] The server periodically collects new data and updates the database.

[0561] Input: Newly collected social media posting data and user feedback.

[0562] What it does: Adds new submissions to the database and improves the analysis algorithm based on feedback.

[0563] Output: Updated database and improved algorithms.

[0564] In this way, this system can collect and analyze gourmet information from SNS posts in real time, and provide users with intuitive and detailed information.

[0565] (Application example 1)

[0566] 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."

[0567] Conventional food delivery systems have the problem that it takes a huge amount of time and effort for users to find a restaurant that suits their preferences. Furthermore, there are not enough methods to utilize gourmet information on social media, and real-time updated rating information cannot be effectively utilized. Furthermore, users have to move between different platforms, which is inconvenient. There is a need for a system that can solve these issues and improve user convenience.

[0568] 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.

[0569] In this invention, the server includes means for collecting information about food from posts on the SNS, means for analyzing the type of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing the quoted location information and identifying accurate geographic information, means for displaying food information based on the analysis on a map, means for introducing restaurants recommended from the analyzed information based on keywords searched by the user and the user's current location, and means for directly ordering from the selected restaurant. This enables users to quickly find their favorite restaurant and easily order from it based on reliable gourmet information collected in real time from SNS posts.

[0570] "SNS posts" refers to information such as comments, images, and videos that users make public on social networking services.

[0571] "Food information" refers to data about the type of food and drink, its characteristics, price range, and the environment in which it is served.

[0572] "Image recognition technology" is a technology that extracts specific features and patterns from image data and performs identification and classification.

[0573] "Natural language processing technology" is a technology that mechanically analyzes, understands, and generates human language.

[0574] "Location Information" refers to geographic data including the latitude and longitude of a specific point.

[0575] "Map display" refers to a map for visually presenting geographic information.

[0576] "Search keywords" refer to words or phrases that users enter to retrieve content of interest.

[0577] "Current location" refers to geographic information about the user's current location.

[0578] "Restaurant" refers to a commercial establishment that serves food and beverages.

[0579] "Order" refers to the act of a User making a request to purchase a product or service.

[0580] "Credibility" refers to the property of indicating the accuracy and reliability of information.

[0581] System Overview

[0582] This invention is a food delivery system that collects and analyzes food information from social media posts, intuitively displays it on a map, and enables users to efficiently find their favorite restaurants and place orders directly with those restaurants. This system consists of social media data collection, image recognition, natural language processing, location information analysis, map display, search engine, and ordering functions.

[0583] Used technologies and data processing

[0584] 1. Data Collection

[0585] The system uses the public API of social media platforms to collect posts with specific hashtags (e.g., "food"). The specific software used is Python and social media APIs (e.g., Twitter API, Instagram API). The collected data is stored in MongoDB.

[0586] 2. Image and video analysis

[0587] The server analyzes the collected images and videos using AI image recognition technology such as Google Cloud Vision API. During the analysis process, characteristics such as the type of food and the atmosphere of the restaurant are identified. For example, from an image of sushi, characteristics such as "sushi," "Japanese food," and "high-end" are extracted.

[0588] 3. Natural Language Processing

[0589] Comments on posts are analyzed using NLP technology (e.g., spaCy and BERT). This extracts user ratings and impressions, and then scores the reliability and recommendation level based on the number of likes and comments. For example, a "high rating" is automatically extracted from a comment such as "The sushi at this restaurant was amazing!", and the recommendation level increases if there are multiple likes.

[0590] 4. Adding location information

[0591] Analyze the location information contained in SNS posts to identify accurate geographic information. Use geographic information services such as Geopy to analyze the location information. Based on the location information contained in the post, match it with other geographic databases (such as Google Maps API).

[0592] 5. Data Mapping and Visualization

[0593] The analyzed information is plotted on a map using map display libraries such as Leaflet.js and Google Maps API, and users can use search filters to narrow down their search by their preferred genre or price range.

[0594] 6. Order function

[0595] Based on the user's search keywords and current location, the app analyzes information and recommends restaurants, which are then displayed on a map. Users can easily check restaurant information and place orders directly from the app.

[0596] Specific examples

[0597] When a smartphone user searches for the keyword "sushi in Shibuya Ward," pins are displayed on a map showing restaurants with "sushi," "Shibuya Ward," and "highly rated" based on recent social media posting data. The user can then select a restaurant called "Sushimaru," check out the highly rated reviews and photos, and place an order within the app.

[0598] Prompt Sentence Examples

[0599] When a user types in the app, "Search for highly rated sushi restaurants in Shibuya Ward," the system retrieves the appropriate information from its internal database and displays the results on a map.

[0600] In this way, the present invention is a system that collects and analyzes SNS data in real time and provides users with useful information, allowing them to select restaurants and place orders easily and efficiently.

[0601] Specific examples of hardware and software used

[0602] SNS API (Twitter API, Instagram API)

[0603] Python

[0604] MongoDB

[0605] Google Cloud Vision API

[0606] spaCy, BERT

[0607] geopy, Google Maps API

[0608] Leaflet.js

[0609] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0610] Step 1:

[0611] The server periodically collects posts with a specific hashtag (e.g., "food") using the public API of the social networking site (e.g., Twitter API, Instagram API). The collected data includes images, videos, comments, number of likes, and location information. This data is stored in MongoDB.

[0612] Input: SNS API

[0613] Output: Collected data stored in MongoDB

[0614] Specific operation: The server calls the SNS API, retrieves relevant posts based on the filter conditions, and saves them in the database.

[0615] Step 2:

[0616] The server analyzes the collected images and videos using the Google Cloud Vision API, identifying characteristics such as the type of food and the restaurant's atmosphere.

[0617] Input: Image data stored in MongoDB

[0618] Output: Analyzed features (e.g. "Sushi", "Japanese food", "High-end")

[0619] Specific operation: The server sends the image data to the Google Cloud Vision API and adds the returned feature information to the database.

[0620] Step 3:

[0621] The server uses NLP technology (e.g., spaCy or BERT) to analyze the collected comments, extract user ratings and impressions, and score the trustworthiness and recommendation level based on the number of likes and comments.

[0622] Input: Comment data stored in MongoDB

[0623] Output: Extracted ratings and recommendation scores

[0624] Specific operation: The server inputs the comment data into the NLP model, extracts ratings and opinions as analysis results, calculates the reliability and recommendation level, and stores them in a database.

[0625] Step 4:

[0626] The server uses the geopy library to analyze the location information contained in the post, identify precise geographic information, and further refine the location information by comparing it with other geographic databases (such as the Google Maps API).

[0627] Input: Geolocation data stored in MongoDB

[0628] Output: Precisely identified geographic location

[0629] What it does: The server inputs the location data into the geopy library and checks the returned latitude and longitude information against a geographic database to verify accuracy.

[0630] Step 5:

[0631] The server plots the analyzed information on a map using Leaflet.js and the Google Maps API. Users can view the information on the map through a smartphone or PC application and use search filters to narrow down the restaurants they find based on their preferences.

[0632] Input: Parsed feature and geographic information

[0633] Output: Restaurant information displayed on a map

[0634] Specific operation: The server inputs the analyzed feature information and location information into the map display library and provides it visually to the user.

[0635] Step 6:

[0636] Users input their search keywords and current location, and the server recommends restaurants based on that information. Users can then check the restaurant information and place an order directly through the application if necessary.

[0637] Input: Search keywords and current location information entered by the user

[0638] Output: Recommended restaurant information displayed as search results and order confirmation information

[0639] Specific operation: The user enters search keywords and current location, and the server retrieves and displays the corresponding information from the database and processes the order for the restaurant selected by the user.

[0640] 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.

[0641] The present invention provides a system for collecting and analyzing gourmet information and user emotion information from social networking site posts, and intuitively displaying the information on a map, with the aim of improving user convenience. Specific embodiments of this system are described below.

[0642] Data collection

[0643] The server periodically collects posts with specific hashtags or keywords (e.g., gourmet, restaurant) using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, location information, and sentiment analysis of comments. For example, the server collects posts tagged with "gourmet" and stores them in a database.

[0644] Image and video analysis

[0645] The server analyzes the collected images and videos using AI image recognition technology, which identifies characteristics such as the type of food, the atmosphere of the restaurant, and the price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[0646] Natural Language Processing (NLP)

[0647] The server uses NLP technology to analyze comments on posts and extract user ratings and impressions. It then scores the reliability and recommendation level of the post based on the number of likes and comments. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and a high recommendation level is assigned to posts with over 1,000 likes.

[0648] Emotion analysis using an emotion engine

[0649] The server analyzes the collected comments and their language data using an emotion engine to recognize the user's emotions. For example, it can extract "positive emotions" from a comment like "I love the atmosphere of this store!"

[0650] The server adjusts the recommendation level for food and restaurants based on the user's emotional data, giving a higher recommendation level to posts with positive emotions and a lower recommendation level to posts with negative emotions.

[0651] Adding location information

[0652] Our servers retrieve the location information contained in the post, use the extralocation data to determine the exact address, and verify the accuracy of the location information by cross-checking it with other geolocation databases.

[0653] Data Mapping and Visualization

[0654] The server plots the data on a map based on the information analyzed. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" will display detailed information about the restaurant and any posted images. The information displayed also takes into account the results of sentiment analysis.

[0655] User Interface

[0656] Users can use the application to view and manipulate information on a map. They can use search filters to narrow down their search by their preferred genre (e.g., Japanese, Western, cafe) or price range. The application also provides information on nearby restaurants based on the user's current location. Furthermore, users can select the "sushi" tag to display highly rated sushi restaurants in Shinjuku Ward on the map.

[0657] Updates and Feedback

[0658] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[0659] In this way, this system collects and analyzes gourmet information and user sentiment information from SNS in real time, helping users select dining locations in an intuitive and personalized way.

[0660] The processing flow will be explained below.

[0661] Step 1: Data collection

[0662] The server uses the SNS's public API to collect posts using specific hashtags or keywords (e.g., gourmet, restaurant).

[0663] The server stores the collected post data in a temporary database, including post IDs, image and video URLs, comments, number of likes, and location information.

[0664] Step 2: Image and video analysis

[0665] The server retrieves images and videos from a temporary database and uses an image recognition engine to analyze the type of food and the atmosphere of the restaurant.

[0666] The server extracts characteristics from the analysis results, such as the type of cuisine (e.g., Japanese, Western), the atmosphere of the restaurant (e.g., casual, high-end), and price range.

[0667] Step 3: Natural Language Processing (NLP)

[0668] The server retrieves the collected comments and uses NLP technology to analyze users' ratings and impressions.

[0669] The server scores the collected posts based on the number of likes and comments, assigning them a credibility and recommendation rating.

[0670] Step 4: Emotion analysis using the emotion engine

[0671] The server analyzes the collected comments and their language data using an emotion engine to recognize the user's emotions.

[0672] Based on the results of the emotion analysis, the server assigns a high recommendation level to positive emotions and a low recommendation level to negative emotions.

[0673] Step 5: Adding location information

[0674] The server retrieves the location information contained in the post and identifies the exact address from the extralocation data.

[0675] The server checks the location against other geographic databases to verify its accuracy.

[0676] Step 6: Data mapping and visualization

[0677] The data is plotted on a map based on the information analyzed by the server.

[0678] The server highlights information that interests the user and visually emphasizes it on the map.

[0679] Step 7: User Interface

[0680] The device obtains the user's current location information and displays it on a map.

[0681] The device accepts user operations and narrows down the information according to the filter conditions (e.g., Japanese food, Western food, cafes, etc.).

[0682] The user browses the restaurant information displayed as a search result and obtains detailed information.

[0683] Step 8: Updates and Feedback

[0684] The server periodically collects new data and updates the existing database with the latest information.

[0685] The server receives feedback from users to improve the accuracy and usability of the system.

[0686] Example 2

[0687] 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."

[0688] Conventional systems have difficulty accurately extracting information about food types, restaurant atmospheres, and user ratings when collecting and analyzing gourmet information on social media. Furthermore, the collected information lacks reliability, resulting in a poor user experience. Furthermore, intuitive map displays that take user emotions and ratings into account are lacking, creating a need for a user-friendly system.

[0689] 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.

[0690] In this invention, the server includes means for collecting information about food from posts on the SNS, means for analyzing the type of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing the sentiment of the collected comments using an emotion engine and adjusting the recommendation level based on the sentiment, means for analyzing quoted location information and identifying accurate geographic information, and means for displaying food information based on the analysis on a map. This allows users to intuitively grasp reliable gourmet information and easily find restaurants and dishes that suit their preferences.

[0691] "SNS posts" refer to content such as text, images, and videos that users make public on social networking services.

[0692] "Information about food" refers to food and related information such as the type of food, name, recipe, restaurant name, price, rating, image, video, and location information.

[0693] "Image recognition technology" is a technology that uses computer vision technology to identify objects in images and videos and analyze their features.

[0694] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language, and is a technology that analyzes text data and extracts emotions.

[0695] "User ratings" refers to user opinions and impressions contained in posts on social media, as well as rating scores based on them.

[0696] "Quoted location information" refers to data indicating geographic coordinates or locations contained in posts on social media.

[0697] An "emotion engine" refers to technology that analyzes emotions from text data and recognizes emotional categories such as positive, negative, and neutral.

[0698] "Recommendation level" is an index that indicates the degree to which a particular dish or restaurant is recommended based on analyzed information.

[0699] "Precise geographic information" is information that accurately identifies a specific address or location based on the location information contained in a post.

[0700] "Means for displaying on a map" refers to technology that uses a geographic information system to visualize the analyzed information on a map.

[0701] The present invention provides a system that collects and analyzes gourmet information and user emotion information from social networking site posts and intuitively displays the information on a map. Specific embodiments of this system will be described below.

[0702] Data collection

[0703] The server periodically collects posts containing specific hashtags or keywords (e.g., food, restaurant) using the public API of the social networking site. For example, it retrieves posts using Facebook's Graph API or Twitter's API. The server stores the collected post content, such as images, videos, comments, number of likes, and location information, in a database. The server searches for posts containing the "food" hashtag every hour and adds newly found posts to the database.

[0704] Image and video analysis

[0705] The server uses AI image recognition technologies such as Google Cloud Vision API and Amazon Rekognition to analyze the collected images and videos. This allows it to identify the type of food, the restaurant's atmosphere, price range, and other information. For example, it can detect the presence of sushi in a particular image and store characteristics such as "sushi," "Japanese food," and "high-end" in a database. Specifically, the server sequentially analyzes newly collected images and generates metadata about the type of food and the restaurant's atmosphere.

[0706] Natural Language Processing (NLP)

[0707] The server uses natural language processing technologies such as Google Cloud Natural Language API and OpenAI's GPT-3 to analyze comments on posts and extract user ratings and impressions. It also scores the reliability and recommendation level of posts based on the number of likes and comments. For example, it extracts a "high rating" from a comment like "The sushi at this restaurant was amazing!" and assigns a high recommendation level to posts with over 1,000 likes. Specifically, the server analyzes newly collected comments, calculates a reliability score, and stores it in a database.

[0708] Emotion analysis using an emotion engine

[0709] The server uses emotion engines such as Azure Text Analytics and IBM Watson to perform emotion analysis on the collected comments. This allows it to recognize positive, negative, and neutral emotions from the comments and adjust the recommendation level for a dish or restaurant accordingly. For example, a "positive emotion" is extracted from a comment like "I love the atmosphere of this restaurant!" The server calculates an emotion score for the collected comments and assigns a higher recommendation level to posts with a high percentage of positive emotions.

[0710] Adding location information

[0711] The server uses the location information contained in the post to identify the exact address using the Google Maps API or OpenStreetMap API. It also verifies the accuracy of the location information by comparing it with other geographic information databases. For example, it can identify the address of a specific restaurant from the location information. Specifically, the server sequentially analyzes posts with location information and stores the exact address information in a database.

[0712] Data Mapping and Visualization

[0713] Based on the analyzed information, the server plots the data on a map using Leaflet, Google Maps, etc. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" displays detailed information about the restaurant and any posted images. Specifically, the server displays data that meets the specified criteria as pins on the map, and clicking on the pin displays detailed information.

[0714] User Interface

[0715] Users can use applications (e.g., mobile apps or web apps) to view and manipulate information on a map. Users can use search filters to narrow down their search by their preferred genre and price range. The app also provides information about nearby restaurants based on the user's current location. For example, if a user selects the "sushi" tag, highly rated sushi restaurants in Shinjuku Ward are displayed on a map and detailed information about them is displayed.

[0716] Updates and Feedback

[0717] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[0718] Example prompt sentence:

[0719] Please explain the system that collects and analyzes gourmet information and user sentiment information from social media posts and displays it intuitively on a map.

[0720] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0721] Step 1:

[0722] Data collection

[0723] The server uses the public API of the social networking site to periodically collect posts containing specific hashtags or keywords (e.g., gourmet, restaurant). Specifically, it retrieves posts using Facebook's Graph API or Twitter's API. It receives the specified hashtag or keyword as input and searches for posts containing that hashtag. As output, it stores the content of the collected posts (images, videos, comments, number of likes, location information) in a database. The server searches for posts containing the hashtag "gourmet" every hour and adds new posts to the database.

[0724] Step 2:

[0725] Image and video analysis

[0726] The server analyzes the collected images and videos using AI image recognition technologies such as Google Cloud Vision API and Amazon Rekognition. It receives the collected image and video data as input and stores features such as the type of food, restaurant atmosphere, and price range as output in a database. Specifically, it detects the presence of sushi in a particular image and extracts features such as "sushi," "Japanese food," and "high-end." The server sequentially analyzes newly collected images and generates metadata related to the type of food and restaurant atmosphere.

[0727] Step 3:

[0728] Natural Language Processing (NLP)

[0729] The server uses natural language processing technologies such as Google Cloud Natural Language API and OpenAI's GPT-3 to analyze comments on posts. It receives collected comment data as input and extracts user ratings and impressions as output, calculating reliability scores and recommendation levels and storing them in a database. Specifically, it extracts "high ratings" from comments such as "The sushi at this restaurant was amazing!" and assigns a high recommendation level to posts with over 1,000 likes. The server analyzes the comments and calculates reliability scores.

[0730] Step 4:

[0731] Emotion analysis using an emotion engine

[0732] The server uses emotion engines such as Azure Text Analytics and IBM Watson to analyze the emotions of the collected comments. It receives the collected comment data as input and stores emotion scores such as positive, negative, and neutral as output in a database. For example, it extracts "positive emotion" from the comment "I love the atmosphere of this store!" The server inputs the collected comments into the emotion engine, calculates the emotion score, and assigns a high recommendation rating to posts with a high percentage of positive emotion.

[0733] Step 5:

[0734] Adding location information

[0735] The server analyzes the location information included in the post using the Google Maps API or OpenStreetMap API to identify the exact address. It receives the location information (coordinate data) included in the post as input and stores the specific address in a database as output. For example, it identifies the address of a specific restaurant from the location information. The server analyzes the post with location information and stores the exact address information in a database.

[0736] Step 6:

[0737] Data Mapping and Visualization

[0738] Based on the analyzed information, the server plots the data on a map using Leaflet, Google Maps, or similar. It receives the analyzed food information, user ratings, and sentiment scores as input, and provides visualized data (such as pins) on the map as output. For example, clicking on a pin labeled "Japanese food," "sushi," or "highly rated" displays detailed information about the restaurant and any posted images. The server displays data that meets the specified criteria as pins on the map, and clicking on the pins provides detailed information.

[0739] Step 7:

[0740] User Interface

[0741] Users use an application (mobile or web) to view and manipulate information on a map. The application receives the user's search criteria (e.g., genre, price range, tags) as input, and displays corresponding restaurant and cuisine information on the map as output. For example, if a user selects the tag "sushi," highly rated sushi restaurants in Shinjuku Ward are displayed on the map and detailed information can be viewed. Users can also receive information about nearby restaurants based on their current location.

[0742] Step 8:

[0743] Updates and Feedback

[0744] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. It receives the collected new data and user feedback as input, and provides an updated database and an analysis algorithm with adjusted accuracy as output. For example, if a user reports that "this restaurant information is not accurate," the accuracy of the location information and analysis results is adjusted based on that feedback.

[0745] (Application example 2)

[0746] 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."

[0747] In today's world, people increasingly have opportunities to obtain gourmet information through social media. However, it is not easy to efficiently find reliable information and restaurants and delivery services that suit one's preferences from the vast amount of information available. In particular, the lack of personalized information based on the user's preferences and current location is a challenge. Another issue is the lack of functionality to analyze emotional information and adjust the recommendation level, making it difficult for users to choose a service that will truly satisfy them.

[0748] 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 collecting information about food from posts on SNS, means for analyzing the types of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing quoted location information and identifying accurate geographic information, means for displaying food information based on the analysis on a map, and means for suggesting recommended delivery services based on the user's preferences and location information. This makes it possible to provide reliable, personalized gourmet information that is suitable for the user from a vast amount of information.

[0749] "SNS" is an abbreviation for social networking service, an online platform that allows users to share information and interact with each other via the Internet.

[0750] "Image recognition technology" is a technology in the field of computer vision that identifies and classifies objects and scenes in images and videos.

[0751] "Natural language processing technology" is a technology that enables computers to analyze and understand human language, and is used to analyze and automatically generate text data.

[0752] "Location information" is information for identifying a geographical location, and is mainly expressed in the form of latitude and longitude.

[0753] "Delivery service" refers to a service that delivers food, beverages, and merchandise directly to a location designated by the user.

[0754] "Personalization" refers to providing individually optimized experiences and services based on each user's preferences and behavior.

[0755] "Reliability" refers to the degree to which information or services are relevant, accurate, and consistent and can be relied upon by users.

[0756] "Emotional information" is data that reflects the user's emotions, such as positive, negative, or neutral, and is the analysis result based on that information.

[0757] This system collects information about food from social media posts and suggests optimal delivery services based on the user's preferences and location. This system mainly uses a server to perform the following processes:

[0758] First, the server periodically collects posts with specific hashtags or keywords (e.g., gourmet, delivery) using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, and location information. For example, the server periodically collects posts tagged with "delivery" and stores them in a database.

[0759] The server then analyzes the collected images and videos using AI image recognition technology, identifying characteristics such as the type of food, atmosphere, and price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[0760] The server then uses natural language processing (NLP) to analyze the collected comments and extract user ratings and impressions. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and the reliability and recommendation of the post are scored based on the number of likes and comments.

[0761] The server then uses an emotion engine to analyze the collected comments and their language data to recognize the user's emotions. For example, a "positive emotion" is extracted from a comment like "I love the atmosphere of this restaurant!" The recommendation level for the food or restaurant is adjusted based on this emotional data.

[0762] Additionally, the server captures the location information contained in the post, uses the extralocation data to determine the exact address, and verifies the accuracy of the location information by checking it against other geographic databases.

[0763] The server then uses the analysis results to suggest delivery services that take into account the user's preferences and location. For example, a user can select the tag "sushi" to display nearby highly rated sushi restaurants on a map. The server also suggests the best delivery options based on the user's current location.

[0764] The system runs on servers on AWS (Amazon Web Services) or Google Cloud Platform, with data stored in a PostgreSQL database. It uses TensorFlow or OpenCV for image recognition, Google Cloud Natural Language API for NLP, IBM Watson Tone Analyzer for sentiment analysis, and Google Maps API for accurate location information.

[0765] For example, consider the following prompt:

[0766] "Analyze the following image to identify the type of food and price range: Sushi image"

[0767] "Analyze the following comment with your sentiment engine to determine whether it's positive, negative, or neutral: 'The sushi at this place was amazing!'"

[0768] In this way, the system can provide users with reliable, personalized gourmet information from a vast amount of information.

[0769] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0770] Step 1:

[0771] The server periodically collects posts with specific hashtags or keywords (e.g., gourmet, delivery) using the public API of the social networking site. Here, it sends an API request and analyzes the returned JSON data to extract images, videos, comments, number of likes, location information, etc. The input is the keyword of the API request, and the output is the collected post data.

[0772] Step 2:

[0773] The server analyzes the collected images and videos using AI image recognition technology (e.g., TensorFlow or OpenCV). This identifies features such as the type of cuisine, the atmosphere of the restaurant, and the price range. Specifically, the image data is input into the model, and feature labels (e.g., "sushi," "Japanese cuisine," "high-end") are obtained as output. The input is the images and videos of the posted data, and the output is the analyzed feature information.

[0774] Step 3:

[0775] The server analyzes the collected comments on posts using natural language processing technology (e.g., Google Cloud Natural Language API) to extract user ratings and impressions. Here, text data is sent to the API, and rating information is extracted based on the returned analysis results. The input is the comments on the post data, and the output is the analyzed ratings and impressions.

[0776] Step 4:

[0777] The server analyzes the collected comments and their language data using an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. Specifically, the comment text is input into the emotion engine, and emotion labels such as positive, negative, and neutral are obtained as output. The input is the posted comments, and the output is the analyzed emotion information.

[0778] Step 5:

[0779] The server retrieves the location information contained in the post, identifies the exact address from the extrapolation data, and verifies the accuracy of the location information by checking it against other geographic information databases (e.g., Google Maps API). The input is the location information of the post data, and the output is the confirmed exact address information.

[0780] Step 6:

[0781] The server then proposes delivery services based on the analysis results, taking into account the user's preferences and location information. Specifically, it runs an algorithm that recommends optimal delivery options based on the user's current location and preferences. The input is the user's current location and preference data, and the output is the proposed delivery service information.

[0782] Step 7:

[0783] Users can check suggested delivery services and restaurant information on a map through their device. Users can manipulate the information on the map to view detailed information and posted images. The input is the suggested delivery service information, and the output is the map information and detailed data that the user can view.

[0784] In this way, the system performs individual processing at each step, providing delivery services and gourmet information that are suited to the user.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] [Third embodiment]

[0789] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0790] 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.

[0791] 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).

[0792] 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.

[0793] 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.

[0794] 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).

[0795] 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. 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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."

[0801] The present invention provides a system for collecting and analyzing gourmet information from social networking site posts and displaying it intuitively on a map, with the aim of improving user convenience. Specific embodiments of this system will be described below.

[0802] Data collection

[0803] The server periodically collects food-related posts using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, location information, etc. For example, the server collects posts tagged with "food" and stores them in a database.

[0804] Image and video analysis

[0805] The server analyzes the collected images and videos using AI image recognition technology, which identifies characteristics such as the type of food, the atmosphere of the restaurant, and the price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[0806] Natural Language Processing (NLP)

[0807] The server uses NLP technology to analyze comments on posts and extract user ratings and impressions. It then scores the reliability and recommendation level of the post based on the number of likes and comments. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and a high recommendation level is assigned to posts with over 1,000 likes.

[0808] Adding location information

[0809] The server analyzes the location information in the post to determine its precise geographic location, using image metadata and any explicit location information provided by the poster, and cross-references it with other geographic databases.

[0810] Data Mapping and Visualization

[0811] The server plots the analyzed information on a map and provides it visually to the user. When a user accesses the application, restaurants are displayed on the map as pins, and clicking on them displays detailed information. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" displays detailed information about the restaurant and any posted images.

[0812] User Interface

[0813] Users can use the application to view and manipulate information on a map. They can use search filters to narrow down their search by their preferred genre (e.g., Japanese, Western, cafe) or price range. The application also provides information on nearby restaurants based on the user's current location. Users can also select the "sushi" tag to display highly rated sushi restaurants in Shinjuku Ward on the map.

[0814] Updates and Feedback

[0815] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[0816] In this way, this system collects and analyzes gourmet information from social media in real time, helping users choose dining locations in an intuitive and personalized way.

[0817] The processing flow will be explained below.

[0818] Step 1: Data collection

[0819] The server uses the SNS's public API to collect posts using specific hashtags or keywords (e.g., gourmet, restaurant).

[0820] The server stores the collected post data in a temporary database, including post IDs, image and video URLs, comments, number of likes, and location information.

[0821] Step 2: Image and video analysis

[0822] The server retrieves images and videos from a temporary database and uses an image recognition engine to analyze the type of food and the atmosphere of the restaurant.

[0823] The server extracts characteristics from the analysis results, such as the type of cuisine (e.g., Japanese, Western), the atmosphere of the restaurant (e.g., casual, high-end), and price range.

[0824] Step 3: Natural Language Processing (NLP)

[0825] The server retrieves the collected comments and uses NLP technology to analyze users' ratings and impressions.

[0826] The server scores the collected posts based on the number of likes and comments, assigning them a credibility and recommendation rating.

[0827] Step 4: Adding location information

[0828] The server retrieves the location information contained in the post and identifies the exact address from the extralocation data.

[0829] The server checks the location against other geographic databases to verify its accuracy.

[0830] Step 5: Data mapping and visualization

[0831] The data is plotted on a map based on the information analyzed by the server.

[0832] The server highlights information that interests the user and visually emphasizes it on the map.

[0833] Step 6: User Interface

[0834] The device obtains the user's current location information and displays it on a map.

[0835] The device accepts user operations and narrows down the information according to the filter conditions (e.g., Japanese food, Western food, cafes, etc.).

[0836] The user browses the restaurant information displayed as a search result and obtains detailed information.

[0837] Step 7: Updates and Feedback

[0838] The server periodically collects new data and updates the existing database with the latest information.

[0839] The server receives feedback from users to improve the accuracy and usability of the system.

[0840] Example 1

[0841] 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."

[0842] Conventional gourmet information systems were unreliable and it was difficult to obtain specific ratings and detailed information. Furthermore, it was time-consuming to manually collect and analyze information from individual posts, making it difficult to provide information intuitively to users. Furthermore, information was not updated in real time, making it difficult to reflect user feedback.

[0843] 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.

[0844] In this invention, the server includes means for collecting information about meals from posts on the SNS, means for analyzing the type of meal and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing location information from the collected information and identifying accurate geographic information, means for displaying the meal information based on the analysis on a map, means for users to check and manipulate the information on the map using an application, means for periodically collecting new data and updating the database, and means for collecting user feedback and improving the accuracy and usability of the analysis algorithm. This allows users to obtain reliable, detailed gourmet information in real time and intuitively check it on a map.

[0845] "SNS" is an abbreviation for social networking service, an online platform for people to share information and interact over the Internet.

[0846] A "server" refers to a computer system that accepts requests from clients over a network and provides data and services.

[0847] "Meal" refers to any food or drink consumed, including the act of consuming food.

[0848] "Information" refers to facts, data, knowledge, etc. about a subject, and is expressed through language, numbers, images, sounds, etc.

[0849] "Image recognition technology" is a technology that allows computers to identify and analyze objects and patterns contained in images and photographs.

[0850] "Natural language processing technology" is a technology that enables computers to understand and generate human language, and includes applications such as text analysis, translation, and dialogue systems.

[0851] A "database" is a collection of structured data, and is a system designed to enable efficient searching, adding, updating, and deleting.

[0852] "Location information" refers to geographical information about a specific point or place, and is represented by data such as latitude, longitude, and address.

[0853] A "map" is a visual representation of a particular portion of geographic space, depicting roads, buildings, natural features, etc.

[0854] "Feedback" refers to opinions and reactions provided by users regarding a system or service, which are used for improvement and adjustment.

[0855] An "analytical algorithm" is a computational procedure or method for analyzing data and finding patterns or regularities in it.

[0856] "Usability" refers to the ease of use and operation of a system or product, and is the characteristic that enables users to achieve their goals efficiently.

[0857] This invention is a system that collects and analyzes gourmet information from social networking sites and intuitively displays it on a map to improve user convenience. This system collects information about food from posts on social networking sites, analyzes it using image recognition technology and natural language processing technology, and plots geographical information based on the results to provide to users.

[0858] Hardware and software used

[0859] Hardware: Servers, user terminals

[0860] Software: Public APIs for social networking sites, image recognition technology (e.g., Google Cloud Vision API), natural language processing technology (e.g., spaCy, GPT-4), map display libraries (e.g., Leaflet.js), databases (e.g., MySQL)

[0861] Specific explanation of the process

[0862] 1. Data Collection

[0863] The server uses the public API of the SNS to collect posts with a specific hashtag (e.g., "gourmet"). For example, the server uses the Twitter API to periodically retrieve posts tagged with "gourmet" every day at 3:00 PM and store them in a database in JSON format.

[0864] 2. Image and video analysis

[0865] The server applies image recognition technology to the collected image data. For example, it uses the Google Cloud Vision API to extract features such as "sushi," "Japanese food," and "luxury" from the image, organizes them, and stores them in a database.

[0866] 3. Natural Language Processing (NLP)

[0867] The server analyzes the comments in the post using natural language processing technology. For example, it uses GPT-4 to extract "likes" from a comment like "The sushi at this restaurant was amazing!", and then scores the reliability of the comment based on the number of likes and comments, and stores the results in a database.

[0868] 4. Adding location information

[0869] The server analyzes the location information attached to the post and converts it into accurate geographic information. Specifically, it compares the metadata and explicit location information in the post with the Google Maps API and registers the coordinates in a database.

[0870] 5. Data Mapping and Visualization

[0871] The server plots the analysis results on a map and displays them in a format that is easy for users to understand. For example, Leaflet.js is used to display the analyzed information as pins on a map, and an interface is provided that allows users to click on the pins to view detailed information.

[0872] 6. User Interface

[0873] Users can use the application to search and manipulate information on a map. For example, if a user enters filter criteria such as "sushi" or "Shinjuku Ward," pins for restaurants that match the criteria will appear on the map.

[0874] 7. Updates and Feedback

[0875] The server periodically collects new data and updates the database with the latest information. It also collects user feedback and updates the analysis algorithm to improve the system's accuracy and usability. For example, if a user reports that "this restaurant information is not accurate," the system uses that feedback to improve the accuracy of location information and analysis results.

[0876] Examples of specific examples and prompts

[0877] Specific examples

[0878] The server uses the Twitter API to automatically collect posts tagged with "gourmet."

[0879] Image data is analyzed using the Google Cloud Vision API and feature tags are generated.

[0880] GPT-4 analyzes comments and calculates a rating score.

[0881] Use the Google Maps API to check geographic information.

[0882] The analysis results are plotted on a map using Leaflet.js, providing a visual presentation to the user.

[0883] Users can use search filters in the application to display information on the map that matches specific criteria.

[0884] The server updates the data based on user feedback to improve the accuracy of the system.

[0885] Prompt Sentence Examples

[0886] "Please explain in detail the process of the system that collects gourmet information from social media posts, analyzes ratings and characteristics, and displays them on a map."

[0887] "Please give me an example of how image recognition technology can be used to extract the type and characteristics of food."

[0888] "Please explain how you would improve the system based on user feedback."

[0889] In this way, this system collects and analyzes gourmet information from social media in real time, helping users choose dining locations in an intuitive and personalized way.

[0890] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0891] Step 1:

[0892] Data collection

[0893] The server uses the SNS's public API to collect posts with the "gourmet" hashtag.

[0894] Input: A social networking site's public API and the hashtag "gourmet."

[0895] What it does: It periodically sends API requests and receives the posted data in response.

[0896] Output: Social media post data (images, videos, comments, likes, location information, etc.).

[0897] Step 2:

[0898] Data Storage

[0899] The server stores the collected post data in a database.

[0900] Input: Post data collected from social media.

[0901] What it does: Organizes submitted data by field and stores it in a database.

[0902] Output: Organized submission data in a database.

[0903] Step 3:

[0904] Image and video analysis

[0905] The server uses the Google Cloud Vision API to analyze the collected image data.

[0906] Input: Image data retrieved from a database.

[0907] How it works: Image data is sent to the Google Cloud Vision API, and the returned analysis results (e.g., characteristics such as "sushi," "Japanese food," and "luxury") are organized.

[0908] Output: Image data with extracted features.

[0909] Step 4:

[0910] Natural Language Processing (NLP)

[0911] The server analyzes the comment portion using natural language processing technology (e.g., spaCy, GPT-4).

[0912] Input: Comment data retrieved from the database.

[0913] How it works: Comment data is input into a natural language processing model, and the returned ratings and recommendation data is organized.

[0914] Output: Comment data with numerical ratings and recommendation levels.

[0915] Step 5:

[0916] Like and comment scoring

[0917] The server scores the credibility and recommendation of posts based on the number of likes and comments.

[0918] Input: Number of likes and comments retrieved from the database.

[0919] How it works: The acquired data is fed into an algorithm to calculate trustworthiness and recommendation score.

[0920] Output: Confidence and recommendation scores.

[0921] Step 6:

[0922] Adding location information

[0923] The server analyzes the location information contained in the collected posts and identifies precise geographic information.

[0924] Input: Post metadata and explicit location information.

[0925] What it does: Sends location information to the Google Maps API and organizes the coordinate data returned.

[0926] Output: Accurate geographic information.

[0927] Step 7:

[0928] Data Mapping and Visualization

[0929] The server plots the analyzed information on a map and provides it visually to the user.

[0930] Input: Analysis results stored in a database.

[0931] How it works: Using a map display library (e.g. Leaflet.js), the analysis results are displayed as pins on a map, and clicking on the pins displays more information.

[0932] Output: Map view with pins.

[0933] Step 8:

[0934] User Interface

[0935] Users use the application to search and manipulate information on the map.

[0936] Input: User's search filter criteria (e.g. cuisine type, price range, region, etc.).

[0937] How it works: Searches a database based on user input and displays information that matches the criteria on a map.

[0938] Output: Map display of restaurant information that matches the conditions.

[0939] Step 9:

[0940] Updates and Feedback

[0941] The server periodically collects new data and updates the database.

[0942] Input: Newly collected social media posting data and user feedback.

[0943] What it does: Adds new submissions to the database and improves the analysis algorithm based on feedback.

[0944] Output: Updated database and improved algorithms.

[0945] In this way, this system can collect and analyze gourmet information from SNS posts in real time, and provide users with intuitive and detailed information.

[0946] (Application example 1)

[0947] 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."

[0948] Conventional food delivery systems have the problem that it takes a huge amount of time and effort for users to find a restaurant that suits their preferences. Furthermore, there are not enough methods to utilize gourmet information on social media, and real-time updated rating information cannot be effectively utilized. Furthermore, users have to move between different platforms, which is inconvenient. There is a need for a system that can solve these issues and improve user convenience.

[0949] 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.

[0950] In this invention, the server includes means for collecting information about food from posts on the SNS, means for analyzing the type of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing the quoted location information and identifying accurate geographic information, means for displaying food information based on the analysis on a map, means for introducing restaurants recommended from the analyzed information based on keywords searched by the user and the user's current location, and means for directly ordering from the selected restaurant. This enables users to quickly find their favorite restaurant and easily order from it based on reliable gourmet information collected in real time from SNS posts.

[0951] "SNS posts" refers to information such as comments, images, and videos that users make public on social networking services.

[0952] "Food information" refers to data about the type of food and drink, its characteristics, price range, and the environment in which it is served.

[0953] "Image recognition technology" is a technology that extracts specific features and patterns from image data and performs identification and classification.

[0954] "Natural language processing technology" is a technology that mechanically analyzes, understands, and generates human language.

[0955] "Location Information" refers to geographic data including the latitude and longitude of a specific point.

[0956] "Map display" refers to a map for visually presenting geographic information.

[0957] "Search keywords" refer to words or phrases that users enter to retrieve content of interest.

[0958] "Current location" refers to geographic information about the user's current location.

[0959] "Restaurant" refers to a commercial establishment that serves food and beverages.

[0960] "Order" refers to the act of a User making a request to purchase a product or service.

[0961] "Credibility" refers to the property of indicating the accuracy and reliability of information.

[0962] System Overview

[0963] This invention is a food delivery system that collects and analyzes food information from social media posts, intuitively displays it on a map, and enables users to efficiently find their favorite restaurants and place orders directly with those restaurants. This system consists of social media data collection, image recognition, natural language processing, location information analysis, map display, search engine, and ordering functions.

[0964] Used technologies and data processing

[0965] 1. Data Collection

[0966] The system uses the public API of social media platforms to collect posts with specific hashtags (e.g., "food"). The specific software used is Python and social media APIs (e.g., Twitter API, Instagram API). The collected data is stored in MongoDB.

[0967] 2. Image and video analysis

[0968] The server analyzes the collected images and videos using AI image recognition technology such as Google Cloud Vision API. During the analysis process, characteristics such as the type of food and the atmosphere of the restaurant are identified. For example, from an image of sushi, characteristics such as "sushi," "Japanese food," and "high-end" are extracted.

[0969] 3. Natural Language Processing

[0970] Comments on posts are analyzed using NLP technology (e.g., spaCy and BERT). This extracts user ratings and impressions, and then scores the reliability and recommendation level based on the number of likes and comments. For example, a "high rating" is automatically extracted from a comment such as "The sushi at this restaurant was amazing!", and the recommendation level increases if there are multiple likes.

[0971] 4. Adding location information

[0972] Analyze the location information contained in SNS posts to identify accurate geographic information. Use geographic information services such as Geopy to analyze the location information. Based on the location information contained in the post, match it with other geographic databases (such as Google Maps API).

[0973] 5. Data Mapping and Visualization

[0974] The analyzed information is plotted on a map using map display libraries such as Leaflet.js and Google Maps API, and users can use search filters to narrow down their search by their preferred genre or price range.

[0975] 6. Order function

[0976] Based on the user's search keywords and current location, the app analyzes information and recommends restaurants, which are then displayed on a map. Users can easily check restaurant information and place orders directly from the app.

[0977] Specific examples

[0978] When a smartphone user searches for the keyword "sushi in Shibuya Ward," pins are displayed on a map showing restaurants with "sushi," "Shibuya Ward," and "highly rated" based on recent social media posting data. The user can then select a restaurant called "Sushimaru," check out the highly rated reviews and photos, and place an order within the app.

[0979] Prompt Sentence Examples

[0980] When a user types in the app, "Search for highly rated sushi restaurants in Shibuya Ward," the system retrieves the appropriate information from its internal database and displays the results on a map.

[0981] In this way, the present invention is a system that collects and analyzes SNS data in real time and provides users with useful information, allowing them to select restaurants and place orders easily and efficiently.

[0982] Specific examples of hardware and software used

[0983] SNS API (Twitter API, Instagram API)

[0984] Python

[0985] MongoDB

[0986] Google Cloud Vision API

[0987] spaCy, BERT

[0988] geopy, Google Maps API

[0989] Leaflet.js

[0990] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0991] Step 1:

[0992] The server periodically collects posts with a specific hashtag (e.g., "food") using the public API of the social networking site (e.g., Twitter API, Instagram API). The collected data includes images, videos, comments, number of likes, and location information. This data is stored in MongoDB.

[0993] Input: SNS API

[0994] Output: Collected data stored in MongoDB

[0995] Specific operation: The server calls the SNS API, retrieves relevant posts based on the filter conditions, and saves them in the database.

[0996] Step 2:

[0997] The server analyzes the collected images and videos using the Google Cloud Vision API, identifying characteristics such as the type of food and the restaurant's atmosphere.

[0998] Input: Image data stored in MongoDB

[0999] Output: Analyzed features (e.g. "Sushi", "Japanese food", "High-end")

[1000] Specific operation: The server sends the image data to the Google Cloud Vision API and adds the returned feature information to the database.

[1001] Step 3:

[1002] The server uses NLP technology (e.g., spaCy or BERT) to analyze the collected comments, extract user ratings and impressions, and score the trustworthiness and recommendation level based on the number of likes and comments.

[1003] Input: Comment data stored in MongoDB

[1004] Output: Extracted ratings and recommendation scores

[1005] Specific operation: The server inputs the comment data into the NLP model, extracts ratings and opinions as analysis results, calculates the reliability and recommendation level, and stores them in a database.

[1006] Step 4:

[1007] The server uses the geopy library to analyze the location information contained in the post, identify precise geographic information, and further refine the location information by comparing it with other geographic databases (such as the Google Maps API).

[1008] Input: Geolocation data stored in MongoDB

[1009] Output: Precisely identified geographic location

[1010] What it does: The server inputs the location data into the geopy library and checks the returned latitude and longitude information against a geographic database to verify accuracy.

[1011] Step 5:

[1012] The server plots the analyzed information on a map using Leaflet.js and the Google Maps API. Users can view the information on the map through a smartphone or PC application and use search filters to narrow down the restaurants they find based on their preferences.

[1013] Input: Parsed feature and geographic information

[1014] Output: Restaurant information displayed on a map

[1015] Specific operation: The server inputs the analyzed feature information and location information into the map display library and provides it visually to the user.

[1016] Step 6:

[1017] Users input their search keywords and current location, and the server recommends restaurants based on that information. Users can then check the restaurant information and place an order directly through the application if necessary.

[1018] Input: Search keywords and current location information entered by the user

[1019] Output: Recommended restaurant information displayed as search results and order confirmation information

[1020] Specific operation: The user enters search keywords and current location, and the server retrieves and displays the corresponding information from the database and processes the order for the restaurant selected by the user.

[1021] 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.

[1022] The present invention provides a system for collecting and analyzing gourmet information and user emotion information from social networking site posts, and intuitively displaying the information on a map, with the aim of improving user convenience. Specific embodiments of this system are described below.

[1023] Data collection

[1024] The server periodically collects posts with specific hashtags or keywords (e.g., gourmet, restaurant) using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, location information, and sentiment analysis of comments. For example, the server collects posts tagged with "gourmet" and stores them in a database.

[1025] Image and video analysis

[1026] The server analyzes the collected images and videos using AI image recognition technology, which identifies characteristics such as the type of food, the atmosphere of the restaurant, and the price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[1027] Natural Language Processing (NLP)

[1028] The server uses NLP technology to analyze comments on posts and extract user ratings and impressions. It then scores the reliability and recommendation level of the post based on the number of likes and comments. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and a high recommendation level is assigned to posts with over 1,000 likes.

[1029] Emotion analysis using an emotion engine

[1030] The server analyzes the collected comments and their language data using an emotion engine to recognize the user's emotions. For example, it can extract "positive emotions" from a comment like "I love the atmosphere of this store!"

[1031] The server adjusts the recommendation level for food and restaurants based on the user's emotional data, giving a higher recommendation level to posts with positive emotions and a lower recommendation level to posts with negative emotions.

[1032] Adding location information

[1033] Our servers retrieve the location information contained in the post, use the extralocation data to determine the exact address, and verify the accuracy of the location information by cross-checking it with other geolocation databases.

[1034] Data Mapping and Visualization

[1035] The server plots the data on a map based on the information analyzed. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" will display detailed information about the restaurant and any posted images. The information displayed also takes into account the results of sentiment analysis.

[1036] User Interface

[1037] Users can use the application to view and manipulate information on a map. They can use search filters to narrow down their search by their preferred genre (e.g., Japanese, Western, cafe) or price range. The application also provides information on nearby restaurants based on the user's current location. Furthermore, users can select the "sushi" tag to display highly rated sushi restaurants in Shinjuku Ward on the map.

[1038] Updates and Feedback

[1039] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[1040] In this way, this system collects and analyzes gourmet information and user sentiment information from SNS in real time, helping users select dining locations in an intuitive and personalized way.

[1041] The processing flow will be explained below.

[1042] Step 1: Data collection

[1043] The server uses the SNS's public API to collect posts using specific hashtags or keywords (e.g., gourmet, restaurant).

[1044] The server stores the collected post data in a temporary database, including post IDs, image and video URLs, comments, number of likes, and location information.

[1045] Step 2: Image and video analysis

[1046] The server retrieves images and videos from a temporary database and uses an image recognition engine to analyze the type of food and the atmosphere of the restaurant.

[1047] The server extracts characteristics from the analysis results, such as the type of cuisine (e.g., Japanese, Western), the atmosphere of the restaurant (e.g., casual, high-end), and price range.

[1048] Step 3: Natural Language Processing (NLP)

[1049] The server retrieves the collected comments and uses NLP technology to analyze users' ratings and impressions.

[1050] The server scores the collected posts based on the number of likes and comments, assigning them a credibility and recommendation rating.

[1051] Step 4: Emotion analysis using the emotion engine

[1052] The server analyzes the collected comments and their language data using an emotion engine to recognize the user's emotions.

[1053] Based on the results of the emotion analysis, the server assigns a high recommendation level to positive emotions and a low recommendation level to negative emotions.

[1054] Step 5: Adding location information

[1055] The server retrieves the location information contained in the post and identifies the exact address from the extralocation data.

[1056] The server checks the location against other geographic databases to verify its accuracy.

[1057] Step 6: Data mapping and visualization

[1058] The data is plotted on a map based on the information analyzed by the server.

[1059] The server highlights information that interests the user and visually emphasizes it on the map.

[1060] Step 7: User Interface

[1061] The device obtains the user's current location information and displays it on a map.

[1062] The device accepts user operations and narrows down the information according to the filter conditions (e.g., Japanese food, Western food, cafes, etc.).

[1063] The user browses the restaurant information displayed as a search result and obtains detailed information.

[1064] Step 8: Updates and Feedback

[1065] The server periodically collects new data and updates the existing database with the latest information.

[1066] The server receives feedback from users to improve the accuracy and usability of the system.

[1067] Example 2

[1068] 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."

[1069] Conventional systems have difficulty accurately extracting information about food types, restaurant atmospheres, and user ratings when collecting and analyzing gourmet information on social media. Furthermore, the collected information lacks reliability, resulting in a poor user experience. Furthermore, intuitive map displays that take user emotions and ratings into account are lacking, creating a need for a user-friendly system.

[1070] 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.

[1071] In this invention, the server includes means for collecting information about food from posts on the SNS, means for analyzing the type of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing the sentiment of the collected comments using an emotion engine and adjusting the recommendation level based on the sentiment, means for analyzing quoted location information and identifying accurate geographic information, and means for displaying food information based on the analysis on a map. This allows users to intuitively grasp reliable gourmet information and easily find restaurants and dishes that suit their preferences.

[1072] "SNS posts" refer to content such as text, images, and videos that users make public on social networking services.

[1073] "Information about food" refers to food and related information such as the type of food, name, recipe, restaurant name, price, rating, image, video, and location information.

[1074] "Image recognition technology" is a technology that uses computer vision technology to identify objects in images and videos and analyze their features.

[1075] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language, and is a technology that analyzes text data and extracts emotions.

[1076] "User ratings" refers to user opinions and impressions contained in posts on social media, as well as rating scores based on them.

[1077] "Quoted location information" refers to data indicating geographic coordinates or locations contained in posts on social media.

[1078] An "emotion engine" refers to technology that analyzes emotions from text data and recognizes emotional categories such as positive, negative, and neutral.

[1079] "Recommendation level" is an index that indicates the degree to which a particular dish or restaurant is recommended based on analyzed information.

[1080] "Precise geographic information" is information that accurately identifies a specific address or location based on the location information contained in a post.

[1081] "Means for displaying on a map" refers to technology that uses a geographic information system to visualize the analyzed information on a map.

[1082] The present invention provides a system that collects and analyzes gourmet information and user emotion information from social networking site posts and intuitively displays the information on a map. Specific embodiments of this system will be described below.

[1083] Data collection

[1084] The server periodically collects posts containing specific hashtags or keywords (e.g., food, restaurant) using the public API of the social networking site. For example, it retrieves posts using Facebook's Graph API or Twitter's API. The server stores the collected post content, such as images, videos, comments, number of likes, and location information, in a database. The server searches for posts containing the "food" hashtag every hour and adds newly found posts to the database.

[1085] Image and video analysis

[1086] The server uses AI image recognition technologies such as Google Cloud Vision API and Amazon Rekognition to analyze the collected images and videos. This allows it to identify the type of food, the restaurant's atmosphere, price range, and other information. For example, it can detect the presence of sushi in a particular image and store characteristics such as "sushi," "Japanese food," and "high-end" in a database. Specifically, the server sequentially analyzes newly collected images and generates metadata about the type of food and the restaurant's atmosphere.

[1087] Natural Language Processing (NLP)

[1088] The server uses natural language processing technologies such as Google Cloud Natural Language API and OpenAI's GPT-3 to analyze comments on posts and extract user ratings and impressions. It also scores the reliability and recommendation level of posts based on the number of likes and comments. For example, it extracts a "high rating" from a comment like "The sushi at this restaurant was amazing!" and assigns a high recommendation level to posts with over 1,000 likes. Specifically, the server analyzes newly collected comments, calculates a reliability score, and stores it in a database.

[1089] Emotion analysis using an emotion engine

[1090] The server uses emotion engines such as Azure Text Analytics and IBM Watson to perform emotion analysis on the collected comments. This allows it to recognize positive, negative, and neutral emotions from the comments and adjust the recommendation level for a dish or restaurant accordingly. For example, a "positive emotion" is extracted from a comment like "I love the atmosphere of this restaurant!" The server calculates an emotion score for the collected comments and assigns a higher recommendation level to posts with a high percentage of positive emotions.

[1091] Adding location information

[1092] The server uses the location information contained in the post to identify the exact address using the Google Maps API or OpenStreetMap API. It also verifies the accuracy of the location information by comparing it with other geographic information databases. For example, it can identify the address of a specific restaurant from the location information. Specifically, the server sequentially analyzes posts with location information and stores the exact address information in a database.

[1093] Data Mapping and Visualization

[1094] Based on the analyzed information, the server plots the data on a map using Leaflet, Google Maps, etc. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" displays detailed information about the restaurant and any posted images. Specifically, the server displays data that meets the specified criteria as pins on the map, and clicking on the pin displays detailed information.

[1095] User Interface

[1096] Users can use applications (e.g., mobile apps or web apps) to view and manipulate information on a map. Users can use search filters to narrow down their search by their preferred genre and price range. The app also provides information about nearby restaurants based on the user's current location. For example, if a user selects the "sushi" tag, highly rated sushi restaurants in Shinjuku Ward are displayed on a map and detailed information about them is displayed.

[1097] Updates and Feedback

[1098] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[1099] Example prompt sentence:

[1100] Please explain the system that collects and analyzes gourmet information and user sentiment information from social media posts and displays it intuitively on a map.

[1101] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1102] Step 1:

[1103] Data collection

[1104] The server uses the public API of the social networking site to periodically collect posts containing specific hashtags or keywords (e.g., gourmet, restaurant). Specifically, it retrieves posts using Facebook's Graph API or Twitter's API. It receives the specified hashtag or keyword as input and searches for posts containing that hashtag. As output, it stores the content of the collected posts (images, videos, comments, number of likes, location information) in a database. The server searches for posts containing the hashtag "gourmet" every hour and adds new posts to the database.

[1105] Step 2:

[1106] Image and video analysis

[1107] The server analyzes the collected images and videos using AI image recognition technologies such as Google Cloud Vision API and Amazon Rekognition. It receives the collected image and video data as input and stores features such as the type of food, restaurant atmosphere, and price range as output in a database. Specifically, it detects the presence of sushi in a particular image and extracts features such as "sushi," "Japanese food," and "high-end." The server sequentially analyzes newly collected images and generates metadata related to the type of food and restaurant atmosphere.

[1108] Step 3:

[1109] Natural Language Processing (NLP)

[1110] The server uses natural language processing technologies such as Google Cloud Natural Language API and OpenAI's GPT-3 to analyze comments on posts. It receives collected comment data as input and extracts user ratings and impressions as output, calculating reliability scores and recommendation levels and storing them in a database. Specifically, it extracts "high ratings" from comments such as "The sushi at this restaurant was amazing!" and assigns a high recommendation level to posts with over 1,000 likes. The server analyzes the comments and calculates reliability scores.

[1111] Step 4:

[1112] Emotion analysis using an emotion engine

[1113] The server uses emotion engines such as Azure Text Analytics and IBM Watson to analyze the emotions of the collected comments. It receives the collected comment data as input and stores emotion scores such as positive, negative, and neutral as output in a database. For example, it extracts "positive emotion" from the comment "I love the atmosphere of this store!" The server inputs the collected comments into the emotion engine, calculates the emotion score, and assigns a high recommendation rating to posts with a high percentage of positive emotion.

[1114] Step 5:

[1115] Adding location information

[1116] The server analyzes the location information included in the post using the Google Maps API or OpenStreetMap API to identify the exact address. It receives the location information (coordinate data) included in the post as input and stores the specific address in a database as output. For example, it identifies the address of a specific restaurant from the location information. The server analyzes the post with location information and stores the exact address information in a database.

[1117] Step 6:

[1118] Data Mapping and Visualization

[1119] Based on the analyzed information, the server plots the data on a map using Leaflet, Google Maps, or similar. It receives the analyzed food information, user ratings, and sentiment scores as input, and provides visualized data (such as pins) on the map as output. For example, clicking on a pin labeled "Japanese food," "sushi," or "highly rated" displays detailed information about the restaurant and any posted images. The server displays data that meets the specified criteria as pins on the map, and clicking on the pins provides detailed information.

[1120] Step 7:

[1121] User Interface

[1122] Users use an application (mobile or web) to view and manipulate information on a map. The application receives the user's search criteria (e.g., genre, price range, tags) as input, and displays corresponding restaurant and cuisine information on the map as output. For example, if a user selects the tag "sushi," highly rated sushi restaurants in Shinjuku Ward are displayed on the map and detailed information can be viewed. Users can also receive information about nearby restaurants based on their current location.

[1123] Step 8:

[1124] Updates and Feedback

[1125] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. It receives the collected new data and user feedback as input, and provides an updated database and an analysis algorithm with adjusted accuracy as output. For example, if a user reports that "this restaurant information is not accurate," the accuracy of the location information and analysis results is adjusted based on that feedback.

[1126] (Application example 2)

[1127] 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."

[1128] In today's world, people increasingly have opportunities to obtain gourmet information through social media. However, it is not easy to efficiently find reliable information and restaurants and delivery services that suit one's preferences from the vast amount of information available. In particular, the lack of personalized information based on the user's preferences and current location is a challenge. Another issue is the lack of functionality to analyze emotional information and adjust the recommendation level, making it difficult for users to choose a service that will truly satisfy them.

[1129] 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 collecting information about food from posts on SNS, means for analyzing the types of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing quoted location information and identifying accurate geographic information, means for displaying food information based on the analysis on a map, and means for suggesting recommended delivery services based on the user's preferences and location information. This makes it possible to provide reliable, personalized gourmet information that is suitable for the user from a vast amount of information.

[1130] "SNS" is an abbreviation for social networking service, an online platform that allows users to share information and interact with each other via the Internet.

[1131] "Image recognition technology" is a technology in the field of computer vision that identifies and classifies objects and scenes in images and videos.

[1132] "Natural language processing technology" is a technology that enables computers to analyze and understand human language, and is used to analyze and automatically generate text data.

[1133] "Location information" is information for identifying a geographical location, and is mainly expressed in the form of latitude and longitude.

[1134] "Delivery service" refers to a service that delivers food, beverages, and merchandise directly to a location designated by the user.

[1135] "Personalization" refers to providing individually optimized experiences and services based on each user's preferences and behavior.

[1136] "Reliability" refers to the degree to which information or services are relevant, accurate, and consistent and can be relied upon by users.

[1137] "Emotional information" is data that reflects the user's emotions, such as positive, negative, or neutral, and is the analysis result based on that information.

[1138] This system collects information about food from social media posts and suggests optimal delivery services based on the user's preferences and location. This system mainly uses a server to perform the following processes:

[1139] First, the server periodically collects posts with specific hashtags or keywords (e.g., gourmet, delivery) using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, and location information. For example, the server periodically collects posts tagged with "delivery" and stores them in a database.

[1140] The server then analyzes the collected images and videos using AI image recognition technology, identifying characteristics such as the type of food, atmosphere, and price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[1141] The server then uses natural language processing (NLP) to analyze the collected comments and extract user ratings and impressions. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and the reliability and recommendation of the post are scored based on the number of likes and comments.

[1142] The server then uses an emotion engine to analyze the collected comments and their language data to recognize the user's emotions. For example, a "positive emotion" is extracted from a comment like "I love the atmosphere of this restaurant!" The recommendation level for the food or restaurant is adjusted based on this emotional data.

[1143] Additionally, the server captures the location information contained in the post, uses the extralocation data to determine the exact address, and verifies the accuracy of the location information by checking it against other geographic databases.

[1144] The server then uses the analysis results to suggest delivery services that take into account the user's preferences and location. For example, a user can select the tag "sushi" to display nearby highly rated sushi restaurants on a map. The server also suggests the best delivery options based on the user's current location.

[1145] The system runs on servers on AWS (Amazon Web Services) or Google Cloud Platform, with data stored in a PostgreSQL database. It uses TensorFlow or OpenCV for image recognition, Google Cloud Natural Language API for NLP, IBM Watson Tone Analyzer for sentiment analysis, and Google Maps API for accurate location information.

[1146] For example, consider the following prompt:

[1147] "Analyze the following image to identify the type of food and price range: Sushi image"

[1148] "Analyze the following comment with your sentiment engine to determine whether it's positive, negative, or neutral: 'The sushi at this place was amazing!'"

[1149] In this way, the system can provide users with reliable, personalized gourmet information from a vast amount of information.

[1150] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1151] Step 1:

[1152] The server periodically collects posts with specific hashtags or keywords (e.g., gourmet, delivery) using the public API of the social networking site. Here, it sends an API request and analyzes the returned JSON data to extract images, videos, comments, number of likes, location information, etc. The input is the keyword of the API request, and the output is the collected post data.

[1153] Step 2:

[1154] The server analyzes the collected images and videos using AI image recognition technology (e.g., TensorFlow or OpenCV). This identifies features such as the type of cuisine, the atmosphere of the restaurant, and the price range. Specifically, the image data is input into the model, and feature labels (e.g., "sushi," "Japanese cuisine," "high-end") are obtained as output. The input is the images and videos of the posted data, and the output is the analyzed feature information.

[1155] Step 3:

[1156] The server analyzes the collected comments on posts using natural language processing technology (e.g., Google Cloud Natural Language API) to extract user ratings and impressions. Here, text data is sent to the API, and rating information is extracted based on the returned analysis results. The input is the comments on the post data, and the output is the analyzed ratings and impressions.

[1157] Step 4:

[1158] The server analyzes the collected comments and their language data using an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. Specifically, the comment text is input into the emotion engine, and emotion labels such as positive, negative, and neutral are obtained as output. The input is the posted comments, and the output is the analyzed emotion information.

[1159] Step 5:

[1160] The server retrieves the location information contained in the post, identifies the exact address from the extrapolation data, and verifies the accuracy of the location information by checking it against other geographic information databases (e.g., Google Maps API). The input is the location information of the post data, and the output is the confirmed exact address information.

[1161] Step 6:

[1162] The server then proposes delivery services based on the analysis results, taking into account the user's preferences and location information. Specifically, it runs an algorithm that recommends optimal delivery options based on the user's current location and preferences. The input is the user's current location and preference data, and the output is the proposed delivery service information.

[1163] Step 7:

[1164] Users can check suggested delivery services and restaurant information on a map through their device. Users can manipulate the information on the map to view detailed information and posted images. The input is the suggested delivery service information, and the output is the map information and detailed data that the user can view.

[1165] In this way, the system performs individual processing at each step, providing delivery services and gourmet information that are suited to the user.

[1166] 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.

[1167] 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.

[1168] 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.

[1169] [Fourth embodiment]

[1170] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1171] 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.

[1172] 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).

[1173] 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.

[1174] 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.

[1175] 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).

[1176] 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. 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.

[1177] 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.

[1178] 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.

[1179] 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.

[1180] 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.

[1181] 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.

[1182] 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."

[1183] The present invention provides a system for collecting and analyzing gourmet information from social networking site posts and displaying it intuitively on a map, with the aim of improving user convenience. Specific embodiments of this system will be described below.

[1184] Data collection

[1185] The server periodically collects food-related posts using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, location information, etc. For example, the server collects posts tagged with "food" and stores them in a database.

[1186] Image and video analysis

[1187] The server analyzes the collected images and videos using AI image recognition technology, which identifies characteristics such as the type of food, the atmosphere of the restaurant, and the price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[1188] Natural Language Processing (NLP)

[1189] The server uses NLP technology to analyze comments on posts and extract user ratings and impressions. It then scores the reliability and recommendation level of the post based on the number of likes and comments. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and a high recommendation level is assigned to posts with over 1,000 likes.

[1190] Adding location information

[1191] The server analyzes the location information in the post to determine its precise geographic location, using image metadata and any explicit location information provided by the poster, and cross-references it with other geographic databases.

[1192] Data Mapping and Visualization

[1193] The server plots the analyzed information on a map and provides it visually to the user. When a user accesses the application, restaurants are displayed on the map as pins, and clicking on them displays detailed information. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" displays detailed information about the restaurant and any posted images.

[1194] User Interface

[1195] Users can use the application to view and manipulate information on a map. They can use search filters to narrow down their search by their preferred genre (e.g., Japanese, Western, cafe) or price range. The application also provides information on nearby restaurants based on the user's current location. Users can also select the "sushi" tag to display highly rated sushi restaurants in Shinjuku Ward on the map.

[1196] Updates and Feedback

[1197] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[1198] In this way, this system collects and analyzes gourmet information from social media in real time, helping users choose dining locations in an intuitive and personalized way.

[1199] The processing flow will be explained below.

[1200] Step 1: Data collection

[1201] The server uses the SNS's public API to collect posts using specific hashtags or keywords (e.g., gourmet, restaurant).

[1202] The server stores the collected post data in a temporary database, including post IDs, image and video URLs, comments, number of likes, and location information.

[1203] Step 2: Image and video analysis

[1204] The server retrieves images and videos from a temporary database and uses an image recognition engine to analyze the type of food and the atmosphere of the restaurant.

[1205] The server extracts characteristics from the analysis results, such as the type of cuisine (e.g., Japanese, Western), the atmosphere of the restaurant (e.g., casual, high-end), and price range.

[1206] Step 3: Natural Language Processing (NLP)

[1207] The server retrieves the collected comments and uses NLP technology to analyze users' ratings and impressions.

[1208] The server scores the collected posts based on the number of likes and comments, assigning them a credibility and recommendation rating.

[1209] Step 4: Adding location information

[1210] The server retrieves the location information contained in the post and identifies the exact address from the extralocation data.

[1211] The server checks the location against other geographic databases to verify its accuracy.

[1212] Step 5: Data mapping and visualization

[1213] The data is plotted on a map based on the information analyzed by the server.

[1214] The server highlights information that interests the user and visually emphasizes it on the map.

[1215] Step 6: User Interface

[1216] The device obtains the user's current location information and displays it on a map.

[1217] The device accepts user operations and narrows down the information according to the filter conditions (e.g., Japanese food, Western food, cafes, etc.).

[1218] The user browses the restaurant information displayed as a search result and obtains detailed information.

[1219] Step 7: Updates and Feedback

[1220] The server periodically collects new data and updates the existing database with the latest information.

[1221] The server receives feedback from users to improve the accuracy and usability of the system.

[1222] Example 1

[1223] 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."

[1224] Conventional gourmet information systems were unreliable and it was difficult to obtain specific ratings and detailed information. Furthermore, it was time-consuming to manually collect and analyze information from individual posts, making it difficult to provide information intuitively to users. Furthermore, information was not updated in real time, making it difficult to reflect user feedback.

[1225] 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.

[1226] In this invention, the server includes means for collecting information about meals from posts on the SNS, means for analyzing the type of meal and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing location information from the collected information and identifying accurate geographic information, means for displaying the meal information based on the analysis on a map, means for users to check and manipulate the information on the map using an application, means for periodically collecting new data and updating the database, and means for collecting user feedback and improving the accuracy and usability of the analysis algorithm. This allows users to obtain reliable, detailed gourmet information in real time and intuitively check it on a map.

[1227] "SNS" is an abbreviation for social networking service, an online platform for people to share information and interact over the Internet.

[1228] A "server" refers to a computer system that accepts requests from clients over a network and provides data and services.

[1229] "Meal" refers to any food or drink consumed, including the act of consuming food.

[1230] "Information" refers to facts, data, knowledge, etc. about a subject, and is expressed through language, numbers, images, sounds, etc.

[1231] "Image recognition technology" is a technology that allows computers to identify and analyze objects and patterns contained in images and photographs.

[1232] "Natural language processing technology" is a technology that enables computers to understand and generate human language, and includes applications such as text analysis, translation, and dialogue systems.

[1233] A "database" is a collection of structured data, and is a system designed to enable efficient searching, adding, updating, and deleting.

[1234] "Location information" refers to geographical information about a specific point or place, and is represented by data such as latitude, longitude, and address.

[1235] A "map" is a visual representation of a particular portion of geographic space, depicting roads, buildings, natural features, etc.

[1236] "Feedback" refers to opinions and reactions provided by users regarding a system or service, which are used for improvement and adjustment.

[1237] An "analytical algorithm" is a computational procedure or method for analyzing data and finding patterns or regularities in it.

[1238] "Usability" refers to the ease of use and operation of a system or product, and is the characteristic that enables users to achieve their goals efficiently.

[1239] This invention is a system that collects and analyzes gourmet information from social networking sites and intuitively displays it on a map to improve user convenience. This system collects information about food from posts on social networking sites, analyzes it using image recognition technology and natural language processing technology, and plots geographical information based on the results to provide to users.

[1240] Hardware and software used

[1241] Hardware: Servers, user terminals

[1242] Software: Public APIs for social networking sites, image recognition technology (e.g., Google Cloud Vision API), natural language processing technology (e.g., spaCy, GPT-4), map display libraries (e.g., Leaflet.js), databases (e.g., MySQL)

[1243] Specific explanation of the process

[1244] 1. Data Collection

[1245] The server uses the public API of the SNS to collect posts with a specific hashtag (e.g., "gourmet"). For example, the server uses the Twitter API to periodically retrieve posts tagged with "gourmet" every day at 3:00 PM and store them in a database in JSON format.

[1246] 2. Image and video analysis

[1247] The server applies image recognition technology to the collected image data. For example, it uses the Google Cloud Vision API to extract features such as "sushi," "Japanese food," and "luxury" from the image, organizes them, and stores them in a database.

[1248] 3. Natural Language Processing (NLP)

[1249] The server analyzes the comments in the post using natural language processing technology. For example, it uses GPT-4 to extract "likes" from a comment like "The sushi at this restaurant was amazing!", and then scores the reliability of the comment based on the number of likes and comments, and stores the results in a database.

[1250] 4. Adding location information

[1251] The server analyzes the location information attached to the post and converts it into accurate geographic information. Specifically, it compares the metadata and explicit location information in the post with the Google Maps API and registers the coordinates in a database.

[1252] 5. Data Mapping and Visualization

[1253] The server plots the analysis results on a map and displays them in a format that is easy for users to understand. For example, Leaflet.js is used to display the analyzed information as pins on a map, and an interface is provided that allows users to click on the pins to view detailed information.

[1254] 6. User Interface

[1255] Users can use the application to search and manipulate information on a map. For example, if a user enters filter criteria such as "sushi" or "Shinjuku Ward," pins for restaurants that match the criteria will appear on the map.

[1256] 7. Updates and Feedback

[1257] The server periodically collects new data and updates the database with the latest information. It also collects user feedback and updates the analysis algorithm to improve the system's accuracy and usability. For example, if a user reports that "this restaurant information is not accurate," the system uses that feedback to improve the accuracy of location information and analysis results.

[1258] Examples of specific examples and prompts

[1259] Specific examples

[1260] The server uses the Twitter API to automatically collect posts tagged with "gourmet."

[1261] Image data is analyzed using the Google Cloud Vision API and feature tags are generated.

[1262] GPT-4 analyzes comments and calculates a rating score.

[1263] Use the Google Maps API to check geographic information.

[1264] The analysis results are plotted on a map using Leaflet.js, providing a visual presentation to the user.

[1265] Users can use search filters in the application to display information on the map that matches specific criteria.

[1266] The server updates the data based on user feedback to improve the accuracy of the system.

[1267] Prompt Sentence Examples

[1268] "Please explain in detail the process of the system that collects gourmet information from social media posts, analyzes ratings and characteristics, and displays them on a map."

[1269] "Please give me an example of how image recognition technology can be used to extract the type and characteristics of food."

[1270] "Please explain how you would improve the system based on user feedback."

[1271] In this way, this system collects and analyzes gourmet information from social media in real time, helping users choose dining locations in an intuitive and personalized way.

[1272] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1273] Step 1:

[1274] Data collection

[1275] The server uses the SNS's public API to collect posts with the "gourmet" hashtag.

[1276] Input: A social networking site's public API and the hashtag "gourmet."

[1277] What it does: It periodically sends API requests and receives the posted data in response.

[1278] Output: Social media post data (images, videos, comments, likes, location information, etc.).

[1279] Step 2:

[1280] Data Storage

[1281] The server stores the collected post data in a database.

[1282] Input: Post data collected from social media.

[1283] What it does: Organizes submitted data by field and stores it in a database.

[1284] Output: Organized submission data in a database.

[1285] Step 3:

[1286] Image and video analysis

[1287] The server uses the Google Cloud Vision API to analyze the collected image data.

[1288] Input: Image data retrieved from a database.

[1289] How it works: Image data is sent to the Google Cloud Vision API, and the returned analysis results (e.g., characteristics such as "sushi," "Japanese food," and "luxury") are organized.

[1290] Output: Image data with extracted features.

[1291] Step 4:

[1292] Natural Language Processing (NLP)

[1293] The server analyzes the comment portion using natural language processing technology (e.g., spaCy, GPT-4).

[1294] Input: Comment data retrieved from the database.

[1295] How it works: Comment data is input into a natural language processing model, and the returned ratings and recommendation data is organized.

[1296] Output: Comment data with numerical ratings and recommendation levels.

[1297] Step 5:

[1298] Like and comment scoring

[1299] The server scores the credibility and recommendation of posts based on the number of likes and comments.

[1300] Input: Number of likes and comments retrieved from the database.

[1301] How it works: The acquired data is fed into an algorithm to calculate trustworthiness and recommendation score.

[1302] Output: Confidence and recommendation scores.

[1303] Step 6:

[1304] Adding location information

[1305] The server analyzes the location information contained in the collected posts and identifies precise geographic information.

[1306] Input: Post metadata and explicit location information.

[1307] What it does: Sends location information to the Google Maps API and organizes the coordinate data returned.

[1308] Output: Accurate geographic information.

[1309] Step 7:

[1310] Data Mapping and Visualization

[1311] The server plots the analyzed information on a map and provides it visually to the user.

[1312] Input: Analysis results stored in a database.

[1313] How it works: Using a map display library (e.g. Leaflet.js), the analysis results are displayed as pins on a map, and clicking on the pins displays more information.

[1314] Output: Map view with pins.

[1315] Step 8:

[1316] User Interface

[1317] Users use the application to search and manipulate information on the map.

[1318] Input: User's search filter criteria (e.g. cuisine type, price range, region, etc.).

[1319] How it works: Searches a database based on user input and displays information that matches the criteria on a map.

[1320] Output: Map display of restaurant information that matches the conditions.

[1321] Step 9:

[1322] Updates and Feedback

[1323] The server periodically collects new data and updates the database.

[1324] Input: Newly collected social media posting data and user feedback.

[1325] What it does: Adds new submissions to the database and improves the analysis algorithm based on feedback.

[1326] Output: Updated database and improved algorithms.

[1327] In this way, this system can collect and analyze gourmet information from SNS posts in real time, and provide users with intuitive and detailed information.

[1328] (Application example 1)

[1329] 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."

[1330] Conventional food delivery systems have the problem that it takes a huge amount of time and effort for users to find a restaurant that suits their preferences. Furthermore, there are not enough methods to utilize gourmet information on social media, and real-time updated rating information cannot be effectively utilized. Furthermore, users have to move between different platforms, which is inconvenient. There is a need for a system that can solve these issues and improve user convenience.

[1331] 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.

[1332] In this invention, the server includes means for collecting information about food from posts on the SNS, means for analyzing the type of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing the quoted location information and identifying accurate geographic information, means for displaying food information based on the analysis on a map, means for introducing restaurants recommended from the analyzed information based on keywords searched by the user and the user's current location, and means for directly ordering from the selected restaurant. This enables users to quickly find their favorite restaurant and easily order from it based on reliable gourmet information collected in real time from SNS posts.

[1333] "SNS posts" refers to information such as comments, images, and videos that users make public on social networking services.

[1334] "Food information" refers to data about the type of food and drink, its characteristics, price range, and the environment in which it is served.

[1335] "Image recognition technology" is a technology that extracts specific features and patterns from image data and performs identification and classification.

[1336] "Natural language processing technology" is a technology that mechanically analyzes, understands, and generates human language.

[1337] "Location Information" refers to geographic data including the latitude and longitude of a specific point.

[1338] "Map display" refers to a map for visually presenting geographic information.

[1339] "Search keywords" refer to words or phrases that users enter to retrieve content of interest.

[1340] "Current location" refers to geographic information about the user's current location.

[1341] "Restaurant" refers to a commercial establishment that serves food and beverages.

[1342] "Order" refers to the act of a User making a request to purchase a product or service.

[1343] "Credibility" refers to the property of indicating the accuracy and reliability of information.

[1344] System Overview

[1345] This invention is a food delivery system that collects and analyzes food information from social media posts, intuitively displays it on a map, and enables users to efficiently find their favorite restaurants and place orders directly with those restaurants. This system consists of social media data collection, image recognition, natural language processing, location information analysis, map display, search engine, and ordering functions.

[1346] Used technologies and data processing

[1347] 1. Data Collection

[1348] The system uses the public API of social media platforms to collect posts with specific hashtags (e.g., "food"). The specific software used is Python and social media APIs (e.g., Twitter API, Instagram API). The collected data is stored in MongoDB.

[1349] 2. Image and video analysis

[1350] The server analyzes the collected images and videos using AI image recognition technology such as Google Cloud Vision API. During the analysis process, characteristics such as the type of food and the atmosphere of the restaurant are identified. For example, from an image of sushi, characteristics such as "sushi," "Japanese food," and "high-end" are extracted.

[1351] 3. Natural Language Processing

[1352] Comments on posts are analyzed using NLP technology (e.g., spaCy and BERT). This extracts user ratings and impressions, and then scores the reliability and recommendation level based on the number of likes and comments. For example, a "high rating" is automatically extracted from a comment such as "The sushi at this restaurant was amazing!", and the recommendation level increases if there are multiple likes.

[1353] 4. Adding location information

[1354] Analyze the location information contained in SNS posts to identify accurate geographic information. Use geographic information services such as Geopy to analyze the location information. Based on the location information contained in the post, match it with other geographic databases (such as Google Maps API).

[1355] 5. Data Mapping and Visualization

[1356] The analyzed information is plotted on a map using map display libraries such as Leaflet.js and Google Maps API, and users can use search filters to narrow down their search by their preferred genre or price range.

[1357] 6. Order function

[1358] Based on the user's search keywords and current location, the app analyzes information and recommends restaurants, which are then displayed on a map. Users can easily check restaurant information and place orders directly from the app.

[1359] Specific examples

[1360] When a smartphone user searches for the keyword "sushi in Shibuya Ward," pins are displayed on a map showing restaurants with "sushi," "Shibuya Ward," and "highly rated" based on recent social media posting data. The user can then select a restaurant called "Sushimaru," check out the highly rated reviews and photos, and place an order within the app.

[1361] Prompt Sentence Examples

[1362] When a user types in the app, "Search for highly rated sushi restaurants in Shibuya Ward," the system retrieves the appropriate information from its internal database and displays the results on a map.

[1363] In this way, the present invention is a system that collects and analyzes SNS data in real time and provides users with useful information, allowing them to select restaurants and place orders easily and efficiently.

[1364] Specific examples of hardware and software used

[1365] SNS API (Twitter API, Instagram API)

[1366] Python

[1367] MongoDB

[1368] Google Cloud Vision API

[1369] spaCy, BERT

[1370] geopy, Google Maps API

[1371] Leaflet.js

[1372] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1373] Step 1:

[1374] The server periodically collects posts with a specific hashtag (e.g., "food") using the public API of the social networking site (e.g., Twitter API, Instagram API). The collected data includes images, videos, comments, number of likes, and location information. This data is stored in MongoDB.

[1375] Input: SNS API

[1376] Output: Collected data stored in MongoDB

[1377] Specific operation: The server calls the SNS API, retrieves relevant posts based on the filter conditions, and saves them in the database.

[1378] Step 2:

[1379] The server analyzes the collected images and videos using the Google Cloud Vision API, identifying characteristics such as the type of food and the restaurant's atmosphere.

[1380] Input: Image data stored in MongoDB

[1381] Output: Analyzed features (e.g. "Sushi", "Japanese food", "High-end")

[1382] Specific operation: The server sends the image data to the Google Cloud Vision API and adds the returned feature information to the database.

[1383] Step 3:

[1384] The server uses NLP technology (e.g., spaCy or BERT) to analyze the collected comments, extract user ratings and impressions, and score the trustworthiness and recommendation level based on the number of likes and comments.

[1385] Input: Comment data stored in MongoDB

[1386] Output: Extracted ratings and recommendation scores

[1387] Specific operation: The server inputs the comment data into the NLP model, extracts ratings and opinions as analysis results, calculates the reliability and recommendation level, and stores them in a database.

[1388] Step 4:

[1389] The server uses the geopy library to analyze the location information contained in the post, identify precise geographic information, and further refine the location information by comparing it with other geographic databases (such as the Google Maps API).

[1390] Input: Geolocation data stored in MongoDB

[1391] Output: Precisely identified geographic location

[1392] What it does: The server inputs the location data into the geopy library and checks the returned latitude and longitude information against a geographic database to verify accuracy.

[1393] Step 5:

[1394] The server plots the analyzed information on a map using Leaflet.js and the Google Maps API. Users can view the information on the map through a smartphone or PC application and use search filters to narrow down the restaurants they find based on their preferences.

[1395] Input: Parsed feature and geographic information

[1396] Output: Restaurant information displayed on a map

[1397] Specific operation: The server inputs the analyzed feature information and location information into the map display library and provides it visually to the user.

[1398] Step 6:

[1399] Users input their search keywords and current location, and the server recommends restaurants based on that information. Users can then check the restaurant information and place an order directly through the application if necessary.

[1400] Input: Search keywords and current location information entered by the user

[1401] Output: Recommended restaurant information displayed as search results and order confirmation information

[1402] Specific operation: The user enters search keywords and current location, and the server retrieves and displays the corresponding information from the database and processes the order for the restaurant selected by the user.

[1403] 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.

[1404] The present invention provides a system for collecting and analyzing gourmet information and user emotion information from social networking site posts, and intuitively displaying the information on a map, with the aim of improving user convenience. Specific embodiments of this system are described below.

[1405] Data collection

[1406] The server periodically collects posts with specific hashtags or keywords (e.g., gourmet, restaurant) using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, location information, and sentiment analysis of comments. For example, the server collects posts tagged with "gourmet" and stores them in a database.

[1407] Image and video analysis

[1408] The server analyzes the collected images and videos using AI image recognition technology, which identifies characteristics such as the type of food, the atmosphere of the restaurant, and the price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[1409] Natural Language Processing (NLP)

[1410] The server uses NLP technology to analyze comments on posts and extract user ratings and impressions. It then scores the reliability and recommendation level of the post based on the number of likes and comments. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and a high recommendation level is assigned to posts with over 1,000 likes.

[1411] Emotion analysis using an emotion engine

[1412] The server analyzes the collected comments and their language data using an emotion engine to recognize the user's emotions. For example, it can extract "positive emotions" from a comment like "I love the atmosphere of this store!"

[1413] The server adjusts the recommendation level for food and restaurants based on the user's emotional data, giving a higher recommendation level to posts with positive emotions and a lower recommendation level to posts with negative emotions.

[1414] Adding location information

[1415] Our servers retrieve the location information contained in the post, use the extralocation data to determine the exact address, and verify the accuracy of the location information by cross-checking it with other geolocation databases.

[1416] Data Mapping and Visualization

[1417] The server plots the data on a map based on the information analyzed. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" will display detailed information about the restaurant and any posted images. The information displayed also takes into account the results of sentiment analysis.

[1418] User Interface

[1419] Users can use the application to view and manipulate information on a map. They can use search filters to narrow down their search by their preferred genre (e.g., Japanese, Western, cafe) or price range. The application also provides information on nearby restaurants based on the user's current location. Furthermore, users can select the "sushi" tag to display highly rated sushi restaurants in Shinjuku Ward on the map.

[1420] Updates and Feedback

[1421] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[1422] In this way, this system collects and analyzes gourmet information and user sentiment information from SNS in real time, helping users select dining locations in an intuitive and personalized way.

[1423] The processing flow will be explained below.

[1424] Step 1: Data collection

[1425] The server uses the SNS's public API to collect posts using specific hashtags or keywords (e.g., gourmet, restaurant).

[1426] The server stores the collected post data in a temporary database, including post IDs, image and video URLs, comments, number of likes, and location information.

[1427] Step 2: Image and video analysis

[1428] The server retrieves images and videos from a temporary database and uses an image recognition engine to analyze the type of food and the atmosphere of the restaurant.

[1429] The server extracts characteristics from the analysis results, such as the type of cuisine (e.g., Japanese, Western), the atmosphere of the restaurant (e.g., casual, high-end), and price range.

[1430] Step 3: Natural Language Processing (NLP)

[1431] The server retrieves the collected comments and uses NLP technology to analyze users' ratings and impressions.

[1432] The server scores the collected posts based on the number of likes and comments, assigning them a credibility and recommendation rating.

[1433] Step 4: Emotion analysis using the emotion engine

[1434] The server analyzes the collected comments and their language data using an emotion engine to recognize the user's emotions.

[1435] Based on the results of the emotion analysis, the server assigns a high recommendation level to positive emotions and a low recommendation level to negative emotions.

[1436] Step 5: Adding location information

[1437] The server retrieves the location information contained in the post and identifies the exact address from the extralocation data.

[1438] The server checks the location against other geographic databases to verify its accuracy.

[1439] Step 6: Data mapping and visualization

[1440] The data is plotted on a map based on the information analyzed by the server.

[1441] The server highlights information that interests the user and visually emphasizes it on the map.

[1442] Step 7: User Interface

[1443] The device obtains the user's current location information and displays it on a map.

[1444] The device accepts user operations and narrows down the information according to the filter conditions (e.g., Japanese food, Western food, cafes, etc.).

[1445] The user browses the restaurant information displayed as a search result and obtains detailed information.

[1446] Step 8: Updates and Feedback

[1447] The server periodically collects new data and updates the existing database with the latest information.

[1448] The server receives feedback from users to improve the accuracy and usability of the system.

[1449] Example 2

[1450] 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."

[1451] Conventional systems have difficulty accurately extracting information about food types, restaurant atmospheres, and user ratings when collecting and analyzing gourmet information on social media. Furthermore, the collected information lacks reliability, resulting in a poor user experience. Furthermore, intuitive map displays that take user emotions and ratings into account are lacking, creating a need for a user-friendly system.

[1452] 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.

[1453] In this invention, the server includes means for collecting information about food from posts on the SNS, means for analyzing the type of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing the sentiment of the collected comments using an emotion engine and adjusting the recommendation level based on the sentiment, means for analyzing quoted location information and identifying accurate geographic information, and means for displaying food information based on the analysis on a map. This allows users to intuitively grasp reliable gourmet information and easily find restaurants and dishes that suit their preferences.

[1454] "SNS posts" refer to content such as text, images, and videos that users make public on social networking services.

[1455] "Information about food" refers to food and related information such as the type of food, name, recipe, restaurant name, price, rating, image, video, and location information.

[1456] "Image recognition technology" is a technology that uses computer vision technology to identify objects in images and videos and analyze their features.

[1457] "Natural language processing technology" is a technology that allows computers to understand, interpret, and generate human language, and is a technology that analyzes text data and extracts emotions.

[1458] "User ratings" refers to user opinions and impressions contained in posts on social media, as well as rating scores based on them.

[1459] "Quoted location information" refers to data indicating geographic coordinates or locations contained in posts on social media.

[1460] An "emotion engine" refers to technology that analyzes emotions from text data and recognizes emotional categories such as positive, negative, and neutral.

[1461] "Recommendation level" is an index that indicates the degree to which a particular dish or restaurant is recommended based on analyzed information.

[1462] "Precise geographic information" is information that accurately identifies a specific address or location based on the location information contained in a post.

[1463] "Means for displaying on a map" refers to technology that uses a geographic information system to visualize the analyzed information on a map.

[1464] The present invention provides a system that collects and analyzes gourmet information and user emotion information from social networking site posts and intuitively displays the information on a map. Specific embodiments of this system will be described below.

[1465] Data collection

[1466] The server periodically collects posts containing specific hashtags or keywords (e.g., food, restaurant) using the public API of the social networking site. For example, it retrieves posts using Facebook's Graph API or Twitter's API. The server stores the collected post content, such as images, videos, comments, number of likes, and location information, in a database. The server searches for posts containing the "food" hashtag every hour and adds newly found posts to the database.

[1467] Image and video analysis

[1468] The server uses AI image recognition technologies such as Google Cloud Vision API and Amazon Rekognition to analyze the collected images and videos. This allows it to identify the type of food, the restaurant's atmosphere, price range, and other information. For example, it can detect the presence of sushi in a particular image and store characteristics such as "sushi," "Japanese food," and "high-end" in a database. Specifically, the server sequentially analyzes newly collected images and generates metadata about the type of food and the restaurant's atmosphere.

[1469] Natural Language Processing (NLP)

[1470] The server uses natural language processing technologies such as Google Cloud Natural Language API and OpenAI's GPT-3 to analyze comments on posts and extract user ratings and impressions. It also scores the reliability and recommendation level of posts based on the number of likes and comments. For example, it extracts a "high rating" from a comment like "The sushi at this restaurant was amazing!" and assigns a high recommendation level to posts with over 1,000 likes. Specifically, the server analyzes newly collected comments, calculates a reliability score, and stores it in a database.

[1471] Emotion analysis using an emotion engine

[1472] The server uses emotion engines such as Azure Text Analytics and IBM Watson to perform emotion analysis on the collected comments. This allows it to recognize positive, negative, and neutral emotions from the comments and adjust the recommendation level for a dish or restaurant accordingly. For example, a "positive emotion" is extracted from a comment like "I love the atmosphere of this restaurant!" The server calculates an emotion score for the collected comments and assigns a higher recommendation level to posts with a high percentage of positive emotions.

[1473] Adding location information

[1474] The server uses the location information contained in the post to identify the exact address using the Google Maps API or OpenStreetMap API. It also verifies the accuracy of the location information by comparing it with other geographic information databases. For example, it can identify the address of a specific restaurant from the location information. Specifically, the server sequentially analyzes posts with location information and stores the exact address information in a database.

[1475] Data Mapping and Visualization

[1476] Based on the analyzed information, the server plots the data on a map using Leaflet, Google Maps, etc. For example, clicking on a pin labeled "Japanese cuisine," "Sushi," or "Highly rated" displays detailed information about the restaurant and any posted images. Specifically, the server displays data that meets the specified criteria as pins on the map, and clicking on the pin displays detailed information.

[1477] User Interface

[1478] Users can use applications (e.g., mobile apps or web apps) to view and manipulate information on a map. Users can use search filters to narrow down their search by their preferred genre and price range. The app also provides information about nearby restaurants based on the user's current location. For example, if a user selects the "sushi" tag, highly rated sushi restaurants in Shinjuku Ward are displayed on a map and detailed information about them is displayed.

[1479] Updates and Feedback

[1480] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. For example, if a user reports that the restaurant information is inaccurate, the server uses that feedback to adjust the accuracy of the location information and analysis results.

[1481] Example prompt sentence:

[1482] Please explain the system that collects and analyzes gourmet information and user sentiment information from social media posts and displays it intuitively on a map.

[1483] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1484] Step 1:

[1485] Data collection

[1486] The server uses the public API of the social networking site to periodically collect posts containing specific hashtags or keywords (e.g., gourmet, restaurant). Specifically, it retrieves posts using Facebook's Graph API or Twitter's API. It receives the specified hashtag or keyword as input and searches for posts containing that hashtag. As output, it stores the content of the collected posts (images, videos, comments, number of likes, location information) in a database. The server searches for posts containing the hashtag "gourmet" every hour and adds new posts to the database.

[1487] Step 2:

[1488] Image and video analysis

[1489] The server analyzes the collected images and videos using AI image recognition technologies such as Google Cloud Vision API and Amazon Rekognition. It receives the collected image and video data as input and stores features such as the type of food, restaurant atmosphere, and price range as output in a database. Specifically, it detects the presence of sushi in a particular image and extracts features such as "sushi," "Japanese food," and "high-end." The server sequentially analyzes newly collected images and generates metadata related to the type of food and restaurant atmosphere.

[1490] Step 3:

[1491] Natural Language Processing (NLP)

[1492] The server uses natural language processing technologies such as Google Cloud Natural Language API and OpenAI's GPT-3 to analyze comments on posts. It receives collected comment data as input and extracts user ratings and impressions as output, calculating reliability scores and recommendation levels and storing them in a database. Specifically, it extracts "high ratings" from comments such as "The sushi at this restaurant was amazing!" and assigns a high recommendation level to posts with over 1,000 likes. The server analyzes the comments and calculates reliability scores.

[1493] Step 4:

[1494] Emotion analysis using an emotion engine

[1495] The server uses emotion engines such as Azure Text Analytics and IBM Watson to analyze the emotions of the collected comments. It receives the collected comment data as input and stores emotion scores such as positive, negative, and neutral as output in a database. For example, it extracts "positive emotion" from the comment "I love the atmosphere of this store!" The server inputs the collected comments into the emotion engine, calculates the emotion score, and assigns a high recommendation rating to posts with a high percentage of positive emotion.

[1496] Step 5:

[1497] Adding location information

[1498] The server analyzes the location information included in the post using the Google Maps API or OpenStreetMap API to identify the exact address. It receives the location information (coordinate data) included in the post as input and stores the specific address in a database as output. For example, it identifies the address of a specific restaurant from the location information. The server analyzes the post with location information and stores the exact address information in a database.

[1499] Step 6:

[1500] Data Mapping and Visualization

[1501] Based on the analyzed information, the server plots the data on a map using Leaflet, Google Maps, or similar. It receives the analyzed food information, user ratings, and sentiment scores as input, and provides visualized data (such as pins) on the map as output. For example, clicking on a pin labeled "Japanese food," "sushi," or "highly rated" displays detailed information about the restaurant and any posted images. The server displays data that meets the specified criteria as pins on the map, and clicking on the pins provides detailed information.

[1502] Step 7:

[1503] User Interface

[1504] Users use an application (mobile or web) to view and manipulate information on a map. The application receives the user's search criteria (e.g., genre, price range, tags) as input, and displays corresponding restaurant and cuisine information on the map as output. For example, if a user selects the tag "sushi," highly rated sushi restaurants in Shinjuku Ward are displayed on the map and detailed information can be viewed. Users can also receive information about nearby restaurants based on their current location.

[1505] Step 8:

[1506] Updates and Feedback

[1507] The server periodically collects new data and updates the existing database with the latest information. It also collects user feedback to improve the accuracy and usability of the analysis algorithm. It receives the collected new data and user feedback as input, and provides an updated database and an analysis algorithm with adjusted accuracy as output. For example, if a user reports that "this restaurant information is not accurate," the accuracy of the location information and analysis results is adjusted based on that feedback.

[1508] (Application example 2)

[1509] 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."

[1510] In today's world, people increasingly have opportunities to obtain gourmet information through social media. However, it is not easy to efficiently find reliable information and restaurants and delivery services that suit one's preferences from the vast amount of information available. In particular, the lack of personalized information based on the user's preferences and current location is a challenge. Another issue is the lack of functionality to analyze emotional information and adjust the recommendation level, making it difficult for users to choose a service that will truly satisfy them.

[1511] 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 collecting information about food from posts on SNS, means for analyzing the types of food and the atmosphere of the restaurant from the collected information using image recognition technology, means for analyzing the content of the posts from the collected information using natural language processing technology and extracting user ratings, means for analyzing quoted location information and identifying accurate geographic information, means for displaying food information based on the analysis on a map, and means for suggesting recommended delivery services based on the user's preferences and location information. This makes it possible to provide reliable, personalized gourmet information that is suitable for the user from a vast amount of information.

[1512] "SNS" is an abbreviation for social networking service, an online platform that allows users to share information and interact with each other via the Internet.

[1513] "Image recognition technology" is a technology in the field of computer vision that identifies and classifies objects and scenes in images and videos.

[1514] "Natural language processing technology" is a technology that enables computers to analyze and understand human language, and is used to analyze and automatically generate text data.

[1515] "Location information" is information for identifying a geographical location, and is mainly expressed in the form of latitude and longitude.

[1516] "Delivery service" refers to a service that delivers food, beverages, and merchandise directly to a location designated by the user.

[1517] "Personalization" refers to providing individually optimized experiences and services based on each user's preferences and behavior.

[1518] "Reliability" refers to the degree to which information or services are relevant, accurate, and consistent and can be relied upon by users.

[1519] "Emotional information" is data that reflects the user's emotions, such as positive, negative, or neutral, and is the analysis result based on that information.

[1520] This system collects information about food from social media posts and suggests optimal delivery services based on the user's preferences and location. This system mainly uses a server to perform the following processes:

[1521] First, the server periodically collects posts with specific hashtags or keywords (e.g., gourmet, delivery) using the public API of the social networking site. The collected information includes images, videos, comments, number of likes, and location information. For example, the server periodically collects posts tagged with "delivery" and stores them in a database.

[1522] The server then analyzes the collected images and videos using AI image recognition technology, identifying characteristics such as the type of food, atmosphere, and price range. For example, from an image of sushi included in a collected post, characteristics such as "sushi," "Japanese food," and "high-end" can be extracted.

[1523] The server then uses natural language processing (NLP) to analyze the collected comments and extract user ratings and impressions. For example, a "high rating" is extracted from a comment like "The sushi at this restaurant was amazing!", and the reliability and recommendation of the post are scored based on the number of likes and comments.

[1524] The server then uses an emotion engine to analyze the collected comments and their language data to recognize the user's emotions. For example, a "positive emotion" is extracted from a comment like "I love the atmosphere of this restaurant!" The recommendation level for the food or restaurant is adjusted based on this emotional data.

[1525] Additionally, the server captures the location information contained in the post, uses the extralocation data to determine the exact address, and verifies the accuracy of the location information by checking it against other geographic databases.

[1526] The server then uses the analysis results to suggest delivery services that take into account the user's preferences and location. For example, a user can select the tag "sushi" to display nearby highly rated sushi restaurants on a map. The server also suggests the best delivery options based on the user's current location.

[1527] The system runs on servers on AWS (Amazon Web Services) or Google Cloud Platform, with data stored in a PostgreSQL database. It uses TensorFlow or OpenCV for image recognition, Google Cloud Natural Language API for NLP, IBM Watson Tone Analyzer for sentiment analysis, and Google Maps API for accurate location information.

[1528] For example, consider the following prompt:

[1529] "Analyze the following image to identify the type of food and price range: Sushi image"

[1530] "Analyze the following comment with your sentiment engine to determine whether it's positive, negative, or neutral: 'The sushi at this place was amazing!'"

[1531] In this way, the system can provide users with reliable, personalized gourmet information from a vast amount of information.

[1532] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1533] Step 1:

[1534] The server periodically collects posts with specific hashtags or keywords (e.g., gourmet, delivery) using the public API of the social networking site. Here, it sends an API request and analyzes the returned JSON data to extract images, videos, comments, number of likes, location information, etc. The input is the keyword of the API request, and the output is the collected post data.

[1535] Step 2:

[1536] The server analyzes the collected images and videos using AI image recognition technology (e.g., TensorFlow or OpenCV). This identifies features such as the type of cuisine, the atmosphere of the restaurant, and the price range. Specifically, the image data is input into the model, and feature labels (e.g., "sushi," "Japanese cuisine," "high-end") are obtained as output. The input is the images and videos of the posted data, and the output is the analyzed feature information.

[1537] Step 3:

[1538] The server analyzes the collected comments on posts using natural language processing technology (e.g., Google Cloud Natural Language API) to extract user ratings and impressions. Here, text data is sent to the API, and rating information is extracted based on the returned analysis results. The input is the comments on the post data, and the output is the analyzed ratings and impressions.

[1539] Step 4:

[1540] The server analyzes the collected comments and their language data using an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. Specifically, the comment text is input into the emotion engine, and emotion labels such as positive, negative, and neutral are obtained as output. The input is the posted comments, and the output is the analyzed emotion information.

[1541] Step 5:

[1542] The server retrieves the location information contained in the post, identifies the exact address from the extrapolation data, and verifies the accuracy of the location information by checking it against other geographic information databases (e.g., Google Maps API). The input is the location information of the post data, and the output is the confirmed exact address information.

[1543] Step 6:

[1544] The server then proposes delivery services based on the analysis results, taking into account the user's preferences and location information. Specifically, it runs an algorithm that recommends optimal delivery options based on the user's current location and preferences. The input is the user's current location and preference data, and the output is the proposed delivery service information.

[1545] Step 7:

[1546] Users can check suggested delivery services and restaurant information on a map through their device. Users can manipulate the information on the map to view detailed information and posted images. The input is the suggested delivery service information, and the output is the map information and detailed data that the user can view.

[1547] In this way, the system performs individual processing at each step, providing delivery services and gourmet information that are suited to the user.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1553] 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.

[1554] 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).

[1555] 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.

[1556] 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."

[1557] 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.

[1558] 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).

[1559] 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.

[1560] 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.

[1561] 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.

[1562] 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.

[1563] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1564] 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.

[1565] 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.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] The following is further disclosed regarding the above embodiment.

[1570] (Claim 1)

[1571] A way to collect information about food from posts on social media,

[1572] A method for analyzing the type of food and the atmosphere of the restaurant using image recognition technology from the collected information, and

[1573] A means for analyzing the posted content from the collected information using natural language processing technology and extracting user evaluations;

[1574] a means for analyzing the cited location information to identify precise geographic information;

[1575] A means for displaying cooking information based on the analysis on a map;

[1576] A system including:

[1577] (Claim 2)

[1578] 10. The system of claim 1, further comprising means for scoring the credibility and recommendation of a post based on the number of likes and comments.

[1579] (Claim 3)

[1580] 10. The system of claim 1, including filtering techniques to respect the privacy of personal information.

[1581] "Example 1"

[1582] (Claim 1)

[1583] A means of collecting information about food from posts on social media,

[1584] A means of analyzing the type of food and the atmosphere of the restaurant using image recognition technology from the collected information, and

[1585] A means for analyzing the posted content from the collected information using natural language processing technology and extracting user evaluations;

[1586] A means for analyzing location information from the collected information and identifying accurate geographic information;

[1587] A means for displaying the meal information based on the analysis on a map;

[1588] A means by which a user can view and manipulate information on a map using an application;

[1589] A means of periodically collecting new data and updating the database;

[1590] A means of collecting user feedback to improve the accuracy and usability of the analysis algorithm;

[1591] A system including:

[1592] (Claim 2)

[1593] 10. The system of claim 1, further comprising means for scoring the credibility and recommendation of a post based on the number of likes and comments.

[1594] (Claim 3)

[1595] 10. The system of claim 1, including filtering techniques to respect the privacy of personal information.

[1596] "Application Example 1"

[1597] (Claim 1)

[1598] A way to collect information about food from posts on social media,

[1599] A method for analyzing the type of food and the atmosphere of the restaurant using image recognition technology from the collected information, and

[1600] A means for analyzing the posted content from the collected information using natural language processing technology and extracting user evaluations;

[1601] a means for analyzing the cited location information to identify precise geographic information;

[1602] A means for displaying cooking information based on the analysis on a map;

[1603] A means to introduce recommended restaurants based on analyzed information based on the keywords searched by the user and their current location,

[1604] A means for placing an order directly with the selected restaurant;

[1605] A system including:

[1606] (Claim 2)

[1607] 10. The system of claim 1, further comprising means for scoring the credibility and recommendation of a post based on the number of likes and comments.

[1608] (Claim 3)

[1609] 10. The system of claim 1, including filtering techniques to respect the privacy of personal information.

[1610] "Example 2: Combining Emotion Engines"

[1611] (Claim 1)

[1612] A way to collect information about food from posts on social media,

[1613] A method for analyzing the type of food and the atmosphere of the restaurant using image recognition technology from the collected information, and

[1614] A means for analyzing the posted content from the collected information using natural language processing technology and extracting user evaluations;

[1615] a means for analyzing the cited location information to identify precise geographic information;

[1616] A means for analyzing the sentiment of the collected comments using an emotion engine and adjusting the recommendation level based on the sentiment;

[1617] A means for displaying cooking information based on the analysis on a map;

[1618] A system including:

[1619] (Claim 2)

[1620] 10. The system of claim 1, further comprising means for scoring the credibility and recommendation of a post based on the number of likes and comments.

[1621] (Claim 3)

[1622] 10. The system of claim 1, including filtering techniques to respect the privacy of personal information.

[1623] "Application example 2 when combining emotion engines"

[1624] (Claim 1)

[1625] A way to collect information about food from posts on social media,

[1626] A method for analyzing the type of food and the atmosphere of the restaurant using image recognition technology from the collected information, and

[1627] A means for analyzing the posted content from the collected information using natural language processing technology and extracting user evaluations;

[1628] a means for analyzing the cited location information to identify precise geographic information;

[1629] A means for displaying cooking information based on the analysis on a map;

[1630] A way to recommend delivery services based on user preferences and location information,

[1631] A system including:

[1632] (Claim 2)

[1633] 10. The system of claim 1, further comprising means for scoring the credibility and recommendation of a post based on the number of likes and comments.

[1634] (Claim 3)

[1635] 10. The system of claim 1, including filtering techniques to respect the privacy of personal information. [Explanation of symbols]

[1636] 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 way to collect information about food from posts on social media, A method for analyzing the type of food and the atmosphere of the restaurant using image recognition technology from the collected information, and A means for analyzing the posted content from the collected information using natural language processing technology and extracting user evaluations; a means for analyzing the cited location information to identify precise geographic information; A means for displaying cooking information based on the analysis on a map; A system including:

2. The system of claim 1 , further comprising means for scoring the trustworthiness and recommendation of a post based on the number of likes and comments.

3. The system of claim 1 , further comprising filtering techniques for respecting the privacy of personal information.

Images