system

Abstract

We provide the system. [Solution] A method for collecting user data anonymly and extracting hobbies, values, and communication styles from message history, A means of incorporating a generative model that recommends the optimal partner based on collected data, A means of providing conversation support to help the initial conversation proceed naturally, A means having a feedback learning module that continuously learns user preferences from daily chat data and improves the accuracy of recommendations, A means of notifying users of the results of conversation support and partner recommendations, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional matching services, since users create profiles based on self-reported information, there were many cases where the profile information was inaccurate or did not meet the expectations of users. As a result, communication between users did not proceed smoothly, and the problem was that matching results with low satisfaction occurred. In addition, since the personalities and communication styles of users could not be fully grasped, it was difficult to find compatible partners.

Means for Solving the Problems

[0005] This invention solves conventional problems by generating accurate user profiles through anonymized user data collection and extraction of hobbies, values, and communication styles from message history. Furthermore, it achieves highly accurate matching that meets user expectations by recommending the most suitable partner based on the collected data using a generative AI model. It also improves satisfaction with matching results by providing conversation support to facilitate natural initial conversations and promoting smooth communication between users. Through a continuous feedback learning module, it learns user preferences and improves recommendation accuracy, providing the most suitable partner for each user.

[0006] "User data" refers to a collection of information related to a user, including anonymized data collected to identify their interests, values, and communication style.

[0007] A "generative model" is an algorithm or computational method that analyzes collected user data to recommend the most suitable partner.

[0008] "Conversation support" is a feature that facilitates smooth communication by providing suggestions and questions to help users naturally engage in their initial conversations.

[0009] The "feedback learning module" is a technology that continuously learns user preferences from everyday chat data to improve the accuracy of recommendations.

[0010] A "profile" is a collection of information that represents a user's characteristics, such as their hobbies, values, and communication style.

[0011] "Partner matching candidates" is a list of other users selected based on the user's profile, who are presumed to be a good match. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention relates to providing a messaging system that personalizes user matching and facilitates smooth communication. This system collects and analyzes user data to recommend the most suitable partner to each individual user.

[0034] First, the server anonymizes and collects the user's message history from the messaging application terminal they are using. This allows the server to identify the user's interests and values ​​based on their conversations while ensuring privacy. The server then analyzes this data to extract the user's hobbies, values, and communication style, and generates a profile.

[0035] Next, the server uses the generated profile to apply the generative model and selects other users who are expected to be a good match for the user as partner matching candidates. The selected candidates are then presented to the user in order of recommendation based on past data and feedback, determined by an algorithm.

[0036] Furthermore, the server provides a means to support initial conversations. Based on the hobbies and interests of potential matches, the server generates conversation topics and example questions, which users can use to initiate natural interactions.

[0037] The system's feedback learning module allows the server to continuously monitor users' daily chat data and learn new preferences and characteristics. This new information is then reflected in the selection of future matching candidates. As a result, the system can always adapt to the latest user preferences and improve the accuracy of recommendations.

[0038] For example, if a user repeatedly sends messages indicating interest in visiting art museums, the server adds this information to their profile and prioritizes recommending potential partners who share their interest in art. As a result, users can meet partners who match their interests and enjoy fulfilling communication.

[0039] Thus, the present invention improves the user experience by achieving highly accurate matching that meets user expectations and providing smooth and engaging communication.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The system collects message history sent and received via LINE from the device. The server anonymizes this message data and stores it in a database while ensuring privacy.

[0043] Step 2:

[0044] The server uses natural language processing algorithms to analyze the collected message history. This extracts the user's hobbies, values, and communication style, and generates individual user profiles.

[0045] Step 3:

[0046] Based on the generated user profile, the server applies a matching algorithm to select other users who are considered a good match for the user as potential partner match candidates. This process takes into account past matching data and user feedback.

[0047] Step 4:

[0048] The server creates a list of selected matching candidates and notifies the user of this list. The user can then select a partner they are interested in from the provided list of candidates.

[0049] Step 5:

[0050] The server generates conversation topics and example questions related to the hobbies and interests of the selected partner match to facilitate an effective initial conversation. Users can leverage this support to start a natural conversation.

[0051] Step 6:

[0052] The server continuously monitors daily chat data and learns new user preferences and communication characteristics. This allows the feedback learning module to accumulate information to make future matching more accurate.

[0053] Step 7:

[0054] Based on the updated learning results, the server updates the relevant matching algorithms and performs processes to improve the accuracy of recommending the best partner for the user.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In recent years, with the advancement of communication technology, online interaction between users has increased. However, conventional systems have been insufficient in providing individualized support based on the diverse interests and values ​​of users, often resulting in one-sided recommendations. Furthermore, there was a lack of support to smoothly initiate initial conversations, hindering effective communication. In addition, as users' interests and preferences change over time, systems have been unable to adequately respond to these changes.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] This invention includes a server that collects anonymized user data and extracts the user's hobbies, values, and communication style from the acquired message history; a means for recommending the most suitable partner based on the collected data using a generative AI model; and a means for providing support to facilitate a natural initial conversation. This enables highly accurate matching based on each user's individual profile and a smooth start to the initial conversation. Furthermore, a feedback learning module allows for continuous learning of user preferences and adaptive improvement of recommendation accuracy.

[0060] "Anonymized user data" refers to user information that has been transformed into an unidentifiable form by removing personally identifiable information.

[0061] "Message history" refers to a record of past conversations and communications that a user has had online.

[0062] "Hobbies" refer to activities that users enjoy doing or things they are interested in.

[0063] "Values" refer to the beliefs and attitudes that users have regarding what they focus on or consider important.

[0064] "Communication style" refers to the methods and characteristics of how users exchange information with others.

[0065] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze data and generate new information or predictions.

[0066] "Dialogue support" refers to means of assisting users in starting and continuing smooth communication with others.

[0067] A "feedback learning module" refers to a component that includes a learning function that analyzes user data and responses and incorporates them into future recommendations.

[0068] An "individual profile" refers to a set of information that summarizes a user's individual characteristics, such as their hobbies and values.

[0069] "Matching candidates" refer to other users who are deemed to be a good match for the user.

[0070] "Communication patterns" refer to behavioral characteristics that indicate the tendencies and frequency of how users communicate.

[0071] This invention relates to a messaging system that personalizes user matching and facilitates smooth communication. The system aims to recommend the most suitable partner to each individual user by collecting and analyzing user data.

[0072] First, the server anonymizes and collects message history from the messaging application terminal used by the user. At this stage, techniques are used to hash personally identifiable information in order to protect data privacy. The collected data is analyzed using natural language processing (NLP) techniques. This analysis extracts the user's hobbies, values, and communication style, and generates an individual profile.

[0073] Next, based on this profile, the server applies a generative AI model. This generative AI model uses the user's information as input parameters to recommend other users that it deems to be a good match for the user. This matching algorithm is continuously optimized using historical data and feedback.

[0074] Furthermore, the server provides conversational support to ensure a smooth start to the first conversation. Specifically, it uses an AI model to automatically generate conversation topics and example questions based on the hobbies and interests of potential matches. Users can then leverage these resources provided by the server to initiate natural interactions.

[0075] Finally, the system uses a feedback learning module to continuously monitor the user's daily chat data and learn new preferences and characteristics. This new information is then reflected in the selection of matching candidates for the next time. For example, a prompt such as "Recommend a partner suitable for a user who enjoys visiting art museums" is input into the generating AI model, and partners based on this information are presented to the user. In this way, the system can constantly adapt to the latest user preferences and provide appropriate matching and smooth communication.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server collects message history from the terminal where the user's messaging application is running. The input used is the user's conversation history data. Specifically, it employs anonymization techniques to remove personally identifiable information from this data. The output is message data in a form that protects personal information.

[0079] Step 2:

[0080] The server analyzes the anonymized message data collected in Step 1. Anonymized message history is used as input data. Natural language processing (NLP) techniques are applied to extract keywords from the messages and identify the user's hobbies, values, and communication style. This data processing outputs an individual user profile.

[0081] Step 3:

[0082] The server uses a generative AI model to select matching candidates based on user profiles. Individual profiles are fed to the generative AI model as input, and after similarity calculations, other users who are expected to be a good match are selected. The output is a group of matching candidates assigned recommendation ranks.

[0083] Step 4:

[0084] The server provides dialogue support to ensure that the first interaction between matched users proceeds smoothly. The input is profile information of the matching candidates, and a generative AI model is used to generate prompt sentences for conversation topics and example questions. These prompt sentences are then generated and provided to the user as output.

[0085] Step 5:

[0086] The server continuously monitors user message data through a feedback learning module, learning new preferences and patterns. Everyday conversation data is used as input, and the information is analyzed by machine learning algorithms. This information is then fed back into the next matching process to improve recommendation accuracy. The output is an updated user profile and refined matching candidates.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] In modern information and communication technology, achieving appropriate and effective matching between users is not easy. In particular, in online content distribution services, it is difficult for users to naturally interact with other users who share their interests. This limits the user experience and reduces the value of the service.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for collecting user data while anonymizing it and extracting hobbies and values ​​from message history, means for incorporating a generative model that recommends the most suitable target based on the collected data, and means for generating relevant conversation topics based on the user's interests. This makes it easier for users to initiate natural conversations with people who match their interests within the service, improving the quality of communication and enhancing the overall user experience.

[0092] "User data" refers to information about individual users, including their interests, values, and communication style.

[0093] "Anonymization" is the process of removing or concealing elements that could identify an individual from collected data in order to prevent the identification of that individual.

[0094] "Message history" refers to a record of the content of communications sent and received by a user, and is used for analyzing their interests and values.

[0095] A "generative model" is an algorithm or framework for analyzing data and providing optimal recommendations to individual users.

[0096] The "feedback learning module" is a mechanism that continuously learns from the user's behavior and reactions to improve the accuracy of recommendations.

[0097] "Conversation support" is a function that assists communication between users by providing suggestions and instructions to improve the smoothness of the conversation.

[0098] A "profile" is a dataset that represents the characteristics of a user, constructed based on collected information.

[0099] "Matching candidates" are other users who have been selected based on the user's interests and values, and who have the potential to interact with the user.

[0100] "Monitoring" refers to the act of observing a user's behavior and interactions, and recording or analyzing the data.

[0101] "Communication patterns" refer to the specific tendencies and styles that a user exhibits in conversation.

[0102] In the system that implements this invention, the server collects user data anonymized and handles message history. This involves using data processing techniques to identify the user's hobbies, values, and communication style from their conversation history. Specifically, the CountVectorizer from scikit-learn is used to vectorize the user's message content and extract important features.

[0103] This system incorporates a generative model, which is used to recommend the most suitable target. To calculate compatibility with users, it calculates the cosine similarity between vectors and selects users with good compatibility. Scikit-learn is also used for this process.

[0104] The server incorporates a feedback learning module that continuously monitors daily conversation records and learns the user's interests. This process involves continuous data collection and analysis, and the information obtained is reflected in the next recommendation candidates.

[0105] For example, if a user shows interest in movies, this trait is added to their profile, and other users who also enjoy movies are recommended preferentially. This allows users to naturally start conversations about a common topic.

[0106] Furthermore, the server generates conversation topics based on the user's interests to support the dialogue. The generative AI model used for this purpose suggests relevant conversation topics based on past data. These suggestions are presented as prompts, such as, "Please suggest conversation starters on topics that the user is interested in."

[0107] Example of a prompt:

[0108] "Please suggest conversation starters related to topics that users are interested in."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server collects anonymized user message history from each device. Here, data related to sending and receiving messages is compiled and anonymized to prevent the identification of individuals. The input is the user's raw message data, and the output is anonymized message history data.

[0112] Step 2:

[0113] The server extracts the user's hobbies, values, and communication style based on anonymized message history. It uses scikit-learn's CountVectorizer to vectorize messages and capture key features within the text. The input is an anonymized message history, and the output is a user feature vector.

[0114] Step 3:

[0115] The server uses a generative model to recommend the most suitable partner based on the collected feature vectors. It calculates cosine similarity and selects users deemed to be a good match as matching candidates. In this process, the input is the user's feature vector, and the output is a list of compatible candidates.

[0116] Step 4:

[0117] The server generates conversation topics for matching candidates. It utilizes a generative AI model that takes into account common interests with the candidates. The input is a list of matching candidates and the user's interest profile, and the output is a list of conversation topics.

[0118] Step 5:

[0119] The server notifies each user of the topic of the generated conversation and the matching results. The notification includes suggestions using prompts. Prompts such as "Please suggest conversation starters on topics that the user may be interested in" are prepared. The input is a list of conversation topics and matching results, and the output is the notification content for the user.

[0120] Step 6:

[0121] Users utilize suggestions received from the server to naturally initiate communication with potential matches. This process involves starting an active dialogue based on the notified topic.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention relates to a system for recognizing users' emotions in a user-to-user matching service and utilizing this information in the conversation and matching process. Specifically, it detects emotions through users' messaging activities and uses this information to optimize communication support and partner selection.

[0124] First, the device collects the user's message history. This data is anonymized and securely managed on a server. The server uses natural language processing to analyze the user's messages and generate a profile of their interests, values, and communication style.

[0125] Next, the server uses an emotion engine to determine the user's emotions in real time from the message content. This emotion data is used to evaluate what emotional state the user is in, such as joy, sadness, or anger. For example, if the emotion analysis reveals that the user is feeling stressed, the server will provide appropriate communication support, offering topics and suggestions to alleviate that stress.

[0126] Furthermore, the server selects the most suitable partner candidates based on the collected profile information and emotional data. This process also takes emotional compatibility into consideration, and is adjusted to ensure that users are matched with partners with whom they can communicate comfortably.

[0127] During the conversation support phase, the server generates appropriate conversation topics and questions based on the selected partner's hobbies and emotional state. This allows the user to initiate a natural and effective conversation tailored to the other person's situation.

[0128] Furthermore, the emotion engine and feedback learning module work together, and the server tracks changes in the user's emotions from everyday chats. This data will be used to improve future matching algorithms and communication support, providing an experience optimized for each individual user.

[0129] For example, if the emotion engine determines that a user is enjoying a new hobby, the server will prioritize other users who share that hobby as matching candidates. In this way, the present invention can dynamically understand the user's emotions and improve the quality of the matching and communication experience, thereby increasing user satisfaction.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The device collects messages sent through the user's messaging app. The collected messages are anonymized under appropriate security measures and sent to the server.

[0133] Step 2:

[0134] The server analyzes the received messages using natural language processing technology. This extracts hobbies, values, and communication styles to generate a profile for each user.

[0135] Step 3:

[0136] The server uses an emotion engine to determine the user's emotional state from the message. For example, it analyzes whether the user is experiencing emotions such as joy, sadness, or anger based on the content of the text and the characteristics of the words used.

[0137] Step 4:

[0138] The server compares the generated profile information with emotional data to select the most suitable partner matching candidates. Here, emotional compatibility and commonalities in profiles are also considered to enhance the suitability between users.

[0139] Step 5:

[0140] The server notifies the user of a list of selected partner matching candidates. The user then selects someone they are interested in from this list and prepares to start a conversation.

[0141] Step 6:

[0142] Based on the results of the emotion engine, the server generates conversation topics and questions to support the initial conversation with the selected partner. Users can use these suggestions to initiate a more personalized conversation.

[0143] Step 7:

[0144] The server continuously monitors chats between users and tracks changes in their emotions. The collected emotional data is sent to a feedback learning module and used to optimize future matching and conversation support.

[0145] (Example 2)

[0146] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0147] Conventional user matching systems have struggled to select the optimal partner based on users' emotional compatibility and circumstances, resulting in insufficient user satisfaction. Furthermore, there was a lack of means to understand users' emotional changes in real time and improve the communication experience.

[0148] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0149] In this invention, the server includes means for collecting user data anonymized and extracting interests, values, and dialogue styles; means for incorporating a generative model that recommends optimal interaction candidates; and means for analyzing the user's emotional state in real time and providing dialogue support that responds to those emotions. This enables highly accurate recommendation of interaction candidates based on the user's emotions and individual profile, as well as optimal communication support that responds to those emotions.

[0150] "User data" is a general term for data obtained from user behavior, messages, and related information.

[0151] "Anonymization" is a process that protects the privacy of data subjects by removing or transforming information that could identify an individual.

[0152] "Interest" refers to the tendency a user shows to be interested in a particular activity or topic.

[0153] "Value" refers to the beliefs and principles that users consider important, and it influences their decision-making and actions.

[0154] "Conversational style" refers to the unique style or pattern that users exhibit in their communication.

[0155] A "generative model" is a type of AI that uses algorithms to generate potential partners and conversation content based on user data.

[0156] "Emotional state" refers to the psychological or emotional state a user is experiencing at a particular point in time.

[0157] A "feedback learning module" is a module that continuously analyzes users' past behavioral data and has the functionality to improve the overall accuracy and adaptability of the system.

[0158] "Interaction candidates" refer to conversation partners that the system recommends as suitable partners for the user.

[0159] To implement this invention, the main elements required are a user terminal, a server for processing data, and a generative AI model. The roles and operations of each are described below.

[0160] First, the user accesses the messaging service using their device. The device automatically collects the user's message history, but all of this data is anonymized before being sent to the server. Anonymizing the collected data is an important step in protecting user privacy.

[0161] The server securely stores the received data and uses natural language processing (NLP) techniques to analyze the user's interests, values, and conversational style. This process may involve the use of open-source NLP libraries and machine learning platforms. For example, libraries such as TENSORFLOW® and PyTorch can be used to analyze the data. The analyzed information is then used to create individual profiles for each user.

[0162] The generative AI model uses this profile information to recommend the best possible interactions between users. This model extracts the user's emotional state in real time and tracks all changes that occur during the conversation, enabling highly accurate recommendations. For example, if a user sends a message such as, "The weather has been nice these past few days, and I'm in a good mood," the server will interpret this as a positive emotional expression and suggest users with similar emotions as potential interactions.

[0163] Furthermore, the server tracks emotional changes and improves overall system performance through a feedback learning module. This allows it to quickly adapt to changes in the user's emotions and behavioral patterns, providing appropriate communication support. Examples of specific prompts include "Let's talk about your recent hobbies!" and "Is there any news that interests you?". These prompts are dynamically generated to match the user's interests and emotions, making the conversation natural and engaging.

[0164] In this way, the present invention can provide highly accurate recommendation of interaction candidates based on the user's emotions and individual profile, as well as optimal communication support tailored to those emotions.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The device collects the user's message history. It takes text data sent and received by the user via messaging apps as input and performs anonymization on this data. Once the anonymization process is complete, the data is sent to the server.

[0168] Step 2:

[0169] The server stores the received anonymized data in a secure database. This step uses anonymized message data sent from the terminal as input and performs data processing by storing it in the database. The output is the stored message data.

[0170] Step 3:

[0171] The server analyzes the data using natural language processing techniques. In this step, message data is retrieved from the database, and interests, values, and conversational styles are extracted. This data processing outputs profile information from the input messages.

[0172] Step 4:

[0173] The server uses a generative AI model to calculate the optimal interaction candidates from profile information. It uses profile information as input and performs data calculations using an algorithm. The output is a list of interaction candidates, including the candidate's profile information.

[0174] Step 5:

[0175] The server uses an emotion engine to analyze the user's emotional state in real time. The input is the latest chat message, and the emotional state is output after emotion analysis. In operation, it tracks the progression of emotions and uses this information to generate prompt messages as needed.

[0176] Step 6:

[0177] The server is equipped with a feedback learning module that continuously learns user preferences. It uses past interaction history and emotion change history as input to apply a learning algorithm and improve recommendation accuracy. The output is the improved recommendation algorithm.

[0178] Step 7:

[0179] The server generates prompt sentences using a generative AI model based on each user's emotional state and profile information. Using the emotional states and profiles of potential interaction candidates as input, the server performs algorithmic data calculations to output appropriate conversation topics and questions.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0182] Conventional user content recommendation systems have had the problem of difficulty in providing optimal content based on the user's emotions and recent communications. While typical recommendation systems primarily recommend content based on the user's past behavior history, recommendations that take the user's current emotional state into account are rarely performed. This invention aims to provide a more personalized experience by recommending appropriate content that takes the user's emotions into account.

[0183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0184] In this invention, the server includes means for anonymizing and collecting user data and extracting hobbies, values, and communication styles from message history; means for incorporating a generative model that recommends optimal information based on the collected data; and means for selecting content that optimizes the suggested content according to the user's emotional state. This enables personalized content recommendations based on the user's emotions.

[0185] "User data" refers to information associated with individual users, including their hobbies, values, and communication style.

[0186] "Anonymization" refers to the process of removing personal information from data so that specific individuals cannot be identified.

[0187] A "generative model" refers to an algorithm or method that generates new information or content based on data input.

[0188] A "feedback learning module" includes algorithms that continuously improve the accuracy of the model or system based on the user's behavior and reactions.

[0189] "Emotional state" refers to a temporary mental state expressed by a user based on their messages and actions.

[0190] "Content selection methods" refer to methods and devices for selecting the most suitable information and entertainment based on the user's preferences and emotions.

[0191] "Natural language processing" includes technologies that enable computers to understand, analyze, and generate human language.

[0192] This invention concretely realizes a content recommendation system based on user emotions, in which the server and terminal work together. The server uses a natural language processing library such as TextBlob to analyze message history data collected from the terminal. From the analyzed data, the user's hobbies, values, and communication style are extracted and securely stored as a user profile.

[0193] The server also uses a generative AI model to estimate the user's emotional state in real time based on the obtained profile. The emotional state is evaluated as positive, negative, or neutral. Based on this information, content selection mechanisms are activated to select information and entertainment optimized for the user.

[0194] For example, if a user sends a message like "I've been feeling tired lately," the server will recognize this as a negative emotion and recommend relaxation music or meditation videos. Conversely, if positive emotions are recognized, it can recommend action movies or positive news.

[0195] The specific hardware used includes terminals for collecting user data (e.g., smartphones) and servers for storing and analyzing that data. On the software side, libraries such as TextBlob are used to support natural language processing techniques.

[0196] An example of a prompt message would be, "Write a program that suggests stress-reducing content when the user is busy and tired." This makes it possible to provide the user with appropriate content that matches their current emotional state.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The device collects the user's message history and sends it to the server. The input is past messages the user has used on the device, which are anonymized and sent to the server. The output is anonymized message data. Specifically, the content of conversations the user has with friends in a chat app is stored on the device and later transferred to the server in a format that can be analyzed.

[0200] Step 2:

[0201] The server uses natural language processing to extract information about the user's hobbies, values, and communication style from the received message data. The input is anonymized message data received from the terminal, which is then analyzed to generate a user profile. The output is profile information such as the user's hobbies and values. Specifically, TextBlob is used to perform semantic analysis of the data and extract user characteristics.

[0202] Step 3:

[0203] The server uses a generative AI model to predict the user's emotional state from profile information and the latest message context. The input consists of extracted profile information and message data, which are processed to estimate the emotional state. The output is the user's emotional state data. Specifically, the generative AI determines the user's emotion (positive, negative, or neutral) from the word choices and writing style within the messages.

[0204] Step 4:

[0205] The server selects the most suitable content based on the user's emotional state, utilizing content selection methods. It receives emotional state data as input and selects content candidates based on that data. The output is content information recommended to the user. Specifically, it might select relaxation music if the user's emotions are negative, or an action movie if their emotions are positive.

[0206] Step 5:

[0207] The server notifies the device of the selected content information and presents it to the user. The input is the selected content information, which is sent to the device. The output is the recommended content displayed on the user's device. Specifically, when the user taps the notification they receive, they are connected to a link where they can view the recommended content.

[0208] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0224] This invention relates to providing a messaging system that personalizes user matching and facilitates smooth communication. This system collects and analyzes user data to recommend the most suitable partner to each individual user.

[0225] First, the server anonymizes and collects the user's message history from the messaging application terminal they are using. This allows the server to identify the user's interests and values ​​based on their conversations while ensuring privacy. The server then analyzes this data to extract the user's hobbies, values, and communication style, and generates a profile.

[0226] Next, the server uses the generated profile to apply the generative model and selects other users who are expected to be a good match for the user as partner matching candidates. The selected candidates are then presented to the user in order of recommendation based on past data and feedback, determined by an algorithm.

[0227] Furthermore, the server provides a means to support initial conversations. Based on the hobbies and interests of potential matches, the server generates conversation topics and example questions, which users can use to initiate natural interactions.

[0228] The system's feedback learning module allows the server to continuously monitor users' daily chat data and learn new preferences and characteristics. This new information is then reflected in the selection of future matching candidates. As a result, the system can always adapt to the latest user preferences and improve the accuracy of recommendations.

[0229] For example, if a user repeatedly sends messages indicating interest in visiting art museums, the server adds this information to their profile and prioritizes recommending potential partners who share their interest in art. As a result, users can meet partners who match their interests and enjoy fulfilling communication.

[0230] Thus, the present invention improves the user experience by achieving highly accurate matching that meets user expectations and providing smooth and engaging communication.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The system collects message history sent and received via LINE from the device. The server anonymizes this message data and stores it in a database while ensuring privacy.

[0234] Step 2:

[0235] The server uses natural language processing algorithms to analyze the collected message history. This extracts the user's hobbies, values, and communication style, and generates individual user profiles.

[0236] Step 3:

[0237] Based on the generated user profile, the server applies a matching algorithm to select other users who are considered a good match for the user as potential partner match candidates. This process takes into account past matching data and user feedback.

[0238] Step 4:

[0239] The server creates a list of selected matching candidates and notifies the user of this list. The user can then select a partner they are interested in from the provided list of candidates.

[0240] Step 5:

[0241] The server generates conversation topics and example questions related to the hobbies and interests of the selected partner match to facilitate an effective initial conversation. Users can leverage this support to start a natural conversation.

[0242] Step 6:

[0243] The server continuously monitors daily chat data and learns new user preferences and communication characteristics. This allows the feedback learning module to accumulate information to make future matching more accurate.

[0244] Step 7:

[0245] Based on the updated learning results, the server updates the relevant matching algorithms and performs processes to improve the accuracy of recommending the best partner for the user.

[0246] (Example 1)

[0247] Next, we will describe Example 1. 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."

[0248] In recent years, with the advancement of communication technology, online interaction between users has increased. However, conventional systems have been insufficient in providing individualized support based on the diverse interests and values ​​of users, often resulting in one-sided recommendations. Furthermore, there was a lack of support to smoothly initiate initial conversations, hindering effective communication. In addition, as users' interests and preferences change over time, systems have been unable to adequately respond to these changes.

[0249] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0250] This invention includes a server that collects anonymized user data and extracts the user's hobbies, values, and communication style from the acquired message history; a means for recommending the most suitable partner based on the collected data using a generative AI model; and a means for providing support to facilitate a natural initial conversation. This enables highly accurate matching based on each user's individual profile and a smooth start to the initial conversation. Furthermore, a feedback learning module allows for continuous learning of user preferences and adaptive improvement of recommendation accuracy.

[0251] "Anonymized user data" refers to user information that has been transformed into an unidentifiable form by removing personally identifiable information.

[0252] "Message history" refers to a record of past conversations and communications that a user has had online.

[0253] "Hobbies" refer to activities that users enjoy doing or things they are interested in.

[0254] "Values" refer to the beliefs and attitudes that users have regarding what they focus on or consider important.

[0255] "Communication style" refers to the methods and characteristics of how users exchange information with others.

[0256] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze data and generate new information or predictions.

[0257] "Dialogue support" refers to means of assisting users in starting and continuing smooth communication with others.

[0258] A "feedback learning module" refers to a component that includes a learning function that analyzes user data and responses and incorporates them into future recommendations.

[0259] An "individual profile" refers to a set of information that summarizes a user's individual characteristics, such as their hobbies and values.

[0260] "Matching candidates" refer to other users who are deemed to be a good match for the user.

[0261] "Communication patterns" refer to behavioral characteristics that indicate the tendencies and frequency of how users communicate.

[0262] This invention relates to a messaging system that personalizes user matching and facilitates smooth communication. The system aims to recommend the most suitable partner to each individual user by collecting and analyzing user data.

[0263] First, the server anonymizes and collects message history from the messaging application terminal used by the user. At this stage, techniques are used to hash personally identifiable information in order to protect data privacy. The collected data is analyzed using natural language processing (NLP) techniques. This analysis extracts the user's hobbies, values, and communication style, and generates an individual profile.

[0264] Next, based on this profile, the server applies a generative AI model. This generative AI model uses the user's information as input parameters to recommend other users that it deems to be a good match for the user. This matching algorithm is continuously optimized using historical data and feedback.

[0265] Furthermore, the server provides conversational support to ensure a smooth start to the first conversation. Specifically, it uses an AI model to automatically generate conversation topics and example questions based on the hobbies and interests of potential matches. Users can then leverage these resources provided by the server to initiate natural interactions.

[0266] Finally, the system uses a feedback learning module to continuously monitor the user's daily chat data and learn new preferences and characteristics. This new information is then reflected in the selection of matching candidates for the next time. For example, a prompt such as "Recommend a partner suitable for a user who enjoys visiting art museums" is input into the generating AI model, and partners based on this information are presented to the user. In this way, the system can constantly adapt to the latest user preferences and provide appropriate matching and smooth communication.

[0267] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0268] Step 1:

[0269] The server collects message history from the terminal where the user's messaging application is running. The input used is the user's conversation history data. Specifically, it employs anonymization techniques to remove personally identifiable information from this data. The output is message data in a form that protects personal information.

[0270] Step 2:

[0271] The server analyzes the anonymized message data collected in Step 1. Anonymized message history is used as input data. Natural language processing (NLP) techniques are applied to extract keywords from the messages and identify the user's hobbies, values, and communication style. This data processing outputs an individual user profile.

[0272] Step 3:

[0273] The server uses a generative AI model to select matching candidates based on user profiles. Individual profiles are fed to the generative AI model as input, and after similarity calculations, other users who are expected to be a good match are selected. The output is a group of matching candidates assigned recommendation ranks.

[0274] Step 4:

[0275] The server provides dialogue support to ensure that the first interaction between matched users proceeds smoothly. The input is profile information of the matching candidates, and a generative AI model is used to generate prompt sentences for conversation topics and example questions. These prompt sentences are then generated and provided to the user as output.

[0276] Step 5:

[0277] The server continuously monitors user message data through a feedback learning module, learning new preferences and patterns. Everyday conversation data is used as input, and the information is analyzed by machine learning algorithms. This information is then fed back into the next matching process to improve recommendation accuracy. The output is an updated user profile and refined matching candidates.

[0278] (Application Example 1)

[0279] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0280] In modern information and communication technology, achieving appropriate and effective matching between users is not easy. In particular, in online content distribution services, it is difficult for users to naturally interact with other users who share their interests. This limits the user experience and reduces the value of the service.

[0281] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0282] In this invention, the server includes means for collecting user data while anonymizing it and extracting hobbies and values from the message history, means for mounting a generation model that recommends an optimal target based on the collected data, and means for generating a relevant conversation topic based on the user's interests. As a result, the user can easily start a natural conversation with a partner who matches their interests within the service, improving the quality of communication and the overall usage experience.

[0283] "User data" is information about individual users, representing interests, values, communication styles, etc.

[0284] "Anonymization" is a process of removing or hiding elements that can identify an individual from the collected data in order to prevent individual identification.

[0285] "Message history" is a record of the communication content sent and received by the user and is used for the analysis of interests and values.

[0286] "Generation model" is an algorithm or framework for analyzing data and making optimal recommendations for individual users.

[0287] "Feedback learning module" is a mechanism that continuously learns from the user's actions and reactions to improve the accuracy of recommendations.

[0288] "Conversation support" is a function that supports communication between users by providing suggestions and instructions to improve the smoothness of the conversation.

[0289] "Profile" is a dataset representing the characteristics of the user, constructed based on the collected information.

[0290] "Matching candidates" are other users who have been selected based on the user's interests and values, and who have the potential to interact with the user.

[0291] "Monitoring" refers to the act of observing a user's behavior and interactions, and recording or analyzing the data.

[0292] "Communication patterns" refer to the specific tendencies and styles that a user exhibits in conversation.

[0293] In the system that implements this invention, the server collects user data anonymized and handles message history. This involves using data processing techniques to identify the user's hobbies, values, and communication style from their conversation history. Specifically, the CountVectorizer from scikit-learn is used to vectorize the user's message content and extract important features.

[0294] This system incorporates a generative model, which is used to recommend the most suitable target. To calculate compatibility with users, it calculates the cosine similarity between vectors and selects users with good compatibility. Scikit-learn is also used for this process.

[0295] The server incorporates a feedback learning module that continuously monitors daily conversation records and learns the user's interests. This process involves continuous data collection and analysis, and the information obtained is reflected in the next recommendation candidates.

[0296] For example, if a user shows interest in movies, this trait is added to their profile, and other users who also enjoy movies are recommended preferentially. This allows users to naturally start conversations about a common topic.

[0297] Furthermore, the server generates conversation topics based on the user's interests to support the dialogue. The generative AI model used for this purpose suggests relevant conversation topics based on past data. These suggestions are presented as prompts, such as, "Please suggest conversation starters on topics that the user is interested in."

[0298] Example of a prompt:

[0299] "Please suggest conversation starters related to topics that users are interested in."

[0300] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0301] Step 1:

[0302] The server collects anonymized user message history from each device. Here, data related to sending and receiving messages is compiled and anonymized to prevent the identification of individuals. The input is the user's raw message data, and the output is anonymized message history data.

[0303] Step 2:

[0304] The server extracts the user's hobbies, values, and communication style based on anonymized message history. It uses scikit-learn's CountVectorizer to vectorize messages and capture key features within the text. The input is an anonymized message history, and the output is a user feature vector.

[0305] Step 3:

[0306] The server uses a generative model to recommend the most suitable partner based on the collected feature vectors. It calculates cosine similarity and selects users deemed to be a good match as matching candidates. In this process, the input is the user's feature vector, and the output is a list of compatible candidates.

[0307] Step 4:

[0308] The server generates conversation topics for the matching candidates. It utilizes a generation AI model and takes into account the common interests with the candidates. The input is the list of matching candidates and the user's interest profile, and the output is a list of conversation topics.

[0309] Step 5:

[0310] The server notifies each user of the generated conversation topics and the matching results. The notification includes suggestions using prompt sentences. Prepare a prompt sentence in the form of "Please propose an opportunity for conversation on topics that the user is interested in". The input is the list of conversation topics and the matching results, and the output is the content of the notification to the user.

[0311] Step 6:

[0312] The user utilizes the suggestions received from the server to start communicating with the matching candidates in a natural form. In this process, an active conversation is initiated based on the notified topics.

[0313] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0314] The present invention relates to a system that recognizes the user's emotion in a user matching service and utilizes this in the process of conversation and matching. Specifically, it detects the emotion through the user's messaging activities and optimizes communication support and partner selection based on that information.

[0315] First, the device collects the user's message history. This data is anonymized and securely managed on a server. The server uses natural language processing to analyze the user's messages and generate a profile of their interests, values, and communication style.

[0316] Next, the server uses an emotion engine to determine the user's emotions in real time from the message content. This emotion data is used to evaluate what emotional state the user is in, such as joy, sadness, or anger. For example, if the emotion analysis reveals that the user is feeling stressed, the server will provide appropriate communication support, offering topics and suggestions to alleviate that stress.

[0317] Furthermore, the server selects the most suitable partner candidates based on the collected profile information and emotional data. This process also takes emotional compatibility into consideration, and is adjusted to ensure that users are matched with partners with whom they can communicate comfortably.

[0318] During the conversation support phase, the server generates appropriate conversation topics and questions based on the selected partner's hobbies and emotional state. This allows the user to initiate a natural and effective conversation tailored to the other person's situation.

[0319] Furthermore, the emotion engine and feedback learning module work together, and the server tracks changes in the user's emotions from everyday chats. This data will be used to improve future matching algorithms and communication support, providing an experience optimized for each individual user.

[0320] For example, if the emotion engine determines that a user is enjoying a new hobby, the server will prioritize other users who share that hobby as matching candidates. In this way, the present invention can dynamically understand the user's emotions and improve the quality of the matching and communication experience, thereby increasing user satisfaction.

[0321] The following describes the processing flow.

[0322] Step 1:

[0323] The device collects messages sent through the user's messaging app. The collected messages are anonymized under appropriate security measures and sent to the server.

[0324] Step 2:

[0325] The server analyzes the received messages using natural language processing technology. This extracts hobbies, values, and communication styles to generate a profile for each user.

[0326] Step 3:

[0327] The server uses an emotion engine to determine the user's emotional state from the message. For example, it analyzes whether the user is experiencing emotions such as joy, sadness, or anger based on the content of the text and the characteristics of the words used.

[0328] Step 4:

[0329] The server compares the generated profile information with emotional data to select the most suitable partner matching candidates. Here, emotional compatibility and commonalities in profiles are also considered to enhance the suitability between users.

[0330] Step 5:

[0331] The server notifies the user of a list of selected partner matching candidates. The user then selects someone they are interested in from this list and prepares to start a conversation.

[0332] Step 6:

[0333] Based on the results of the emotion engine, the server generates conversation topics and questions to support the initial conversation with the selected partner. Users can use these suggestions to initiate a more personalized conversation.

[0334] Step 7:

[0335] The server continuously monitors chats between users and tracks changes in their emotions. The collected emotional data is sent to a feedback learning module and used to optimize future matching and conversation support.

[0336] (Example 2)

[0337] Next, we will describe Example 2. 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".

[0338] Conventional user matching systems have struggled to select the optimal partner based on users' emotional compatibility and circumstances, resulting in insufficient user satisfaction. Furthermore, there was a lack of means to understand users' emotional changes in real time and improve the communication experience.

[0339] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0340] In this invention, the server includes means for collecting user data anonymized and extracting interests, values, and dialogue styles; means for incorporating a generative model that recommends optimal interaction candidates; and means for analyzing the user's emotional state in real time and providing dialogue support that responds to those emotions. This enables highly accurate recommendation of interaction candidates based on the user's emotions and individual profile, as well as optimal communication support that responds to those emotions.

[0341] "User data" is a general term for data obtained from user behavior, messages, and related information.

[0342] "Anonymization" is a process that protects the privacy of data subjects by removing or transforming information that could identify an individual.

[0343] "Interest" refers to the tendency a user shows to be interested in a particular activity or topic.

[0344] "Value" refers to the beliefs and principles that users consider important, and it influences their decision-making and actions.

[0345] "Conversational style" refers to the unique style or pattern that users exhibit in their communication.

[0346] A "generative model" is a type of AI that uses algorithms to generate potential partners and conversation content based on user data.

[0347] "Emotional state" refers to the psychological or emotional state a user is experiencing at a particular point in time.

[0348] A "feedback learning module" is a module that continuously analyzes users' past behavioral data and has the functionality to improve the overall accuracy and adaptability of the system.

[0349] "Interaction candidates" refer to conversation partners that the system recommends as suitable partners for the user.

[0350] To implement this invention, the main elements required are a user terminal, a server for processing data, and a generative AI model. The roles and operations of each are described below.

[0351] First, the user accesses the messaging service using their device. The device automatically collects the user's message history, but all of this data is anonymized before being sent to the server. Anonymizing the collected data is an important step in protecting user privacy.

[0352] The server securely stores the received data and uses natural language processing (NLP) techniques to analyze the user's interests, values, and conversational style. This process may involve using open-source NLP libraries and machine learning platforms. For example, libraries such as TensorFlow and PyTorch can be used to analyze the data. The analyzed information is then used to create individual profiles for each user.

[0353] The generative AI model uses this profile information to recommend the best possible interactions between users. This model extracts the user's emotional state in real time and tracks all changes that occur during the conversation, enabling highly accurate recommendations. For example, if a user sends a message such as, "The weather has been nice these past few days, and I'm in a good mood," the server will interpret this as a positive emotional expression and suggest users with similar emotions as potential interactions.

[0354] Furthermore, the server tracks emotional changes and improves overall system performance through a feedback learning module. This allows it to quickly adapt to changes in the user's emotions and behavioral patterns, providing appropriate communication support. Examples of specific prompts include "Let's talk about your recent hobbies!" and "Is there any news that interests you?". These prompts are dynamically generated to match the user's interests and emotions, making the conversation natural and engaging.

[0355] In this way, the present invention can provide highly accurate recommendation of interaction candidates based on the user's emotions and individual profile, as well as optimal communication support tailored to those emotions.

[0356] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0357] Step 1:

[0358] The device collects the user's message history. It takes text data sent and received by the user via messaging apps as input and performs anonymization on this data. Once the anonymization process is complete, the data is sent to the server.

[0359] Step 2:

[0360] The server stores the received anonymized data in a secure database. This step uses anonymized message data sent from the terminal as input and performs data processing by storing it in the database. The output is the stored message data.

[0361] Step 3:

[0362] The server analyzes the data using natural language processing techniques. In this step, message data is retrieved from the database, and interests, values, and conversational styles are extracted. This data processing outputs profile information from the input messages.

[0363] Step 4:

[0364] The server uses a generative AI model to calculate the optimal interaction candidates from profile information. It uses profile information as input and performs data calculations using an algorithm. The output is a list of interaction candidates, including the candidate's profile information.

[0365] Step 5:

[0366] The server uses an emotion engine to analyze the user's emotional state in real time. The input is the latest chat message, and the emotional state is output after emotion analysis. In operation, it tracks the progression of emotions and uses this information to generate prompt messages as needed.

[0367] Step 6:

[0368] The server is equipped with a feedback learning module that continuously learns user preferences. It uses past interaction history and emotion change history as input to apply a learning algorithm and improve recommendation accuracy. The output is the improved recommendation algorithm.

[0369] Step 7:

[0370] The server generates prompt sentences using a generative AI model based on each user's emotional state and profile information. Using the emotional states and profiles of potential interaction candidates as input, the server performs algorithmic data calculations to output appropriate conversation topics and questions.

[0371] (Application Example 2)

[0372] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0373] Conventional user content recommendation systems have had the problem of difficulty in providing optimal content based on the user's emotions and recent communications. While typical recommendation systems primarily recommend content based on the user's past behavior history, recommendations that take the user's current emotional state into account are rarely performed. This invention aims to provide a more personalized experience by recommending appropriate content that takes the user's emotions into account.

[0374] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0375] In this invention, the server includes means for anonymizing and collecting user data and extracting hobbies, values, and communication styles from message history; means for incorporating a generative model that recommends optimal information based on the collected data; and means for selecting content that optimizes the suggested content according to the user's emotional state. This enables personalized content recommendations based on the user's emotions.

[0376] "User data" refers to information associated with individual users, including their hobbies, values, and communication style.

[0377] "Anonymization" refers to the process of removing personal information from data so that specific individuals cannot be identified.

[0378] A "generative model" refers to an algorithm or method that generates new information or content based on data input.

[0379] A "feedback learning module" includes algorithms that continuously improve the accuracy of the model or system based on the user's behavior and reactions.

[0380] "Emotional state" refers to a temporary mental state expressed by a user based on their messages and actions.

[0381] "Content selection methods" refer to methods and devices for selecting the most suitable information and entertainment based on the user's preferences and emotions.

[0382] "Natural language processing" includes technologies that enable computers to understand, analyze, and generate human language.

[0383] This invention concretely realizes a content recommendation system based on user emotions, in which the server and terminal work together. The server uses a natural language processing library such as TextBlob to analyze message history data collected from the terminal. From the analyzed data, the user's hobbies, values, and communication style are extracted and securely stored as a user profile.

[0384] The server also uses a generative AI model to estimate the user's emotional state in real time based on the obtained profile. The emotional state is evaluated as positive, negative, or neutral. Based on this information, content selection mechanisms are activated to select information and entertainment optimized for the user.

[0385] For example, if a user sends a message like "I've been feeling tired lately," the server will recognize this as a negative emotion and recommend relaxation music or meditation videos. Conversely, if positive emotions are recognized, it can recommend action movies or positive news.

[0386] The specific hardware used includes terminals for collecting user data (e.g., smartphones) and servers for storing and analyzing that data. On the software side, libraries such as TextBlob are used to support natural language processing techniques.

[0387] An example of a prompt message would be, "Write a program that suggests stress-reducing content when the user is busy and tired." This makes it possible to provide the user with appropriate content that matches their current emotional state.

[0388] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0389] Step 1:

[0390] The device collects the user's message history and sends it to the server. The input is past messages the user has used on the device, which are anonymized and sent to the server. The output is anonymized message data. Specifically, the content of conversations the user has with friends in a chat app is stored on the device and later transferred to the server in a format that can be analyzed.

[0391] Step 2:

[0392] The server uses natural language processing to extract information about the user's hobbies, values, and communication style from the received message data. The input is anonymized message data received from the terminal, which is then analyzed to generate a user profile. The output is profile information such as the user's hobbies and values. Specifically, TextBlob is used to perform semantic analysis of the data and extract user characteristics.

[0393] Step 3:

[0394] The server uses a generative AI model to predict the user's emotional state from profile information and the latest message context. The input consists of extracted profile information and message data, which are processed to estimate the emotional state. The output is the user's emotional state data. Specifically, the generative AI determines the user's emotion (positive, negative, or neutral) from the word choices and writing style within the messages.

[0395] Step 4:

[0396] The server selects the most suitable content based on the user's emotional state, utilizing content selection methods. It receives emotional state data as input and selects content candidates based on that data. The output is content information recommended to the user. Specifically, it might select relaxation music if the user's emotions are negative, or an action movie if their emotions are positive.

[0397] Step 5:

[0398] The server notifies the device of the selected content information and presents it to the user. The input is the selected content information, which is sent to the device. The output is the recommended content displayed on the user's device. Specifically, when the user taps the notification they receive, they are connected to a link where they can view the recommended content.

[0399] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0400] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0401] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0402] [Third Embodiment]

[0403] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0404] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0405] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0406] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0407] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0408] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0409] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0410] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0411] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0412] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0413] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0414] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0415] This invention relates to providing a messaging system that personalizes user matching and facilitates smooth communication. This system collects and analyzes user data to recommend the most suitable partner to each individual user.

[0416] First, the server anonymizes and collects the user's message history from the messaging application terminal they are using. This allows the server to identify the user's interests and values ​​based on their conversations while ensuring privacy. The server then analyzes this data to extract the user's hobbies, values, and communication style, and generates a profile.

[0417] Next, the server uses the generated profile to apply the generative model and selects other users who are expected to be a good match for the user as partner matching candidates. The selected candidates are then presented to the user in order of recommendation based on past data and feedback, determined by an algorithm.

[0418] Furthermore, the server provides a means to support initial conversations. Based on the hobbies and interests of potential matches, the server generates conversation topics and example questions, which users can use to initiate natural interactions.

[0419] The system's feedback learning module allows the server to continuously monitor users' daily chat data and learn new preferences and characteristics. This new information is then reflected in the selection of future matching candidates. As a result, the system can always adapt to the latest user preferences and improve the accuracy of recommendations.

[0420] For example, if a user repeatedly sends messages indicating interest in visiting art museums, the server adds this information to their profile and prioritizes recommending potential partners who share their interest in art. As a result, users can meet partners who match their interests and enjoy fulfilling communication.

[0421] Thus, the present invention improves the user experience by achieving highly accurate matching that meets user expectations and providing smooth and engaging communication.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The system collects message history sent and received via LINE from the device. The server anonymizes this message data and stores it in a database while ensuring privacy.

[0425] Step 2:

[0426] The server uses natural language processing algorithms to analyze the collected message history. This extracts the user's hobbies, values, and communication style, and generates individual user profiles.

[0427] Step 3:

[0428] Based on the generated user profile, the server applies a matching algorithm to select other users who are considered a good match for the user as potential partner match candidates. This process takes into account past matching data and user feedback.

[0429] Step 4:

[0430] The server creates a list of selected matching candidates and notifies the user of this list. The user can then select a partner they are interested in from the provided list of candidates.

[0431] Step 5:

[0432] The server generates conversation topics and example questions related to the hobbies and interests of the selected partner match to facilitate an effective initial conversation. Users can leverage this support to start a natural conversation.

[0433] Step 6:

[0434] The server continuously monitors daily chat data and learns new user preferences and communication characteristics. This allows the feedback learning module to accumulate information to make future matching more accurate.

[0435] Step 7:

[0436] Based on the updated learning results, the server updates the relevant matching algorithms and performs processes to improve the accuracy of recommending the best partner for the user.

[0437] (Example 1)

[0438] Next, we will describe Example 1. 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."

[0439] In recent years, with the advancement of communication technology, online interaction between users has increased. However, conventional systems have been insufficient in providing individualized support based on the diverse interests and values ​​of users, often resulting in one-sided recommendations. Furthermore, there was a lack of support to smoothly initiate initial conversations, hindering effective communication. In addition, as users' interests and preferences change over time, systems have been unable to adequately respond to these changes.

[0440] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0441] This invention includes a server that collects anonymized user data and extracts the user's hobbies, values, and communication style from the acquired message history; a means for recommending the most suitable partner based on the collected data using a generative AI model; and a means for providing support to facilitate a natural initial conversation. This enables highly accurate matching based on each user's individual profile and a smooth start to the initial conversation. Furthermore, a feedback learning module allows for continuous learning of user preferences and adaptive improvement of recommendation accuracy.

[0442] "Anonymized user data" refers to user information that has been transformed into an unidentifiable form by removing personally identifiable information.

[0443] "Message history" refers to a record of past conversations and communications that a user has had online.

[0444] "Hobbies" refer to activities that users enjoy doing or things they are interested in.

[0445] "Values" refer to the beliefs and attitudes that users have regarding what they focus on or consider important.

[0446] "Communication style" refers to the methods and characteristics of how users exchange information with others.

[0447] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze data and generate new information or predictions.

[0448] "Dialogue support" refers to means of assisting users in starting and continuing smooth communication with others.

[0449] A "feedback learning module" refers to a component that includes a learning function that analyzes user data and responses and incorporates them into future recommendations.

[0450] An "individual profile" refers to a set of information that summarizes a user's individual characteristics, such as their hobbies and values.

[0451] "Matching candidates" refer to other users who are deemed to be a good match for the user.

[0452] "Communication patterns" refer to behavioral characteristics that indicate the tendencies and frequency of how users communicate.

[0453] This invention relates to a messaging system that personalizes user matching and facilitates smooth communication. The system aims to recommend the most suitable partner to each individual user by collecting and analyzing user data.

[0454] First, the server anonymizes and collects message history from the messaging application terminal used by the user. At this stage, techniques are used to hash personally identifiable information in order to protect data privacy. The collected data is analyzed using natural language processing (NLP) techniques. This analysis extracts the user's hobbies, values, and communication style, and generates an individual profile.

[0455] Next, based on this profile, the server applies a generative AI model. This generative AI model uses the user's information as input parameters to recommend other users that it deems to be a good match for the user. This matching algorithm is continuously optimized using historical data and feedback.

[0456] Furthermore, the server provides conversational support to ensure a smooth start to the first conversation. Specifically, it uses an AI model to automatically generate conversation topics and example questions based on the hobbies and interests of potential matches. Users can then leverage these resources provided by the server to initiate natural interactions.

[0457] Finally, the system uses a feedback learning module to continuously monitor the user's daily chat data and learn new preferences and characteristics. This new information is then reflected in the selection of matching candidates for the next time. For example, a prompt such as "Recommend a partner suitable for a user who enjoys visiting art museums" is input into the generating AI model, and partners based on this information are presented to the user. In this way, the system can constantly adapt to the latest user preferences and provide appropriate matching and smooth communication.

[0458] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0459] Step 1:

[0460] The server collects message history from the terminal where the user's messaging application is running. The input used is the user's conversation history data. Specifically, it employs anonymization techniques to remove personally identifiable information from this data. The output is message data in a form that protects personal information.

[0461] Step 2:

[0462] The server analyzes the anonymized message data collected in Step 1. Anonymized message history is used as input data. Natural language processing (NLP) techniques are applied to extract keywords from the messages and identify the user's hobbies, values, and communication style. This data processing outputs an individual user profile.

[0463] Step 3:

[0464] The server uses a generative AI model to select matching candidates based on user profiles. Individual profiles are fed to the generative AI model as input, and after similarity calculations, other users who are expected to be a good match are selected. The output is a group of matching candidates assigned recommendation ranks.

[0465] Step 4:

[0466] The server provides dialogue support to ensure that the first interaction between matched users proceeds smoothly. The input is profile information of the matching candidates, and a generative AI model is used to generate prompt sentences for conversation topics and example questions. These prompt sentences are then generated and provided to the user as output.

[0467] Step 5:

[0468] The server continuously monitors user message data through a feedback learning module, learning new preferences and patterns. Everyday conversation data is used as input, and the information is analyzed by machine learning algorithms. This information is then fed back into the next matching process to improve recommendation accuracy. The output is an updated user profile and refined matching candidates.

[0469] (Application Example 1)

[0470] Next, we will explain Application Example 1. In the following explanation, 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."

[0471] In modern information and communication technology, achieving appropriate and effective matching between users is not easy. In particular, in online content distribution services, it is difficult for users to naturally interact with other users who share their interests. This limits the user experience and reduces the value of the service.

[0472] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0473] In this invention, the server includes means for collecting user data while anonymizing it and extracting hobbies and values ​​from message history, means for incorporating a generative model that recommends the most suitable target based on the collected data, and means for generating relevant conversation topics based on the user's interests. This makes it easier for users to initiate natural conversations with people who match their interests within the service, improving the quality of communication and enhancing the overall user experience.

[0474] "User data" refers to information about individual users, including their interests, values, and communication style.

[0475] "Anonymization" is the process of removing or concealing elements that could identify an individual from collected data in order to prevent the identification of that individual.

[0476] "Message history" refers to a record of the content of communications sent and received by a user, and is used for analyzing their interests and values.

[0477] A "generative model" is an algorithm or framework for analyzing data and providing optimal recommendations to individual users.

[0478] The "feedback learning module" is a mechanism that continuously learns from the user's behavior and reactions to improve the accuracy of recommendations.

[0479] "Conversation support" is a function that assists communication between users by providing suggestions and instructions to improve the smoothness of the conversation.

[0480] A "profile" is a dataset that represents the characteristics of a user, constructed based on collected information.

[0481] "Matching candidates" are other users who have been selected based on the user's interests and values, and who have the potential to interact with the user.

[0482] "Monitoring" refers to the act of observing a user's behavior and interactions, and recording or analyzing the data.

[0483] "Communication patterns" refer to the specific tendencies and styles that a user exhibits in conversation.

[0484] In the system that implements this invention, the server collects user data anonymized and handles message history. This involves using data processing techniques to identify the user's hobbies, values, and communication style from their conversation history. Specifically, the CountVectorizer from scikit-learn is used to vectorize the user's message content and extract important features.

[0485] This system incorporates a generative model, which is used to recommend the most suitable target. To calculate compatibility with users, it calculates the cosine similarity between vectors and selects users with good compatibility. Scikit-learn is also used for this process.

[0486] The server incorporates a feedback learning module that continuously monitors daily conversation records and learns the user's interests. This process involves continuous data collection and analysis, and the information obtained is reflected in the next recommendation candidates.

[0487] For example, if a user shows interest in movies, this trait is added to their profile, and other users who also enjoy movies are recommended preferentially. This allows users to naturally start conversations about a common topic.

[0488] Furthermore, the server generates conversation topics based on the user's interests to support the dialogue. The generative AI model used for this purpose suggests relevant conversation topics based on past data. These suggestions are presented as prompts, such as, "Please suggest conversation starters on topics that the user is interested in."

[0489] Example of a prompt:

[0490] "Please suggest conversation starters related to topics that users are interested in."

[0491] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0492] Step 1:

[0493] The server collects anonymized user message history from each device. Here, data related to sending and receiving messages is compiled and anonymized to prevent the identification of individuals. The input is the user's raw message data, and the output is anonymized message history data.

[0494] Step 2:

[0495] The server extracts the user's hobbies, values, and communication style based on anonymized message history. It uses scikit-learn's CountVectorizer to vectorize messages and capture key features within the text. The input is an anonymized message history, and the output is a user feature vector.

[0496] Step 3:

[0497] The server uses a generative model to recommend the most suitable partner based on the collected feature vectors. It calculates cosine similarity and selects users deemed to be a good match as matching candidates. In this process, the input is the user's feature vector, and the output is a list of compatible candidates.

[0498] Step 4:

[0499] The server generates conversation topics for matching candidates. It utilizes a generative AI model that takes into account common interests with the candidates. The input is a list of matching candidates and the user's interest profile, and the output is a list of conversation topics.

[0500] Step 5:

[0501] The server notifies each user of the topic of the generated conversation and the matching results. The notification includes suggestions using prompts. Prompts such as "Please suggest conversation starters on topics that the user may be interested in" are prepared. The input is a list of conversation topics and matching results, and the output is the notification content for the user.

[0502] Step 6:

[0503] Users utilize suggestions received from the server to naturally initiate communication with potential matches. This process involves starting an active dialogue based on the notified topic.

[0504] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0505] This invention relates to a system for recognizing users' emotions in a user-to-user matching service and utilizing this information in the conversation and matching process. Specifically, it detects emotions through users' messaging activities and uses this information to optimize communication support and partner selection.

[0506] First, the device collects the user's message history. This data is anonymized and securely managed on a server. The server uses natural language processing to analyze the user's messages and generate a profile of their interests, values, and communication style.

[0507] Next, the server uses an emotion engine to determine the user's emotions in real time from the message content. This emotion data is used to evaluate what emotional state the user is in, such as joy, sadness, or anger. For example, if the emotion analysis reveals that the user is feeling stressed, the server will provide appropriate communication support, offering topics and suggestions to alleviate that stress.

[0508] Furthermore, the server selects the most suitable partner candidates based on the collected profile information and emotional data. This process also takes emotional compatibility into consideration, and is adjusted to ensure that users are matched with partners with whom they can communicate comfortably.

[0509] During the conversation support phase, the server generates appropriate conversation topics and questions based on the selected partner's hobbies and emotional state. This allows the user to initiate a natural and effective conversation tailored to the other person's situation.

[0510] Furthermore, the emotion engine and feedback learning module work together, and the server tracks changes in the user's emotions from everyday chats. This data will be used to improve future matching algorithms and communication support, providing an experience optimized for each individual user.

[0511] For example, if the emotion engine determines that a user is enjoying a new hobby, the server will prioritize other users who share that hobby as matching candidates. In this way, the present invention can dynamically understand the user's emotions and improve the quality of the matching and communication experience, thereby increasing user satisfaction.

[0512] The following describes the processing flow.

[0513] Step 1:

[0514] The device collects messages sent through the user's messaging app. The collected messages are anonymized under appropriate security measures and sent to the server.

[0515] Step 2:

[0516] The server analyzes the received messages using natural language processing technology. This extracts hobbies, values, and communication styles to generate a profile for each user.

[0517] Step 3:

[0518] The server uses an emotion engine to determine the user's emotional state from the message. For example, it analyzes whether the user is experiencing emotions such as joy, sadness, or anger based on the content of the text and the characteristics of the words used.

[0519] Step 4:

[0520] The server compares the generated profile information with emotional data to select the most suitable partner matching candidates. Here, emotional compatibility and commonalities in profiles are also considered to enhance the suitability between users.

[0521] Step 5:

[0522] The server notifies the user of a list of selected partner matching candidates. The user then selects someone they are interested in from this list and prepares to start a conversation.

[0523] Step 6:

[0524] Based on the results of the emotion engine, the server generates conversation topics and questions to support the initial conversation with the selected partner. Users can use these suggestions to initiate a more personalized conversation.

[0525] Step 7:

[0526] The server continuously monitors chats between users and tracks changes in their emotions. The collected emotional data is sent to a feedback learning module and used to optimize future matching and conversation support.

[0527] (Example 2)

[0528] Next, we will describe Example 2. 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."

[0529] Conventional user matching systems have struggled to select the optimal partner based on users' emotional compatibility and circumstances, resulting in insufficient user satisfaction. Furthermore, there was a lack of means to understand users' emotional changes in real time and improve the communication experience.

[0530] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0531] In this invention, the server includes means for collecting user data anonymized and extracting interests, values, and dialogue styles; means for incorporating a generative model that recommends optimal interaction candidates; and means for analyzing the user's emotional state in real time and providing dialogue support that responds to those emotions. This enables highly accurate recommendation of interaction candidates based on the user's emotions and individual profile, as well as optimal communication support that responds to those emotions.

[0532] "User data" is a general term for data obtained from user behavior, messages, and related information.

[0533] "Anonymization" is a process that protects the privacy of data subjects by removing or transforming information that could identify an individual.

[0534] "Interest" refers to the tendency a user shows to be interested in a particular activity or topic.

[0535] "Value" refers to the beliefs and principles that users consider important, and it influences their decision-making and actions.

[0536] "Conversational style" refers to the unique style or pattern that users exhibit in their communication.

[0537] A "generative model" is a type of AI that uses algorithms to generate potential partners and conversation content based on user data.

[0538] "Emotional state" refers to the psychological or emotional state a user is experiencing at a particular point in time.

[0539] A "feedback learning module" is a module that continuously analyzes users' past behavioral data and has the functionality to improve the overall accuracy and adaptability of the system.

[0540] "Interaction candidates" refer to conversation partners that the system recommends as suitable partners for the user.

[0541] To implement this invention, the main elements required are a user terminal, a server for processing data, and a generative AI model. The roles and operations of each are described below.

[0542] First, the user accesses the messaging service using their device. The device automatically collects the user's message history, but all of this data is anonymized before being sent to the server. Anonymizing the collected data is an important step in protecting user privacy.

[0543] The server securely stores the received data and uses natural language processing (NLP) techniques to analyze the user's interests, values, and conversational style. This process may involve using open-source NLP libraries and machine learning platforms. For example, libraries such as TensorFlow and PyTorch can be used to analyze the data. The analyzed information is then used to create individual profiles for each user.

[0544] The generative AI model uses this profile information to recommend the best possible interactions between users. This model extracts the user's emotional state in real time and tracks all changes that occur during the conversation, enabling highly accurate recommendations. For example, if a user sends a message such as, "The weather has been nice these past few days, and I'm in a good mood," the server will interpret this as a positive emotional expression and suggest users with similar emotions as potential interactions.

[0545] Furthermore, the server tracks emotional changes and improves overall system performance through a feedback learning module. This allows it to quickly adapt to changes in the user's emotions and behavioral patterns, providing appropriate communication support. Examples of specific prompts include "Let's talk about your recent hobbies!" and "Is there any news that interests you?". These prompts are dynamically generated to match the user's interests and emotions, making the conversation natural and engaging.

[0546] In this way, the present invention can provide highly accurate recommendation of interaction candidates based on the user's emotions and individual profile, as well as optimal communication support tailored to those emotions.

[0547] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0548] Step 1:

[0549] The device collects the user's message history. It takes text data sent and received by the user via messaging apps as input and performs anonymization on this data. Once the anonymization process is complete, the data is sent to the server.

[0550] Step 2:

[0551] The server stores the received anonymized data in a secure database. This step uses anonymized message data sent from the terminal as input and performs data processing by storing it in the database. The output is the stored message data.

[0552] Step 3:

[0553] The server analyzes the data using natural language processing techniques. In this step, message data is retrieved from the database, and interests, values, and conversational styles are extracted. This data processing outputs profile information from the input messages.

[0554] Step 4:

[0555] The server uses a generative AI model to calculate the optimal interaction candidates from profile information. It uses profile information as input and performs data calculations using an algorithm. The output is a list of interaction candidates, including the candidate's profile information.

[0556] Step 5:

[0557] The server uses an emotion engine to analyze the user's emotional state in real time. The input is the latest chat message, and the emotional state is output after emotion analysis. In operation, it tracks the progression of emotions and uses this information to generate prompt messages as needed.

[0558] Step 6:

[0559] The server is equipped with a feedback learning module that continuously learns user preferences. It uses past interaction history and emotion change history as input to apply a learning algorithm and improve recommendation accuracy. The output is the improved recommendation algorithm.

[0560] Step 7:

[0561] The server generates prompt sentences using a generative AI model based on each user's emotional state and profile information. Using the emotional states and profiles of potential interaction candidates as input, the server performs algorithmic data calculations to output appropriate conversation topics and questions.

[0562] (Application Example 2)

[0563] Next, we will explain application example 2. In the following explanation, 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."

[0564] Conventional user content recommendation systems have had the problem of difficulty in providing optimal content based on the user's emotions and recent communications. While typical recommendation systems primarily recommend content based on the user's past behavior history, recommendations that take the user's current emotional state into account are rarely performed. This invention aims to provide a more personalized experience by recommending appropriate content that takes the user's emotions into account.

[0565] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0566] In this invention, the server includes means for anonymizing and collecting user data and extracting hobbies, values, and communication styles from message history; means for incorporating a generative model that recommends optimal information based on the collected data; and means for selecting content that optimizes the suggested content according to the user's emotional state. This enables personalized content recommendations based on the user's emotions.

[0567] "User data" refers to information associated with individual users, including their hobbies, values, and communication style.

[0568] "Anonymization" refers to the process of removing personal information from data so that specific individuals cannot be identified.

[0569] A "generative model" refers to an algorithm or method that generates new information or content based on data input.

[0570] A "feedback learning module" includes algorithms that continuously improve the accuracy of the model or system based on the user's behavior and reactions.

[0571] "Emotional state" refers to a temporary mental state expressed by a user based on their messages and actions.

[0572] "Content selection methods" refer to methods and devices for selecting the most suitable information and entertainment based on the user's preferences and emotions.

[0573] "Natural language processing" includes technologies that enable computers to understand, analyze, and generate human language.

[0574] This invention concretely realizes a content recommendation system based on user emotions, in which the server and terminal work together. The server uses a natural language processing library such as TextBlob to analyze message history data collected from the terminal. From the analyzed data, the user's hobbies, values, and communication style are extracted and securely stored as a user profile.

[0575] The server also uses a generative AI model to estimate the user's emotional state in real time based on the obtained profile. The emotional state is evaluated as positive, negative, or neutral. Based on this information, content selection mechanisms are activated to select information and entertainment optimized for the user.

[0576] For example, if a user sends a message like "I've been feeling tired lately," the server will recognize this as a negative emotion and recommend relaxation music or meditation videos. Conversely, if positive emotions are recognized, it can recommend action movies or positive news.

[0577] The specific hardware used includes terminals for collecting user data (e.g., smartphones) and servers for storing and analyzing that data. On the software side, libraries such as TextBlob are used to support natural language processing techniques.

[0578] An example of a prompt message would be, "Write a program that suggests stress-reducing content when the user is busy and tired." This makes it possible to provide the user with appropriate content that matches their current emotional state.

[0579] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0580] Step 1:

[0581] The device collects the user's message history and sends it to the server. The input is past messages the user has used on the device, which are anonymized and sent to the server. The output is anonymized message data. Specifically, the content of conversations the user has with friends in a chat app is stored on the device and later transferred to the server in a format that can be analyzed.

[0582] Step 2:

[0583] The server uses natural language processing to extract information about the user's hobbies, values, and communication style from the received message data. The input is anonymized message data received from the terminal, which is then analyzed to generate a user profile. The output is profile information such as the user's hobbies and values. Specifically, TextBlob is used to perform semantic analysis of the data and extract user characteristics.

[0584] Step 3:

[0585] The server uses a generative AI model to predict the user's emotional state from profile information and the latest message context. The input consists of extracted profile information and message data, which are processed to estimate the emotional state. The output is the user's emotional state data. Specifically, the generative AI determines the user's emotion (positive, negative, or neutral) from the word choices and writing style within the messages.

[0586] Step 4:

[0587] The server selects the most suitable content based on the user's emotional state, utilizing content selection methods. It receives emotional state data as input and selects content candidates based on that data. The output is content information recommended to the user. Specifically, it might select relaxation music if the user's emotions are negative, or an action movie if their emotions are positive.

[0588] Step 5:

[0589] The server notifies the device of the selected content information and presents it to the user. The input is the selected content information, which is sent to the device. The output is the recommended content displayed on the user's device. Specifically, when the user taps the notification they receive, they are connected to a link where they can view the recommended content.

[0590] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0591] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0592] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0593] [Fourth Embodiment]

[0594] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0595] As shown in Figure 7, the 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.

[0596] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0597] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0598] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0599] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0600] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0601] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0602] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0603] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0604] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0605] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0606] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0607] This invention relates to providing a messaging system that personalizes user matching and facilitates smooth communication. This system collects and analyzes user data to recommend the most suitable partner to each individual user.

[0608] First, the server anonymizes and collects the user's message history from the messaging application terminal they are using. This allows the server to identify the user's interests and values ​​based on their conversations while ensuring privacy. The server then analyzes this data to extract the user's hobbies, values, and communication style, and generates a profile.

[0609] Next, the server uses the generated profile to apply the generative model and selects other users who are expected to be a good match for the user as partner matching candidates. The selected candidates are then presented to the user in order of recommendation based on past data and feedback, determined by an algorithm.

[0610] Furthermore, the server provides a means to support initial conversations. Based on the hobbies and interests of potential matches, the server generates conversation topics and example questions, which users can use to initiate natural interactions.

[0611] The system's feedback learning module allows the server to continuously monitor users' daily chat data and learn new preferences and characteristics. This new information is then reflected in the selection of future matching candidates. As a result, the system can always adapt to the latest user preferences and improve the accuracy of recommendations.

[0612] For example, if a user repeatedly sends messages indicating interest in visiting art museums, the server adds this information to their profile and prioritizes recommending potential partners who share their interest in art. As a result, users can meet partners who match their interests and enjoy fulfilling communication.

[0613] Thus, the present invention improves the user experience by achieving highly accurate matching that meets user expectations and providing smooth and engaging communication.

[0614] The following describes the processing flow.

[0615] Step 1:

[0616] The system collects message history sent and received via LINE from the device. The server anonymizes this message data and stores it in a database while ensuring privacy.

[0617] Step 2:

[0618] The server uses natural language processing algorithms to analyze the collected message history. This extracts the user's hobbies, values, and communication style, and generates individual user profiles.

[0619] Step 3:

[0620] Based on the generated user profile, the server applies a matching algorithm to select other users who are considered a good match for the user as potential partner match candidates. This process takes into account past matching data and user feedback.

[0621] Step 4:

[0622] The server creates a list of selected matching candidates and notifies the user of this list. The user can then select a partner they are interested in from the provided list of candidates.

[0623] Step 5:

[0624] The server generates conversation topics and example questions related to the hobbies and interests of the selected partner match to facilitate an effective initial conversation. Users can leverage this support to start a natural conversation.

[0625] Step 6:

[0626] The server continuously monitors daily chat data and learns new user preferences and communication characteristics. This allows the feedback learning module to accumulate information to make future matching more accurate.

[0627] Step 7:

[0628] Based on the updated learning results, the server updates the relevant matching algorithms and performs processes to improve the accuracy of recommending the best partner for the user.

[0629] (Example 1)

[0630] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0631] In recent years, with the advancement of communication technology, online interaction between users has increased. However, conventional systems have been insufficient in providing individualized support based on the diverse interests and values ​​of users, often resulting in one-sided recommendations. Furthermore, there was a lack of support to smoothly initiate initial conversations, hindering effective communication. In addition, as users' interests and preferences change over time, systems have been unable to adequately respond to these changes.

[0632] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0633] This invention includes a server that collects anonymized user data and extracts the user's hobbies, values, and communication style from the acquired message history; a means for recommending the most suitable partner based on the collected data using a generative AI model; and a means for providing support to facilitate a natural initial conversation. This enables highly accurate matching based on each user's individual profile and a smooth start to the initial conversation. Furthermore, a feedback learning module allows for continuous learning of user preferences and adaptive improvement of recommendation accuracy.

[0634] "Anonymized user data" refers to user information that has been transformed into an unidentifiable form by removing personally identifiable information.

[0635] "Message history" refers to a record of past conversations and communications that a user has had online.

[0636] "Hobbies" refer to activities that users enjoy doing or things they are interested in.

[0637] "Values" refer to the beliefs and attitudes that users have regarding what they focus on or consider important.

[0638] "Communication style" refers to the methods and characteristics of how users exchange information with others.

[0639] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze data and generate new information or predictions.

[0640] "Dialogue support" refers to means of assisting users in starting and continuing smooth communication with others.

[0641] A "feedback learning module" refers to a component that includes a learning function that analyzes user data and responses and incorporates them into future recommendations.

[0642] An "individual profile" refers to a set of information that summarizes a user's individual characteristics, such as their hobbies and values.

[0643] "Matching candidates" refer to other users who are deemed to be a good match for the user.

[0644] "Communication patterns" refer to behavioral characteristics that indicate the tendencies and frequency of how users communicate.

[0645] This invention relates to a messaging system that personalizes user matching and facilitates smooth communication. The system aims to recommend the most suitable partner to each individual user by collecting and analyzing user data.

[0646] First, the server anonymizes and collects message history from the messaging application terminal used by the user. At this stage, techniques are used to hash personally identifiable information in order to protect data privacy. The collected data is analyzed using natural language processing (NLP) techniques. This analysis extracts the user's hobbies, values, and communication style, and generates an individual profile.

[0647] Next, based on this profile, the server applies a generative AI model. This generative AI model uses the user's information as input parameters to recommend other users that it deems to be a good match for the user. This matching algorithm is continuously optimized using historical data and feedback.

[0648] Furthermore, the server provides conversational support to ensure a smooth start to the first conversation. Specifically, it uses an AI model to automatically generate conversation topics and example questions based on the hobbies and interests of potential matches. Users can then leverage these resources provided by the server to initiate natural interactions.

[0649] Finally, the system uses a feedback learning module to continuously monitor the user's daily chat data and learn new preferences and characteristics. This new information is then reflected in the selection of matching candidates for the next time. For example, a prompt such as "Recommend a partner suitable for a user who enjoys visiting art museums" is input into the generating AI model, and partners based on this information are presented to the user. In this way, the system can constantly adapt to the latest user preferences and provide appropriate matching and smooth communication.

[0650] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0651] Step 1:

[0652] The server collects message history from the terminal where the user's messaging application is running. The input used is the user's conversation history data. Specifically, it employs anonymization techniques to remove personally identifiable information from this data. The output is message data in a form that protects personal information.

[0653] Step 2:

[0654] The server analyzes the anonymized message data collected in Step 1. Anonymized message history is used as input data. Natural language processing (NLP) techniques are applied to extract keywords from the messages and identify the user's hobbies, values, and communication style. This data processing outputs an individual user profile.

[0655] Step 3:

[0656] The server uses a generative AI model to select matching candidates based on user profiles. Individual profiles are fed to the generative AI model as input, and after similarity calculations, other users who are expected to be a good match are selected. The output is a group of matching candidates assigned recommendation ranks.

[0657] Step 4:

[0658] The server provides dialogue support to ensure that the first interaction between matched users proceeds smoothly. The input is profile information of the matching candidates, and a generative AI model is used to generate prompt sentences for conversation topics and example questions. These prompt sentences are then generated and provided to the user as output.

[0659] Step 5:

[0660] The server continuously monitors user message data through a feedback learning module, learning new preferences and patterns. Everyday conversation data is used as input, and the information is analyzed by machine learning algorithms. This information is then fed back into the next matching process to improve recommendation accuracy. The output is an updated user profile and refined matching candidates.

[0661] (Application Example 1)

[0662] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0663] In modern information and communication technology, achieving appropriate and effective matching between users is not easy. In particular, in online content distribution services, it is difficult for users to naturally interact with other users who share their interests. This limits the user experience and reduces the value of the service.

[0664] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0665] In this invention, the server includes means for collecting user data while anonymizing it and extracting hobbies and values ​​from message history, means for incorporating a generative model that recommends the most suitable target based on the collected data, and means for generating relevant conversation topics based on the user's interests. This makes it easier for users to initiate natural conversations with people who match their interests within the service, improving the quality of communication and enhancing the overall user experience.

[0666] "User data" refers to information about individual users, including their interests, values, and communication style.

[0667] "Anonymization" is the process of removing or concealing elements that could identify an individual from collected data in order to prevent the identification of that individual.

[0668] "Message history" refers to a record of the content of communications sent and received by a user, and is used for analyzing their interests and values.

[0669] A "generative model" is an algorithm or framework for analyzing data and providing optimal recommendations to individual users.

[0670] The "feedback learning module" is a mechanism that continuously learns from the user's behavior and reactions to improve the accuracy of recommendations.

[0671] "Conversation support" is a function that assists communication between users by providing suggestions and instructions to improve the smoothness of the conversation.

[0672] A "profile" is a dataset that represents the characteristics of a user, constructed based on collected information.

[0673] "Matching candidates" are other users who have been selected based on the user's interests and values, and who have the potential to interact with the user.

[0674] "Monitoring" refers to the act of observing a user's behavior and interactions, and recording or analyzing the data.

[0675] "Communication patterns" refer to the specific tendencies and styles that a user exhibits in conversation.

[0676] In the system that implements this invention, the server collects user data anonymized and handles message history. This involves using data processing techniques to identify the user's hobbies, values, and communication style from their conversation history. Specifically, the CountVectorizer from scikit-learn is used to vectorize the user's message content and extract important features.

[0677] This system incorporates a generative model, which is used to recommend the most suitable target. To calculate compatibility with users, it calculates the cosine similarity between vectors and selects users with good compatibility. Scikit-learn is also used for this process.

[0678] The server incorporates a feedback learning module that continuously monitors daily conversation records and learns the user's interests. This process involves continuous data collection and analysis, and the information obtained is reflected in the next recommendation candidates.

[0679] For example, if a user shows interest in movies, this trait is added to their profile, and other users who also enjoy movies are recommended preferentially. This allows users to naturally start conversations about a common topic.

[0680] Furthermore, the server generates conversation topics based on the user's interests to support the dialogue. The generative AI model used for this purpose suggests relevant conversation topics based on past data. These suggestions are presented as prompts, such as, "Please suggest conversation starters on topics that the user is interested in."

[0681] Example of a prompt:

[0682] "Please suggest conversation starters related to topics that users are interested in."

[0683] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0684] Step 1:

[0685] The server collects anonymized user message history from each device. Here, data related to sending and receiving messages is compiled and anonymized to prevent the identification of individuals. The input is the user's raw message data, and the output is anonymized message history data.

[0686] Step 2:

[0687] The server extracts the user's hobbies, values, and communication style based on anonymized message history. It uses scikit-learn's CountVectorizer to vectorize messages and capture key features within the text. The input is an anonymized message history, and the output is a user feature vector.

[0688] Step 3:

[0689] The server uses a generative model to recommend the most suitable partner based on the collected feature vectors. It calculates cosine similarity and selects users deemed to be a good match as matching candidates. In this process, the input is the user's feature vector, and the output is a list of compatible candidates.

[0690] Step 4:

[0691] The server generates conversation topics for matching candidates. It utilizes a generative AI model that takes into account common interests with the candidates. The input is a list of matching candidates and the user's interest profile, and the output is a list of conversation topics.

[0692] Step 5:

[0693] The server notifies each user of the topic of the generated conversation and the matching results. The notification includes suggestions using prompts. Prompts such as "Please suggest conversation starters on topics that the user may be interested in" are prepared. The input is a list of conversation topics and matching results, and the output is the notification content for the user.

[0694] Step 6:

[0695] Users utilize suggestions received from the server to naturally initiate communication with potential matches. This process involves starting an active dialogue based on the notified topic.

[0696] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0697] This invention relates to a system for recognizing users' emotions in a user-to-user matching service and utilizing this information in the conversation and matching process. Specifically, it detects emotions through users' messaging activities and uses this information to optimize communication support and partner selection.

[0698] First, the device collects the user's message history. This data is anonymized and securely managed on a server. The server uses natural language processing to analyze the user's messages and generate a profile of their interests, values, and communication style.

[0699] Next, the server uses an emotion engine to determine the user's emotions in real time from the message content. This emotion data is used to evaluate what emotional state the user is in, such as joy, sadness, or anger. For example, if the emotion analysis reveals that the user is feeling stressed, the server will provide appropriate communication support, offering topics and suggestions to alleviate that stress.

[0700] Furthermore, the server selects the most suitable partner candidates based on the collected profile information and emotional data. This process also takes emotional compatibility into consideration, and is adjusted to ensure that users are matched with partners with whom they can communicate comfortably.

[0701] During the conversation support phase, the server generates appropriate conversation topics and questions based on the selected partner's hobbies and emotional state. This allows the user to initiate a natural and effective conversation tailored to the other person's situation.

[0702] Furthermore, the emotion engine and feedback learning module work together, and the server tracks changes in the user's emotions from everyday chats. This data will be used to improve future matching algorithms and communication support, providing an experience optimized for each individual user.

[0703] For example, if the emotion engine determines that a user is enjoying a new hobby, the server will prioritize other users who share that hobby as matching candidates. In this way, the present invention can dynamically understand the user's emotions and improve the quality of the matching and communication experience, thereby increasing user satisfaction.

[0704] The following describes the processing flow.

[0705] Step 1:

[0706] The device collects messages sent through the user's messaging app. The collected messages are anonymized under appropriate security measures and sent to the server.

[0707] Step 2:

[0708] The server analyzes the received messages using natural language processing technology. This extracts hobbies, values, and communication styles to generate a profile for each user.

[0709] Step 3:

[0710] The server uses an emotion engine to determine the user's emotional state from the message. For example, it analyzes whether the user is experiencing emotions such as joy, sadness, or anger based on the content of the text and the characteristics of the words used.

[0711] Step 4:

[0712] The server compares the generated profile information with emotional data to select the most suitable partner matching candidates. Here, emotional compatibility and commonalities in profiles are also considered to enhance the suitability between users.

[0713] Step 5:

[0714] The server notifies the user of a list of selected partner matching candidates. The user then selects someone they are interested in from this list and prepares to start a conversation.

[0715] Step 6:

[0716] Based on the results of the emotion engine, the server generates conversation topics and questions to support the initial conversation with the selected partner. Users can use these suggestions to initiate a more personalized conversation.

[0717] Step 7:

[0718] The server continuously monitors chats between users and tracks changes in their emotions. The collected emotional data is sent to a feedback learning module and used to optimize future matching and conversation support.

[0719] (Example 2)

[0720] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0721] Conventional user matching systems have struggled to select the optimal partner based on users' emotional compatibility and circumstances, resulting in insufficient user satisfaction. Furthermore, there was a lack of means to understand users' emotional changes in real time and improve the communication experience.

[0722] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0723] In this invention, the server includes means for collecting user data anonymized and extracting interests, values, and dialogue styles; means for incorporating a generative model that recommends optimal interaction candidates; and means for analyzing the user's emotional state in real time and providing dialogue support that responds to those emotions. This enables highly accurate recommendation of interaction candidates based on the user's emotions and individual profile, as well as optimal communication support that responds to those emotions.

[0724] "User data" is a general term for data obtained from user behavior, messages, and related information.

[0725] "Anonymization" is a process that protects the privacy of data subjects by removing or transforming information that could identify an individual.

[0726] "Interest" refers to the tendency a user shows to be interested in a particular activity or topic.

[0727] "Value" refers to the beliefs and principles that users consider important, and it influences their decision-making and actions.

[0728] "Conversational style" refers to the unique style or pattern that users exhibit in their communication.

[0729] A "generative model" is a type of AI that uses algorithms to generate potential partners and conversation content based on user data.

[0730] "Emotional state" refers to the psychological or emotional state a user is experiencing at a particular point in time.

[0731] A "feedback learning module" is a module that continuously analyzes users' past behavioral data and has the functionality to improve the overall accuracy and adaptability of the system.

[0732] "Interaction candidates" refer to conversation partners that the system recommends as suitable partners for the user.

[0733] To implement this invention, the main elements required are a user terminal, a server for processing data, and a generative AI model. The roles and operations of each are described below.

[0734] First, the user accesses the messaging service using their device. The device automatically collects the user's message history, but all of this data is anonymized before being sent to the server. Anonymizing the collected data is an important step in protecting user privacy.

[0735] The server securely stores the received data and uses natural language processing (NLP) techniques to analyze the user's interests, values, and conversational style. This process may involve using open-source NLP libraries and machine learning platforms. For example, libraries such as TensorFlow and PyTorch can be used to analyze the data. The analyzed information is then used to create individual profiles for each user.

[0736] The generative AI model uses this profile information to recommend the best possible interactions between users. This model extracts the user's emotional state in real time and tracks all changes that occur during the conversation, enabling highly accurate recommendations. For example, if a user sends a message such as, "The weather has been nice these past few days, and I'm in a good mood," the server will interpret this as a positive emotional expression and suggest users with similar emotions as potential interactions.

[0737] Furthermore, the server tracks emotional changes and improves overall system performance through a feedback learning module. This allows it to quickly adapt to changes in the user's emotions and behavioral patterns, providing appropriate communication support. Examples of specific prompts include "Let's talk about your recent hobbies!" and "Is there any news that interests you?". These prompts are dynamically generated to match the user's interests and emotions, making the conversation natural and engaging.

[0738] In this way, the present invention can provide highly accurate recommendation of interaction candidates based on the user's emotions and individual profile, as well as optimal communication support tailored to those emotions.

[0739] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0740] Step 1:

[0741] The device collects the user's message history. It takes text data sent and received by the user via messaging apps as input and performs anonymization on this data. Once the anonymization process is complete, the data is sent to the server.

[0742] Step 2:

[0743] The server stores the received anonymized data in a secure database. This step uses anonymized message data sent from the terminal as input and performs data processing by storing it in the database. The output is the stored message data.

[0744] Step 3:

[0745] The server analyzes the data using natural language processing techniques. In this step, message data is retrieved from the database, and interests, values, and conversational styles are extracted. This data processing outputs profile information from the input messages.

[0746] Step 4:

[0747] The server uses a generative AI model to calculate the optimal interaction candidates from profile information. It uses profile information as input and performs data calculations using an algorithm. The output is a list of interaction candidates, including the candidate's profile information.

[0748] Step 5:

[0749] The server uses an emotion engine to analyze the user's emotional state in real time. The input is the latest chat message, and the emotional state is output after emotion analysis. In operation, it tracks the progression of emotions and uses this information to generate prompt messages as needed.

[0750] Step 6:

[0751] The server is equipped with a feedback learning module that continuously learns user preferences. It uses past interaction history and emotion change history as input to apply a learning algorithm and improve recommendation accuracy. The output is the improved recommendation algorithm.

[0752] Step 7:

[0753] The server generates prompt sentences using a generative AI model based on each user's emotional state and profile information. Using the emotional states and profiles of potential interaction candidates as input, the server performs algorithmic data calculations to output appropriate conversation topics and questions.

[0754] (Application Example 2)

[0755] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0756] Conventional user content recommendation systems have had the problem of difficulty in providing optimal content based on the user's emotions and recent communications. While typical recommendation systems primarily recommend content based on the user's past behavior history, recommendations that take the user's current emotional state into account are rarely performed. This invention aims to provide a more personalized experience by recommending appropriate content that takes the user's emotions into account.

[0757] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0758] In this invention, the server includes means for anonymizing and collecting user data and extracting hobbies, values, and communication styles from message history; means for incorporating a generative model that recommends optimal information based on the collected data; and means for selecting content that optimizes the suggested content according to the user's emotional state. This enables personalized content recommendations based on the user's emotions.

[0759] "User data" refers to information associated with individual users, including their hobbies, values, and communication style.

[0760] "Anonymization" refers to the process of removing personal information from data so that specific individuals cannot be identified.

[0761] A "generative model" refers to an algorithm or method that generates new information or content based on data input.

[0762] A "feedback learning module" includes algorithms that continuously improve the accuracy of the model or system based on the user's behavior and reactions.

[0763] "Emotional state" refers to a temporary mental state expressed by a user based on their messages and actions.

[0764] "Content selection methods" refer to methods and devices for selecting the most suitable information and entertainment based on the user's preferences and emotions.

[0765] "Natural language processing" includes technologies that enable computers to understand, analyze, and generate human language.

[0766] This invention concretely realizes a content recommendation system based on user emotions, in which the server and terminal work together. The server uses a natural language processing library such as TextBlob to analyze message history data collected from the terminal. From the analyzed data, the user's hobbies, values, and communication style are extracted and securely stored as a user profile.

[0767] The server also uses a generative AI model to estimate the user's emotional state in real time based on the obtained profile. The emotional state is evaluated as positive, negative, or neutral. Based on this information, content selection mechanisms are activated to select information and entertainment optimized for the user.

[0768] For example, if a user sends a message like "I've been feeling tired lately," the server will recognize this as a negative emotion and recommend relaxation music or meditation videos. Conversely, if positive emotions are recognized, it can recommend action movies or positive news.

[0769] The specific hardware used includes terminals for collecting user data (e.g., smartphones) and servers for storing and analyzing that data. On the software side, libraries such as TextBlob are used to support natural language processing techniques.

[0770] An example of a prompt message would be, "Write a program that suggests stress-reducing content when the user is busy and tired." This makes it possible to provide the user with appropriate content that matches their current emotional state.

[0771] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0772] Step 1:

[0773] The device collects the user's message history and sends it to the server. The input is past messages the user has used on the device, which are anonymized and sent to the server. The output is anonymized message data. Specifically, the content of conversations the user has with friends in a chat app is stored on the device and later transferred to the server in a format that can be analyzed.

[0774] Step 2:

[0775] The server uses natural language processing to extract information about the user's hobbies, values, and communication style from the received message data. The input is anonymized message data received from the terminal, which is then analyzed to generate a user profile. The output is profile information such as the user's hobbies and values. Specifically, TextBlob is used to perform semantic analysis of the data and extract user characteristics.

[0776] Step 3:

[0777] The server uses a generative AI model to predict the user's emotional state from profile information and the latest message context. The input consists of extracted profile information and message data, which are processed to estimate the emotional state. The output is the user's emotional state data. Specifically, the generative AI determines the user's emotion (positive, negative, or neutral) from the word choices and writing style within the messages.

[0778] Step 4:

[0779] The server selects the most suitable content based on the user's emotional state, utilizing content selection methods. It receives emotional state data as input and selects content candidates based on that data. The output is content information recommended to the user. Specifically, it might select relaxation music if the user's emotions are negative, or an action movie if their emotions are positive.

[0780] Step 5:

[0781] The server notifies the device of the selected content information and presents it to the user. The input is the selected content information, which is sent to the device. The output is the recommended content displayed on the user's device. Specifically, when the user taps the notification they receive, they are connected to a link where they can view the recommended content.

[0782] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0783] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0784] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0785] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0786] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0787] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0788] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0789] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0790] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0791] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0792] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0793] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0794] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0795] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0796] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0797] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0798] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0799] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0800] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0801] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0802] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0803] The following is further disclosed regarding the embodiments described above.

[0804] (Claim 1)

[0805] A method for collecting user data anonymly and extracting hobbies, values, and communication styles from message history,

[0806] A means of incorporating a generative model that recommends the optimal partner based on collected data,

[0807] A means of providing conversation support to help the initial conversation proceed naturally,

[0808] A means having a feedback learning module that continuously learns user preferences from daily chat data and improves the accuracy of recommendations,

[0809] A means of notifying users of the results of conversation support and partner recommendations,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, comprising means for generating a profile based on collected user data and selecting compatible partner matching candidates based on that profile.

[0813] (Claim 3)

[0814] The system according to claim 1, further comprising means for improving the prediction of the next match by monitoring the user's chat and analyzing their communication patterns.

[0815] "Example 1"

[0816] (Claim 1)

[0817] A method for collecting information by anonymizing user data and extracting hobbies, values, and communication styles from message history,

[0818] A means of incorporating a generative model that recommends the most suitable partner based on collected information,

[0819] A means of providing dialogue support to facilitate the initial conversation,

[0820] A means having a feedback learning module that continuously learns user preferences from everyday message data and improves the accuracy of recommendations,

[0821] A means of notifying users of the results of dialogue support and partner recommendations,

[0822] A means for generating a user profile and selecting compatible matching candidates based on this profile,

[0823] By monitoring user messages and analyzing communication patterns, we can improve predictions for future matches.

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, comprising means for generating individual profiles based on collected user information and selecting the most suitable partner candidate based on those profiles.

[0827] (Claim 3)

[0828] The system according to claim 1, further comprising means for improving the prediction of the next matching by monitoring the content of the user's conversation and analyzing the communication pattern.

[0829] "Application Example 1"

[0830] (Claim 1)

[0831] A method for collecting user data anonymly and extracting hobbies, values, and communication styles from message history,

[0832] A means of incorporating a generative model that recommends the optimal target based on collected data,

[0833] A means of providing dialogue support to facilitate a natural initial conversation,

[0834] A means having a feedback learning module that continuously learns the user's preferences from everyday conversation data and improves the accuracy of recommendations,

[0835] A means of generating relevant conversation topics based on interests,

[0836] A means of notifying users of the results of conversation support and target recommendations,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, comprising means for generating a profile based on collected user data and selecting compatible target matching candidates based on that profile.

[0840] (Claim 3)

[0841] The system according to claim 1, further comprising means for improving the prediction of the next matching by monitoring the user's conversation and analyzing the communication pattern.

[0842] "Example 2 of combining an emotion engine"

[0843] (Claim 1)

[0844] A means for collecting user data anonymized and extracting interests, values, and conversational styles from message history,

[0845] A means of incorporating a generative model that recommends the optimal interaction candidate based on the collected data,

[0846] A means of providing conversational support to facilitate a natural initial conversation,

[0847] A means having a feedback learning module that continuously learns user preferences from daily communication data and improves the accuracy of recommendations,

[0848] A means of analyzing the user's emotional state in real time and providing dialogue support that responds to those emotions,

[0849] A means to track changes in user emotions and improve the accuracy of future interaction algorithms,

[0850] A means of notifying users of the results of conversation support and candidate recommendations,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, comprising means for generating individual information based on collected user data and selecting compatible interaction candidates based on that information.

[0854] (Claim 3)

[0855] The system according to claim 1, further comprising means for improving the prediction of the next interaction by monitoring user communications and analyzing dialogue patterns.

[0856] "Application example 2 when combining with an emotional engine"

[0857] (Claim 1)

[0858] A method for collecting user data anonymly and extracting hobbies, values, and communication styles from message history,

[0859] A means of incorporating a generative model that recommends optimal information based on collected data,

[0860] A content selection method that optimizes suggested content according to the user's emotional state,

[0861] A means having a feedback learning module that continuously learns user preferences from everyday data and improves the accuracy of recommendations,

[0862] A means of notifying users of the results of content proposals,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, comprising means for generating a profile based on collected user data and selecting appropriate content matching candidates based on that profile.

[0866] (Claim 3)

[0867] The system according to claim 1, further comprising means for improving future information recommendations by monitoring user communication and analyzing patterns. [Explanation of Symbols]

[0868] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A method for collecting user data anonymly and extracting hobbies, values, and communication styles from message history, A means of incorporating a generative model that recommends the optimal partner based on collected data, A means of providing conversation support to help the initial conversation proceed naturally, A means having a feedback learning module that continuously learns user preferences from daily chat data and improves the accuracy of recommendations, A means of notifying users of the results of conversation support and partner recommendations, A system that includes this.

2. The system according to claim 1, comprising means for generating a profile based on collected user data and selecting compatible partner matching candidates based on that profile.

3. The system according to claim 1, further comprising means for improving the prediction of the next match by monitoring the user's chat and analyzing communication patterns.

Images