System

Abstract

A system is provided.SOLUTION: A system comprising: means for transmitting word-of-mouth / review by a user; means for receiving the word-of-mouth / review by a server and storing it in a database; means for analyzing the stored word-of-mouth / review by an artificial intelligence engine and learning values and hobbies and preferences of the user; means for selecting another user having close values and a product highly evaluated by the user based on data learned by the server; means for transmitting the product selected by the server to a user terminal; and means for displaying the product received by the user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's society, where products, content, and services are overflowing, users often refer to word-of-mouth and reviews when making purchases or choices. However, the values ​​and circumstances of those who post reviews may not necessarily match their own, making it difficult to obtain useful information. This can lead to issues such as users being unable to make appropriate choices or being overwhelmed with information, making decision-making difficult. [Means for solving the problem]

[0005] This invention provides a system in which an artificial intelligence (AI) system learns a user's values, hobbies, and preferences based on word-of-mouth reviews and recommends highly rated products from other users with similar values. Specifically, the system includes a means for users to submit word-of-mouth reviews and recommendations, a server receiving and storing the reviews in a database, an AI engine analyzing the stored word-of-mouth reviews and recommendations to learn the user's values, hobbies, and preferences, a server selecting other users with similar values ​​and highly rated products based on the learned data, a server transmitting the selected products to the user's device, and a user device displaying the products received. This allows users to obtain appropriate information based on their own values, expanding their options and eliminating filter bubbles.

[0006] "Word of mouth reviews" are user ratings and opinions about specific products, content, or services recorded in the form of text or rating scores.

[0007] A "server" is a computer system that receives, stores, and processes data submitted by users.

[0008] An "artificial intelligence engine" is a computer program that analyzes user word-of-mouth and reviews to learn their values, hobbies, and preferences.

[0009] "Analysis" is the process of extracting information related to users' values, hobbies, and preferences from the text and evaluation scores contained in word-of-mouth reviews.

[0010] "Learning" is the process of updating a user's profile based on extracted information so that it can be used for future recommendations.

[0011] "Recommendation" is the act of presenting highly rated products or content from other users with similar values ​​to a specific user based on learned information.

[0012] "User" means a person or organization that posts a word-of-mouth / review and receives recommendations based on that word-of-mouth / review.

[0013] "Values" are specific thought and emotional tendencies held by individual users, and are criteria that influence the selection of products, content, and services.

[0014] "Interests" are specific activities, products, services, or content categories that a user prefers.

[0015] A "filter bubble" is a phenomenon in which users only receive information related to their own values ​​and interests, blocking out other diverse perspectives and information. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a system that uses word-of-mouth reviews "for yourself" to recommend the most suitable products and content to users. This system uses artificial intelligence to learn the user's values ​​and preferences based on the word-of-mouth reviews posted by the user, and recommends items that have been highly rated by other users with similar values, thereby assisting the user in decision-making. The system's program processing is described in detail below in natural language.

[0038] (Post a review)

[0039] Device: The user launches an application that displays a testimonial / review submission form. The submission form includes a text input field and a star rating slider. The user enters their opinion and rating about a specific product or service and sets the star rating. They then confirm the review and press the submit button.

[0040] Server: Receives the word-of-mouth and review data sent from the device. The received data is sent as structured data in JSON format, etc. The server then saves the review content in a database. The information saved includes the user ID, review content, star rating, and posting date and time. For example, if User A gives a five-star rating along with the comment, "The coffee at this cafe has a nice aroma and is relaxing," that data will be saved in the database.

[0041] (AI-based data analysis and learning)

[0042] Server: Notifies the AI ​​engine that newly posted review data has been received. The notified data is sent to the AI ​​engine for analysis.

[0043] AI model: The artificial intelligence engine analyzes the text of user reviews and extracts important keywords and sentiments. Using natural language processing (NLP) techniques, it extracts features such as "nice aroma" and "relaxing." The AI ​​model then learns these features and adds the user's values ​​and preferences to the user profile. For example, preferences such as "coffee aroma" and "relaxing" are added to User A's profile.

[0044] (Generating recommendation content)

[0045] Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model finds users with similar values ​​from the training database and selects products and content that those users have highly rated.

[0046] Server: The selected recommendation content is encoded in JSON format and sent to the user's device. For example, if user A is looking for a new cafe, the server will recommend a cafe called "Aroma Coffee," which has been highly rated by user B, who shares similar values.

[0047] (Display of recommendation content)

[0048] Device: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed within the application. This allows the user to select the recommended products and services based on the information.

[0049] This invention allows users to obtain useful information based on their own values ​​and preferences, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] Device: The user launches the application and is presented with a testimonial / review submission form, which includes a text input field and a star rating slider.

[0053] Step 2:

[0054] User: Enter your thoughts and ratings about the product or service in the text input field and set the rating using the star rating slider. For example, to review a cafe, you might write, "The coffee at this cafe is fragrant and relaxing," and set it to 5 stars.

[0055] Step 3:

[0056] Device: When the user checks the review content and presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[0057] Step 4:

[0058] Server: Receives word-of-mouth and review data sent from the device. The received data is temporarily stored in memory.

[0059] Step 5:

[0060] Server: The received data is stored in a database. This includes the user ID, review text, star rating, and posting date and time. For example, an SQL query like the following is executed: INSERT INTO reviews (user_id, review_text, star_rating, created_at) VALUES (...).

[0061] Step 6:

[0062] Server: Notifies the AI ​​engine that a new post has been made. When notifying, an API is called to pass the saved word-of-mouth and review data to the AI ​​engine.

[0063] Step 7:

[0064] AI model: The artificial intelligence engine analyzes the received word-of-mouth and reviews. Natural language processing (NLP) techniques are used to extract keywords and emotions. For example, characteristics such as "nice scent" and "relaxing" are detected.

[0065] Step 8:

[0066] AI model: Learns the user's values, hobbies, and preferences based on the extracted features and adds them to the user profile. "Coffee aroma" and "Relaxation" are added to User A's profile.

[0067] Step 9:

[0068] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[0069] Step 10:

[0070] AI model: Based on learning data, it searches for other users with similar values. It finds User B with a similar profile.

[0071] Step 11:

[0072] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[0073] Step 12:

[0074] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[0075] Step 13:

[0076] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[0077] Step 14:

[0078] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[0079] Example 1

[0080] 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."

[0081] Conventional word-of-mouth and review systems have had difficulty providing users with truly useful information. In particular, they have been inadequate in providing personalized recommendations based on the user's values ​​and interests. Furthermore, they have the problem of filter bubbles, which can limit new discoveries and the breadth of options. The purpose of this invention is to solve these issues and provide users with more valuable information.

[0082] 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.

[0083] In this invention, the server includes a means for users to send rating information, a means for the server to receive the rating information and store it in a database, a means for an artificial intelligence engine to analyze the stored rating information and learn the user's values ​​and interests, a means for the server to select other users with similar values ​​and products that the users have highly rated based on the learned data, a means for the server to send the products selected by the server to a user terminal, and a means for the user terminal to display the products received. This allows users to obtain useful information based on their own values ​​and interests, enabling new discoveries and a variety of options.

[0084] "User" means a person who uses the System to post reviews and receive product and content recommendations.

[0085] "Rating Information" means text reviews and star ratings submitted by users about products or services.

[0086] "Server" means a computer system that receives and stores rating information, manages analysis results, and generates recommendations.

[0087] "Database" means data storage for storing and managing rating information and user profiles.

[0088] An "artificial intelligence engine" is a machine learning model or algorithm that analyzes stored rating information and learns user values ​​and interests.

[0089] "Values" or "Interests" refer to the preferences and priorities that users express through their ratings information.

[0090] A "recommended list" is a list of products and services that have been highly rated by other users, selected by an artificial intelligence engine based on the user's values ​​and interests.

[0091] "Natural language processing technology" is a computer technology for analyzing text data and extracting important keywords and emotions.

[0092] "User terminal" refers to a device, such as a computer or smartphone, that a user uses to post rating information and receive and display recommendations.

[0093] The present invention is a system that uses an artificial intelligence engine to recommend personalized products and services based on evaluation information (word of mouth reviews) posted by users. A specific embodiment of this system is described below.

[0094] System Overview

[0095] 1. User-submitted evaluation information

[0096] - Device: The user launches the application on a computer or smartphone. The application displays a form for submitting a review. The form contains a text input field and a star rating slider, allowing the user to enter their opinion and rating about a specific product or service and set the star rating. The user then confirms the review and presses the submit button.

[0097] - Example: A user writes a review saying, "The coffee at this cafe is aromatic and relaxing," and gives it a 5-star rating.

[0098] 2. Receipt and storage of rating information by the server

[0099] - Server: Receives rating information sent from the device in JSON format. The received data is stored in a database on the server. The stored information includes the user ID, review content, star rating, and posting date and time.

[0100] - Specific technology: The server uses, for example, a "MySQL" database.

[0101] 3. Data analysis and user profile updating using an AI engine

[0102] - Server: Notifies the AI ​​engine that newly posted rating information has been received and forwards the data for analysis.

[0103] - AI model: The AI ​​engine uses natural language processing (NLP) technology to analyze the text of the evaluation information, extracting characteristics such as "nice scent" and "relaxing," and adding the user's values ​​and interests to the profile.

[0104] - Specific technology: Natural language processing libraries such as "Transformers" can be used for AI models.

[0105] - Example: Preferences such as "coffee aroma" and "relaxation" are added to a user's profile.

[0106] 4. Server-generated and transmitted recommendations

[0107] - Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model finds users with similar profiles from the learning database and selects products and services that those users have highly rated.

[0108] - Recommendation generation: The selected recommendation content is encoded in JSON format and sent to the user's device.

[0109] - Example: If a user is looking for a new cafe, the AI ​​engine will recommend a cafe called "Aroma Coffee," which has been highly rated by other users with similar values.

[0110] - Example prompt: In response to the review, "The coffee at this cafe is fragrant and relaxing," what kind of cafe would you recommend?

[0111] 5. Display of recommendations by device

[0112] - Device: The recommendation received from the server is displayed to the user. The application displays "Aroma Coffee, a cafe highly rated by other users" for the user to refer to.

[0113] This system allows users to obtain useful information based on their values ​​and interests, allowing them to enjoy new discoveries and diverse options. It also reduces the problem of filter bubbles and provides a more satisfying consumption experience.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] User: The user launches the application and opens the testimonial / review submission form. The form contains a text input field and a star rating slider, allowing the user to enter their opinion about a specific product or service and set a star rating. Once they're done, they press the submit button.

[0117] Input: User-entered text review and star rating

[0118] Output: The request to send the post to the server

[0119] Specific action: The user enters "The coffee at this cafe is fragrant and relaxing" and sets a 5-star rating.

[0120] Step 2:

[0121] Server: Receives the rating information sent from the user device. The rating information is sent in JSON format, and the server parses it and stores it in a database.

[0122] Input: JSON format rating information (e.g., user ID, review content, star rating, posting date and time)

[0123] Output: Evaluation information stored in a database

[0124] Specific operation: The server saves User A's review, "The coffee at this cafe is fragrant and relaxing," with a five-star rating, in the database.

[0125] Step 3:

[0126] Server: Notifies the AI ​​engine that new evaluation information has been received. The server forwards the data to the AI ​​engine for analysis.

[0127] Input: Newly received rating information

[0128] Output: Evaluation information sent to the AI ​​engine

[0129] Specific operation: The server notifies the AI ​​engine of a new review from user A and sends the data.

[0130] Step 4:

[0131] AI Model: The AI ​​engine analyzes the review text using natural language processing (NLP) techniques to extract key keywords and sentiment, then adds these findings to the user profile.

[0132] Input: Evaluation information text data

[0133] Output: Updated user profile

[0134] Specific operation: The AI ​​model extracts the keywords "nice aroma" and "relaxing" and adds the preferences for "coffee aroma" and "relaxation" to User A's profile.

[0135] Step 5:

[0136] Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model then finds users with similar values ​​from the training database and selects products and services that those users have highly rated.

[0137] Input: User request

[0138] Output: A list of recommended products and services

[0139] Specific operation: When a user is looking for a new cafe, the server sends a request to the AI ​​engine, and the AI ​​model selects "Aroma Coffee," a cafe that User B highly rated.

[0140] Step 6:

[0141] Server: The selected recommendations are encoded in JSON format and sent to the user's device.

[0142] Input: Recommendation list

[0143] Output: Recommendation content in JSON format sent to the user device

[0144] Specific operation: The server sends "Aroma Coffee" as a recommendation to User A's terminal.

[0145] Step 7:

[0146] Terminal: The user terminal displays the recommendations received from the server.

[0147] Input: Recommendation received from the server

[0148] Output: Recommendations displayed to the user

[0149] Specific operation: "Cafes highly rated by other users: Aroma Coffee" will be displayed on User A's device, and the user can use it as a reference.

[0150] The above is the specific flow and operation of each processing step.

[0151] (Application example 1)

[0152] 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."

[0153] Conventional recommendation systems based on word-of-mouth and reviews have the problem of not being able to fully respond to the individual values ​​and tastes of users. It is also difficult to provide recommendations that match the user's interests in real time, which has prevented them from increasing user satisfaction. Furthermore, they lack the functionality to effectively utilize reviews from other users with similar values ​​to recommend new products and services. This has led to problems such as users finding the most suitable products and content.

[0154] 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.

[0155] In this invention, the server includes a means for providing recommendations based on individual values ​​in real time for categories that the user has shown interest in, a means for recommending new products based on reviews by other users with similar values, and a means for receiving product recommendations in real time, which makes it possible to recommend optimal products and content according to the user's individual values, hobbies, and preferences, thereby significantly improving user satisfaction.

[0156] "Word of mouth / review" refers to information in which users write their evaluations of specific products or services.

[0157] "Server" means a computer system that receives and stores data sent by users, and processes and analyzes it as necessary.

[0158] A "database" is a system for storing information such as the content of word-of-mouth reviews, user IDs, star ratings, and posting dates and times in a structured format.

[0159] An "artificial intelligence engine" is a software or hardware component that analyzes posted word-of-mouth and reviews and learns users' values, hobbies, and preferences.

[0160] "Natural language processing technology" is a technology that analyzes meaning and emotions from text data and extracts important keywords.

[0161] "Other users with similar values" are other users who are determined to have similar values, hobbies, and preferences based on the analysis of posted word-of-mouth and reviews.

[0162] "Product selection" means determining products or services that meet specific conditions based on learned user data.

[0163] A "user device" is a device such as a smartphone or tablet that receives recommended products or content and displays them to the user.

[0164] "Providing recommendations in real time" means presenting the most appropriate products and services to users on the spot based on their current interests and concerns.

[0165] "Recommending new products" means suggesting products or services that the user is not yet aware of, based on high ratings from other users who share similar values.

[0166] This invention is a system that recommends optimal products and content to users based on word-of-mouth reviews. Specific embodiments for carrying out this invention are described below.

[0167] System Program Overview

[0168] The server receives user testimonials and reviews and stores them in a database. This data is stored as structured data in JSON format or similar. The server plays a central role in the system, receiving, storing, and analyzing testimonials and reviews, selecting recommended products, and sending the recommended products. The hardware used includes a database server and an application server. The software used includes Python, Django, MySQL, and other programs.

[0169] Artificial intelligence engine and natural language processing technology

[0170] The server then sends the received customer review data to an AI engine, which then uses natural language processing (NLP) techniques to analyze the customer review text and extract key keywords and sentiment. This analysis is performed using libraries such as TensorFlow and PyTorch. The extracted feature keywords are added to the user profile and used for subsequent recommendations.

[0171] For example, if a user posts a review saying, "The coffee at this cafe has a wonderful aroma and is relaxing," the AI ​​engine will extract keywords such as "a wonderful aroma" and "relaxing." These keywords will be added to the user's profile.

[0172] Generate and send product recommendations

[0173] When a user requests a recommendation for a new product or service, the server instructs the AI ​​engine to search for other users with similar values ​​and select products or services that those users have highly rated. The selected products or services are then sent from the server to the user's device and displayed to the user.

[0174] For example, if a user is searching for a product related to cafes, the AI ​​engine will recommend a cafe called "Aroma Coffee," which has been highly rated by other users with similar values. This recommendation will be displayed to the user in the application as "Cafe highly rated by User B: Aroma Coffee."

[0175] Real-time recommendation function

[0176] The system will include the ability to provide users with personalized recommendations in real time, so that when a user searches for a product or category, the system will instantly recommend the most suitable products and services based on their values, tastes, and preferences.

[0177] Examples of concrete examples and prompts

[0178] Users post reviews about "stylish cafes," and the AI ​​learns from them and reflects them in their profiles. Next, when a user searches for products in the "cafe" category, "Aroma Coffee" is recommended based on reviews from other users with similar values.

[0179] An example of a prompt sentence to input to the generative AI model is as follows:

[0180] We will create an AI model that learns a user's values ​​and preferences based on word of mouth and reviews, and recommends new products. We will perform NLP analysis on the content of the user's reviews, extract characteristic keywords, and add them to their profile. We will then recommend products that have been highly rated by other users with similar values. We will implement this model in Python.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] Users submit their testimonials and reviews.

[0184] Specific operation: The user launches the smartphone app, enters text and a star rating into the word-of-mouth / review submission form, and presses the submit button to send the input to the server.

[0185] Input: Text review, star rating

[0186] Output: Customer reviews sent to the server

[0187] Step 2:

[0188] The server receives the reviews and stores them in a database.

[0189] Specific operation: The server receives the data sent by the user in JSON format and stores it in a database, including the user ID, review content, star rating, posting date and time, etc.

[0190] Input: JSON formatted customer reviews

[0191] Output: Reviews stored in a database

[0192] Step 3:

[0193] The server notifies the AI ​​engine of new word-of-mouth and review data.

[0194] What it does: The server detects newly saved data and requests the AI ​​engine to analyze it.

[0195] Input: Newly saved customer review data

[0196] Output: Analysis request to AI engine

[0197] Step 4:

[0198] An artificial intelligence engine analyzes the text of reviews and extracts important keywords and sentiments.

[0199] How it works: The AI ​​engine uses TensorFlow and PyTorch to perform NLP analysis and extract characteristic keywords and emotional expressions from text reviews, such as "nice scent" and "relaxing."

[0200] Input: Text data of word-of-mouth reviews

[0201] Output: Extracted feature keywords and sentiment

[0202] Step 5:

[0203] The extracted characteristic keywords are added to the user profile.

[0204] How it works: The AI ​​engine updates the user profile based on the extracted keywords.

[0205] Input: Extracted feature keywords

[0206] Output: Updated user profile

[0207] Step 6:

[0208] A user requests recommendations for new products or services.

[0209] What happens: A user searches for a specific product category within a smartphone app, for example, by entering "cafe" as the category.

[0210] Input: Recommendation request

[0211] Output: Search query to the server

[0212] Step 7:

[0213] The server detects other users with similar values ​​and selects products and services that those users have given high ratings to.

[0214] Specific operation: The server has the AI ​​engine search for users with similar values ​​and selects products and services that those users have given high ratings to.

[0215] Input: Search query and user profile

[0216] Output: A list of recommended products or services

[0217] Step 8:

[0218] The server sends the selected products and services to the user's device.

[0219] Specific operation: The server encodes the selected product or service list in JSON format and sends it to the user's device.

[0220] Input: Recommended product or service list

[0221] Output: Data sent to the user's terminal

[0222] Step 9:

[0223] Display the products and services received by the user device.

[0224] Specific operation: The user device displays the received data on the screen, for example, "User B's highly rated cafe: Aroma Coffee."

[0225] Input: Data received from the server

[0226] Output: Recommended products or services displayed on the screen

[0227] Through the above steps, the present invention is able to recommend optimal products and content to users.

[0228] 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.

[0229] This invention is a system that learns a user's values, preferences, and emotions based on word-of-mouth reviews and recommends the most suitable products and content to the user. This system supports the user's decision-making by analyzing word-of-mouth reviews posted by the user using an artificial intelligence engine and an emotion engine, and recommending highly rated products from other users who share similar values. The system's program processing is described in detail below in natural language.

[0230] (Post a review)

[0231] Device: The user launches the application and is presented with a form for submitting a user review. The submission form includes a text input field and a star rating slider. The user enters their thoughts and evaluation of a specific product or service and sets a star rating. For example, a user might write a review of a cafe, saying, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[0232] User: Check the content of the word-of-mouth / review and press the post button.

[0233] (Data reception and storage)

[0234] Terminal: When the user presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[0235] Server: Receives word-of-mouth and review data sent from the device. Stores the received data in a database. Data stored includes the user ID, review content, star rating, posting date and time, etc. For example, if User A gives a five-star rating along with the comment, "The coffee at this cafe has a nice aroma and is relaxing," that data will be stored in the database.

[0236] (Data analysis and learning using AI and emotion engines)

[0237] Server: Notifies the AI ​​engine that newly posted customer reviews have been received. When notifying, passes the saved customer reviews to the AI ​​engine and emotion engine.

[0238] Emotion engine: Analyzes the text contained in word-of-mouth reviews and extracts emotions. The extracted emotions are expressed in a format such as positive or negative and sent to the server as analysis results. For example, a positive emotion is extracted from a review that reads, "The coffee at this cafe has a nice aroma and is relaxing."

[0239] AI model: The artificial intelligence engine analyzes word-of-mouth reviews based on the emotional information sent from the emotion engine. Natural language processing (NLP) technology is used to extract important keywords and emotions, and learn the user's values, hobbies, and preferences. For example, characteristics such as "nice scent" and "relaxing" are detected and added to User A's profile.

[0240] (Generating recommendation content)

[0241] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[0242] AI model: Based on learning data, it searches for other users with similar values. It also takes into account emotional information to find User B with a similar profile.

[0243] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[0244] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[0245] (Display of recommendation content)

[0246] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[0247] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[0248] This invention allows users to obtain useful information based on their values, tastes, and emotions, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[0249] The processing flow will be explained below.

[0250] Step 1:

[0251] Device: The user launches the application and is presented with a testimonial / review submission form, which includes a text input field and a star rating slider.

[0252] Step 2:

[0253] User: Enter your thoughts and ratings about the product or service in the text input field and set the rating using the star rating slider. For example, to review a cafe, you might write, "The coffee at this cafe is fragrant and relaxing," and set it to 5 stars.

[0254] Step 3:

[0255] Device: When the user checks the review content and presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[0256] Step 4:

[0257] Server: Receives word-of-mouth and review data sent from the device. The received data is temporarily stored in memory.

[0258] Step 5:

[0259] Server: The received data is stored in a database. This includes the user ID, review text, star rating, and posting date and time. For example, an SQL query like the following is executed: INSERT INTO reviews (user_id, review_text, star_rating, created_at) VALUES (...).

[0260] Step 6:

[0261] Server: Notifies the AI ​​engine and emotion engine that a new post has been made. When notifying, passes the saved word-of-mouth and review data for analysis.

[0262] Step 7:

[0263] Emotion engine: Analyzes text contained in reviews and extracts emotions. For example, it detects positive emotions in the comment, "The coffee at this cafe has a nice aroma and is relaxing."

[0264] Step 8:

[0265] Emotion engine: The extracted emotional information is sent to the server. For example, data containing the emotional information "positive" is returned to the server.

[0266] Step 9:

[0267] AI model: The artificial intelligence engine receives the emotional information and analyzes the text of the reviews. Natural language processing (NLP) techniques are used to extract keywords and emotions. For example, features such as "nice scent" and "relaxing" are extracted.

[0268] Step 10:

[0269] AI model: Based on the extracted features and emotional information, the AI ​​model learns the user's values, hobbies, and preferences and updates the user profile. Preferences such as "coffee aroma" and "relaxation" are added to User A's profile.

[0270] Step 11:

[0271] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[0272] Step 12:

[0273] AI model: Based on learning data, it searches for other users with similar values. It finds User B with a similar profile. It also takes into account emotional information when selecting users.

[0274] Step 13:

[0275] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[0276] Step 14:

[0277] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[0278] Step 15:

[0279] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[0280] Step 16:

[0281] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[0282] Example 2

[0283] 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."

[0284] Conventional recommendation systems have difficulty recommending appropriate products and content that accurately reflect users' ratings and preferences. Furthermore, when used by many users, recommendations are often not based on individual values ​​and emotions, resulting in a decline in user satisfaction. Furthermore, there is a lack of recommendation systems that take emotional information into account, and there is a need to improve the user experience.

[0285] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for a user to transmit rating information, a means for the server to receive the rating information and store it in an information collection device, a means for a machine learning engine to analyze the stored rating information and learn the user's values ​​and preferences, a means for the server to select other users with similar values ​​and products that the users have highly rated based on the learned data, a means for transmitting the products selected by the server to the user's information terminal, and a means for the user's information terminal to display the received products. This enables recommendations that accurately reflect the user's emotional information and preferences.

[0286] "Rating information" refers to feedback that a user gives about a particular product or service, and is typically expressed in the form of text content and star ratings.

[0287] A "server" is a computer system that receives data sent by a user and processes it.

[0288] The "information collection device" includes a database and a storage device installed in the server, and is a device for saving received evaluation information.

[0289] A "machine learning engine" is a computer program that analyzes received and stored rating information and executes algorithms or models to learn user values ​​and preferences.

[0290] "Natural language processing technology" is a technology that analyzes text data and extracts important keywords and emotions from it.

[0291] A "recommended list" is a list of products and services selected based on the user's values ​​and preferences.

[0292] A "user's information terminal" is an electronic device used by a user, such as a smartphone or computer, that displays data sent from the server.

[0293] "Other users with similar values" refers to other users who share the same tastes and behavioral patterns as a given user.

[0294] "Product" refers to the specific product or service recommended to a user.

[0295] "Means" refers to a method or device, or a combination thereof, for achieving a particular purpose.

[0296] The present invention relates to a system that recommends optimal products and content based on user evaluation information. The system of this invention is implemented using the following hardware and software: a server and a user's information terminal (such as a smartphone or PC). It also uses software such as an artificial intelligence engine, a machine learning engine using natural language processing technology, and an information collection device for data storage.

[0297] The main functions of the system are as follows: When a user submits rating information through the application, the information is sent to the server in JSON format. The server stores the received data in an information collection device. Next, a machine learning engine analyzes the data and learns the user's values ​​and preferences. This analysis uses natural language processing technology, and emotional information is also extracted.

[0298] Next, the server uses the learned data to select other users with similar values ​​and products that those users have highly rated. The selected products are sent from the server to the user's information terminal and displayed on the user's information terminal.

[0299] Specific examples are shown below.

[0300] First, a user submits a review of a specific product, writing, "The coffee at this cafe has a nice aroma and is relaxing," along with a rating of 5 stars. The server receives this review and stores it in a database. A machine learning engine then analyzes the review, extracting keywords such as "nice aroma" and "relaxing" as well as positive emotions, and adds them to the user's profile.

[0301] When the user then sends a request to "find a new cafe," the server searches for other users with similar values ​​and recommends products that those users have given high ratings to, such as a cafe called "Aroma Coffee." This recommendation information is sent in JSON format to the user's device, and is displayed as "Cafe highly rated by User B: Aroma Coffee."

[0302] Below are some example prompts to be input to the generative AI model:

[0303] "Analyze the following review posted by user A and extract sentiment and value information:

[0304] Review: "The coffee at this cafe is aromatic and relaxing." Star rating: 5 stars

[0305] Analyze various reviews, find users with a similar profile to User B, and recommend highly rated products. For example, recommend "Aroma Coffee," which User B highly rated.

[0306] This system enables recommendations that accurately reflect the user's emotional information and preferences, thereby increasing user satisfaction.

[0307] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0308] Step 1: Submit a review

[0309] Device: The user launches the application and opens the review submission form. The submission form includes a text input field and a star rating slider. The user enters their thoughts and evaluation of a specific product or service and sets a star rating. For example, a user might write a review of a cafe saying, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[0310] Input: User input of text and star rating.

[0311] Output: When the submit button is pressed, the entered data is passed to the following step.

[0312] Specific behavior: When the user presses the submit button, the application prepares the data to be sent in JSON format.

[0313] Step 2: Receiving and storing data

[0314] Terminal: When the submit button is pressed, the application sends the data in JSON format to the server.

[0315] Input: JSON formatted word-of-mouth and review data (user ID, review content, star rating, etc.).

[0316] Server: The server receives the word-of-mouth and review data sent from the device and stores it in an information collection device (database). The stored data includes the user ID, review content, star rating, posting date and time, etc.

[0317] Output: The saved data will be used for analysis in the next step.

[0318] Specific behavior: To confirm that the data was saved successfully, the success / failure of the save process is recorded in the log.

[0319] Step 3: Data analysis and learning using AI and emotion engines

[0320] Server: Notifies the AI ​​engine of newly posted word-of-mouth and review data.

[0321] Input: Customer reviews stored in a database.

[0322] Emotion engine: Analyzes the text of reviews and extracts emotional information such as positive and negative sentiment. This emotional information is sent back to the server.

[0323] AI model: The AI ​​engine analyzes user reviews based on emotional information and extracts important keywords and emotions, thereby learning user values ​​and preferences.

[0324] Output: The analysis results are reflected in the user's profile, and values ​​and preferences are updated.

[0325] Specific operation: The results of extracting emotional information and important keywords are recorded in a log and added to the user profile.

[0326] Step 4: Generate recommendations

[0327] Server: The user requests a new recommendation (e.g., "Find a new cafe").

[0328] Input: A user's profile and a new recommendation request.

[0329] AI model: Based on learning data, it searches for other users with similar values ​​and identifies users with similar profiles by taking into account emotional information. It then selects products and content that User B has highly rated. For example, it selects a cafe called "Aroma Coffee."

[0330] Output: Selected recommendations encoded in JSON format.

[0331] Specific operations: Generate a recommendation list, execute a test process to confirm the selection results, and record the generated recommendation list in a log.

[0332] Step 5: View your recommendations

[0333] Server: Sends the selected recommendations to the user's device.

[0334] Input: JSON format data of recommendation content.

[0335] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[0336] Output: The displayed recommendation.

[0337] Specific behavior: Display recommendations in a format that is easy for users to review and provide an interface for users to take the next action.

[0338] (Application example 2)

[0339] 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."

[0340] Conventional recommendation systems have difficulty accurately grasping a user's values ​​and preferences, and have therefore been unable to provide recommendations that meet individual needs. Furthermore, due to a lack of means to analyze emotional information, highly accurate recommendations based on the user's emotions have not been realized. As a result, user satisfaction is low and the filter bubble problem is likely to occur.

[0341] 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.

[0342] In this invention, the server includes: a means for users to send word-of-mouth reviews; a means for the server to receive the word-of-mouth reviews and store them in a database; a sentiment analysis engine to analyze the emotions contained in the word-of-mouth reviews and extract emotional information; an artificial intelligence engine to learn the user's values ​​and preferences based on the stored word-of-mouth reviews and emotional information; a means for the server to select other users with similar values ​​and products highly rated by those users based on the learned data; a means for transmitting the products selected by the server to a user terminal; and a means for the user terminal to display the products received. This enables highly accurate recommendations based on the user's values ​​and emotions.

[0343] "Means for users to submit word-of-mouth / reviews" refers to the functions and interfaces that allow users to input their ratings and opinions about products and services and send them to the server.

[0344] "Means by which the server receives the reviews and stores them in a database" refers to the functions and processes by which the server receives the reviews and comments sent by users and stores them in a database.

[0345] "Means for an emotion analysis engine to analyze emotions contained in word-of-mouth reviews and extract emotional information" refers to technology and software that analyzes emotional elements such as positive and negative emotions from word-of-mouth reviews and extracts them as data.

[0346] "Means for an artificial intelligence engine to learn a user's values, hobbies, and preferences based on saved word-of-mouth reviews and emotional information" refers to algorithms and programs that analyze saved word-of-mouth reviews and emotional information to learn a user's characteristics and preferences.

[0347] "Means for the server to select other users with similar values ​​and products that have been highly rated by those users based on learned data" refers to the function or process of selecting other users with similar values ​​and products that have been highly rated by those users based on learned data.

[0348] The "means for transmitting the selected product from the server to the user terminal" refers to the function or process for transmitting information about the selected product to the user terminal.

[0349] The "means for displaying the product received by the user terminal" is an interface for visually displaying the product information received by the user terminal to the user.

[0350] This invention is a system that learns a user's values, preferences, and emotions based on word-of-mouth and reviews, and recommends the most suitable products and content to the user. This system uses an artificial intelligence engine and a sentiment analysis engine to analyze word-of-mouth and reviews posted by the user, and recommends highly rated products from other users who share the same values. The system's program processing is explained in detail below.

[0351] Hardware and software used

[0352] Hardware

[0353] Smartphone

[0354] server

[0355] software

[0356] Python

[0357] Flask (server-side web framework)

[0358] TextBlob (emotional analysis)

[0359] JSON (data format)

[0360] Requests (HTTP request library)

[0361] User reviews and data processing

[0362] First, users submit testimonials and reviews about products and services through a smartphone application. The submission form includes a text input field and a star rating slider. For example, users can write, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[0363] Receiving and storing data on the server

[0364] When a user clicks the submit button, the entered user feedback and review data is sent to the server in JSON format. The data includes the user ID, review content, star rating, and posting date and time. The server stores the received data in a database.

[0365] Analysis using sentiment analysis engine and artificial intelligence engine

[0366] The server notifies the sentiment analysis engine of newly posted word-of-mouth and review data. The sentiment analysis engine analyzes the text and extracts emotional information, such as positive or negative. For example, a review that reads, "The coffee at this cafe has a nice aroma and is relaxing," would extract a positive sentiment.

[0367] Next, an artificial intelligence engine analyzes the reviews based on emotional information. Using natural language processing (NLP) technology, it extracts important keywords and emotions, learning the user's values, hobbies, and preferences. For example, characteristics such as "nice scent" and "relaxing" are detected and added to the user's profile.

[0368] Recommendation generation

[0369] The server receives a new recommendation request from a user. Based on the learning data, the AI ​​model searches for other users with similar values ​​and selects products that have been highly rated by users with similar profiles, taking into account emotional information. For example, it selects "Aroma Coffee," a cafe highly rated by User B.

[0370] Displaying recommendations

[0371] The selected recommendation is encoded as JSON data and sent to the user's device. The device then displays the received recommendation to the user. For example, it might say, "User B highly rated cafe: Aroma Coffee." The user can review the recommendation and decide what to do next.

[0372] Examples of concrete examples and prompts

[0373] Here are some examples of prompts to input to a generative AI model:

[0374] "Analyze user values ​​and sentiments based on the following reviews:

[0375] Review: The coffee at this cafe is aromatic and relaxing.

[0376] Extract the detected emotions and features that may represent values, interests, and preferences.

[0377] By using this prompt, the model can learn emotions and specific values ​​and recommend the best products for the user.

[0378] This invention allows users to obtain useful information based on their values, tastes, and emotions, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

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

[0380] Step 1:

[0381] Users submit their testimonials and reviews

[0382] Users post word-of-mouth reviews of products and services through a smartphone app. The input form includes a text field and a star rating slider. For example, a user might enter "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars. This is the input data. When the user presses the submit button, the data is sent to the server in JSON format.

[0383] Step 2:

[0384] The server receives the reviews and stores them in a database.

[0385] The server receives the testimonials and reviews sent by users. The data includes the user ID, review content, star rating, and posting date and time. The server parses the received data and saves it in a database. Specifically, it parses the received JSON data and stores it in the appropriate fields. The output data is a record saved in the database.

[0386] Step 3:

[0387] The sentiment analysis engine analyzes the emotions contained in word-of-mouth reviews and extracts emotional information.

[0388] The server notifies the sentiment analysis engine of newly posted word-of-mouth and review data. The sentiment analysis engine uses NLP techniques such as TextBlob to analyze the sentiment from the review content and extract emotional information such as positive and negative. For example, a positive sentiment is extracted from the review "The coffee at this cafe has a nice aroma and is relaxing." The input data is the review content, and the output data is emotional information.

[0389] Step 4:

[0390] The AI ​​engine learns the user's values, preferences, and tastes based on the saved reviews and emotional information.

[0391] The server passes the word-of-mouth and review data along with emotional information to an AI engine. The AI ​​engine uses natural language processing technology to extract important keywords and features from the review content and learns the user's values, hobbies, and preferences. For example, features such as "nice scent" and "relaxing" are detected and added to the user profile. The input data is the word-of-mouth and review data and emotional information, and the output data is the updated user profile.

[0392] Step 5:

[0393] Based on the learned data, the server selects other users with similar values ​​and products that those users have highly rated.

[0394] The server searches for other users with similar values ​​and hobbies based on data learned by the artificial intelligence engine. In doing so, it also takes into account emotional information and selects products that have been highly rated by users with similar profiles. For example, it selects "Aroma Coffee," a cafe that other users have highly rated. The input data is the user profile, and the output data is a list of recommended products.

[0395] Step 6:

[0396] The server sends the selected product to the user's device.

[0397] The server sends the selected product information in JSON format to the user's device. Specifically, the server encodes the recommended product list and sends it to the user's device via an HTTP request. The input data is the recommended product list, and the output data is the data sent to the user's device.

[0398] Step 7:

[0399] Display the received product on the user's device

[0400] The user device displays the received recommended product information. The application decodes the JSON data and displays it visually to the user. For example, it displays "User B's highly rated cafe: Aroma Coffee." The input data is the recommended product data received from the server, and the output data is the content displayed to the user.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] [Second embodiment]

[0405] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0416] 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."

[0417] This invention is a system that uses word-of-mouth reviews "for yourself" to recommend the most suitable products and content to users. This system uses artificial intelligence to learn the user's values ​​and preferences based on the word-of-mouth reviews posted by the user, and recommends items that have been highly rated by other users with similar values, thereby assisting the user in decision-making. The system's program processing is described in detail below in natural language.

[0418] (Post a review)

[0419] Device: The user launches an application that displays a testimonial / review submission form. The submission form includes a text input field and a star rating slider. The user enters their opinion and rating about a specific product or service and sets the star rating. They then confirm the review and press the submit button.

[0420] Server: Receives the word-of-mouth and review data sent from the device. The received data is sent as structured data in JSON format, etc. The server then saves the review content in a database. The information saved includes the user ID, review content, star rating, and posting date and time. For example, if User A gives a five-star rating along with the comment, "The coffee at this cafe has a nice aroma and is relaxing," that data will be saved in the database.

[0421] (AI-based data analysis and learning)

[0422] Server: Notifies the AI ​​engine that newly posted review data has been received. The notified data is sent to the AI ​​engine for analysis.

[0423] AI model: The artificial intelligence engine analyzes the text of user reviews and extracts important keywords and sentiments. Using natural language processing (NLP) techniques, it extracts features such as "nice aroma" and "relaxing." The AI ​​model then learns these features and adds the user's values ​​and preferences to the user profile. For example, preferences such as "coffee aroma" and "relaxing" are added to User A's profile.

[0424] (Generating recommendation content)

[0425] Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model finds users with similar values ​​from the training database and selects products and content that those users have highly rated.

[0426] Server: The selected recommendation content is encoded in JSON format and sent to the user's device. For example, if user A is looking for a new cafe, the server will recommend a cafe called "Aroma Coffee," which has been highly rated by user B, who shares similar values.

[0427] (Display of recommendation content)

[0428] Device: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed within the application. This allows the user to select the recommended products and services based on the information.

[0429] This invention allows users to obtain useful information based on their own values ​​and preferences, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[0430] The processing flow will be explained below.

[0431] Step 1:

[0432] Device: The user launches the application and is presented with a testimonial / review submission form, which includes a text input field and a star rating slider.

[0433] Step 2:

[0434] User: Enter your thoughts and ratings about the product or service in the text input field and set the rating using the star rating slider. For example, to review a cafe, you might write, "The coffee at this cafe is fragrant and relaxing," and set it to 5 stars.

[0435] Step 3:

[0436] Device: When the user checks the review content and presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[0437] Step 4:

[0438] Server: Receives word-of-mouth and review data sent from the device. The received data is temporarily stored in memory.

[0439] Step 5:

[0440] Server: The received data is stored in a database. This includes the user ID, review text, star rating, and posting date and time. For example, an SQL query like the following is executed: INSERT INTO reviews (user_id, review_text, star_rating, created_at) VALUES (...).

[0441] Step 6:

[0442] Server: Notifies the AI ​​engine that a new post has been made. When notifying, an API is called to pass the saved word-of-mouth and review data to the AI ​​engine.

[0443] Step 7:

[0444] AI model: The artificial intelligence engine analyzes the received word-of-mouth and reviews. Natural language processing (NLP) techniques are used to extract keywords and emotions. For example, characteristics such as "nice scent" and "relaxing" are detected.

[0445] Step 8:

[0446] AI model: Learns the user's values, hobbies, and preferences based on the extracted features and adds them to the user profile. "Coffee aroma" and "Relaxation" are added to User A's profile.

[0447] Step 9:

[0448] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[0449] Step 10:

[0450] AI model: Based on learning data, it searches for other users with similar values. It finds User B with a similar profile.

[0451] Step 11:

[0452] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[0453] Step 12:

[0454] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[0455] Step 13:

[0456] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[0457] Step 14:

[0458] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[0459] Example 1

[0460] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0461] Conventional word-of-mouth and review systems have had difficulty providing users with truly useful information. In particular, they have been inadequate in providing personalized recommendations based on the user's values ​​and interests. Furthermore, they have the problem of filter bubbles, which can limit new discoveries and the breadth of options. The purpose of this invention is to solve these issues and provide users with more valuable information.

[0462] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0463] In this invention, the server includes a means for users to send rating information, a means for the server to receive the rating information and store it in a database, a means for an artificial intelligence engine to analyze the stored rating information and learn the user's values ​​and interests, a means for the server to select other users with similar values ​​and products that the users have highly rated based on the learned data, a means for the server to send the products selected by the server to a user terminal, and a means for the user terminal to display the products received. This allows users to obtain useful information based on their own values ​​and interests, enabling new discoveries and a variety of options.

[0464] "User" means a person who uses the System to post reviews and receive product and content recommendations.

[0465] "Rating Information" means text reviews and star ratings submitted by users about products or services.

[0466] "Server" means a computer system that receives and stores rating information, manages analysis results, and generates recommendations.

[0467] "Database" means data storage for storing and managing rating information and user profiles.

[0468] An "artificial intelligence engine" is a machine learning model or algorithm that analyzes stored rating information and learns user values ​​and interests.

[0469] "Values" or "Interests" refer to the preferences and priorities that users express through their ratings information.

[0470] A "recommended list" is a list of products and services that have been highly rated by other users, selected by an artificial intelligence engine based on the user's values ​​and interests.

[0471] "Natural language processing technology" is a computer technology for analyzing text data and extracting important keywords and emotions.

[0472] "User terminal" refers to a device such as a computer or smartphone that a user uses to post rating information and receive and display recommendations.

[0473] The present invention is a system that uses an artificial intelligence engine to recommend personalized products and services based on evaluation information (word of mouth reviews) posted by users. A specific embodiment of this system is described below.

[0474] System Overview

[0475] 1. User-submitted evaluation information

[0476] - Device: The user launches the application on a computer or smartphone. The application displays a form for submitting a review. The form contains a text input field and a star rating slider, allowing the user to enter their opinion and rating about a specific product or service and set the star rating. The user then confirms the review and presses the submit button.

[0477] - Example: A user writes a review saying, "The coffee at this cafe is aromatic and relaxing," and gives it a 5-star rating.

[0478] 2. Receipt and storage of rating information by the server

[0479] - Server: Receives rating information sent from the device in JSON format. The received data is stored in a database on the server. The stored information includes the user ID, review content, star rating, and posting date and time.

[0480] - Specific technology: The server uses, for example, a "MySQL" database.

[0481] 3. Data analysis and user profile updating using an AI engine

[0482] - Server: Notifies the AI ​​engine that newly posted rating information has been received and forwards the data for analysis.

[0483] - AI model: The AI ​​engine uses natural language processing (NLP) technology to analyze the text of the evaluation information, extracting characteristics such as "nice scent" and "relaxing," and adding the user's values ​​and interests to the profile.

[0484] - Specific technology: Natural language processing libraries such as "Transformers" can be used for AI models.

[0485] - Example: Preferences such as "coffee aroma" and "relaxation" are added to a user's profile.

[0486] 4. Server-generated and transmitted recommendations

[0487] - Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model finds users with similar profiles from the training database and selects products and services that those users have highly rated.

[0488] - Recommendation generation: The selected recommendation content is encoded in JSON format and sent to the user's device.

[0489] - Example: If a user is looking for a new cafe, the AI ​​engine will recommend a cafe called "Aroma Coffee," which has been highly rated by other users with similar values.

[0490] - Example prompt: In response to the review, "The coffee at this cafe is fragrant and relaxing," what kind of cafe would you recommend?

[0491] 5. Display of recommendations by device

[0492] - Device: The recommendation received from the server is displayed to the user. The application displays "Aroma Coffee, a cafe highly rated by other users" for the user to refer to.

[0493] This system allows users to obtain useful information based on their values ​​and interests, allowing them to enjoy new discoveries and diverse options. It also reduces the problem of filter bubbles and provides a more satisfying consumption experience.

[0494] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0495] Step 1:

[0496] User: The user launches the application and opens the testimonial / review submission form. The form contains a text input field and a star rating slider, allowing the user to enter their opinion about a specific product or service and set a star rating. Once they are done, they press the submit button.

[0497] Input: User-entered text review and star rating

[0498] Output: The request to send the post to the server

[0499] Specific action: The user enters "The coffee at this cafe is fragrant and relaxing" and sets a 5-star rating.

[0500] Step 2:

[0501] Server: Receives the rating information sent from the user device. The rating information is sent in JSON format, and the server parses it and stores it in a database.

[0502] Input: JSON format rating information (e.g., user ID, review content, star rating, posting date and time)

[0503] Output: Evaluation information stored in a database

[0504] Specific operation: The server saves User A's review, "The coffee at this cafe is fragrant and relaxing," with a five-star rating, in the database.

[0505] Step 3:

[0506] Server: Notifies the AI ​​engine that new evaluation information has been received. The server forwards the data to the AI ​​engine for analysis.

[0507] Input: Newly received rating information

[0508] Output: Evaluation information sent to the AI ​​engine

[0509] Specific operation: The server notifies the AI ​​engine of a new review from user A and sends the data.

[0510] Step 4:

[0511] AI Model: The AI ​​engine analyzes the review text using natural language processing (NLP) techniques to extract key keywords and sentiment, then adds these findings to the user profile.

[0512] Input: Evaluation information text data

[0513] Output: Updated user profile

[0514] Specific operation: The AI ​​model extracts the keywords "nice aroma" and "relaxing" and adds the preferences for "coffee aroma" and "relaxation" to User A's profile.

[0515] Step 5:

[0516] Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model then finds users with similar values ​​from the training database and selects products and services that those users have highly rated.

[0517] Input: User request

[0518] Output: A list of recommended products and services

[0519] Specific operation: When a user is looking for a new cafe, the server sends a request to the AI ​​engine, and the AI ​​model selects "Aroma Coffee," a cafe that User B highly rated.

[0520] Step 6:

[0521] Server: The selected recommendations are encoded in JSON format and sent to the user's device.

[0522] Input: Recommendation list

[0523] Output: Recommendation content in JSON format sent to the user device

[0524] Specific operation: The server sends "Aroma Coffee" as a recommendation to User A's terminal.

[0525] Step 7:

[0526] Terminal: The user terminal displays the recommendations received from the server.

[0527] Input: Recommendation received from the server

[0528] Output: Recommendations displayed to the user

[0529] Specific operation: "Cafes highly rated by other users: Aroma Coffee" will be displayed on User A's device, and the user can use it as a reference.

[0530] The above is the specific flow and operation of each processing step.

[0531] (Application example 1)

[0532] 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."

[0533] Conventional recommendation systems based on word-of-mouth and reviews have the problem of not being able to fully respond to the individual values ​​and tastes of users. It is also difficult to provide recommendations that match the user's interests in real time, which has prevented them from increasing user satisfaction. Furthermore, they lack the functionality to effectively utilize reviews from other users with similar values ​​to recommend new products and services. This has led to problems such as users finding the most suitable products and content.

[0534] 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.

[0535] In this invention, the server includes a means for providing recommendations based on individual values ​​in real time for categories that the user has shown interest in, a means for recommending new products based on reviews by other users with similar values, and a means for receiving product recommendations in real time, which makes it possible to recommend optimal products and content according to the user's individual values ​​and hobbies and preferences, thereby significantly improving user satisfaction.

[0536] "Word of mouth / review" refers to information in which users write their evaluations of specific products or services.

[0537] "Server" means a computer system that receives and stores data sent by users, and processes and analyzes it as necessary.

[0538] A "database" is a system for storing information such as the content of word-of-mouth reviews, user IDs, star ratings, and posting dates and times in a structured format.

[0539] An "artificial intelligence engine" is a software or hardware component that analyzes posted word-of-mouth and reviews and learns users' values, hobbies, and preferences.

[0540] "Natural language processing technology" is a technology that analyzes meaning and emotions from text data and extracts important keywords.

[0541] "Other users with similar values" are other users who are determined to have similar values, hobbies, and preferences based on the analysis of posted word-of-mouth and reviews.

[0542] "Product selection" means determining products or services that meet specific conditions based on learned user data.

[0543] A "user device" is a device such as a smartphone or tablet that receives recommended products or content and displays them to the user.

[0544] "Providing recommendations in real time" means presenting the most appropriate products and services to users on the spot based on their current interests and concerns.

[0545] "Recommending new products" means suggesting products or services that the user is not yet aware of, based on high ratings from other users who share similar values.

[0546] This invention is a system that recommends optimal products and content to users based on word-of-mouth reviews. Specific embodiments for carrying out this invention are described below.

[0547] System Program Overview

[0548] The server receives user testimonials and reviews and stores them in a database. This data is stored as structured data in JSON format or similar. The server plays a central role in the system, receiving, storing, and analyzing testimonials and reviews, selecting recommended products, and sending the recommended products. The hardware used includes a database server and an application server. The software used includes Python, Django, MySQL, and other programs.

[0549] Artificial intelligence engine and natural language processing technology

[0550] The server then sends the received customer review data to an AI engine, which then uses natural language processing (NLP) techniques to analyze the customer review text and extract key keywords and sentiment. This analysis is performed using libraries such as TensorFlow and PyTorch. The extracted feature keywords are added to the user profile and used for subsequent recommendations.

[0551] For example, if a user posts a review saying, "The coffee at this cafe has a wonderful aroma and is relaxing," the AI ​​engine will extract keywords such as "a wonderful aroma" and "relaxing." These keywords will be added to the user's profile.

[0552] Generate and send product recommendations

[0553] When a user requests a recommendation for a new product or service, the server instructs the AI ​​engine to search for other users with similar values ​​and select products or services that those users have highly rated. The selected products or services are then sent from the server to the user's device and displayed to the user.

[0554] For example, if a user is searching for a product related to cafes, the AI ​​engine will recommend a cafe called "Aroma Coffee," which has been highly rated by other users with similar values. This recommendation will be displayed to the user in the application as "Cafe highly rated by User B: Aroma Coffee."

[0555] Real-time recommendation function

[0556] The system will include the ability to provide users with personalized recommendations in real time, so that when a user searches for a product or category, the system will instantly recommend the most suitable products and services based on their values, tastes, and preferences.

[0557] Examples of concrete examples and prompts

[0558] Users post reviews about "stylish cafes," and the AI ​​learns from them and reflects them in their profiles. Next, when a user searches for products in the "cafe" category, "Aroma Coffee" is recommended based on reviews from other users with similar values.

[0559] An example of a prompt sentence to input to the generative AI model is as follows:

[0560] We will create an AI model that learns a user's values ​​and preferences based on word of mouth and reviews, and recommends new products. We will perform NLP analysis on the content of the user's reviews, extract characteristic keywords, and add them to their profile. We will then recommend products that have been highly rated by other users with similar values. We will implement this model in Python.

[0561] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0562] Step 1:

[0563] Users submit their testimonials and reviews.

[0564] Specific operation: The user launches the smartphone app, enters text and a star rating into the word-of-mouth / review submission form, and then presses the submit button to send the input to the server.

[0565] Input: Text review, star rating

[0566] Output: Customer reviews sent to the server

[0567] Step 2:

[0568] The server receives the reviews and stores them in a database.

[0569] Specific operation: The server receives the data sent by the user in JSON format and stores it in a database, including the user ID, review content, star rating, posting date and time, etc.

[0570] Input: JSON formatted customer reviews

[0571] Output: Reviews stored in a database

[0572] Step 3:

[0573] The server notifies the AI ​​engine of new word-of-mouth and review data.

[0574] What it does: The server detects newly saved data and requests the AI ​​engine to analyze it.

[0575] Input: Newly saved customer review data

[0576] Output: Analysis request to AI engine

[0577] Step 4:

[0578] An artificial intelligence engine analyzes the text of reviews and extracts important keywords and sentiments.

[0579] How it works: The AI ​​engine uses TensorFlow and PyTorch to perform NLP analysis and extract characteristic keywords and emotional expressions from text reviews, such as "nice scent" and "relaxing."

[0580] Input: Text data of word-of-mouth reviews

[0581] Output: Extracted feature keywords and sentiment

[0582] Step 5:

[0583] The extracted characteristic keywords are added to the user profile.

[0584] How it works: The AI ​​engine updates the user profile based on the extracted keywords.

[0585] Input: Extracted feature keywords

[0586] Output: Updated user profile

[0587] Step 6:

[0588] A user requests recommendations for new products or services.

[0589] What happens: A user searches for a specific product category within a smartphone app, for example, by entering "cafe" as the category.

[0590] Input: Recommendation request

[0591] Output: Search query to the server

[0592] Step 7:

[0593] The server detects other users with similar values ​​and selects products and services that those users have given high ratings to.

[0594] Specific operation: The server has the AI ​​engine search for users with similar values ​​and selects products and services that those users have given high ratings to.

[0595] Input: Search query and user profile

[0596] Output: A list of recommended products or services

[0597] Step 8:

[0598] The server sends the selected products and services to the user's device.

[0599] Specific operation: The server encodes the selected product or service list in JSON format and sends it to the user's device.

[0600] Input: Recommended product or service list

[0601] Output: Data sent to the user's terminal

[0602] Step 9:

[0603] Display the products and services received by the user device.

[0604] Specific operation: The user device displays the received data on the screen, for example, "User B's highly rated cafe: Aroma Coffee."

[0605] Input: Data received from the server

[0606] Output: Recommended products or services displayed on the screen

[0607] Through the above steps, the present invention is able to recommend optimal products and content to users.

[0608] 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.

[0609] This invention is a system that learns a user's values, preferences, and emotions based on word-of-mouth reviews and recommends the most suitable products and content to the user. This system supports the user's decision-making by analyzing word-of-mouth reviews posted by the user using an artificial intelligence engine and an emotion engine, and recommending highly rated products from other users who share similar values. The system's program processing is described in detail below in natural language.

[0610] (Post a review)

[0611] Device: The user launches the application and is presented with a form for submitting a user review. The submission form includes a text input field and a star rating slider. The user enters their thoughts and evaluation of a specific product or service and sets a star rating. For example, a user might write a review of a cafe, saying, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[0612] User: Check the content of the word-of-mouth / review and press the post button.

[0613] (Data reception and storage)

[0614] Terminal: When the user presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[0615] Server: Receives word-of-mouth and review data sent from the device. Stores the received data in a database. Data stored includes the user ID, review content, star rating, posting date and time, etc. For example, if User A gives a five-star rating along with the comment, "The coffee at this cafe has a nice aroma and is relaxing," that data will be stored in the database.

[0616] (Data analysis and learning using AI and emotion engines)

[0617] Server: Notifies the AI ​​engine that newly posted customer reviews have been received. When notifying, passes the saved customer reviews to the AI ​​engine and emotion engine.

[0618] Emotion engine: Analyzes the text contained in word-of-mouth reviews and extracts emotions. The extracted emotions are expressed in a format such as positive or negative and sent to the server as analysis results. For example, a positive emotion is extracted from a review that reads, "The coffee at this cafe has a nice aroma and is relaxing."

[0619] AI model: The artificial intelligence engine analyzes word-of-mouth reviews based on the emotional information sent from the emotion engine. Natural language processing (NLP) technology is used to extract important keywords and emotions, and learn the user's values, hobbies, and preferences. For example, characteristics such as "nice scent" and "relaxing" are detected and added to User A's profile.

[0620] (Generating recommendation content)

[0621] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[0622] AI model: Based on learning data, it searches for other users with similar values. It also takes into account emotional information to find User B with a similar profile.

[0623] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[0624] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[0625] (Display of recommendation content)

[0626] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[0627] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[0628] This invention allows users to obtain useful information based on their values, tastes, and emotions, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[0629] The processing flow will be explained below.

[0630] Step 1:

[0631] Device: The user launches the application and is presented with a testimonial / review submission form, which includes a text input field and a star rating slider.

[0632] Step 2:

[0633] User: Enter your thoughts and ratings about the product or service in the text input field and set the rating using the star rating slider. For example, to review a cafe, you might write, "The coffee at this cafe is fragrant and relaxing," and set it to 5 stars.

[0634] Step 3:

[0635] Device: When the user checks the review content and presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[0636] Step 4:

[0637] Server: Receives word-of-mouth and review data sent from the device. The received data is temporarily stored in memory.

[0638] Step 5:

[0639] Server: The received data is stored in a database. This includes the user ID, review text, star rating, and posting date and time. For example, an SQL query like the following is executed: INSERT INTO reviews (user_id, review_text, star_rating, created_at) VALUES (...).

[0640] Step 6:

[0641] Server: Notifies the AI ​​engine and emotion engine that a new post has been made. When notifying, passes the saved word-of-mouth and review data for analysis.

[0642] Step 7:

[0643] Emotion engine: Analyzes text contained in reviews and extracts emotions. For example, it detects positive emotions in the comment, "The coffee at this cafe has a nice aroma and is relaxing."

[0644] Step 8:

[0645] Emotion engine: The extracted emotional information is sent to the server. For example, data containing the emotional information "positive" is returned to the server.

[0646] Step 9:

[0647] AI model: The artificial intelligence engine receives the emotional information and analyzes the text of the reviews. Natural language processing (NLP) techniques are used to extract keywords and emotions. For example, features such as "nice scent" and "relaxing" are extracted.

[0648] Step 10:

[0649] AI model: Based on the extracted features and emotional information, the AI ​​model learns the user's values, hobbies, and preferences and updates the user profile. Preferences such as "coffee aroma" and "relaxation" are added to User A's profile.

[0650] Step 11:

[0651] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[0652] Step 12:

[0653] AI model: Based on learning data, it searches for other users with similar values. It finds User B with a similar profile. It also takes into account emotional information when selecting users.

[0654] Step 13:

[0655] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[0656] Step 14:

[0657] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[0658] Step 15:

[0659] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[0660] Step 16:

[0661] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[0662] Example 2

[0663] 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."

[0664] Conventional recommendation systems have difficulty recommending appropriate products and content that accurately reflect users' ratings and preferences. Furthermore, when used by many users, recommendations are often not based on individual values ​​and emotions, resulting in a decline in user satisfaction. Furthermore, there is a lack of recommendation systems that take emotional information into account, and there is a need to improve the user experience.

[0665] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for a user to transmit rating information, a means for the server to receive the rating information and store it in an information collection device, a means for a machine learning engine to analyze the stored rating information and learn the user's values ​​and preferences, a means for the server to select other users with similar values ​​and products that the users have highly rated based on the learned data, a means for transmitting the products selected by the server to the user's information terminal, and a means for the user's information terminal to display the received products. This enables recommendations that accurately reflect the user's emotional information and preferences.

[0666] "Rating information" refers to feedback that a user gives about a particular product or service, and is typically expressed in the form of text content and star ratings.

[0667] A "server" is a computer system that receives data sent by a user and processes it.

[0668] The "information collection device" includes a database and a storage device installed in the server, and is a device for saving received evaluation information.

[0669] A "machine learning engine" is a computer program that analyzes received and stored rating information and executes algorithms or models to learn user values ​​and preferences.

[0670] "Natural language processing technology" is a technology that analyzes text data and extracts important keywords and emotions from it.

[0671] A "recommended list" is a list of products and services selected based on the user's values ​​and preferences.

[0672] A "user's information terminal" is an electronic device used by a user, such as a smartphone or computer, that displays data sent from the server.

[0673] "Other users with similar values" refers to other users who share the same tastes and behavioral patterns as a given user.

[0674] "Product" refers to the specific product or service recommended to a user.

[0675] "Means" refers to a method or device, or a combination thereof, for achieving a particular purpose.

[0676] The present invention relates to a system that recommends optimal products and content based on user evaluation information. The system of this invention is implemented using the following hardware and software: a server and a user's information terminal (such as a smartphone or PC). It also uses software such as an artificial intelligence engine, a machine learning engine using natural language processing technology, and an information collection device for data storage.

[0677] The system's main functions are as follows: When a user submits rating information through the application, the information is sent to the server in JSON format. The server stores the received data in an information collection device. Next, a machine learning engine analyzes the data and learns the user's values ​​and preferences. This analysis uses natural language processing technology, and emotional information is also extracted.

[0678] Next, the server uses the learned data to select other users with similar values ​​and products that those users have highly rated. The selected products are sent from the server to the user's information terminal and displayed on the user's information terminal.

[0679] Specific examples are shown below.

[0680] First, a user submits a review of a specific product, writing, "The coffee at this cafe has a nice aroma and is relaxing," along with a rating of 5 stars. The server receives this review and stores it in a database. A machine learning engine then analyzes the review, extracting keywords such as "nice aroma" and "relaxing" as well as positive emotions, and adds them to the user's profile.

[0681] When the user then sends a request to "find a new cafe," the server searches for other users with similar values ​​and recommends products that those users have given high ratings to, such as a cafe called "Aroma Coffee." This recommendation information is sent in JSON format to the user's device, and is displayed as "Cafe highly rated by User B: Aroma Coffee."

[0682] Below are some example prompts to be input to the generative AI model:

[0683] "Analyze the following review posted by user A and extract sentiment and value information:

[0684] Review: "The coffee at this cafe is aromatic and relaxing." Star rating: 5 stars

[0685] Analyze various reviews, find users with a similar profile to User B, and recommend highly rated products. For example, recommend "Aroma Coffee," which User B highly rated.

[0686] This system enables recommendations that accurately reflect the user's emotional information and preferences, thereby increasing user satisfaction.

[0687] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0688] Step 1: Submit a review

[0689] Device: The user launches the application and opens the review submission form. The submission form includes a text input field and a star rating slider. The user enters their thoughts and evaluation of a specific product or service and sets a star rating. For example, a user might write a review of a cafe saying, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[0690] Input: User input of text and star rating.

[0691] Output: When the submit button is pressed, the entered data is passed to the following step.

[0692] Specific behavior: When the user presses the submit button, the application prepares the data to be sent in JSON format.

[0693] Step 2: Receiving and storing data

[0694] Terminal: When the submit button is pressed, the application sends the data in JSON format to the server.

[0695] Input: JSON formatted word-of-mouth and review data (user ID, review content, star rating, etc.).

[0696] Server: The server receives the word-of-mouth and review data sent from the device and stores it in an information collection device (database). The stored data includes the user ID, review content, star rating, posting date and time, etc.

[0697] Output: The saved data will be used for analysis in the next step.

[0698] Specific behavior: To confirm that the data was saved successfully, the success / failure of the save process is recorded in the log.

[0699] Step 3: Data analysis and learning using AI and emotion engines

[0700] Server: Notifies the AI ​​engine of newly posted word-of-mouth and review data.

[0701] Input: Customer reviews stored in a database.

[0702] Emotion engine: Analyzes the text of reviews and extracts emotional information such as positive and negative sentiment. This emotional information is sent back to the server.

[0703] AI model: The AI ​​engine analyzes user reviews based on emotional information and extracts important keywords and emotions, thereby learning user values ​​and preferences.

[0704] Output: The analysis results are reflected in the user's profile, and values ​​and preferences are updated.

[0705] Specific operation: The results of extracting emotional information and important keywords are recorded in a log and added to the user profile.

[0706] Step 4: Generate recommendations

[0707] Server: The user requests a new recommendation (e.g., "Find a new cafe").

[0708] Input: A user's profile and a new recommendation request.

[0709] AI model: Based on learning data, it searches for other users with similar values ​​and identifies users with similar profiles by taking into account emotional information. It then selects products and content that User B has highly rated. For example, it selects a cafe called "Aroma Coffee."

[0710] Output: Selected recommendations encoded in JSON format.

[0711] Specific operations: Generate a recommendation list, execute a test process to confirm the selection results, and record the generated recommendation list in a log.

[0712] Step 5: View your recommendations

[0713] Server: Sends the selected recommendations to the user's device.

[0714] Input: JSON format data of recommendation content.

[0715] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[0716] Output: The displayed recommendation.

[0717] Specific behavior: Display recommendations in a format that is easy for users to review and provide an interface for users to take the next action.

[0718] (Application example 2)

[0719] 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."

[0720] Conventional recommendation systems have difficulty accurately grasping a user's values ​​and preferences, and have therefore been unable to provide recommendations that adequately meet individual needs. Furthermore, due to a lack of means to analyze emotional information, highly accurate recommendations based on the user's emotions have not been realized. As a result, user satisfaction is low and the filter bubble problem is likely to occur.

[0721] 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.

[0722] In this invention, the server includes: a means for users to send word-of-mouth reviews; a means for the server to receive the word-of-mouth reviews and store them in a database; a sentiment analysis engine to analyze the emotions contained in the word-of-mouth reviews and extract emotional information; an artificial intelligence engine to learn the user's values ​​and preferences based on the stored word-of-mouth reviews and emotional information; a means for the server to select other users with similar values ​​and products highly rated by those users based on the learned data; a means for transmitting the products selected by the server to a user terminal; and a means for the user terminal to display the products received. This enables highly accurate recommendations based on the user's values ​​and emotions.

[0723] "Means for users to submit word-of-mouth / reviews" refers to the functions and interfaces that allow users to input their ratings and opinions about products and services and send them to the server.

[0724] "Means by which the server receives the reviews and comments and stores them in a database" refers to the functions and processes by which the server receives the reviews and comments sent by users and stores them in a database.

[0725] "Means for an emotion analysis engine to analyze emotions contained in word-of-mouth reviews and extract emotional information" refers to technology and software that analyzes emotional elements such as positive and negative emotions from word-of-mouth reviews and extracts them as data.

[0726] "Means for an artificial intelligence engine to learn a user's values, hobbies, and preferences based on saved word-of-mouth reviews and emotional information" refers to algorithms and programs that analyze saved word-of-mouth reviews and emotional information to learn a user's characteristics and preferences.

[0727] "Means for the server to select other users with similar values ​​and products that have been highly rated by those users based on learned data" refers to the function or process of selecting other users with similar values ​​and products that have been highly rated by those users based on learned data.

[0728] The "means for the server to transmit the selected product to the user terminal" refers to the function or process for transmitting information about the selected product to the user terminal.

[0729] The "means for displaying the product received by the user terminal" is an interface for visually displaying the product information received by the user terminal to the user.

[0730] This invention is a system that learns a user's values, preferences, and emotions based on word-of-mouth and reviews, and recommends the most suitable products and content to the user. This system uses an artificial intelligence engine and a sentiment analysis engine to analyze word-of-mouth and reviews posted by the user, and recommends highly rated products from other users who share the same values. The system's program processing is explained in detail below.

[0731] Hardware and software used

[0732] Hardware

[0733] Smartphone

[0734] server

[0735] software

[0736] Python

[0737] Flask (server-side web framework)

[0738] TextBlob (emotion analysis)

[0739] JSON (data format)

[0740] Requests (HTTP request library)

[0741] User reviews and data processing

[0742] First, users submit testimonials and reviews about products and services through a smartphone application. The submission form includes a text input field and a star rating slider. For example, users can write, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[0743] Receiving and storing data on the server

[0744] When a user clicks the submit button, the entered user feedback and review data is sent to the server in JSON format. The data includes the user ID, review content, star rating, and posting date and time. The server stores the received data in a database.

[0745] Analysis using sentiment analysis engine and artificial intelligence engine

[0746] The server notifies the sentiment analysis engine of newly posted word-of-mouth and review data. The sentiment analysis engine analyzes the text and extracts emotional information, such as positive or negative. For example, a review that reads, "The coffee at this cafe has a nice aroma and is relaxing," would extract a positive sentiment.

[0747] Next, an artificial intelligence engine analyzes the reviews based on emotional information. Using natural language processing (NLP) technology, it extracts important keywords and emotions, learning the user's values, hobbies, and preferences. For example, characteristics such as "nice scent" and "relaxing" are detected and added to the user's profile.

[0748] Recommendation generation

[0749] The server receives a new recommendation request from a user. Based on the learning data, the AI ​​model searches for other users with similar values ​​and selects products that have been highly rated by users with similar profiles, taking into account emotional information. For example, it selects "Aroma Coffee," a cafe highly rated by User B.

[0750] Displaying recommendations

[0751] The selected recommendation is encoded as JSON data and sent to the user's device. The device then displays the received recommendation to the user. For example, it might say, "User B highly rated cafe: Aroma Coffee." The user can review the recommendation and decide what to do next.

[0752] Examples of concrete examples and prompts

[0753] Here are some examples of prompts to input to a generative AI model:

[0754] "Analyze user values ​​and sentiments based on the following reviews:

[0755] Review: The coffee at this cafe is aromatic and relaxing.

[0756] Extract the detected emotions and features that may represent values, interests, and preferences.

[0757] By using this prompt, the model can learn emotions and specific values ​​and recommend the best products for the user.

[0758] This invention allows users to obtain useful information based on their values, tastes, and emotions, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[0759] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0760] Step 1:

[0761] Users submit their testimonials and reviews

[0762] Users post word-of-mouth reviews of products and services through a smartphone app. The input form includes a text field and a star rating slider. For example, a user might enter "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars. This is the input data. When the user presses the submit button, the data is sent to the server in JSON format.

[0763] Step 2:

[0764] The server receives the reviews and stores them in a database.

[0765] The server receives the testimonials and reviews sent by users. The data includes the user ID, review content, star rating, and posting date and time. The server parses the received data and saves it in a database. Specifically, it parses the received JSON data and stores it in the appropriate fields. The output data is a record saved in the database.

[0766] Step 3:

[0767] The sentiment analysis engine analyzes the emotions contained in word-of-mouth reviews and extracts emotional information.

[0768] The server notifies the sentiment analysis engine of newly posted word-of-mouth and review data. The sentiment analysis engine uses NLP techniques such as TextBlob to analyze the sentiment from the review content and extract emotional information such as positive and negative. For example, a positive sentiment is extracted from the review "The coffee at this cafe has a nice aroma and is relaxing." The input data is the review content, and the output data is emotional information.

[0769] Step 4:

[0770] The AI ​​engine learns the user's values, preferences, and tastes based on the saved reviews and emotional information.

[0771] The server passes the word-of-mouth and review data along with emotional information to an AI engine. The AI ​​engine uses natural language processing technology to extract important keywords and features from the review content and learns the user's values, hobbies, and preferences. For example, features such as "nice scent" and "relaxing" are detected and added to the user profile. The input data is the word-of-mouth and review data and emotional information, and the output data is the updated user profile.

[0772] Step 5:

[0773] Based on the learned data, the server selects other users with similar values ​​and products that those users have highly rated.

[0774] The server searches for other users with similar values ​​and hobbies based on data learned by the artificial intelligence engine. In doing so, it also takes into account emotional information and selects products that have been highly rated by users with similar profiles. For example, it selects "Aroma Coffee," a cafe that other users have highly rated. The input data is the user profile, and the output data is a list of recommended products.

[0775] Step 6:

[0776] The server sends the selected product to the user's device.

[0777] The server sends the selected product information in JSON format to the user's device. Specifically, the server encodes the recommended product list and sends it to the user's device via an HTTP request. The input data is the recommended product list, and the output data is the data sent to the user's device.

[0778] Step 7:

[0779] Display the received product on the user's device

[0780] The user device displays the received recommended product information. The application decodes the JSON data and displays it visually to the user. For example, it displays "User B's highly rated cafe: Aroma Coffee." The input data is the recommended product data received from the server, and the output data is the content displayed to the user.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] [Third embodiment]

[0785] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0786] 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.

[0787] 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).

[0788] 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.

[0789] 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.

[0790] 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).

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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."

[0797] This invention is a system that uses word-of-mouth reviews "for yourself" to recommend the most suitable products and content to users. This system uses artificial intelligence to learn the user's values ​​and preferences based on the word-of-mouth reviews posted by the user, and recommends items that have been highly rated by other users with similar values, thereby assisting the user in decision-making. The system's program processing is described in detail below in natural language.

[0798] (Post a review)

[0799] Device: The user launches an application that displays a testimonial / review submission form. The submission form includes a text input field and a star rating slider. The user enters their opinion and rating about a specific product or service and sets the star rating. They then confirm the review and press the submit button.

[0800] Server: Receives the word-of-mouth and review data sent from the device. The received data is sent as structured data in JSON format, etc. The server then saves the review content in a database. The information saved includes the user ID, review content, star rating, and posting date and time. For example, if User A gives a five-star rating along with the comment, "The coffee at this cafe has a nice aroma and is relaxing," that data will be saved in the database.

[0801] (AI-based data analysis and learning)

[0802] Server: Notifies the AI ​​engine that newly posted review data has been received. The notified data is sent to the AI ​​engine for analysis.

[0803] AI model: The artificial intelligence engine analyzes the text of user reviews and extracts important keywords and sentiments. Using natural language processing (NLP) techniques, it extracts features such as "nice aroma" and "relaxing." The AI ​​model then learns these features and adds the user's values ​​and preferences to the user profile. For example, preferences such as "coffee aroma" and "relaxing" are added to User A's profile.

[0804] (Generating recommendation content)

[0805] Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model finds users with similar values ​​from the training database and selects products and content that those users have highly rated.

[0806] Server: The selected recommendation content is encoded in JSON format and sent to the user's device. For example, if user A is looking for a new cafe, the server will recommend a cafe called "Aroma Coffee," which has been highly rated by user B, who shares similar values.

[0807] (Display of recommendation content)

[0808] Device: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed within the application. This allows the user to select the recommended products and services based on the information.

[0809] This invention allows users to obtain useful information based on their own values ​​and preferences, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[0810] The processing flow will be explained below.

[0811] Step 1:

[0812] Device: The user launches the application and is presented with a testimonial / review submission form, which includes a text input field and a star rating slider.

[0813] Step 2:

[0814] User: Enter your thoughts and ratings about the product or service in the text input field and set the rating using the star rating slider. For example, to review a cafe, you might write, "The coffee at this cafe is fragrant and relaxing," and set it to 5 stars.

[0815] Step 3:

[0816] Device: When the user checks the review content and presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[0817] Step 4:

[0818] Server: Receives word-of-mouth and review data sent from the device. The received data is temporarily stored in memory.

[0819] Step 5:

[0820] Server: The received data is stored in a database. This includes the user ID, review text, star rating, and posting date and time. For example, an SQL query like the following is executed: INSERT INTO reviews (user_id, review_text, star_rating, created_at) VALUES (...).

[0821] Step 6:

[0822] Server: Notifies the AI ​​engine that a new post has been made. When notifying, an API is called to pass the saved word-of-mouth and review data to the AI ​​engine.

[0823] Step 7:

[0824] AI model: The artificial intelligence engine analyzes the received word-of-mouth and reviews. Natural language processing (NLP) techniques are used to extract keywords and emotions. For example, characteristics such as "nice scent" and "relaxing" are detected.

[0825] Step 8:

[0826] AI model: Learns the user's values, hobbies, and preferences based on the extracted features and adds them to the user profile. "Coffee aroma" and "Relaxation" are added to User A's profile.

[0827] Step 9:

[0828] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[0829] Step 10:

[0830] AI model: Based on learning data, it searches for other users with similar values. It finds User B with a similar profile.

[0831] Step 11:

[0832] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[0833] Step 12:

[0834] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[0835] Step 13:

[0836] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[0837] Step 14:

[0838] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[0839] Example 1

[0840] 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."

[0841] Conventional word-of-mouth and review systems have had difficulty providing users with truly useful information. In particular, they have been inadequate in providing personalized recommendations based on the user's values ​​and interests. Furthermore, they have the problem of filter bubbles, which can limit new discoveries and the breadth of options. The purpose of this invention is to solve these issues and provide users with more valuable information.

[0842] 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.

[0843] In this invention, the server includes a means for users to send rating information, a means for the server to receive the rating information and store it in a database, a means for an artificial intelligence engine to analyze the stored rating information and learn the user's values ​​and interests, a means for the server to select other users with similar values ​​and products that the users have highly rated based on the learned data, a means for the server to send the products selected by the server to a user terminal, and a means for the user terminal to display the products received. This allows users to obtain useful information based on their own values ​​and interests, enabling new discoveries and a variety of options.

[0844] "User" means a person who uses the System to post reviews and receive product and content recommendations.

[0845] "Rating Information" means text reviews and star ratings submitted by users about products or services.

[0846] "Server" means a computer system that receives and stores rating information, manages analysis results, and generates recommendations.

[0847] "Database" means data storage for storing and managing rating information and user profiles.

[0848] An "artificial intelligence engine" is a machine learning model or algorithm that analyzes stored rating information and learns user values ​​and interests.

[0849] "Values" or "Interests" refer to the preferences and priorities that users express through their ratings information.

[0850] A "recommended list" is a list of products and services that have been highly rated by other users, selected by an artificial intelligence engine based on the user's values ​​and interests.

[0851] "Natural language processing technology" is a computer technology for analyzing text data and extracting important keywords and emotions.

[0852] "User terminal" refers to a device such as a computer or smartphone that a user uses to post rating information and receive and display recommendations.

[0853] The present invention is a system that uses an artificial intelligence engine to recommend personalized products and services based on evaluation information (word of mouth reviews) posted by users. A specific embodiment of this system is described below.

[0854] System Overview

[0855] 1. User-submitted evaluation information

[0856] - Device: The user launches the application on a computer or smartphone. The application displays a form for submitting a review. The form contains a text input field and a star rating slider, allowing the user to enter their opinion and rating about a specific product or service and set the star rating. The user then confirms the review and presses the submit button.

[0857] - Example: A user writes a review saying, "The coffee at this cafe is aromatic and relaxing," and gives it a 5-star rating.

[0858] 2. Receipt and storage of rating information by the server

[0859] - Server: Receives rating information sent from the device in JSON format. The received data is stored in a database on the server. The stored information includes the user ID, review content, star rating, and posting date and time.

[0860] - Specific technology: The server uses, for example, a "MySQL" database.

[0861] 3. Data analysis and user profile updating using an AI engine

[0862] - Server: Notifies the AI ​​engine that newly posted rating information has been received and forwards the data for analysis.

[0863] - AI model: The AI ​​engine uses natural language processing (NLP) technology to analyze the text of the evaluation information, extracting characteristics such as "nice scent" and "relaxing," and adding the user's values ​​and interests to the profile.

[0864] - Specific technology: Natural language processing libraries such as "Transformers" can be used for AI models.

[0865] - Example: Preferences such as "coffee aroma" and "relaxation" are added to a user's profile.

[0866] 4. Server-generated and transmitted recommendations

[0867] - Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model finds users with similar profiles from the training database and selects products and services that those users have highly rated.

[0868] - Recommendation generation: The selected recommendation content is encoded in JSON format and sent to the user's device.

[0869] - Example: If a user is looking for a new cafe, the AI ​​engine will recommend a cafe called "Aroma Coffee," which has been highly rated by other users with similar values.

[0870] - Example prompt: In response to the review, "The coffee at this cafe is fragrant and relaxing," what kind of cafe would you recommend?

[0871] 5. Display of recommendations by device

[0872] - Device: The recommendation received from the server is displayed to the user. The application displays "Aroma Coffee, a cafe highly rated by other users" for the user to refer to.

[0873] This system allows users to obtain useful information based on their values ​​and interests, allowing them to enjoy new discoveries and diverse options. It also reduces the problem of filter bubbles and provides a more satisfying consumption experience.

[0874] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0875] Step 1:

[0876] User: The user launches the application and opens the testimonial / review submission form. The form contains a text input field and a star rating slider, allowing the user to enter their opinion about a specific product or service and set a star rating. Once they are done, they press the submit button.

[0877] Input: User-entered text review and star rating

[0878] Output: The request to send the post to the server

[0879] Specific action: The user enters "The coffee at this cafe is fragrant and relaxing" and sets a 5-star rating.

[0880] Step 2:

[0881] Server: Receives the rating information sent from the user device. The rating information is sent in JSON format, and the server parses it and stores it in a database.

[0882] Input: JSON format rating information (e.g., user ID, review content, star rating, posting date and time)

[0883] Output: Evaluation information stored in a database

[0884] Specific operation: The server saves User A's review, "The coffee at this cafe is fragrant and relaxing," with a five-star rating, in the database.

[0885] Step 3:

[0886] Server: Notifies the AI ​​engine that new evaluation information has been received. The server forwards the data to the AI ​​engine for analysis.

[0887] Input: Newly received rating information

[0888] Output: Evaluation information sent to the AI ​​engine

[0889] Specific operation: The server notifies the AI ​​engine of a new review from user A and sends the data.

[0890] Step 4:

[0891] AI Model: The AI ​​engine analyzes the review text using natural language processing (NLP) techniques to extract key keywords and sentiment, then adds these findings to the user profile.

[0892] Input: Evaluation information text data

[0893] Output: Updated user profile

[0894] Specific operation: The AI ​​model extracts the keywords "nice aroma" and "relaxing" and adds the preferences for "coffee aroma" and "relaxation" to User A's profile.

[0895] Step 5:

[0896] Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model then finds users with similar values ​​from the training database and selects products and services that those users have highly rated.

[0897] Input: User request

[0898] Output: A list of recommended products and services

[0899] Specific operation: When a user is looking for a new cafe, the server sends a request to the AI ​​engine, and the AI ​​model selects "Aroma Coffee," a cafe that User B highly rated.

[0900] Step 6:

[0901] Server: The selected recommendations are encoded in JSON format and sent to the user's device.

[0902] Input: Recommendation list

[0903] Output: Recommendation content in JSON format sent to the user device

[0904] Specific operation: The server sends "Aroma Coffee" as a recommendation to User A's terminal.

[0905] Step 7:

[0906] Terminal: The user terminal displays the recommendations received from the server.

[0907] Input: Recommendation received from the server

[0908] Output: Recommendations displayed to the user

[0909] Specific operation: "Cafes highly rated by other users: Aroma Coffee" will be displayed on User A's device, and the user can use it as a reference.

[0910] The above is the specific flow and operation of each processing step.

[0911] (Application example 1)

[0912] 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."

[0913] Conventional recommendation systems based on word-of-mouth and reviews have the problem of not being able to fully respond to the individual values ​​and tastes of users. It is also difficult to provide recommendations that match the user's interests in real time, which has prevented them from increasing user satisfaction. Furthermore, they lack the functionality to effectively utilize reviews from other users with similar values ​​to recommend new products and services. This has led to problems such as users finding the most suitable products and content.

[0914] 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.

[0915] In this invention, the server includes a means for providing recommendations based on individual values ​​in real time for categories that the user has shown interest in, a means for recommending new products based on reviews by other users with similar values, and a means for receiving product recommendations in real time, which makes it possible to recommend optimal products and content according to the user's individual values ​​and hobbies and preferences, thereby significantly improving user satisfaction.

[0916] "Word of mouth / review" refers to information in which users write their evaluations of specific products or services.

[0917] "Server" means a computer system that receives and stores data sent by users, and processes and analyzes it as necessary.

[0918] A "database" is a system for storing information such as the content of word-of-mouth reviews, user IDs, star ratings, and posting dates and times in a structured format.

[0919] An "artificial intelligence engine" is a software or hardware component that analyzes posted word-of-mouth and reviews and learns users' values, hobbies, and preferences.

[0920] "Natural language processing technology" is a technology that analyzes meaning and emotions from text data and extracts important keywords.

[0921] "Other users with similar values" are other users who are determined to have similar values, hobbies, and preferences based on the analysis of posted word-of-mouth and reviews.

[0922] "Product selection" means determining products or services that meet specific conditions based on learned user data.

[0923] A "user device" is a device such as a smartphone or tablet that receives recommended products or content and displays them to the user.

[0924] "Providing recommendations in real time" means presenting the most appropriate products and services to users on the spot based on their current interests and concerns.

[0925] "Recommending new products" means suggesting products or services that the user is not yet aware of, based on high ratings from other users who share similar values.

[0926] This invention is a system that recommends optimal products and content to users based on word-of-mouth reviews. Specific embodiments for carrying out this invention are described below.

[0927] System Program Overview

[0928] The server receives user testimonials and reviews and stores them in a database. This data is stored as structured data in JSON format or similar. The server plays a central role in the system, receiving, storing, and analyzing testimonials and reviews, selecting recommended products, and sending the recommended products. The hardware used includes a database server and an application server. The software used includes Python, Django, MySQL, and other programs.

[0929] Artificial intelligence engine and natural language processing technology

[0930] The server then sends the received customer review data to an AI engine, which then uses natural language processing (NLP) techniques to analyze the customer review text and extract key keywords and sentiment. This analysis is performed using libraries such as TensorFlow and PyTorch. The extracted feature keywords are added to the user profile and used for subsequent recommendations.

[0931] For example, if a user posts a review saying, "The coffee at this cafe has a wonderful aroma and is relaxing," the AI ​​engine will extract keywords such as "a wonderful aroma" and "relaxing." These keywords will be added to the user's profile.

[0932] Generate and send product recommendations

[0933] When a user requests a recommendation for a new product or service, the server instructs the AI ​​engine to search for other users with similar values ​​and select products or services that those users have highly rated. The selected products or services are then sent from the server to the user's device and displayed to the user.

[0934] For example, if a user is searching for a product related to cafes, the AI ​​engine will recommend a cafe called "Aroma Coffee," which has been highly rated by other users with similar values. This recommendation will be displayed to the user in the application as "Cafe highly rated by User B: Aroma Coffee."

[0935] Real-time recommendation function

[0936] The system will include the ability to provide users with personalized recommendations in real time, so that when a user searches for a product or category, the system will instantly recommend the most suitable products and services based on their values, tastes, and preferences.

[0937] Examples of concrete examples and prompts

[0938] Users post reviews about "stylish cafes," and the AI ​​learns from them and reflects them in their profiles. Next, when a user searches for products in the "cafe" category, "Aroma Coffee" is recommended based on reviews from other users with similar values.

[0939] An example of a prompt sentence to input to the generative AI model is as follows:

[0940] We will create an AI model that learns a user's values ​​and preferences based on word of mouth and reviews, and recommends new products. We will perform NLP analysis on the content of the user's reviews, extract characteristic keywords, and add them to their profile. We will then recommend products that have been highly rated by other users with similar values. We will implement this model in Python.

[0941] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0942] Step 1:

[0943] Users submit their testimonials and reviews.

[0944] Specific operation: The user launches the smartphone app, enters text and a star rating into the word-of-mouth / review submission form, and then presses the submit button to send the input to the server.

[0945] Input: Text review, star rating

[0946] Output: Customer reviews sent to the server

[0947] Step 2:

[0948] The server receives the reviews and stores them in a database.

[0949] Specific operation: The server receives the data sent by the user in JSON format and stores it in a database, including the user ID, review content, star rating, posting date and time, etc.

[0950] Input: JSON formatted customer reviews

[0951] Output: Reviews stored in a database

[0952] Step 3:

[0953] The server notifies the AI ​​engine of new word-of-mouth and review data.

[0954] What it does: The server detects newly saved data and requests the AI ​​engine to analyze it.

[0955] Input: Newly saved customer review data

[0956] Output: Analysis request to AI engine

[0957] Step 4:

[0958] An artificial intelligence engine analyzes the text of reviews and extracts important keywords and sentiments.

[0959] How it works: The AI ​​engine uses TensorFlow and PyTorch to perform NLP analysis and extract characteristic keywords and emotional expressions from text reviews, such as "nice scent" and "relaxing."

[0960] Input: Text data of word-of-mouth reviews

[0961] Output: Extracted feature keywords and sentiment

[0962] Step 5:

[0963] The extracted characteristic keywords are added to the user profile.

[0964] How it works: The AI ​​engine updates the user profile based on the extracted keywords.

[0965] Input: Extracted feature keywords

[0966] Output: Updated user profile

[0967] Step 6:

[0968] A user requests recommendations for new products or services.

[0969] What happens: A user searches for a specific product category within a smartphone app, for example, by entering "cafe" as the category.

[0970] Input: Recommendation request

[0971] Output: Search query to the server

[0972] Step 7:

[0973] The server detects other users with similar values ​​and selects products and services that those users have given high ratings to.

[0974] Specific operation: The server has the AI ​​engine search for users with similar values ​​and selects products and services that those users have given high ratings to.

[0975] Input: Search query and user profile

[0976] Output: A list of recommended products or services

[0977] Step 8:

[0978] The server sends the selected products and services to the user's device.

[0979] Specific operation: The server encodes the selected product or service list in JSON format and sends it to the user's device.

[0980] Input: Recommended product or service list

[0981] Output: Data sent to the user's terminal

[0982] Step 9:

[0983] Display the products and services received by the user device.

[0984] Specific operation: The user device displays the received data on the screen, for example, "User B's highly rated cafe: Aroma Coffee."

[0985] Input: Data received from the server

[0986] Output: Recommended products or services displayed on the screen

[0987] Through the above steps, the present invention is able to recommend optimal products and content to users.

[0988] 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.

[0989] This invention is a system that learns a user's values, preferences, and emotions based on word-of-mouth reviews and recommends the most suitable products and content to the user. This system supports the user's decision-making by analyzing word-of-mouth reviews posted by the user using an artificial intelligence engine and an emotion engine, and recommending highly rated products from other users who share similar values. The system's program processing is described in detail below in natural language.

[0990] (Post a review)

[0991] Device: The user launches the application and is presented with a form for submitting a user review. The submission form includes a text input field and a star rating slider. The user enters their thoughts and evaluation of a specific product or service and sets a star rating. For example, a user might write a review of a cafe, saying, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[0992] User: Check the content of the word-of-mouth / review and press the post button.

[0993] (Data reception and storage)

[0994] Terminal: When the user presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[0995] Server: Receives word-of-mouth and review data sent from the device. Stores the received data in a database. Data stored includes the user ID, review content, star rating, posting date and time, etc. For example, if User A gives a five-star rating along with the comment, "The coffee at this cafe has a nice aroma and is relaxing," that data will be stored in the database.

[0996] (Data analysis and learning using AI and emotion engines)

[0997] Server: Notifies the AI ​​engine that newly posted customer reviews have been received. When notifying, passes the saved customer reviews to the AI ​​engine and emotion engine.

[0998] Emotion engine: Analyzes the text contained in word-of-mouth reviews and extracts emotions. The extracted emotions are expressed in a format such as positive or negative and sent to the server as analysis results. For example, a positive emotion is extracted from a review that reads, "The coffee at this cafe has a nice aroma and is relaxing."

[0999] AI model: The artificial intelligence engine analyzes word-of-mouth reviews based on the emotional information sent from the emotion engine. Natural language processing (NLP) technology is used to extract important keywords and emotions, and learn the user's values, hobbies, and preferences. For example, characteristics such as "nice scent" and "relaxing" are detected and added to User A's profile.

[1000] (Generating recommendation content)

[1001] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[1002] AI model: Based on learning data, it searches for other users with similar values. It also takes into account emotional information to find User B with a similar profile.

[1003] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[1004] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[1005] (Display of recommendation content)

[1006] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[1007] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[1008] This invention allows users to obtain useful information based on their values, tastes, and emotions, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[1009] The processing flow will be explained below.

[1010] Step 1:

[1011] Device: The user launches the application and is presented with a testimonial / review submission form, which includes a text input field and a star rating slider.

[1012] Step 2:

[1013] User: Enter your thoughts and ratings about the product or service in the text input field and set the rating using the star rating slider. For example, to review a cafe, you might write, "The coffee at this cafe is fragrant and relaxing," and set it to 5 stars.

[1014] Step 3:

[1015] Device: When the user checks the review content and presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[1016] Step 4:

[1017] Server: Receives word-of-mouth and review data sent from the device. The received data is temporarily stored in memory.

[1018] Step 5:

[1019] Server: The received data is stored in a database. This includes the user ID, review text, star rating, and posting date and time. For example, an SQL query like the following is executed: INSERT INTO reviews (user_id, review_text, star_rating, created_at) VALUES (...).

[1020] Step 6:

[1021] Server: Notifies the AI ​​engine and emotion engine that a new post has been made. When notifying, passes the saved word-of-mouth and review data for analysis.

[1022] Step 7:

[1023] Emotion engine: Analyzes text contained in reviews and extracts emotions. For example, it detects positive emotions in the comment, "The coffee at this cafe has a nice aroma and is relaxing."

[1024] Step 8:

[1025] Emotion engine: The extracted emotional information is sent to the server. For example, data containing the emotional information "positive" is returned to the server.

[1026] Step 9:

[1027] AI model: The artificial intelligence engine receives the emotional information and analyzes the text of the reviews. Natural language processing (NLP) techniques are used to extract keywords and emotions. For example, features such as "nice scent" and "relaxing" are extracted.

[1028] Step 10:

[1029] AI model: Based on the extracted features and emotional information, the AI ​​model learns the user's values, hobbies, and preferences and updates the user profile. Preferences such as "coffee aroma" and "relaxation" are added to User A's profile.

[1030] Step 11:

[1031] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[1032] Step 12:

[1033] AI model: Based on learning data, it searches for other users with similar values. It finds User B with a similar profile. It also takes into account emotional information when selecting users.

[1034] Step 13:

[1035] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[1036] Step 14:

[1037] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[1038] Step 15:

[1039] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[1040] Step 16:

[1041] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[1042] Example 2

[1043] 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."

[1044] Conventional recommendation systems have difficulty recommending appropriate products and content that accurately reflect users' ratings and preferences. Furthermore, when used by many users, recommendations are often not based on individual values ​​and emotions, resulting in a decline in user satisfaction. Furthermore, there is a lack of recommendation systems that take emotional information into account, and there is a need to improve the user experience.

[1045] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for a user to transmit rating information, a means for the server to receive the rating information and store it in an information collection device, a means for a machine learning engine to analyze the stored rating information and learn the user's values ​​and preferences, a means for the server to select other users with similar values ​​and products that the users have highly rated based on the learned data, a means for transmitting the products selected by the server to the user's information terminal, and a means for the user's information terminal to display the received products. This enables recommendations that accurately reflect the user's emotional information and preferences.

[1046] "Rating information" refers to feedback that a user gives about a particular product or service, and is typically expressed in the form of text content and star ratings.

[1047] A "server" is a computer system that receives data sent by a user and processes it.

[1048] The "information collection device" includes a database and a storage device installed in the server, and is a device for saving received evaluation information.

[1049] A "machine learning engine" is a computer program that analyzes received and stored rating information and executes algorithms or models to learn user values ​​and preferences.

[1050] "Natural language processing technology" is a technology that analyzes text data and extracts important keywords and emotions from it.

[1051] A "recommended list" is a list of products and services selected based on the user's values ​​and preferences.

[1052] A "user's information terminal" is an electronic device used by a user, such as a smartphone or computer, that displays data sent from the server.

[1053] "Other users with similar values" refers to other users who share the same tastes and behavioral patterns as a given user.

[1054] "Product" refers to the specific product or service recommended to a user.

[1055] "Means" refers to a method or device, or a combination thereof, for achieving a particular purpose.

[1056] The present invention relates to a system that recommends optimal products and content based on user evaluation information. The system of this invention is implemented using the following hardware and software: a server and a user's information terminal (such as a smartphone or PC). It also uses software such as an artificial intelligence engine, a machine learning engine using natural language processing technology, and an information collection device for data storage.

[1057] The system's main functions are as follows: When a user submits rating information through the application, the information is sent to the server in JSON format. The server stores the received data in an information collection device. Next, a machine learning engine analyzes the data and learns the user's values ​​and preferences. This analysis uses natural language processing technology, and emotional information is also extracted.

[1058] Next, the server uses the learned data to select other users with similar values ​​and products that those users have highly rated. The selected products are sent from the server to the user's information terminal and displayed on the user's information terminal.

[1059] Specific examples are shown below.

[1060] First, a user submits a review of a specific product, writing, "The coffee at this cafe has a nice aroma and is relaxing," along with a rating of 5 stars. The server receives this review and stores it in a database. A machine learning engine then analyzes the review, extracting keywords such as "nice aroma" and "relaxing" as well as positive emotions, and adds them to the user's profile.

[1061] When the user then sends a request to "find a new cafe," the server searches for other users with similar values ​​and recommends products that those users have given high ratings to, such as a cafe called "Aroma Coffee." This recommendation information is sent in JSON format to the user's device, and is displayed as "Cafe highly rated by User B: Aroma Coffee."

[1062] Below are some example prompts to be input to the generative AI model:

[1063] "Analyze the following review posted by user A and extract sentiment and value information:

[1064] Review: "The coffee at this cafe is aromatic and relaxing." Star rating: 5 stars

[1065] Analyze various reviews, find users with a similar profile to User B, and recommend highly rated products. For example, recommend "Aroma Coffee," which User B highly rated.

[1066] This system enables recommendations that accurately reflect the user's emotional information and preferences, thereby increasing user satisfaction.

[1067] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1068] Step 1: Submit a review

[1069] Device: The user launches the application and opens the review submission form. The submission form includes a text input field and a star rating slider. The user enters their thoughts and evaluation of a specific product or service and sets a star rating. For example, a user might write a review of a cafe saying, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[1070] Input: User input of text and star rating.

[1071] Output: When the submit button is pressed, the entered data is passed to the following step.

[1072] Specific behavior: When the user presses the submit button, the application prepares the data to be sent in JSON format.

[1073] Step 2: Receiving and storing data

[1074] Terminal: When the submit button is pressed, the application sends the data in JSON format to the server.

[1075] Input: JSON formatted word-of-mouth and review data (user ID, review content, star rating, etc.).

[1076] Server: The server receives the word-of-mouth and review data sent from the device and stores it in an information collection device (database). The stored data includes the user ID, review content, star rating, posting date and time, etc.

[1077] Output: The saved data will be used for analysis in the next step.

[1078] Specific behavior: To confirm that the data was saved successfully, the success / failure of the save process is recorded in the log.

[1079] Step 3: Data analysis and learning using AI and emotion engines

[1080] Server: Notifies the AI ​​engine of newly posted word-of-mouth and review data.

[1081] Input: Customer reviews stored in a database.

[1082] Emotion engine: Analyzes the text of reviews and extracts emotional information such as positive and negative sentiment. This emotional information is sent back to the server.

[1083] AI model: The AI ​​engine analyzes user reviews based on emotional information and extracts important keywords and emotions, thereby learning user values ​​and preferences.

[1084] Output: The analysis results are reflected in the user's profile, and values ​​and preferences are updated.

[1085] Specific operation: The results of extracting emotional information and important keywords are recorded in a log and added to the user profile.

[1086] Step 4: Generate recommendations

[1087] Server: The user requests a new recommendation (e.g., "Find a new cafe").

[1088] Input: A user's profile and a new recommendation request.

[1089] AI model: Based on learning data, it searches for other users with similar values ​​and identifies users with similar profiles by taking into account emotional information. It then selects products and content that User B has highly rated. For example, it selects a cafe called "Aroma Coffee."

[1090] Output: Selected recommendations encoded in JSON format.

[1091] Specific operations: Generate a recommendation list, execute a test process to confirm the selection results, and record the generated recommendation list in a log.

[1092] Step 5: View your recommendations

[1093] Server: Sends the selected recommendations to the user's device.

[1094] Input: JSON format data of recommendation content.

[1095] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[1096] Output: The displayed recommendation.

[1097] Specific behavior: Display recommendations in a format that is easy for users to review and provide an interface for users to take the next action.

[1098] (Application example 2)

[1099] 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."

[1100] Conventional recommendation systems have difficulty accurately grasping a user's values ​​and preferences, and have therefore been unable to provide recommendations that adequately meet individual needs. Furthermore, due to a lack of means to analyze emotional information, highly accurate recommendations based on the user's emotions have not been realized. As a result, user satisfaction is low and the filter bubble problem is likely to occur.

[1101] 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.

[1102] In this invention, the server includes: a means for users to send word-of-mouth reviews; a means for the server to receive the word-of-mouth reviews and store them in a database; a sentiment analysis engine to analyze the emotions contained in the word-of-mouth reviews and extract emotional information; an artificial intelligence engine to learn the user's values ​​and preferences based on the stored word-of-mouth reviews and emotional information; a means for the server to select other users with similar values ​​and products highly rated by those users based on the learned data; a means for transmitting the products selected by the server to a user terminal; and a means for the user terminal to display the products received. This enables highly accurate recommendations based on the user's values ​​and emotions.

[1103] "Means for users to submit word-of-mouth / reviews" refers to the functions and interfaces that allow users to input their ratings and opinions about products and services and send them to the server.

[1104] "Means by which the server receives the reviews and comments and stores them in a database" refers to the functions and processes by which the server receives the reviews and comments sent by users and stores them in a database.

[1105] "Means for an emotion analysis engine to analyze emotions contained in word-of-mouth reviews and extract emotional information" refers to technology and software that analyzes emotional elements such as positive and negative emotions from word-of-mouth reviews and extracts them as data.

[1106] "Means for an artificial intelligence engine to learn a user's values, hobbies, and preferences based on saved word-of-mouth reviews and emotional information" refers to algorithms and programs that analyze saved word-of-mouth reviews and emotional information to learn a user's characteristics and preferences.

[1107] "Means for the server to select other users with similar values ​​and products that have been highly rated by those users based on learned data" refers to the function or process of selecting other users with similar values ​​and products that have been highly rated by those users based on learned data.

[1108] The "means for the server to transmit the selected product to the user terminal" refers to the function or process for transmitting information about the selected product to the user terminal.

[1109] The "means for displaying the product received by the user terminal" is an interface for visually displaying the product information received by the user terminal to the user.

[1110] This invention is a system that learns a user's values, preferences, and emotions based on word-of-mouth and reviews, and recommends the most suitable products and content to the user. This system uses an artificial intelligence engine and a sentiment analysis engine to analyze word-of-mouth and reviews posted by the user, and recommends highly rated products from other users who share the same values. The system's program processing is explained in detail below.

[1111] Hardware and software used

[1112] Hardware

[1113] Smartphone

[1114] server

[1115] software

[1116] Python

[1117] Flask (server-side web framework)

[1118] TextBlob (emotion analysis)

[1119] JSON (data format)

[1120] Requests (HTTP request library)

[1121] User reviews and data processing

[1122] First, users submit testimonials and reviews about products and services through a smartphone application. The submission form includes a text input field and a star rating slider. For example, users can write, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[1123] Receiving and storing data on the server

[1124] When a user clicks the submit button, the entered user feedback and review data is sent to the server in JSON format. The data includes the user ID, review content, star rating, and posting date and time. The server stores the received data in a database.

[1125] Analysis using sentiment analysis engine and artificial intelligence engine

[1126] The server notifies the sentiment analysis engine of newly posted word-of-mouth and review data. The sentiment analysis engine analyzes the text and extracts emotional information, such as positive or negative. For example, a review that reads, "The coffee at this cafe has a nice aroma and is relaxing," would extract a positive sentiment.

[1127] Next, an artificial intelligence engine analyzes the reviews based on emotional information. Using natural language processing (NLP) technology, it extracts important keywords and emotions, learning the user's values, hobbies, and preferences. For example, characteristics such as "nice scent" and "relaxing" are detected and added to the user's profile.

[1128] Recommendation generation

[1129] The server receives a new recommendation request from a user. Based on the learning data, the AI ​​model searches for other users with similar values ​​and selects products that have been highly rated by users with similar profiles, taking into account emotional information. For example, it selects "Aroma Coffee," a cafe highly rated by User B.

[1130] Displaying recommendations

[1131] The selected recommendation is encoded as JSON data and sent to the user's device. The device then displays the received recommendation to the user. For example, it might say, "User B highly rated cafe: Aroma Coffee." The user can review the recommendation and decide what to do next.

[1132] Examples of concrete examples and prompts

[1133] Here are some examples of prompts to input to a generative AI model:

[1134] "Analyze user values ​​and sentiments based on the following reviews:

[1135] Review: The coffee at this cafe is aromatic and relaxing.

[1136] Extract the detected emotions and features that may represent values, interests, and preferences.

[1137] By using this prompt, the model can learn emotions and specific values ​​and recommend the best products for the user.

[1138] This invention allows users to obtain useful information based on their values, tastes, and emotions, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[1139] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1140] Step 1:

[1141] Users submit their testimonials and reviews

[1142] Users post word-of-mouth reviews of products and services through a smartphone app. The input form includes a text field and a star rating slider. For example, a user might enter "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars. This is the input data. When the user presses the submit button, the data is sent to the server in JSON format.

[1143] Step 2:

[1144] The server receives the reviews and stores them in a database.

[1145] The server receives the testimonials and reviews sent by users. The data includes the user ID, review content, star rating, and posting date and time. The server parses the received data and saves it in a database. Specifically, it parses the received JSON data and stores it in the appropriate fields. The output data is a record saved in the database.

[1146] Step 3:

[1147] The sentiment analysis engine analyzes the emotions contained in word-of-mouth reviews and extracts emotional information.

[1148] The server notifies the sentiment analysis engine of newly posted word-of-mouth and review data. The sentiment analysis engine uses NLP techniques such as TextBlob to analyze the sentiment from the review content and extract emotional information such as positive and negative. For example, a positive sentiment is extracted from the review "The coffee at this cafe has a nice aroma and is relaxing." The input data is the review content, and the output data is emotional information.

[1149] Step 4:

[1150] The AI ​​engine learns the user's values, preferences, and tastes based on the saved reviews and emotional information.

[1151] The server passes the word-of-mouth and review data along with emotional information to an AI engine. The AI ​​engine uses natural language processing technology to extract important keywords and features from the review content and learns the user's values, hobbies, and preferences. For example, features such as "nice scent" and "relaxing" are detected and added to the user profile. The input data is the word-of-mouth and review data and emotional information, and the output data is the updated user profile.

[1152] Step 5:

[1153] Based on the learned data, the server selects other users with similar values ​​and products that those users have highly rated.

[1154] The server searches for other users with similar values ​​and hobbies based on data learned by the artificial intelligence engine. In doing so, it also takes into account emotional information and selects products that have been highly rated by users with similar profiles. For example, it selects "Aroma Coffee," a cafe that other users have highly rated. The input data is the user profile, and the output data is a list of recommended products.

[1155] Step 6:

[1156] The server sends the selected product to the user's device.

[1157] The server sends the selected product information in JSON format to the user's device. Specifically, the server encodes the recommended product list and sends it to the user's device via an HTTP request. The input data is the recommended product list, and the output data is the data sent to the user's device.

[1158] Step 7:

[1159] Display the received product on the user's device

[1160] The user device displays the received recommended product information. The application decodes the JSON data and displays it visually to the user. For example, it displays "User B's highly rated cafe: Aroma Coffee." The input data is the recommended product data received from the server, and the output data is the content displayed to the user.

[1161] 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.

[1162] 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.

[1163] 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.

[1164] [Fourth embodiment]

[1165] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1166] 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.

[1167] 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).

[1168] 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.

[1169] 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.

[1170] 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).

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] 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."

[1178] This invention is a system that uses word-of-mouth reviews "for yourself" to recommend the most suitable products and content to users. This system uses artificial intelligence to learn the user's values ​​and preferences based on the word-of-mouth reviews posted by the user, and recommends items that have been highly rated by other users with similar values, thereby assisting the user in decision-making. The system's program processing is described in detail below in natural language.

[1179] (Post a review)

[1180] Device: The user launches an application that displays a testimonial / review submission form. The submission form includes a text input field and a star rating slider. The user enters their opinion and rating about a specific product or service and sets the star rating. They then confirm the review and press the submit button.

[1181] Server: Receives the word-of-mouth and review data sent from the device. The received data is sent as structured data in JSON format, etc. The server then saves the review content in a database. The information saved includes the user ID, review content, star rating, and posting date and time. For example, if User A gives a five-star rating along with the comment, "The coffee at this cafe has a nice aroma and is relaxing," that data will be saved in the database.

[1182] (AI-based data analysis and learning)

[1183] Server: Notifies the AI ​​engine that newly posted review data has been received. The notified data is sent to the AI ​​engine for analysis.

[1184] AI model: The artificial intelligence engine analyzes the text of user reviews and extracts important keywords and sentiments. Using natural language processing (NLP) techniques, it extracts features such as "nice aroma" and "relaxing." The AI ​​model then learns these features and adds the user's values ​​and preferences to the user profile. For example, preferences such as "coffee aroma" and "relaxing" are added to User A's profile.

[1185] (Generating recommendation content)

[1186] Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model finds users with similar values ​​from the training database and selects products and content that those users have highly rated.

[1187] Server: The selected recommendation content is encoded in JSON format and sent to the user's device. For example, if user A is looking for a new cafe, the server will recommend a cafe called "Aroma Coffee," which has been highly rated by user B, who shares similar values.

[1188] (Display of recommendation content)

[1189] Device: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed within the application. This allows the user to select the recommended products and services based on the information.

[1190] This invention allows users to obtain useful information based on their own values ​​and preferences, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[1191] The processing flow will be explained below.

[1192] Step 1:

[1193] Device: The user launches the application and is presented with a testimonial / review submission form, which includes a text input field and a star rating slider.

[1194] Step 2:

[1195] User: Enter your thoughts and ratings about the product or service in the text input field and set the rating using the star rating slider. For example, to review a cafe, you might write, "The coffee at this cafe is fragrant and relaxing," and set it to 5 stars.

[1196] Step 3:

[1197] Device: When the user checks the review content and presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[1198] Step 4:

[1199] Server: Receives word-of-mouth and review data sent from the device. The received data is temporarily stored in memory.

[1200] Step 5:

[1201] Server: The received data is stored in a database. This includes the user ID, review text, star rating, and posting date and time. For example, an SQL query like the following is executed: INSERT INTO reviews (user_id, review_text, star_rating, created_at) VALUES (...).

[1202] Step 6:

[1203] Server: Notifies the AI ​​engine that a new post has been made. When notifying, an API is called to pass the saved word-of-mouth and review data to the AI ​​engine.

[1204] Step 7:

[1205] AI model: The artificial intelligence engine analyzes the received word-of-mouth and reviews. Natural language processing (NLP) techniques are used to extract keywords and emotions. For example, characteristics such as "nice scent" and "relaxing" are detected.

[1206] Step 8:

[1207] AI model: Learns the user's values, hobbies, and preferences based on the extracted features and adds them to the user profile. "Coffee aroma" and "Relaxation" are added to User A's profile.

[1208] Step 9:

[1209] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[1210] Step 10:

[1211] AI model: Based on learning data, it searches for other users with similar values. It finds User B with a similar profile.

[1212] Step 11:

[1213] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[1214] Step 12:

[1215] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[1216] Step 13:

[1217] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[1218] Step 14:

[1219] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[1220] Example 1

[1221] 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."

[1222] Conventional word-of-mouth and review systems have had difficulty providing users with truly useful information. In particular, they have been inadequate in providing personalized recommendations based on the user's values ​​and interests. Furthermore, they have the problem of filter bubbles, which can limit new discoveries and the breadth of options. The purpose of this invention is to solve these issues and provide users with more valuable information.

[1223] 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.

[1224] In this invention, the server includes a means for users to send rating information, a means for the server to receive the rating information and store it in a database, a means for an artificial intelligence engine to analyze the stored rating information and learn the user's values ​​and interests, a means for the server to select other users with similar values ​​and products that the users have highly rated based on the learned data, a means for the server to send the products selected by the server to a user terminal, and a means for the user terminal to display the products received. This allows users to obtain useful information based on their own values ​​and interests, enabling new discoveries and a variety of options.

[1225] "User" means a person who uses the System to post reviews and receive product and content recommendations.

[1226] "Rating Information" means text reviews and star ratings submitted by users about products or services.

[1227] "Server" means a computer system that receives and stores rating information, manages analysis results, and generates recommendations.

[1228] "Database" means data storage for storing and managing rating information and user profiles.

[1229] An "artificial intelligence engine" is a machine learning model or algorithm that analyzes stored rating information and learns user values ​​and interests.

[1230] "Values" or "Interests" refer to the preferences and priorities that users express through their ratings information.

[1231] A "recommended list" is a list of products and services that have been highly rated by other users, selected by an artificial intelligence engine based on the user's values ​​and interests.

[1232] "Natural language processing technology" is a computer technology for analyzing text data and extracting important keywords and emotions.

[1233] "User terminal" refers to a device such as a computer or smartphone that a user uses to post rating information and receive and display recommendations.

[1234] The present invention is a system that uses an artificial intelligence engine to recommend personalized products and services based on evaluation information (word of mouth reviews) posted by users. A specific embodiment of this system is described below.

[1235] System Overview

[1236] 1. User-submitted evaluation information

[1237] - Device: The user launches the application on a computer or smartphone. The application displays a form for submitting a review. The form contains a text input field and a star rating slider, allowing the user to enter their opinion and rating about a specific product or service and set the star rating. The user then confirms the review and presses the submit button.

[1238] - Example: A user writes a review saying, "The coffee at this cafe is aromatic and relaxing," and gives it a 5-star rating.

[1239] 2. Receipt and storage of rating information by the server

[1240] - Server: Receives rating information sent from the device in JSON format. The received data is stored in a database on the server. The stored information includes the user ID, review content, star rating, and posting date and time.

[1241] - Specific technology: The server uses, for example, a "MySQL" database.

[1242] 3. Data analysis and user profile updating using an AI engine

[1243] - Server: Notifies the AI ​​engine that newly posted rating information has been received and forwards the data for analysis.

[1244] - AI model: The AI ​​engine uses natural language processing (NLP) technology to analyze the text of the evaluation information, extracting characteristics such as "nice scent" and "relaxing," and adding the user's values ​​and interests to the profile.

[1245] - Specific technology: Natural language processing libraries such as "Transformers" can be used for AI models.

[1246] - Example: Preferences such as "coffee aroma" and "relaxation" are added to a user's profile.

[1247] 4. Server-generated and transmitted recommendations

[1248] - Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model finds users with similar profiles from the training database and selects products and services that those users have highly rated.

[1249] - Recommendation generation: The selected recommendation content is encoded in JSON format and sent to the user's device.

[1250] - Example: If a user is looking for a new cafe, the AI ​​engine will recommend a cafe called "Aroma Coffee," which has been highly rated by other users with similar values.

[1251] - Example prompt: In response to the review, "The coffee at this cafe is fragrant and relaxing," what kind of cafe would you recommend?

[1252] 5. Display of recommendations by device

[1253] - Device: The recommendation received from the server is displayed to the user. The application displays "Aroma Coffee, a cafe highly rated by other users" for the user to refer to.

[1254] This system allows users to obtain useful information based on their values ​​and interests, allowing them to enjoy new discoveries and diverse options. It also reduces the problem of filter bubbles and provides a more satisfying consumption experience.

[1255] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1256] Step 1:

[1257] User: The user launches the application and opens the testimonial / review submission form. The form contains a text input field and a star rating slider, allowing the user to enter their opinion about a specific product or service and set a star rating. Once they are done, they press the submit button.

[1258] Input: User-entered text review and star rating

[1259] Output: The request to send the post to the server

[1260] Specific action: The user enters "The coffee at this cafe is fragrant and relaxing" and sets a 5-star rating.

[1261] Step 2:

[1262] Server: Receives the rating information sent from the user device. The rating information is sent in JSON format, and the server parses it and stores it in a database.

[1263] Input: JSON format rating information (e.g., user ID, review content, star rating, posting date and time)

[1264] Output: Evaluation information stored in a database

[1265] Specific operation: The server saves User A's review, "The coffee at this cafe is fragrant and relaxing," with a five-star rating, in the database.

[1266] Step 3:

[1267] Server: Notifies the AI ​​engine that new evaluation information has been received. The server forwards the data to the AI ​​engine for analysis.

[1268] Input: Newly received rating information

[1269] Output: Evaluation information sent to the AI ​​engine

[1270] Specific operation: The server notifies the AI ​​engine of a new review from user A and sends the data.

[1271] Step 4:

[1272] AI Model: The AI ​​engine analyzes the review text using natural language processing (NLP) techniques to extract key keywords and sentiment, then adds these findings to the user profile.

[1273] Input: Evaluation information text data

[1274] Output: Updated user profile

[1275] Specific operation: The AI ​​model extracts the keywords "nice aroma" and "relaxing" and adds the preferences for "coffee aroma" and "relaxation" to User A's profile.

[1276] Step 5:

[1277] Server: When a user requests a new recommendation, the server instructs the AI ​​engine to search for other users with similar values. The AI ​​model then finds users with similar values ​​from the training database and selects products and services that those users have highly rated.

[1278] Input: User request

[1279] Output: A list of recommended products and services

[1280] Specific operation: When a user is looking for a new cafe, the server sends a request to the AI ​​engine, and the AI ​​model selects "Aroma Coffee," a cafe that User B highly rated.

[1281] Step 6:

[1282] Server: The selected recommendations are encoded in JSON format and sent to the user's device.

[1283] Input: Recommendation list

[1284] Output: Recommendation content in JSON format sent to the user device

[1285] Specific operation: The server sends "Aroma Coffee" as a recommendation to User A's terminal.

[1286] Step 7:

[1287] Terminal: The user terminal displays the recommendations received from the server.

[1288] Input: Recommendation received from the server

[1289] Output: Recommendations displayed to the user

[1290] Specific operation: "Cafes highly rated by other users: Aroma Coffee" will be displayed on User A's device, and the user can use it as a reference.

[1291] The above is the specific flow and operation of each processing step.

[1292] (Application example 1)

[1293] 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."

[1294] Conventional recommendation systems based on word-of-mouth and reviews have the problem of not being able to fully respond to the individual values ​​and tastes of users. It is also difficult to provide recommendations that match the user's interests in real time, which has prevented them from increasing user satisfaction. Furthermore, they lack the functionality to effectively utilize reviews from other users with similar values ​​to recommend new products and services. This has led to problems such as users finding the most suitable products and content.

[1295] 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.

[1296] In this invention, the server includes a means for providing recommendations based on individual values ​​in real time for categories that the user has shown interest in, a means for recommending new products based on reviews by other users with similar values, and a means for receiving product recommendations in real time, which makes it possible to recommend optimal products and content according to the user's individual values ​​and hobbies and preferences, thereby significantly improving user satisfaction.

[1297] "Word of mouth / review" refers to information in which users write their evaluations of specific products or services.

[1298] "Server" means a computer system that receives and stores data sent by users, and processes and analyzes it as necessary.

[1299] A "database" is a system for storing information such as the content of word-of-mouth reviews, user IDs, star ratings, and posting dates and times in a structured format.

[1300] An "artificial intelligence engine" is a software or hardware component that analyzes posted word-of-mouth and reviews and learns users' values, hobbies, and preferences.

[1301] "Natural language processing technology" is a technology that analyzes meaning and emotions from text data and extracts important keywords.

[1302] "Other users with similar values" are other users who are determined to have similar values, hobbies, and preferences based on the analysis of posted word-of-mouth and reviews.

[1303] "Product selection" means determining products or services that meet specific conditions based on learned user data.

[1304] A "user device" is a device such as a smartphone or tablet that receives recommended products or content and displays them to the user.

[1305] "Providing recommendations in real time" means presenting the most appropriate products and services to users on the spot based on their current interests and concerns.

[1306] "Recommending new products" means suggesting products or services that the user is not yet aware of, based on high ratings from other users who share similar values.

[1307] This invention is a system that recommends optimal products and content to users based on word-of-mouth reviews. Specific embodiments for carrying out this invention are described below.

[1308] System Program Overview

[1309] The server receives user testimonials and reviews and stores them in a database. This data is stored as structured data in JSON format or similar. The server plays a central role in the system, receiving, storing, and analyzing testimonials and reviews, selecting recommended products, and sending the recommended products. The hardware used includes a database server and an application server. The software used includes Python, Django, MySQL, and other programs.

[1310] Artificial intelligence engine and natural language processing technology

[1311] The server then sends the received customer review data to an AI engine, which then uses natural language processing (NLP) techniques to analyze the customer review text and extract key keywords and sentiment. This analysis is performed using libraries such as TensorFlow and PyTorch. The extracted feature keywords are added to the user profile and used for subsequent recommendations.

[1312] For example, if a user posts a review saying, "The coffee at this cafe has a wonderful aroma and is relaxing," the AI ​​engine will extract keywords such as "a wonderful aroma" and "relaxing." These keywords will be added to the user's profile.

[1313] Generate and send product recommendations

[1314] When a user requests a recommendation for a new product or service, the server instructs the AI ​​engine to search for other users with similar values ​​and select products or services that those users have highly rated. The selected products or services are then sent from the server to the user's device and displayed to the user.

[1315] For example, if a user is searching for a product related to cafes, the AI ​​engine will recommend a cafe called "Aroma Coffee," which has been highly rated by other users with similar values. This recommendation will be displayed to the user in the application as "Cafe highly rated by User B: Aroma Coffee."

[1316] Real-time recommendation function

[1317] The system will include the ability to provide users with personalized recommendations in real time, so that when a user searches for a product or category, the system will instantly recommend the most suitable products and services based on their values, tastes, and preferences.

[1318] Examples of concrete examples and prompts

[1319] Users post reviews about "stylish cafes," and the AI ​​learns from them and reflects them in their profiles. Next, when a user searches for products in the "cafe" category, "Aroma Coffee" is recommended based on reviews from other users with similar values.

[1320] An example of a prompt sentence to input to the generative AI model is as follows:

[1321] We will create an AI model that learns a user's values ​​and preferences based on word of mouth and reviews, and recommends new products. We will perform NLP analysis on the content of the user's reviews, extract characteristic keywords, and add them to their profile. We will then recommend products that have been highly rated by other users with similar values. We will implement this model in Python.

[1322] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1323] Step 1:

[1324] Users submit their testimonials and reviews.

[1325] Specific operation: The user launches the smartphone app, enters text and a star rating into the word-of-mouth / review submission form, and then presses the submit button to send the input to the server.

[1326] Input: Text review, star rating

[1327] Output: Customer reviews sent to the server

[1328] Step 2:

[1329] The server receives the reviews and stores them in a database.

[1330] Specific operation: The server receives the data sent by the user in JSON format and stores it in a database, including the user ID, review content, star rating, posting date and time, etc.

[1331] Input: JSON formatted customer reviews

[1332] Output: Reviews stored in a database

[1333] Step 3:

[1334] The server notifies the AI ​​engine of new word-of-mouth and review data.

[1335] What it does: The server detects newly saved data and requests the AI ​​engine to analyze it.

[1336] Input: Newly saved customer review data

[1337] Output: Analysis request to AI engine

[1338] Step 4:

[1339] An artificial intelligence engine analyzes the text of reviews and extracts important keywords and sentiments.

[1340] How it works: The AI ​​engine uses TensorFlow and PyTorch to perform NLP analysis and extract characteristic keywords and emotional expressions from text reviews, such as "nice scent" and "relaxing."

[1341] Input: Text data of word-of-mouth reviews

[1342] Output: Extracted feature keywords and sentiment

[1343] Step 5:

[1344] The extracted characteristic keywords are added to the user profile.

[1345] How it works: The AI ​​engine updates the user profile based on the extracted keywords.

[1346] Input: Extracted feature keywords

[1347] Output: Updated user profile

[1348] Step 6:

[1349] A user requests recommendations for new products or services.

[1350] What happens: A user searches for a specific product category within a smartphone app, for example, by entering "cafe" as the category.

[1351] Input: Recommendation request

[1352] Output: Search query to the server

[1353] Step 7:

[1354] The server detects other users with similar values ​​and selects products and services that those users have given high ratings to.

[1355] Specific operation: The server has the AI ​​engine search for users with similar values ​​and selects products and services that those users have given high ratings to.

[1356] Input: Search query and user profile

[1357] Output: A list of recommended products or services

[1358] Step 8:

[1359] The server sends the selected products and services to the user's device.

[1360] Specific operation: The server encodes the selected product or service list in JSON format and sends it to the user's device.

[1361] Input: Recommended product or service list

[1362] Output: Data sent to the user's terminal

[1363] Step 9:

[1364] Display the products and services received by the user device.

[1365] Specific operation: The user device displays the received data on the screen, for example, "User B's highly rated cafe: Aroma Coffee."

[1366] Input: Data received from the server

[1367] Output: Recommended products or services displayed on the screen

[1368] Through the above steps, the present invention is able to recommend optimal products and content to users.

[1369] 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.

[1370] This invention is a system that learns a user's values, preferences, and emotions based on word-of-mouth reviews and recommends the most suitable products and content to the user. This system supports the user's decision-making by analyzing word-of-mouth reviews posted by the user using an artificial intelligence engine and an emotion engine, and recommending highly rated products from other users who share similar values. The system's program processing is described in detail below in natural language.

[1371] (Post a review)

[1372] Device: The user launches the application and is presented with a form for submitting a user review. The submission form includes a text input field and a star rating slider. The user enters their thoughts and evaluation of a specific product or service and sets a star rating. For example, a user might write a review of a cafe, saying, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[1373] User: Check the content of the word-of-mouth / review and press the post button.

[1374] (Data reception and storage)

[1375] Terminal: When the user presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[1376] Server: Receives word-of-mouth and review data sent from the device. Stores the received data in a database. Data stored includes the user ID, review content, star rating, posting date and time, etc. For example, if User A gives a five-star rating along with the comment, "The coffee at this cafe has a nice aroma and is relaxing," that data will be stored in the database.

[1377] (Data analysis and learning using AI and emotion engines)

[1378] Server: Notifies the AI ​​engine that newly posted customer reviews have been received. When notifying, passes the saved customer reviews to the AI ​​engine and emotion engine.

[1379] Emotion engine: Analyzes the text contained in word-of-mouth reviews and extracts emotions. The extracted emotions are expressed in a format such as positive or negative and sent to the server as analysis results. For example, a positive emotion is extracted from a review that reads, "The coffee at this cafe has a nice aroma and is relaxing."

[1380] AI model: The artificial intelligence engine analyzes word-of-mouth reviews based on the emotional information sent from the emotion engine. Natural language processing (NLP) technology is used to extract important keywords and emotions, and learn the user's values, hobbies, and preferences. For example, characteristics such as "nice scent" and "relaxing" are detected and added to User A's profile.

[1381] (Generating recommendation content)

[1382] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[1383] AI model: Based on learning data, it searches for other users with similar values. It also takes into account emotional information to find User B with a similar profile.

[1384] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[1385] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[1386] (Display of recommendation content)

[1387] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[1388] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[1389] This invention allows users to obtain useful information based on their values, tastes, and emotions, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[1390] The processing flow will be explained below.

[1391] Step 1:

[1392] Device: The user launches the application and is presented with a testimonial / review submission form, which includes a text input field and a star rating slider.

[1393] Step 2:

[1394] User: Enter your thoughts and ratings about the product or service in the text input field and set the rating using the star rating slider. For example, to review a cafe, you might write, "The coffee at this cafe is fragrant and relaxing," and set it to 5 stars.

[1395] Step 3:

[1396] Device: When the user checks the review content and presses the submit button, the entered data is sent to the server in JSON format, including the user ID, review content, star rating, etc.

[1397] Step 4:

[1398] Server: Receives word-of-mouth and review data sent from the device. The received data is temporarily stored in memory.

[1399] Step 5:

[1400] Server: The received data is stored in a database. This includes the user ID, review text, star rating, and posting date and time. For example, an SQL query like the following is executed: INSERT INTO reviews (user_id, review_text, star_rating, created_at) VALUES (...).

[1401] Step 6:

[1402] Server: Notifies the AI ​​engine and emotion engine that a new post has been made. When notifying, passes the saved word-of-mouth and review data for analysis.

[1403] Step 7:

[1404] Emotion engine: Analyzes text contained in reviews and extracts emotions. For example, it detects positive emotions in the comment, "The coffee at this cafe has a nice aroma and is relaxing."

[1405] Step 8:

[1406] Emotion engine: The extracted emotional information is sent to the server. For example, data containing the emotional information "positive" is returned to the server.

[1407] Step 9:

[1408] AI model: The artificial intelligence engine receives the emotional information and analyzes the text of the reviews. Natural language processing (NLP) techniques are used to extract keywords and emotions. For example, features such as "nice scent" and "relaxing" are extracted.

[1409] Step 10:

[1410] AI model: Based on the extracted features and emotional information, the AI ​​model learns the user's values, hobbies, and preferences and updates the user profile. Preferences such as "coffee aroma" and "relaxation" are added to User A's profile.

[1411] Step 11:

[1412] Server: Receives a new recommendation request from the user. For example, the user selects "Find a new cafe."

[1413] Step 12:

[1414] AI model: Based on learning data, it searches for other users with similar values. It finds User B with a similar profile. It also takes into account emotional information when selecting users.

[1415] Step 13:

[1416] AI model: Selects products and content that User B has given a high rating to. For example, selects a cafe called "Aroma Coffee" that User B has given a high rating to.

[1417] Step 14:

[1418] Server: The selected recommendations are encoded as JSON format data and sent to the user's device.

[1419] Step 15:

[1420] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[1421] Step 16:

[1422] User: Review the recommendations and decide on the next action. For example, User A decides to check the details of "Aroma Coffee" or visit the store.

[1423] Example 2

[1424] 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."

[1425] Conventional recommendation systems have difficulty recommending appropriate products and content that accurately reflect users' ratings and preferences. Furthermore, when used by many users, recommendations are often not based on individual values ​​and emotions, resulting in a decline in user satisfaction. Furthermore, there is a lack of recommendation systems that take emotional information into account, and there is a need to improve the user experience.

[1426] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for a user to transmit rating information, a means for the server to receive the rating information and store it in an information collection device, a means for a machine learning engine to analyze the stored rating information and learn the user's values ​​and preferences, a means for the server to select other users with similar values ​​and products that the users have highly rated based on the learned data, a means for transmitting the products selected by the server to the user's information terminal, and a means for the user's information terminal to display the received products. This enables recommendations that accurately reflect the user's emotional information and preferences.

[1427] "Rating information" refers to feedback that a user gives about a particular product or service, and is typically expressed in the form of text content and star ratings.

[1428] A "server" is a computer system that receives data sent by a user and processes it.

[1429] The "information collection device" includes a database and a storage device installed in the server, and is a device for saving received evaluation information.

[1430] A "machine learning engine" is a computer program that analyzes received and stored rating information and executes algorithms or models to learn user values ​​and preferences.

[1431] "Natural language processing technology" is a technology that analyzes text data and extracts important keywords and emotions from it.

[1432] A "recommended list" is a list of products and services selected based on the user's values ​​and preferences.

[1433] A "user's information terminal" is an electronic device used by a user, such as a smartphone or computer, that displays data sent from the server.

[1434] "Other users with similar values" refers to other users who share the same tastes and behavioral patterns as a given user.

[1435] "Product" refers to the specific product or service recommended to a user.

[1436] "Means" refers to a method or device, or a combination thereof, for achieving a particular purpose.

[1437] The present invention relates to a system that recommends optimal products and content based on user evaluation information. The system of this invention is implemented using the following hardware and software: a server and a user's information terminal (such as a smartphone or PC). It also uses software such as an artificial intelligence engine, a machine learning engine using natural language processing technology, and an information collection device for data storage.

[1438] The system's main functions are as follows: When a user submits rating information through the application, the information is sent to the server in JSON format. The server stores the received data in an information collection device. Next, a machine learning engine analyzes the data and learns the user's values ​​and preferences. This analysis uses natural language processing technology, and emotional information is also extracted.

[1439] Next, the server uses the learned data to select other users with similar values ​​and products that those users have highly rated. The selected products are sent from the server to the user's information terminal and displayed on the user's information terminal.

[1440] Specific examples are shown below.

[1441] First, a user submits a review of a specific product, writing, "The coffee at this cafe has a nice aroma and is relaxing," along with a rating of 5 stars. The server receives this review and stores it in a database. A machine learning engine then analyzes the review, extracting keywords such as "nice aroma" and "relaxing" as well as positive emotions, and adds them to the user's profile.

[1442] When the user then sends a request to "find a new cafe," the server searches for other users with similar values ​​and recommends products that those users have given high ratings to, such as a cafe called "Aroma Coffee." This recommendation information is sent in JSON format to the user's device, and is displayed as "Cafe highly rated by User B: Aroma Coffee."

[1443] Below are some example prompts to be input to the generative AI model:

[1444] "Analyze the following review posted by user A and extract sentiment and value information:

[1445] Review: "The coffee at this cafe is aromatic and relaxing." Star rating: 5 stars

[1446] Analyze various reviews, find users with a similar profile to User B, and recommend highly rated products. For example, recommend "Aroma Coffee," which User B highly rated.

[1447] This system enables recommendations that accurately reflect the user's emotional information and preferences, thereby increasing user satisfaction.

[1448] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1449] Step 1: Submit a review

[1450] Device: The user launches the application and opens the review submission form. The submission form includes a text input field and a star rating slider. The user enters their thoughts and evaluation of a specific product or service and sets a star rating. For example, a user might write a review of a cafe saying, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[1451] Input: User input of text and star rating.

[1452] Output: When the submit button is pressed, the entered data is passed to the following step.

[1453] Specific behavior: When the user presses the submit button, the application prepares the data to be sent in JSON format.

[1454] Step 2: Receiving and storing data

[1455] Terminal: When the submit button is pressed, the application sends the data in JSON format to the server.

[1456] Input: JSON formatted word-of-mouth and review data (user ID, review content, star rating, etc.).

[1457] Server: The server receives the word-of-mouth and review data sent from the device and stores it in an information collection device (database). The stored data includes the user ID, review content, star rating, posting date and time, etc.

[1458] Output: The saved data will be used for analysis in the next step.

[1459] Specific behavior: To confirm that the data was saved successfully, the success / failure of the save process is recorded in the log.

[1460] Step 3: Data analysis and learning using AI and emotion engines

[1461] Server: Notifies the AI ​​engine of newly posted word-of-mouth and review data.

[1462] Input: Customer reviews stored in a database.

[1463] Emotion engine: Analyzes the text of reviews and extracts emotional information such as positive and negative sentiment. This emotional information is sent back to the server.

[1464] AI model: The AI ​​engine analyzes user reviews based on emotional information and extracts important keywords and emotions, thereby learning user values ​​and preferences.

[1465] Output: The analysis results are reflected in the user's profile, and values ​​and preferences are updated.

[1466] Specific operation: The results of extracting emotional information and important keywords are recorded in a log and added to the user profile.

[1467] Step 4: Generate recommendations

[1468] Server: The user requests a new recommendation (e.g., "Find a new cafe").

[1469] Input: A user's profile and a new recommendation request.

[1470] AI model: Based on learning data, it searches for other users with similar values ​​and identifies users with similar profiles by taking into account emotional information. It then selects products and content that User B has highly rated. For example, it selects a cafe called "Aroma Coffee."

[1471] Output: Selected recommendations encoded in JSON format.

[1472] Specific operations: Generate a recommendation list, execute a test process to confirm the selection results, and record the generated recommendation list in a log.

[1473] Step 5: View your recommendations

[1474] Server: Sends the selected recommendations to the user's device.

[1475] Input: JSON format data of recommendation content.

[1476] Terminal: The recommendation received from the server is displayed to the user. For example, "User B's highly rated cafe: Aroma Coffee" is displayed.

[1477] Output: The displayed recommendation.

[1478] Specific behavior: Display recommendations in a format that is easy for users to review and provide an interface for users to take the next action.

[1479] (Application example 2)

[1480] 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."

[1481] Conventional recommendation systems have difficulty accurately grasping a user's values ​​and preferences, and have therefore been unable to provide recommendations that adequately meet individual needs. Furthermore, due to a lack of means to analyze emotional information, highly accurate recommendations based on the user's emotions have not been realized. As a result, user satisfaction is low and the filter bubble problem is likely to occur.

[1482] 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.

[1483] In this invention, the server includes: a means for users to send word-of-mouth reviews; a means for the server to receive the word-of-mouth reviews and store them in a database; a sentiment analysis engine to analyze the emotions contained in the word-of-mouth reviews and extract emotional information; an artificial intelligence engine to learn the user's values ​​and preferences based on the stored word-of-mouth reviews and emotional information; a means for the server to select other users with similar values ​​and products highly rated by those users based on the learned data; a means for transmitting the products selected by the server to a user terminal; and a means for the user terminal to display the products received. This enables highly accurate recommendations based on the user's values ​​and emotions.

[1484] "Means for users to submit word-of-mouth / reviews" refers to the functions and interfaces that allow users to input their ratings and opinions about products and services and send them to the server.

[1485] "Means by which the server receives the reviews and comments and stores them in a database" refers to the functions and processes by which the server receives the reviews and comments sent by users and stores them in a database.

[1486] "Means for an emotion analysis engine to analyze emotions contained in word-of-mouth reviews and extract emotional information" refers to technology and software that analyzes emotional elements such as positive and negative emotions from word-of-mouth reviews and extracts them as data.

[1487] "Means for an artificial intelligence engine to learn a user's values, hobbies, and preferences based on saved word-of-mouth reviews and emotional information" refers to algorithms and programs that analyze saved word-of-mouth reviews and emotional information to learn a user's characteristics and preferences.

[1488] "Means for the server to select other users with similar values ​​and products that have been highly rated by those users based on learned data" refers to the function or process of selecting other users with similar values ​​and products that have been highly rated by those users based on learned data.

[1489] The "means for the server to transmit the selected product to the user terminal" refers to the function or process for transmitting information about the selected product to the user terminal.

[1490] The "means for displaying the product received by the user terminal" is an interface for visually displaying the product information received by the user terminal to the user.

[1491] This invention is a system that learns a user's values, preferences, and emotions based on word-of-mouth and reviews, and recommends the most suitable products and content to the user. This system uses an artificial intelligence engine and a sentiment analysis engine to analyze word-of-mouth and reviews posted by the user, and recommends highly rated products from other users who share the same values. The system's program processing is explained in detail below.

[1492] Hardware and software used

[1493] Hardware

[1494] Smartphone

[1495] server

[1496] software

[1497] Python

[1498] Flask (server-side web framework)

[1499] TextBlob (emotion analysis)

[1500] JSON (data format)

[1501] Requests (HTTP request library)

[1502] User reviews and data processing

[1503] First, users submit testimonials and reviews about products and services through a smartphone application. The submission form includes a text input field and a star rating slider. For example, users can write, "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars.

[1504] Receiving and storing data on the server

[1505] When a user clicks the submit button, the entered user feedback and review data is sent to the server in JSON format. The data includes the user ID, review content, star rating, and posting date and time. The server stores the received data in a database.

[1506] Analysis using sentiment analysis engine and artificial intelligence engine

[1507] The server notifies the sentiment analysis engine of newly posted word-of-mouth and review data. The sentiment analysis engine analyzes the text and extracts emotional information, such as positive or negative. For example, a review that reads, "The coffee at this cafe has a nice aroma and is relaxing," would extract a positive sentiment.

[1508] Next, an artificial intelligence engine analyzes the reviews based on emotional information. Using natural language processing (NLP) technology, it extracts important keywords and emotions, learning the user's values, hobbies, and preferences. For example, characteristics such as "nice scent" and "relaxing" are detected and added to the user's profile.

[1509] Recommendation generation

[1510] The server receives a new recommendation request from a user. Based on the learning data, the AI ​​model searches for other users with similar values ​​and selects products that have been highly rated by users with similar profiles, taking into account emotional information. For example, it selects "Aroma Coffee," a cafe highly rated by User B.

[1511] Displaying recommendations

[1512] The selected recommendation is encoded as JSON data and sent to the user's device. The device then displays the received recommendation to the user. For example, it might say, "User B highly rated cafe: Aroma Coffee." The user can review the recommendation and decide what to do next.

[1513] Examples of concrete examples and prompts

[1514] Here are some examples of prompts to input to a generative AI model:

[1515] "Analyze user values ​​and sentiments based on the following reviews:

[1516] Review: The coffee at this cafe is aromatic and relaxing.

[1517] Extract the detected emotions and features that may represent values, interests, and preferences.

[1518] By using this prompt, the model can learn emotions and specific values ​​and recommend the best products for the user.

[1519] This invention allows users to obtain useful information based on their values, tastes, and emotions, expanding their options and eliminating the filter bubble problem. It also allows users to enjoy new discoveries, providing a more satisfying consumer experience.

[1520] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1521] Step 1:

[1522] Users submit their testimonials and reviews

[1523] Users post word-of-mouth reviews of products and services through a smartphone app. The input form includes a text field and a star rating slider. For example, a user might enter "The coffee at this cafe is fragrant and relaxing," and set the rating to five stars. This is the input data. When the user presses the submit button, the data is sent to the server in JSON format.

[1524] Step 2:

[1525] The server receives the reviews and stores them in a database.

[1526] The server receives the testimonials and reviews sent by users. The data includes the user ID, review content, star rating, and posting date and time. The server parses the received data and saves it in a database. Specifically, it parses the received JSON data and stores it in the appropriate fields. The output data is a record saved in the database.

[1527] Step 3:

[1528] The sentiment analysis engine analyzes the emotions contained in word-of-mouth reviews and extracts emotional information.

[1529] The server notifies the sentiment analysis engine of newly posted word-of-mouth and review data. The sentiment analysis engine uses NLP techniques such as TextBlob to analyze the sentiment from the review content and extract emotional information such as positive and negative. For example, a positive sentiment is extracted from the review "The coffee at this cafe has a nice aroma and is relaxing." The input data is the review content, and the output data is emotional information.

[1530] Step 4:

[1531] The AI ​​engine learns the user's values, preferences, and tastes based on the saved reviews and emotional information.

[1532] The server passes the word-of-mouth and review data along with emotional information to an AI engine. The AI ​​engine uses natural language processing technology to extract important keywords and features from the review content and learns the user's values, hobbies, and preferences. For example, features such as "nice scent" and "relaxing" are detected and added to the user profile. The input data is the word-of-mouth and review data and emotional information, and the output data is the updated user profile.

[1533] Step 5:

[1534] Based on the learned data, the server selects other users with similar values ​​and products that those users have highly rated.

[1535] The server searches for other users with similar values ​​and hobbies based on data learned by the artificial intelligence engine. In doing so, it also takes into account emotional information and selects products that have been highly rated by users with similar profiles. For example, it selects "Aroma Coffee," a cafe that other users have highly rated. The input data is the user profile, and the output data is a list of recommended products.

[1536] Step 6:

[1537] The server sends the selected product to the user's device.

[1538] The server sends the selected product information in JSON format to the user's device. Specifically, the server encodes the recommended product list and sends it to the user's device via an HTTP request. The input data is the recommended product list, and the output data is the data sent to the user's device.

[1539] Step 7:

[1540] Display the received product on the user's device

[1541] The user device displays the received recommended product information. The application decodes the JSON data and displays it visually to the user. For example, it displays "User B's highly rated cafe: Aroma Coffee." The input data is the recommended product data received from the server, and the output data is the content displayed to the user.

[1542] 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.

[1543] 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.

[1544] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1545] 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.

[1546] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1547] 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.

[1548] 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).

[1549] 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.

[1550] 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."

[1551] 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.

[1552] 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).

[1553] 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.

[1554] 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.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] 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.

[1561] 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.

[1562] 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.

[1563] The following is further disclosed regarding the above embodiment.

[1564] (Claim 1)

[1565] A means for users to submit testimonials and reviews,

[1566] A server receives the reviews and stores them in a database;

[1567] The AI ​​engine analyzes the saved word-of-mouth reviews and learns the user's values, tastes, and preferences.

[1568] The server uses the learned data to select other users with similar values ​​and products that those users have highly rated.

[1569] A means for transmitting the selected product to a user terminal by the server;

[1570] The system includes means for displaying the received merchandise by the user terminal.

[1571] (Claim 2)

[1572] The system according to claim 1, further comprising means for extracting user values, hobbies and preferences using natural language processing technology when the artificial intelligence engine analyzes word-of-mouth and reviews.

[1573] (Claim 3)

[1574] 10. The system of claim 1, wherein the server includes means for generating a recommendation list in response to a user request.

[1575] "Example 1"

[1576] (Claim 1)

[1577] a means for users to submit rating information;

[1578] a means for the server to receive the rating information and store it in a database;

[1579] A means for an artificial intelligence engine to analyze the stored rating information and learn about the user's values ​​and interests;

[1580] The server uses the learned data to select other users with similar values ​​and products that those users have highly rated.

[1581] A means for transmitting the selected product to a user terminal by the server;

[1582] The system includes means for displaying the received merchandise by the user terminal.

[1583] (Claim 2)

[1584] 2. The system according to claim 1, further comprising means for extracting the user's values ​​and interests using natural language processing technology when the artificial intelligence engine analyzes the evaluation information.

[1585] (Claim 3)

[1586] 10. The system of claim 1, wherein the server includes means for generating a recommendation list in response to a user request.

[1587] "Application Example 1"

[1588] (Claim 1)

[1589] A means for users to submit testimonials and reviews,

[1590] A server receives the reviews and stores them in a database;

[1591] The AI ​​engine analyzes the saved word-of-mouth reviews and learns the user's values, tastes, and preferences.

[1592] The server uses the learned data to select other users with similar values ​​and products that those users have highly rated.

[1593] A means for transmitting the selected product to a user terminal by the server;

[1594] A means for displaying the received product on the user terminal;

[1595] A means to provide real-time, value-based recommendations for categories of interest to users;

[1596] A way to recommend new products based on reviews from other users who share similar values

[1597] A system including:

[1598] (Claim 2)

[1599] The system according to claim 1, further comprising means for extracting user values, hobbies and preferences using natural language processing technology when the artificial intelligence engine analyzes word-of-mouth and reviews.

[1600] (Claim 3)

[1601] 2. The system according to claim 1, further comprising: means for the server to generate a recommendation list in response to a user request; and means for the user to receive product recommendations in real time.

[1602] "Example 2: Combining Emotion Engines"

[1603] (Claim 1)

[1604] a means for users to submit rating information;

[1605] A server receives the evaluation information and stores it in an information collection device;

[1606] A machine learning engine analyzes the stored rating information and learns the user's values ​​and preferences.

[1607] The server uses the learned data to select other users with similar values ​​and products that those users have highly rated.

[1608] A means for transmitting the selected product by the server to the user's information terminal;

[1609] The system includes a means for displaying the received product on the user's information terminal.

[1610] (Claim 2)

[1611] 2. The system according to claim 1, further comprising means for extracting user values ​​and preferences using natural language processing technology when the machine learning engine analyzes the evaluation information.

[1612] (Claim 3)

[1613] 10. The system of claim 1, wherein the server includes means for generating a recommendation list in response to a user request.

[1614] "Application example 2 when combining emotion engines"

[1615] (Claim 1)

[1616] A means for users to submit testimonials and reviews,

[1617] A server receives the reviews and stores them in a database;

[1618] A sentiment analysis engine analyzes the sentiment contained in word-of-mouth reviews and extracts emotional information;

[1619] The AI ​​engine learns the user's values ​​and preferences based on the stored word-of-mouth reviews and emotional information,

[1620] The server uses the learned data to select other users with similar values ​​and products that those users have highly rated.

[1621] A means for transmitting the selected product to a user terminal by the server;

[1622] The system includes means for displaying the received merchandise by the user terminal.

[1623] (Claim 2)

[1624] The system according to claim 1, further comprising means for extracting user values, hobbies and preferences using natural language processing technology when the artificial intelligence engine analyzes word-of-mouth and reviews.

[1625] (Claim 3)

[1626] 10. The system of claim 1, wherein the server includes means for generating a recommendation list in response to a user request. [Explanation of symbols]

[1627] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A way for users to submit word-of-mouth and reviews, A server receives the word-of-mouth reviews and stores them in a database. The AI ​​engine analyzes the saved word-of-mouth and reviews to learn the user's values, hobbies, and preferences. The server uses the learned data to select other users with similar values ​​and products that those users have highly rated. A means for transmitting the selected product to a user terminal by the server; The system includes means for displaying the received merchandise by the user terminal.

2. 2. The system according to claim 1, further comprising means for extracting user values ​​and preferences using natural language processing technology when the artificial intelligence engine analyzes word-of-mouth and reviews.

3. 2. The system of claim 1, wherein the server includes means for generating a recommendation list in response to a user request.

Images