system

Abstract

Provide a system. A means for collecting word-of-mouth information from the Internet; A means for storing the collected word-of-mouth information in a database; A means of retrieving review information from the database and filtering positive reviews; A means for automatically generating store or product descriptions based on the filtered word-of-mouth information; means for displaying the generated testimonial on a website; A system including:

Description

[Technical Field]

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

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

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

[0004] Traditional store and product introduction websites were primarily based on static data, making it difficult to reflect rapidly changing word-of-mouth information. Furthermore, they lacked a system for effectively aggregating only positive reviews while avoiding the influence of negative reviews, making it impossible to provide optimal information to consumers. Furthermore, advertising and reservation systems as a means of monetization were not integrated, making efficient monetization impossible. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that collects word-of-mouth information from the Internet, filters positive reviews, and automatically generates reviews for stores or products. Specifically, the system includes a means for collecting word-of-mouth information, a means for storing the information in a database, a filtering means, a means for automatically generating reviews, and a means for displaying website information. Furthermore, the system generates rankings based on the scores of the word-of-mouth information, and displays reviews for stores or products that match search queries from user terminals, thereby optimizing the provision of information to users and monetizing the system.

[0006] "Collection means" refers to a means for automatically acquiring word-of-mouth information from the Internet.

[0007] A "database" is a system for organizing and storing collected word-of-mouth information on storage.

[0008] The "filtering means" is a means for extracting only positive information from the word-of-mouth information stored in the database.

[0009] The "automatic generation means" is a means for generating a description of a store or product based on filtered word-of-mouth information.

[0010] The "website display means" is a means for displaying the generated introduction on a website in a form that can be viewed by a user.

[0011] "Ranking" refers to ranking based on the score of word-of-mouth information.

[0012] A "search query" is a string of characters or keywords that a user enters when searching for specific information.

[0013] "Monetization means" are means for obtaining economic benefits through advertising, reservation systems, etc. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention is a system based on a client-server model, where the server is the central player in collecting data, filtering, generating content, and displaying it, while the terminal functions as an interface with the user. A specific implementation of the present invention will be described below.

[0036] Data collection

[0037] The server first executes a process to automatically retrieve review information from the Internet. The server sends an HTTP request to the website containing the target review information and analyzes the retrieved HTML data. To analyze, it parses the DOM structure of the webpage and extracts the review score and text. All of this information is stored in a database.

[0038] Storage in the database

[0039] The server stores the acquired word-of-mouth information in a database as structured data. Therefore, each piece of word-of-mouth information is organized and stored in the database by fields such as "store name," "product name," "score," and "text." This allows the data to be extracted and analyzed efficiently in later processing.

[0040] Filtering Methods

[0041] The server retrieves reviews from the database and filters out positive reviews (e.g., scores of 4 or higher). Specifically, it loops through all reviews, checks their scores, and extracts only those that meet the criteria. This filtered data is then used as the basis for ranking.

[0042] Creating rankings

[0043] The server creates a ranking based on the filtered reviews. The ranking is sorted by highest score to make it easier to find highly rated stores and products, and the ranking results are used as the basis for generating testimonials.

[0044] Automated content generation

[0045] The server automatically generates store and product descriptions based on the ranked reviews. Using a natural language generation tool, the acquired review text is used as training data to generate high-quality descriptions. These descriptions become the main content displayed to users.

[0046] Website display method

[0047] A user accesses a website from their device and enters a search query. The device sends this search query to the server, which searches the database and returns rankings and testimonials of relevant stores and products. The user can then review this information and view the testimonial page for more detailed information.

[0048] Reservation System

[0049] Users can make reservations directly from the store or product introduction page. They enter the required information (e.g., user ID, reservation time, etc.) into the reservation form and send it to the server. The server stores this information in the reservation database and notifies the user that the reservation was successful.

[0050] Advertisement display

[0051] The server generates appropriate advertisements based on users' interests and search queries and displays them on web pages, generating revenue from these advertisements to ensure the system's sustainable operation.

[0052] As described above, the present invention automatically generates high-quality introductory content using word-of-mouth information, providing users with optimal store and product information. It also realizes monetization through reservations and advertising, providing an efficient and effective media platform.

[0053] The processing flow will be explained below.

[0054] Data collection and storage

[0055] Step 1:

[0056] The server retrieves the review information from the Internet. Specifically, it sends an HTTP request to the website that contains the review information in question and retrieves the HTML data.

[0057] Step 2:

[0058] To analyze the retrieved HTML data, the server parses it into a Document Object Model (DOM) structure, which makes it easier to access each element of the web page.

[0059] Step 3:

[0060] The server extracts review scores and text from the parsed HTML structure, for example by extracting the required data based on specific CSS classes or tags.

[0061] Step 4:

[0062] The server stores the extracted review information (score and text) in a database. Specifically, it stores the data in the appropriate table using an insert statement.

[0063] Data Filtering and Analysis

[0064] Step 5:

[0065] The server retrieves all the reviews stored in the database by executing a query that selects all records from the database.

[0066] Step 6:

[0067] The server analyzes the data and filters out only positive reviews, for example, those with a score of 4 or higher.

[0068] Step 7:

[0069] The server sorts the filtered reviews in order of score and creates a ranking, which allows stores and products to be sorted in descending order of their ratings.

[0070] Automated content generation

[0071] Step 8:

[0072] The server automatically generates store and product descriptions based on the sorted review information. It uses a natural language generation tool (e.g., TextgenRnn) to generate the descriptions using the review text as training data.

[0073] Search and Display

[0074] Step 9:

[0075] A user accesses a website from a terminal and enters a search query.

[0076] Step 10:

[0077] The terminal transmits a search query from the user to the server.

[0078] Step 11:

[0079] The server searches the database based on the submitted search query to retrieve relevant reviews and rankings. The database is searched using an appropriate SQL query.

[0080] Step 12:

[0081] The server converts the search results into HTML format and generates a web page for display to the user.

[0082] Bookings and Advertising

[0083] Step 13:

[0084] When a user makes a reservation directly from a store or product introduction page, the user enters the necessary information (for example, user ID, reservation time, etc.) into a form on the terminal.

[0085] Step 14:

[0086] The terminal transmits the input reservation information to the server.

[0087] Step 15:

[0088] The server stores the received reservation information in the database by executing an insert statement on the reservation table.

[0089] Step 16:

[0090] The server notifies the user that the reservation was successful, and generates a reservation success page and sends it to the terminal for display to the user.

[0091] Step 17:

[0092] The server selects advertising data for displaying appropriate advertisements based on the user's interests and search queries, thereby displaying effective advertisements that attract the user's attention.

[0093] In this way, this system automatically generates high-quality content based on word-of-mouth information, providing optimal information to users, and also realizing monetization through reservations and advertising.

[0094] Example 1

[0095] 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."

[0096] Currently, many users are seeking reliable word-of-mouth information via the Internet, but collecting and organizing information is cumbersome, and finding the right information requires a great deal of effort. Another issue is the lack of systems that can quickly and accurately provide users with the information they are looking for. Additionally, the process of finding information about stores and products that users are truly interested in and making reservations based on that information is also cumbersome. Furthermore, in order to ensure profits, system operators need a way to efficiently display advertisements based on users' interests.

[0097] 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.

[0098] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering positive word-of-mouth information, means for automatically generating store or product descriptions based on the filtered word-of-mouth information, means for displaying the generated descriptions on a website, means for a user to access the website from a terminal and input a search query, means for the user to display rankings and descriptions of relevant stores or products based on the search query, means for displaying advertisements based on the ranked word-of-mouth information, means for inputting information required for a reservation form and transmitting it to the server, and means for notifying the user that the reservation was successful. This allows the information desired by the user to be provided quickly and accurately, enabling easy reservation, and also enables efficient advertisement display to ensure profits for the system operator.

[0099] "Word-of-mouth information" refers to the evaluations and impressions of users on the Internet, including opinions and evaluations of specific products and services.

[0100] A "database" is a collection of systematically organized data that has a structure that allows specific information to be searched and extracted from it.

[0101] "Filtering" refers to the process of selecting data that meets specific conditions from the acquired data.

[0102] An "introduction" is a text that explains a store or product, and conveys its features and advantages to users in an easy-to-understand manner.

[0103] A "website" is a collection of information published on the Internet that users can access using a web browser.

[0104] A "search query" is a keyword or phrase that a user enters to search for information within a search engine or a particular website.

[0105] A "ranking" is a list in which multiple objects are evaluated and ranked based on certain criteria.

[0106] An "advertisement" is a message or visual that promotes a particular product or service and is displayed on a web page to attract a user's attention.

[0107] A "reservation" is a procedure for reserving a store or service date and time in advance.

[0108] A "generative AI model" is an artificial intelligence system that learns from large amounts of data to generate and understand natural language, and specifically refers to a language model.

[0109] A "prompt" is input text given to a generative AI model to request a specific output.

[0110] "User" refers to an individual or corporation that uses this system, and is primarily someone who accesses it via the Internet.

[0111] A "terminal" is a device that a user uses to connect to the Internet to obtain information and perform operations.

[0112] A "server" is a computer system that manages data on a network and provides services to multiple users.

[0113] The present invention is a system based on a client-server model, where the server is the central player in data collection, filtering, content generation, and display, while the terminals act as the interface with the user.

[0114] First, the server collects review information from the Internet. Specifically, the server sends an HTTP request to a specific review site and analyzes the HTML data it retrieves. This analysis is performed using Python and BeautifulSoup. The server then parses the HTML data, extracts review scores and text, and stores the organized data in a database. MySQL (registered trademark) is used for database management.

[0115] Next, the server retrieves the reviews from the database and filters out the positive reviews. The filtering criteria is to extract reviews with a score of 4 or higher. This operation is performed using SQLAlchemy. After the data is filtered, the server creates a ranking based on the results. The ranking is sorted by highest score, making it easier for users to find highly rated stores and products. This is done using Python's sorting function.

[0116] The server then generates store and product descriptions based on the ranking results. This process uses a generative AI model (e.g., GPT-3 (registered trademark)) and uses the review text as training data. An example of a prompt for generation is: "Generate a high-quality store description based on the following review data: {review text}." The generated description is stored in a database and displayed on the website.

[0117] A user accesses a website from a device and enters a search query. The device sends the search query to the server, which searches the database and returns rankings and reviews of relevant stores and products to the device. This information is then displayed to the user through a web browser.

[0118] Users can also make reservations directly from the introduction page. After entering the necessary information into the reservation form and sending it to the server, the server stores this information in the reservation database and notifies the user that the reservation was successful. This also involves database operations such as SQL.

[0119] Finally, the server displays appropriate advertisements based on the user's interests and search queries. The server analyzes the user's search history and other factors to select and display the most relevant advertisements on the web page. Revenue generated from these advertisements allows the system to operate sustainably.

[0120] The present invention allows users to quickly and accurately receive the information they require, and simplifies the reservation process. Furthermore, efficient advertising display also enables monetization, making it possible to provide effective services.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1:

[0123] The server collects reviews from the Internet.

[0124] Input: URL of the target review site.

[0125] Output: HTML data.

[0126] Specific behavior:

[0127] The server executes "requests.get(URL)" to retrieve the HTML of the target page.

[0128] The server parses the HTML using "BeautifulSoup(html, 'html.parser')".

[0129] The server navigates the DOM tree and extracts the review data using the "find_all" method.

[0130] Step 2:

[0131] The server stores the extracted word-of-mouth information in a database.

[0132] Input: Extracted review score and text.

[0133] Output: Structured data stored in a database.

[0134] Specific behavior:

[0135] The server inserts the data into the database using the SQL query "INSERT INTO Reviews (store_name, product_name, score, text) VALUES ...".

[0136] The server manages these operations using a database connectivity library (e.g., SQLAlchemy).

[0137] Step 3:

[0138] The server retrieves review information from the database and filters out positive reviews.

[0139] Input: Reviews in the database.

[0140] Output: Filtered review data that meets the criteria.

[0141] Specific behavior:

[0142] The server executes "SELECT FROM Reviews WHERE score >= 4" and retrieves data that meets the condition.

[0143] The server stores the retrieved data in a list or other suitable data structure for further processing.

[0144] Step 4:

[0145] The server creates a ranking based on the filtered word-of-mouth information.

[0146] Input: Filtered review data.

[0147] Output: Data organized in a ranking format.

[0148] Specific behavior:

[0149] The server sorts the data in a way like "sorted(reviews, key=lambda x: x['score'], reverse=True)".

[0150] The server stores the sorted data in a ranking format.

[0151] Step 5:

[0152] The server generates store and product descriptions based on the ranking data.

[0153] Input: Ranked reviews.

[0154] Output: Generated store and product descriptions.

[0155] Specific behavior:

[0156] The server sends a prompt to the "generative AI model" and generates an introduction in response.

[0157] Example: "Generate high-quality store descriptions based on the following review data: {review text}"

[0158] The server stores the generated testimonial in a database.

[0159] Step 6:

[0160] A user accesses a website from a terminal and enters a search query.

[0161] Input: Search query.

[0162] Output: Rankings and descriptions of stores and products displayed as search results.

[0163] Specific behavior:

[0164] A user enters a query into a search form in a web browser and clicks "Submit."

[0165] The device sends the search query to the server as a POST request.

[0166] The server searches the database and returns matching data in HTML format.

[0167] The device displays the received HTML in the browser.

[0168] Step 7:

[0169] Users can make reservations directly from the referral page.

[0170] Input: Information entered into the reservation form (e.g., user ID, reservation time, etc.).

[0171] Output: Notification that the reservation was successful.

[0172] Specific behavior:

[0173] The user fills in the reservation form and clicks the "Book" button.

[0174] The terminal sends the input information to the server as a POST request.

[0175] The server stores this information in the reservation database as "INSERT INTO Reservations (user_id, reservation_time, ...) VALUES ...".

[0176] The server generates a message confirming successful reservation and returns it to the user.

[0177] Step 8:

[0178] The server displays appropriate advertisements based on the user's interests and search queries.

[0179] Input: User search queries and browsing history.

[0180] Output: Relevant ads.

[0181] Specific behavior:

[0182] The server analyzes search queries and browsing history and selects relevant advertisements from a database.

[0183] The server embeds the selected advertisement into HTML and returns it to the user.

[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] In recent years, consumer decision-making based on word-of-mouth information has been increasing, but there are currently no systems in place that can efficiently collect this information and present it to users in an appropriate format. There is also a need to utilize this word-of-mouth information to enable users to easily make reservations and purchases. Furthermore, there is a need to display advertisements based on user behavior and interests, thereby generating revenue. Conventional systems face the challenge of being unable to meet these multiple requirements.

[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 word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering out positive word-of-mouth information, means for automatically generating store or product descriptions based on the filtered word-of-mouth information, means for displaying the generated description on a website, means for displaying the generated description on a smartphone application, means for users to make reservations through the application, and means for displaying advertisements based on the user's interests and behavior. This not only enables efficient collection and presentation of word-of-mouth information, allowing users to easily make reservations and purchases, but also enables monetization through the display of advertisements.

[0189] "Word-of-mouth information" refers to reviews and opinions about stores and products provided by users on the Internet.

[0190] A "database" is a data storage system for structuring and storing collected word-of-mouth information.

[0191] "Filtering" refers to the process of selecting only information that meets specific conditions from collected word-of-mouth information.

[0192] "Positive reviews" are reviews that show favorable evaluations, many of which are accompanied by high scores.

[0193] An "introduction" is a text automatically generated based on filtered word-of-mouth information, which explains the features of the store or product.

[0194] A "website" is a collection of information accessible to users over the Internet, identified by a particular URL.

[0195] A "smartphone application" is a program that runs on a smartphone and allows users to use specific functions through an interface.

[0196] "Reservation" means that a user applies in advance for a particular service or product.

[0197] "Advertisement" means a commercial message displayed based on a user's interests or behavior, which is intended to promote a particular product or service.

[0198] "Server" means a central management system that collects, stores, processes, and distributes data, and serves to provide data to terminals that interface with users.

[0199] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0200] System Configuration

[0201] This invention consists of a server and a user terminal. The server collects, stores, and filters reviews, automatically generates and displays testimonials, and manages reservations and advertisements. Meanwhile, users access these functions using a smartphone application.

[0202] Hardware and software used

[0203] Server: Node.js and Express.js are used for server-side processing. MongoDB is used as the database.

[0204] Natural Language Generation: Utilizing the OpenAI (registered trademark) API, we generate testimonials based on reviews.

[0205] Front-end: Develop a smartphone application using React Native.

[0206] Data processing and calculation

[0207] Data collection

[0208] The server collects review information from review websites on the Internet by sending HTTP requests to retrieve the target HTML data and then performing DOM analysis to extract review text and scores.

[0209] Storage in the database

[0210] The collected reviews are stored in an organized format in a MongoDB database, allowing for efficient subsequent filtering and ranking.

[0211] filtering

[0212] The server filters the reviews retrieved from the database for positive reviews with high scores, using MongoDB's query function for this process.

[0213] Creating rankings

[0214] A ranking is created based on the filtered reviews. The reviews are sorted in descending order of score, and highly rated stores and products are extracted.

[0215] Automated content generation

[0216] Using the OpenAI API, a natural language generation tool, we automatically generate high-quality testimonials based on the ranked reviews, which then become the main content displayed to users.

[0217] Website display and smartphone application display

[0218] The generated introduction is sent from the server to the device and displayed on the website and smartphone application, which uses React Native to provide the interface.

[0219] Reservation System

[0220] Users can access store and product introduction pages from their smartphone application and make reservations. The information required for the reservation is sent to the server and stored in a reservation database.

[0221] Advertisement display

[0222] The server automatically generates advertisements based on the user's interests and behavior and displays them on the application. Revenue from these advertisements enables the system to operate sustainably.

[0223] Specific examples

[0224] For example, if a user opens the application and searches for "pasta restaurant," the server retrieves reviews of highly rated pasta restaurants from the database, creates a ranking, and then uses the OpenAI API to generate a review based on the following prompt:

[0225] Generate engaging restaurant descriptions for your users based on the following reviews:

[0226] Review 1: "The pasta was amazing, especially the carbonara."

[0227] Review 2: "The staff were very friendly and I had a great time."

[0228] The generated introduction is displayed on the smartphone application, and users can make reservations based on that information.

[0229] The above is a specific embodiment for carrying out the present invention.

[0230] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0231] Step 1:

[0232] The server collects review information from the Internet. The server sends an HTTP request to retrieve HTML data from the target website. It analyzes this HTML data and extracts review text and scores. The input is review information from the Internet, and the output is the extracted review text and scores.

[0233] Step 2:

[0234] The server stores the extracted review information in a database. The database uses MongoDB, and stores the review information organized by fields such as "store name," "product name," "score," and "text." The input is the review information extracted in step 1, and the output is a structured database entry.

[0235] Step 3:

[0236] The server retrieves reviews from the database and filters out positive reviews. The server uses MongoDB's query function to select reviews with a score of 4 or higher. The input is all reviews in the database, and the output is the positive reviews that match the criteria.

[0237] Step 4:

[0238] The server creates a ranking based on the filtered reviews. It sorts the positive reviews in descending order of score and extracts highly rated stores and products. The input is the reviews filtered in step 3, and the output is ranked data.

[0239] Step 5:

[0240] The server automatically generates store or product descriptions based on the ranked reviews. Using OpenAI's API, the review information is used as training data to generate high-quality descriptions. The input is the ranking data from Step 4 and a prompt for the AI ​​model, and the output is the generated description.

[0241] Step 6:

[0242] The server displays the generated testimonial on the smartphone application. The generated testimonial is sent to a smartphone app using React Native and displayed to the user. The input is the testimonial generated in step 5, and the output is the visualized testimonial on the application.

[0243] Step 7:

[0244] A user makes a reservation through an application. The user enters the required information into a reservation form from the application and submits it to the server. The server stores this information in a reservation database and notifies the user of a reservation confirmation. The input is the reservation information entered by the user, and the output is a reservation entry in the database and a confirmation to the user.

[0245] Step 8:

[0246] The server displays advertisements based on the user's interests and behavior. Based on the user's search query and browsing history, appropriate advertisements are selected and displayed on the smartphone application. The input is user behavior data and advertisement information from an advertisement database, and the output is the displayed advertisement.

[0247] 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.

[0248] The present invention is a system based on a client-server model, where the server is the central player in collecting data, filtering, generating content, and displaying it, while the terminal functions as an interface with the user. A specific implementation of the present invention will be described below.

[0249] Data collection and storage

[0250] The server automatically retrieves review information from the Internet. Specifically, it sends an HTTP request to the website containing the target review information and retrieves the HTML data. It then analyzes the HTML data, parses it into a DOM structure, and extracts the review score and text. The extracted review information is then stored in a database.

[0251] Data Filtering and Analysis

[0252] The server retrieves all reviews from the database and filters out positive reviews (e.g., scores of 4 or higher). The filtered reviews are sorted by score and stored as rankings.

[0253] Automated content generation

[0254] The server automatically generates store and product descriptions based on the ranked reviews. It uses a natural language generation tool to generate high-quality descriptions using the acquired review text as training data.

[0255] Search and Display

[0256] A user accesses a website from a terminal and enters a search query. The terminal sends the search query to the server, which searches the database to obtain relevant reviews and rankings, and generates a web page to display to the user. The user then browses the reviews displayed as search results.

[0257] Emotion engine integration

[0258] The server integrates an emotion engine into the review information collection and filtering process. It performs sentiment analysis on the review data and prioritizes filtering of reviews with positive sentiment. This procedure allows the server to provide more reliable and useful information to users.

[0259] The emotion engine also analyzes word-of-mouth information related to search queries from devices, and prioritizes displaying information with positive sentiment to users.

[0260] Emotion-based advertising

[0261] The server monitors the user's real-time emotions with an emotion engine and dynamically changes the advertising content based on those emotions, thereby presenting ads that best fit the user's emotional state and improving advertising effectiveness.

[0262] Reservation System

[0263] Users can make reservations directly from the store or product introduction page. They enter the required information (e.g., user ID, reservation time, etc.) into the form on their terminal and send it to the server. The server stores the received reservation information in a database and notifies the user that the reservation was successful. A reservation success page is generated and displayed to the user.

[0264] Specific examples of processing

[0265] For example, when a user searches for a restaurant, the server collects reviews of that restaurant and analyzes them using an emotion engine. It filters out only the positive reviews and automatically generates a review based on them. When a user enters a search query about a specific dish, the server prioritizes the display of positive reviews related to the query.

[0266] In this way, this system automatically generates high-quality content based on word-of-mouth information and provides users with the most appropriate information. In addition, by integrating an emotion engine, it is possible to provide more reliable information and improve advertising effectiveness.

[0267] The processing flow will be explained below.

[0268] Processing steps of a system that combines emotion engines

[0269] Step 1:

[0270] The server retrieves review information from the Internet. Specifically, it sends an HTTP request to the target review site and retrieves the HTML data.

[0271] Step 2:

[0272] The server parses the HTML data and parses it into a DOM structure to extract review scores and text, using specific CSS selectors and tags to identify the data it needs.

[0273] Step 3:

[0274] The server stores the extracted word-of-mouth information in a database, which contains fields such as "store name," "product name," "score," and "text."

[0275] Step 4:

[0276] The server retrieves all reviews from the database and uses an appropriate SQL query to select all records.

[0277] Step 5:

[0278] The server analyzes the acquired reviews using a sentiment engine and adds a sentiment score. The sentiment engine analyzes the text of each review and generates a sentiment score such as positive, negative, or neutral.

[0279] Step 6:

[0280] The server filters the reviews based on the sentiment score, specifically selecting reviews with a positive sentiment score (e.g., a score of 4 or higher).

[0281] Step 7:

[0282] The server sorts the filtered reviews by score and creates a ranking, which results in a list of stores and products with the highest ratings.

[0283] Step 8:

[0284] The server automatically generates store and product descriptions based on the ranked reviews. It uses a natural language generation tool to generate high-quality descriptions using the review text as training data.

[0285] Step 9:

[0286] A user accesses a website from a device and enters a search query, which may be for a specific store or product.

[0287] Step 10:

[0288] The device sends a search query to the server, which passes the query entered by the user to the server.

[0289] Step 11:

[0290] The server searches the database based on the search query to retrieve relevant reviews and rankings. The search results include reviews that are recognized as positive by the sentiment engine.

[0291] Step 12:

[0292] The server generates a web page based on the search results to display to the user, including the generated testimonial and ranking information.

[0293] Step 13:

[0294] The user can view the displayed introductions and rankings, and check detailed store and product information as needed. Specifically, they can access the introduction page.

[0295] Step 14:

[0296] Users make reservations directly from the store or product introduction page, entering necessary information such as user ID and reservation time into the reservation form.

[0297] Step 15:

[0298] The terminal sends the entered reservation information to the server. When the user submits the form, the reservation request is passed to the server.

[0299] Step 16:

[0300] The server stores the received reservation information in the database and executes an SQL query to insert the reservation information into the reservation table.

[0301] Step 17:

[0302] The server notifies the user that the reservation was successful by generating a reservation success page and sending it to the terminal.

[0303] Step 18:

[0304] The server monitors the user's emotions in real time and displays appropriate advertisements based on those emotions. The emotion engine analyzes the user's emotions and dynamically changes the advertisement content.

[0305] In this way, the system generates high-quality content based on word-of-mouth information and user sentiment analysis, providing optimal information to users and generating revenue.

[0306] Example 2

[0307] 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."

[0308] Conventional word-of-mouth information collection systems have had the problem of not being able to adequately evaluate or filter the collected word-of-mouth information, making it difficult to provide useful information to users. Furthermore, since they do not evaluate word-of-mouth information using an emotion engine or dynamically display advertisements based on the user's emotional state, it has been impossible to improve the reliability of word-of-mouth information or the effectiveness of advertisements.

[0309] 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.

[0310] In this invention, the server includes a means for collecting word-of-mouth information from the Internet, a means for storing the collected word-of-mouth information in a database, and a means for retrieving word-of-mouth information from the database and filtering out positive reviews. This makes it possible to provide users with highly reliable, positive word-of-mouth information. Furthermore, the server also includes a means for evaluating word-of-mouth information and user search queries using a sentiment analysis engine and preferentially displaying positive information, a means for dynamically changing advertisements based on the user's emotional state, a means for notifying the user based on the results of the sentiment analysis by the sentiment engine, and a means for generating testimonials using a generative AI model, thereby improving the reliability of word-of-mouth information and advertising effectiveness.

[0311] "Word-of-mouth information" refers to information posted online by ordinary consumers that includes their evaluations and opinions about products and services.

[0312] A "database" is a digital storage system for systematically storing and managing collected word-of-mouth information.

[0313] "Filtering" is the process of selecting collected word-of-mouth information that meets specific criteria (e.g., positive reviews).

[0314] "Automatic generation" is the process of generating text or content using a computer program without human intervention.

[0315] "Display" refers to the act of visually presenting the generated testimonials and filtered word-of-mouth information to the user.

[0316] A "sentiment analysis engine" is software that automatically evaluates the sentiment (positive, negative, neutral, etc.) of text data.

[0317] "Advertisement" refers to content that presents information about products or services to users for promotional purposes.

[0318] A "generative AI model" is a trained model that uses artificial intelligence techniques to generate text or content.

[0319] A "search query" is a keyword or phrase that a user enters into a search engine or system to search for information.

[0320] "Positive reviews" are reviews that have a high rating (e.g., a score of 4 or higher) and contain positive opinions and emotions.

[0321] "Dynamic change" refers to the automatic change of display content and behavior in real time according to conditions.

[0322] MODE FOR CARRYING OUT THE INVENTION

[0323] The present invention is a system based on a client-server model, where the server is the central point responsible for data collection, filtering, content generation and display, while the terminals act as the interface with the user.

[0324] Data collection

[0325] The server collects review information from the Internet. Specifically, it sends an HTTP request to the target website and retrieves the HTML data. This process uses the Apache (registered trademark) HttpClient library. The retrieved HTML data is parsed into a DOM structure using JSoup, and the review score and text are extracted.

[0326] Data analysis

[0327] The server analyzes the parsed HTML data using the JSoup library and extracts the review scores and text. The extracted data is stored in a database such as MySQL or PostgreSQL. Data is stored in the database using JDBC.

[0328] Data Filtering

[0329] The server retrieves all reviews from the database and filters out positive reviews (e.g., scores of 4 or higher). It uses an SQL query to extract only records that meet the specified criteria. The extracted data is stored as rankings in an in-memory database such as Redis or ElasticSearch (registered trademark).

[0330] Content Generation

[0331] The server automatically generates testimonials based on the filtered review information using a natural language generation model (e.g., GPT-3 or BERT). By using the review text as training data and inputting prompts into the generative AI model, high-quality testimonials are generated.

[0332] Search and Display

[0333] A user accesses a website from a device (e.g., a PC or smartphone) and enters a search query. The device sends this search query to the server, which searches a database to return relevant reviews and rankings, and generates a web page to display to the user. The user can then view the reviews displayed as search results.

[0334] sentiment analysis

[0335] The server uses a sentiment analysis engine (e.g., TextBlob or VADER) to filter reviews. By performing sentiment analysis, it prioritizes filtering of positive reviews and provides reliable information.

[0336] Emotion-based advertising

[0337] The server monitors the user's emotional state in real time and dynamically changes the advertisements based on that emotion. It uses an emotion engine to evaluate the user's emotions and displays the most appropriate advertising content by using Google® Ads or Facebook Ads APIs.

[0338] Reservation System

[0339] The user enters the necessary information (e.g., user ID, reservation time, etc.) into the form on the terminal and sends it to the server. The server stores the reservation information in a database and notifies the user that the reservation was successful. A reservation success page is also generated at the same time and displayed to the user.

[0340] Prompt Sentence Examples

[0341] "Generate testimonials with positive reviews for this restaurant. The reviews are: [list of reviews]"

[0342] "Please suggest optimal ad content based on the user's emotional state. The user's emotional state is: [user's emotional data]"

[0343] In this way, this system automatically generates high-quality content based on word-of-mouth information and provides users with the most appropriate information. In addition, by integrating an emotion engine, it provides more reliable information and improves advertising effectiveness.

[0344] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0345] Step 1:

[0346] The server collects reviews from the Internet. As input, it receives the URLs of target websites and sends an HTTP request to retrieve HTML data. Using the Apache HttpClient library, it sends a GET request and receives a response with HTML data. As output, it generates the retrieved HTML data. Specifically, it creates an instance of HttpClient and sends a GET request to the specified URL.

[0347] Step 2:

[0348] The server parses the retrieved HTML data. As input, it receives the HTML data retrieved in step 1 and parses it into a DOM structure using the JSoup library. This allows it to extract review scores and text. As output, it generates a list of the extracted scores and text. Specifically, it extracts review scores and text from the Document object parsed by JSoup using the specified CSS selector.

[0349] Step 3:

[0350] The server stores the extracted review information in a database. As input, it receives the scores and text list extracted in step 2 and stores them in a database such as MySQL or PostgreSQL. It connects to the database using JDBC and inserts the data. As output, review information stored in the database is generated. Specifically, it executes an insert SQL statement using PreparedStatement and stores the review scores and text in the corresponding tables in the database.

[0351] Step 4:

[0352] The server retrieves all reviews from the database and filters out the positive ones. As input, it takes all reviews stored in the database and executes a SQL query to filter reviews with a score of 4 or higher. As output, it generates a list of reviews that are determined to be positive. Specifically, it uses a Statement object to execute a SELECT query and extracts records that match the criteria.

[0353] Step 5:

[0354] The server automatically generates testimonials using a generative AI model based on the filtered reviews. As input, it receives a list of filtered reviews and generates a prompt. The testimonials are generated using natural language generation models such as GPT-3 and BERT. As output, a high-quality testimonial is generated. Specifically, the prompt is input to the generative AI model and the generated text is obtained as a response.

[0355] Step 6:

[0356] A user accesses a website from a terminal and enters a search query. The search query entered by the user is received as input and sent to the server. The terminal then sends the search query to the server as a POST request. As output, the search results are displayed to the user. Specifically, the system retrieves the search query from an HTML form and generates an HTTP request to send to the server.

[0357] Step 7:

[0358] The server uses a sentiment analysis engine to evaluate reviews and search queries. As input, it receives collected reviews and search queries from users, and calculates a sentiment score using a sentiment analysis library such as TextBlob or VADER. As output, information rated as positive is displayed preferentially. Specifically, text is input into the analysis library, its sentiment score is calculated, and filtering is performed.

[0359] Step 8:

[0360] The server dynamically changes ads based on the user's emotional state. It receives user emotional data as input and dynamically selects ad content. It uses Google Ads or Facebook Ads API to retrieve and display the most suitable ad. The output is an ad optimized for the user's emotions. Specifically, it calls the advertising API based on the user's emotional data and renders the retrieved ad data for display.

[0361] Step 9:

[0362] A user makes a reservation through a website. As input, the information entered by the user in the reservation form (user ID, reservation time, etc.) is received and sent to the server. The server stores this information in a database and notifies the user of the reservation result. As output, a notification that the reservation was successful is displayed to the user. Specifically, the system retrieves information from the reservation form, generates an HTTP request to send to the server, stores the information in the database on the server side, and then generates a response notifying the result.

[0363] (Application example 2)

[0364] 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."

[0365] Conventional review information collection systems only filter positive reviews and are unable to provide optimal information based on the user's emotional state. Furthermore, they are unable to centrally handle facility and product reservation functions, limiting the user experience. This has created challenges in effectively utilizing review information and improving user convenience.

[0366] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0367] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering out positive word-of-mouth information, means for automatically generating a facility or product introduction text based on the filtered word-of-mouth information, means for displaying the generated text on a website, means for dynamically displaying advertisements that are optimal for the user's emotional state using a sentiment analysis module, and means for receiving data for making reservations for facilities or products from a terminal and storing the data in the database. This allows users to view high-quality content based on positive word-of-mouth information, and by receiving advertisements that are tailored to their emotions, the effectiveness of the advertisements is improved, making it possible for users to easily make reservations for facilities or products.

[0368] "Word-of-mouth information" is data that includes user ratings and opinions posted on the Internet.

[0369] A "database" is a system for storing and managing data in a structured way.

[0370] "Positive reviews" are reviews with favorable content that have a rating above a certain score.

[0371] "Filtering" is a method of selecting data based on specific conditions.

[0372] "Facility or product introduction text" is a description of a facility or product that is automatically generated based on filtered word-of-mouth information.

[0373] A "sentiment analysis module" is a software component for detecting and classifying emotions from text data.

[0374] "Dynamic display of advertisements" means that advertisement content is displayed while changing in response to the user's real-time emotional state.

[0375] "Data for reserving a facility or product" refers to information required when a user makes a reservation (e.g., user ID, reservation time, etc.).

[0376] A "terminal" is a computing device through which a user accesses the Internet.

[0377] MODE FOR CARRYING OUT THE INVENTION

[0378] System Overview

[0379] The system for implementing this invention collects word-of-mouth information, filters it, analyzes its sentiment, generates content, and displays it on a user terminal. The system is mainly composed of a server, a database, a sentiment analysis module, and a user terminal.

[0380] Hardware and software used

[0381] Server: Cloud server such as AWS (registered trademark) EC2

[0382] Database: SQLite or AWS RDS

[0383] Sentiment analysis module: TextBlob or AWS Comprehend

[0384] Scraping tool: BeautifulSoup

[0385] User interface: Web browser or smartphone application (e.g., Flask)

[0386] Processing flow

[0387] Server-side processing

[0388] The server collects reviews from the Internet and stores them in a database. Specifically, it uses BeautifulSoup to retrieve HTML data from target websites, parses the data, and extracts review information. The extracted reviews are then stored in a structured format in the database.

[0389] The server retrieves the reviews from the database and uses TextBlob to filter the positive reviews. The positive reviews are sorted by score and stored as a ranking. Furthermore, it utilizes a sentiment analysis module to monitor the user's emotional state and dynamically change the advertising content based on the user's emotion.

[0390] Processing on the user terminal side

[0391] A user inputs a search query through a website or smartphone application. The input query is sent to a server, which retrieves related reviews and generated introductory text and displays them to the user. The user can then use the displayed reviews and introductory text to check details about the facility or product and view advertisements. Furthermore, the user can also make reservations for the facility or product within the application.

[0392] Specific examples

[0393] For example, when a user searches for a restaurant, the server collects reviews related to that restaurant and performs sentiment analysis. It filters out only positive reviews and automatically generates high-quality restaurant descriptions based on that information. When a user enters a search query about a specific dish, the server prioritizes displaying related positive reviews.

[0394] Prompt Sentence Examples

[0395] Filter reviews with positive sentiment from word of mouth information and generate high-quality descriptions of restaurants and dishes. The filtered information format is: [restaurant name, score, review text].

[0396] This system allows users to view high-quality content based on positive word-of-mouth, and by displaying advertisements that are tailored to their emotions, advertising effectiveness is improved, making it possible to easily reserve facilities and products.

[0397] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0398] Step 1:

[0399] The server collects reviews from the target website. Specifically, the server sends an HTTP request and receives the website's HTML data.

[0400] (Input: URL, Output: HTML data). Analyze the received HTML data using BeautifulSoup and extract the reviews.

[0401] (Input: HTML data, Output: Reviews).

[0402] Step 2:

[0403] The server stores the extracted reviews in a structured format in a database.

[0404] (Input: review information, output: data stored in a database). Specifically, the server connects to a database such as SQLite and inserts the review information into a table.

[0405] Step 3:

[0406] The server retrieves reviews from the database and filters out positive reviews using a sentiment analysis module (e.g., TextBlob).

[0407] (Input: review information in the database, Output: positive reviews). The server calculates a sentiment score for each review using TextBlob and extracts only reviews with a positive score (e.g., 4 or higher).

[0408] Step 4:

[0409] The server automatically generates facility or product introduction text based on the filtered reviews.

[0410] (Input: positive reviews, Output: introduction text for the facility or product). Specifically, the server uses a natural language generation tool (e.g., a generative AI model) to automatically generate high-quality introduction text. An example of a prompt is as follows:

[0411] Filter reviews with positive sentiment from word of mouth information and generate high-quality descriptions of restaurants and dishes. The filtered information format is: [restaurant name, score, review text].

[0412] Step 5:

[0413] A user uses a device to enter a search query through a website or smartphone application

[0414] (Input: search query, output: sending query to server). Specifically, the device accepts user input and sends the search query to the server.

[0415] Step 6:

[0416] The server retrieves relevant reviews and generated testimonials from a database based on the received search query and generates a web page to display to the user.

[0417] (Input: search query, output: search result page). Specifically, the server queries the database for relevant information and generates it as an HTML page.

[0418] Step 7:

[0419] The server utilizes a sentiment analysis module to monitor the user's emotional state and dynamically change the advertising content based on the emotional state.

[0420] (Input: user behavior data, output: dynamic advertising content). Specifically, the server collects user behavior data, analyzes it using a sentiment analysis module, and displays appropriate advertising in real time.

[0421] Step 8:

[0422] The user inputs data for making a reservation for a facility or product using the terminal and sends the data to the server.

[0423] (Input: reservation data, Output: sending data to the server) In concrete terms, the user enters the necessary information into the reservation form and sends it to the server.

[0424] Step 9:

[0425] The server saves the received reservation data in the database and notifies the user that the reservation was successful.

[0426] (Input: reservation data, Output: reservation success message). Specifically, the server saves the reservation data in the database and generates a reservation success page to display to the user.

[0427] This allows users to view high-quality content based on positive word-of-mouth, and by receiving advertisements that match their emotions, advertising effectiveness is improved, making it possible to easily reserve facilities and products.

[0428] 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.

[0429] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0430] 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.

[0431] [Second embodiment]

[0432] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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).

[0438] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0443] 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."

[0444] The present invention is a system based on a client-server model, where the server is the central player in collecting data, filtering, generating content, and displaying it, while the terminal functions as an interface with the user. A specific implementation of the present invention will be described below.

[0445] Data collection

[0446] The server first executes a process to automatically retrieve review information from the Internet. The server sends an HTTP request to the website containing the target review information and analyzes the retrieved HTML data. To analyze, it parses the DOM structure of the webpage and extracts the review score and text. All of this information is stored in a database.

[0447] Storage in the database

[0448] The server stores the acquired word-of-mouth information in a database as structured data. Therefore, each piece of word-of-mouth information is organized and stored in the database by fields such as "store name," "product name," "score," and "text." This allows the data to be extracted and analyzed efficiently in later processing.

[0449] Filtering Methods

[0450] The server retrieves reviews from the database and filters out positive reviews (e.g., scores of 4 or higher). Specifically, it loops through all reviews, checks their scores, and extracts only those that meet the criteria. This filtered data is then used as the basis for ranking.

[0451] Creating rankings

[0452] The server creates a ranking based on the filtered reviews. The ranking is sorted by highest score to make it easier to find highly rated stores and products, and the ranking results are used as the basis for generating testimonials.

[0453] Automated content generation

[0454] The server automatically generates store and product descriptions based on the ranked reviews. Using a natural language generation tool, the acquired review text is used as training data to generate high-quality descriptions. These descriptions become the main content displayed to users.

[0455] Website display method

[0456] A user accesses a website from their device and enters a search query. The device sends this search query to the server, which searches the database and returns rankings and testimonials of relevant stores and products. The user can then review this information and view the testimonial page for more detailed information.

[0457] Reservation System

[0458] Users can make reservations directly from the store or product introduction page. They enter the required information (e.g., user ID, reservation time, etc.) into the reservation form and send it to the server. The server stores this information in the reservation database and notifies the user that the reservation was successful.

[0459] Advertisement display

[0460] The server generates appropriate advertisements based on users' interests and search queries and displays them on web pages, generating revenue from these advertisements to ensure the system's sustainable operation.

[0461] As described above, the present invention automatically generates high-quality introductory content using word-of-mouth information, providing users with optimal store and product information. It also realizes monetization through reservations and advertising, providing an efficient and effective media platform.

[0462] The processing flow will be explained below.

[0463] Data collection and storage

[0464] Step 1:

[0465] The server retrieves the review information from the Internet. Specifically, it sends an HTTP request to the website that contains the review information in question and retrieves the HTML data.

[0466] Step 2:

[0467] To analyze the retrieved HTML data, the server parses it into a Document Object Model (DOM) structure, which makes it easier to access each element of the web page.

[0468] Step 3:

[0469] The server extracts review scores and text from the parsed HTML structure, for example by extracting the required data based on specific CSS classes or tags.

[0470] Step 4:

[0471] The server stores the extracted review information (score and text) in a database. Specifically, it stores the data in the appropriate table using an insert statement.

[0472] Data Filtering and Analysis

[0473] Step 5:

[0474] The server retrieves all the reviews stored in the database by executing a query that selects all records from the database.

[0475] Step 6:

[0476] The server analyzes the data and filters out only positive reviews, for example, those with a score of 4 or higher.

[0477] Step 7:

[0478] The server sorts the filtered reviews in order of score and creates a ranking, which allows stores and products to be sorted in descending order of their ratings.

[0479] Automated content generation

[0480] Step 8:

[0481] The server automatically generates store and product descriptions based on the sorted review information. It uses a natural language generation tool (e.g., TextgenRnn) to generate the descriptions using the review text as training data.

[0482] Search and Display

[0483] Step 9:

[0484] A user accesses a website from a terminal and enters a search query.

[0485] Step 10:

[0486] The terminal transmits a search query from the user to the server.

[0487] Step 11:

[0488] The server searches the database based on the submitted search query to retrieve relevant reviews and rankings. The database is searched using an appropriate SQL query.

[0489] Step 12:

[0490] The server converts the search results into HTML format and generates a web page for display to the user.

[0491] Bookings and Advertising

[0492] Step 13:

[0493] When a user makes a reservation directly from a store or product introduction page, the user enters the necessary information (for example, user ID, reservation time, etc.) into a form on the terminal.

[0494] Step 14:

[0495] The terminal transmits the input reservation information to the server.

[0496] Step 15:

[0497] The server stores the received reservation information in the database by executing an insert statement on the reservation table.

[0498] Step 16:

[0499] The server notifies the user that the reservation was successful, and generates a reservation success page and sends it to the terminal for display to the user.

[0500] Step 17:

[0501] The server selects advertising data for displaying appropriate advertisements based on the user's interests and search queries, thereby displaying effective advertisements that attract the user's attention.

[0502] In this way, this system automatically generates high-quality content based on word-of-mouth information, providing optimal information to users, and also realizing monetization through reservations and advertising.

[0503] Example 1

[0504] 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."

[0505] Currently, many users are seeking reliable word-of-mouth information via the Internet, but collecting and organizing information is cumbersome, and finding the right information requires a great deal of effort. Another issue is the lack of systems that can quickly and accurately provide users with the information they are looking for. Additionally, the process of finding information about stores and products that users are truly interested in and making reservations based on that information is also cumbersome. Furthermore, in order to ensure profits, system operators need a way to efficiently display advertisements based on users' interests.

[0506] 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.

[0507] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering positive word-of-mouth information, means for automatically generating store or product descriptions based on the filtered word-of-mouth information, means for displaying the generated descriptions on a website, means for a user to access the website from a terminal and input a search query, means for the user to display rankings and descriptions of relevant stores or products based on the search query, means for displaying advertisements based on the ranked word-of-mouth information, means for inputting information required for a reservation form and transmitting it to the server, and means for notifying the user that the reservation was successful. This allows the information desired by the user to be provided quickly and accurately, enabling easy reservation, and also enables efficient advertisement display to ensure profits for the system operator.

[0508] "Word-of-mouth information" refers to the evaluations and impressions of users on the Internet, including opinions and evaluations of specific products and services.

[0509] A "database" is a collection of systematically organized data that has a structure that allows specific information to be searched and extracted from it.

[0510] "Filtering" refers to the process of selecting data that meets specific conditions from the acquired data.

[0511] An "introduction" is a text that explains a store or product, and conveys its features and advantages to users in an easy-to-understand manner.

[0512] A "website" is a collection of information published on the Internet that users can access using a web browser.

[0513] A "search query" is a keyword or phrase that a user enters to search for information within a search engine or a particular website.

[0514] A "ranking" is a list in which multiple objects are evaluated and ranked based on certain criteria.

[0515] An "advertisement" is a message or visual that promotes a particular product or service and is displayed on a web page to attract a user's attention.

[0516] A "reservation" is a procedure for reserving a store or service date and time in advance.

[0517] A "generative AI model" is an artificial intelligence system that learns from large amounts of data to generate and understand natural language, and specifically refers to a language model.

[0518] A "prompt" is input text given to a generative AI model to request a specific output.

[0519] "User" refers to an individual or corporation that uses this system, and is primarily someone who accesses it via the Internet.

[0520] A "terminal" is a device that a user uses to connect to the Internet to obtain information and perform operations.

[0521] A "server" is a computer system that manages data on a network and provides services to multiple users.

[0522] The present invention is a system based on a client-server model, where the server is the central player in data collection, filtering, content generation, and display, while the terminals act as the interface with the user.

[0523] First, the server collects review information from the Internet. Specifically, the server sends an HTTP request to a specific review site and analyzes the HTML data it retrieves. This analysis is performed using Python and BeautifulSoup. The server then parses the HTML data, extracts the review scores and text, and stores the organized data in a database. MySQL is used for database management.

[0524] Next, the server retrieves the reviews from the database and filters out the positive reviews. The filtering criteria is to extract reviews with a score of 4 or higher. This operation is performed using SQLAlchemy. After the data is filtered, the server creates a ranking based on the results. The ranking is sorted by highest score, making it easier for users to find highly rated stores and products. This is done using Python's sorting function.

[0525] The server then generates store and product descriptions based on the ranking results. This process uses a generative AI model (e.g., GPT-3) and uses the review text as training data. An example of a prompt for generation is: "Generate a high-quality store description based on the following review data: {review text}." The generated description is stored in a database and displayed on the website.

[0526] A user accesses a website from a device and enters a search query. The device sends the search query to the server, which searches the database and returns rankings and reviews of relevant stores and products to the device. This information is then displayed to the user through a web browser.

[0527] Users can also make reservations directly from the introduction page. After entering the necessary information into the reservation form and sending it to the server, the server stores this information in the reservation database and notifies the user that the reservation was successful. This also involves database operations such as SQL.

[0528] Finally, the server displays appropriate advertisements based on the user's interests and search queries. The server analyzes the user's search history and other factors to select and display the most relevant advertisements on the web page. Revenue generated from these advertisements allows the system to operate sustainably.

[0529] The present invention allows users to quickly and accurately receive the information they require, and simplifies the reservation process. Furthermore, efficient advertising display also enables monetization, making it possible to provide effective services.

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

[0531] Step 1:

[0532] The server collects reviews from the Internet.

[0533] Input: URL of the target review site.

[0534] Output: HTML data.

[0535] Specific behavior:

[0536] The server executes "requests.get(URL)" to retrieve the HTML of the target page.

[0537] The server parses the HTML using "BeautifulSoup(html, 'html.parser')".

[0538] The server navigates the DOM tree and extracts the review data using the "find_all" method.

[0539] Step 2:

[0540] The server stores the extracted word-of-mouth information in a database.

[0541] Input: Extracted review score and text.

[0542] Output: Structured data stored in a database.

[0543] Specific behavior:

[0544] The server inserts the data into the database using the SQL query "INSERT INTO Reviews (store_name, product_name, score, text) VALUES ...".

[0545] The server manages these operations using a database connectivity library (e.g., SQLAlchemy).

[0546] Step 3:

[0547] The server retrieves review information from the database and filters out positive reviews.

[0548] Input: Reviews in the database.

[0549] Output: Filtered review data that meets the criteria.

[0550] Specific behavior:

[0551] The server executes "SELECT FROM Reviews WHERE score >= 4" and retrieves data that meets the condition.

[0552] The server stores the retrieved data in a list or other suitable data structure for further processing.

[0553] Step 4:

[0554] The server creates a ranking based on the filtered word-of-mouth information.

[0555] Input: Filtered review data.

[0556] Output: Data organized in a ranking format.

[0557] Specific behavior:

[0558] The server sorts the data in a way like "sorted(reviews, key=lambda x: x['score'], reverse=True)".

[0559] The server stores the sorted data in a ranking format.

[0560] Step 5:

[0561] The server generates store and product descriptions based on the ranking data.

[0562] Input: Ranked reviews.

[0563] Output: Generated store and product descriptions.

[0564] Specific behavior:

[0565] The server sends a prompt to the "generative AI model" and generates an introduction in response.

[0566] Example: "Generate high-quality store descriptions based on the following review data: {review text}"

[0567] The server stores the generated testimonial in a database.

[0568] Step 6:

[0569] A user accesses a website from a terminal and enters a search query.

[0570] Input: Search query.

[0571] Output: Rankings and descriptions of stores and products displayed as search results.

[0572] Specific behavior:

[0573] A user enters a query into a search form in a web browser and clicks "Submit."

[0574] The device sends the search query to the server as a POST request.

[0575] The server searches the database and returns matching data in HTML format.

[0576] The device displays the received HTML in the browser.

[0577] Step 7:

[0578] Users can make reservations directly from the referral page.

[0579] Input: Information entered into the reservation form (e.g., user ID, reservation time, etc.).

[0580] Output: Notification that the reservation was successful.

[0581] Specific behavior:

[0582] The user fills in the reservation form and clicks the "Book" button.

[0583] The terminal sends the input information to the server as a POST request.

[0584] The server stores this information in the reservation database as "INSERT INTO Reservations (user_id, reservation_time, ...) VALUES ...".

[0585] The server generates a message confirming successful reservation and returns it to the user.

[0586] Step 8:

[0587] The server displays appropriate advertisements based on the user's interests and search queries.

[0588] Input: User search queries and browsing history.

[0589] Output: Relevant ads.

[0590] Specific behavior:

[0591] The server analyzes search queries and browsing history and selects relevant advertisements from a database.

[0592] The server embeds the selected advertisement into HTML and returns it to the user.

[0593] (Application example 1)

[0594] 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."

[0595] In recent years, consumer decision-making based on word-of-mouth information has been increasing, but there are currently no systems in place that can efficiently collect this information and present it to users in an appropriate format. There is also a need to utilize this word-of-mouth information to enable users to easily make reservations and purchases. Furthermore, there is a need to display advertisements based on user behavior and interests, thereby generating revenue. Conventional systems face the challenge of being unable to meet these multiple requirements.

[0596] 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.

[0597] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering out positive word-of-mouth information, means for automatically generating store or product descriptions based on the filtered word-of-mouth information, means for displaying the generated description on a website, means for displaying the generated description on a smartphone application, means for users to make reservations through the application, and means for displaying advertisements based on the user's interests and behavior. This not only enables efficient collection and presentation of word-of-mouth information, allowing users to easily make reservations and purchases, but also enables monetization through the display of advertisements.

[0598] "Word-of-mouth information" refers to reviews and opinions about stores and products provided by users on the Internet.

[0599] A "database" is a data storage system for structuring and storing collected word-of-mouth information.

[0600] "Filtering" refers to the process of selecting only information that meets specific conditions from collected word-of-mouth information.

[0601] "Positive reviews" are reviews that show favorable evaluations, many of which are accompanied by high scores.

[0602] An "introduction" is a text automatically generated based on filtered word-of-mouth information, which explains the features of the store or product.

[0603] A "website" is a collection of information accessible to users over the Internet, identified by a particular URL.

[0604] A "smartphone application" is a program that runs on a smartphone and allows users to use specific functions through an interface.

[0605] "Reservation" means that a user applies in advance for a particular service or product.

[0606] "Advertisement" means a commercial message displayed based on a user's interests or behavior, which is intended to promote a particular product or service.

[0607] "Server" means a central management system that collects, stores, processes, and distributes data, and serves to provide data to terminals that interface with users.

[0608] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0609] System Configuration

[0610] This invention consists of a server and a user terminal. The server collects, stores, and filters reviews, automatically generates and displays testimonials, and manages reservations and advertisements. Meanwhile, users access these functions using a smartphone application.

[0611] Hardware and software used

[0612] Server: Node.js and Express.js are used for server-side processing. MongoDB is used as the database.

[0613] Natural language generation: Utilizing the OpenAI API, we generate testimonials based on reviews.

[0614] Front-end: Develop a smartphone application using React Native.

[0615] Data processing and calculation

[0616] Data collection

[0617] The server collects review information from review websites on the Internet by sending HTTP requests to retrieve the target HTML data and then performing DOM analysis to extract review text and scores.

[0618] Storage in the database

[0619] The collected reviews are stored in an organized format in a MongoDB database, allowing for efficient subsequent filtering and ranking.

[0620] filtering

[0621] The server filters the reviews retrieved from the database for positive reviews with high scores, using MongoDB's query function for this process.

[0622] Creating rankings

[0623] A ranking is created based on the filtered reviews. The reviews are sorted in descending order of score, and highly rated stores and products are extracted.

[0624] Automated content generation

[0625] Using the OpenAI API, a natural language generation tool, we automatically generate high-quality testimonials based on the ranked reviews, which then become the main content displayed to users.

[0626] Website display and smartphone application display

[0627] The generated introduction is sent from the server to the device and displayed on the website and smartphone application, which uses React Native to provide the interface.

[0628] Reservation System

[0629] Users can access store and product introduction pages from their smartphone application and make reservations. The information required for the reservation is sent to the server and stored in a reservation database.

[0630] Advertisement display

[0631] The server automatically generates advertisements based on the user's interests and behavior and displays them on the application. Revenue from these advertisements enables the system to operate sustainably.

[0632] Specific examples

[0633] For example, if a user opens the application and searches for "pasta restaurant," the server retrieves reviews of highly rated pasta restaurants from the database, creates a ranking, and then uses the OpenAI API to generate a review based on the following prompt:

[0634] Generate engaging restaurant descriptions for your users based on the following reviews:

[0635] Review 1: "The pasta was amazing, especially the carbonara."

[0636] Review 2: "The staff were very friendly and I had a great time."

[0637] The generated introduction is displayed on the smartphone application, and users can make reservations based on that information.

[0638] The above is a specific embodiment for carrying out the present invention.

[0639] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0640] Step 1:

[0641] The server collects review information from the Internet. The server sends an HTTP request to retrieve HTML data from the target website. It analyzes this HTML data and extracts review text and scores. The input is review information from the Internet, and the output is the extracted review text and scores.

[0642] Step 2:

[0643] The server stores the extracted review information in a database. The database uses MongoDB, and stores the review information organized by fields such as "store name," "product name," "score," and "text." The input is the review information extracted in step 1, and the output is a structured database entry.

[0644] Step 3:

[0645] The server retrieves reviews from the database and filters out positive reviews. The server uses MongoDB's query function to select reviews with a score of 4 or higher. The input is all reviews in the database, and the output is the positive reviews that match the criteria.

[0646] Step 4:

[0647] The server creates a ranking based on the filtered reviews. It sorts the positive reviews in descending order of score and extracts highly rated stores and products. The input is the reviews filtered in step 3, and the output is ranked data.

[0648] Step 5:

[0649] The server automatically generates store or product descriptions based on the ranked reviews. Using OpenAI's API, the review information is used as training data to generate high-quality descriptions. The input is the ranking data from Step 4 and a prompt for the AI ​​model, and the output is the generated description.

[0650] Step 6:

[0651] The server displays the generated testimonial on the smartphone application. The generated testimonial is sent to a smartphone app using React Native and displayed to the user. The input is the testimonial generated in step 5, and the output is the visualized testimonial on the application.

[0652] Step 7:

[0653] A user makes a reservation through an application. The user enters the required information into a reservation form from the application and submits it to the server. The server stores this information in a reservation database and notifies the user of a reservation confirmation. The input is the reservation information entered by the user, and the output is a reservation entry in the database and a confirmation to the user.

[0654] Step 8:

[0655] The server displays advertisements based on the user's interests and behavior. Based on the user's search query and browsing history, appropriate advertisements are selected and displayed on the smartphone application. The input is user behavior data and advertisement information from an advertisement database, and the output is the displayed advertisement.

[0656] 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.

[0657] The present invention is a system based on a client-server model, where the server is the central player in collecting data, filtering, generating content, and displaying it, while the terminal functions as an interface with the user. A specific implementation of the present invention will be described below.

[0658] Data collection and storage

[0659] The server automatically retrieves review information from the Internet. Specifically, it sends an HTTP request to the website containing the target review information and retrieves the HTML data. It then analyzes the HTML data, parses it into a DOM structure, and extracts the review score and text. The extracted review information is then stored in a database.

[0660] Data Filtering and Analysis

[0661] The server retrieves all reviews from the database and filters out positive reviews (e.g., scores of 4 or higher). The filtered reviews are sorted by score and stored as rankings.

[0662] Automated content generation

[0663] The server automatically generates store and product descriptions based on the ranked reviews. It uses a natural language generation tool to generate high-quality descriptions using the acquired review text as training data.

[0664] Search and Display

[0665] A user accesses a website from a terminal and enters a search query. The terminal sends the search query to the server, which searches the database to obtain relevant reviews and rankings, and generates a web page to display to the user. The user then browses the reviews displayed as search results.

[0666] Emotion engine integration

[0667] The server integrates an emotion engine into the review information collection and filtering process. It performs sentiment analysis on the review data and prioritizes filtering of reviews with positive sentiment. This procedure allows the server to provide more reliable and useful information to users.

[0668] The emotion engine also analyzes word-of-mouth information related to search queries from devices, and prioritizes displaying information with positive sentiment to users.

[0669] Emotion-based advertising

[0670] The server monitors the user's real-time emotions with an emotion engine and dynamically changes the advertising content based on those emotions, thereby presenting ads that best fit the user's emotional state and improving advertising effectiveness.

[0671] Reservation System

[0672] Users can make reservations directly from the store or product introduction page. They enter the required information (e.g., user ID, reservation time, etc.) into the form on their terminal and send it to the server. The server stores the received reservation information in a database and notifies the user that the reservation was successful. A reservation success page is generated and displayed to the user.

[0673] Specific examples of processing

[0674] For example, when a user searches for a restaurant, the server collects reviews of that restaurant and analyzes them using an emotion engine. It filters out only the positive reviews and automatically generates a review based on them. When a user enters a search query about a specific dish, the server prioritizes the display of positive reviews related to the query.

[0675] In this way, this system automatically generates high-quality content based on word-of-mouth information and provides users with the most appropriate information. In addition, by integrating an emotion engine, it is possible to provide more reliable information and improve advertising effectiveness.

[0676] The processing flow will be explained below.

[0677] Processing steps of a system that combines emotion engines

[0678] Step 1:

[0679] The server retrieves review information from the Internet. Specifically, it sends an HTTP request to the target review site and retrieves the HTML data.

[0680] Step 2:

[0681] The server parses the HTML data and parses it into a DOM structure to extract review scores and text, using specific CSS selectors and tags to identify the data it needs.

[0682] Step 3:

[0683] The server stores the extracted word-of-mouth information in a database, which contains fields such as "store name," "product name," "score," and "text."

[0684] Step 4:

[0685] The server retrieves all reviews from the database and uses an appropriate SQL query to select all records.

[0686] Step 5:

[0687] The server analyzes the acquired reviews using a sentiment engine and adds a sentiment score. The sentiment engine analyzes the text of each review and generates a sentiment score such as positive, negative, or neutral.

[0688] Step 6:

[0689] The server filters the reviews based on the sentiment score, specifically selecting reviews with a positive sentiment score (e.g., a score of 4 or higher).

[0690] Step 7:

[0691] The server sorts the filtered reviews by score and creates a ranking, which results in a list of stores and products with the highest ratings.

[0692] Step 8:

[0693] The server automatically generates store and product descriptions based on the ranked reviews. It uses a natural language generation tool to generate high-quality descriptions using the review text as training data.

[0694] Step 9:

[0695] A user accesses a website from a device and enters a search query, which may be for a specific store or product.

[0696] Step 10:

[0697] The device sends a search query to the server, which passes the query entered by the user to the server.

[0698] Step 11:

[0699] The server searches the database based on the search query to retrieve relevant reviews and rankings. The search results include reviews that are recognized as positive by the sentiment engine.

[0700] Step 12:

[0701] The server generates a web page based on the search results to display to the user, including the generated testimonial and ranking information.

[0702] Step 13:

[0703] The user can view the displayed introductions and rankings, and check detailed store and product information as needed. Specifically, they can access the introduction page.

[0704] Step 14:

[0705] Users make reservations directly from the store or product introduction page, entering necessary information such as user ID and reservation time into the reservation form.

[0706] Step 15:

[0707] The terminal sends the entered reservation information to the server. When the user submits the form, the reservation request is passed to the server.

[0708] Step 16:

[0709] The server stores the received reservation information in the database and executes an SQL query to insert the reservation information into the reservation table.

[0710] Step 17:

[0711] The server notifies the user that the reservation was successful by generating a reservation success page and sending it to the terminal.

[0712] Step 18:

[0713] The server monitors the user's emotions in real time and displays appropriate advertisements based on those emotions. The emotion engine analyzes the user's emotions and dynamically changes the advertisement content.

[0714] In this way, the system generates high-quality content based on word-of-mouth information and user sentiment analysis, providing optimal information to users and generating revenue.

[0715] Example 2

[0716] 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."

[0717] Conventional word-of-mouth information collection systems have had the problem of not being able to adequately evaluate or filter the collected word-of-mouth information, making it difficult to provide useful information to users. Furthermore, since they do not evaluate word-of-mouth information using an emotion engine or dynamically display advertisements based on the user's emotional state, it has been impossible to improve the reliability of word-of-mouth information or the effectiveness of advertisements.

[0718] 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.

[0719] In this invention, the server includes a means for collecting word-of-mouth information from the Internet, a means for storing the collected word-of-mouth information in a database, and a means for retrieving word-of-mouth information from the database and filtering out positive reviews. This makes it possible to provide users with highly reliable, positive word-of-mouth information. Furthermore, the server also includes a means for evaluating word-of-mouth information and user search queries using a sentiment analysis engine and preferentially displaying positive information, a means for dynamically changing advertisements based on the user's emotional state, a means for notifying the user based on the results of the sentiment analysis by the sentiment engine, and a means for generating testimonials using a generative AI model, thereby improving the reliability of word-of-mouth information and advertising effectiveness.

[0720] "Word-of-mouth information" refers to information posted online by ordinary consumers that includes their evaluations and opinions about products and services.

[0721] A "database" is a digital storage system for systematically storing and managing collected word-of-mouth information.

[0722] "Filtering" is the process of selecting collected word-of-mouth information that meets specific criteria (e.g., positive reviews).

[0723] "Automatic generation" is the process of generating text or content using a computer program without human intervention.

[0724] "Display" refers to the act of visually presenting the generated testimonials and filtered word-of-mouth information to the user.

[0725] A "sentiment analysis engine" is software that automatically evaluates the sentiment (positive, negative, neutral, etc.) of text data.

[0726] "Advertisement" refers to content that presents information about products or services to users for promotional purposes.

[0727] A "generative AI model" is a trained model that uses artificial intelligence techniques to generate text or content.

[0728] A "search query" is a keyword or phrase that a user enters into a search engine or system to search for information.

[0729] "Positive reviews" are reviews that have a high rating (e.g., a score of 4 or higher) and contain positive opinions and emotions.

[0730] "Dynamic change" refers to the automatic change of display content and behavior in real time according to conditions.

[0731] MODE FOR CARRYING OUT THE INVENTION

[0732] The present invention is a system based on a client-server model, where the server is the central point responsible for data collection, filtering, content generation and display, while the terminals act as the interface with the user.

[0733] Data collection

[0734] The server collects review information from the Internet. Specifically, it sends an HTTP request to the target website and retrieves the HTML data. This process uses the Apache HttpClient library. The retrieved HTML data is parsed into a DOM structure using JSoup, and the review score and text are extracted.

[0735] Data analysis

[0736] The server analyzes the parsed HTML data using the JSoup library and extracts the review scores and text. The extracted data is stored in a database such as MySQL or PostgreSQL. Data is stored in the database using JDBC.

[0737] Data Filtering

[0738] The server retrieves all reviews from the database and filters out positive reviews (e.g., scores above 4). It uses an SQL query to extract only records that meet the specified criteria. The extracted data is stored as rankings in an in-memory database such as Redis or Elasticsearch.

[0739] Content Generation

[0740] The server automatically generates testimonials based on the filtered review information using a natural language generation model (e.g., GPT-3 or BERT). By using the review text as training data and inputting prompts into the generative AI model, high-quality testimonials are generated.

[0741] Search and Display

[0742] A user accesses a website from a device (e.g., a PC or smartphone) and enters a search query. The device sends this search query to the server, which searches a database to return relevant reviews and rankings, and generates a web page to display to the user. The user can then view the reviews displayed as search results.

[0743] sentiment analysis

[0744] The server uses a sentiment analysis engine (e.g., TextBlob or VADER) to filter reviews. By performing sentiment analysis, it prioritizes filtering of positive reviews and provides reliable information.

[0745] Emotion-based advertising

[0746] The server monitors the user's emotional state in real time and dynamically changes the advertisements based on that emotion. It uses an emotion engine to evaluate the user's emotions and uses Google Ads and Facebook Ads APIs to display the most appropriate advertising content.

[0747] Reservation System

[0748] The user enters the necessary information (e.g., user ID, reservation time, etc.) into the form on the terminal and sends it to the server. The server stores the reservation information in a database and notifies the user that the reservation was successful. A reservation success page is also generated at the same time and displayed to the user.

[0749] Prompt Sentence Examples

[0750] "Generate testimonials with positive reviews for this restaurant. The reviews are: [list of reviews]"

[0751] "Please suggest optimal ad content based on the user's emotional state. The user's emotional state is: [user's emotional data]"

[0752] In this way, this system automatically generates high-quality content based on word-of-mouth information and provides users with the most appropriate information. In addition, by integrating an emotion engine, it provides more reliable information and improves advertising effectiveness.

[0753] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0754] Step 1:

[0755] The server collects reviews from the Internet. As input, it receives the URLs of target websites and sends an HTTP request to retrieve HTML data. Using the Apache HttpClient library, it sends a GET request and receives a response with HTML data. As output, it generates the retrieved HTML data. Specifically, it creates an instance of HttpClient and sends a GET request to the specified URL.

[0756] Step 2:

[0757] The server parses the retrieved HTML data. As input, it receives the HTML data retrieved in step 1 and parses it into a DOM structure using the JSoup library. This allows it to extract review scores and text. As output, it generates a list of the extracted scores and text. Specifically, it extracts review scores and text from the Document object parsed by JSoup using the specified CSS selector.

[0758] Step 3:

[0759] The server stores the extracted review information in a database. As input, it receives the scores and text list extracted in step 2 and stores them in a database such as MySQL or PostgreSQL. It connects to the database using JDBC and inserts the data. As output, review information stored in the database is generated. Specifically, it executes an insert SQL statement using PreparedStatement and stores the review scores and text in the corresponding tables in the database.

[0760] Step 4:

[0761] The server retrieves all reviews from the database and filters out the positive ones. As input, it takes all reviews stored in the database and executes a SQL query to filter reviews with a score of 4 or higher. As output, it generates a list of reviews that are determined to be positive. Specifically, it uses a Statement object to execute a SELECT query and extracts records that match the criteria.

[0762] Step 5:

[0763] The server automatically generates testimonials using a generative AI model based on the filtered reviews. As input, it receives a list of filtered reviews and generates a prompt. The testimonials are generated using natural language generation models such as GPT-3 and BERT. As output, a high-quality testimonial is generated. Specifically, the prompt is input to the generative AI model and the generated text is obtained as a response.

[0764] Step 6:

[0765] A user accesses a website from a terminal and enters a search query. The search query entered by the user is received as input and sent to the server. The terminal then sends the search query to the server as a POST request. As output, the search results are displayed to the user. Specifically, the system retrieves the search query from an HTML form and generates an HTTP request to send to the server.

[0766] Step 7:

[0767] The server uses a sentiment analysis engine to evaluate reviews and search queries. As input, it receives collected reviews and search queries from users, and calculates a sentiment score using a sentiment analysis library such as TextBlob or VADER. As output, information rated as positive is displayed preferentially. Specifically, text is input into the analysis library, its sentiment score is calculated, and filtering is performed.

[0768] Step 8:

[0769] The server dynamically changes ads based on the user's emotional state. It receives user emotional data as input and dynamically selects ad content. It uses Google Ads or Facebook Ads API to retrieve and display the most suitable ad. The output is an ad optimized for the user's emotions. Specifically, it calls the advertising API based on the user's emotional data and renders the retrieved ad data for display.

[0770] Step 9:

[0771] A user makes a reservation through a website. As input, the information entered by the user in the reservation form (user ID, reservation time, etc.) is received and sent to the server. The server stores this information in a database and notifies the user of the reservation result. As output, a notification that the reservation was successful is displayed to the user. Specifically, the system retrieves information from the reservation form, generates an HTTP request to send to the server, stores the information in the database on the server side, and then generates a response notifying the result.

[0772] (Application example 2)

[0773] 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."

[0774] Conventional review information collection systems only filter positive reviews and are unable to provide optimal information based on the user's emotional state. Furthermore, they are unable to centrally handle facility and product reservation functions, limiting the user experience. This has created challenges in effectively utilizing review information and improving user convenience.

[0775] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0776] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering out positive word-of-mouth information, means for automatically generating a facility or product introduction text based on the filtered word-of-mouth information, means for displaying the generated text on a website, means for dynamically displaying advertisements that are optimal for the user's emotional state using a sentiment analysis module, and means for receiving data for making reservations for facilities or products from a terminal and storing the data in the database. This allows users to view high-quality content based on positive word-of-mouth information, and by receiving advertisements that are tailored to their emotions, the effectiveness of the advertisements is improved, making it possible for users to easily make reservations for facilities or products.

[0777] "Word-of-mouth information" is data that includes user ratings and opinions posted on the Internet.

[0778] A "database" is a system for storing and managing data in a structured way.

[0779] "Positive reviews" are reviews with favorable content that have a rating above a certain score.

[0780] "Filtering" is a method of selecting data based on specific conditions.

[0781] "Facility or product introduction text" is a description of a facility or product that is automatically generated based on filtered word-of-mouth information.

[0782] A "sentiment analysis module" is a software component for detecting and classifying emotions from text data.

[0783] "Dynamic display of advertisements" means that advertisement content is displayed while changing in response to the user's real-time emotional state.

[0784] "Data for reserving a facility or product" refers to information required when a user makes a reservation (e.g., user ID, reservation time, etc.).

[0785] A "terminal" is a computing device through which a user accesses the Internet.

[0786] MODE FOR CARRYING OUT THE INVENTION

[0787] System Overview

[0788] The system for implementing this invention collects word-of-mouth information, filters it, analyzes its sentiment, generates content, and displays it on a user terminal. The system is mainly composed of a server, a database, a sentiment analysis module, and a user terminal.

[0789] Hardware and software used

[0790] Server: Cloud server such as AWS EC2

[0791] Database: SQLite or AWS RDS

[0792] Sentiment analysis module: TextBlob or AWS Comprehend

[0793] Scraping tool: BeautifulSoup

[0794] User interface: Web browser or smartphone application (e.g., Flask)

[0795] Processing flow

[0796] Server-side processing

[0797] The server collects reviews from the Internet and stores them in a database. Specifically, it uses BeautifulSoup to retrieve HTML data from target websites, parses the data, and extracts review information. The extracted reviews are then stored in a structured format in the database.

[0798] The server retrieves the reviews from the database and uses TextBlob to filter the positive reviews. The positive reviews are sorted by score and stored as a ranking. Furthermore, it utilizes a sentiment analysis module to monitor the user's emotional state and dynamically change the advertising content based on the user's emotion.

[0799] Processing on the user terminal side

[0800] A user inputs a search query through a website or smartphone application. The input query is sent to a server, which retrieves related reviews and generated introductory text and displays them to the user. The user can then use the displayed reviews and introductory text to check details about the facility or product and view advertisements. Furthermore, the user can also make reservations for the facility or product within the application.

[0801] Specific examples

[0802] For example, when a user searches for a restaurant, the server collects reviews related to that restaurant and performs sentiment analysis. It filters out only positive reviews and automatically generates high-quality restaurant descriptions based on that information. When a user enters a search query about a specific dish, the server prioritizes displaying related positive reviews.

[0803] Prompt Sentence Examples

[0804] Filter reviews with positive sentiment from word of mouth information and generate high-quality descriptions of restaurants and dishes. The filtered information format is: [restaurant name, score, review text].

[0805] This system allows users to view high-quality content based on positive word-of-mouth, and by displaying advertisements that are tailored to their emotions, advertising effectiveness is improved, making it possible to easily reserve facilities and products.

[0806] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0807] Step 1:

[0808] The server collects reviews from the target website. Specifically, the server sends an HTTP request and receives the website's HTML data.

[0809] (Input: URL, Output: HTML data). Analyze the received HTML data using BeautifulSoup and extract the reviews.

[0810] (Input: HTML data, Output: Reviews).

[0811] Step 2:

[0812] The server stores the extracted reviews in a structured format in a database.

[0813] (Input: review information, output: data stored in a database). Specifically, the server connects to a database such as SQLite and inserts the review information into a table.

[0814] Step 3:

[0815] The server retrieves reviews from the database and filters out positive reviews using a sentiment analysis module (e.g., TextBlob).

[0816] (Input: review information in the database, Output: positive reviews). The server calculates a sentiment score for each review using TextBlob and extracts only reviews with a positive score (e.g., 4 or higher).

[0817] Step 4:

[0818] The server automatically generates facility or product introduction text based on the filtered reviews.

[0819] (Input: positive reviews, Output: introduction text for the facility or product). Specifically, the server uses a natural language generation tool (e.g., a generative AI model) to automatically generate high-quality introduction text. An example of a prompt is as follows:

[0820] Filter reviews with positive sentiment from word of mouth information and generate high-quality descriptions of restaurants and dishes. The filtered information format is: [restaurant name, score, review text].

[0821] Step 5:

[0822] A user uses a device to enter a search query through a website or smartphone application

[0823] (Input: search query, output: sending query to server). Specifically, the device accepts user input and sends the search query to the server.

[0824] Step 6:

[0825] The server retrieves relevant reviews and generated testimonials from a database based on the received search query and generates a web page to display to the user.

[0826] (Input: search query, output: search result page). Specifically, the server queries the database for relevant information and generates it as an HTML page.

[0827] Step 7:

[0828] The server utilizes a sentiment analysis module to monitor the user's emotional state and dynamically change the advertising content based on the emotional state.

[0829] (Input: user behavior data, output: dynamic advertising content). Specifically, the server collects user behavior data, analyzes it using a sentiment analysis module, and displays appropriate advertising in real time.

[0830] Step 8:

[0831] The user inputs data for making a reservation for a facility or product using the terminal and sends the data to the server.

[0832] (Input: reservation data, Output: sending data to the server) In concrete terms, the user enters the necessary information into the reservation form and sends it to the server.

[0833] Step 9:

[0834] The server saves the received reservation data in the database and notifies the user that the reservation was successful.

[0835] (Input: reservation data, Output: reservation success message). Specifically, the server saves the reservation data in the database and generates a reservation success page to display to the user.

[0836] This allows users to view high-quality content based on positive word-of-mouth, and by receiving advertisements that match their emotions, advertising effectiveness is improved, making it possible to easily reserve facilities and products.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] [Third embodiment]

[0841] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0842] 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.

[0843] 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).

[0844] 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.

[0845] 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.

[0846] 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).

[0847] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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."

[0853] The present invention is a system based on a client-server model, where the server is the central player in collecting data, filtering, generating content, and displaying it, while the terminal functions as an interface with the user. A specific implementation of the present invention will be described below.

[0854] Data collection

[0855] The server first executes a process to automatically retrieve review information from the Internet. The server sends an HTTP request to the website containing the target review information and analyzes the retrieved HTML data. To analyze, it parses the DOM structure of the webpage and extracts the review score and text. All of this information is stored in a database.

[0856] Storage in the database

[0857] The server stores the acquired word-of-mouth information in a database as structured data. Therefore, each piece of word-of-mouth information is organized and stored in the database by fields such as "store name," "product name," "score," and "text." This allows the data to be extracted and analyzed efficiently in later processing.

[0858] Filtering Methods

[0859] The server retrieves reviews from the database and filters out positive reviews (e.g., scores of 4 or higher). Specifically, it loops through all reviews, checks their scores, and extracts only those that meet the criteria. This filtered data is then used as the basis for ranking.

[0860] Creating rankings

[0861] The server creates a ranking based on the filtered reviews. The ranking is sorted by highest score to make it easier to find highly rated stores and products, and the ranking results are used as the basis for generating testimonials.

[0862] Automated content generation

[0863] The server automatically generates store and product descriptions based on the ranked reviews. Using a natural language generation tool, the acquired review text is used as training data to generate high-quality descriptions. These descriptions become the main content displayed to users.

[0864] Website display method

[0865] A user accesses a website from their device and enters a search query. The device sends this search query to the server, which searches the database and returns rankings and testimonials of relevant stores and products. The user can then review this information and view the testimonial page for more detailed information.

[0866] Reservation System

[0867] Users can make reservations directly from the store or product introduction page. They enter the required information (e.g., user ID, reservation time, etc.) into the reservation form and send it to the server. The server stores this information in the reservation database and notifies the user that the reservation was successful.

[0868] Advertisement display

[0869] The server generates appropriate advertisements based on users' interests and search queries and displays them on web pages, generating revenue from these advertisements to ensure the system's sustainable operation.

[0870] As described above, the present invention automatically generates high-quality introductory content using word-of-mouth information, providing users with optimal store and product information. It also realizes monetization through reservations and advertising, providing an efficient and effective media platform.

[0871] The processing flow will be explained below.

[0872] Data collection and storage

[0873] Step 1:

[0874] The server retrieves the review information from the Internet. Specifically, it sends an HTTP request to the website that contains the review information in question and retrieves the HTML data.

[0875] Step 2:

[0876] To analyze the retrieved HTML data, the server parses it into a Document Object Model (DOM) structure, which makes it easier to access each element of the web page.

[0877] Step 3:

[0878] The server extracts review scores and text from the parsed HTML structure, for example by extracting the required data based on specific CSS classes or tags.

[0879] Step 4:

[0880] The server stores the extracted review information (score and text) in a database. Specifically, it stores the data in the appropriate table using an insert statement.

[0881] Data Filtering and Analysis

[0882] Step 5:

[0883] The server retrieves all the reviews stored in the database by executing a query that selects all records from the database.

[0884] Step 6:

[0885] The server analyzes the data and filters out only positive reviews, for example, those with a score of 4 or higher.

[0886] Step 7:

[0887] The server sorts the filtered reviews in order of score and creates a ranking, which allows stores and products to be sorted in descending order of their ratings.

[0888] Automated content generation

[0889] Step 8:

[0890] The server automatically generates store and product descriptions based on the sorted review information. It uses a natural language generation tool (e.g., TextgenRnn) to generate the descriptions using the review text as training data.

[0891] Search and Display

[0892] Step 9:

[0893] A user accesses a website from a terminal and enters a search query.

[0894] Step 10:

[0895] The terminal transmits a search query from the user to the server.

[0896] Step 11:

[0897] The server searches the database based on the submitted search query to retrieve relevant reviews and rankings. The database is searched using an appropriate SQL query.

[0898] Step 12:

[0899] The server converts the search results into HTML format and generates a web page for display to the user.

[0900] Bookings and Advertising

[0901] Step 13:

[0902] When a user makes a reservation directly from a store or product introduction page, the user enters the necessary information (for example, user ID, reservation time, etc.) into a form on the terminal.

[0903] Step 14:

[0904] The terminal transmits the input reservation information to the server.

[0905] Step 15:

[0906] The server stores the received reservation information in the database by executing an insert statement on the reservation table.

[0907] Step 16:

[0908] The server notifies the user that the reservation was successful, and generates a reservation success page and sends it to the terminal for display to the user.

[0909] Step 17:

[0910] The server selects advertising data for displaying appropriate advertisements based on the user's interests and search queries, thereby displaying effective advertisements that attract the user's attention.

[0911] In this way, this system automatically generates high-quality content based on word-of-mouth information, providing optimal information to users, and also realizing monetization through reservations and advertising.

[0912] Example 1

[0913] 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."

[0914] Currently, many users are seeking reliable word-of-mouth information via the Internet, but collecting and organizing information is cumbersome, and finding the right information requires a great deal of effort. Another issue is the lack of systems that can quickly and accurately provide users with the information they are looking for. Additionally, the process of finding information about stores and products that users are truly interested in and making reservations based on that information is also cumbersome. Furthermore, in order to ensure profits, system operators need a way to efficiently display advertisements based on users' interests.

[0915] 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.

[0916] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering positive word-of-mouth information, means for automatically generating store or product descriptions based on the filtered word-of-mouth information, means for displaying the generated descriptions on a website, means for a user to access the website from a terminal and input a search query, means for the user to display rankings and descriptions of relevant stores or products based on the search query, means for displaying advertisements based on the ranked word-of-mouth information, means for inputting information required for a reservation form and transmitting it to the server, and means for notifying the user that the reservation was successful. This allows the information desired by the user to be provided quickly and accurately, enabling easy reservation, and also enables efficient advertisement display to ensure profits for the system operator.

[0917] "Word-of-mouth information" refers to the evaluations and impressions of users on the Internet, including opinions and evaluations of specific products and services.

[0918] A "database" is a collection of systematically organized data that has a structure that allows specific information to be searched and extracted from it.

[0919] "Filtering" refers to the process of selecting data that meets specific conditions from the acquired data.

[0920] An "introduction" is a text that explains a store or product, and conveys its features and advantages to users in an easy-to-understand manner.

[0921] A "website" is a collection of information published on the Internet that users can access using a web browser.

[0922] A "search query" is a keyword or phrase that a user enters to search for information within a search engine or a particular website.

[0923] A "ranking" is a list in which multiple objects are evaluated and ranked based on certain criteria.

[0924] An "advertisement" is a message or visual that promotes a particular product or service and is displayed on a web page to attract a user's attention.

[0925] A "reservation" is a procedure for reserving a store or service date and time in advance.

[0926] A "generative AI model" is an artificial intelligence system that learns from large amounts of data to generate and understand natural language, and specifically refers to a language model.

[0927] A "prompt" is input text given to a generative AI model to request a specific output.

[0928] "User" refers to an individual or corporation that uses this system, and is primarily someone who accesses it via the Internet.

[0929] A "terminal" is a device that a user uses to connect to the Internet to obtain information and perform operations.

[0930] A "server" is a computer system that manages data on a network and provides services to multiple users.

[0931] The present invention is a system based on a client-server model, where the server is the central player in data collection, filtering, content generation, and display, while the terminals act as the interface with the user.

[0932] First, the server collects review information from the Internet. Specifically, the server sends an HTTP request to a specific review site and analyzes the HTML data it retrieves. This analysis is performed using Python and BeautifulSoup. The server then parses the HTML data, extracts the review scores and text, and stores the organized data in a database. MySQL is used for database management.

[0933] Next, the server retrieves the reviews from the database and filters out the positive reviews. The filtering criteria is to extract reviews with a score of 4 or higher. This operation is performed using SQLAlchemy. After the data is filtered, the server creates a ranking based on the results. The ranking is sorted by highest score, making it easier for users to find highly rated stores and products. This is done using Python's sorting function.

[0934] The server then generates store and product descriptions based on the ranking results. This process uses a generative AI model (e.g., GPT-3) and uses the review text as training data. An example of a prompt for generation is: "Generate a high-quality store description based on the following review data: {review text}." The generated description is stored in a database and displayed on the website.

[0935] A user accesses a website from a device and enters a search query. The device sends the search query to the server, which searches the database and returns rankings and reviews of relevant stores and products to the device. This information is then displayed to the user through a web browser.

[0936] Users can also make reservations directly from the introduction page. After entering the necessary information into the reservation form and sending it to the server, the server stores this information in the reservation database and notifies the user that the reservation was successful. This also involves database operations such as SQL.

[0937] Finally, the server displays appropriate advertisements based on the user's interests and search queries. The server analyzes the user's search history and other factors to select and display the most relevant advertisements on the web page. Revenue generated from these advertisements allows the system to operate sustainably.

[0938] The present invention allows users to quickly and accurately receive the information they require, and simplifies the reservation process. Furthermore, efficient advertising display also enables monetization, making it possible to provide effective services.

[0939] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0940] Step 1:

[0941] The server collects reviews from the Internet.

[0942] Input: URL of the target review site.

[0943] Output: HTML data.

[0944] Specific behavior:

[0945] The server executes "requests.get(URL)" to retrieve the HTML of the target page.

[0946] The server parses the HTML using "BeautifulSoup(html, 'html.parser')".

[0947] The server navigates the DOM tree and extracts the review data using the "find_all" method.

[0948] Step 2:

[0949] The server stores the extracted word-of-mouth information in a database.

[0950] Input: Extracted review score and text.

[0951] Output: Structured data stored in a database.

[0952] Specific behavior:

[0953] The server inserts the data into the database using the SQL query "INSERT INTO Reviews (store_name, product_name, score, text) VALUES ...".

[0954] The server manages these operations using a database connectivity library (e.g., SQLAlchemy).

[0955] Step 3:

[0956] The server retrieves review information from the database and filters out positive reviews.

[0957] Input: Reviews in the database.

[0958] Output: Filtered review data that meets the criteria.

[0959] Specific behavior:

[0960] The server executes "SELECT FROM Reviews WHERE score >= 4" and retrieves data that meets the condition.

[0961] The server stores the retrieved data in a list or other suitable data structure for further processing.

[0962] Step 4:

[0963] The server creates a ranking based on the filtered word-of-mouth information.

[0964] Input: Filtered review data.

[0965] Output: Data organized in a ranking format.

[0966] Specific behavior:

[0967] The server sorts the data in a way like "sorted(reviews, key=lambda x: x['score'], reverse=True)".

[0968] The server stores the sorted data in a ranking format.

[0969] Step 5:

[0970] The server generates store and product descriptions based on the ranking data.

[0971] Input: Ranked reviews.

[0972] Output: Generated store and product descriptions.

[0973] Specific behavior:

[0974] The server sends a prompt to the "generative AI model" and generates an introduction in response.

[0975] Example: "Generate high-quality store descriptions based on the following review data: {review text}"

[0976] The server stores the generated testimonial in a database.

[0977] Step 6:

[0978] A user accesses a website from a terminal and enters a search query.

[0979] Input: Search query.

[0980] Output: Rankings and descriptions of stores and products displayed as search results.

[0981] Specific behavior:

[0982] A user enters a query into a search form in a web browser and clicks "Submit."

[0983] The device sends the search query to the server as a POST request.

[0984] The server searches the database and returns matching data in HTML format.

[0985] The device displays the received HTML in the browser.

[0986] Step 7:

[0987] Users can make reservations directly from the referral page.

[0988] Input: Information entered into the reservation form (e.g., user ID, reservation time, etc.).

[0989] Output: Notification that the reservation was successful.

[0990] Specific behavior:

[0991] The user fills in the reservation form and clicks the "Book" button.

[0992] The terminal sends the input information to the server as a POST request.

[0993] The server stores this information in the reservation database as "INSERT INTO Reservations (user_id, reservation_time, ...) VALUES ...".

[0994] The server generates a message confirming successful reservation and returns it to the user.

[0995] Step 8:

[0996] The server displays appropriate advertisements based on the user's interests and search queries.

[0997] Input: User search queries and browsing history.

[0998] Output: Relevant ads.

[0999] Specific behavior:

[1000] The server analyzes search queries and browsing history and selects relevant advertisements from a database.

[1001] The server embeds the selected advertisement into HTML and returns it to the user.

[1002] (Application example 1)

[1003] 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."

[1004] In recent years, consumer decision-making based on word-of-mouth information has been increasing, but there are currently no systems in place that can efficiently collect this information and present it to users in an appropriate format. There is also a need to utilize this word-of-mouth information to enable users to easily make reservations and purchases. Furthermore, there is a need to display advertisements based on user behavior and interests, thereby generating revenue. Conventional systems face the challenge of being unable to meet these multiple requirements.

[1005] 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.

[1006] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering out positive word-of-mouth information, means for automatically generating store or product descriptions based on the filtered word-of-mouth information, means for displaying the generated description on a website, means for displaying the generated description on a smartphone application, means for users to make reservations through the application, and means for displaying advertisements based on the user's interests and behavior. This not only enables efficient collection and presentation of word-of-mouth information, allowing users to easily make reservations and purchases, but also enables monetization through the display of advertisements.

[1007] "Word-of-mouth information" refers to reviews and opinions about stores and products provided by users on the Internet.

[1008] A "database" is a data storage system for structuring and storing collected word-of-mouth information.

[1009] "Filtering" refers to the process of selecting only information that meets specific conditions from collected word-of-mouth information.

[1010] "Positive reviews" are reviews that show favorable evaluations, many of which are accompanied by high scores.

[1011] An "introduction" is a text automatically generated based on filtered word-of-mouth information, which explains the features of the store or product.

[1012] A "website" is a collection of information accessible to users over the Internet, identified by a particular URL.

[1013] A "smartphone application" is a program that runs on a smartphone and allows users to use specific functions through an interface.

[1014] "Reservation" means that a user applies in advance for a particular service or product.

[1015] "Advertisement" means a commercial message displayed based on a user's interests or behavior, which is intended to promote a particular product or service.

[1016] "Server" means a central management system that collects, stores, processes, and distributes data, and serves to provide data to terminals that interface with users.

[1017] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[1018] System Configuration

[1019] This invention consists of a server and a user terminal. The server collects, stores, and filters reviews, automatically generates and displays testimonials, and manages reservations and advertisements. Meanwhile, users access these functions using a smartphone application.

[1020] Hardware and software used

[1021] Server: Node.js and Express.js are used for server-side processing. MongoDB is used as the database.

[1022] Natural language generation: Utilizing the OpenAI API, we generate testimonials based on reviews.

[1023] Front-end: Develop a smartphone application using React Native.

[1024] Data processing and calculation

[1025] Data collection

[1026] The server collects review information from review websites on the Internet by sending HTTP requests to retrieve the target HTML data and then performing DOM analysis to extract review text and scores.

[1027] Storage in the database

[1028] The collected reviews are stored in an organized format in a MongoDB database, allowing for efficient subsequent filtering and ranking.

[1029] filtering

[1030] The server filters the reviews retrieved from the database for positive reviews with high scores, using MongoDB's query function for this process.

[1031] Creating rankings

[1032] A ranking is created based on the filtered reviews. The reviews are sorted in descending order of score, and highly rated stores and products are extracted.

[1033] Automated content generation

[1034] Using the OpenAI API, a natural language generation tool, we automatically generate high-quality testimonials based on the ranked reviews, which then become the main content displayed to users.

[1035] Website display and smartphone application display

[1036] The generated introduction is sent from the server to the device and displayed on the website and smartphone application, which uses React Native to provide the interface.

[1037] Reservation System

[1038] Users can access store and product introduction pages from their smartphone application and make reservations. The information required for the reservation is sent to the server and stored in a reservation database.

[1039] Advertisement display

[1040] The server automatically generates advertisements based on the user's interests and behavior and displays them on the application. Revenue from these advertisements enables the system to operate sustainably.

[1041] Specific examples

[1042] For example, if a user opens the application and searches for "pasta restaurant," the server retrieves reviews of highly rated pasta restaurants from the database, creates a ranking, and then uses the OpenAI API to generate a review based on the following prompt:

[1043] Generate engaging restaurant descriptions for your users based on the following reviews:

[1044] Review 1: "The pasta was amazing, especially the carbonara."

[1045] Review 2: "The staff were very friendly and I had a great time."

[1046] The generated introduction is displayed on the smartphone application, and users can make reservations based on that information.

[1047] The above is a specific embodiment for carrying out the present invention.

[1048] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1049] Step 1:

[1050] The server collects review information from the Internet. The server sends an HTTP request to retrieve HTML data from the target website. It analyzes this HTML data and extracts review text and scores. The input is review information from the Internet, and the output is the extracted review text and scores.

[1051] Step 2:

[1052] The server stores the extracted review information in a database. The database uses MongoDB, and stores the review information organized by fields such as "store name," "product name," "score," and "text." The input is the review information extracted in step 1, and the output is a structured database entry.

[1053] Step 3:

[1054] The server retrieves reviews from the database and filters out positive reviews. The server uses MongoDB's query function to select reviews with a score of 4 or higher. The input is all reviews in the database, and the output is the positive reviews that match the criteria.

[1055] Step 4:

[1056] The server creates a ranking based on the filtered reviews. It sorts the positive reviews in descending order of score and extracts highly rated stores and products. The input is the reviews filtered in step 3, and the output is ranked data.

[1057] Step 5:

[1058] The server automatically generates store or product descriptions based on the ranked reviews. Using OpenAI's API, the review information is used as training data to generate high-quality descriptions. The input is the ranking data from Step 4 and a prompt for the AI ​​model, and the output is the generated description.

[1059] Step 6:

[1060] The server displays the generated testimonial on the smartphone application. The generated testimonial is sent to a smartphone app using React Native and displayed to the user. The input is the testimonial generated in step 5, and the output is the visualized testimonial on the application.

[1061] Step 7:

[1062] A user makes a reservation through an application. The user enters the required information into a reservation form from the application and submits it to the server. The server stores this information in a reservation database and notifies the user of a reservation confirmation. The input is the reservation information entered by the user, and the output is a reservation entry in the database and a confirmation to the user.

[1063] Step 8:

[1064] The server displays advertisements based on the user's interests and behavior. Based on the user's search query and browsing history, appropriate advertisements are selected and displayed on the smartphone application. The input is user behavior data and advertisement information from an advertisement database, and the output is the displayed advertisement.

[1065] 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.

[1066] The present invention is a system based on a client-server model, where the server is the central player in collecting data, filtering, generating content, and displaying it, while the terminal functions as an interface with the user. A specific implementation of the present invention will be described below.

[1067] Data collection and storage

[1068] The server automatically retrieves review information from the Internet. Specifically, it sends an HTTP request to the website containing the target review information and retrieves the HTML data. It then analyzes the HTML data, parses it into a DOM structure, and extracts the review score and text. The extracted review information is then stored in a database.

[1069] Data Filtering and Analysis

[1070] The server retrieves all reviews from the database and filters out positive reviews (e.g., scores of 4 or higher). The filtered reviews are sorted by score and stored as rankings.

[1071] Automated content generation

[1072] The server automatically generates store and product descriptions based on the ranked reviews. It uses a natural language generation tool to generate high-quality descriptions using the acquired review text as training data.

[1073] Search and Display

[1074] A user accesses a website from a terminal and enters a search query. The terminal sends the search query to the server, which searches the database to obtain relevant reviews and rankings, and generates a web page to display to the user. The user then browses the reviews displayed as search results.

[1075] Emotion engine integration

[1076] The server integrates an emotion engine into the review information collection and filtering process. It performs sentiment analysis on the review data and prioritizes filtering of reviews with positive sentiment. This procedure allows the server to provide more reliable and useful information to users.

[1077] The emotion engine also analyzes word-of-mouth information related to search queries from devices, and prioritizes displaying information with positive sentiment to users.

[1078] Emotion-based advertising

[1079] The server monitors the user's real-time emotions with an emotion engine and dynamically changes the advertising content based on those emotions, thereby presenting ads that best fit the user's emotional state and improving advertising effectiveness.

[1080] Reservation System

[1081] Users can make reservations directly from the store or product introduction page. They enter the required information (e.g., user ID, reservation time, etc.) into the form on their terminal and send it to the server. The server stores the received reservation information in a database and notifies the user that the reservation was successful. A reservation success page is generated and displayed to the user.

[1082] Specific examples of processing

[1083] For example, when a user searches for a restaurant, the server collects reviews of that restaurant and analyzes them using an emotion engine. It filters out only the positive reviews and automatically generates a review based on them. When a user enters a search query about a specific dish, the server prioritizes the display of positive reviews related to the query.

[1084] In this way, this system automatically generates high-quality content based on word-of-mouth information and provides users with the most appropriate information. In addition, by integrating an emotion engine, it is possible to provide more reliable information and improve advertising effectiveness.

[1085] The processing flow will be explained below.

[1086] Processing steps of a system that combines emotion engines

[1087] Step 1:

[1088] The server retrieves review information from the Internet. Specifically, it sends an HTTP request to the target review site and retrieves the HTML data.

[1089] Step 2:

[1090] The server parses the HTML data and parses it into a DOM structure to extract review scores and text, using specific CSS selectors and tags to identify the data it needs.

[1091] Step 3:

[1092] The server stores the extracted word-of-mouth information in a database, which contains fields such as "store name," "product name," "score," and "text."

[1093] Step 4:

[1094] The server retrieves all reviews from the database and uses an appropriate SQL query to select all records.

[1095] Step 5:

[1096] The server analyzes the acquired reviews using a sentiment engine and adds a sentiment score. The sentiment engine analyzes the text of each review and generates a sentiment score such as positive, negative, or neutral.

[1097] Step 6:

[1098] The server filters the reviews based on the sentiment score, specifically selecting reviews with a positive sentiment score (e.g., a score of 4 or higher).

[1099] Step 7:

[1100] The server sorts the filtered reviews by score and creates a ranking, which results in a list of stores and products with the highest ratings.

[1101] Step 8:

[1102] The server automatically generates store and product descriptions based on the ranked reviews. It uses a natural language generation tool to generate high-quality descriptions using the review text as training data.

[1103] Step 9:

[1104] A user accesses a website from a device and enters a search query, which may be for a specific store or product.

[1105] Step 10:

[1106] The device sends a search query to the server, which passes the query entered by the user to the server.

[1107] Step 11:

[1108] The server searches the database based on the search query to retrieve relevant reviews and rankings. The search results include reviews that are recognized as positive by the sentiment engine.

[1109] Step 12:

[1110] The server generates a web page based on the search results to display to the user, including the generated testimonial and ranking information.

[1111] Step 13:

[1112] The user can view the displayed introductions and rankings, and check detailed store and product information as needed. Specifically, they can access the introduction page.

[1113] Step 14:

[1114] Users make reservations directly from the store or product introduction page, entering necessary information such as user ID and reservation time into the reservation form.

[1115] Step 15:

[1116] The terminal sends the entered reservation information to the server. When the user submits the form, the reservation request is passed to the server.

[1117] Step 16:

[1118] The server stores the received reservation information in the database and executes an SQL query to insert the reservation information into the reservation table.

[1119] Step 17:

[1120] The server notifies the user that the reservation was successful by generating a reservation success page and sending it to the terminal.

[1121] Step 18:

[1122] The server monitors the user's emotions in real time and displays appropriate advertisements based on those emotions. The emotion engine analyzes the user's emotions and dynamically changes the advertisement content.

[1123] In this way, the system generates high-quality content based on word-of-mouth information and user sentiment analysis, providing optimal information to users and generating revenue.

[1124] Example 2

[1125] 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."

[1126] Conventional word-of-mouth information collection systems have had the problem of not being able to adequately evaluate or filter the collected word-of-mouth information, making it difficult to provide useful information to users. Furthermore, they have not been able to evaluate word-of-mouth information using an emotion engine or dynamically display advertisements based on the user's emotional state, making it difficult to improve the reliability of word-of-mouth information or the effectiveness of advertisements.

[1127] 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.

[1128] In this invention, the server includes a means for collecting word-of-mouth information from the Internet, a means for storing the collected word-of-mouth information in a database, and a means for retrieving word-of-mouth information from the database and filtering out positive reviews. This makes it possible to provide users with highly reliable, positive word-of-mouth information. Furthermore, the server also includes a means for evaluating word-of-mouth information and user search queries using a sentiment analysis engine and preferentially displaying positive information, a means for dynamically changing advertisements based on the user's emotional state, a means for notifying the user based on the results of the sentiment analysis by the sentiment engine, and a means for generating testimonials using a generative AI model, thereby improving the reliability of word-of-mouth information and advertising effectiveness.

[1129] "Word-of-mouth information" refers to information posted online by ordinary consumers that includes their evaluations and opinions about products and services.

[1130] A "database" is a digital storage system for systematically storing and managing collected word-of-mouth information.

[1131] "Filtering" is the process of selecting collected word-of-mouth information that meets specific criteria (e.g., positive reviews).

[1132] "Automatic generation" is the process of generating text or content using a computer program without human intervention.

[1133] "Display" refers to the act of visually presenting the generated testimonials and filtered word-of-mouth information to the user.

[1134] A "sentiment analysis engine" is software that automatically evaluates the sentiment (positive, negative, neutral, etc.) of text data.

[1135] "Advertisement" refers to content that presents information about products or services to users for promotional purposes.

[1136] A "generative AI model" is a trained model that uses artificial intelligence techniques to generate text or content.

[1137] A "search query" is a keyword or phrase that a user enters into a search engine or system to search for information.

[1138] "Positive reviews" are reviews that have a high rating (e.g., a score of 4 or higher) and contain positive opinions and emotions.

[1139] "Dynamic change" refers to the automatic change of display content and behavior in real time according to conditions.

[1140] MODE FOR CARRYING OUT THE INVENTION

[1141] The present invention is a system based on a client-server model, where the server is the central point responsible for data collection, filtering, content generation and display, while the terminals act as the interface with the user.

[1142] Data collection

[1143] The server collects review information from the Internet. Specifically, it sends an HTTP request to the target website and retrieves the HTML data. This process uses the Apache HttpClient library. The retrieved HTML data is parsed into a DOM structure using JSoup, and the review score and text are extracted.

[1144] Data analysis

[1145] The server analyzes the parsed HTML data using the JSoup library and extracts the review scores and text. The extracted data is stored in a database such as MySQL or PostgreSQL. Data is stored in the database using JDBC.

[1146] Data Filtering

[1147] The server retrieves all reviews from the database and filters out positive reviews (e.g., scores above 4). It uses an SQL query to extract only records that meet the specified criteria. The extracted data is stored as rankings in an in-memory database such as Redis or Elasticsearch.

[1148] Content Generation

[1149] The server automatically generates testimonials based on the filtered review information using a natural language generation model (e.g., GPT-3 or BERT). By using the review text as training data and inputting prompts into the generative AI model, high-quality testimonials are generated.

[1150] Search and Display

[1151] A user accesses a website from a device (e.g., a PC or smartphone) and enters a search query. The device sends this search query to the server, which searches a database to return relevant reviews and rankings, and generates a web page to display to the user. The user can then view the reviews displayed as search results.

[1152] sentiment analysis

[1153] The server uses a sentiment analysis engine (e.g., TextBlob or VADER) to filter reviews. By performing sentiment analysis, it prioritizes filtering of positive reviews and provides reliable information.

[1154] Emotion-based advertising

[1155] The server monitors the user's emotional state in real time and dynamically changes the advertisements based on that emotion. It uses an emotion engine to evaluate the user's emotions and uses Google Ads and Facebook Ads APIs to display the most appropriate advertising content.

[1156] Reservation System

[1157] The user enters the necessary information (e.g., user ID, reservation time, etc.) into the form on the terminal and sends it to the server. The server stores the reservation information in a database and notifies the user that the reservation was successful. A reservation success page is also generated at the same time and displayed to the user.

[1158] Prompt Sentence Examples

[1159] "Generate testimonials with positive reviews for this restaurant. The reviews are: [list of reviews]"

[1160] "Please suggest optimal ad content based on the user's emotional state. The user's emotional state is: [user's emotional data]"

[1161] In this way, this system automatically generates high-quality content based on word-of-mouth information and provides users with the most appropriate information. In addition, by integrating an emotion engine, it provides more reliable information and improves advertising effectiveness.

[1162] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1163] Step 1:

[1164] The server collects reviews from the Internet. As input, it receives the URLs of target websites and sends an HTTP request to retrieve HTML data. Using the Apache HttpClient library, it sends a GET request and receives a response with HTML data. As output, it generates the retrieved HTML data. Specifically, it creates an instance of HttpClient and sends a GET request to the specified URL.

[1165] Step 2:

[1166] The server parses the retrieved HTML data. As input, it receives the HTML data retrieved in step 1 and parses it into a DOM structure using the JSoup library. This allows it to extract review scores and text. As output, it generates a list of the extracted scores and text. Specifically, it extracts review scores and text from the Document object parsed by JSoup using the specified CSS selector.

[1167] Step 3:

[1168] The server stores the extracted review information in a database. As input, it receives the scores and text list extracted in step 2 and stores them in a database such as MySQL or PostgreSQL. It connects to the database using JDBC and inserts the data. As output, review information stored in the database is generated. Specifically, it executes an insert SQL statement using PreparedStatement and stores the review scores and text in the corresponding tables in the database.

[1169] Step 4:

[1170] The server retrieves all reviews from the database and filters out the positive ones. As input, it takes all reviews stored in the database and executes a SQL query to filter reviews with a score of 4 or higher. As output, it generates a list of reviews that are determined to be positive. Specifically, it uses a Statement object to execute a SELECT query and extracts records that match the criteria.

[1171] Step 5:

[1172] The server automatically generates testimonials using a generative AI model based on the filtered reviews. As input, it receives a list of filtered reviews and generates a prompt. The testimonials are generated using natural language generation models such as GPT-3 and BERT. As output, a high-quality testimonial is generated. Specifically, the prompt is input to the generative AI model and the generated text is obtained as a response.

[1173] Step 6:

[1174] A user accesses a website from a terminal and enters a search query. The search query entered by the user is received as input and sent to the server. The terminal then sends the search query to the server as a POST request. As output, the search results are displayed to the user. Specifically, the system retrieves the search query from an HTML form and generates an HTTP request to send to the server.

[1175] Step 7:

[1176] The server uses a sentiment analysis engine to evaluate reviews and search queries. As input, it receives collected reviews and search queries from users, and calculates a sentiment score using a sentiment analysis library such as TextBlob or VADER. As output, information rated as positive is displayed preferentially. Specifically, text is input into the analysis library, its sentiment score is calculated, and filtering is performed.

[1177] Step 8:

[1178] The server dynamically changes ads based on the user's emotional state. It receives user emotional data as input and dynamically selects ad content. It uses Google Ads or Facebook Ads API to retrieve and display the most suitable ad. The output is an ad optimized for the user's emotions. Specifically, it calls the advertising API based on the user's emotional data and renders the retrieved ad data for display.

[1179] Step 9:

[1180] A user makes a reservation through a website. As input, the information entered by the user in the reservation form (user ID, reservation time, etc.) is received and sent to the server. The server stores this information in a database and notifies the user of the reservation result. As output, a notification that the reservation was successful is displayed to the user. Specifically, the system retrieves information from the reservation form, generates an HTTP request to send to the server, stores the information in the database on the server side, and then generates a response notifying the result.

[1181] (Application example 2)

[1182] 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."

[1183] Conventional review information collection systems only filter positive reviews and are unable to provide optimal information based on the user's emotional state. Furthermore, they are unable to centrally handle facility and product reservation functions, limiting the user experience. This has created challenges in effectively utilizing review information and improving user convenience.

[1184] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1185] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering out positive word-of-mouth information, means for automatically generating a facility or product introduction text based on the filtered word-of-mouth information, means for displaying the generated text on a website, means for dynamically displaying advertisements that are optimal for the user's emotional state using a sentiment analysis module, and means for receiving data for making reservations for facilities or products from a terminal and storing the data in the database. This allows users to view high-quality content based on positive word-of-mouth information, and by receiving advertisements that are tailored to their emotions, the effectiveness of the advertisements is improved, making it possible for users to easily make reservations for facilities or products.

[1186] "Word-of-mouth information" is data that includes user ratings and opinions posted on the Internet.

[1187] A "database" is a system for storing and managing data in a structured way.

[1188] "Positive reviews" are reviews with favorable content that have a rating above a certain score.

[1189] "Filtering" is a method of selecting data based on specific conditions.

[1190] "Facility or product introduction text" is a description of a facility or product that is automatically generated based on filtered word-of-mouth information.

[1191] A "sentiment analysis module" is a software component for detecting and classifying emotions from text data.

[1192] "Dynamic display of advertisements" means that advertisement content is displayed while changing in response to the user's real-time emotional state.

[1193] "Data for reserving a facility or product" refers to information required when a user makes a reservation (e.g., user ID, reservation time, etc.).

[1194] A "terminal" is a computing device through which a user accesses the Internet.

[1195] MODE FOR CARRYING OUT THE INVENTION

[1196] System Overview

[1197] The system for implementing this invention collects word-of-mouth information, filters it, analyzes its sentiment, generates content, and displays it on a user terminal. The system is mainly composed of a server, a database, a sentiment analysis module, and a user terminal.

[1198] Hardware and software used

[1199] Server: Cloud server such as AWS EC2

[1200] Database: SQLite or AWS RDS

[1201] Sentiment analysis module: TextBlob or AWS Comprehend

[1202] Scraping tool: BeautifulSoup

[1203] User interface: Web browser or smartphone application (e.g., Flask)

[1204] Processing flow

[1205] Server-side processing

[1206] The server collects reviews from the Internet and stores them in a database. Specifically, it uses BeautifulSoup to retrieve HTML data from target websites, parses the data, and extracts review information. The extracted reviews are then stored in a structured format in the database.

[1207] The server retrieves the reviews from the database and uses TextBlob to filter the positive reviews. The positive reviews are sorted by score and stored as a ranking. Furthermore, it utilizes a sentiment analysis module to monitor the user's emotional state and dynamically change the advertising content based on the user's emotion.

[1208] Processing on the user terminal side

[1209] A user inputs a search query through a website or smartphone application. The input query is sent to a server, which retrieves related reviews and generated introductory text and displays them to the user. The user can then use the displayed reviews and introductory text to check details about the facility or product and view advertisements. Furthermore, the user can also make reservations for the facility or product within the application.

[1210] Specific examples

[1211] For example, when a user searches for a restaurant, the server collects reviews related to that restaurant and performs sentiment analysis. It filters out only positive reviews and automatically generates high-quality restaurant descriptions based on that information. When a user enters a search query about a specific dish, the server prioritizes displaying related positive reviews.

[1212] Prompt Sentence Examples

[1213] Filter reviews with positive sentiment from word of mouth information and generate high-quality descriptions of restaurants and dishes. The filtered information format is: [restaurant name, score, review text].

[1214] This system allows users to view high-quality content based on positive word-of-mouth, and by displaying advertisements that are tailored to their emotions, advertising effectiveness is improved, making it possible to easily reserve facilities and products.

[1215] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1216] Step 1:

[1217] The server collects reviews from the target website. Specifically, the server sends an HTTP request and receives the website's HTML data.

[1218] (Input: URL, Output: HTML data). Analyze the received HTML data using BeautifulSoup and extract the reviews.

[1219] (Input: HTML data, Output: Reviews).

[1220] Step 2:

[1221] The server stores the extracted reviews in a structured format in a database.

[1222] (Input: review information, output: data stored in a database). Specifically, the server connects to a database such as SQLite and inserts the review information into a table.

[1223] Step 3:

[1224] The server retrieves reviews from the database and filters out positive reviews using a sentiment analysis module (e.g., TextBlob).

[1225] (Input: review information in the database, Output: positive reviews). The server calculates a sentiment score for each review using TextBlob and extracts only reviews with a positive score (e.g., 4 or higher).

[1226] Step 4:

[1227] The server automatically generates facility or product introduction text based on the filtered reviews.

[1228] (Input: positive reviews, Output: introduction text for the facility or product). Specifically, the server uses a natural language generation tool (e.g., a generative AI model) to automatically generate high-quality introduction text. An example of a prompt is as follows:

[1229] Filter reviews with positive sentiment from word of mouth information and generate high-quality descriptions of restaurants and dishes. The filtered information format is: [restaurant name, score, review text].

[1230] Step 5:

[1231] A user uses a device to enter a search query through a website or smartphone application

[1232] (Input: search query, output: sending query to server). Specifically, the device accepts user input and sends the search query to the server.

[1233] Step 6:

[1234] The server retrieves relevant reviews and generated testimonials from a database based on the received search query and generates a web page to display to the user.

[1235] (Input: search query, output: search result page). Specifically, the server queries the database for relevant information and generates it as an HTML page.

[1236] Step 7:

[1237] The server utilizes a sentiment analysis module to monitor the user's emotional state and dynamically change the advertising content based on the emotional state.

[1238] (Input: user behavior data, output: dynamic advertising content). Specifically, the server collects user behavior data, analyzes it using a sentiment analysis module, and displays appropriate advertising in real time.

[1239] Step 8:

[1240] The user inputs data for making a reservation for a facility or product using the terminal and sends the data to the server.

[1241] (Input: reservation data, Output: sending data to the server) In concrete terms, the user enters the necessary information into the reservation form and sends it to the server.

[1242] Step 9:

[1243] The server saves the received reservation data in the database and notifies the user that the reservation was successful.

[1244] (Input: reservation data, Output: reservation success message). Specifically, the server saves the reservation data in the database and generates a reservation success page to display to the user.

[1245] This allows users to view high-quality content based on positive word-of-mouth, and by receiving advertisements that match their emotions, advertising effectiveness is improved, making it possible to easily reserve facilities and products.

[1246] 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.

[1247] 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.

[1248] 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.

[1249] [Fourth embodiment]

[1250] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1251] 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.

[1252] 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).

[1253] 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.

[1254] 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.

[1255] 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).

[1256] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1257] 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.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] 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.

[1262] 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."

[1263] The present invention is a system based on a client-server model, where the server is the central player in collecting data, filtering, generating content, and displaying it, while the terminal functions as an interface with the user. A specific implementation of the present invention will be described below.

[1264] Data collection

[1265] The server first executes a process to automatically retrieve review information from the Internet. The server sends an HTTP request to the website containing the target review information and analyzes the retrieved HTML data. To analyze, it parses the DOM structure of the webpage and extracts the review score and text. All of this information is stored in a database.

[1266] Storage in the database

[1267] The server stores the acquired word-of-mouth information in a database as structured data. Therefore, each piece of word-of-mouth information is organized and stored in the database by fields such as "store name," "product name," "score," and "text." This allows the data to be extracted and analyzed efficiently in later processing.

[1268] Filtering Methods

[1269] The server retrieves reviews from the database and filters out positive reviews (e.g., scores of 4 or higher). Specifically, it loops through all reviews, checks their scores, and extracts only those that meet the criteria. This filtered data is then used as the basis for ranking.

[1270] Creating rankings

[1271] The server creates a ranking based on the filtered reviews. The ranking is sorted by highest score to make it easier to find highly rated stores and products, and the ranking results are used as the basis for generating testimonials.

[1272] Automated content generation

[1273] The server automatically generates store and product descriptions based on the ranked reviews. Using a natural language generation tool, the acquired review text is used as training data to generate high-quality descriptions. These descriptions become the main content displayed to users.

[1274] Website display method

[1275] A user accesses a website from their device and enters a search query. The device sends this search query to the server, which searches the database and returns rankings and testimonials of relevant stores and products. The user can then review this information and view the testimonial page for more detailed information.

[1276] Reservation System

[1277] Users can make reservations directly from the store or product introduction page. They enter the required information (e.g., user ID, reservation time, etc.) into the reservation form and send it to the server. The server stores this information in the reservation database and notifies the user that the reservation was successful.

[1278] Advertisement display

[1279] The server generates appropriate advertisements based on users' interests and search queries and displays them on web pages, generating revenue from these advertisements to ensure the system's sustainable operation.

[1280] As described above, the present invention automatically generates high-quality introductory content using word-of-mouth information, providing users with optimal store and product information. It also realizes monetization through reservations and advertising, providing an efficient and effective media platform.

[1281] The processing flow will be explained below.

[1282] Data collection and storage

[1283] Step 1:

[1284] The server retrieves the review information from the Internet. Specifically, it sends an HTTP request to the website that contains the review information in question and retrieves the HTML data.

[1285] Step 2:

[1286] To analyze the retrieved HTML data, the server parses it into a Document Object Model (DOM) structure, which makes it easier to access each element of the web page.

[1287] Step 3:

[1288] The server extracts review scores and text from the parsed HTML structure, for example by extracting the required data based on specific CSS classes or tags.

[1289] Step 4:

[1290] The server stores the extracted review information (score and text) in a database. Specifically, it stores the data in the appropriate table using an insert statement.

[1291] Data Filtering and Analysis

[1292] Step 5:

[1293] The server retrieves all the reviews stored in the database by executing a query that selects all records from the database.

[1294] Step 6:

[1295] The server analyzes the data and filters out only positive reviews, for example, those with a score of 4 or higher.

[1296] Step 7:

[1297] The server sorts the filtered reviews in order of score and creates a ranking, which allows stores and products to be sorted in descending order of their ratings.

[1298] Automated content generation

[1299] Step 8:

[1300] The server automatically generates store and product descriptions based on the sorted review information. It uses a natural language generation tool (e.g., TextgenRnn) to generate the descriptions using the review text as training data.

[1301] Search and Display

[1302] Step 9:

[1303] A user accesses a website from a terminal and enters a search query.

[1304] Step 10:

[1305] The terminal transmits a search query from the user to the server.

[1306] Step 11:

[1307] The server searches the database based on the submitted search query to retrieve relevant reviews and rankings. The database is searched using an appropriate SQL query.

[1308] Step 12:

[1309] The server converts the search results into HTML format and generates a web page for display to the user.

[1310] Bookings and Advertising

[1311] Step 13:

[1312] When a user makes a reservation directly from a store or product introduction page, the user enters the necessary information (for example, user ID, reservation time, etc.) into a form on the terminal.

[1313] Step 14:

[1314] The terminal transmits the input reservation information to the server.

[1315] Step 15:

[1316] The server stores the received reservation information in the database by executing an insert statement on the reservation table.

[1317] Step 16:

[1318] The server notifies the user that the reservation was successful, and generates a reservation success page and sends it to the terminal for display to the user.

[1319] Step 17:

[1320] The server selects advertising data for displaying appropriate advertisements based on the user's interests and search queries, thereby displaying effective advertisements that attract the user's attention.

[1321] In this way, this system automatically generates high-quality content based on word-of-mouth information, providing optimal information to users, and also realizing monetization through reservations and advertising.

[1322] Example 1

[1323] 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."

[1324] Currently, many users are seeking reliable word-of-mouth information via the Internet, but collecting and organizing information is cumbersome, and finding the right information requires a great deal of effort. Another issue is the lack of systems that can quickly and accurately provide users with the information they are looking for. Additionally, the process of finding information about stores and products that users are truly interested in and making reservations based on that information is also cumbersome. Furthermore, in order to ensure profits, system operators need a way to efficiently display advertisements based on users' interests.

[1325] 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.

[1326] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering positive word-of-mouth information, means for automatically generating store or product descriptions based on the filtered word-of-mouth information, means for displaying the generated descriptions on a website, means for a user to access the website from a terminal and input a search query, means for the user to display rankings and descriptions of relevant stores or products based on the search query, means for displaying advertisements based on the ranked word-of-mouth information, means for inputting information required for a reservation form and transmitting it to the server, and means for notifying the user that the reservation was successful. This allows the information desired by the user to be provided quickly and accurately, enabling easy reservation, and also enables efficient advertisement display to ensure profits for the system operator.

[1327] "Word-of-mouth information" refers to the evaluations and impressions of users on the Internet, including opinions and evaluations of specific products and services.

[1328] A "database" is a collection of systematically organized data that has a structure that allows specific information to be searched and extracted from it.

[1329] "Filtering" refers to the process of selecting data that meets specific conditions from the acquired data.

[1330] An "introduction" is a text that explains a store or product, and conveys its features and advantages to users in an easy-to-understand manner.

[1331] A "website" is a collection of information published on the Internet that users can access using a web browser.

[1332] A "search query" is a keyword or phrase that a user enters to search for information within a search engine or a particular website.

[1333] A "ranking" is a list in which multiple objects are evaluated and ranked based on certain criteria.

[1334] An "advertisement" is a message or visual that promotes a particular product or service and is displayed on a web page to attract a user's attention.

[1335] A "reservation" is a procedure for reserving a store or service date and time in advance.

[1336] A "generative AI model" is an artificial intelligence system that learns from large amounts of data to generate and understand natural language, and specifically refers to a language model.

[1337] A "prompt" is input text given to a generative AI model to request a specific output.

[1338] "User" refers to an individual or corporation that uses this system, and is primarily someone who accesses it via the Internet.

[1339] A "terminal" is a device that a user uses to connect to the Internet to obtain information and perform operations.

[1340] A "server" is a computer system that manages data on a network and provides services to multiple users.

[1341] The present invention is a system based on a client-server model, where the server is the central player in data collection, filtering, content generation, and display, while the terminals act as the interface with the user.

[1342] First, the server collects review information from the Internet. Specifically, the server sends an HTTP request to a specific review site and analyzes the HTML data it retrieves. This analysis is performed using Python and BeautifulSoup. The server then parses the HTML data, extracts the review scores and text, and stores the organized data in a database. MySQL is used for database management.

[1343] Next, the server retrieves the reviews from the database and filters out the positive reviews. The filtering criteria is to extract reviews with a score of 4 or higher. This operation is performed using SQLAlchemy. After the data is filtered, the server creates a ranking based on the results. The ranking is sorted by highest score, making it easier for users to find highly rated stores and products. This is done using Python's sorting function.

[1344] The server then generates store and product descriptions based on the ranking results. This process uses a generative AI model (e.g., GPT-3) and uses the review text as training data. An example of a prompt for generation is: "Generate a high-quality store description based on the following review data: {review text}." The generated description is stored in a database and displayed on the website.

[1345] A user accesses a website from a device and enters a search query. The device sends the search query to the server, which searches the database and returns rankings and reviews of relevant stores and products to the device. This information is then displayed to the user through a web browser.

[1346] Users can also make reservations directly from the introduction page. After entering the necessary information into the reservation form and sending it to the server, the server stores this information in the reservation database and notifies the user that the reservation was successful. This also involves database operations such as SQL.

[1347] Finally, the server displays appropriate advertisements based on the user's interests and search queries. The server analyzes the user's search history and other factors to select and display the most relevant advertisements on the web page. Revenue generated from these advertisements allows the system to operate sustainably.

[1348] The present invention allows users to quickly and accurately receive the information they require, and simplifies the reservation process. Furthermore, efficient advertising display also enables monetization, making it possible to provide effective services.

[1349] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1350] Step 1:

[1351] The server collects reviews from the Internet.

[1352] Input: URL of the target review site.

[1353] Output: HTML data.

[1354] Specific behavior:

[1355] The server executes "requests.get(URL)" to retrieve the HTML of the target page.

[1356] The server parses the HTML using "BeautifulSoup(html, 'html.parser')".

[1357] The server navigates the DOM tree and extracts the review data using the "find_all" method.

[1358] Step 2:

[1359] The server stores the extracted word-of-mouth information in a database.

[1360] Input: Extracted review score and text.

[1361] Output: Structured data stored in a database.

[1362] Specific behavior:

[1363] The server inserts the data into the database using the SQL query "INSERT INTO Reviews (store_name, product_name, score, text) VALUES ...".

[1364] The server manages these operations using a database connectivity library (e.g., SQLAlchemy).

[1365] Step 3:

[1366] The server retrieves review information from the database and filters out positive reviews.

[1367] Input: Reviews in the database.

[1368] Output: Filtered review data that meets the criteria.

[1369] Specific behavior:

[1370] The server executes "SELECT FROM Reviews WHERE score >= 4" and retrieves data that meets the condition.

[1371] The server stores the retrieved data in a list or other suitable data structure for further processing.

[1372] Step 4:

[1373] The server creates a ranking based on the filtered word-of-mouth information.

[1374] Input: Filtered review data.

[1375] Output: Data organized in a ranking format.

[1376] Specific behavior:

[1377] The server sorts the data in a way like "sorted(reviews, key=lambda x: x['score'], reverse=True)".

[1378] The server stores the sorted data in a ranking format.

[1379] Step 5:

[1380] The server generates store and product descriptions based on the ranking data.

[1381] Input: Ranked reviews.

[1382] Output: Generated store and product descriptions.

[1383] Specific behavior:

[1384] The server sends a prompt to the "generative AI model" and generates an introduction in response.

[1385] Example: "Generate high-quality store descriptions based on the following review data: {review text}"

[1386] The server stores the generated testimonial in a database.

[1387] Step 6:

[1388] A user accesses a website from a terminal and enters a search query.

[1389] Input: Search query.

[1390] Output: Rankings and descriptions of stores and products displayed as search results.

[1391] Specific behavior:

[1392] A user enters a query into a search form in a web browser and clicks "Submit."

[1393] The device sends the search query to the server as a POST request.

[1394] The server searches the database and returns matching data in HTML format.

[1395] The device displays the received HTML in the browser.

[1396] Step 7:

[1397] Users can make reservations directly from the referral page.

[1398] Input: Information entered into the reservation form (e.g., user ID, reservation time, etc.).

[1399] Output: Notification that the reservation was successful.

[1400] Specific behavior:

[1401] The user fills in the reservation form and clicks the "Book" button.

[1402] The terminal sends the input information to the server as a POST request.

[1403] The server stores this information in the reservation database as "INSERT INTO Reservations (user_id, reservation_time, ...) VALUES ...".

[1404] The server generates a message confirming successful reservation and returns it to the user.

[1405] Step 8:

[1406] The server displays appropriate advertisements based on the user's interests and search queries.

[1407] Input: User search queries and browsing history.

[1408] Output: Relevant ads.

[1409] Specific behavior:

[1410] The server analyzes search queries and browsing history and selects relevant advertisements from a database.

[1411] The server embeds the selected advertisement into HTML and returns it to the user.

[1412] (Application example 1)

[1413] 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."

[1414] In recent years, consumer decision-making based on word-of-mouth information has been increasing, but there are currently no systems in place that can efficiently collect this information and present it to users in an appropriate format. There is also a need to utilize this word-of-mouth information to enable users to easily make reservations and purchases. Furthermore, there is a need to display advertisements based on user behavior and interests, thereby generating revenue. Conventional systems face the challenge of being unable to meet these multiple requirements.

[1415] 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.

[1416] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering out positive word-of-mouth information, means for automatically generating store or product descriptions based on the filtered word-of-mouth information, means for displaying the generated description on a website, means for displaying the generated description on a smartphone application, means for users to make reservations through the application, and means for displaying advertisements based on the user's interests and behavior. This not only enables efficient collection and presentation of word-of-mouth information, allowing users to easily make reservations and purchases, but also enables monetization through the display of advertisements.

[1417] "Word-of-mouth information" refers to reviews and opinions about stores and products provided by users on the Internet.

[1418] A "database" is a data storage system for structuring and storing collected word-of-mouth information.

[1419] "Filtering" refers to the process of selecting only information that meets specific conditions from collected word-of-mouth information.

[1420] "Positive reviews" are reviews that show favorable evaluations, many of which are accompanied by high scores.

[1421] An "introduction" is a text automatically generated based on filtered word-of-mouth information, which explains the features of the store or product.

[1422] A "website" is a collection of information accessible to users over the Internet, identified by a particular URL.

[1423] A "smartphone application" is a program that runs on a smartphone and allows users to use specific functions through an interface.

[1424] "Reservation" means that a user applies in advance for a particular service or product.

[1425] "Advertisement" means a commercial message displayed based on a user's interests or behavior, which is intended to promote a particular product or service.

[1426] "Server" means a central management system that collects, stores, processes, and distributes data, and serves to provide data to terminals that interface with users.

[1427] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[1428] System Configuration

[1429] This invention consists of a server and a user terminal. The server collects, stores, and filters reviews, automatically generates and displays testimonials, and manages reservations and advertisements. Meanwhile, users access these functions using a smartphone application.

[1430] Hardware and software used

[1431] Server: Node.js and Express.js are used for server-side processing. MongoDB is used as the database.

[1432] Natural language generation: Utilizing the OpenAI API, we generate testimonials based on reviews.

[1433] Front-end: Develop a smartphone application using React Native.

[1434] Data processing and calculation

[1435] Data collection

[1436] The server collects review information from review websites on the Internet by sending HTTP requests to retrieve the target HTML data and then performing DOM analysis to extract review text and scores.

[1437] Storage in the database

[1438] The collected reviews are stored in an organized format in a MongoDB database, allowing for efficient subsequent filtering and ranking.

[1439] filtering

[1440] The server filters the reviews retrieved from the database for positive reviews with high scores, using MongoDB's query function for this process.

[1441] Creating rankings

[1442] A ranking is created based on the filtered reviews. The reviews are sorted in descending order of score, and highly rated stores and products are extracted.

[1443] Automated content generation

[1444] Using the OpenAI API, a natural language generation tool, we automatically generate high-quality testimonials based on the ranked reviews, which then become the main content displayed to users.

[1445] Website display and smartphone application display

[1446] The generated introduction is sent from the server to the device and displayed on the website and smartphone application, which uses React Native to provide the interface.

[1447] Reservation System

[1448] Users can access store and product introduction pages from their smartphone application and make reservations. The information required for the reservation is sent to the server and stored in a reservation database.

[1449] Advertisement display

[1450] The server automatically generates advertisements based on the user's interests and behavior and displays them on the application. Revenue from these advertisements enables the system to operate sustainably.

[1451] Specific examples

[1452] For example, if a user opens the application and searches for "pasta restaurant," the server retrieves reviews of highly rated pasta restaurants from the database, creates a ranking, and then uses the OpenAI API to generate a review based on the following prompt:

[1453] Generate engaging restaurant descriptions for your users based on the following reviews:

[1454] Review 1: "The pasta was amazing, especially the carbonara."

[1455] Review 2: "The staff were very friendly and I had a great time."

[1456] The generated introduction is displayed on the smartphone application, and users can make reservations based on that information.

[1457] The above is a specific embodiment for carrying out the present invention.

[1458] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1459] Step 1:

[1460] The server collects review information from the Internet. The server sends an HTTP request to retrieve HTML data from the target website. It analyzes this HTML data and extracts review text and scores. The input is review information from the Internet, and the output is the extracted review text and scores.

[1461] Step 2:

[1462] The server stores the extracted review information in a database. The database uses MongoDB, and stores the review information organized by fields such as "store name," "product name," "score," and "text." The input is the review information extracted in step 1, and the output is a structured database entry.

[1463] Step 3:

[1464] The server retrieves reviews from the database and filters out positive reviews. The server uses MongoDB's query function to select reviews with a score of 4 or higher. The input is all reviews in the database, and the output is the positive reviews that match the criteria.

[1465] Step 4:

[1466] The server creates a ranking based on the filtered reviews. It sorts the positive reviews in descending order of score and extracts highly rated stores and products. The input is the reviews filtered in step 3, and the output is ranked data.

[1467] Step 5:

[1468] The server automatically generates store or product descriptions based on the ranked reviews. Using OpenAI's API, the review information is used as training data to generate high-quality descriptions. The input is the ranking data from Step 4 and a prompt for the AI ​​model, and the output is the generated description.

[1469] Step 6:

[1470] The server displays the generated testimonial on the smartphone application. The generated testimonial is sent to a smartphone app using React Native and displayed to the user. The input is the testimonial generated in step 5, and the output is the visualized testimonial on the application.

[1471] Step 7:

[1472] A user makes a reservation through an application. The user enters the required information into a reservation form from the application and submits it to the server. The server stores this information in a reservation database and notifies the user of a reservation confirmation. The input is the reservation information entered by the user, and the output is a reservation entry in the database and a confirmation to the user.

[1473] Step 8:

[1474] The server displays advertisements based on the user's interests and behavior. Based on the user's search query and browsing history, appropriate advertisements are selected and displayed on the smartphone application. The input is user behavior data and advertisement information from an advertisement database, and the output is the displayed advertisement.

[1475] 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.

[1476] The present invention is a system based on a client-server model, where the server is the central player in collecting data, filtering, generating content, and displaying it, while the terminal functions as an interface with the user. A specific implementation of the present invention will be described below.

[1477] Data collection and storage

[1478] The server automatically retrieves review information from the Internet. Specifically, it sends an HTTP request to the website containing the target review information and retrieves the HTML data. It then analyzes the HTML data, parses it into a DOM structure, and extracts the review score and text. The extracted review information is then stored in a database.

[1479] Data Filtering and Analysis

[1480] The server retrieves all reviews from the database and filters out positive reviews (e.g., scores of 4 or higher). The filtered reviews are sorted by score and stored as rankings.

[1481] Automated content generation

[1482] The server automatically generates store and product descriptions based on the ranked reviews. It uses a natural language generation tool to generate high-quality descriptions using the acquired review text as training data.

[1483] Search and Display

[1484] A user accesses a website from a terminal and enters a search query. The terminal sends the search query to the server, which searches the database to obtain relevant reviews and rankings, and generates a web page to display to the user. The user then browses the reviews displayed as search results.

[1485] Emotion engine integration

[1486] The server integrates an emotion engine into the review information collection and filtering process. It performs sentiment analysis on the review data and prioritizes filtering of reviews with positive sentiment. This procedure allows the server to provide more reliable and useful information to users.

[1487] The emotion engine also analyzes word-of-mouth information related to search queries from devices, and prioritizes displaying information with positive sentiment to users.

[1488] Emotion-based advertising

[1489] The server monitors the user's real-time emotions with an emotion engine and dynamically changes the advertising content based on those emotions, thereby presenting ads that best fit the user's emotional state and improving advertising effectiveness.

[1490] Reservation System

[1491] Users can make reservations directly from the store or product introduction page. They enter the required information (e.g., user ID, reservation time, etc.) into the form on their terminal and send it to the server. The server stores the received reservation information in a database and notifies the user that the reservation was successful. A reservation success page is generated and displayed to the user.

[1492] Specific examples of processing

[1493] For example, when a user searches for a restaurant, the server collects reviews of that restaurant and analyzes them using an emotion engine. It filters out only the positive reviews and automatically generates a review based on them. When a user enters a search query about a specific dish, the server prioritizes the display of positive reviews related to the query.

[1494] In this way, this system automatically generates high-quality content based on word-of-mouth information and provides users with the most appropriate information. In addition, by integrating an emotion engine, it is possible to provide more reliable information and improve advertising effectiveness.

[1495] The processing flow will be explained below.

[1496] Processing steps of a system that combines emotion engines

[1497] Step 1:

[1498] The server retrieves review information from the Internet. Specifically, it sends an HTTP request to the target review site and retrieves the HTML data.

[1499] Step 2:

[1500] The server parses the HTML data and parses it into a DOM structure to extract review scores and text, using specific CSS selectors and tags to identify the data it needs.

[1501] Step 3:

[1502] The server stores the extracted word-of-mouth information in a database, which contains fields such as "store name," "product name," "score," and "text."

[1503] Step 4:

[1504] The server retrieves all reviews from the database and uses an appropriate SQL query to select all records.

[1505] Step 5:

[1506] The server analyzes the acquired reviews using a sentiment engine and adds a sentiment score. The sentiment engine analyzes the text of each review and generates a sentiment score such as positive, negative, or neutral.

[1507] Step 6:

[1508] The server filters the reviews based on the sentiment score, specifically selecting reviews with a positive sentiment score (e.g., a score of 4 or higher).

[1509] Step 7:

[1510] The server sorts the filtered reviews by score and creates a ranking, which results in a list of stores and products with the highest ratings.

[1511] Step 8:

[1512] The server automatically generates store and product descriptions based on the ranked reviews. It uses a natural language generation tool to generate high-quality descriptions using the review text as training data.

[1513] Step 9:

[1514] A user accesses a website from a device and enters a search query, which may be for a specific store or product.

[1515] Step 10:

[1516] The device sends a search query to the server, which passes the query entered by the user to the server.

[1517] Step 11:

[1518] The server searches the database based on the search query to retrieve relevant reviews and rankings. The search results include reviews that are recognized as positive by the sentiment engine.

[1519] Step 12:

[1520] The server generates a web page based on the search results to display to the user, including the generated testimonial and ranking information.

[1521] Step 13:

[1522] The user can view the displayed introductions and rankings, and check detailed store and product information as needed. Specifically, they can access the introduction page.

[1523] Step 14:

[1524] Users make reservations directly from the store or product introduction page, entering necessary information such as user ID and reservation time into the reservation form.

[1525] Step 15:

[1526] The terminal sends the entered reservation information to the server. When the user submits the form, the reservation request is passed to the server.

[1527] Step 16:

[1528] The server stores the received reservation information in the database and executes an SQL query to insert the reservation information into the reservation table.

[1529] Step 17:

[1530] The server notifies the user that the reservation was successful by generating a reservation success page and sending it to the terminal.

[1531] Step 18:

[1532] The server monitors the user's emotions in real time and displays appropriate advertisements based on those emotions. The emotion engine analyzes the user's emotions and dynamically changes the advertisement content.

[1533] In this way, the system generates high-quality content based on word-of-mouth information and user sentiment analysis, providing optimal information to users and generating revenue.

[1534] Example 2

[1535] 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."

[1536] Conventional word-of-mouth information collection systems have had the problem of not being able to adequately evaluate or filter the collected word-of-mouth information, making it difficult to provide useful information to users. Furthermore, since they do not evaluate word-of-mouth information using an emotion engine or dynamically display advertisements based on the user's emotional state, it has been impossible to improve the reliability of word-of-mouth information or the effectiveness of advertisements.

[1537] 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.

[1538] In this invention, the server includes a means for collecting word-of-mouth information from the Internet, a means for storing the collected word-of-mouth information in a database, and a means for retrieving word-of-mouth information from the database and filtering out positive reviews. This makes it possible to provide users with highly reliable, positive word-of-mouth information. Furthermore, the server also includes a means for evaluating word-of-mouth information and user search queries using a sentiment analysis engine and preferentially displaying positive information, a means for dynamically changing advertisements based on the user's emotional state, a means for notifying the user based on the results of the sentiment analysis by the sentiment engine, and a means for generating testimonials using a generative AI model, thereby improving the reliability of word-of-mouth information and advertising effectiveness.

[1539] "Word-of-mouth information" refers to information posted online by ordinary consumers that includes their evaluations and opinions about products and services.

[1540] A "database" is a digital storage system for systematically storing and managing collected word-of-mouth information.

[1541] "Filtering" is the process of selecting collected word-of-mouth information that meets specific criteria (e.g., positive reviews).

[1542] "Automatic generation" is the process of generating text or content using a computer program without human intervention.

[1543] "Display" refers to the act of visually presenting the generated testimonials and filtered word-of-mouth information to the user.

[1544] A "sentiment analysis engine" is software that automatically evaluates the sentiment (positive, negative, neutral, etc.) of text data.

[1545] "Advertisement" refers to content that presents information about products or services to users for promotional purposes.

[1546] A "generative AI model" is a trained model that uses artificial intelligence techniques to generate text or content.

[1547] A "search query" is a keyword or phrase that a user enters into a search engine or system to search for information.

[1548] "Positive reviews" are reviews that have a high rating (e.g., a score of 4 or higher) and contain positive opinions and emotions.

[1549] "Dynamic change" refers to the automatic change of display content and behavior in real time according to conditions.

[1550] MODE FOR CARRYING OUT THE INVENTION

[1551] The present invention is a system based on a client-server model, where the server is the central point responsible for data collection, filtering, content generation and display, while the terminals act as the interface with the user.

[1552] Data collection

[1553] The server collects review information from the Internet. Specifically, it sends an HTTP request to the target website and retrieves the HTML data. This process uses the Apache HttpClient library. The retrieved HTML data is parsed into a DOM structure using JSoup, and the review score and text are extracted.

[1554] Data analysis

[1555] The server analyzes the parsed HTML data using the JSoup library and extracts the review scores and text. The extracted data is stored in a database such as MySQL or PostgreSQL. Data is stored in the database using JDBC.

[1556] Data Filtering

[1557] The server retrieves all reviews from the database and filters out positive reviews (e.g., scores above 4). It uses an SQL query to extract only records that meet the specified criteria. The extracted data is stored as rankings in an in-memory database such as Redis or Elasticsearch.

[1558] Content Generation

[1559] The server automatically generates testimonials based on the filtered review information using a natural language generation model (e.g., GPT-3 or BERT). By using the review text as training data and inputting prompts into the generative AI model, high-quality testimonials are generated.

[1560] Search and Display

[1561] A user accesses a website from a device (e.g., a PC or smartphone) and enters a search query. The device sends this search query to the server, which searches a database to return relevant reviews and rankings, and generates a web page to display to the user. The user can then view the reviews displayed as search results.

[1562] sentiment analysis

[1563] The server uses a sentiment analysis engine (e.g., TextBlob or VADER) to filter reviews. By performing sentiment analysis, it prioritizes filtering of positive reviews and provides reliable information.

[1564] Emotion-based advertising

[1565] The server monitors the user's emotional state in real time and dynamically changes the advertisements based on that emotion. It uses an emotion engine to evaluate the user's emotions and uses Google Ads and Facebook Ads APIs to display the most appropriate advertising content.

[1566] Reservation System

[1567] The user enters the necessary information (e.g., user ID, reservation time, etc.) into the form on the terminal and sends it to the server. The server stores the reservation information in a database and notifies the user that the reservation was successful. A reservation success page is also generated at the same time and displayed to the user.

[1568] Prompt Sentence Examples

[1569] "Generate testimonials with positive reviews for this restaurant. The reviews are: [list of reviews]"

[1570] "Please suggest optimal ad content based on the user's emotional state. The user's emotional state is: [user's emotional data]"

[1571] In this way, this system automatically generates high-quality content based on word-of-mouth information and provides users with the most appropriate information. In addition, by integrating an emotion engine, it provides more reliable information and improves advertising effectiveness.

[1572] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1573] Step 1:

[1574] The server collects reviews from the Internet. As input, it receives the URLs of target websites and sends an HTTP request to retrieve HTML data. Using the Apache HttpClient library, it sends a GET request and receives a response with HTML data. As output, it generates the retrieved HTML data. Specifically, it creates an instance of HttpClient and sends a GET request to the specified URL.

[1575] Step 2:

[1576] The server parses the retrieved HTML data. As input, it receives the HTML data retrieved in step 1 and parses it into a DOM structure using the JSoup library. This allows it to extract review scores and text. As output, it generates a list of the extracted scores and text. Specifically, it extracts review scores and text from the Document object parsed by JSoup using the specified CSS selector.

[1577] Step 3:

[1578] The server stores the extracted review information in a database. As input, it receives the scores and text list extracted in step 2 and stores them in a database such as MySQL or PostgreSQL. It connects to the database using JDBC and inserts the data. As output, review information stored in the database is generated. Specifically, it executes an insert SQL statement using PreparedStatement and stores the review scores and text in the corresponding tables in the database.

[1579] Step 4:

[1580] The server retrieves all reviews from the database and filters out the positive ones. As input, it takes all reviews stored in the database and executes a SQL query to filter reviews with a score of 4 or higher. As output, it generates a list of reviews that are determined to be positive. Specifically, it uses a Statement object to execute a SELECT query and extracts records that match the criteria.

[1581] Step 5:

[1582] The server automatically generates testimonials using a generative AI model based on the filtered reviews. As input, it receives a list of filtered reviews and generates a prompt. The testimonials are generated using natural language generation models such as GPT-3 and BERT. As output, a high-quality testimonial is generated. Specifically, the prompt is input to the generative AI model and the generated text is obtained as a response.

[1583] Step 6:

[1584] A user accesses a website from a terminal and enters a search query. The search query entered by the user is received as input and sent to the server. The terminal then sends the search query to the server as a POST request. As output, the search results are displayed to the user. Specifically, the system retrieves the search query from an HTML form and generates an HTTP request to send to the server.

[1585] Step 7:

[1586] The server uses a sentiment analysis engine to evaluate reviews and search queries. As input, it receives collected reviews and search queries from users, and calculates a sentiment score using a sentiment analysis library such as TextBlob or VADER. As output, information rated as positive is displayed preferentially. Specifically, text is input into the analysis library, its sentiment score is calculated, and filtering is performed.

[1587] Step 8:

[1588] The server dynamically changes ads based on the user's emotional state. It receives user emotional data as input and dynamically selects ad content. It uses Google Ads or Facebook Ads API to retrieve and display the most suitable ad. The output is an ad optimized for the user's emotions. Specifically, it calls the advertising API based on the user's emotional data and renders the retrieved ad data for display.

[1589] Step 9:

[1590] A user makes a reservation through a website. As input, the information entered by the user in the reservation form (user ID, reservation time, etc.) is received and sent to the server. The server stores this information in a database and notifies the user of the reservation result. As output, a notification that the reservation was successful is displayed to the user. Specifically, the system retrieves information from the reservation form, generates an HTTP request to send to the server, stores the information in the database on the server side, and then generates a response notifying the result.

[1591] (Application example 2)

[1592] 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."

[1593] Conventional review information collection systems only filter positive reviews and are unable to provide optimal information based on the user's emotional state. Furthermore, they are unable to centrally handle facility and product reservation functions, limiting the user experience. This has created challenges in effectively utilizing review information and improving user convenience.

[1594] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1595] In this invention, the server includes means for collecting word-of-mouth information from the Internet, means for storing the collected word-of-mouth information in a database, means for retrieving word-of-mouth information from the database and filtering out positive word-of-mouth information, means for automatically generating a facility or product introduction text based on the filtered word-of-mouth information, means for displaying the generated text on a website, means for dynamically displaying advertisements that are optimal for the user's emotional state using a sentiment analysis module, and means for receiving data for making reservations for facilities or products from a terminal and storing the data in the database. This allows users to view high-quality content based on positive word-of-mouth information, and by receiving advertisements that are tailored to their emotions, the effectiveness of the advertisements is improved, making it possible for users to easily make reservations for facilities or products.

[1596] "Word-of-mouth information" is data that includes user ratings and opinions posted on the Internet.

[1597] A "database" is a system for storing and managing data in a structured way.

[1598] "Positive reviews" are reviews with favorable content that have a rating above a certain score.

[1599] "Filtering" is a method of selecting data based on specific conditions.

[1600] "Facility or product introduction text" is a description of a facility or product that is automatically generated based on filtered word-of-mouth information.

[1601] A "sentiment analysis module" is a software component for detecting and classifying emotions from text data.

[1602] "Dynamic display of advertisements" means that advertisement content is displayed while changing in response to the user's real-time emotional state.

[1603] "Data for reserving a facility or product" refers to information required when a user makes a reservation (e.g., user ID, reservation time, etc.).

[1604] A "terminal" is a computing device through which a user accesses the Internet.

[1605] MODE FOR CARRYING OUT THE INVENTION

[1606] System Overview

[1607] The system for implementing this invention collects word-of-mouth information, filters it, analyzes its sentiment, generates content, and displays it on a user terminal. The system is mainly composed of a server, a database, a sentiment analysis module, and a user terminal.

[1608] Hardware and software used

[1609] Server: Cloud server such as AWS EC2

[1610] Database: SQLite or AWS RDS

[1611] Sentiment analysis module: TextBlob or AWS Comprehend

[1612] Scraping tool: BeautifulSoup

[1613] User interface: Web browser or smartphone application (e.g., Flask)

[1614] Processing flow

[1615] Server-side processing

[1616] The server collects reviews from the Internet and stores them in a database. Specifically, it uses BeautifulSoup to retrieve HTML data from target websites, parses the data, and extracts review information. The extracted reviews are then stored in a structured format in the database.

[1617] The server retrieves the reviews from the database and uses TextBlob to filter the positive reviews. The positive reviews are sorted by score and stored as a ranking. Furthermore, it utilizes a sentiment analysis module to monitor the user's emotional state and dynamically change the advertising content based on the user's emotion.

[1618] Processing on the user terminal side

[1619] A user inputs a search query through a website or smartphone application. The input query is sent to a server, which retrieves related reviews and generated introductory text and displays them to the user. The user can then use the displayed reviews and introductory text to check details about the facility or product and view advertisements. Furthermore, the user can also make reservations for the facility or product within the application.

[1620] Specific examples

[1621] For example, when a user searches for a restaurant, the server collects reviews related to that restaurant and performs sentiment analysis. It filters out only positive reviews and automatically generates high-quality restaurant descriptions based on that information. When a user enters a search query about a specific dish, the server prioritizes displaying related positive reviews.

[1622] Prompt Sentence Examples

[1623] Filter reviews with positive sentiment from word of mouth information and generate high-quality descriptions of restaurants and dishes. The filtered information format is: [restaurant name, score, review text].

[1624] This system allows users to view high-quality content based on positive word-of-mouth, and by displaying advertisements that are tailored to their emotions, advertising effectiveness is improved, making it possible to easily reserve facilities and products.

[1625] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1626] Step 1:

[1627] The server collects reviews from the target website. Specifically, the server sends an HTTP request and receives the website's HTML data.

[1628] (Input: URL, Output: HTML data). Analyze the received HTML data using BeautifulSoup and extract the reviews.

[1629] (Input: HTML data, Output: Reviews).

[1630] Step 2:

[1631] The server stores the extracted reviews in a structured format in a database.

[1632] (Input: review information, output: data stored in a database). Specifically, the server connects to a database such as SQLite and inserts the review information into a table.

[1633] Step 3:

[1634] The server retrieves reviews from the database and filters out positive reviews using a sentiment analysis module (e.g., TextBlob).

[1635] (Input: review information in the database, Output: positive reviews). The server calculates a sentiment score for each review using TextBlob and extracts only reviews with a positive score (e.g., 4 or higher).

[1636] Step 4:

[1637] The server automatically generates facility or product introduction text based on the filtered reviews.

[1638] (Input: positive reviews, Output: introduction text for the facility or product). Specifically, the server uses a natural language generation tool (e.g., a generative AI model) to automatically generate high-quality introduction text. An example of a prompt is as follows:

[1639] Filter reviews with positive sentiment from user reviews and generate high-quality descriptions of restaurants and cuisines. The filtered information format is: [restaurant name, score, review text].

[1640] Step 5:

[1641] A user uses a device to enter a search query through a website or smartphone application

[1642] (Input: search query, output: sending query to server). Specifically, the device accepts user input and sends the search query to the server.

[1643] Step 6:

[1644] The server retrieves relevant reviews and generated testimonials from a database based on the received search query and generates a web page to display to the user.

[1645] (Input: search query, output: search result page). Specifically, the server queries the database for relevant information and generates it as an HTML page.

[1646] Step 7:

[1647] The server utilizes a sentiment analysis module to monitor the user's emotional state and dynamically change the advertising content based on the emotional state.

[1648] (Input: user behavior data, output: dynamic advertising content). Specifically, the server collects user behavior data, analyzes it using a sentiment analysis module, and displays appropriate advertising in real time.

[1649] Step 8:

[1650] The user inputs data for making a reservation for a facility or product using the terminal and sends the data to the server.

[1651] (Input: reservation data, Output: sending data to the server) In concrete terms, the user enters the necessary information into the reservation form and sends it to the server.

[1652] Step 9:

[1653] The server saves the received reservation data in the database and notifies the user that the reservation was successful.

[1654] (Input: reservation data, Output: reservation success message). Specifically, the server saves the reservation data in the database and generates a reservation success page to display to the user.

[1655] This allows users to view high-quality content based on positive word-of-mouth, and by receiving advertisements that match their emotions, advertising effectiveness is improved, making it possible to easily reserve facilities and products.

[1656] 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.

[1657] 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.

[1658] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1659] 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.

[1660] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1661] 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.

[1662] 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).

[1663] 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.

[1664] 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."

[1665] 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.

[1666] 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).

[1667] 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.

[1668] 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.

[1669] 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.

[1670] 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.

[1671] 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.

[1672] 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.

[1673] 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.

[1674] 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.

[1675] 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.

[1676] 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.

[1677] The following is further disclosed regarding the above embodiment.

[1678] (Claim 1)

[1679] A means of collecting word-of-mouth information from the Internet,

[1680] A means for storing the collected word-of-mouth information in a database;

[1681] A means of retrieving review information from the database and filtering positive reviews;

[1682] A means for automatically generating store or product descriptions based on the filtered word-of-mouth information;

[1683] means for displaying the generated testimonial on a website;

[1684] A system including:

[1685] (Claim 2)

[1686] The system according to claim 1, wherein a ranking is created based on the scores of the collected word-of-mouth information, and a testimonial is generated based on the ranking.

[1687] (Claim 3)

[1688] 2. The system according to claim 1, which accepts a search query from a user terminal and displays an introduction to a corresponding store or product.

[1689] "Example 1"

[1690] (Claim 1)

[1691] A means of collecting word-of-mouth information from the Internet,

[1692] A means for storing the collected word-of-mouth information in a database;

[1693] A means of retrieving review information from the database and filtering positive reviews;

[1694] A means for automatically generating store or product descriptions based on the filtered word-of-mouth information;

[1695] means for displaying the generated testimonial on a website;

[1696] A means for a user to access a website from a terminal and enter a search query;

[1697] A means for displaying rankings and testimonials of relevant stores or products based on a user's search query;

[1698] A method for displaying advertisements based on ranked reviews,

[1699] A means for inputting the necessary information into the reservation form and sending it to the server;

[1700] means for notifying the user that the reservation has been successful;

[1701] A system including:

[1702] (Claim 2)

[1703] The system according to claim 1, wherein a ranking is created based on the scores of the collected word-of-mouth information, and a testimonial is generated based on the ranking.

[1704] (Claim 3)

[1705] 2. The system according to claim 1, which accepts a search query from a user terminal and displays an introduction to a corresponding store or product.

[1706] "Application Example 1"

[1707] (Claim 1)

[1708] A means of collecting word-of-mouth information from the Internet,

[1709] A means for storing the collected word-of-mouth information in a database;

[1710] A means of retrieving review information from the database and filtering positive reviews;

[1711] A means for automatically generating store or product descriptions based on the filtered word-of-mouth information;

[1712] means for displaying the generated testimonial on a website;

[1713] A means for displaying the generated introduction on a smartphone application;

[1714] a means for users to make reservations through the application;

[1715] means for displaying advertisements based on user interests and behavior;

[1716] A system including:

[1717] (Claim 2)

[1718] The system according to claim 1, wherein a ranking is created based on the scores of the collected word-of-mouth information, and a testimonial is generated based on the ranking.

[1719] (Claim 3)

[1720] 2. The system according to claim 1, which accepts a search query from a user terminal and displays an introduction to a corresponding store or product.

[1721] "Example 2: Combining Emotion Engines"

[1722] (Claim 1)

[1723] A means of collecting word-of-mouth information from the Internet,

[1724] A means for storing the collected word-of-mouth information in a database;

[1725] A means of retrieving review information from the database and filtering positive reviews;

[1726] A method for automatically generating product and service introductions based on filtered word-of-mouth information,

[1727] means for displaying the generated testimonial on a website;

[1728] A method to use a sentiment analysis engine to evaluate reviews and user search queries and prioritize positive information.

[1729] means for dynamically modifying advertisements based on the emotional state of a user;

[1730] a means for notifying a user based on the emotion analysis result by the emotion engine;

[1731] a means for generating a testimonial using a generative AI model;

[1732] A system including:

[1733] (Claim 2)

[1734] The system according to claim 1, wherein a ranking is created based on the evaluation of the collected word-of-mouth information, and a testimonial is generated based on the ranking.

[1735] (Claim 3)

[1736] The system according to claim 1, which accepts a search query from a user terminal and displays a review based on the corresponding word-of-mouth information and rankings.

[1737] "Application example 2 when combining emotion engines"

[1738] (Claim 1)

[1739] A means of collecting word-of-mouth information from the Internet,

[1740] A means for storing the collected word-of-mouth information in a database;

[1741] A means of retrieving review information from the database and filtering positive reviews;

[1742] A means for automatically generating facility or product introduction text based on the filtered word-of-mouth information;

[1743] a means for displaying the generated text on a website;

[1744] means for dynamically displaying advertisements that best fit the emotional state of a user using a sentiment analysis module;

[1745] a means for receiving data for making a reservation for a facility or product from the terminal and storing the data in a database;

[1746] A system including:

[1747] (Claim 2)

[1748] The system according to claim 1, wherein a ranking is created based on the scores of the collected word-of-mouth information, and an introductory text is generated based on the ranking.

[1749] (Claim 3)

[1750] The system according to claim 1, which accepts a search query from a user terminal and displays a corresponding facility or product introduction text. [Explanation of symbols]

[1751] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting word-of-mouth information from the Internet, A means for storing the collected word-of-mouth information in a database; A means of retrieving review information from the database and filtering positive reviews; A means for automatically generating store or product descriptions based on the filtered word-of-mouth information; means for displaying the generated testimonial on a website; A system including:

2. The system according to claim 1, wherein a ranking is created based on the scores of the collected word-of-mouth information, and an introduction is generated based on the ranking.

3. The system according to claim 1, wherein the system receives a search query from a user terminal and displays an introduction to a corresponding store or product.

Images