System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting and storing information of a user, a means for recommending an optimum matching partner on the basis of the information of the user, a means for analyzing conversation logs and posting contents of the user and generating appropriate advice, and a means for proposing a date plan of the user.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 modern society, the declining birthrate and aging population have become serious problems, making it essential to improve the success rate of romantic relationships. However, many people have anxiety and worries about love, making it difficult to find a suitable partner. Many also experience a lack of communication and find it difficult to form relationships. To solve these issues, there is a need to build a system that provides users with personalized advice, training, and date plan suggestions, thereby increasing the success rate of romantic relationships. [Means for solving the problem]

[0005] The present invention provides a means for collecting and storing user information and a means for recommending optimal matches based on that information. The above-mentioned problems are solved by constructing a system that includes a means for analyzing users' conversation logs and posts, generating appropriate advice, and proposing date plans. Furthermore, by adding a means for collecting and storing user feedback and a means for reflecting this feedback in subsequent proposals, the system's accuracy is improved and user satisfaction is enhanced. Furthermore, by comprehensively collecting and analyzing users' profile information, preferences, and romantic goals, and providing individually optimized advice and training, the success rate of romantic relationships can be increased.

[0006] "User" refers to an individual who uses the system.

[0007] "Information" refers to data including a user's profile information, preferences, relationship goals, conversation logs, and posted content.

[0008] "Collection" refers to the act of gathering specific data or information.

[0009] "Storage" refers to the act of keeping collected data or information in a storage device or the like.

[0010] "Optimal" refers to the state that is most suitable for specific conditions or purposes.

[0011] "Matching partners" refer to potential partners who are suitable based on the user's profile and preferences.

[0012] "Recommendation" refers to the act of selecting and presenting a specific target.

[0013] "Conversation log" refers to a record of messages exchanged between users through the system.

[0014] "Posted Content" refers to messages and content posted by users on social media or other platforms.

[0015] "Analysis" refers to the act of analyzing data or information and clarifying its meaning and trends.

[0016] "Advice" refers to advice or suggestions provided to assist a user in taking action or making a decision.

[0017] "Training" refers to training or instruction to improve a user's abilities or skills.

[0018] "Date Plan" refers to suggestions and schedules that users can use as a reference when planning a date.

[0019] "Proposal" refers to the act of offering a specific idea or plan.

[0020] "Feedback" refers to information collected from users about their opinions and evaluations, and used to make improvements and changes.

[0021] "Profile Information" refers to a user's basic personal information, such as name, age, hobbies, and occupation.

[0022] "Interest Information" refers to information about a user's interests, preferences, preferred activities and interests.

[0023] "Love goals" refers to the objectives or goals that users want to achieve in love.

[0024] "Natural language processing (NLP)" refers to technology for understanding, interpreting, and generating human language, and is used for text analysis, etc. [Brief explanation of the drawings]

[0025] [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

[0026] 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.

[0027] First, the terms used in the following description will be explained.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] [First embodiment]

[0034] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0035] 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.

[0036] 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).

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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."

[0046] The present invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans.

[0047] Overall system configuration

[0048] This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and provides suggestions for information, while the terminal provides an interface for users. Users use the system to input information and receive suggestions.

[0049] Collection and storage of user information

[0050] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, hobbies, relationship goals, etc.).

[0051] Terminal: Sends the entered information to the server.

[0052] Server: Stores the received information in a database.

[0053] Matching partner recommendations

[0054] Server: Uses the user's profile and preferences to select the most suitable match from the database.

[0055] Server: Sends the selected matching candidates to the device.

[0056] Device: The profile of the recommended person is displayed to the user for confirmation.

[0057] User: View the recommended people and select "Like" or "Dislike."

[0058] Terminal: Sends the selection results to the server.

[0059] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[0060] Analysis of conversation logs and social media posts

[0061] Device: The user's conversation log and social media posts are periodically sent to the server.

[0062] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content, extracting the other person's interests, concerns, and emotional tone.

[0063] Example: For example, if a user talks a lot about movies and music, the system can analyze that information and determine that the other person is likely interested in movies and music.

[0064] Providing advice and training

[0065] Server: Based on the analysis results, the server generates advice and training tailored to the user. For example, it provides advice such as "Talk about the other person's favorite movie in your next conversation."

[0066] Server: Sends the generated advice to the device.

[0067] Terminal: Display the received advice to the user.

[0068] User: Check out the advice and apply it to your next conversation or date.

[0069] Date plan suggestions

[0070] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[0071] Terminal: Sends the entered conditions to the server.

[0072] Server: Generates optimal date plans based on the conditions and the user's preferences. For example, it suggests restaurants and events.

[0073] Server: Sends the proposed date plan to the device.

[0074] Device: Display date plans to the user.

[0075] Gathering and implementing feedback

[0076] Device: After the date, users are sent a feedback survey and asked to enter their impressions and evaluation of the date.

[0077] User: Enter your feedback and tap the submit button.

[0078] Device: Sends feedback to the server.

[0079] Server: Stores the collected feedback and incorporates it into the next proposal.

[0080] This enables the system to increase users' chances of success in love and help them form efficient and effective partnerships.

[0081] The processing flow will be explained below.

[0082] Collection and storage of user information

[0083] Step 1:

[0084] User: Launch the app and enter user information (name, age, hobbies, relationship goals, etc.).

[0085] Step 2:

[0086] Terminal: Sends the entered information to the server.

[0087] Step 3:

[0088] Server: Stores the received user information in a database.

[0089] Matching partner recommendations

[0090] Step 1:

[0091] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[0092] Step 2:

[0093] Server: Sends the selected matching candidates to the device.

[0094] Step 3:

[0095] On your device: The profile of the recommended person will be displayed to you.

[0096] Step 4:

[0097] User: View the recommended people and select "Like" or "Dislike."

[0098] Step 5:

[0099] Terminal: Sends the user's selection to the server.

[0100] Step 6:

[0101] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[0102] Analysis of conversation logs and social media posts

[0103] Step 1:

[0104] Device: The user's conversation log and SNS postings are periodically sent to the server.

[0105] Step 2:

[0106] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[0107] Step 3:

[0108] Server: Extract the other person's interest, concern, and emotional tone.

[0109] Providing advice and training

[0110] Step 1:

[0111] Server: Based on the analysis results, it generates advice and training content tailored to the user.

[0112] Step 2:

[0113] Server: Sends the generated advice to the device.

[0114] Step 3:

[0115] Device: Displays received advice and training content to the user.

[0116] Step 4:

[0117] Users: Review advice and training and apply it to their next conversation or date.

[0118] Date plan suggestions

[0119] Step 1:

[0120] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[0121] Step 2:

[0122] Terminal: Sends the entered conditions to the server.

[0123] Step 3:

[0124] Server: Generates the optimal date plan taking into account the conditions and the user's preferences.

[0125] Step 4:

[0126] Server: Sends the proposed date plan to the device.

[0127] Step 5:

[0128] Device: Display date plans to the user.

[0129] Gathering and implementing feedback

[0130] Step 1:

[0131] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[0132] Step 2:

[0133] User: Enters date feedback and taps submit.

[0134] Step 3:

[0135] Device: Sends feedback to the server.

[0136] Step 4:

[0137] Server: Stores the collected feedback and incorporates it into the next proposal.

[0138] Example 1

[0139] 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."

[0140] In conventional matchmaking systems, the collection and storage of user information, the recommendation of potential matches, and the generation of advice are often carried out separately, resulting in a lack of integration as a whole system. Furthermore, insufficient analysis of users' conversation logs and social media posts can lead to issues such as inappropriate advice not being provided and date plan suggestions not matching the user's preferences or requirements. Furthermore, there are also issues with inefficient collection and reflection of feedback, which means that improvements are not incorporated into future proposals.

[0141] 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.

[0142] In this invention, the server includes means for collecting and storing user information, means for recommending optimal matches based on the user information, means for analyzing the user's conversation log and postings and generating appropriate advice using a natural language processing engine, and means for proposing date plans that meet the user's requirements. This enables integrated management of user information, providing highly accurate matching and advice, and proposing date plans that meet the user's preferences and requirements. Furthermore, by collecting feedback and analyzing it using a machine learning algorithm, it is possible to continuously improve the recommendation algorithm and reflect this in future recommendations.

[0143] A "user" is an individual who uses the system and provides information such as personal information, hobbies, preferences, and romantic intentions.

[0144] "Means of collecting and storing information" refers to various functions for storing information provided by users, such as personal information, hobbies, preferences, and romantic intentions, in a database.

[0145] "Means for recommending matching partners" refers to algorithms and functions that select the most suitable partner based on the user's information and provide that information to the user.

[0146] "Means for analyzing conversation logs and posted content" refers to the function of analyzing users' conversation logs and SNS posts using a natural language processing engine, etc., and generating appropriate advice for users based on the results obtained.

[0147] A "natural language processing engine" is a software engine that analyzes text data and extracts meaning, emotion, topics, etc.

[0148] "Means for generating advice" refers to a function that generates and provides appropriate advice on actions and conversations to users based on the analysis results.

[0149] "Means for proposing date plans" refers to a function that generates an appropriate date plan based on the conditions provided by the user (location, budget, date and time, etc.) and proposes it to the user.

[0150] "Means for collecting and storing feedback" refers to a function for storing feedback provided by users, such as impressions and ratings after a date, in a database.

[0151] A "machine learning algorithm" is an algorithm that analyzes feedback data and learns to improve the accuracy of future suggestions and recommendation algorithms.

[0152] "Profile Information" refers to a user's basic personal information (such as name, age, etc.).

[0153] "Interest information" refers to information about a user's interests, hobbies, and preferences.

[0154] "Love goals" refers to the objectives that users want to achieve in love (e.g., serious relationship, finding friends, etc.).

[0155] "Generation policy" refers to guidelines and standards for providing optimal advice and training to users based on the analysis results.

[0156] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions.

[0157] Collection and storage of user information

[0158] Users start the application from a device such as a smartphone or PC and enter initial registration information such as their name, age, hobbies, and romantic interests. The device then sends the collected information to the server, which then stores the received information in a database. Data is sent in JSON or XML format, and is securely transmitted via HTTPS requests.

[0159] Matching partner recommendations

[0160] The server uses an algorithm to select the most suitable match based on the user's profile and preferences. The algorithm uses KNN (nearest neighbor search) and collaborative filtering to select candidates with many similarities. The selected match candidates are sent from the server to the device, which displays the information to the user. The user looks at the recommended partners and selects either "like" or "dislike," and sends the result to the server via the device. The server stores the selection results in a database and uses them to improve the recommendation algorithm in the future.

[0161] Analysis of conversation logs and social media posts

[0162] The device periodically sends the user's conversation log and social media posts to a server. The server then analyzes the collected data using a natural language processing (NLP) engine. Libraries such as spaCy and NLTK are used for this analysis. The analysis extracts the other person's interests, concerns, and emotional tone. Specifically, if the user talks a lot about movies and music, the system determines that the other person is likely to be interested in these subjects.

[0163] Providing advice and training

[0164] The server generates optimal advice and training for the user based on the results of NLP analysis. A generative AI model (e.g., GPT-3 (registered trademark)) is used for this generation. For example, advice such as "Talk about the other person's favorite movie in your next conversation" is provided. The generated advice is sent from the server to the device, which displays it to the user. The user can confirm the advice and put it into practice in their next conversation or date.

[0165] Date plan suggestions

[0166] The user requests a date plan proposal and enters conditions (location, budget, date and time, etc.). These conditions are sent from the device to the server. The server generates the optimal date plan taking into account the conditions and the user's preferences. For example, it may suggest restaurants or events. To generate this plan, it references various APIs and databases to select a plan that meets the user's conditions. The generated date plan is sent from the server to the device, which then displays it to the user.

[0167] Gathering and implementing feedback

[0168] After the date, the device sends the user a feedback survey. The user enters their impressions and evaluation of the date and taps the send button. The collected feedback is sent from the device to the server, which stores it in a database. The server then analyzes this feedback data using a machine learning algorithm and reflects it in future recommendations. This allows for continuous improvement of the recommendation algorithm.

[0169] Prompt Sentence Examples

[0170] Examples of prompts with examples include:

[0171] "User A is a 35-year-old man whose hobbies are watching movies and hiking. After he enters his profile, please explain how the system recommends his best matches. Also, please explain the specific process of providing advice and proposing date plans."

[0172] This prompt is fed into a generative AI model, which then provides a concrete explanation of the overall flow of the system.

[0173] The above is a form for implementing the present invention, and this system can increase the user's success rate in romance and support the formation of efficient and effective partnerships.

[0174] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0175] Step 1:

[0176] Input: The user launches the application from their smartphone or computer and enters their initial registration information (name, age, hobbies, and romantic intent).

[0177] Action: The user fills in the application's registration form and presses the submit button.

[0178] Terminal: The input information is packaged in JSON or XML format and sent to the server via an HTTPS request.

[0179] Output: Personal information sent to the server.

[0180] Step 2:

[0181] Input: User information sent from the device in step 1.

[0182] How it works: The server parses the incoming data and stores the information in a database using SQL queries. The database used is MySQL (registered trademark) or PostgreSQL.

[0183] Server: Inserts and stores the received information into a database.

[0184] Output: User information stored in the database.

[0185] Step 3:

[0186] Input: User profile and interest information stored in a database.

[0187] How it works: The server uses KNN (Knowledge Neighborhood Search) and collaborative filtering algorithms to select the best match.

[0188] Server: Packages the selection results in JSON format and sends them to the terminal.

[0189] Output: Match candidate information sent to the device.

[0190] Step 4:

[0191] Input: Match candidate information sent from the server.

[0192] What it does: The device displays profiles of potential matches to the user, using a list view or card layout.

[0193] Terminal: Displays the selection results to the user.

[0194] Output: Match candidate information displayed to the user.

[0195] Step 5:

[0196] Input: The match candidate information displayed to the user.

[0197] How it works: The user selects "like" or "dislike" and the result is sent from the device to the server.

[0198] User: Look at the recommended partners and make a selection.

[0199] Terminal: The selection results are packaged in JSON format and sent to the server.

[0200] Output: The selection results sent to the server.

[0201] Step 6:

[0202] Input: The selection sent from the terminal in step 5.

[0203] How it works: The server analyzes the selection results, stores them in a database, and uses them to improve the recommendation algorithm in the future.

[0204] Server: Records preference data and uses it as training data for recommendation algorithms.

[0205] Output: Selection results stored in a database.

[0206] Step 7:

[0207] Input: User conversation logs and social media posts.

[0208] How it works: The device periodically sends conversation logs and social media posts in JSON format to the server.

[0209] Terminal: Collects log data, packages it, and sends it to the server.

[0210] Output: Conversation logs and SNS posting data sent to the server.

[0211] Step 8:

[0212] Input: Conversation logs and social media post data sent in step 7.

[0213] How it works: The server performs the analysis using a natural language processing (NLP) engine (e.g. spaCy or NLTK).

[0214] Server: Performs sentiment analysis and key phrase extraction using collected data.

[0215] Output: Areas of interest and emotional tone derived from the analysis.

[0216] Step 9:

[0217] Input: NLP analysis results.

[0218] How it works: The server generates appropriate advice and training content based on the analysis results. It uses a generative AI model (e.g., GPT-3).

[0219] Server: Utilizes generative AI models to generate personalized advice.

[0220] Output: The generated advice and training content.

[0221] Step 10:

[0222] Input: Generated advice and training content.

[0223] Operation: The server sends advice to the device.

[0224] Server: Packages advice in JSON format and sends it to the device.

[0225] Output: Advice sent to the terminal.

[0226] Step 11:

[0227] Input: Advice sent by the server.

[0228] What it does: The device displays advice to the user, using a pop-up message or notification bar.

[0229] Terminal: Presents advice to the user.

[0230] Output: The advice displayed to the user.

[0231] Step 12:

[0232] Input: The date plan conditions requested by the user (location, budget, date and time).

[0233] Operation: The device sends the conditions in JSON format to the server.

[0234] User: Enter the conditions for the date plan.

[0235] Terminal: Packages and sends the conditions.

[0236] Output: Dateplan conditions sent to the server.

[0237] Step 13:

[0238] Input: Date plan conditions and user preferences.

[0239] How it works: The server generates the optimal date plan based on the conditions and preferences. It does so by referencing various APIs and databases.

[0240] Server: Searches a database of restaurants and events and selects plans that match your criteria.

[0241] Output: The generated date plan.

[0242] Step 14:

[0243] Input: Date plan sent from the server.

[0244] How it works: The server sends the plan to the device, packaging it in JSON format.

[0245] Server: Sends the generated date plan to the device.

[0246] Output: The date plan sent to the device.

[0247] Step 15:

[0248] Input: Date plan information sent from the server.

[0249] Action: The device displays the date plan to the user. Use the details page.

[0250] Device: Display date plans.

[0251] Output: The date plan displayed to the user.

[0252] Step 16:

[0253] Input: Post-date feedback survey.

[0254] Operation: The device sends a survey to the user via push notification. The user fills out the survey and presses the send button.

[0255] Terminal: Collects surveys and sends them to the server.

[0256] Output: Feedback data sent to the server.

[0257] Step 17:

[0258] Input: Feedback data collected in step 16.

[0259] How it works: The server stores the feedback data in a database and analyzes it using machine learning algorithms.

[0260] Server: Updates the recommendation algorithm based on the feedback data and reflects it in the next proposal.

[0261] Output: Analysis results stored in a database and updated recommendation algorithms.

[0262] The above is the specific processing flow of the system program.

[0263] (Application example 1)

[0264] 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."

[0265] Conventional content distribution services have recommended limited content based on users' past viewing history and preferences. This has made it difficult for users to efficiently discover diverse new content that interests them. Furthermore, the provision of appropriate viewing schedules and advice has been insufficient, preventing users from maximizing their viewing experience. The present invention aims to solve these problems and improve user satisfaction by providing individually customized content recommendations and viewing advice to users.

[0266] 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.

[0267] In this invention, the server includes means for collecting and storing user information, means for recommending optimal content, means for analyzing user conversation logs and posted content to generate appropriate advice, and means for proposing viewing schedules, thereby enabling users to efficiently discover a variety of new content that interests them and receive appropriate viewing schedules and advice.

[0268] "User information" is a collective term for profile information, preference information, and viewing history collected when using the system.

[0269] "Storage means" refers to a function for storing collected user information in a storage device such as a database.

[0270] "Recommendation means" is a function that selects and suggests the most appropriate content based on saved user information.

[0271] "Conversation log" refers to the text messages and communication history entered by the user.

[0272] "Posted content" refers to comments and feedback posted by users on social media or review sites.

[0273] "Means of analysis" refers to a function that analyzes conversation logs and posted content using natural language processing technology, etc., to extract users' hobbies and interests.

[0274] The "means for generating advice" is a function that automatically generates appropriate content and viewing advice for users based on the analysis results.

[0275] The "means for proposing a viewing schedule" is a function that proposes an optimal content viewing schedule based on the user's lifestyle and past viewing patterns.

[0276] "Feedback" refers to opinions such as ratings and impressions of content viewed by users.

[0277] "Means of reflection" is a function that analyzes collected feedback and uses it to recommend content or generate advice next time.

[0278] The present invention is embodied as a personalized video recommendation system for use in a content distribution service. The system is mainly composed of a server, a terminal, and a user, and is realized by the following means and processing steps.

[0279] Overall system configuration

[0280] This system consists of a client terminal (e.g., a smartphone) and a server. The server collects, stores, analyzes, and recommends information, while the terminal provides an interface with the user. The user also uses the system to input information and receive suggestions.

[0281] Collection and storage of user information

[0282] User: Launches the smartphone app and enters information such as name, age, hobbies, and viewing history when registering for the first time.

[0283] Terminal: Sends collected user information to the server.

[0284] Server: Stores the received information in a database, which is used for future data analysis and to improve recommendation algorithms.

[0285] Content Recommendations

[0286] Server: Selects the most suitable video content from the database based on the user's profile, preferences, and viewing history. For example, if a user likes sci-fi movies, it will recommend new and highly rated movies in the sci-fi genre.

[0287] Device: A list of recommended content is displayed to the user, who can select "Like" or "Dislike."

[0288] Server: Stores the user's selections and uses them to improve the recommendation algorithm in the future.

[0289] Analysis of conversation logs and postings

[0290] Device: The user's conversation log and social media posts are periodically sent to the server.

[0291] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content. For example, generative AI models such as spaCy and BERT are used. Through analysis, the user's interests, concerns, and emotional tone are extracted. For example, if a user frequently comments about a particular actor on social media, movies starring that actor can be recommended.

[0292] Advice generation and viewing schedule suggestions

[0293] Server: Based on the analysis results, the server generates advice and viewing schedules tailored to the user. For example, it provides advice such as "This is the next sci-fi movie you should watch."

[0294] Device: The generated advice and schedule are displayed to the user, who can use them to plan their viewing plans.

[0295] Gathering and implementing feedback

[0296] Device: After viewing the content, a feedback survey is sent to the user, in which they are asked to enter their rating and impressions.

[0297] User: Enter feedback and tap submit.

[0298] Device: Sends feedback to the server.

[0299] Server: Stores the collected feedback and uses it to generate the next recommendation or advice.

[0300] This allows the system to improve the user's viewing experience and effectively support the discovery of diverse new content. For example, if a user has a preference for "sci-fi movies," the system will recommend "Interstellar." An example of a prompt is, "Based on the user's viewing history, please generate three new content recommendations."

[0301] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0302] Step 1:

[0303] User: Launches the smartphone app and enters information such as name, age, hobbies, and viewing history when registering for the first time. This provides basic information about the user.

[0304] Step 2:

[0305] Terminal: Sends collected user information to the server. The entered user information is sent as a data packet to the server.

[0306] Step 3:

[0307] Server: Stores the received information in a database. The entered user information is converted into an appropriate format and stored in the database. For example, name, age, hobbies, and viewing history are stored as entries.

[0308] Step 4:

[0309] Server: Selects the most suitable video content from the database using the user's profile, preferences, and viewing history. For example, if a user's hobby is sci-fi movies, the server searches the database to select recommended content from a list of movies in the sci-fi genre.

[0310] Step 5:

[0311] Device: Presents a list of recommended content to the user. Presents a list of selected content in the user interface. This list is generated based on data retrieved from the server.

[0312] Step 6:

[0313] User: View the recommended content list and select "I like it" or "I don't like it." The user's selection becomes the next input.

[0314] Step 7:

[0315] Terminal: Sends the user's selection to the server. The user's selection data is sent to the server as a data packet.

[0316] Step 8:

[0317] Server: Stores user selections and uses them to improve the recommendation algorithm in the future. Stores the selection data in a database and uses it as training data for machine learning models.

[0318] Step 9:

[0319] Device: The device periodically sends the user's conversation logs and SNS posts to the server. The conversation logs and SNS posts recorded by the user become input data and are sent to the server.

[0320] Step 10:

[0321] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content. For example, spaCy or BERT is used to analyze and extract the user's interests, concerns, and emotional tone from the input data. The analysis results are used as input for the next process.

[0322] Step 11:

[0323] Server: Based on the analysis results, generate advice and viewing schedules tailored to the user. For example, generate advice such as "This is the next sci-fi movie you should watch." The generated advice becomes the output data.

[0324] Step 12:

[0325] Terminal: The generated advice and schedule are displayed to the user. The advice sent from the server is displayed in the user interface, allowing the user to create a viewing plan based on this.

[0326] Step 13:

[0327] Terminal: After viewing the content, a feedback survey is sent to the user, in which they are asked to enter their evaluation and impressions. Feedback is obtained as input data after viewing.

[0328] Step 14:

[0329] User: Enter feedback and tap the submit button. The feedback is sent from the device as the final input data.

[0330] Step 15:

[0331] Terminal: Sends feedback to the server. Feedback data is sent to the server as a data packet.

[0332] Step 16:

[0333] Server: Stores the collected feedback and uses it to generate the next recommendation or advice. Stores the feedback data in a database and uses it to improve the algorithm next time.

[0334] 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.

[0335] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and plans based on that.

[0336] Overall system configuration

[0337] This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions. The emotion engine analyzes the user's conversation log and posted content to identify the user's emotional state.

[0338] Collection and storage of user information

[0339] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, hobbies, relationship goals, etc.).

[0340] Terminal: Sends the entered information to the server.

[0341] Server: Stores the received user information in a database.

[0342] Matching partner recommendations

[0343] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[0344] Server: Sends the selected matching candidates to the device.

[0345] On your device: The profile of the recommended person will be displayed to you.

[0346] User: View the recommended people and select "Like" or "Dislike."

[0347] Terminal: Sends the user's selection to the server.

[0348] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[0349] Analysis of conversation logs and social media posts

[0350] Device: The user's conversation log and social media posts are periodically sent to the server.

[0351] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[0352] Server: Extract the other person's interest, concern, and emotional tone.

[0353] Use of emotion engine

[0354] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, by detecting positive and negative expressions, it identifies the user's current emotional state (joy, anxiety, excitement, etc.).

[0355] Example: If a user posts, "I'm feeling great today," the sentiment engine determines that the user is in a positive mood.

[0356] Providing advice and training

[0357] Server: Based on the analysis results, the server generates advice and training content tailored to the user. Taking into account the results of the emotion engine, the server provides specific advice, such as "When the other person talks about a movie, suggest going to see it together."

[0358] Server: Sends the generated advice to the device.

[0359] Device: Displays received advice and training content to the user.

[0360] Users: Review advice and training and apply it to their next conversation or date.

[0361] Date plan suggestions

[0362] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[0363] Terminal: Sends the entered conditions to the server.

[0364] Server: Generates optimal date plans based on the conditions, the user's preferences, and the results of the emotion engine. For example, if the user is in a positive mood, it may suggest outdoor activities for that day's date.

[0365] Server: Sends the proposed date plan to the device.

[0366] Device: Display date plans to the user.

[0367] Gathering and implementing feedback

[0368] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[0369] User: Enters date feedback and taps submit.

[0370] Device: Sends feedback to the server.

[0371] Server: Stores the collected feedback and incorporates it into the next proposal.

[0372] Continuous learning with emotion engine

[0373] Emotion engine: Improves analysis accuracy while taking feedback into consideration. For example, based on feedback such as "I was very satisfied with this date suggestion," the effectiveness of emotion-based suggestions can be further improved.

[0374] This will enable the system to increase users' chances of finding love and help them form efficient and effective partnerships.The use of an emotion engine will enable the system to provide more personalized advice and plans that are in line with the user's emotional state, which is expected to improve the user experience.

[0375] The processing flow will be explained below.

[0376] Processing steps of a system that combines emotion engines

[0377] Collection and storage of user information

[0378] Step 1:

[0379] User: Launch the app and enter user information (name, age, hobbies, relationship goals, etc.).

[0380] Step 2:

[0381] Terminal: Sends the entered information to the server.

[0382] Step 3:

[0383] Server: Stores the received user information in a database.

[0384] Matching partner recommendations

[0385] Step 1:

[0386] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[0387] Step 2:

[0388] Server: Sends the selected matching candidates to the device.

[0389] Step 3:

[0390] On your device: The profile of the recommended person will be displayed to you.

[0391] Step 4:

[0392] User: View the recommended people and select "Like" or "Dislike."

[0393] Step 5:

[0394] Terminal: Sends the user's selection to the server.

[0395] Step 6:

[0396] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[0397] Analysis of conversation logs and social media posts

[0398] Step 1:

[0399] Device: The user's conversation log and social media posts are periodically sent to the server.

[0400] Step 2:

[0401] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[0402] Step 3:

[0403] Server: Extract the other person's interest, concern, and emotional tone.

[0404] Use of emotion engine

[0405] Step 1:

[0406] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, it identifies the user's current emotional state (joy, anxiety, excitement, etc.) by detecting positive and negative expressions.

[0407] Step 2:

[0408] Server: The analysis results from the emotion engine are stored in a database and used for future advice and planning.

[0409] Providing advice and training

[0410] Step 1:

[0411] Server: Based on the analysis results, the server generates advice and training content tailored to the user. Taking into account the results of the emotion engine, the server provides specific advice, such as "When the other person talks about a movie, suggest going to see it together."

[0412] Step 2:

[0413] Server: Sends the generated advice to the device.

[0414] Step 3:

[0415] Device: Displays received advice and training content to the user.

[0416] Step 4:

[0417] Users: Review advice and training and apply it to their next conversation or date.

[0418] Date plan suggestions

[0419] Step 1:

[0420] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[0421] Step 2:

[0422] Terminal: Sends the entered conditions to the server.

[0423] Step 3:

[0424] Server: Generates the optimal date plan taking into account the conditions, the user's preferences, and the results of the emotion engine.

[0425] Step 4:

[0426] Server: Sends the proposed date plan to the device.

[0427] Step 5:

[0428] Device: Display date plans to the user.

[0429] Gathering and implementing feedback

[0430] Step 1:

[0431] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[0432] Step 2:

[0433] User: Enters date feedback and taps submit.

[0434] Step 3:

[0435] Device: Sends feedback to the server.

[0436] Step 4:

[0437] Server: Stores the collected feedback and incorporates it into the next proposal.

[0438] Continuous learning with emotion engine

[0439] Step 1:

[0440] Emotion engine: Improves analysis accuracy while taking feedback into consideration. For example, based on feedback such as "I was very satisfied with this date suggestion," the effectiveness of emotion-based suggestions can be further improved.

[0441] This will enable the system to increase users' chances of finding love and help them form efficient and effective partnerships.The use of an emotion engine will enable the system to provide more personalized advice and plans that are in line with the user's emotional state, which is expected to improve the user experience.

[0442] Example 2

[0443] 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."

[0444] Conventional matchmaking systems simply collect user information and recommend potential partners based on that information. They lack the ability to provide personalized advice or date plans that take into account data such as the user's emotional state and conversation logs. This makes it difficult to improve the user experience and effectively support users in increasing their chances of finding love. The present invention aims to solve this problem by providing personalized suggestions that take into account the user's information and emotional state.

[0445] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0446] In this invention, the server includes means for collecting and storing user information, means for recommending optimal matches based on the user information, means for analyzing the user's conversation records and posted content to generate appropriate advice, means for analyzing the user's emotional state to personalize the advice and date plans, and means for proposing date plans for the user. This makes it possible to not only recommend matches that meet the user's expectations, but also to provide specific and personalized advice and date plans that are tailored to each individual user.

[0447] "User information" refers to data such as profile information, hobby information, and relationship goals entered when using the system.

[0448] "Storage means" refers to a device or system that has the function of storing collected user information in a storage device such as a database.

[0449] "Means for recommending matching partners" refers to a system that selects the most suitable partner from a database based on the user's information and notifies the user of the results.

[0450] "Conversation records" refer to the content of conversations that users have on the system.

[0451] "Posted content" refers to the content of text, comments, updates, etc. posted by users on social media or the system.

[0452] "Means of analysis" refers to a system that uses natural language processing and sentiment analysis techniques to analyze user tendencies and emotions from conversation records and posted content.

[0453] "Means for generating appropriate advice" refers to a system that automatically generates advice and suggested actions that are useful to users based on the analysis results.

[0454] "Means for analyzing emotional state" refers to a system that determines a user's positive or negative emotional state from their conversation records and posted content.

[0455] "Means for proposing date plans" refers to a system that automatically designs and proposes optimal date itineraries based on user information and analysis results.

[0456] "Means for collecting feedback" refers to a system that allows users to input and record their evaluations and impressions of dates and proposals.

[0457] "Means of reflecting this in the next proposal" refers to a system that uses the collected feedback to improve and optimize future advice and proposals.

[0458] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. By combining this system with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and plans based on that analysis.

[0459] Configuration overview

[0460] This system consists of a server, terminals, and users.

[0461] Server: Collects, stores, analyzes, and provides recommendations on information. The server software uses a database (e.g., MySQL), a natural language processing (NLP) engine (e.g., Google® Natural Language API), and an emotion engine (e.g., IBM Watson® Emotional Analysis).

[0462] Terminal: Provides an interface with the user. Terminals are general information devices such as smartphones and PCs.

[0463] User: Uses the system to enter information and receive suggestions.

[0464] Collection and storage of user information

[0465] User: Launch the app from a smartphone or PC and enter necessary information such as name, age, hobbies, and romantic goals when registering for the first time. For example, enter data such as "Ichiro Tanaka, 30 years old, reading, looking for a marriage partner."

[0466] Terminal: Sends this input information to the server.

[0467] Server: Save the received user information in a database. For example, create a table called "User Information" in a MySQL database and store data in each field.

[0468] Matching partner recommendations

[0469] Server: Queries the database based on the user's profile and preferences to select the most suitable match. For example, if Ichiro Tanaka's hobby is "reading" and his goal is "finding a marriage partner," the server will select candidates with the same hobbies and goals.

[0470] Server: Sends a list of selected match candidates to the device. The list includes information such as the match's name, hobbies, and photo.

[0471] On your device: The profile of the recommended person will be displayed to you.

[0472] User: View the recommended person and select "Like" or "Dislike." For example, by pressing the "♡" button next to the person's profile, you can register them as "Like."

[0473] Terminal: Sends the user's selection to the server.

[0474] Server: The selection results are stored in a database and used to improve the recommendation algorithm in the future.

[0475] Analysis of conversation logs and social media posts

[0476] Device: The device periodically sends the user's conversation logs and social media posts to the server. For example, it collects conversation history within a chat app and public posts on social media.

[0477] Server: Analyzes collected logs and posts using a natural language processing (NLP) engine. Specifically, it uses the Google Natural Language API to analyze various texts.

[0478] Server: Extracts the other person's interests, concerns, and emotional tone. For example, it obtains information such as "Today's posts contain many words like 'fun' and 'happy'."

[0479] Use of emotion engine

[0480] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, if a user posts, "I'm feeling great today," the emotion engine will identify this as a positive emotion.

[0481] Example: Detecting positive sentiment from posts such as "I'm feeling great today."

[0482] Providing advice and training

[0483] Server: Based on the analysis results, the server generates advice and training content tailored to the user. It also takes into account the results of the emotion engine to create specific advice. For example, it provides advice such as, "When the other person talks about a movie, suggest going to see it together."

[0484] Server: Sends the generated advice to the device.

[0485] Device: Displays received advice and training content to the user.

[0486] Users: Review advice and training and apply it to their next conversation or date.

[0487] Date plan suggestions

[0488] User: Requests date plan suggestions and enters criteria such as location, budget, date, etc. For example, "Shibuya, under 5,000 yen, Saturday afternoon."

[0489] Terminal: Sends the entered conditions to the server.

[0490] Server: Based on the input conditions, the server generates the optimal date plan based on the user's preferences and the results of the emotion engine. For example, it suggests "lunch at a cafe in Shibuya and then watch a movie."

[0491] Server: Sends the proposed date plan to the device.

[0492] Device: Display date plans to the user.

[0493] Gathering and implementing feedback

[0494] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date. For example, the device displays questions such as, "How satisfied were you with the date?"

[0495] User: Enter your feedback and tap the submit button. For example, "Satisfaction rating: 8 / 10."

[0496] Device: Sends feedback to the server.

[0497] Server: Store the collected feedback in a database and use it to make the next recommendation. For example, store satisfaction in a "Dating Experience" table.

[0498] Continuous learning with emotion engine

[0499] Emotion engine: Improves analysis accuracy while taking into account feedback. For example, improves the effectiveness of emotion-based suggestions based on information such as "This date suggestion was very satisfying."

[0500] This allows the system to increase the user's chances of finding love. By using a generative AI model and specific prompts, it is possible to provide more advanced advice and plans. A specific example would be to input the user's past conversation logs into the generative AI model to perform a deep analysis of emotional fluctuations.

[0501] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0502] Step 1:

[0503] User: Launch the app from a smartphone or PC and enter the necessary information such as name, age, hobbies, and relationship goals when registering for the first time. For example, enter data such as "Suzuki Hanako, 28 years old, traveling, looking for a marriage partner."

[0504] Input: Profile information, hobbies, relationship goals, etc. that you enter into the app.

[0505] Output: Input information is sent to the device and converted into a format for storage on the server.

[0506] Step 2:

[0507] Device: The entered user information is sent to the server. This operation is performed by pressing the "Register" button in the app.

[0508] Input: User information (name, age, hobbies, love goals, etc.)

[0509] Output: User information is sent to the server.

[0510] Step 3:

[0511] Server: Save the received user information in a database. For example, create a table called "User Information" in a MySQL database and store data in each field.

[0512] Input: User information sent from the terminal

[0513] Output: User information is saved in the database.

[0514] Step 4:

[0515] Server: Queries the database based on the user's profile and preferences to select the most suitable match. For example, based on information such as "Suzuki Hanako loves traveling and is looking for a marriage partner," it selects candidates with the same hobbies and goals.

[0516] Input: User information (profile, hobbies, relationship goals)

[0517] Output: A list of potential matches is generated.

[0518] Step 5:

[0519] Server: Sends a list of selected match candidates to the device, including information such as the matchee's name, hobbies, and photo.

[0520] Input: A list of possible matches

[0521] Output: A list of potential matches is sent to the device.

[0522] Step 6:

[0523] On your device: The profile of the recommended person will be displayed to you. It will be displayed on the "Matching Candidates" screen in the app.

[0524] Input: A list of match candidates sent by the server

[0525] Output: Information that is visually displayed to the user (profile, photo, etc.).

[0526] Step 7:

[0527] User: View the recommended person and select "Like" or "Dislike." For example, by pressing the "♡" button next to the person's profile, you can register them as "Like."

[0528] Input: User's choice (like it or not)

[0529] Output: The selections are logged to the terminal.

[0530] Step 8:

[0531] Terminal: Sends the user's selection to the server.

[0532] Input: User selection

[0533] Output: The selection results are sent to the server.

[0534] Step 9:

[0535] Server: The selection results are stored in a database to help improve the recommendation algorithm in the future, for example in a "User Behavior History" table.

[0536] Input: User selection

[0537] Output: The selection results are saved in a database and added to the data used for analysis.

[0538] Step 10:

[0539] Device: The device periodically sends the user's conversation logs and social media posts to the server. For example, it collects conversation history within a chat app and public posts on social media.

[0540] Input: Conversation logs, social media posts

[0541] Output: Conversation logs and SNS posts are transferred to the server.

[0542] Step 11:

[0543] Server: Analyzes collected logs and posts using a natural language processing (NLP) engine. Specifically, analysis is performed using the Google Natural Language API.

[0544] Input: Conversation logs, social media posts

[0545] Output: Data about the user's emotional state and interests is generated.

[0546] Step 12:

[0547] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, if a user posts, "I'm feeling great today," the emotion engine will identify this as a positive emotion.

[0548] Input: Conversation logs, social media posts

[0549] Output: The user's emotional state (positive, negative, etc.). Example: A post saying "I'm feeling great today" is judged to have a positive emotion.

[0550] Step 13:

[0551] Server: Based on the analysis results, the server generates advice and training content tailored to the user. It also takes into account the results of the emotion engine to provide specific advice. For example, it creates advice such as "When the other person talks about a movie, suggest going to see it together."

[0552] Input: Analysis results, emotion engine results

[0553] Output: Generate specific advice and training content

[0554] Step 14:

[0555] Server: Sends the generated advice to the device.

[0556] Input: Generated advice and training content

[0557] Output: Advice and training content are transferred to the device.

[0558] Step 15:

[0559] On your device: Displaying received advice and training content to you, for example in the "Advice" section within the app.

[0560] Input: Advice and training content sent

[0561] Output: Visually displayed advice and training content

[0562] Step 16:

[0563] Users: Review advice and training and apply it to their next conversation or date.

[0564] Input: Received advice, training content

[0565] Output: Advice implementation reflected in actual behavior

[0566] Step 17:

[0567] User: Requests date plan suggestions and enters criteria such as location, budget, date, etc. For example, "Shibuya, under 5,000 yen, Saturday afternoon."

[0568] Input: Date plan conditions (location, budget, date, etc.)

[0569] Output: The condition is sent to the terminal and forwarded to the server.

[0570] Step 18:

[0571] Terminal: Sends the entered conditions to the server.

[0572] Input: Date plan conditions

[0573] Output: The condition is sent to the server.

[0574] Step 19:

[0575] Server: Based on the input conditions, the server generates the optimal date plan based on the user's preferences and the results of the emotion engine. For example, it suggests "lunch at a cafe in Shibuya and then watch a movie."

[0576] Input: Date plan conditions, preference information, emotion engine results

[0577] Output: Proposed date plan

[0578] Step 20:

[0579] Server: Sends the proposed date plan to the device.

[0580] Enter: Date plan

[0581] Output: The date plan is sent to the device.

[0582] Step 21:

[0583] Device: Display date plans to the user.

[0584] Input: Date plan sent from the server

[0585] Output: A visual representation of the date plan

[0586] Step 22:

[0587] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date. For example, the device displays questions such as, "How satisfied were you with the date?"

[0588] Input: Feedback Question

[0589] Output: Feedback survey displayed to the user

[0590] Step 23:

[0591] User: Enter your feedback and tap the submit button. For example, "Satisfaction rating: 8 / 10."

[0592] Input: Date feedback (impressions, ratings, etc.)

[0593] Output: Feedback information is sent to the terminal.

[0594] Step 24:

[0595] Device: Sends feedback to the server.

[0596] Input: Feedback information entered by the user

[0597] Output: The feedback information is sent to the server.

[0598] Step 25:

[0599] Server: Stores the collected feedback in a database and uses it to improve future recommendations. For example, satisfaction is stored in a "Dating Experience" table.

[0600] Input: Feedback information

[0601] Output: Saved feedback information, data to be reflected in the next proposal

[0602] Step 26:

[0603] Emotion engine: Improves analysis accuracy while taking into account feedback. For example, improves the effectiveness of emotion-based suggestions based on information such as "This date suggestion was very satisfying."

[0604] Input: Feedback information

[0605] Output: Improved analysis accuracy and improved proposal accuracy based on that.

[0606] (Application example 2)

[0607] 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."

[0608] Conventional online shopping sites lack personalized product recommendations based on users' emotions and preferences, making it difficult for users to find the products that are best suited to them. Furthermore, they lack a system for effectively incorporating user feedback, making it difficult to make continuous improvements.

[0609] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing user information, means for recommending optimal products based on the user information, means for analyzing the user's conversation log and posted content and generating appropriate advice, and means for suggesting product information and sale information to the user. This enables personalized product recommendations based on the user's emotions and preferences, improving the user's purchasing experience. In addition, analyzing user feedback and reflecting it in the next recommendation content enables continuous system improvement.

[0610] "User information" refers to information including the profile information, purchase history, and browsing history of the user of the online shopping site.

[0611] "Means of collecting and storing" refers to the means of sending the information provided by the user to the server and storing it in a database.

[0612] "Means for recommending optimal products" refers to means for selecting and recommending the product that best suits a user based on the user's information.

[0613] "Means for analyzing conversation logs and posted content" refers to means for analyzing the conversations and social media posts of users and understanding their emotions and interests from the content.

[0614] The "means for generating appropriate advice" is a means for generating advice for presenting product recommendations and sale information suited to a user based on analyzed user information.

[0615] The "means for suggesting product information and sale information" is a means for displaying appropriate product information and sale information to the user based on the generated advice.

[0616] The "means for collecting and storing feedback" refers to a means for collecting impressions and ratings provided by users after purchase and storing them on a server.

[0617] "Means for analyzing feedback and reflecting it in the next recommendation" refers to means for analyzing collected feedback information and using it to improve the recommendation content from the next time onwards.

[0618] "Profile information" refers to information that includes personal information such as a user's name, age, gender, and hobbies.

[0619] "Purchase history" is information that includes a record of products that a user has purchased in the past.

[0620] "Browsing history" is information that includes a record of products and pages that a user has viewed in the past.

[0621] "Means for providing appropriate product recommendations and training based on analysis" refers to means for providing users with appropriate product recommendations, usage instructions, and related training content based on the analysis results.

[0622] Overall system configuration

[0623] This invention is a system that collects and analyzes user information, recommends optimal products, and provides appropriate advice and product information. The system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and product information based on that.

[0624] Collection and storage of user information

[0625] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, purchase history, browsing history, etc.).

[0626] Terminal: Sends the entered information to the server.

[0627] Server: Stores the received user information in a database.

[0628] Product Recommendations

[0629] Server: Uses a recommendation algorithm to select the most suitable products from a database based on the user's profile and purchasing history.

[0630] Server: Sends the selected product to the device.

[0631] Device: Display recommended product information to the user.

[0632] Analysis of conversation logs and social media posts

[0633] Device: The user's conversation log and social media posts are periodically sent to the server.

[0634] Server: A natural language processing (NLP) engine (e.g., Google Cloud Natural Language API) and a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) are used to analyze the collected logs and posts.

[0635] Server: Extracts emotional tone and stores it as data for recommending optimal products.

[0636] Providing advice and product information

[0637] Server: Based on the analysis results, the server generates advice and product information tailored to the user. For example, it generates specific advice such as "If a user mentions in a recent post that they like flowers, provide them with information about sale items for flower arrangements."

[0638] Server: Sends the generated advice to the device.

[0639] Terminal: Displays received advice and product information to the user.

[0640] Gathering and implementing feedback

[0641] Device: After purchasing a product, a feedback survey is sent to the user, asking them to enter their impressions and ratings.

[0642] User: Enters feedback about a purchased item and taps the submit button.

[0643] Device: Sends feedback to the server.

[0644] Server: Stores the collected feedback and uses it to improve future recommendations.

[0645] Continuous learning with emotion engine

[0646] Emotion engine: Improves analysis accuracy while taking feedback into account. For example, feedback such as "very satisfied" can be used to improve the effectiveness of suggestions based on further emotion recognition.

[0647] Server: Train a new product recommendation model using the sentiment data.

[0648] Specific examples

[0649] Example prompts to input to the generative AI model

[0650] Prompt: "A user recently posted on social media, 'I'm in a great mood today, so I bought some flowers!' What product recommendations would you give them?"

[0651] This system enables personalized product recommendations based on the user's emotions and preferences, improving the user's purchasing experience. Furthermore, by analyzing user feedback and reflecting it in the next recommendation, the system can be continuously improved.

[0652] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0653] Step 1:

[0654] When a user launches the app from a device such as a smartphone or PC, they enter the necessary information for initial registration (name, age, purchase history, browsing history, etc.), and the device sends this information to the server. The input data includes name, age, purchase history, and browsing history, and is saved in a database.

[0655] Step 2:

[0656] The server stores the received user information in a database and then stores the user information in an integrated database at the specified timing. This process accumulates the user's basic information and behavioral history data.

[0657] Step 3:

[0658] The server selects products from a database using an optimal recommendation algorithm based on the user's profile and purchase history, generates a list of recommended products as output, and sends it to the terminal.

[0659] Step 4:

[0660] The terminal displays the received recommended product list to the user, who then confirms the recommended products. The terminal records the user's choice (whether to purchase or not) and sends it to the server.

[0661] Step 5:

[0662] The device periodically sends the user's conversation log and social media posts to the server. These conversation logs and posts serve as input data for analysis.

[0663] Step 6:

[0664] The server uses a natural language processing (NLP) engine and a sentiment analysis engine to analyze the collected conversation logs and posted content. For example, it uses the Google Cloud Natural Language API to extract emotional tones from text and stores the analysis results in a database.

[0665] Step 7:

[0666] The server generates advice and product information tailored to the user based on the analysis results. For example, it generates specific advice such as "If a user mentions in a recent post that they like flowers, provide them with information about sale items for flower arrangements."

[0667] Step 8:

[0668] The server sends the generated advice and product information to the terminal, which then displays it to the user, who then checks the displayed advice and product information.

[0669] Step 9:

[0670] After a product is purchased, the terminal sends a feedback survey to the user, prompting them to enter their impressions and evaluations. The input data includes the user's satisfaction with the purchased product and their impressions of use.

[0671] Step 10:

[0672] The user inputs the feedback and taps the send button, and the terminal transmits the user's feedback data to the server.

[0673] Step 11:

[0674] The server stores the collected feedback in a database and uses it to improve the recommendation algorithm for the next step. Based on the analysis of the feedback, a new product recommendation model is trained.

[0675] Step 12:

[0676] The emotion engine uses feedback to improve analysis accuracy. For example, feedback such as "very satisfied" can be used to improve the effectiveness of suggestions based on further emotion recognition.

[0677] In this way, the system can provide personalized product recommendations based on users' emotions and preferences, and achieve continuous improvement by incorporating effective feedback.

[0678] 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.

[0679] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0680] 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.

[0681] [Second embodiment]

[0682] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0683] 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.

[0684] 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).

[0685] 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.

[0686] 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.

[0687] 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).

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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.

[0693] 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."

[0694] The present invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans.

[0695] Overall system configuration

[0696] This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and provides suggestions for information, while the terminal provides an interface for users. Users use the system to input information and receive suggestions.

[0697] Collection and storage of user information

[0698] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, hobbies, relationship goals, etc.).

[0699] Terminal: Sends the entered information to the server.

[0700] Server: Stores the received information in a database.

[0701] Matching partner recommendations

[0702] Server: Uses the user's profile and preferences to select the most suitable match from the database.

[0703] Server: Sends the selected matching candidates to the device.

[0704] Device: The profile of the recommended person is displayed to the user for confirmation.

[0705] User: View the recommended people and select "Like" or "Dislike."

[0706] Terminal: Sends the selection results to the server.

[0707] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[0708] Analysis of conversation logs and social media posts

[0709] Device: The user's conversation log and social media posts are periodically sent to the server.

[0710] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content, extracting the other person's interests, concerns, and emotional tone.

[0711] Example: For example, if a user talks a lot about movies and music, the system can analyze that information and determine that the other person is likely interested in movies and music.

[0712] Providing advice and training

[0713] Server: Based on the analysis results, the server generates advice and training tailored to the user. For example, it provides advice such as "Talk about the other person's favorite movie in your next conversation."

[0714] Server: Sends the generated advice to the device.

[0715] Terminal: Display the received advice to the user.

[0716] User: Check out the advice and apply it to your next conversation or date.

[0717] Date plan suggestions

[0718] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[0719] Terminal: Sends the entered conditions to the server.

[0720] Server: Generates optimal date plans based on the conditions and the user's preferences. For example, it suggests restaurants and events.

[0721] Server: Sends the proposed date plan to the device.

[0722] Device: Display date plans to the user.

[0723] Gathering and implementing feedback

[0724] Device: After the date, users are sent a feedback survey and asked to enter their impressions and evaluation of the date.

[0725] User: Enter your feedback and tap the submit button.

[0726] Device: Sends feedback to the server.

[0727] Server: Stores the collected feedback and incorporates it into the next proposal.

[0728] This enables the system to increase users' chances of success in love and help them form efficient and effective partnerships.

[0729] The processing flow will be explained below.

[0730] Collection and storage of user information

[0731] Step 1:

[0732] User: Launch the app and enter user information (name, age, hobbies, relationship goals, etc.).

[0733] Step 2:

[0734] Terminal: Sends the entered information to the server.

[0735] Step 3:

[0736] Server: Stores the received user information in a database.

[0737] Matching partner recommendations

[0738] Step 1:

[0739] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[0740] Step 2:

[0741] Server: Sends the selected matching candidates to the device.

[0742] Step 3:

[0743] On your device: The profile of the recommended person will be displayed to you.

[0744] Step 4:

[0745] User: View the recommended people and select "Like" or "Dislike."

[0746] Step 5:

[0747] Terminal: Sends the user's selection to the server.

[0748] Step 6:

[0749] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[0750] Analysis of conversation logs and social media posts

[0751] Step 1:

[0752] Device: The user's conversation log and SNS postings are periodically sent to the server.

[0753] Step 2:

[0754] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[0755] Step 3:

[0756] Server: Extract the other person's interest, concern, and emotional tone.

[0757] Providing advice and training

[0758] Step 1:

[0759] Server: Based on the analysis results, it generates advice and training content tailored to the user.

[0760] Step 2:

[0761] Server: Sends the generated advice to the device.

[0762] Step 3:

[0763] Device: Displays received advice and training content to the user.

[0764] Step 4:

[0765] Users: Review advice and training and apply it to their next conversation or date.

[0766] Date plan suggestions

[0767] Step 1:

[0768] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[0769] Step 2:

[0770] Terminal: Sends the entered conditions to the server.

[0771] Step 3:

[0772] Server: Generates the optimal date plan taking into account the conditions and the user's preferences.

[0773] Step 4:

[0774] Server: Sends the proposed date plan to the device.

[0775] Step 5:

[0776] Device: Display date plans to the user.

[0777] Gathering and implementing feedback

[0778] Step 1:

[0779] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[0780] Step 2:

[0781] User: Enters date feedback and taps submit.

[0782] Step 3:

[0783] Device: Sends feedback to the server.

[0784] Step 4:

[0785] Server: Stores the collected feedback and incorporates it into the next proposal.

[0786] Example 1

[0787] 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."

[0788] In conventional matchmaking systems, the collection and storage of user information, the recommendation of potential matches, and the generation of advice are often carried out separately, resulting in a lack of integration as a whole system. Furthermore, insufficient analysis of users' conversation logs and social media posts can lead to issues such as inappropriate advice not being provided and date plan suggestions not matching the user's preferences or requirements. Furthermore, there are also issues with inefficient collection and reflection of feedback, which means that improvements are not incorporated into future proposals.

[0789] 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.

[0790] In this invention, the server includes means for collecting and storing user information, means for recommending optimal matches based on the user information, means for analyzing the user's conversation log and postings and generating appropriate advice using a natural language processing engine, and means for proposing date plans that meet the user's requirements. This enables integrated management of user information, providing highly accurate matching and advice, and proposing date plans that meet the user's preferences and requirements. Furthermore, by collecting feedback and analyzing it using a machine learning algorithm, it is possible to continuously improve the recommendation algorithm and reflect this in future recommendations.

[0791] A "user" is an individual who uses the system and provides information such as personal information, hobbies, preferences, and romantic intentions.

[0792] "Means of collecting and storing information" refers to various functions for storing information provided by users, such as personal information, hobbies, preferences, and romantic intentions, in a database.

[0793] "Means for recommending matching partners" refers to algorithms and functions that select the most suitable partner based on the user's information and provide that information to the user.

[0794] "Means for analyzing conversation logs and posted content" refers to the function of analyzing users' conversation logs and SNS posts using a natural language processing engine, etc., and generating appropriate advice for users based on the results obtained.

[0795] A "natural language processing engine" is a software engine that analyzes text data and extracts meaning, emotion, topics, etc.

[0796] "Means for generating advice" refers to a function that generates and provides appropriate advice on actions and conversations to users based on the analysis results.

[0797] "Means for proposing date plans" refers to a function that generates an appropriate date plan based on the conditions provided by the user (location, budget, date and time, etc.) and proposes it to the user.

[0798] "Means for collecting and storing feedback" refers to a function for storing feedback provided by users, such as impressions and ratings after a date, in a database.

[0799] A "machine learning algorithm" is an algorithm that analyzes feedback data and learns to improve the accuracy of future suggestions and recommendation algorithms.

[0800] "Profile Information" refers to a user's basic personal information (such as name, age, etc.).

[0801] "Interest information" refers to information about a user's interests, hobbies, and preferences.

[0802] "Love goals" refers to the objectives that users want to achieve in love (e.g., serious relationship, finding friends, etc.).

[0803] "Generation policy" refers to guidelines and standards for providing optimal advice and training to users based on the analysis results.

[0804] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions.

[0805] Collection and storage of user information

[0806] Users start the application from a device such as a smartphone or PC and enter initial registration information such as their name, age, hobbies, and romantic interests. The device then sends the collected information to the server, which then stores the received information in a database. Data is sent in JSON or XML format, and is securely transmitted via HTTPS requests.

[0807] Matching partner recommendations

[0808] The server uses an algorithm to select the most suitable match based on the user's profile and preferences. The algorithm uses KNN (nearest neighbor search) and collaborative filtering to select candidates with many similarities. The selected match candidates are sent from the server to the device, which displays the information to the user. The user looks at the recommended partners and selects either "like" or "dislike," and sends the result to the server via the device. The server stores the selection results in a database and uses them to improve the recommendation algorithm in the future.

[0809] Analysis of conversation logs and social media posts

[0810] The device periodically sends the user's conversation log and social media posts to a server. The server then analyzes the collected data using a natural language processing (NLP) engine. Libraries such as spaCy and NLTK are used for this analysis. The analysis extracts the other person's interests, concerns, and emotional tone. Specifically, if the user talks a lot about movies and music, the system determines that the other person is likely to be interested in these subjects.

[0811] Providing advice and training

[0812] The server generates optimal advice and training for the user based on the results of NLP analysis. A generative AI model (e.g., GPT-3) is used for this generation. For example, advice such as "Talk about the other person's favorite movie in your next conversation" may be provided. The generated advice is sent from the server to the device, which displays it to the user. The user can confirm the advice and put it into practice in their next conversation or date.

[0813] Date plan suggestions

[0814] The user requests a date plan proposal and enters conditions (location, budget, date and time, etc.). These conditions are sent from the device to the server. The server generates the optimal date plan taking into account the conditions and the user's preferences. For example, it may suggest restaurants or events. To generate this plan, it references various APIs and databases to select a plan that meets the user's conditions. The generated date plan is sent from the server to the device, which then displays it to the user.

[0815] Gathering and implementing feedback

[0816] After the date, the device sends the user a feedback survey. The user enters their impressions and evaluation of the date and taps the send button. The collected feedback is sent from the device to the server, which stores it in a database. The server then analyzes this feedback data using a machine learning algorithm and reflects it in future recommendations. This allows for continuous improvement of the recommendation algorithm.

[0817] Prompt Sentence Examples

[0818] Examples of prompts with examples include:

[0819] "User A is a 35-year-old man whose hobbies are watching movies and hiking. After he enters his profile, please explain how the system recommends his best matches. Also, please explain the specific process of providing advice and proposing date plans."

[0820] This prompt is fed into a generative AI model, which then provides a concrete explanation of the overall flow of the system.

[0821] The above is a form for implementing the present invention, and this system can increase the user's success rate in romance and support the formation of efficient and effective partnerships.

[0822] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0823] Step 1:

[0824] Input: The user launches the application from their smartphone or computer and enters their initial registration information (name, age, hobbies, and romantic intent).

[0825] Action: The user fills in the application's registration form and presses the submit button.

[0826] Terminal: The input information is packaged in JSON or XML format and sent to the server via an HTTPS request.

[0827] Output: Personal information sent to the server.

[0828] Step 2:

[0829] Input: User information sent from the device in step 1.

[0830] How it works: The server parses the incoming data and stores the information in a database using SQL queries, typically MySQL or PostgreSQL.

[0831] Server: Inserts and stores the received information into a database.

[0832] Output: User information stored in the database.

[0833] Step 3:

[0834] Input: User profile and interest information stored in a database.

[0835] How it works: The server uses KNN (Knowledge Neighborhood Search) and collaborative filtering algorithms to select the best match.

[0836] Server: Packages the selection results in JSON format and sends them to the terminal.

[0837] Output: Match candidate information sent to the device.

[0838] Step 4:

[0839] Input: Match candidate information sent from the server.

[0840] What it does: The device displays profiles of potential matches to the user, using a list view or card layout.

[0841] Terminal: Displays the selection results to the user.

[0842] Output: Match candidate information displayed to the user.

[0843] Step 5:

[0844] Input: The match candidate information displayed to the user.

[0845] How it works: The user selects "like" or "dislike" and the result is sent from the device to the server.

[0846] User: Look at the recommended partners and make a selection.

[0847] Terminal: The selection results are packaged in JSON format and sent to the server.

[0848] Output: The selection results sent to the server.

[0849] Step 6:

[0850] Input: The selection sent from the terminal in step 5.

[0851] How it works: The server analyzes the selection results, stores them in a database, and uses them to improve the recommendation algorithm in the future.

[0852] Server: Records preference data and uses it as training data for recommendation algorithms.

[0853] Output: Selection results stored in a database.

[0854] Step 7:

[0855] Input: User conversation logs and social media posts.

[0856] How it works: The device periodically sends conversation logs and social media posts in JSON format to the server.

[0857] Terminal: Collects log data, packages it, and sends it to the server.

[0858] Output: Conversation logs and SNS posting data sent to the server.

[0859] Step 8:

[0860] Input: Conversation logs and social media post data sent in step 7.

[0861] How it works: The server performs the analysis using a natural language processing (NLP) engine (e.g. spaCy or NLTK).

[0862] Server: Performs sentiment analysis and key phrase extraction using collected data.

[0863] Output: Areas of interest and emotional tone derived from the analysis.

[0864] Step 9:

[0865] Input: NLP analysis results.

[0866] How it works: The server generates appropriate advice and training content based on the analysis results. It uses a generative AI model (e.g., GPT-3).

[0867] Server: Utilizes generative AI models to generate personalized advice.

[0868] Output: The generated advice and training content.

[0869] Step 10:

[0870] Input: Generated advice and training content.

[0871] Operation: The server sends advice to the device.

[0872] Server: Packages advice in JSON format and sends it to the device.

[0873] Output: Advice sent to the terminal.

[0874] Step 11:

[0875] Input: Advice sent by the server.

[0876] What it does: The device displays advice to the user, using a pop-up message or notification bar.

[0877] Terminal: Presents advice to the user.

[0878] Output: The advice displayed to the user.

[0879] Step 12:

[0880] Input: The date plan conditions requested by the user (location, budget, date and time).

[0881] Operation: The device sends the conditions in JSON format to the server.

[0882] User: Enter the conditions for the date plan.

[0883] Terminal: Packages and sends the conditions.

[0884] Output: Dateplan conditions sent to the server.

[0885] Step 13:

[0886] Input: Date plan conditions and user preferences.

[0887] How it works: The server generates the optimal date plan based on the conditions and preferences. It does so by referencing various APIs and databases.

[0888] Server: Searches a database of restaurants and events and selects plans that match your criteria.

[0889] Output: The generated date plan.

[0890] Step 14:

[0891] Input: Date plan sent from the server.

[0892] How it works: The server sends the plan to the device, packaging it in JSON format.

[0893] Server: Sends the generated date plan to the device.

[0894] Output: The date plan sent to the device.

[0895] Step 15:

[0896] Input: Date plan information sent from the server.

[0897] Action: The device displays the date plan to the user. Use the details page.

[0898] Device: Display date plans.

[0899] Output: The date plan displayed to the user.

[0900] Step 16:

[0901] Input: Post-date feedback survey.

[0902] Operation: The device sends a survey to the user via push notification. The user fills out the survey and presses the send button.

[0903] Terminal: Collects surveys and sends them to the server.

[0904] Output: Feedback data sent to the server.

[0905] Step 17:

[0906] Input: Feedback data collected in step 16.

[0907] How it works: The server stores the feedback data in a database and analyzes it using machine learning algorithms.

[0908] Server: Updates the recommendation algorithm based on the feedback data and reflects it in the next proposal.

[0909] Output: Analysis results stored in a database and updated recommendation algorithms.

[0910] The above is the specific processing flow of the system program.

[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 smart glasses 214 will be referred to as a "terminal."

[0913] Conventional content distribution services have recommended limited content based on users' past viewing history and preferences. This has made it difficult for users to efficiently discover diverse new content that interests them. Furthermore, the provision of appropriate viewing schedules and advice has been insufficient, preventing users from maximizing their viewing experience. The present invention aims to solve these problems and improve user satisfaction by providing individually customized content recommendations and viewing advice to users.

[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 means for collecting and storing user information, means for recommending optimal content, means for analyzing user conversation logs and posted content to generate appropriate advice, and means for proposing viewing schedules, thereby enabling users to efficiently discover a variety of new content that interests them and receive appropriate viewing schedules and advice.

[0916] "User information" is a collective term for profile information, preference information, and viewing history collected when using the system.

[0917] "Storage means" refers to a function for storing collected user information in a storage device such as a database.

[0918] "Recommendation means" is a function that selects and suggests the most appropriate content based on saved user information.

[0919] "Conversation log" refers to the text messages and communication history entered by the user.

[0920] "Posted content" refers to comments and feedback posted by users on social media or review sites.

[0921] "Means of analysis" refers to a function that analyzes conversation logs and posted content using natural language processing technology, etc., to extract users' hobbies and interests.

[0922] The "means for generating advice" is a function that automatically generates appropriate content and viewing advice for users based on the analysis results.

[0923] The "means for proposing a viewing schedule" is a function that proposes an optimal content viewing schedule based on the user's lifestyle and past viewing patterns.

[0924] "Feedback" refers to opinions such as ratings and impressions of content viewed by users.

[0925] "Means of reflection" is a function that analyzes collected feedback and uses it to recommend content or generate advice next time.

[0926] The present invention is embodied as a personalized video recommendation system for use in a content distribution service. The system is mainly composed of a server, a terminal, and a user, and is realized by the following means and processing steps.

[0927] Overall system configuration

[0928] This system consists of a client terminal (e.g., a smartphone) and a server. The server collects, stores, analyzes, and recommends information, while the terminal provides an interface with the user. The user also uses the system to input information and receive suggestions.

[0929] Collection and storage of user information

[0930] User: Launches the smartphone app and enters information such as name, age, hobbies, and viewing history when registering for the first time.

[0931] Terminal: Sends collected user information to the server.

[0932] Server: Stores the received information in a database, which is used for future data analysis and to improve recommendation algorithms.

[0933] Content Recommendations

[0934] Server: Selects the most suitable video content from the database based on the user's profile, preferences, and viewing history. For example, if a user likes sci-fi movies, it will recommend new and highly rated movies in the sci-fi genre.

[0935] Device: A list of recommended content is displayed to the user, who can select "Like" or "Dislike."

[0936] Server: Stores the user's selections and uses them to improve the recommendation algorithm in the future.

[0937] Analysis of conversation logs and postings

[0938] Device: The user's conversation log and social media posts are periodically sent to the server.

[0939] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content. For example, generative AI models such as spaCy and BERT are used. Through analysis, the user's interests, concerns, and emotional tone are extracted. For example, if a user frequently comments about a particular actor on social media, movies starring that actor can be recommended.

[0940] Advice generation and viewing schedule suggestions

[0941] Server: Based on the analysis results, the server generates advice and viewing schedules tailored to the user. For example, it provides advice such as "This is the next sci-fi movie you should watch."

[0942] Device: The generated advice and schedule are displayed to the user, who can use them to plan their viewing plans.

[0943] Gathering and implementing feedback

[0944] Device: After viewing the content, a feedback survey is sent to the user, in which they are asked to enter their rating and impressions.

[0945] User: Enter feedback and tap submit.

[0946] Device: Sends feedback to the server.

[0947] Server: Stores the collected feedback and uses it to generate the next recommendation or advice.

[0948] This allows the system to improve the user's viewing experience and effectively support the discovery of diverse new content. For example, if a user has a preference for "sci-fi movies," the system will recommend "Interstellar." An example of a prompt is, "Based on the user's viewing history, please generate three new content recommendations."

[0949] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0950] Step 1:

[0951] User: Launches the smartphone app and enters information such as name, age, hobbies, and viewing history when registering for the first time. This provides basic information about the user.

[0952] Step 2:

[0953] Terminal: Sends collected user information to the server. The entered user information is sent as a data packet to the server.

[0954] Step 3:

[0955] Server: Stores the received information in a database. The entered user information is converted into an appropriate format and stored in the database. For example, name, age, hobbies, and viewing history are stored as entries.

[0956] Step 4:

[0957] Server: Selects the most suitable video content from the database using the user's profile, preferences, and viewing history. For example, if a user's hobby is sci-fi movies, the server searches the database to select recommended content from a list of movies in the sci-fi genre.

[0958] Step 5:

[0959] Device: Presents a list of recommended content to the user. Presents a list of selected content in the user interface. This list is generated based on data retrieved from the server.

[0960] Step 6:

[0961] User: View the recommended content list and select "I like it" or "I don't like it." The user's selection becomes the next input.

[0962] Step 7:

[0963] Terminal: Sends the user's selection to the server. The user's selection data is sent to the server as a data packet.

[0964] Step 8:

[0965] Server: Stores user selections and uses them to improve the recommendation algorithm in the future. Stores the selection data in a database and uses it as training data for machine learning models.

[0966] Step 9:

[0967] Device: The device periodically sends the user's conversation logs and SNS posts to the server. The conversation logs and SNS posts recorded by the user become input data and are sent to the server.

[0968] Step 10:

[0969] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content. For example, spaCy or BERT is used to analyze and extract the user's interests, concerns, and emotional tone from the input data. The analysis results are used as input for the next process.

[0970] Step 11:

[0971] Server: Based on the analysis results, generate advice and viewing schedules tailored to the user. For example, generate advice such as "This is the next sci-fi movie you should watch." The generated advice becomes the output data.

[0972] Step 12:

[0973] Terminal: The generated advice and schedule are displayed to the user. The advice sent from the server is displayed in the user interface, allowing the user to create a viewing plan based on this.

[0974] Step 13:

[0975] Terminal: After viewing the content, a feedback survey is sent to the user, in which they are asked to enter their evaluation and impressions. Feedback is obtained as input data after viewing.

[0976] Step 14:

[0977] User: Enter feedback and tap the submit button. The feedback is sent from the device as the final input data.

[0978] Step 15:

[0979] Terminal: Sends feedback to the server. Feedback data is sent to the server as a data packet.

[0980] Step 16:

[0981] Server: Stores the collected feedback and uses it to generate the next recommendation or advice. Stores the feedback data in a database and uses it to improve the algorithm next time.

[0982] 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.

[0983] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and plans based on that.

[0984] Overall system configuration

[0985] This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions. The emotion engine analyzes the user's conversation log and posted content to identify the user's emotional state.

[0986] Collection and storage of user information

[0987] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, hobbies, relationship goals, etc.).

[0988] Terminal: Sends the entered information to the server.

[0989] Server: Stores the received user information in a database.

[0990] Matching partner recommendations

[0991] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[0992] Server: Sends the selected matching candidates to the device.

[0993] On your device: The profile of the recommended person will be displayed to you.

[0994] User: View the recommended people and select "Like" or "Dislike."

[0995] Terminal: Sends the user's selection to the server.

[0996] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[0997] Analysis of conversation logs and social media posts

[0998] Device: The user's conversation log and social media posts are periodically sent to the server.

[0999] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[1000] Server: Extract the other person's interest, concern, and emotional tone.

[1001] Use of emotion engine

[1002] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, by detecting positive and negative expressions, it identifies the user's current emotional state (joy, anxiety, excitement, etc.).

[1003] Example: If a user posts, "I'm feeling great today," the sentiment engine determines that the user is in a positive mood.

[1004] Providing advice and training

[1005] Server: Based on the analysis results, the server generates advice and training content tailored to the user. Taking into account the results of the emotion engine, the server provides specific advice, such as "When the other person talks about a movie, suggest going to see it together."

[1006] Server: Sends the generated advice to the device.

[1007] Device: Displays received advice and training content to the user.

[1008] Users: Review advice and training and apply it to their next conversation or date.

[1009] Date plan suggestions

[1010] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[1011] Terminal: Sends the entered conditions to the server.

[1012] Server: Generates optimal date plans based on the conditions, the user's preferences, and the results of the emotion engine. For example, if the user is in a positive mood, it may suggest outdoor activities for that day's date.

[1013] Server: Sends the proposed date plan to the device.

[1014] Device: Display date plans to the user.

[1015] Gathering and implementing feedback

[1016] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[1017] User: Enters date feedback and taps submit.

[1018] Device: Sends feedback to the server.

[1019] Server: Stores the collected feedback and incorporates it into the next proposal.

[1020] Continuous learning with emotion engine

[1021] Emotion engine: Improves analysis accuracy while taking feedback into consideration. For example, based on feedback such as "I was very satisfied with this date suggestion," the effectiveness of emotion-based suggestions can be further improved.

[1022] This will enable the system to increase users' chances of finding love and help them form efficient and effective partnerships.The use of an emotion engine will enable the system to provide more personalized advice and plans that are in line with the user's emotional state, which is expected to improve the user experience.

[1023] The processing flow will be explained below.

[1024] Processing steps of a system that combines emotion engines

[1025] Collection and storage of user information

[1026] Step 1:

[1027] User: Launch the app and enter user information (name, age, hobbies, relationship goals, etc.).

[1028] Step 2:

[1029] Terminal: Sends the entered information to the server.

[1030] Step 3:

[1031] Server: Stores the received user information in a database.

[1032] Matching partner recommendations

[1033] Step 1:

[1034] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[1035] Step 2:

[1036] Server: Sends the selected matching candidates to the device.

[1037] Step 3:

[1038] On your device: The profile of the recommended person will be displayed to you.

[1039] Step 4:

[1040] User: View the recommended people and select "Like" or "Dislike."

[1041] Step 5:

[1042] Terminal: Sends the user's selection to the server.

[1043] Step 6:

[1044] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[1045] Analysis of conversation logs and social media posts

[1046] Step 1:

[1047] Device: The user's conversation log and social media posts are periodically sent to the server.

[1048] Step 2:

[1049] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[1050] Step 3:

[1051] Server: Extract the other person's interest, concern, and emotional tone.

[1052] Use of emotion engine

[1053] Step 1:

[1054] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, it identifies the user's current emotional state (joy, anxiety, excitement, etc.) by detecting positive and negative expressions.

[1055] Step 2:

[1056] Server: The analysis results from the emotion engine are stored in a database and used for future advice and planning.

[1057] Providing advice and training

[1058] Step 1:

[1059] Server: Based on the analysis results, the server generates advice and training content tailored to the user. Taking into account the results of the emotion engine, the server provides specific advice, such as "When the other person talks about a movie, suggest going to see it together."

[1060] Step 2:

[1061] Server: Sends the generated advice to the device.

[1062] Step 3:

[1063] Device: Displays received advice and training content to the user.

[1064] Step 4:

[1065] Users: Review advice and training and apply it to their next conversation or date.

[1066] Date plan suggestions

[1067] Step 1:

[1068] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[1069] Step 2:

[1070] Terminal: Sends the entered conditions to the server.

[1071] Step 3:

[1072] Server: Generates the optimal date plan taking into account the conditions, the user's preferences, and the results of the emotion engine.

[1073] Step 4:

[1074] Server: Sends the proposed date plan to the device.

[1075] Step 5:

[1076] Device: Display date plans to the user.

[1077] Gathering and implementing feedback

[1078] Step 1:

[1079] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[1080] Step 2:

[1081] User: Enters date feedback and taps submit.

[1082] Step 3:

[1083] Device: Sends feedback to the server.

[1084] Step 4:

[1085] Server: Stores the collected feedback and incorporates it into the next proposal.

[1086] Continuous learning with emotion engine

[1087] Step 1:

[1088] Emotion engine: Improves analysis accuracy while taking feedback into consideration. For example, based on feedback such as "I was very satisfied with this date suggestion," the effectiveness of emotion-based suggestions can be further improved.

[1089] This will enable the system to increase users' chances of finding love and help them form efficient and effective partnerships.The use of an emotion engine will enable the system to provide more personalized advice and plans that are in line with the user's emotional state, which is expected to improve the user experience.

[1090] Example 2

[1091] 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."

[1092] Conventional matchmaking systems simply collect user information and recommend potential partners based on that information. They lack the ability to provide personalized advice or date plans that take into account data such as the user's emotional state and conversation logs. This makes it difficult to improve the user experience and effectively support users in increasing their chances of finding love. The present invention aims to solve this problem by providing personalized suggestions that take into account the user's information and emotional state.

[1093] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1094] In this invention, the server includes means for collecting and storing user information, means for recommending optimal matches based on the user information, means for analyzing the user's conversation records and posted content to generate appropriate advice, means for analyzing the user's emotional state to personalize the advice and date plans, and means for proposing date plans for the user. This makes it possible to not only recommend matches that meet the user's expectations, but also to provide specific and personalized advice and date plans that are tailored to each individual user.

[1095] "User information" refers to data such as profile information, hobby information, and relationship goals entered when using the system.

[1096] "Storage means" refers to a device or system that has the function of storing collected user information in a storage device such as a database.

[1097] "Means for recommending matching partners" refers to a system that selects the most suitable partner from a database based on the user's information and notifies the user of the results.

[1098] "Conversation records" refer to the content of conversations that users have on the system.

[1099] "Posted content" refers to the content of text, comments, updates, etc. posted by users on social media or the system.

[1100] "Means of analysis" refers to a system that uses natural language processing and sentiment analysis techniques to analyze user tendencies and emotions from conversation records and posted content.

[1101] "Means for generating appropriate advice" refers to a system that automatically generates advice and suggested actions that are useful to users based on the analysis results.

[1102] "Means for analyzing emotional state" refers to a system that determines a user's positive or negative emotional state from their conversation records and posted content.

[1103] "Means for proposing date plans" refers to a system that automatically designs and proposes optimal date itineraries based on user information and analysis results.

[1104] "Means for collecting feedback" refers to a system that allows users to input and record their evaluations and impressions of dates and proposals.

[1105] "Means of reflecting this in the next proposal" refers to a system that uses the collected feedback to improve and optimize future advice and proposals.

[1106] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. By combining this system with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and plans based on that analysis.

[1107] Configuration overview

[1108] This system consists of a server, terminals, and users.

[1109] Server: Collects, stores, analyzes, and provides recommendations based on information. Server software includes databases (e.g., MySQL), natural language processing (NLP) engines (e.g., Google Natural Language API), and emotion engines (e.g., IBM Watson Emotional Analysis).

[1110] Terminal: Provides an interface with the user. Terminals are general information devices such as smartphones and PCs.

[1111] User: Uses the system to enter information and receive suggestions.

[1112] Collection and storage of user information

[1113] User: Launch the app from a smartphone or PC and enter necessary information such as name, age, hobbies, and romantic goals when registering for the first time. For example, enter data such as "Ichiro Tanaka, 30 years old, reading, looking for a marriage partner."

[1114] Terminal: Sends this input information to the server.

[1115] Server: Save the received user information in a database. For example, create a table called "User Information" in a MySQL database and store data in each field.

[1116] Matching partner recommendations

[1117] Server: Queries the database based on the user's profile and preferences to select the most suitable match. For example, if Ichiro Tanaka's hobby is "reading" and his goal is "finding a marriage partner," the server will select candidates with the same hobbies and goals.

[1118] Server: Sends a list of selected match candidates to the device. The list includes information such as the match's name, hobbies, and photo.

[1119] On your device: The profile of the recommended person will be displayed to you.

[1120] User: View the recommended person and select "Like" or "Dislike." For example, by pressing the "♡" button next to the person's profile, you can register them as "Like."

[1121] Terminal: Sends the user's selection to the server.

[1122] Server: The selection results are stored in a database and used to improve the recommendation algorithm in the future.

[1123] Analysis of conversation logs and social media posts

[1124] Device: The device periodically sends the user's conversation logs and social media posts to the server. For example, it collects conversation history within a chat app and public posts on social media.

[1125] Server: Analyzes collected logs and posts using a natural language processing (NLP) engine. Specifically, it uses the Google Natural Language API to analyze various texts.

[1126] Server: Extracts the other person's interests, concerns, and emotional tone. For example, it obtains information such as "Today's posts contain many words like 'fun' and 'happy'."

[1127] Use of emotion engine

[1128] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, if a user posts, "I'm feeling great today," the emotion engine will identify this as a positive emotion.

[1129] Example: Detecting positive sentiment from posts such as "I'm feeling great today."

[1130] Providing advice and training

[1131] Server: Based on the analysis results, the server generates advice and training content tailored to the user. It also takes into account the results of the emotion engine to create specific advice. For example, it provides advice such as, "When the other person talks about a movie, suggest going to see it together."

[1132] Server: Sends the generated advice to the device.

[1133] Device: Displays received advice and training content to the user.

[1134] Users: Review advice and training and apply it to their next conversation or date.

[1135] Date plan suggestions

[1136] User: Requests date plan suggestions and enters criteria such as location, budget, date, etc. For example, "Shibuya, under 5,000 yen, Saturday afternoon."

[1137] Terminal: Sends the entered conditions to the server.

[1138] Server: Based on the input conditions, the server generates the optimal date plan based on the user's preferences and the results of the emotion engine. For example, it suggests "lunch at a cafe in Shibuya and then watch a movie."

[1139] Server: Sends the proposed date plan to the device.

[1140] Device: Display date plans to the user.

[1141] Gathering and implementing feedback

[1142] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date. For example, the device displays questions such as, "How satisfied were you with the date?"

[1143] User: Enter your feedback and tap the submit button. For example, "Satisfaction rating: 8 / 10."

[1144] Device: Sends feedback to the server.

[1145] Server: Store the collected feedback in a database and use it to make the next recommendation. For example, store satisfaction in a "Dating Experience" table.

[1146] Continuous learning with emotion engine

[1147] Emotion engine: Improves analysis accuracy while taking into account feedback. For example, improves the effectiveness of emotion-based suggestions based on information such as "This date suggestion was very satisfying."

[1148] This allows the system to increase the user's chances of finding love. By using a generative AI model and specific prompts, it is possible to provide more advanced advice and plans. A specific example would be to input the user's past conversation logs into the generative AI model to perform a deep analysis of emotional fluctuations.

[1149] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1150] Step 1:

[1151] User: Launch the app from a smartphone or PC and enter the necessary information such as name, age, hobbies, and relationship goals when registering for the first time. For example, enter data such as "Suzuki Hanako, 28 years old, traveling, looking for a marriage partner."

[1152] Input: Profile information, hobbies, relationship goals, etc. that you enter into the app.

[1153] Output: Input information is sent to the device and converted into a format for storage on the server.

[1154] Step 2:

[1155] Device: The entered user information is sent to the server. This operation is performed by pressing the "Register" button in the app.

[1156] Input: User information (name, age, hobbies, love goals, etc.)

[1157] Output: User information is sent to the server.

[1158] Step 3:

[1159] Server: Save the received user information in a database. For example, create a table called "User Information" in a MySQL database and store data in each field.

[1160] Input: User information sent from the terminal

[1161] Output: User information is saved in the database.

[1162] Step 4:

[1163] Server: Queries the database based on the user's profile and preferences to select the most suitable match. For example, based on information such as "Suzuki Hanako loves traveling and is looking for a marriage partner," it selects candidates with the same hobbies and goals.

[1164] Input: User information (profile, hobbies, relationship goals)

[1165] Output: A list of potential matches is generated.

[1166] Step 5:

[1167] Server: Sends a list of selected match candidates to the device, including information such as the matchee's name, hobbies, and photo.

[1168] Input: A list of possible matches

[1169] Output: A list of potential matches is sent to the device.

[1170] Step 6:

[1171] On your device: The profile of the recommended person will be displayed to you. It will be displayed on the "Matching Candidates" screen in the app.

[1172] Input: A list of match candidates sent by the server

[1173] Output: Information that is visually displayed to the user (profile, photo, etc.).

[1174] Step 7:

[1175] User: View the recommended person and select "Like" or "Dislike." For example, by pressing the "♡" button next to the person's profile, you can register them as "Like."

[1176] Input: User's choice (like it or not)

[1177] Output: The selections are logged to the terminal.

[1178] Step 8:

[1179] Terminal: Sends the user's selection to the server.

[1180] Input: User selection

[1181] Output: The selection results are sent to the server.

[1182] Step 9:

[1183] Server: The selection results are stored in a database to help improve the recommendation algorithm in the future, for example in a "User Behavior History" table.

[1184] Input: User selection

[1185] Output: The selection results are saved in a database and added to the data used for analysis.

[1186] Step 10:

[1187] Device: The device periodically sends the user's conversation logs and social media posts to the server. For example, it collects conversation history within a chat app and public posts on social media.

[1188] Input: Conversation logs, social media posts

[1189] Output: Conversation logs and SNS posts are transferred to the server.

[1190] Step 11:

[1191] Server: Analyzes collected logs and posts using a natural language processing (NLP) engine. Specifically, analysis is performed using the Google Natural Language API.

[1192] Input: Conversation logs, social media posts

[1193] Output: Data about the user's emotional state and interests is generated.

[1194] Step 12:

[1195] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, if a user posts, "I'm feeling great today," the emotion engine will identify this as a positive emotion.

[1196] Input: Conversation logs, social media posts

[1197] Output: The user's emotional state (positive, negative, etc.). Example: A post saying "I'm feeling great today" is judged to have a positive emotion.

[1198] Step 13:

[1199] Server: Based on the analysis results, the server generates advice and training content tailored to the user. It also takes into account the results of the emotion engine to provide specific advice. For example, it creates advice such as "When the other person talks about a movie, suggest going to see it together."

[1200] Input: Analysis results, emotion engine results

[1201] Output: Generate specific advice and training content

[1202] Step 14:

[1203] Server: Sends the generated advice to the device.

[1204] Input: Generated advice and training content

[1205] Output: Advice and training content are transferred to the device.

[1206] Step 15:

[1207] On your device: Displaying received advice and training content to you, for example in the "Advice" section within the app.

[1208] Input: Advice and training content sent

[1209] Output: Visually displayed advice and training content

[1210] Step 16:

[1211] Users: Review advice and training and apply it to their next conversation or date.

[1212] Input: Received advice, training content

[1213] Output: Advice implementation reflected in actual behavior

[1214] Step 17:

[1215] User: Requests date plan suggestions and enters criteria such as location, budget, date, etc. For example, "Shibuya, under 5,000 yen, Saturday afternoon."

[1216] Input: Date plan conditions (location, budget, date, etc.)

[1217] Output: The condition is sent to the terminal and forwarded to the server.

[1218] Step 18:

[1219] Terminal: Sends the entered conditions to the server.

[1220] Input: Date plan conditions

[1221] Output: The condition is sent to the server.

[1222] Step 19:

[1223] Server: Based on the input conditions, the server generates the optimal date plan based on the user's preferences and the results of the emotion engine. For example, it suggests "lunch at a cafe in Shibuya and then watch a movie."

[1224] Input: Date plan conditions, preference information, emotion engine results

[1225] Output: Proposed date plan

[1226] Step 20:

[1227] Server: Sends the proposed date plan to the device.

[1228] Enter: Date plan

[1229] Output: The date plan is sent to the device.

[1230] Step 21:

[1231] Device: Display date plans to the user.

[1232] Input: Date plan sent from the server

[1233] Output: A visual representation of the date plan

[1234] Step 22:

[1235] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date. For example, the device displays questions such as, "How satisfied were you with the date?"

[1236] Input: Feedback Question

[1237] Output: Feedback survey displayed to the user

[1238] Step 23:

[1239] User: Enter your feedback and tap the submit button. For example, "Satisfaction rating: 8 / 10."

[1240] Input: Date feedback (impressions, ratings, etc.)

[1241] Output: Feedback information is sent to the terminal.

[1242] Step 24:

[1243] Device: Sends feedback to the server.

[1244] Input: Feedback information entered by the user

[1245] Output: The feedback information is sent to the server.

[1246] Step 25:

[1247] Server: Stores the collected feedback in a database and uses it to improve future recommendations. For example, satisfaction is stored in a "Dating Experience" table.

[1248] Input: Feedback information

[1249] Output: Saved feedback information, data to be reflected in the next proposal

[1250] Step 26:

[1251] Emotion engine: Improves analysis accuracy while taking into account feedback. For example, improves the effectiveness of emotion-based suggestions based on information such as "This date suggestion was very satisfying."

[1252] Input: Feedback information

[1253] Output: Improved analysis accuracy and improved proposal accuracy based on that.

[1254] (Application example 2)

[1255] 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."

[1256] Conventional online shopping sites lack personalized product recommendations based on users' emotions and preferences, making it difficult for users to find the products that are best suited to them. Furthermore, they lack a system for effectively incorporating user feedback, making it difficult to make continuous improvements.

[1257] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing user information, means for recommending optimal products based on the user information, means for analyzing the user's conversation log and posted content and generating appropriate advice, and means for suggesting product information and sale information to the user. This enables personalized product recommendations based on the user's emotions and preferences, improving the user's purchasing experience. In addition, analyzing user feedback and reflecting it in the next recommendation content enables continuous system improvement.

[1258] "User information" refers to information including the profile information, purchase history, and browsing history of the user of the online shopping site.

[1259] "Means of collecting and storing" refers to the means of sending the information provided by the user to the server and storing it in a database.

[1260] "Means for recommending optimal products" refers to means for selecting and recommending the product that best suits a user based on the user's information.

[1261] "Means for analyzing conversation logs and posted content" refers to means for analyzing the conversations and social media posts of users and understanding their emotions and interests from the content.

[1262] The "means for generating appropriate advice" is a means for generating advice for presenting product recommendations and sale information suited to a user based on analyzed user information.

[1263] The "means for suggesting product information and sale information" is a means for displaying appropriate product information and sale information to the user based on the generated advice.

[1264] The "means for collecting and storing feedback" refers to a means for collecting impressions and ratings provided by users after purchase and storing them on a server.

[1265] "Means for analyzing feedback and reflecting it in the next recommendation" refers to means for analyzing collected feedback information and using it to improve the recommendation content from the next time onwards.

[1266] "Profile information" refers to information that includes personal information such as a user's name, age, gender, and hobbies.

[1267] "Purchase history" is information that includes a record of products that a user has purchased in the past.

[1268] "Browsing history" is information that includes a record of products and pages that a user has viewed in the past.

[1269] "Means for providing appropriate product recommendations and training based on analysis" refers to means for providing users with appropriate product recommendations, usage instructions, and related training content based on the analysis results.

[1270] Overall system configuration

[1271] This invention is a system that collects and analyzes user information, recommends optimal products, and provides appropriate advice and product information. The system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and product information based on that.

[1272] Collection and storage of user information

[1273] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, purchase history, browsing history, etc.).

[1274] Terminal: Sends the entered information to the server.

[1275] Server: Stores the received user information in a database.

[1276] Product Recommendations

[1277] Server: Uses a recommendation algorithm to select the most suitable products from a database based on the user's profile and purchasing history.

[1278] Server: Sends the selected product to the device.

[1279] Device: Display recommended product information to the user.

[1280] Analysis of conversation logs and social media posts

[1281] Device: The user's conversation log and social media posts are periodically sent to the server.

[1282] Server: A natural language processing (NLP) engine (e.g., Google Cloud Natural Language API) and a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) are used to analyze the collected logs and posts.

[1283] Server: Extracts emotional tone and stores it as data for recommending optimal products.

[1284] Providing advice and product information

[1285] Server: Based on the analysis results, the server generates advice and product information tailored to the user. For example, it generates specific advice such as "If a user mentions in a recent post that they like flowers, provide them with information about sale items for flower arrangements."

[1286] Server: Sends the generated advice to the device.

[1287] Terminal: Displays received advice and product information to the user.

[1288] Gathering and implementing feedback

[1289] Device: After purchasing a product, a feedback survey is sent to the user, asking them to enter their impressions and ratings.

[1290] User: Enters feedback about a purchased item and taps the submit button.

[1291] Device: Sends feedback to the server.

[1292] Server: Stores the collected feedback and uses it to improve future recommendations.

[1293] Continuous learning with emotion engine

[1294] Emotion engine: Improves analysis accuracy while taking feedback into account. For example, feedback such as "very satisfied" can be used to improve the effectiveness of suggestions based on further emotion recognition.

[1295] Server: Train a new product recommendation model using the sentiment data.

[1296] Specific examples

[1297] Example prompts to input to the generative AI model

[1298] Prompt: "A user recently posted on social media, 'I'm in a great mood today, so I bought some flowers!' What product recommendations would you give them?"

[1299] This system enables personalized product recommendations based on the user's emotions and preferences, improving the user's purchasing experience. Furthermore, by analyzing user feedback and reflecting it in the next recommendation, the system can be continuously improved.

[1300] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1301] Step 1:

[1302] When a user launches the app from a device such as a smartphone or PC, they enter the necessary information for initial registration (name, age, purchase history, browsing history, etc.), and the device sends this information to the server. The input data includes name, age, purchase history, and browsing history, and is saved in a database.

[1303] Step 2:

[1304] The server stores the received user information in a database and then stores the user information in an integrated database at the specified timing. This process accumulates the user's basic information and behavioral history data.

[1305] Step 3:

[1306] The server selects products from a database using an optimal recommendation algorithm based on the user's profile and purchase history, generates a list of recommended products as output, and sends it to the terminal.

[1307] Step 4:

[1308] The terminal displays the received recommended product list to the user, who then confirms the recommended products. The terminal records the user's choice (whether to purchase or not) and sends it to the server.

[1309] Step 5:

[1310] The device periodically sends the user's conversation log and social media posts to the server. These conversation logs and posts serve as input data for analysis.

[1311] Step 6:

[1312] The server uses a natural language processing (NLP) engine and a sentiment analysis engine to analyze the collected conversation logs and posted content. For example, it uses the Google Cloud Natural Language API to extract emotional tones from text and stores the analysis results in a database.

[1313] Step 7:

[1314] The server generates advice and product information tailored to the user based on the analysis results. For example, it generates specific advice such as "If a user mentions in a recent post that they like flowers, provide them with information about sale items for flower arrangements."

[1315] Step 8:

[1316] The server sends the generated advice and product information to the terminal, which then displays it to the user, who then checks the displayed advice and product information.

[1317] Step 9:

[1318] After a product is purchased, the terminal sends a feedback survey to the user, prompting them to enter their impressions and evaluations. The input data includes the user's satisfaction with the purchased product and their impressions of use.

[1319] Step 10:

[1320] The user inputs the feedback and taps the send button, and the terminal transmits the user's feedback data to the server.

[1321] Step 11:

[1322] The server stores the collected feedback in a database and uses it to improve the recommendation algorithm for the next step. Based on the analysis of the feedback, a new product recommendation model is trained.

[1323] Step 12:

[1324] The emotion engine uses feedback to improve analysis accuracy. For example, feedback such as "very satisfied" can be used to improve the effectiveness of suggestions based on further emotion recognition.

[1325] In this way, the system can provide personalized product recommendations based on users' emotions and preferences, and achieve continuous improvement by incorporating effective feedback.

[1326] 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.

[1327] 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.

[1328] 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.

[1329] [Third embodiment]

[1330] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1331] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1332] 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).

[1333] 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.

[1334] 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.

[1335] 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).

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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."

[1342] The present invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans.

[1343] Overall system configuration

[1344] This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and provides suggestions for information, while the terminal provides an interface for users. Users use the system to input information and receive suggestions.

[1345] Collection and storage of user information

[1346] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, hobbies, relationship goals, etc.).

[1347] Terminal: Sends the entered information to the server.

[1348] Server: Stores the received information in a database.

[1349] Matching partner recommendations

[1350] Server: Uses the user's profile and preferences to select the most suitable match from the database.

[1351] Server: Sends the selected matching candidates to the device.

[1352] Device: The profile of the recommended person is displayed to the user for confirmation.

[1353] User: View the recommended people and select "Like" or "Dislike."

[1354] Terminal: Sends the selection results to the server.

[1355] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[1356] Analysis of conversation logs and social media posts

[1357] Device: The user's conversation log and social media posts are periodically sent to the server.

[1358] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content, extracting the other person's interests, concerns, and emotional tone.

[1359] Example: For example, if a user talks a lot about movies and music, the system can analyze that information and determine that the other person is likely interested in movies and music.

[1360] Providing advice and training

[1361] Server: Based on the analysis results, the server generates advice and training tailored to the user. For example, it provides advice such as "Talk about the other person's favorite movie in your next conversation."

[1362] Server: Sends the generated advice to the device.

[1363] Terminal: Display the received advice to the user.

[1364] User: Check out the advice and apply it to your next conversation or date.

[1365] Date plan suggestions

[1366] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[1367] Terminal: Sends the entered conditions to the server.

[1368] Server: Generates optimal date plans based on the conditions and the user's preferences. For example, it suggests restaurants and events.

[1369] Server: Sends the proposed date plan to the device.

[1370] Device: Display date plans to the user.

[1371] Gathering and implementing feedback

[1372] Device: After the date, users are sent a feedback survey and asked to enter their impressions and evaluation of the date.

[1373] User: Enter your feedback and tap the submit button.

[1374] Device: Sends feedback to the server.

[1375] Server: Stores the collected feedback and incorporates it into the next proposal.

[1376] This enables the system to increase users' chances of success in love and help them form efficient and effective partnerships.

[1377] The processing flow will be explained below.

[1378] Collection and storage of user information

[1379] Step 1:

[1380] User: Launch the app and enter user information (name, age, hobbies, relationship goals, etc.).

[1381] Step 2:

[1382] Terminal: Sends the entered information to the server.

[1383] Step 3:

[1384] Server: Stores the received user information in a database.

[1385] Matching partner recommendations

[1386] Step 1:

[1387] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[1388] Step 2:

[1389] Server: Sends the selected matching candidates to the device.

[1390] Step 3:

[1391] On your device: The profile of the recommended person will be displayed to you.

[1392] Step 4:

[1393] User: View the recommended people and select "Like" or "Dislike."

[1394] Step 5:

[1395] Terminal: Sends the user's selection to the server.

[1396] Step 6:

[1397] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[1398] Analysis of conversation logs and social media posts

[1399] Step 1:

[1400] Device: The user's conversation log and SNS postings are periodically sent to the server.

[1401] Step 2:

[1402] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[1403] Step 3:

[1404] Server: Extract the other person's interest, concern, and emotional tone.

[1405] Providing advice and training

[1406] Step 1:

[1407] Server: Based on the analysis results, it generates advice and training content tailored to the user.

[1408] Step 2:

[1409] Server: Sends the generated advice to the device.

[1410] Step 3:

[1411] Device: Displays received advice and training content to the user.

[1412] Step 4:

[1413] Users: Review advice and training and apply it to their next conversation or date.

[1414] Date plan suggestions

[1415] Step 1:

[1416] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[1417] Step 2:

[1418] Terminal: Sends the entered conditions to the server.

[1419] Step 3:

[1420] Server: Generates the optimal date plan taking into account the conditions and the user's preferences.

[1421] Step 4:

[1422] Server: Sends the proposed date plan to the device.

[1423] Step 5:

[1424] Device: Display date plans to the user.

[1425] Gathering and implementing feedback

[1426] Step 1:

[1427] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[1428] Step 2:

[1429] User: Enters date feedback and taps submit.

[1430] Step 3:

[1431] Device: Sends feedback to the server.

[1432] Step 4:

[1433] Server: Stores the collected feedback and incorporates it into the next proposal.

[1434] Example 1

[1435] 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."

[1436] In conventional matchmaking systems, the collection and storage of user information, the recommendation of potential matches, and the generation of advice are often carried out separately, resulting in a lack of integration as a whole system. Furthermore, insufficient analysis of users' conversation logs and social media posts can lead to issues such as inappropriate advice not being provided and date plan suggestions not matching the user's preferences or requirements. Furthermore, there are also issues with inefficient collection and reflection of feedback, which means that improvements are not incorporated into future proposals.

[1437] 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.

[1438] In this invention, the server includes means for collecting and storing user information, means for recommending optimal matches based on the user information, means for analyzing the user's conversation log and postings and generating appropriate advice using a natural language processing engine, and means for proposing date plans that meet the user's requirements. This enables integrated management of user information, providing highly accurate matching and advice, and proposing date plans that meet the user's preferences and requirements. Furthermore, by collecting feedback and analyzing it using a machine learning algorithm, it is possible to continuously improve the recommendation algorithm and reflect this in future recommendations.

[1439] A "user" is an individual who uses the system and provides information such as personal information, hobbies, preferences, and romantic intentions.

[1440] "Means of collecting and storing information" refers to various functions for storing information provided by users, such as personal information, hobbies, preferences, and romantic intentions, in a database.

[1441] "Means for recommending matching partners" refers to algorithms and functions that select the most suitable partner based on the user's information and provide that information to the user.

[1442] "Means for analyzing conversation logs and posted content" refers to the function of analyzing users' conversation logs and SNS posts using a natural language processing engine, etc., and generating appropriate advice for users based on the results obtained.

[1443] A "natural language processing engine" is a software engine that analyzes text data and extracts meaning, emotion, topics, etc.

[1444] "Means for generating advice" refers to a function that generates and provides appropriate advice on actions and conversations to users based on the analysis results.

[1445] "Means for proposing date plans" refers to a function that generates an appropriate date plan based on the conditions provided by the user (location, budget, date and time, etc.) and proposes it to the user.

[1446] "Means for collecting and storing feedback" refers to a function for storing feedback provided by users, such as impressions and ratings after a date, in a database.

[1447] A "machine learning algorithm" is an algorithm that analyzes feedback data and learns to improve the accuracy of future suggestions and recommendation algorithms.

[1448] "Profile Information" refers to a user's basic personal information (such as name, age, etc.).

[1449] "Interest information" refers to information about a user's interests, hobbies, and preferences.

[1450] "Love goals" refers to the objectives that users want to achieve in love (e.g., serious relationship, finding friends, etc.).

[1451] "Generation policy" refers to guidelines and standards for providing optimal advice and training to users based on the analysis results.

[1452] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions.

[1453] Collection and storage of user information

[1454] Users start the application from a device such as a smartphone or PC and enter initial registration information such as their name, age, hobbies, and romantic interests. The device then sends the collected information to the server, which then stores the received information in a database. Data is sent in JSON or XML format, and is securely transmitted via HTTPS requests.

[1455] Matching partner recommendations

[1456] The server uses an algorithm to select the most suitable match based on the user's profile and preferences. The algorithm uses KNN (nearest neighbor search) and collaborative filtering to select candidates with many similarities. The selected match candidates are sent from the server to the device, which displays the information to the user. The user looks at the recommended partners and selects either "like" or "dislike," and sends the result to the server via the device. The server stores the selection results in a database and uses them to improve the recommendation algorithm in the future.

[1457] Analysis of conversation logs and social media posts

[1458] The device periodically sends the user's conversation log and social media posts to a server. The server then analyzes the collected data using a natural language processing (NLP) engine. Libraries such as spaCy and NLTK are used for this analysis. The analysis extracts the other person's interests, concerns, and emotional tone. Specifically, if the user talks a lot about movies and music, the system determines that the other person is likely to be interested in these subjects.

[1459] Providing advice and training

[1460] The server generates optimal advice and training for the user based on the results of NLP analysis. A generative AI model (e.g., GPT-3) is used for this generation. For example, advice such as "Talk about the other person's favorite movie in your next conversation" may be provided. The generated advice is sent from the server to the device, which displays it to the user. The user can confirm the advice and put it into practice in their next conversation or date.

[1461] Date plan suggestions

[1462] The user requests a date plan proposal and enters conditions (location, budget, date and time, etc.). These conditions are sent from the device to the server. The server generates the optimal date plan taking into account the conditions and the user's preferences. For example, it may suggest restaurants or events. To generate this plan, it references various APIs and databases to select a plan that meets the user's conditions. The generated date plan is sent from the server to the device, which then displays it to the user.

[1463] Gathering and implementing feedback

[1464] After the date, the device sends the user a feedback survey. The user enters their impressions and evaluation of the date and taps the send button. The collected feedback is sent from the device to the server, which stores it in a database. The server then analyzes this feedback data using a machine learning algorithm and reflects it in future recommendations. This allows for continuous improvement of the recommendation algorithm.

[1465] Prompt Sentence Examples

[1466] Examples of prompts with examples include:

[1467] "User A is a 35-year-old man whose hobbies are watching movies and hiking. After he enters his profile, please explain how the system recommends his best matches. Also, please explain the specific process of providing advice and proposing date plans."

[1468] This prompt is fed into a generative AI model, which then provides a concrete explanation of the overall flow of the system.

[1469] The above is a form for implementing the present invention, and this system can increase the user's success rate in romance and support the formation of efficient and effective partnerships.

[1470] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1471] Step 1:

[1472] Input: The user launches the application from their smartphone or computer and enters their initial registration information (name, age, hobbies, and romantic intent).

[1473] Action: The user fills in the application's registration form and presses the submit button.

[1474] Terminal: The input information is packaged in JSON or XML format and sent to the server via an HTTPS request.

[1475] Output: Personal information sent to the server.

[1476] Step 2:

[1477] Input: User information sent from the device in step 1.

[1478] How it works: The server parses the incoming data and stores the information in a database using SQL queries, typically MySQL or PostgreSQL.

[1479] Server: Inserts and stores the received information into a database.

[1480] Output: User information stored in the database.

[1481] Step 3:

[1482] Input: User profile and interest information stored in a database.

[1483] How it works: The server uses KNN (Knowledge Neighborhood Search) and collaborative filtering algorithms to select the best match.

[1484] Server: Packages the selection results in JSON format and sends them to the terminal.

[1485] Output: Match candidate information sent to the device.

[1486] Step 4:

[1487] Input: Match candidate information sent from the server.

[1488] What it does: The device displays profiles of potential matches to the user, using a list view or card layout.

[1489] Terminal: Displays the selection results to the user.

[1490] Output: Match candidate information displayed to the user.

[1491] Step 5:

[1492] Input: The match candidate information displayed to the user.

[1493] How it works: The user selects "like" or "dislike" and the result is sent from the device to the server.

[1494] User: Look at the recommended partners and make a selection.

[1495] Terminal: The selection results are packaged in JSON format and sent to the server.

[1496] Output: The selection results sent to the server.

[1497] Step 6:

[1498] Input: The selection sent from the terminal in step 5.

[1499] How it works: The server analyzes the selection results, stores them in a database, and uses them to improve the recommendation algorithm in the future.

[1500] Server: Records preference data and uses it as training data for recommendation algorithms.

[1501] Output: Selection results stored in a database.

[1502] Step 7:

[1503] Input: User conversation logs and social media posts.

[1504] How it works: The device periodically sends conversation logs and social media posts in JSON format to the server.

[1505] Terminal: Collects log data, packages it, and sends it to the server.

[1506] Output: Conversation logs and SNS posting data sent to the server.

[1507] Step 8:

[1508] Input: Conversation logs and social media post data sent in step 7.

[1509] How it works: The server performs the analysis using a natural language processing (NLP) engine (e.g. spaCy or NLTK).

[1510] Server: Performs sentiment analysis and key phrase extraction using collected data.

[1511] Output: Areas of interest and emotional tone derived from the analysis.

[1512] Step 9:

[1513] Input: NLP analysis results.

[1514] How it works: The server generates appropriate advice and training content based on the analysis results. It uses a generative AI model (e.g., GPT-3).

[1515] Server: Utilizes generative AI models to generate personalized advice.

[1516] Output: The generated advice and training content.

[1517] Step 10:

[1518] Input: Generated advice and training content.

[1519] Operation: The server sends advice to the device.

[1520] Server: Packages advice in JSON format and sends it to the device.

[1521] Output: Advice sent to the terminal.

[1522] Step 11:

[1523] Input: Advice sent by the server.

[1524] What it does: The device displays advice to the user, using a pop-up message or notification bar.

[1525] Terminal: Presents advice to the user.

[1526] Output: The advice displayed to the user.

[1527] Step 12:

[1528] Input: The date plan conditions requested by the user (location, budget, date and time).

[1529] Operation: The device sends the conditions in JSON format to the server.

[1530] User: Enter the conditions for the date plan.

[1531] Terminal: Packages and sends the conditions.

[1532] Output: Dateplan conditions sent to the server.

[1533] Step 13:

[1534] Input: Date plan conditions and user preferences.

[1535] How it works: The server generates the optimal date plan based on the conditions and preferences. It does so by referencing various APIs and databases.

[1536] Server: Searches a database of restaurants and events and selects plans that match your criteria.

[1537] Output: The generated date plan.

[1538] Step 14:

[1539] Input: Date plan sent from the server.

[1540] How it works: The server sends the plan to the device, packaging it in JSON format.

[1541] Server: Sends the generated date plan to the device.

[1542] Output: The date plan sent to the device.

[1543] Step 15:

[1544] Input: Date plan information sent from the server.

[1545] Action: The device displays the date plan to the user. Use the details page.

[1546] Device: Display date plans.

[1547] Output: The date plan displayed to the user.

[1548] Step 16:

[1549] Input: Post-date feedback survey.

[1550] Operation: The device sends a survey to the user via push notification. The user fills out the survey and presses the send button.

[1551] Terminal: Collects surveys and sends them to the server.

[1552] Output: Feedback data sent to the server.

[1553] Step 17:

[1554] Input: Feedback data collected in step 16.

[1555] How it works: The server stores the feedback data in a database and analyzes it using machine learning algorithms.

[1556] Server: Updates the recommendation algorithm based on the feedback data and reflects it in the next proposal.

[1557] Output: Analysis results stored in a database and updated recommendation algorithms.

[1558] The above is the specific processing flow of the system program.

[1559] (Application example 1)

[1560] 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."

[1561] Conventional content distribution services have recommended limited content based on users' past viewing history and preferences. This has made it difficult for users to efficiently discover diverse new content that interests them. Furthermore, the provision of appropriate viewing schedules and advice has been insufficient, preventing users from maximizing their viewing experience. The present invention aims to solve these problems and improve user satisfaction by providing individually customized content recommendations and viewing advice to users.

[1562] 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.

[1563] In this invention, the server includes means for collecting and storing user information, means for recommending optimal content, means for analyzing user conversation logs and posted content to generate appropriate advice, and means for proposing viewing schedules, thereby enabling users to efficiently discover a variety of new content that interests them and receive appropriate viewing schedules and advice.

[1564] "User information" is a collective term for profile information, preference information, and viewing history collected when using the system.

[1565] "Storage means" refers to a function for storing collected user information in a storage device such as a database.

[1566] "Recommendation means" is a function that selects and suggests the most appropriate content based on saved user information.

[1567] "Conversation log" refers to the text messages and communication history entered by the user.

[1568] "Posted content" refers to comments and feedback posted by users on social media or review sites.

[1569] "Means of analysis" refers to a function that analyzes conversation logs and posted content using natural language processing technology, etc., to extract users' hobbies and interests.

[1570] The "means for generating advice" is a function that automatically generates appropriate content and viewing advice for users based on the analysis results.

[1571] The "means for proposing a viewing schedule" is a function that proposes an optimal content viewing schedule based on the user's lifestyle and past viewing patterns.

[1572] "Feedback" refers to opinions such as ratings and impressions of content viewed by users.

[1573] "Means of reflection" is a function that analyzes collected feedback and uses it to recommend content or generate advice next time.

[1574] The present invention is embodied as a personalized video recommendation system for use in a content distribution service. The system is mainly composed of a server, a terminal, and a user, and is realized by the following means and processing steps.

[1575] Overall system configuration

[1576] This system consists of a client terminal (e.g., a smartphone) and a server. The server collects, stores, analyzes, and recommends information, while the terminal provides an interface with the user. The user also uses the system to input information and receive suggestions.

[1577] Collection and storage of user information

[1578] User: Launches the smartphone app and enters information such as name, age, hobbies, and viewing history when registering for the first time.

[1579] Terminal: Sends collected user information to the server.

[1580] Server: Stores the received information in a database, which is used for future data analysis and to improve recommendation algorithms.

[1581] Content Recommendations

[1582] Server: Selects the most suitable video content from the database based on the user's profile, preferences, and viewing history. For example, if a user likes sci-fi movies, it will recommend new and highly rated movies in the sci-fi genre.

[1583] Device: A list of recommended content is displayed to the user, who can select "Like" or "Dislike."

[1584] Server: Stores the user's selections and uses them to improve the recommendation algorithm in the future.

[1585] Analysis of conversation logs and postings

[1586] Device: The user's conversation log and social media posts are periodically sent to the server.

[1587] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content. For example, generative AI models such as spaCy and BERT are used. Through analysis, the user's interests, concerns, and emotional tone are extracted. For example, if a user frequently comments about a particular actor on social media, movies starring that actor can be recommended.

[1588] Advice generation and viewing schedule suggestions

[1589] Server: Based on the analysis results, the server generates advice and viewing schedules tailored to the user. For example, it provides advice such as "This is the next sci-fi movie you should watch."

[1590] Device: The generated advice and schedule are displayed to the user, who can use them to plan their viewing plans.

[1591] Gathering and implementing feedback

[1592] Device: After viewing the content, a feedback survey is sent to the user, in which they are asked to enter their rating and impressions.

[1593] User: Enter feedback and tap submit.

[1594] Device: Sends feedback to the server.

[1595] Server: Stores the collected feedback and uses it to generate the next recommendation or advice.

[1596] This allows the system to improve the user's viewing experience and effectively support the discovery of diverse new content. For example, if a user has a preference for "sci-fi movies," the system will recommend "Interstellar." An example of a prompt is, "Based on the user's viewing history, please generate three new content recommendations."

[1597] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1598] Step 1:

[1599] User: Launches the smartphone app and enters information such as name, age, hobbies, and viewing history when registering for the first time. This provides basic information about the user.

[1600] Step 2:

[1601] Terminal: Sends collected user information to the server. The entered user information is sent as a data packet to the server.

[1602] Step 3:

[1603] Server: Stores the received information in a database. The entered user information is converted into an appropriate format and stored in the database. For example, name, age, hobbies, and viewing history are stored as entries.

[1604] Step 4:

[1605] Server: Selects the most suitable video content from the database using the user's profile, preferences, and viewing history. For example, if a user's hobby is sci-fi movies, the server searches the database to select recommended content from a list of movies in the sci-fi genre.

[1606] Step 5:

[1607] Device: Presents a list of recommended content to the user. Presents a list of selected content in the user interface. This list is generated based on data retrieved from the server.

[1608] Step 6:

[1609] User: View the recommended content list and select "I like it" or "I don't like it." The user's selection becomes the next input.

[1610] Step 7:

[1611] Terminal: Sends the user's selection to the server. The user's selection data is sent to the server as a data packet.

[1612] Step 8:

[1613] Server: Stores user selections and uses them to improve the recommendation algorithm in the future. Stores the selection data in a database and uses it as training data for machine learning models.

[1614] Step 9:

[1615] Device: The device periodically sends the user's conversation logs and SNS posts to the server. The conversation logs and SNS posts recorded by the user become input data and are sent to the server.

[1616] Step 10:

[1617] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content. For example, spaCy or BERT is used to analyze and extract the user's interests, concerns, and emotional tone from the input data. The analysis results are used as input for the next process.

[1618] Step 11:

[1619] Server: Based on the analysis results, generate advice and viewing schedules tailored to the user. For example, generate advice such as "This is the next sci-fi movie you should watch." The generated advice becomes the output data.

[1620] Step 12:

[1621] Terminal: The generated advice and schedule are displayed to the user. The advice sent from the server is displayed in the user interface, allowing the user to create a viewing plan based on this.

[1622] Step 13:

[1623] Terminal: After viewing the content, a feedback survey is sent to the user, in which they are asked to enter their evaluation and impressions. Feedback is obtained as input data after viewing.

[1624] Step 14:

[1625] User: Enter feedback and tap the submit button. The feedback is sent from the device as the final input data.

[1626] Step 15:

[1627] Terminal: Sends feedback to the server. Feedback data is sent to the server as a data packet.

[1628] Step 16:

[1629] Server: Stores the collected feedback and uses it to generate the next recommendation or advice. Stores the feedback data in a database and uses it to improve the algorithm next time.

[1630] 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.

[1631] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and plans based on that.

[1632] Overall system configuration

[1633] This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions. The emotion engine analyzes the user's conversation log and posted content to identify the user's emotional state.

[1634] Collection and storage of user information

[1635] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, hobbies, relationship goals, etc.).

[1636] Terminal: Sends the entered information to the server.

[1637] Server: Stores the received user information in a database.

[1638] Matching partner recommendations

[1639] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[1640] Server: Sends the selected matching candidates to the device.

[1641] On your device: The profile of the recommended person will be displayed to you.

[1642] User: View the recommended people and select "Like" or "Dislike."

[1643] Terminal: Sends the user's selection to the server.

[1644] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[1645] Analysis of conversation logs and social media posts

[1646] Device: The user's conversation log and social media posts are periodically sent to the server.

[1647] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[1648] Server: Extract the other person's interest, concern, and emotional tone.

[1649] Use of emotion engine

[1650] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, by detecting positive and negative expressions, it identifies the user's current emotional state (joy, anxiety, excitement, etc.).

[1651] Example: If a user posts, "I'm feeling great today," the sentiment engine determines that the user is in a positive mood.

[1652] Providing advice and training

[1653] Server: Based on the analysis results, the server generates advice and training content tailored to the user. Taking into account the results of the emotion engine, the server provides specific advice, such as "When the other person talks about a movie, suggest going to see it together."

[1654] Server: Sends the generated advice to the device.

[1655] Device: Displays received advice and training content to the user.

[1656] Users: Review advice and training and apply it to their next conversation or date.

[1657] Date plan suggestions

[1658] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[1659] Terminal: Sends the entered conditions to the server.

[1660] Server: Generates optimal date plans based on the conditions, the user's preferences, and the results of the emotion engine. For example, if the user is in a positive mood, it may suggest outdoor activities for that day's date.

[1661] Server: Sends the proposed date plan to the device.

[1662] Device: Display date plans to the user.

[1663] Gathering and implementing feedback

[1664] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[1665] User: Enters date feedback and taps submit.

[1666] Device: Sends feedback to the server.

[1667] Server: Stores the collected feedback and incorporates it into the next proposal.

[1668] Continuous learning with emotion engine

[1669] Emotion engine: Improves analysis accuracy while taking feedback into consideration. For example, based on feedback such as "I was very satisfied with this date suggestion," the effectiveness of emotion-based suggestions can be further improved.

[1670] This will enable the system to increase users' chances of finding love and help them form efficient and effective partnerships.The use of an emotion engine will enable the system to provide more personalized advice and plans that are in line with the user's emotional state, which is expected to improve the user experience.

[1671] The processing flow will be explained below.

[1672] Processing steps of a system that combines emotion engines

[1673] Collection and storage of user information

[1674] Step 1:

[1675] User: Launch the app and enter user information (name, age, hobbies, relationship goals, etc.).

[1676] Step 2:

[1677] Terminal: Sends the entered information to the server.

[1678] Step 3:

[1679] Server: Stores the received user information in a database.

[1680] Matching partner recommendations

[1681] Step 1:

[1682] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[1683] Step 2:

[1684] Server: Sends the selected matching candidates to the device.

[1685] Step 3:

[1686] On your device: The profile of the recommended person will be displayed to you.

[1687] Step 4:

[1688] User: View the recommended people and select "Like" or "Dislike."

[1689] Step 5:

[1690] Terminal: Sends the user's selection to the server.

[1691] Step 6:

[1692] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[1693] Analysis of conversation logs and social media posts

[1694] Step 1:

[1695] Device: The user's conversation log and social media posts are periodically sent to the server.

[1696] Step 2:

[1697] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[1698] Step 3:

[1699] Server: Extract the other person's interest, concern, and emotional tone.

[1700] Use of emotion engine

[1701] Step 1:

[1702] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, it identifies the user's current emotional state (joy, anxiety, excitement, etc.) by detecting positive and negative expressions.

[1703] Step 2:

[1704] Server: The analysis results from the emotion engine are stored in a database and used for future advice and planning.

[1705] Providing advice and training

[1706] Step 1:

[1707] Server: Based on the analysis results, the server generates advice and training content tailored to the user. Taking into account the results of the emotion engine, the server provides specific advice, such as "When the other person talks about a movie, suggest going to see it together."

[1708] Step 2:

[1709] Server: Sends the generated advice to the device.

[1710] Step 3:

[1711] Device: Displays received advice and training content to the user.

[1712] Step 4:

[1713] Users: Review advice and training and apply it to their next conversation or date.

[1714] Date plan suggestions

[1715] Step 1:

[1716] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[1717] Step 2:

[1718] Terminal: Sends the entered conditions to the server.

[1719] Step 3:

[1720] Server: Generates the optimal date plan taking into account the conditions, the user's preferences, and the results of the emotion engine.

[1721] Step 4:

[1722] Server: Sends the proposed date plan to the device.

[1723] Step 5:

[1724] Device: Display date plans to the user.

[1725] Gathering and implementing feedback

[1726] Step 1:

[1727] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[1728] Step 2:

[1729] User: Enters date feedback and taps submit.

[1730] Step 3:

[1731] Device: Sends feedback to the server.

[1732] Step 4:

[1733] Server: Stores the collected feedback and incorporates it into the next proposal.

[1734] Continuous learning with emotion engine

[1735] Step 1:

[1736] Emotion engine: Improves analysis accuracy while taking feedback into consideration. For example, based on feedback such as "I was very satisfied with this date suggestion," the effectiveness of emotion-based suggestions can be further improved.

[1737] This will enable the system to increase users' chances of finding love and help them form efficient and effective partnerships.The use of an emotion engine will enable the system to provide more personalized advice and plans that are in line with the user's emotional state, which is expected to improve the user experience.

[1738] Example 2

[1739] 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."

[1740] Conventional matchmaking systems simply collect user information and recommend potential partners based on that information. They lack the ability to provide personalized advice or date plans that take into account data such as the user's emotional state and conversation logs. This makes it difficult to improve the user experience and effectively support users in increasing their chances of finding love. The present invention aims to solve this problem by providing personalized suggestions that take into account the user's information and emotional state.

[1741] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1742] In this invention, the server includes means for collecting and storing user information, means for recommending optimal matches based on the user information, means for analyzing the user's conversation records and posted content to generate appropriate advice, means for analyzing the user's emotional state to personalize the advice and date plans, and means for proposing date plans for the user. This makes it possible to not only recommend matches that meet the user's expectations, but also to provide specific and personalized advice and date plans that are tailored to each individual user.

[1743] "User information" refers to data such as profile information, hobby information, and relationship goals entered when using the system.

[1744] "Storage means" refers to a device or system that has the function of storing collected user information in a storage device such as a database.

[1745] "Means for recommending matching partners" refers to a system that selects the most suitable partner from a database based on the user's information and notifies the user of the results.

[1746] "Conversation records" refer to the content of conversations that users have on the system.

[1747] "Posted content" refers to the content of text, comments, updates, etc. posted by users on social media or the system.

[1748] "Means of analysis" refers to a system that uses natural language processing and sentiment analysis techniques to analyze user tendencies and emotions from conversation records and posted content.

[1749] "Means for generating appropriate advice" refers to a system that automatically generates advice and suggested actions that are useful to users based on the analysis results.

[1750] "Means for analyzing emotional state" refers to a system that determines a user's positive or negative emotional state from their conversation records and posted content.

[1751] "Means for proposing date plans" refers to a system that automatically designs and proposes optimal date itineraries based on user information and analysis results.

[1752] "Means for collecting feedback" refers to a system that allows users to input and record their evaluations and impressions of dates and proposals.

[1753] "Means of reflecting this in the next proposal" refers to a system that uses the collected feedback to improve and optimize future advice and proposals.

[1754] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. By combining this system with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and plans based on that analysis.

[1755] Configuration overview

[1756] This system consists of a server, terminals, and users.

[1757] Server: Collects, stores, analyzes, and provides recommendations based on information. Server software includes databases (e.g., MySQL), natural language processing (NLP) engines (e.g., Google Natural Language API), and emotion engines (e.g., IBM Watson Emotional Analysis).

[1758] Terminal: Provides an interface with the user. Terminals are general information devices such as smartphones and PCs.

[1759] User: Uses the system to enter information and receive suggestions.

[1760] Collection and storage of user information

[1761] User: Launch the app from a smartphone or PC and enter necessary information such as name, age, hobbies, and romantic goals when registering for the first time. For example, enter data such as "Ichiro Tanaka, 30 years old, reading, looking for a marriage partner."

[1762] Terminal: Sends this input information to the server.

[1763] Server: Save the received user information in a database. For example, create a table called "User Information" in a MySQL database and store data in each field.

[1764] Matching partner recommendations

[1765] Server: Queries the database based on the user's profile and preferences to select the most suitable match. For example, if Ichiro Tanaka's hobby is "reading" and his goal is "finding a marriage partner," the server will select candidates with the same hobbies and goals.

[1766] Server: Sends a list of selected match candidates to the device. The list includes information such as the match's name, hobbies, and photo.

[1767] On your device: The profile of the recommended person will be displayed to you.

[1768] User: View the recommended person and select "Like" or "Dislike." For example, by pressing the "♡" button next to the person's profile, you can register them as "Like."

[1769] Terminal: Sends the user's selection to the server.

[1770] Server: The selection results are stored in a database and used to improve the recommendation algorithm in the future.

[1771] Analysis of conversation logs and social media posts

[1772] Device: The device periodically sends the user's conversation logs and social media posts to the server. For example, it collects conversation history within a chat app and public posts on social media.

[1773] Server: Analyzes collected logs and posts using a natural language processing (NLP) engine. Specifically, it uses the Google Natural Language API to analyze various texts.

[1774] Server: Extracts the other person's interests, concerns, and emotional tone. For example, it obtains information such as "Today's posts contain many words like 'fun' and 'happy'."

[1775] Use of emotion engine

[1776] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, if a user posts, "I'm feeling great today," the emotion engine will identify this as a positive emotion.

[1777] Example: Detecting positive sentiment from posts such as "I'm feeling great today."

[1778] Providing advice and training

[1779] Server: Based on the analysis results, the server generates advice and training content tailored to the user. It also takes into account the results of the emotion engine to create specific advice. For example, it provides advice such as, "When the other person talks about a movie, suggest going to see it together."

[1780] Server: Sends the generated advice to the device.

[1781] Device: Displays received advice and training content to the user.

[1782] Users: Review advice and training and apply it to their next conversation or date.

[1783] Date plan suggestions

[1784] User: Requests date plan suggestions and enters criteria such as location, budget, date, etc. For example, "Shibuya, under 5,000 yen, Saturday afternoon."

[1785] Terminal: Sends the entered conditions to the server.

[1786] Server: Based on the input conditions, the server generates the optimal date plan based on the user's preferences and the results of the emotion engine. For example, it suggests "lunch at a cafe in Shibuya and then watch a movie."

[1787] Server: Sends the proposed date plan to the device.

[1788] Device: Display date plans to the user.

[1789] Gathering and implementing feedback

[1790] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date. For example, the device displays questions such as, "How satisfied were you with the date?"

[1791] User: Enter your feedback and tap the submit button. For example, "Satisfaction rating: 8 / 10."

[1792] Device: Sends feedback to the server.

[1793] Server: Store the collected feedback in a database and use it to make the next recommendation. For example, store satisfaction in a "Dating Experience" table.

[1794] Continuous learning with emotion engine

[1795] Emotion engine: Improves analysis accuracy while taking into account feedback. For example, improves the effectiveness of emotion-based suggestions based on information such as "This date suggestion was very satisfying."

[1796] This allows the system to increase the user's chances of finding love. By using a generative AI model and specific prompts, it is possible to provide more advanced advice and plans. A specific example would be to input the user's past conversation logs into the generative AI model to perform a deep analysis of emotional fluctuations.

[1797] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1798] Step 1:

[1799] User: Launch the app from a smartphone or PC and enter the necessary information such as name, age, hobbies, and relationship goals when registering for the first time. For example, enter data such as "Suzuki Hanako, 28 years old, traveling, looking for a marriage partner."

[1800] Input: Profile information, hobbies, relationship goals, etc. that you enter into the app.

[1801] Output: Input information is sent to the device and converted into a format for storage on the server.

[1802] Step 2:

[1803] Device: The entered user information is sent to the server. This operation is performed by pressing the "Register" button in the app.

[1804] Input: User information (name, age, hobbies, love goals, etc.)

[1805] Output: User information is sent to the server.

[1806] Step 3:

[1807] Server: Save the received user information in a database. For example, create a table called "User Information" in a MySQL database and store data in each field.

[1808] Input: User information sent from the terminal

[1809] Output: User information is saved in the database.

[1810] Step 4:

[1811] Server: Queries the database based on the user's profile and preferences to select the most suitable match. For example, based on information such as "Suzuki Hanako loves traveling and is looking for a marriage partner," it selects candidates with the same hobbies and goals.

[1812] Input: User information (profile, hobbies, relationship goals)

[1813] Output: A list of potential matches is generated.

[1814] Step 5:

[1815] Server: Sends a list of selected match candidates to the device, including information such as the matchee's name, hobbies, and photo.

[1816] Input: A list of possible matches

[1817] Output: A list of potential matches is sent to the device.

[1818] Step 6:

[1819] On your device: The profile of the recommended person will be displayed to you. It will be displayed on the "Matching Candidates" screen in the app.

[1820] Input: A list of match candidates sent by the server

[1821] Output: Information that is visually displayed to the user (profile, photo, etc.).

[1822] Step 7:

[1823] User: View the recommended person and select "Like" or "Dislike." For example, by pressing the "♡" button next to the person's profile, you can register them as "Like."

[1824] Input: User's choice (like it or not)

[1825] Output: The selections are logged to the terminal.

[1826] Step 8:

[1827] Terminal: Sends the user's selection to the server.

[1828] Input: User selection

[1829] Output: The selection results are sent to the server.

[1830] Step 9:

[1831] Server: The selection results are stored in a database to help improve the recommendation algorithm in the future, for example in a "User Behavior History" table.

[1832] Input: User selection

[1833] Output: The selection results are saved in a database and added to the data used for analysis.

[1834] Step 10:

[1835] Device: The device periodically sends the user's conversation logs and social media posts to the server. For example, it collects conversation history within a chat app and public posts on social media.

[1836] Input: Conversation logs, social media posts

[1837] Output: Conversation logs and SNS posts are transferred to the server.

[1838] Step 11:

[1839] Server: Analyzes collected logs and posts using a natural language processing (NLP) engine. Specifically, analysis is performed using the Google Natural Language API.

[1840] Input: Conversation logs, social media posts

[1841] Output: Data about the user's emotional state and interests is generated.

[1842] Step 12:

[1843] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, if a user posts, "I'm feeling great today," the emotion engine will identify this as a positive emotion.

[1844] Input: Conversation logs, social media posts

[1845] Output: The user's emotional state (positive, negative, etc.). Example: A post saying "I'm feeling great today" is judged to have a positive emotion.

[1846] Step 13:

[1847] Server: Based on the analysis results, the server generates advice and training content tailored to the user. It also takes into account the results of the emotion engine to provide specific advice. For example, it creates advice such as "When the other person talks about a movie, suggest going to see it together."

[1848] Input: Analysis results, emotion engine results

[1849] Output: Generate specific advice and training content

[1850] Step 14:

[1851] Server: Sends the generated advice to the device.

[1852] Input: Generated advice and training content

[1853] Output: Advice and training content are transferred to the device.

[1854] Step 15:

[1855] On your device: Displaying received advice and training content to you, for example in the "Advice" section within the app.

[1856] Input: Advice and training content sent

[1857] Output: Visually displayed advice and training content

[1858] Step 16:

[1859] Users: Review advice and training and apply it to their next conversation or date.

[1860] Input: Received advice, training content

[1861] Output: Advice implementation reflected in actual behavior

[1862] Step 17:

[1863] User: Requests date plan suggestions and enters criteria such as location, budget, date, etc. For example, "Shibuya, under 5,000 yen, Saturday afternoon."

[1864] Input: Date plan conditions (location, budget, date, etc.)

[1865] Output: The condition is sent to the terminal and forwarded to the server.

[1866] Step 18:

[1867] Terminal: Sends the entered conditions to the server.

[1868] Input: Date plan conditions

[1869] Output: The condition is sent to the server.

[1870] Step 19:

[1871] Server: Based on the input conditions, the server generates the optimal date plan based on the user's preferences and the results of the emotion engine. For example, it suggests "lunch at a cafe in Shibuya and then watch a movie."

[1872] Input: Date plan conditions, preference information, emotion engine results

[1873] Output: Proposed date plan

[1874] Step 20:

[1875] Server: Sends the proposed date plan to the device.

[1876] Enter: Date plan

[1877] Output: The date plan is sent to the device.

[1878] Step 21:

[1879] Device: Display date plans to the user.

[1880] Input: Date plan sent from the server

[1881] Output: A visual representation of the date plan

[1882] Step 22:

[1883] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date. For example, the device displays questions such as, "How satisfied were you with the date?"

[1884] Input: Feedback Question

[1885] Output: Feedback survey displayed to the user

[1886] Step 23:

[1887] User: Enter your feedback and tap the submit button. For example, "Satisfaction rating: 8 / 10."

[1888] Input: Date feedback (impressions, ratings, etc.)

[1889] Output: Feedback information is sent to the terminal.

[1890] Step 24:

[1891] Device: Sends feedback to the server.

[1892] Input: Feedback information entered by the user

[1893] Output: The feedback information is sent to the server.

[1894] Step 25:

[1895] Server: Stores the collected feedback in a database and uses it to improve future recommendations. For example, satisfaction is stored in a "Dating Experience" table.

[1896] Input: Feedback information

[1897] Output: Saved feedback information, data to be reflected in the next proposal

[1898] Step 26:

[1899] Emotion engine: Improves analysis accuracy while taking into account feedback. For example, improves the effectiveness of emotion-based suggestions based on information such as "This date suggestion was very satisfying."

[1900] Input: Feedback information

[1901] Output: Improved analysis accuracy and improved proposal accuracy based on that.

[1902] (Application example 2)

[1903] 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."

[1904] Conventional online shopping sites lack personalized product recommendations based on users' emotions and preferences, making it difficult for users to find the products that are best suited to them. Furthermore, they lack a system for effectively incorporating user feedback, making it difficult to make continuous improvements.

[1905] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing user information, means for recommending optimal products based on the user information, means for analyzing the user's conversation log and posted content and generating appropriate advice, and means for suggesting product information and sale information to the user. This enables personalized product recommendations based on the user's emotions and preferences, improving the user's purchasing experience. In addition, analyzing user feedback and reflecting it in the next recommendation content enables continuous system improvement.

[1906] "User information" refers to information including the profile information, purchase history, and browsing history of the user of the online shopping site.

[1907] "Means of collecting and storing" refers to the means of sending the information provided by the user to the server and storing it in a database.

[1908] "Means for recommending optimal products" refers to means for selecting and recommending the product that best suits a user based on the user's information.

[1909] "Means for analyzing conversation logs and posted content" refers to means for analyzing the conversations and social media posts of users and understanding their emotions and interests from the content.

[1910] The "means for generating appropriate advice" is a means for generating advice for presenting product recommendations and sale information suited to a user based on analyzed user information.

[1911] The "means for suggesting product information and sale information" is a means for displaying appropriate product information and sale information to the user based on the generated advice.

[1912] The "means for collecting and storing feedback" refers to a means for collecting impressions and ratings provided by users after purchase and storing them on a server.

[1913] "Means for analyzing feedback and reflecting it in the next recommendation" refers to means for analyzing collected feedback information and using it to improve the recommendation content from the next time onwards.

[1914] "Profile information" refers to information that includes personal information such as a user's name, age, gender, and hobbies.

[1915] "Purchase history" is information that includes a record of products that a user has purchased in the past.

[1916] "Browsing history" is information that includes a record of products and pages that a user has viewed in the past.

[1917] "Means for providing appropriate product recommendations and training based on analysis" refers to means for providing users with appropriate product recommendations, usage instructions, and related training content based on the analysis results.

[1918] Overall system configuration

[1919] This invention is a system that collects and analyzes user information, recommends optimal products, and provides appropriate advice and product information. The system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and product information based on that.

[1920] Collection and storage of user information

[1921] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, purchase history, browsing history, etc.).

[1922] Terminal: Sends the entered information to the server.

[1923] Server: Stores the received user information in a database.

[1924] Product Recommendations

[1925] Server: Uses a recommendation algorithm to select the most suitable products from a database based on the user's profile and purchasing history.

[1926] Server: Sends the selected product to the device.

[1927] Device: Display recommended product information to the user.

[1928] Analysis of conversation logs and social media posts

[1929] Device: The user's conversation log and social media posts are periodically sent to the server.

[1930] Server: A natural language processing (NLP) engine (e.g., Google Cloud Natural Language API) and a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) are used to analyze the collected logs and posts.

[1931] Server: Extracts emotional tone and stores it as data for recommending optimal products.

[1932] Providing advice and product information

[1933] Server: Based on the analysis results, the server generates advice and product information tailored to the user. For example, it generates specific advice such as "If a user mentions in a recent post that they like flowers, provide them with information about sale items for flower arrangements."

[1934] Server: Sends the generated advice to the device.

[1935] Terminal: Displays received advice and product information to the user.

[1936] Gathering and implementing feedback

[1937] Device: After purchasing a product, a feedback survey is sent to the user, asking them to enter their impressions and ratings.

[1938] User: Enters feedback about a purchased item and taps the submit button.

[1939] Device: Sends feedback to the server.

[1940] Server: Stores the collected feedback and uses it to improve future recommendations.

[1941] Continuous learning with emotion engine

[1942] Emotion engine: Improves analysis accuracy while taking feedback into account. For example, feedback such as "very satisfied" can be used to improve the effectiveness of suggestions based on further emotion recognition.

[1943] Server: Train a new product recommendation model using the sentiment data.

[1944] Specific examples

[1945] Example prompts to input to the generative AI model

[1946] Prompt: "A user recently posted on social media, 'I'm in a great mood today, so I bought some flowers!' What product recommendations would you give them?"

[1947] This system enables personalized product recommendations based on the user's emotions and preferences, improving the user's purchasing experience. Furthermore, by analyzing user feedback and reflecting it in the next recommendation, the system can be continuously improved.

[1948] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1949] Step 1:

[1950] When a user launches the app from a device such as a smartphone or PC, they enter the necessary information for initial registration (name, age, purchase history, browsing history, etc.), and the device sends this information to the server. The input data includes name, age, purchase history, and browsing history, and is saved in a database.

[1951] Step 2:

[1952] The server stores the received user information in a database and then stores the user information in an integrated database at the specified timing. This process accumulates the user's basic information and behavioral history data.

[1953] Step 3:

[1954] The server selects products from a database using an optimal recommendation algorithm based on the user's profile and purchase history, generates a list of recommended products as output, and sends it to the terminal.

[1955] Step 4:

[1956] The terminal displays the received recommended product list to the user, who then confirms the recommended products. The terminal records the user's choice (whether to purchase or not) and sends it to the server.

[1957] Step 5:

[1958] The device periodically sends the user's conversation log and social media posts to the server. These conversation logs and posts serve as input data for analysis.

[1959] Step 6:

[1960] The server uses a natural language processing (NLP) engine and a sentiment analysis engine to analyze the collected conversation logs and posted content. For example, it uses the Google Cloud Natural Language API to extract emotional tones from text and stores the analysis results in a database.

[1961] Step 7:

[1962] The server generates advice and product information tailored to the user based on the analysis results. For example, it generates specific advice such as "If a user mentions in a recent post that they like flowers, provide them with information about sale items for flower arrangements."

[1963] Step 8:

[1964] The server sends the generated advice and product information to the terminal, which then displays it to the user, who then checks the displayed advice and product information.

[1965] Step 9:

[1966] After a product is purchased, the terminal sends a feedback survey to the user, prompting them to enter their impressions and evaluations. The input data includes the user's satisfaction with the purchased product and their impressions of use.

[1967] Step 10:

[1968] The user inputs the feedback and taps the send button, and the terminal transmits the user's feedback data to the server.

[1969] Step 11:

[1970] The server stores the collected feedback in a database and uses it to improve the recommendation algorithm for the next step. Based on the analysis of the feedback, a new product recommendation model is trained.

[1971] Step 12:

[1972] The emotion engine uses feedback to improve analysis accuracy. For example, feedback such as "very satisfied" can be used to improve the effectiveness of suggestions based on further emotion recognition.

[1973] In this way, the system can provide personalized product recommendations based on users' emotions and preferences, and achieve continuous improvement by incorporating effective feedback.

[1974] 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.

[1975] 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.

[1976] 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.

[1977] [Fourth embodiment]

[1978] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1979] 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.

[1980] 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).

[1981] 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.

[1982] 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.

[1983] 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).

[1984] 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.

[1985] 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.

[1986] 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.

[1987] 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.

[1988] 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.

[1989] 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.

[1990] 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."

[1991] The present invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans.

[1992] Overall system configuration

[1993] This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and provides suggestions for information, while the terminal provides an interface for users. Users use the system to input information and receive suggestions.

[1994] Collection and storage of user information

[1995] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, hobbies, relationship goals, etc.).

[1996] Terminal: Sends the entered information to the server.

[1997] Server: Stores the received information in a database.

[1998] Matching partner recommendations

[1999] Server: Uses the user's profile and preferences to select the most suitable match from the database.

[2000] Server: Sends the selected matching candidates to the device.

[2001] Device: The profile of the recommended person is displayed to the user for confirmation.

[2002] User: View the recommended people and select "Like" or "Dislike."

[2003] Terminal: Sends the selection results to the server.

[2004] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[2005] Analysis of conversation logs and social media posts

[2006] Device: The user's conversation log and social media posts are periodically sent to the server.

[2007] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content, extracting the other person's interests, concerns, and emotional tone.

[2008] Example: For example, if a user talks a lot about movies and music, the system can analyze that information and determine that the other person is likely interested in movies and music.

[2009] Providing advice and training

[2010] Server: Based on the analysis results, the server generates advice and training tailored to the user. For example, it provides advice such as "Talk about the other person's favorite movie in your next conversation."

[2011] Server: Sends the generated advice to the device.

[2012] Terminal: Display the received advice to the user.

[2013] User: Check out the advice and apply it to your next conversation or date.

[2014] Date plan suggestions

[2015] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[2016] Terminal: Sends the entered conditions to the server.

[2017] Server: Generates optimal date plans based on the conditions and the user's preferences. For example, it suggests restaurants and events.

[2018] Server: Sends the proposed date plan to the device.

[2019] Device: Display date plans to the user.

[2020] Gathering and implementing feedback

[2021] Device: After the date, users are sent a feedback survey and asked to enter their impressions and evaluation of the date.

[2022] User: Enter your feedback and tap the submit button.

[2023] Device: Sends feedback to the server.

[2024] Server: Stores the collected feedback and incorporates it into the next proposal.

[2025] This enables the system to increase users' chances of success in love and help them form efficient and effective partnerships.

[2026] The processing flow will be explained below.

[2027] Collection and storage of user information

[2028] Step 1:

[2029] User: Launch the app and enter user information (name, age, hobbies, relationship goals, etc.).

[2030] Step 2:

[2031] Terminal: Sends the entered information to the server.

[2032] Step 3:

[2033] Server: Stores the received user information in a database.

[2034] Matching partner recommendations

[2035] Step 1:

[2036] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[2037] Step 2:

[2038] Server: Sends the selected matching candidates to the device.

[2039] Step 3:

[2040] On your device: The profile of the recommended person will be displayed to you.

[2041] Step 4:

[2042] User: View the recommended people and select "Like" or "Dislike."

[2043] Step 5:

[2044] Terminal: Sends the user's selection to the server.

[2045] Step 6:

[2046] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[2047] Analysis of conversation logs and social media posts

[2048] Step 1:

[2049] Device: The user's conversation log and SNS postings are periodically sent to the server.

[2050] Step 2:

[2051] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[2052] Step 3:

[2053] Server: Extract the other person's interest, concern, and emotional tone.

[2054] Providing advice and training

[2055] Step 1:

[2056] Server: Based on the analysis results, it generates advice and training content tailored to the user.

[2057] Step 2:

[2058] Server: Sends the generated advice to the device.

[2059] Step 3:

[2060] Device: Displays received advice and training content to the user.

[2061] Step 4:

[2062] Users: Review advice and training and apply it to their next conversation or date.

[2063] Date plan suggestions

[2064] Step 1:

[2065] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[2066] Step 2:

[2067] Terminal: Sends the entered conditions to the server.

[2068] Step 3:

[2069] Server: Generates the optimal date plan taking into account the conditions and the user's preferences.

[2070] Step 4:

[2071] Server: Sends the proposed date plan to the device.

[2072] Step 5:

[2073] Device: Display date plans to the user.

[2074] Gathering and implementing feedback

[2075] Step 1:

[2076] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[2077] Step 2:

[2078] User: Enters date feedback and taps submit.

[2079] Step 3:

[2080] Device: Sends feedback to the server.

[2081] Step 4:

[2082] Server: Stores the collected feedback and incorporates it into the next proposal.

[2083] Example 1

[2084] 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."

[2085] In conventional matchmaking systems, the collection and storage of user information, the recommendation of potential matches, and the generation of advice are often carried out separately, resulting in a lack of integration as a whole system. Furthermore, insufficient analysis of users' conversation logs and social media posts can lead to issues such as inappropriate advice not being provided and date plan suggestions not matching the user's preferences or requirements. Furthermore, there are also issues with inefficient collection and reflection of feedback, which means that improvements are not incorporated into future proposals.

[2086] 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.

[2087] In this invention, the server includes means for collecting and storing user information, means for recommending optimal matches based on the user information, means for analyzing the user's conversation log and postings and generating appropriate advice using a natural language processing engine, and means for proposing date plans that meet the user's requirements. This enables integrated management of user information, providing highly accurate matching and advice, and proposing date plans that meet the user's preferences and requirements. Furthermore, by collecting feedback and analyzing it using a machine learning algorithm, it is possible to continuously improve the recommendation algorithm and reflect this in future recommendations.

[2088] A "user" is an individual who uses the system and provides information such as personal information, hobbies, preferences, and romantic intentions.

[2089] "Means of collecting and storing information" refers to various functions for storing information provided by users, such as personal information, hobbies, preferences, and romantic intentions, in a database.

[2090] "Means for recommending matching partners" refers to algorithms and functions that select the most suitable partner based on the user's information and provide that information to the user.

[2091] "Means for analyzing conversation logs and posted content" refers to the function of analyzing users' conversation logs and SNS posts using a natural language processing engine, etc., and generating appropriate advice for users based on the results obtained.

[2092] A "natural language processing engine" is a software engine that analyzes text data and extracts meaning, emotion, topics, etc.

[2093] "Means for generating advice" refers to a function that generates and provides appropriate advice on actions and conversations to users based on the analysis results.

[2094] "Means for proposing date plans" refers to a function that generates an appropriate date plan based on the conditions provided by the user (location, budget, date and time, etc.) and proposes it to the user.

[2095] "Means for collecting and storing feedback" refers to a function for storing feedback provided by users, such as impressions and ratings after a date, in a database.

[2096] A "machine learning algorithm" is an algorithm that analyzes feedback data and learns to improve the accuracy of future suggestions and recommendation algorithms.

[2097] "Profile Information" refers to a user's basic personal information (such as name, age, etc.).

[2098] "Interest information" refers to information about a user's interests, hobbies, and preferences.

[2099] "Love goals" refers to the objectives that users want to achieve in love (e.g., serious relationship, finding friends, etc.).

[2100] "Generation policy" refers to guidelines and standards for providing optimal advice and training to users based on the analysis results.

[2101] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions.

[2102] Collection and storage of user information

[2103] Users start the application from a device such as a smartphone or PC and enter initial registration information such as their name, age, hobbies, and romantic interests. The device then sends the collected information to the server, which then stores the received information in a database. Data is sent in JSON or XML format, and is securely transmitted via HTTPS requests.

[2104] Matching partner recommendations

[2105] The server uses an algorithm to select the most suitable match based on the user's profile and preferences. The algorithm uses KNN (nearest neighbor search) and collaborative filtering to select candidates with many similarities. The selected match candidates are sent from the server to the device, which displays the information to the user. The user looks at the recommended partners and selects either "like" or "dislike," and sends the result to the server via the device. The server stores the selection results in a database and uses them to improve the recommendation algorithm in the future.

[2106] Analysis of conversation logs and social media posts

[2107] The device periodically sends the user's conversation log and social media posts to a server. The server then analyzes the collected data using a natural language processing (NLP) engine. Libraries such as spaCy and NLTK are used for this analysis. The analysis extracts the other person's interests, concerns, and emotional tone. Specifically, if the user talks a lot about movies and music, the system determines that the other person is likely to be interested in these subjects.

[2108] Providing advice and training

[2109] The server generates optimal advice and training for the user based on the results of NLP analysis. A generative AI model (e.g., GPT-3) is used for this generation. For example, advice such as "Talk about the other person's favorite movie in your next conversation" may be provided. The generated advice is sent from the server to the device, which displays it to the user. The user can confirm the advice and put it into practice in their next conversation or date.

[2110] Date plan suggestions

[2111] The user requests a date plan proposal and enters conditions (location, budget, date and time, etc.). These conditions are sent from the device to the server. The server generates the optimal date plan taking into account the conditions and the user's preferences. For example, it may suggest restaurants or events. To generate this plan, it references various APIs and databases to select a plan that meets the user's conditions. The generated date plan is sent from the server to the device, which then displays it to the user.

[2112] Gathering and implementing feedback

[2113] After the date, the device sends the user a feedback survey. The user enters their impressions and evaluation of the date and taps the send button. The collected feedback is sent from the device to the server, which stores it in a database. The server then analyzes this feedback data using a machine learning algorithm and reflects it in future recommendations. This allows for continuous improvement of the recommendation algorithm.

[2114] Prompt Sentence Examples

[2115] Examples of prompts with examples include:

[2116] "User A is a 35-year-old man whose hobbies are watching movies and hiking. After he enters his profile, please explain how the system recommends his best matches. Also, please explain the specific process of providing advice and proposing date plans."

[2117] This prompt is fed into a generative AI model, which then provides a concrete explanation of the overall flow of the system.

[2118] The above is a form for implementing the present invention, and this system can increase the user's success rate in romance and support the formation of efficient and effective partnerships.

[2119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2120] Step 1:

[2121] Input: The user launches the application from their smartphone or computer and enters their initial registration information (name, age, hobbies, and romantic intent).

[2122] Action: The user fills in the application's registration form and presses the submit button.

[2123] Terminal: The input information is packaged in JSON or XML format and sent to the server via an HTTPS request.

[2124] Output: Personal information sent to the server.

[2125] Step 2:

[2126] Input: User information sent from the device in step 1.

[2127] How it works: The server parses the incoming data and stores the information in a database using SQL queries, typically MySQL or PostgreSQL.

[2128] Server: Inserts and stores the received information into a database.

[2129] Output: User information stored in the database.

[2130] Step 3:

[2131] Input: User profile and interest information stored in a database.

[2132] How it works: The server uses KNN (Knowledge Neighborhood Search) and collaborative filtering algorithms to select the best match.

[2133] Server: Packages the selection results in JSON format and sends them to the terminal.

[2134] Output: Match candidate information sent to the device.

[2135] Step 4:

[2136] Input: Match candidate information sent from the server.

[2137] What it does: The device displays profiles of potential matches to the user, using a list view or card layout.

[2138] Terminal: Displays the selection results to the user.

[2139] Output: Match candidate information displayed to the user.

[2140] Step 5:

[2141] Input: The match candidate information displayed to the user.

[2142] How it works: The user selects "like" or "dislike" and the result is sent from the device to the server.

[2143] User: Look at the recommended partners and make a selection.

[2144] Terminal: The selection results are packaged in JSON format and sent to the server.

[2145] Output: The selection results sent to the server.

[2146] Step 6:

[2147] Input: The selection sent from the terminal in step 5.

[2148] How it works: The server analyzes the selection results, stores them in a database, and uses them to improve the recommendation algorithm in the future.

[2149] Server: Records preference data and uses it as training data for recommendation algorithms.

[2150] Output: Selection results stored in a database.

[2151] Step 7:

[2152] Input: User conversation logs and social media posts.

[2153] How it works: The device periodically sends conversation logs and social media posts in JSON format to the server.

[2154] Terminal: Collects log data, packages it, and sends it to the server.

[2155] Output: Conversation logs and SNS posting data sent to the server.

[2156] Step 8:

[2157] Input: Conversation logs and social media post data sent in step 7.

[2158] How it works: The server performs the analysis using a natural language processing (NLP) engine (e.g. spaCy or NLTK).

[2159] Server: Performs sentiment analysis and key phrase extraction using collected data.

[2160] Output: Areas of interest and emotional tone derived from the analysis.

[2161] Step 9:

[2162] Input: NLP analysis results.

[2163] How it works: The server generates appropriate advice and training content based on the analysis results. It uses a generative AI model (e.g., GPT-3).

[2164] Server: Utilizes generative AI models to generate personalized advice.

[2165] Output: The generated advice and training content.

[2166] Step 10:

[2167] Input: Generated advice and training content.

[2168] Operation: The server sends advice to the device.

[2169] Server: Packages advice in JSON format and sends it to the device.

[2170] Output: Advice sent to the terminal.

[2171] Step 11:

[2172] Input: Advice sent by the server.

[2173] What it does: The device displays advice to the user, using a pop-up message or notification bar.

[2174] Terminal: Presents advice to the user.

[2175] Output: The advice displayed to the user.

[2176] Step 12:

[2177] Input: The date plan conditions requested by the user (location, budget, date and time).

[2178] Operation: The device sends the conditions in JSON format to the server.

[2179] User: Enter the conditions for the date plan.

[2180] Terminal: Packages and sends the conditions.

[2181] Output: Dateplan conditions sent to the server.

[2182] Step 13:

[2183] Input: Date plan conditions and user preferences.

[2184] How it works: The server generates the optimal date plan based on the conditions and preferences. It does so by referencing various APIs and databases.

[2185] Server: Searches a database of restaurants and events and selects plans that match your criteria.

[2186] Output: The generated date plan.

[2187] Step 14:

[2188] Input: Date plan sent from the server.

[2189] How it works: The server sends the plan to the device, packaging it in JSON format.

[2190] Server: Sends the generated date plan to the device.

[2191] Output: The date plan sent to the device.

[2192] Step 15:

[2193] Input: Date plan information sent from the server.

[2194] Action: The device displays the date plan to the user. Use the details page.

[2195] Device: Display date plans.

[2196] Output: The date plan displayed to the user.

[2197] Step 16:

[2198] Input: Post-date feedback survey.

[2199] Operation: The device sends a survey to the user via push notification. The user fills out the survey and presses the send button.

[2200] Terminal: Collects surveys and sends them to the server.

[2201] Output: Feedback data sent to the server.

[2202] Step 17:

[2203] Input: Feedback data collected in step 16.

[2204] How it works: The server stores the feedback data in a database and analyzes it using machine learning algorithms.

[2205] Server: Updates the recommendation algorithm based on the feedback data and reflects it in the next proposal.

[2206] Output: Analysis results stored in a database and updated recommendation algorithms.

[2207] The above is the specific processing flow of the system program.

[2208] (Application example 1)

[2209] 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."

[2210] Conventional content distribution services have recommended limited content based on users' past viewing history and preferences. This has made it difficult for users to efficiently discover diverse new content that interests them. Furthermore, the provision of appropriate viewing schedules and advice has been insufficient, preventing users from maximizing their viewing experience. The present invention aims to solve these problems and improve user satisfaction by providing individually customized content recommendations and viewing advice to users.

[2211] 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.

[2212] In this invention, the server includes means for collecting and storing user information, means for recommending optimal content, means for analyzing user conversation logs and posted content to generate appropriate advice, and means for proposing viewing schedules, thereby enabling users to efficiently discover a variety of new content that interests them and receive appropriate viewing schedules and advice.

[2213] "User information" is a collective term for profile information, preference information, and viewing history collected when using the system.

[2214] "Storage means" refers to a function for storing collected user information in a storage device such as a database.

[2215] "Recommendation means" is a function that selects and suggests the most appropriate content based on saved user information.

[2216] "Conversation log" refers to the text messages and communication history entered by the user.

[2217] "Posted content" refers to comments and feedback posted by users on social media or review sites.

[2218] "Means of analysis" refers to a function that analyzes conversation logs and posted content using natural language processing technology, etc., to extract users' hobbies and interests.

[2219] The "means for generating advice" is a function that automatically generates appropriate content and viewing advice for users based on the analysis results.

[2220] The "means for proposing a viewing schedule" is a function that proposes an optimal content viewing schedule based on the user's lifestyle and past viewing patterns.

[2221] "Feedback" refers to opinions such as ratings and impressions of content viewed by users.

[2222] "Means of reflection" is a function that analyzes collected feedback and uses it to recommend content or generate advice next time.

[2223] The present invention is embodied as a personalized video recommendation system for use in a content distribution service. The system is mainly composed of a server, a terminal, and a user, and is realized by the following means and processing steps.

[2224] Overall system configuration

[2225] This system consists of a client terminal (e.g., a smartphone) and a server. The server collects, stores, analyzes, and recommends information, while the terminal provides an interface with the user. The user also uses the system to input information and receive suggestions.

[2226] Collection and storage of user information

[2227] User: Launches the smartphone app and enters information such as name, age, hobbies, and viewing history when registering for the first time.

[2228] Terminal: Sends collected user information to the server.

[2229] Server: Stores the received information in a database, which is used for future data analysis and to improve recommendation algorithms.

[2230] Content Recommendations

[2231] Server: Selects the most suitable video content from the database based on the user's profile, preferences, and viewing history. For example, if a user likes sci-fi movies, it will recommend new and highly rated movies in the sci-fi genre.

[2232] Device: A list of recommended content is displayed to the user, who can select "Like" or "Dislike."

[2233] Server: Stores the user's selections and uses them to improve the recommendation algorithm in the future.

[2234] Analysis of conversation logs and postings

[2235] Device: The user's conversation log and social media posts are periodically sent to the server.

[2236] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content. For example, generative AI models such as spaCy and BERT are used. Through analysis, the user's interests, concerns, and emotional tone are extracted. For example, if a user frequently comments about a particular actor on social media, movies starring that actor can be recommended.

[2237] Advice generation and viewing schedule suggestions

[2238] Server: Based on the analysis results, the server generates advice and viewing schedules tailored to the user. For example, it provides advice such as "This is the next sci-fi movie you should watch."

[2239] Device: The generated advice and schedule are displayed to the user, who can use them to plan their viewing plans.

[2240] Gathering and implementing feedback

[2241] Device: After viewing the content, a feedback survey is sent to the user, in which they are asked to enter their rating and impressions.

[2242] User: Enter feedback and tap submit.

[2243] Device: Sends feedback to the server.

[2244] Server: Stores the collected feedback and uses it to generate the next recommendation or advice.

[2245] This allows the system to improve the user's viewing experience and effectively support the discovery of diverse new content. For example, if a user has a preference for "sci-fi movies," the system will recommend "Interstellar." An example of a prompt is, "Based on the user's viewing history, please generate three new content recommendations."

[2246] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2247] Step 1:

[2248] User: Launches the smartphone app and enters information such as name, age, hobbies, and viewing history when registering for the first time. This provides basic information about the user.

[2249] Step 2:

[2250] Terminal: Sends collected user information to the server. The entered user information is sent as a data packet to the server.

[2251] Step 3:

[2252] Server: Stores the received information in a database. The entered user information is converted into an appropriate format and stored in the database. For example, name, age, hobbies, and viewing history are stored as entries.

[2253] Step 4:

[2254] Server: Selects the most suitable video content from the database using the user's profile, preferences, and viewing history. For example, if a user's hobby is sci-fi movies, the server searches the database to select recommended content from a list of movies in the sci-fi genre.

[2255] Step 5:

[2256] Device: Presents a list of recommended content to the user. Presents a list of selected content in the user interface. This list is generated based on data retrieved from the server.

[2257] Step 6:

[2258] User: View the recommended content list and select "I like it" or "I don't like it." The user's selection becomes the next input.

[2259] Step 7:

[2260] Terminal: Sends the user's selection to the server. The user's selection data is sent to the server as a data packet.

[2261] Step 8:

[2262] Server: Stores user selections and uses them to improve the recommendation algorithm in the future. Stores the selection data in a database and uses it as training data for machine learning models.

[2263] Step 9:

[2264] Device: The device periodically sends the user's conversation logs and SNS posts to the server. The conversation logs and SNS posts recorded by the user become input data and are sent to the server.

[2265] Step 10:

[2266] Server: A natural language processing (NLP) engine is used to analyze the collected conversation logs and posted content. For example, spaCy or BERT is used to analyze and extract the user's interests, concerns, and emotional tone from the input data. The analysis results are used as input for the next process.

[2267] Step 11:

[2268] Server: Based on the analysis results, generate advice and viewing schedules tailored to the user. For example, generate advice such as "This is the next sci-fi movie you should watch." The generated advice becomes the output data.

[2269] Step 12:

[2270] Terminal: The generated advice and schedule are displayed to the user. The advice sent from the server is displayed in the user interface, allowing the user to create a viewing plan based on this.

[2271] Step 13:

[2272] Terminal: After viewing the content, a feedback survey is sent to the user, in which they are asked to enter their evaluation and impressions. Feedback is obtained as input data after viewing.

[2273] Step 14:

[2274] User: Enter feedback and tap the submit button. The feedback is sent from the device as the final input data.

[2275] Step 15:

[2276] Terminal: Sends feedback to the server. Feedback data is sent to the server as a data packet.

[2277] Step 16:

[2278] Server: Stores the collected feedback and uses it to generate the next recommendation or advice. Stores the feedback data in a database and uses it to improve the algorithm next time.

[2279] 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.

[2280] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. Furthermore, by combining it with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and plans based on that.

[2281] Overall system configuration

[2282] This system consists of a server, a terminal, and a user. The server collects, stores, analyzes, and makes suggestions about information, while the terminal provides an interface with the user, who uses the system to input information and receive suggestions. The emotion engine analyzes the user's conversation log and posted content to identify the user's emotional state.

[2283] Collection and storage of user information

[2284] User: Launch the app from a device such as a smartphone or computer and enter the information required for initial registration (name, age, hobbies, relationship goals, etc.).

[2285] Terminal: Sends the entered information to the server.

[2286] Server: Stores the received user information in a database.

[2287] Matching partner recommendations

[2288] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[2289] Server: Sends the selected matching candidates to the device.

[2290] On your device: The profile of the recommended person will be displayed to you.

[2291] User: View the recommended people and select "Like" or "Dislike."

[2292] Terminal: Sends the user's selection to the server.

[2293] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[2294] Analysis of conversation logs and social media posts

[2295] Device: The user's conversation log and social media posts are periodically sent to the server.

[2296] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[2297] Server: Extract the other person's interest, concern, and emotional tone.

[2298] Use of emotion engine

[2299] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, by detecting positive and negative expressions, it identifies the user's current emotional state (joy, anxiety, excitement, etc.).

[2300] Example: If a user posts, "I'm feeling great today," the sentiment engine determines that the user is in a positive mood.

[2301] Providing advice and training

[2302] Server: Based on the analysis results, the server generates advice and training content tailored to the user. Taking into account the results of the emotion engine, the server provides specific advice, such as "When the other person talks about a movie, suggest going to see it together."

[2303] Server: Sends the generated advice to the device.

[2304] Device: Displays received advice and training content to the user.

[2305] Users: Review advice and training and apply it to their next conversation or date.

[2306] Date plan suggestions

[2307] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[2308] Terminal: Sends the entered conditions to the server.

[2309] Server: Generates optimal date plans based on the conditions, the user's preferences, and the results of the emotion engine. For example, if the user is in a positive mood, it may suggest outdoor activities for that day's date.

[2310] Server: Sends the proposed date plan to the device.

[2311] Device: Display date plans to the user.

[2312] Gathering and implementing feedback

[2313] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[2314] User: Enters date feedback and taps submit.

[2315] Device: Sends feedback to the server.

[2316] Server: Stores the collected feedback and incorporates it into the next proposal.

[2317] Continuous learning with emotion engine

[2318] Emotion engine: Improves analysis accuracy while taking feedback into consideration. For example, based on feedback such as "I was very satisfied with this date suggestion," the effectiveness of emotion-based suggestions can be further improved.

[2319] This will enable the system to increase users' chances of finding love and help them form efficient and effective partnerships.The use of an emotion engine will enable the system to provide more personalized advice and plans that are in line with the user's emotional state, which is expected to improve the user experience.

[2320] The processing flow will be explained below.

[2321] Processing steps of a system that combines emotion engines

[2322] Collection and storage of user information

[2323] Step 1:

[2324] User: Launch the app and enter user information (name, age, hobbies, relationship goals, etc.).

[2325] Step 2:

[2326] Terminal: Sends the entered information to the server.

[2327] Step 3:

[2328] Server: Stores the received user information in a database.

[2329] Matching partner recommendations

[2330] Step 1:

[2331] Server: Selects the most suitable match from the database based on the user's profile and preferences.

[2332] Step 2:

[2333] Server: Sends the selected matching candidates to the device.

[2334] Step 3:

[2335] On your device: The profile of the recommended person will be displayed to you.

[2336] Step 4:

[2337] User: View the recommended people and select "Like" or "Dislike."

[2338] Step 5:

[2339] Terminal: Sends the user's selection to the server.

[2340] Step 6:

[2341] Server: Saves the selection results and uses them to improve the recommendation algorithm in the future.

[2342] Analysis of conversation logs and social media posts

[2343] Step 1:

[2344] Device: The user's conversation log and social media posts are periodically sent to the server.

[2345] Step 2:

[2346] Server: Uses a natural language processing (NLP) engine to analyze collected logs and posts.

[2347] Step 3:

[2348] Server: Extract the other person's interest, concern, and emotional tone.

[2349] Use of emotion engine

[2350] Step 1:

[2351] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, it identifies the user's current emotional state (joy, anxiety, excitement, etc.) by detecting positive and negative expressions.

[2352] Step 2:

[2353] Server: The analysis results from the emotion engine are stored in a database and used for future advice and planning.

[2354] Providing advice and training

[2355] Step 1:

[2356] Server: Based on the analysis results, the server generates advice and training content tailored to the user. Taking into account the results of the emotion engine, the server provides specific advice, such as "When the other person talks about a movie, suggest going to see it together."

[2357] Step 2:

[2358] Server: Sends the generated advice to the device.

[2359] Step 3:

[2360] Device: Displays received advice and training content to the user.

[2361] Step 4:

[2362] Users: Review advice and training and apply it to their next conversation or date.

[2363] Date plan suggestions

[2364] Step 1:

[2365] User: Requests date plan suggestions and enters criteria (location, budget, date and time, etc.).

[2366] Step 2:

[2367] Terminal: Sends the entered conditions to the server.

[2368] Step 3:

[2369] Server: Generates the optimal date plan taking into account the conditions, the user's preferences, and the results of the emotion engine.

[2370] Step 4:

[2371] Server: Sends the proposed date plan to the device.

[2372] Step 5:

[2373] Device: Display date plans to the user.

[2374] Gathering and implementing feedback

[2375] Step 1:

[2376] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date.

[2377] Step 2:

[2378] User: Enters date feedback and taps submit.

[2379] Step 3:

[2380] Device: Sends feedback to the server.

[2381] Step 4:

[2382] Server: Stores the collected feedback and incorporates it into the next proposal.

[2383] Continuous learning with emotion engine

[2384] Step 1:

[2385] Emotion engine: Improves analysis accuracy while taking feedback into consideration. For example, based on feedback such as "I was very satisfied with this date suggestion," the effectiveness of emotion-based suggestions can be further improved.

[2386] This will enable the system to increase users' chances of finding love and help them form efficient and effective partnerships.The use of an emotion engine will enable the system to provide more personalized advice and plans that are in line with the user's emotional state, which is expected to improve the user experience.

[2387] Example 2

[2388] 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."

[2389] Conventional matchmaking systems simply collect user information and recommend potential partners based on that information. They lack the ability to provide personalized advice or date plans that take into account data such as the user's emotional state and conversation logs. This makes it difficult to improve the user experience and effectively support users in increasing their chances of finding love. The present invention aims to solve this problem by providing personalized suggestions that take into account the user's information and emotional state.

[2390] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2391] In this invention, the server includes means for collecting and storing user information, means for recommending optimal matches based on the user information, means for analyzing the user's conversation records and posted content to generate appropriate advice, means for analyzing the user's emotional state to personalize the advice and date plans, and means for proposing date plans for the user. This makes it possible to not only recommend matches that meet the user's expectations, but also to provide specific and personalized advice and date plans that are tailored to each individual user.

[2392] "User information" refers to data such as profile information, hobby information, and relationship goals entered when using the system.

[2393] "Storage means" refers to a device or system that has the function of storing collected user information in a storage device such as a database.

[2394] "Means for recommending matching partners" refers to a system that selects the most suitable partner from a database based on the user's information and notifies the user of the results.

[2395] "Conversation records" refer to the content of conversations that users have on the system.

[2396] "Posted content" refers to the content of text, comments, updates, etc. posted by users on social media or the system.

[2397] "Means of analysis" refers to a system that uses natural language processing and sentiment analysis techniques to analyze user tendencies and emotions from conversation records and posted content.

[2398] "Means for generating appropriate advice" refers to a system that automatically generates advice and suggested actions that are useful to users based on the analysis results.

[2399] "Means for analyzing emotional state" refers to a system that determines a user's positive or negative emotional state from their conversation records and posted content.

[2400] "Means for proposing date plans" refers to a system that automatically designs and proposes optimal date itineraries based on user information and analysis results.

[2401] "Means for collecting feedback" refers to a system that allows users to input and record their evaluations and impressions of dates and proposals.

[2402] "Means of reflecting this in the next proposal" refers to a system that uses the collected feedback to improve and optimize future advice and proposals.

[2403] This invention is a system that collects and analyzes user information, recommends optimal matches, and provides appropriate advice, training, and even date plans. By combining this system with an emotion engine, it is possible to analyze the user's emotional state and provide more accurate advice and plans based on that analysis.

[2404] Configuration overview

[2405] This system consists of a server, terminals, and users.

[2406] Server: Collects, stores, analyzes, and provides recommendations based on information. Server software includes databases (e.g., MySQL), natural language processing (NLP) engines (e.g., Google Natural Language API), and emotion engines (e.g., IBM Watson Emotional Analysis).

[2407] Terminal: Provides an interface with the user. Terminals are general information devices such as smartphones and PCs.

[2408] User: Uses the system to enter information and receive suggestions.

[2409] Collection and storage of user information

[2410] User: Launch the app from a smartphone or PC and enter necessary information such as name, age, hobbies, and romantic goals when registering for the first time. For example, enter data such as "Ichiro Tanaka, 30 years old, reading, looking for a marriage partner."

[2411] Terminal: Sends this input information to the server.

[2412] Server: Save the received user information in a database. For example, create a table called "User Information" in a MySQL database and store data in each field.

[2413] Matching partner recommendations

[2414] Server: Queries the database based on the user's profile and preferences to select the most suitable match. For example, if Ichiro Tanaka's hobby is "reading" and his goal is "finding a marriage partner," the server will select candidates with the same hobbies and goals.

[2415] Server: Sends a list of selected match candidates to the device. The list includes information such as the match's name, hobbies, and photo.

[2416] On your device: The profile of the recommended person will be displayed to you.

[2417] User: View the recommended person and select "Like" or "Dislike." For example, by pressing the "♡" button next to the person's profile, you can register them as "Like."

[2418] Terminal: Sends the user's selection to the server.

[2419] Server: The selection results are stored in a database and used to improve the recommendation algorithm in the future.

[2420] Analysis of conversation logs and social media posts

[2421] Device: The device periodically sends the user's conversation logs and social media posts to the server. For example, it collects conversation history within a chat app and public posts on social media.

[2422] Server: Analyzes collected logs and posts using a natural language processing (NLP) engine. Specifically, it uses the Google Natural Language API to analyze various texts.

[2423] Server: Extracts the other person's interests, concerns, and emotional tone. For example, it obtains information such as "Today's posts contain many words like 'fun' and 'happy'."

[2424] Use of emotion engine

[2425] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, if a user posts, "I'm feeling great today," the emotion engine will identify this as a positive emotion.

[2426] Example: Detecting positive sentiment from posts such as "I'm feeling great today."

[2427] Providing advice and training

[2428] Server: Based on the analysis results, the server generates advice and training content tailored to the user. It also takes into account the results of the emotion engine to create specific advice. For example, it provides advice such as, "When the other person talks about a movie, suggest going to see it together."

[2429] Server: Sends the generated advice to the device.

[2430] Device: Displays received advice and training content to the user.

[2431] Users: Review advice and training and apply it to their next conversation or date.

[2432] Date plan suggestions

[2433] User: Requests date plan suggestions and enters criteria such as location, budget, date, etc. For example, "Shibuya, under 5,000 yen, Saturday afternoon."

[2434] Terminal: Sends the entered conditions to the server.

[2435] Server: Based on the input conditions, the server generates the optimal date plan based on the user's preferences and the results of the emotion engine. For example, it suggests "lunch at a cafe in Shibuya and then watch a movie."

[2436] Server: Sends the proposed date plan to the device.

[2437] Device: Display date plans to the user.

[2438] Gathering and implementing feedback

[2439] Device: After the date, a feedback survey is sent to the user, asking them to enter their impressions and evaluation of the date. For example, the device displays questions such as, "How satisfied were you with the date?"

[2440] User: Enter your feedback and tap the submit button. For example, "Satisfaction rating: 8 / 10."

[2441] Device: Sends feedback to the server.

[2442] Server: Store the collected feedback in a database and use it to make the next recommendation. For example, store satisfaction in a "Dating Experience" table.

[2443] Continuous learning with emotion engine

[2444] Emotion engine: Improves analysis accuracy while taking into account feedback. For example, improves the effectiveness of emotion-based suggestions based on information such as "This date suggestion was very satisfying."

[2445] This allows the system to increase the user's chances of finding love. By using a generative AI model and specific prompts, it is possible to provide more advanced advice and plans. A specific example would be to input the user's past conversation logs into the generative AI model to perform a deep analysis of emotional fluctuations.

[2446] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2447] Step 1:

[2448] User: Launch the app from a smartphone or PC and enter the necessary information such as name, age, hobbies, and relationship goals when registering for the first time. For example, enter data such as "Suzuki Hanako, 28 years old, traveling, looking for a marriage partner."

[2449] Input: Profile information, hobbies, relationship goals, etc. that you enter into the app.

[2450] Output: Input information is sent to the device and converted into a format for storage on the server.

[2451] Step 2:

[2452] Device: The entered user information is sent to the server. This operation is performed by pressing the "Register" button in the app.

[2453] Input: User information (name, age, hobbies, love goals, etc.)

[2454] Output: User information is sent to the server.

[2455] Step 3:

[2456] Server: Save the received user information in a database. For example, create a table called "User Information" in a MySQL database and store data in each field.

[2457] Input: User information sent from the terminal

[2458] Output: User information is saved in the database.

[2459] Step 4:

[2460] Server: Queries the database based on the user's profile and preferences to select the most suitable match. For example, based on information such as "Suzuki Hanako loves traveling and is looking for a marriage partner," it selects candidates with the same hobbies and goals.

[2461] Input: User information (profile, hobbies, relationship goals)

[2462] Output: A list of potential matches is generated.

[2463] Step 5:

[2464] Server: Sends a list of selected match candidates to the device, including information such as the matchee's name, hobbies, and photo.

[2465] Input: A list of possible matches

[2466] Output: A list of potential matches is sent to the device.

[2467] Step 6:

[2468] On your device: The profile of the recommended person will be displayed to you. It will be displayed on the "Matching Candidates" screen in the app.

[2469] Input: A list of match candidates sent by the server

[2470] Output: Information that is visually displayed to the user (profile, photo, etc.).

[2471] Step 7:

[2472] User: View the recommended person and select "Like" or "Dislike." For example, by pressing the "♡" button next to the person's profile, you can register them as "Like."

[2473] Input: User's choice (like it or not)

[2474] Output: The selections are logged to the terminal.

[2475] Step 8:

[2476] Terminal: Sends the user's selection to the server.

[2477] Input: User selection

[2478] Output: The selection results are sent to the server.

[2479] Step 9:

[2480] Server: The selection results are stored in a database to help improve the recommendation algorithm in the future, for example in a "User Behavior History" table.

[2481] Input: User selection

[2482] Output: The selection results are saved in a database and added to the data used for analysis.

[2483] Step 10:

[2484] Device: The device periodically sends the user's conversation logs and social media posts to the server. For example, it collects conversation history within a chat app and public posts on social media.

[2485] Input: Conversation logs, social media posts

[2486] Output: Conversation logs and SNS posts are transferred to the server.

[2487] Step 11:

[2488] Server: Analyzes collected logs and posts using a natural language processing (NLP) engine. Specifically, analysis is performed using the Google Natural Language API.

[2489] Input: Conversation logs, social media posts

[2490] Output: Data about the user's emotional state and interests is generated.

[2491] Step 12:

[2492] Emotion engine: Analyzes user emotions from conversation logs and social media posts. For example, if a user posts, "I'm feeling great today," the emotion engine will identify this as a positive emotion.

[2493] Input: Conversation logs, social media posts

[2494] Output: The user's emotional state (positive, negative, etc.). Example: A post saying "I'm feeling great today" is judged to have a positive emotion.

[2495] Step 13:

[2496] Server: Based on the analysis results, the server generates advice and training content tailored to the user. It also takes into account the results of the emotion engine to provide specific advice. For example, it creates advice such as "When the other person talks about a movie, suggest going to see it together."

[2497] Input: Analysis results, emotion engine results

[2498] Output: Generate specific advice and training content

[2499] Step 14:

[2500] Server: Sends the generated advice to the device.

[2501] Input: Generated advice and training content

[2502] Output: Advice and training content are transferred to the device.

[2503] Step 15:

[2504] On your device: Displaying received advice and training content to you, for example in the "Advice" section within the app.

[2505] Input: Advice and training content sent

[2506] Output: Visually displayed advice and training content

[2507] Step 16:

[2508] Users: Review advice and training and apply it to their next conversation or date.

[2509] Input: Received advice, training content

[2510] Output: Advice implementation reflected in actual behavior

[2511] Step 17:

[2512] User: Requests date plan suggestions and enters criteria such as location, budget, date, etc. For example, "Shibuya, under 5,000 yen, Saturday afternoon."

[2513] Input: Date plan conditions (location, budget, date, etc.)

[2514] Output: The condition is sent to the terminal and forwarded to the s...

Claims

1. How we collect and store your information; A means for recommending an optimal match partner based on the user information; A means for analyzing the conversation log and posted content of a user and generating appropriate advice; A means of proposing date plans to users, A system including:

2. A means of collecting and storing user feedback; A means for analyzing the feedback and reflecting the results in the next proposal; The system of claim 1 further comprising:

3. A means for including profile information, interest information, and love goals as the user information; means for providing appropriate advice and training to the user based on said analysis; The system of claim 1 further comprising:

Images