System

Abstract

A system is provided.SOLUTION: A system comprising: means for allowing a user to input basic information; means for storing generated conversation data; means for analyzing the stored conversation data to extract a sense of values, a behavior pattern, an interest, and a thinking pattern of the user; means for generating an optimal matching candidate based on the extracted user information; and means for presenting the generated matching candidate to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional matching systems mainly use superficial information such as hobbies and job titles as user profile information. This often results in incompatible deeper aspects such as values, thoughts, and lifestyle patterns after actual matching, resulting in unsatisfactory matching results. To solve this issue, it is necessary to collect and analyze deeper information such as users' values, thoughts, and behavioral patterns, and provide highly accurate matching based on this information. [Means for solving the problem]

[0005] This invention provides a system in which a user inputs basic information and stores and analyzes conversation data generated through natural conversation with a generative AI model. The stored conversation data is analyzed to extract the user's values, behavioral patterns, interests, and thought patterns, and optimal match candidates are generated based on this information. Furthermore, by presenting the generated match candidates to the user, highly accurate matching based on in-depth matching elements that are often overlooked in conventional systems is achieved. This system allows users to be matched with partners who match their values, behavioral patterns, and other in-depth aspects, providing highly satisfying encounters.

[0006] "Basic information" refers to information about initial settings such as name, age, sex, and hobbies that the user provides to the system.

[0007] A "generative AI model" is an artificial intelligence model that understands the user's intentions and emotions through natural conversation and generates appropriate responses.

[0008] "Conversational data" refers to text and audio data of interactions between a user and a generative AI model.

[0009] "Storage" refers to recording conversation data in a database or storage.

[0010] "Analysis" is the process of using natural language processing (NLP) and machine learning algorithms on stored conversation data to extract and identify users' values, behavioral patterns, interests, and thought patterns.

[0011] "Values" are the user's spiritual and moral subjective views, such as priorities, beliefs, and standards of judgment.

[0012] A "behavioral pattern" is a series of actions or habits that a user repeatedly performs in daily life.

[0013] An "interest" is a user's strong interest in a particular activity or topic.

[0014] A "thought pattern" is a user's unique way of understanding, interpreting, and reacting to things.

[0015] "Matching candidates" are other users who are selected based on the analysis results and are judged to be compatible with the user.

[0016] "Presenting" refers to informing the user of information about the generated match candidates visually or by notification. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention is a system that collects in-depth information such as a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on this information. How this system is implemented will be explained below.

[0039] System configuration

[0040] 1. User Device:

[0041] Users access the system using internet-connected devices such as smartphones and personal computers.

[0042] 2. Server:

[0043] The server is a platform for processing data sent from user devices, and is equipped with a database, a natural language processing engine, a generative AI model, and a matching algorithm.

[0044] Program processing

[0045] 1. User registration and initial setup:

[0046] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[0047] The terminal transmits the input information to the server.

[0048] The server stores the information in a database and notifies the terminal that the initial setup is complete.

[0049] 2. Natural conversation starters:

[0050] The server launches the generative AI model and sends an initial message to the device to initiate a natural conversation with the user.

[0051] The device will prompt the user with questions such as "How was your day today?"

[0052] Users can freely respond to everyday topics through conversations with the generative AI model.

[0053] For example, if the user replies, "Today I went to a cafe with a friend to relax," the terminal sends this to the server.

[0054] 3. Information Collection and Analysis:

[0055] The server analyzes the received conversation data using a natural language processing engine.

[0056] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data and the user profile is updated.

[0057] The updated profile information is saved in a database.

[0058] 4. Generate match candidates:

[0059] The server accumulates conversation data over a certain period of time (usually one week) and analyzes the user's values, behavioral patterns, interests, and thought patterns.

[0060] Based on the analysis results, the profile is compared with other users' profiles to generate matching candidates with common values ​​and interests.

[0061] The server lists the best matching candidates and sends them to the device.

[0062] 5. Presentation of results:

[0063] The device will display details of potential matches, commonalities, and reasons for the match to the user, providing specific information such as, "We've found someone who's perfect for you. We share common interests of 'loving cafes' and 'relaxing'."

[0064] The user can review the details of the presented match and proceed to the next step (e.g., sending a message or starting a conversation).

[0065] Specific examples

[0066] For example, when User A registers with the system and starts a conversation with the generative AI model, it is learned through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and presents User A with this matching candidate. User A receives this information, and if he or she becomes interested in User B, he or she can send a direct message to the other person.

[0067] As described above, the present invention is a system that collects and analyzes in-depth information about users and provides optimal matches based on that information, thereby providing more satisfying encounters.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] A user accesses the system and enters basic information (name, age, gender, hobbies, etc.).

[0071] The terminal sends the input information to the server.

[0072] The server stores the received information in a database.

[0073] Step 2:

[0074] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[0075] The terminal displays this message to the user.

[0076] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[0077] The terminal sends the user's reply to the server.

[0078] Step 3:

[0079] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[0080] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data.

[0081] The server reflects the extracted information in the user profile and stores it in a database.

[0082] Step 4:

[0083] The generative AI model generates the next question for the user and sends it to the device.

[0084] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[0085] The user replies, "I went to Starbucks."

[0086] The terminal sends the user's reply back to the server.

[0087] Step 5:

[0088] The server continuously collects and analyzes conversation data and updates user profiles accordingly.

[0089] Data accumulated over a certain period (usually one week) is comprehensively analyzed.

[0090] Clarify the user's values, behavioral patterns, interests, and thought patterns.

[0091] Step 6:

[0092] The server uses the parsed user profile to match it with other user profiles.

[0093] Extract matching candidates with common values ​​and interests.

[0094] The server lists the best matching candidates and sends them to the device.

[0095] Step 7:

[0096] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'love cafes' and 'relaxation-oriented'."

[0097] The user reviews the details of the proposed match and selects the next action, such as "Learn more" or "Send a message."

[0098] The terminal communicates the user's actions to the server and takes the next action.

[0099] The above are the processing steps of the program in the present invention. This series of processes makes it possible to achieve highly accurate matching based on the user's values ​​and behavioral patterns.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] Conventional matching systems perform matching based only on basic user information and simple hobbies and preferences, making it difficult to achieve highly accurate matching that reflects deeper values ​​and behavioral patterns. Furthermore, there was a lack of means to collect deeper information through natural conversation, which resulted in low accuracy of user profiles and made it difficult to provide highly satisfying encounters.

[0103] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0104] In this invention, the server includes means for a user to input basic information, means for saving generated conversation data, means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, means for generating optimal match candidates based on the extracted user information, means for presenting the generated match candidates to the user, means for starting a conversation with the user using a generative AI model and receiving user input, and means for analyzing the received conversation data with a natural language processing engine and updating the user profile. This enables the collection and analysis of in-depth information and highly accurate matching based on the user's values ​​and behavioral patterns.

[0105] "User" refers to a person who accesses the system and enters personal information and conversation data.

[0106] "Basic information" refers to the initial setting data such as name, age, gender, and hobbies that a user enters when registering with the system.

[0107] "Conversational Data" refers to the textual content of the dialogue between a user and a generative AI model.

[0108] "Database" refers to a storage device for storing basic user information, conversation data, analysis results, etc.

[0109] A "generative AI model" refers to an artificial intelligence algorithm that generates natural conversations and engages in dialogue with users.

[0110] A "natural language processing engine" refers to software that analyzes text data and extracts keywords and sentiment information.

[0111] A "user profile" refers to data that compiles information such as a user's values, behavioral patterns, interests, and thought patterns.

[0112] "Matching candidates" refer to other users who share common values ​​and interests based on analyzed user information.

[0113] A "prompt sentence" is an instruction sentence input to a generative AI model to start or manage a dialogue.

[0114] "Analysis results" refers to the keywords and sentiment information extracted by the natural language processing engine by analyzing the conversation data.

[0115] The present invention is a system that collects in-depth information such as a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on this information. The configuration and operation of this system are described in detail below.

[0116] System configuration

[0117] The system consists of the following main components:

[0118] 1. User terminal: Users access the system using internet-connected devices such as smartphones and personal computers.

[0119] 2. Server: The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, and matching algorithm.

[0120] Specific processing of the program

[0121] 1. User registration and initial setup:

[0122] A user accesses the system and enters basic information such as name, age, gender, and hobbies, using a web form or mobile application as the interface.

[0123] The device receives this basic information and sends it to the server using an HTTP request.

[0124] The server stores the received information in a database and notifies the terminal that the initial settings are complete.

[0125] 2. Natural conversation starters:

[0126] The server invokes the generative AI model to generate an initial message to initiate a natural conversation with the user, for example, using a prompt such as "Hello, how are you doing today?"

[0127] The terminal displays the initial message received from the server to the user.

[0128] The user responds to the displayed message by inputting content such as "Today I went to a cafe with a friend and relaxed."

[0129] The terminal sends the user's response to the server.

[0130] 3. Information Collection and Analysis:

[0131] The server analyzes the received conversation data using a natural language processing engine (such as NLTK or SpaCy) to extract keywords and sentiment information. Specifically, it identifies the keywords "friends," "cafe," and "relax."

[0132] Based on these keywords and sentiment information, the user profile is updated.

[0133] The updated profile is stored in a database, improving the accuracy of the user's values ​​and behavioral patterns.

[0134] 4. Generate match candidates:

[0135] The server analyzes the accumulated conversation data and user profiles to generate optimal matching candidates between other users who share common values ​​and interests.

[0136] The generated matching candidates include specific information such as, "User B (ID: 67890) and you share common interests in 'outdoor activities' and 'cafe hopping'."

[0137] 5. Presentation of results:

[0138] The terminal displays details of the generated match candidates, as well as commonalities and reasons for matching, to the user.

[0139] The user can review the presented matching candidates and select an option, for example, "Would you like to send a message to User B?"

[0140] Specific examples

[0141] For example, when User A registers with the system and begins a conversation with the generative AI model, it is learned through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and presents User A with this matching candidate. User A receives this information, and if he or she becomes interested in User B, he or she can send a direct message to the other person.

[0142] As described above, the present invention collects and analyzes in-depth information about users and provides optimal matching based on that information, thereby achieving encounters that are highly satisfying for users.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] Step 1:

[0145] User registration and initial settings

[0146] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[0147] Input: Name (e.g., Taro), Age (e.g., 30 years old), Gender (e.g., male), Hobbies (e.g., reading, running)

[0148] What it does: Enter information using a web form or mobile application.

[0149] Output: Basic information entered.

[0150] The device receives this basic information and sends it to the server using an HTTP request.

[0151] Input: Basic information entered by the user.

[0152] What it does: Creates an HTTP POST request and sends it to the server.

[0153] Output: The request with basic information.

[0154] The server stores the received information in a database and notifies the terminal that the initial settings are complete.

[0155] Input: Basic information sent from the device.

[0156] Data processing: Basic information is stored in a database.

[0157] Output: Notification that initial setup is complete.

[0158] Step 2:

[0159] Natural conversation starters

[0160] The server launches the generative AI model and generates an initial message to initiate a natural conversation with the user.

[0161] Input: User information after initial setup is complete.

[0162] Data calculation: The generative AI model is given the prompt, "Hello, how are you doing today?"

[0163] Output: Initial message.

[0164] The terminal displays the initial message received from the server to the user.

[0165] Input: The initial message sent by the server.

[0166] Behavior: Displays a message in the chat box or other UI.

[0167] Output: Start of user interaction.

[0168] The user responds to the displayed message by inputting content such as "Today I went to a cafe with a friend and relaxed."

[0169] Input: The user's response message.

[0170] Action: Type something into the chat box.

[0171] Output: The user's response data.

[0172] The terminal sends the user's response to the server.

[0173] Input: User response data.

[0174] What it does: Creates an HTTP POST request and sends it to the server.

[0175] Output: The response data sent to the server.

[0176] Step 3:

[0177] Information collection and analysis

[0178] The server analyzes the received conversation data using a natural language processing engine (e.g., NLTK or SpaCy) to extract keywords and sentiment information.

[0179] Input: User conversation data.

[0180] Data calculation: A natural language processing engine performs text analysis to extract important keywords (e.g., "friends," "cafe," "relax") and sentiment information.

[0181] Output: Extracted keywords and sentiment information.

[0182] The extracted keywords and sentiment information are used to update the user profile.

[0183] Input: Keywords and sentiment information.

[0184] Data processing: Add and update keywords and sentiment data to user profile information.

[0185] Output: The updated user profile.

[0186] The updated profile information is saved in the database.

[0187] Input: The updated user profile.

[0188] What it does: Saves information to a database.

[0189] Output: Profiles stored in a database.

[0190] Step 4:

[0191] Generating match candidates

[0192] The server analyzes the accumulated conversation data and user profiles to generate optimal matching candidates between other users who share common values ​​and interests.

[0193] Input: User profile and conversation data.

[0194] Data calculation: Matching candidates are extracted using analytical algorithms.

[0195] Output: A list of potential matches.

[0196] Step 5:

[0197] Presentation of results

[0198] The server sends the matching candidates to the terminal.

[0199] Input: Match candidates.

[0200] Operation: Sends match candidate information to the device.

[0201] Output: Match candidates sent to the device.

[0202] The terminal displays details of the generated match candidates, as well as commonalities and reasons for matching, to the user.

[0203] Input: Submitted match candidate information.

[0204] Operation: Displays matching candidates and commonalities information on the display screen.

[0205] Output: The matching details displayed to the user.

[0206] The user can review the presented matching candidates and select an option, for example, "Would you like to send a message to User B?"

[0207] Input: User actions based on presented information.

[0208] Action: Choice selection operation.

[0209] Output: The user's next action (e.g., send a message).

[0210] (Application example 1)

[0211] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0212] Conventional food delivery applications make recommendations based solely on user preferences and past ordering history, without adequately collecting and analyzing in-depth user information. As a result, they are unable to provide truly personalized suggestions based on the user's values ​​and daily behavioral patterns, and are unable to fully increase user satisfaction. The objective of this invention is to provide a system that collects in-depth information, such as values, behavioral patterns, interests, and thought patterns, through natural conversations with users, and recommends optimal food delivery options based on this information.

[0213] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0214] In this invention, the server includes a means for a user to input basic information, a means for saving the generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for generating optimal match candidates and proposals based on the extracted user information, and a means for presenting the generated match candidates and proposals to the user, thereby making it possible to propose optimal food delivery options based on the user's in-depth information.

[0215] "Basic information" is data entered by the user, such as name, age, gender, allergy information, and favorite dishes.

[0216] The "generated conversation data" is text data obtained through natural conversation with the user.

[0217] "Storage means" refers to the technology used to store conversation data in a database or server.

[0218] The "means of analysis" refers to natural language processing engines and algorithms that extract values, behavioral patterns, interests, and thought patterns from stored conversation data.

[0219] "User information" refers to data such as the user's values, behavioral patterns, interests, and thought patterns obtained through analysis.

[0220] "Matching suggestions" are suitable food delivery options and other recommendations based on the user's in-depth information.

[0221] The "presenting means" refers to a technique for displaying the generated match candidates and suggestions on the user's device.

[0222] A "generative AI model" is an artificial intelligence technology for generating natural conversations with users.

[0223] "Keywords" are important words and phrases extracted from conversation data.

[0224] "Sentiment information" is information about emotions and evaluations obtained from conversation data.

[0225] "Food delivery options" are meal delivery options recommended based on a user's preferences and behavioral patterns.

[0226] This invention is a personalized recommendation system that utilizes in-depth user information in the food delivery field. The system collects information such as values, behavioral patterns, interests, and thought patterns through natural conversation with the user, and provides optimal food delivery options based on this information.

[0227] System configuration

[0228] 1. User Device:

[0229] Users access the system using a smartphone, which has an application installed and an interface for users to enter basic information.

[0230] 2. Server:

[0231] The server is a platform for processing data sent from user devices, and is equipped with a database, a natural language processing engine, a generative AI model, and a matching algorithm.

[0232] Program processing

[0233] 1. User registration and initial setup:

[0234] Users download and launch the app and enter basic information such as their name, age, gender, allergies, and favorite dishes. This data is sent from the device to a server and stored in a database.

[0235] 2. Natural conversation starters:

[0236] The server runs a generative AI model (e.g., GPT-4) and sends prompts to the user, such as, "What kind of food have you liked recently?" The user's response data is sent from the device to the server and stored in a database.

[0237] Examples:

[0238] Example prompt: "What kind of food have you been enjoying lately?"

[0239] 3. Information Collection and Analysis:

[0240] A natural language processing engine (e.g., spaCy) on the server analyzes user response data and extracts and updates values, behavioral patterns, interests, thought patterns, etc. This data is stored in a database as a user profile.

[0241] 4. Present options:

[0242] The server's matching algorithm (e.g., TensorFlow) generates optimal food delivery options based on accumulated user information. The generated options are sent to the device and presented to the user. Specific suggestions are made, such as, "How about having dinner with your family today?"

[0243] Hardware and software used

[0244] Hardware: Smartphone (user device)

[0245] software:

[0246] Firebase (database): Used to store basic user information and conversation data

[0247] GPT-4 (generative AI model): Generates natural conversations with users

[0248] spaCy (natural language processing engine): Used to analyze conversation data

[0249] TensorFlow (Matching Algorithm): Generating Food Delivery Options

[0250] Specific examples

[0251] For example, if a user types into the app, "I've been craving curry lately," the generative AI model might respond, "That's great! What kind of curry do you like?" If the user responds, "I like spicy Indian curry," the server might use this information to suggest the best Indian curry delivery options. An example prompt might be, "What kind of food have you been enjoying lately?"

[0252] As described above, the present invention is a system that collects and analyzes in-depth information about users and provides optimal food delivery options based on that information, thereby increasing user satisfaction.

[0253] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0254] Step 1:

[0255] A user downloads and launches a food delivery application. The user enters basic information (such as name, age, gender, allergy information, and favorite dishes). This data is sent from the device to the server and stored in the Firebase database. The input is the user's basic information, and the output is the user's basic information data sent to the server.

[0256] Step 2:

[0257] The server launches a generative AI model (e.g., GPT-4) and sends the user an initial prompt: "What kind of food have you liked recently?" This prompt encourages the user to start a natural conversation. The input is the prompt, and the output is the prompt displayed on the user's device.

[0258] Step 3:

[0259] The user responds to the prompt by typing "I've been craving curry lately." This response data is sent from the device to the server and stored in the Firebase database. The input is the user's response data, and the output is the response data stored on the server.

[0260] Step 4:

[0261] The server uses a natural language processing engine (e.g., spaCy) to analyze the user's response data. This analysis extracts keywords and sentiment information such as values, behavioral patterns, interests, and thought patterns, and updates the user profile. The input is the user's response data, and the output is the updated user profile data.

[0262] Step 5:

[0263] The server uses a matching algorithm (e.g., TensorFlow) to generate optimal food delivery options based on the updated user profile, which match the user's preferences and behavioral patterns. The input is the updated user profile data, and the output is the food delivery options.

[0264] Step 6:

[0265] The generated food delivery options are sent from the server to the user's device and presented to the user. Specifically, suggestions such as "How about this curry for dinner with your family today?" are displayed to the user. The input is the food delivery options, and the output is the options presented on the user's device.

[0266] Step 7:

[0267] The user reviews the proposed options and places an order if they like them. This order information is again sent to the server and stored in a database. The input is the user's order information, and the output is the order data stored on the server.

[0268] Through the above processing steps, personalized food delivery suggestions based on the user's in-depth information are realized, which can increase user satisfaction.

[0269] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0270] The present invention aims to improve matching accuracy by combining an emotion engine with a system that collects a user's values, behavioral patterns, interests, and thought patterns through natural conversation and provides highly accurate matching based on that information, thereby generating a more accurate profile based on the user's emotions.

[0271] System configuration

[0272] 1. User Device:

[0273] Users access the system using internet-connected devices such as smartphones and personal computers.

[0274] 2. Server:

[0275] The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, emotion engine, and matching algorithm.

[0276] Program processing

[0277] 1. User registration and initial setup:

[0278] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[0279] The terminal sends the input information to the server.

[0280] The server stores the received information in a database.

[0281] 2. Natural conversation starters:

[0282] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[0283] The terminal displays this message to the user.

[0284] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[0285] The terminal sends the user's reply to the server.

[0286] 3. Information Collection and Analysis:

[0287] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[0288] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the analyzed conversation data.

[0289] The server uses an emotion engine to recognize the user's emotion from the conversation data.

[0290] The user profile is updated based on the recognized emotion information and keywords.

[0291] The updated profile information is saved in a database.

[0292] 4. Continue the conversation and refine your profile:

[0293] The server then has the generative AI model generate the next question and send it to the device.

[0294] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[0295] The user replies, "I went to Starbucks."

[0296] The terminal sends the user's reply back to the server.

[0297] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine user profiles.

[0298] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[0299] 5. Generate candidate matches:

[0300] The server uses the analyzed emotion information and the user profile to match other user profiles.

[0301] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[0302] The server lists the best matching candidates and sends them to the device.

[0303] 6. Presentation of results:

[0304] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'loving cafes' and 'relaxing'."

[0305] Users can check the details of the presented matching candidates and select their next action, such as "View more" or "Send a message."

[0306] The terminal communicates the user's actions to the server and takes the next action.

[0307] Specific examples

[0308] For example, when User A registers with the system and begins a conversation with the generative AI model, it becomes clear through daily conversation that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that User A feels "spending time at cafes is very relaxing." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and further confirms that there are many similarities in terms of emotions. User A is presented with a matching candidate and notified, "We've found someone who suits you. You share common interests of 'cafe-loving' and 'relaxing,' as well as similar emotions." User A receives this information and, if he or she becomes interested in User B, can send a direct message.

[0309] The present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about users into the analysis, thereby providing highly satisfying encounters that could not be achieved with conventional systems.

[0310] The processing flow will be explained below.

[0311] Step 1:

[0312] A user accesses the system and enters basic information (name, age, gender, hobbies, etc.).

[0313] The terminal sends the input information to the server.

[0314] The server stores the received information in a database.

[0315] Step 2:

[0316] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[0317] The terminal displays this message to the user.

[0318] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[0319] The terminal sends the user's reply to the server.

[0320] Step 3:

[0321] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[0322] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data.

[0323] The server uses an emotion engine to recognize the user's emotion from the conversation data.

[0324] The server updates the user profile based on the recognized emotion information and keywords.

[0325] The updated profile information is saved in a database.

[0326] Step 4:

[0327] The server then has the generative AI model generate the next question and send it to the device.

[0328] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[0329] The user replies, "I went to Starbucks."

[0330] The terminal sends the user's reply back to the server.

[0331] Step 5:

[0332] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine user profiles.

[0333] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[0334] Step 6:

[0335] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[0336] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[0337] The server lists the best matching candidates and sends them to the device.

[0338] Step 7:

[0339] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'love cafes' and 'relaxation-oriented'."

[0340] The user reviews the details of the proposed match and selects the next action, such as "Learn more" or "Send a message."

[0341] The terminal communicates the user's actions to the server and takes the next action.

[0342] Examples:

[0343] For example, user A registers with the system and begins a conversation with the generative AI model. Through daily conversations, it becomes clear that user A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that user A finds "spending time at cafes very relaxing." Based on this information, the server analyzes that another user, user B, likes outdoor activities and enjoys cafe hopping, and further confirms that there are many similarities in terms of emotions. The server presents user A with matching candidates and notifies him / her, "We've found someone who suits you. You share common interests of 'cafe-loving' and 'relaxing,' as well as similar emotions." User A receives this information, and if he / she becomes interested in user B, he / she can send a direct message to the other person.

[0344] The present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about users into the analysis, thereby providing highly satisfying encounters that could not be achieved with conventional systems.

[0345] Example 2

[0346] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0347] Conventional matching systems have difficulty creating profiles that consider not only basic user information but also deeper values ​​and emotions. This results in low matching accuracy and fails to sufficiently increase user satisfaction. Furthermore, they are unable to reflect the continually changing interests and emotions of users, meaning that once a profile is created, it easily becomes outdated.

[0348] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for a user to input basic information, a means for saving generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for analyzing the user's emotional information using a sentiment analysis engine, and a means for causing the generative AI model to generate the next prompt and continuously collect conversation data. This makes it possible to keep a profile containing in-depth information of the user always up-to-date, enabling highly accurate matching that takes emotional information into consideration.

[0349] The "means for users to input basic information" is a function that provides an interface that allows users to input basic information such as name, age, sex, and hobbies.

[0350] The "means for saving generated conversation data" is a function for saving data generated from a conversation with a user in a storage device such as a database.

[0351] "Means of analyzing saved conversation data to extract a user's values, behavioral patterns, interests, and thought patterns" refers to a function that analyzes saved conversation data using natural language processing technology, etc., to extract a user's personal characteristics and patterns.

[0352] The "means for generating optimal matching candidates based on extracted user information" is a function for generating optimal matching candidates with other users using the characteristic information of the user obtained by analysis.

[0353] The "means for presenting generated match candidates to the user" is a function for displaying detailed information about the generated match candidates to the user.

[0354] The "means for analyzing user emotional information using an emotion analysis engine" is a function for analyzing user emotions from conversation data and extracting the emotional information.

[0355] "Means for having the generative AI model generate the next prompt and continuously collect conversation data" is a function that uses the generative AI model to generate the next question or message, and collects data while encouraging the continuation of the conversation with the user.

[0356] This invention relates to a system that collects a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on the collected information. The system aims to improve matching accuracy by combining an emotion engine to generate a highly accurate profile based on the user's emotions.

[0357] The system consists of the following:

[0358] 1. User Device:

[0359] Users access the system using internet-connected devices such as smartphones and personal computers.

[0360] 2. Server:

[0361] The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, emotion engine, and matching algorithm.

[0362] Specific embodiments of the invention are set out below:

[0363] 1. User registration and initial setup:

[0364] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[0365] The terminal sends the input information to the server.

[0366] The server stores the received information in a database.

[0367] 2. Natural conversation starters:

[0368] The server launches the generative AI model, generates the initial message "How was your day today?" and sends it to the device.

[0369] The terminal displays this message to the user.

[0370] The user replies, "Today I went to a cafe with a friend to relax."

[0371] The terminal sends this reply to the server.

[0372] 3. Information Collection and Analysis:

[0373] The server analyzes the received conversation data using a natural language processing (NLP) engine, such as Google Natural Language or Amazon Comprehend.

[0374] Keywords such as "friends," "cafe," and "relaxation" and emotional information are extracted from the analyzed data.

[0375] The server uses an emotion engine, such as IBM Watson Tone Analyzer, to recognize the user's emotions from the conversation data.

[0376] The user profile is updated based on the recognized emotion information and keywords.

[0377] The updated profile is saved in the database.

[0378] 4. Continue the conversation and refine your profile:

[0379] The server then has the generative AI model generate the next question, for example, "Which cafe did you go to?", and sends it to the device.

[0380] The terminal displays the generated question to the user.

[0381] The user replies, "I went to Starbucks."

[0382] The terminal sends this reply back to the server.

[0383] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine the user profile. Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep values, behavioral patterns, interests, and thought patterns.

[0384] 5. Generate candidate matches:

[0385] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[0386] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[0387] The server lists the best matching candidates and sends them to the device.

[0388] 6. Presentation of results:

[0389] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'liking cafes' and 'relaxing'."

[0390] Users can review the details of the proposed matches and select their next action, such as "View more" or "Send a message."

[0391] The terminal communicates the user's actions to the server and takes the next action (e.g., prepares to send a message).

[0392] To explain how it works in detail, when User A registers with the system and begins a conversation with the generative AI model, it is discovered through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that User A feels that "spending time at cafes is very relaxing." Based on this information, the server analyzes that User B is also a person who likes outdoor activities and enjoys cafe hopping. It also confirms that there are many similarities in terms of emotions. For example, the server may notify User A that "We've found someone who suits you. Common interests include a love of cafes and a desire to relax." If User A receives this information and becomes more interested in User B, he or she can send a direct message to the other person.

[0393] Examples of prompts include:

[0394] "How was your day today?"

[0395] "Which cafe did you go to?"

[0396] "What was the most memorable thing that happened today?"

[0397] As described above, the present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about the user into the analysis.

[0398] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0399] Step 1: User registration and initial setup

[0400] Specific behavior:

[0401] Users access the system using a smartphone or computer.

[0402] The server displays a form for the user to enter basic information such as name, age, sex, and hobbies.

[0403] The user fills in the required information in the form and clicks the "Submit" button.

[0404] Input: Basic information entered by the user (name, age, gender, hobbies, etc.)

[0405] Output: The input information is sent to the server and stored in a database.

[0406] Data processing: The server checks the format of the information it receives and converts it into the required format before storing it in the database.

[0407] Step 2: Start a natural conversation

[0408] Specific behavior:

[0409] The server launches the generative AI model and generates the first message: "How was your day?"

[0410] The server sends this message to the terminal, which displays the message to the user.

[0411] The user replies, "Today I went to a cafe with a friend to relax."

[0412] The terminal sends the user's reply to the server.

[0413] Input: Basic information about the user, the initial message generated by the generative AI model

[0414] Output: The user's reply is sent to the server.

[0415] Data processing: The generative AI model generates the initial message and sends the user's response to the server.

[0416] Step 3: Collect and analyze information

[0417] Specific behavior:

[0418] The server analyzes the received conversation data using a natural language processing (NLP) engine, such as Google Natural Language.

[0419] The NLP engine extracts keywords such as "friends," "cafe," and "relaxation" as well as emotional information from the conversation data.

[0420] The server uses an emotion engine, such as IBM Watson Tone Analyzer, to recognize the user's emotions from the conversation data.

[0421] Update user profiles based on keywords and recognized emotion information.

[0422] The server saves the updated profile in the database.

[0423] Input: User conversation data

[0424] Output: Extracted keywords and sentiment information, updated user profile

[0425] Data processing: The NLP engine analyzes the conversation data and extracts keywords and emotional information. The emotional engine recognizes the emotional information and updates the user profile accordingly.

[0426] Step 4: Continue the conversation and refine your profile

[0427] Specific behavior:

[0428] The server then asks the generative AI model to generate the next question, for example, "Which cafe did you go to?"

[0429] The server sends the generated question to the terminal, which displays it to the user.

[0430] The user replies, "I went to Starbucks."

[0431] The terminal sends this reply to the server.

[0432] The server then analyzes the received data using an NLP engine and also uses an emotion engine to further refine the user profile.

[0433] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[0434] Input: Previous conversation data and the next prompt to generate

[0435] Output: New answers from the user and an updated profile

[0436] Data processing: Generative AI models generate new questions and continue the conversation based on them, analyzing incoming data to refine profiles.

[0437] Step 5: Generate candidate matches

[0438] Specific behavior:

[0439] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[0440] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[0441] The server lists the best matching candidates and sends this information to the device.

[0442] Input: Parsed user profile and emotional information

[0443] Output: A list of potential matches

[0444] Data processing: Matching user profiles with other user profiles to extract the best possible matches.

[0445] Step 6: Presenting the results

[0446] Specific behavior:

[0447] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'liking cafes' and 'relaxing'."

[0448] The user checks the details of the presented match candidates and selects the next action, such as "View more" or "Send a message."

[0449] The terminal communicates the user's actions to the server and takes the next action.

[0450] Input: A list of potential matches and user actions

[0451] Output: Details of the match candidate and the user's selected next action

[0452] Data processing: Displaying information about potential matches to the user and communicating the user's selected action to the server.

[0453] (Application example 2)

[0454] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0455] Conventional ad delivery systems often present uniform ads because they are unable to fully understand users' interests. This results in problems such as users not being presented with ads that are beneficial to them, resulting in reduced advertising effectiveness. Furthermore, because ad delivery does not take into account user emotions, the user experience does not improve and the accuracy of ad targeting also decreases.

[0456] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0457] In this invention, the server includes a means for a user to input basic information, a means for saving the generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for selecting an optimal advertisement based on the extracted user information, and a means for presenting the selected advertisement to the user, thereby enabling highly accurate advertisement delivery based on the user's individual interests and emotions.

[0458] A "user" is an individual who uses the system.

[0459] "Basic information" refers to information such as name, age, sex, and hobbies that the user inputs during initial setup.

[0460] "Conversation data" is text data generated from natural interactions with the user.

[0461] "Means of storage" refers to the process of recording the generated conversation data in storage such as a database.

[0462] The "analysis means" is a process of analyzing saved conversation data using a natural language processing engine or the like to extract the user's values, behavioral patterns, interests, and thought patterns.

[0463] "Extracted user information" refers to data such as the user's values, behavioral patterns, interests, and thought patterns obtained through the analysis of conversation data.

[0464] The "means for selecting the most suitable advertisement" is an algorithm that automatically selects the advertisement that is most relevant to the user based on the extracted user information.

[0465] "Selected Advertisement" refers to the most suitable advertisement based on user information.

[0466] "Presenting means" refers to the process of displaying the selected advertisement on the screen of the device used by the user.

[0467] A "generative AI model" is an artificial intelligence model used to engage in natural conversations with users.

[0468] "Emotion information" is data relating to the user's emotions extracted from conversation data.

[0469] A "user profile" is a set of detailed information that includes a user's values, behavioral patterns, interests, thought patterns, emotional information, and so on.

[0470] "Advertisement" is information for advertising products or services to users.

[0471] An "advertising distribution system" is a system that uses user information to select the most suitable advertisement and present it to the user.

[0472] MODE FOR CARRYING OUT THE INVENTION

[0473] This invention is a system for optimizing advertisements based on a user's values, behavioral patterns, interests, thought patterns, and emotional information. This system operates when a user accesses it via the Internet using a device such as a smartphone or smart glasses.

[0474] Hardware and software used

[0475] Hardware:

[0476] Smartphone

[0477] Smart Glasses

[0478] head-mounted display

[0479] software:

[0480] Python

[0481] SQLite

[0482] TextBlob

[0483] Transformers pipeline(Hugging Face)

[0484] System Configuration

[0485] 1. User registration and initial setup:

[0486] Users access the system and enter basic information such as their name, age, gender, hobbies, etc. The terminal sends the entered information to the server, which then stores the received information in a database.

[0487] 2. Natural conversation starters:

[0488] The server uses the generative AI model to initiate a natural conversation with the user. For example, it might send an initial message like, "How was your day today?", to which the user replies, "Today I went to a cafe with a friend to relax." The device then sends this reply to the server.

[0489] 3. Information Collection and Analysis:

[0490] The server analyzes the received conversation data and uses an NLP engine (TextBlob) to extract keywords and sentiment information. It also performs sentiment analysis using a Transformers pipeline. Based on this information, it updates the user profile and saves it in the database.

[0491] 4. Ad optimization:

[0492] The server selects the most suitable advertisements based on the updated user profile. The selection algorithm takes into account the user's values, behavioral patterns, interests, thought patterns, and emotional information.

[0493] 5. Advertising Presentation:

[0494] The server sends the selected advertisement to the device, which then presents it to the user, allowing the user to receive advertisements that match their interests and emotions.

[0495] Specific examples

[0496] For example, if a user replies, "Today I went to a cafe with friends and relaxed," the server extracts the keywords "friends," "cafe," and "relaxation," and recognizes the emotion as "positive." Based on this information, it presents the user with advertisements related to cafes and products related to relaxation.

[0497] Prompt Sentence Examples

[0498] A generative AI model that allows a system to generate questions for a user could use prompts like this:

[0499] "You are a model for an ad selection engine. Please identify your interests from the following conversation and select the most suitable ad. Conversation: Today I went to a cafe with a friend to relax."

[0500] This invention makes it possible to realize highly accurate advertisement distribution based on the individual interests and emotions of users.

[0501] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0502] Step 1: User registration and initial setup

[0503] A user accesses the system and enters basic information such as name, age, gender, hobbies, etc. The terminal sends the entered information to the server, which then stores the received information in a database.

[0504] Input: Basic information entered by the user (name, age, gender, hobbies)

[0505] Output: Basic information is saved to the database

[0506] Step 2: Start a natural conversation

[0507] The server uses the generative AI model to initiate a natural conversation with the user. For example, it might send an initial message like, "How was your day today?" The user might reply, "Today I went to a cafe with a friend to relax." The device then sends this reply to the server.

[0508] Input: A conversational prompt sent by the server to the user ("How was your day?")

[0509] Output: User response ("Today I went to a cafe with a friend to relax.")

[0510] Step 3: Collect and analyze information

[0511] The server analyzes the received conversation data and uses an NLP engine (TextBlob) to extract keywords and sentiment information. It also performs sentiment analysis using a Transformers pipeline. Based on this information, it updates the user profile and saves it in the database.

[0512] Input: User conversation data ("Today I went to a cafe with a friend to relax.")

[0513] Output: Extracted keywords ("friends", "cafe", "relax") and sentiment information (positive)

[0514] Step 4: Optimize your ads

[0515] The server selects the most suitable advertisements based on the updated user profile. The selection algorithm takes into account the user's values, behavioral patterns, interests, thought patterns, and emotional information.

[0516] Input: Updated user profile (specific values, behavioral patterns, interests, thought patterns, emotional information)

[0517] Output: Selection of the best ad

[0518] Step 5: Present your ad

[0519] The server sends the selected advertisement to the device, which then presents it to the user, allowing the user to receive advertisements that match their interests and emotions.

[0520] Input: Best ad selection results

[0521] Output: The ad is displayed on the user's device

[0522] Through the above steps, highly accurate advertisement delivery based on the individual interests and emotions of each user is realized.

[0523] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0524] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0525] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0526] [Second embodiment]

[0527] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0528] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0529] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0530] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0531] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0532] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0533] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0534] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0535] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0536] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0537] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0538] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0539] The present invention is a system that collects in-depth information such as a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on this information. How this system is implemented will be explained below.

[0540] System configuration

[0541] 1. User Device:

[0542] Users access the system using internet-connected devices such as smartphones and personal computers.

[0543] 2. Server:

[0544] The server is a platform for processing data sent from user devices, and is equipped with a database, a natural language processing engine, a generative AI model, and a matching algorithm.

[0545] Program processing

[0546] 1. User registration and initial setup:

[0547] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[0548] The terminal transmits the input information to the server.

[0549] The server stores the information in a database and notifies the terminal that the initial setup is complete.

[0550] 2. Natural conversation starters:

[0551] The server launches the generative AI model and sends an initial message to the device to initiate a natural conversation with the user.

[0552] The device will prompt the user with questions such as "How was your day today?"

[0553] Users can freely respond to everyday topics through conversations with the generative AI model.

[0554] For example, if the user replies, "Today I went to a cafe with a friend to relax," the terminal sends this to the server.

[0555] 3. Information Collection and Analysis:

[0556] The server analyzes the received conversation data using a natural language processing engine.

[0557] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data and the user profile is updated.

[0558] The updated profile information is saved in a database.

[0559] 4. Generate match candidates:

[0560] The server accumulates conversation data over a certain period of time (usually one week) and analyzes the user's values, behavioral patterns, interests, and thought patterns.

[0561] Based on the analysis results, the profile is compared with other users' profiles to generate matching candidates with common values ​​and interests.

[0562] The server lists the best matching candidates and sends them to the device.

[0563] 5. Presentation of results:

[0564] The device will display details of potential matches, commonalities, and reasons for the match to the user, providing specific information such as, "We've found someone who's perfect for you. We share common interests of 'loving cafes' and 'relaxing'."

[0565] The user can review the details of the presented match and proceed to the next step (e.g., sending a message or starting a conversation).

[0566] Specific examples

[0567] For example, when User A registers with the system and starts a conversation with the generative AI model, it is learned through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and presents User A with this matching candidate. User A receives this information, and if he or she becomes interested in User B, he or she can send a direct message to the other person.

[0568] As described above, the present invention is a system that collects and analyzes in-depth information about users and provides optimal matches based on that information, thereby providing more satisfying encounters.

[0569] The processing flow will be explained below.

[0570] Step 1:

[0571] A user accesses the system and enters basic information (name, age, gender, hobbies, etc.).

[0572] The terminal sends the input information to the server.

[0573] The server stores the received information in a database.

[0574] Step 2:

[0575] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[0576] The terminal displays this message to the user.

[0577] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[0578] The terminal sends the user's reply to the server.

[0579] Step 3:

[0580] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[0581] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data.

[0582] The server reflects the extracted information in the user profile and stores it in a database.

[0583] Step 4:

[0584] The generative AI model generates the next question for the user and sends it to the device.

[0585] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[0586] The user replies, "I went to Starbucks."

[0587] The terminal sends the user's reply back to the server.

[0588] Step 5:

[0589] The server continuously collects and analyzes conversation data and updates user profiles accordingly.

[0590] Data accumulated over a certain period (usually one week) is comprehensively analyzed.

[0591] Clarify the user's values, behavioral patterns, interests, and thought patterns.

[0592] Step 6:

[0593] The server uses the parsed user profile to match it with other user profiles.

[0594] Extract matching candidates with common values ​​and interests.

[0595] The server lists the best matching candidates and sends them to the device.

[0596] Step 7:

[0597] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'love cafes' and 'relaxation-oriented'."

[0598] The user reviews the details of the proposed match and selects the next action, such as "Learn more" or "Send a message."

[0599] The terminal communicates the user's actions to the server and takes the next action.

[0600] The above are the processing steps of the program in the present invention. This series of processes makes it possible to achieve highly accurate matching based on the user's values ​​and behavioral patterns.

[0601] Example 1

[0602] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0603] Conventional matching systems perform matching based only on basic user information and simple hobbies and preferences, making it difficult to achieve highly accurate matching that reflects deeper values ​​and behavioral patterns. Furthermore, there was a lack of means to collect deeper information through natural conversation, which resulted in low accuracy of user profiles and made it difficult to provide highly satisfying encounters.

[0604] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0605] In this invention, the server includes means for a user to input basic information, means for saving generated conversation data, means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, means for generating optimal match candidates based on the extracted user information, means for presenting the generated match candidates to the user, means for starting a conversation with the user using a generative AI model and receiving user input, and means for analyzing the received conversation data with a natural language processing engine and updating the user profile. This enables the collection and analysis of in-depth information and highly accurate matching based on the user's values ​​and behavioral patterns.

[0606] "User" refers to a person who accesses the system and enters personal information and conversation data.

[0607] "Basic information" refers to the initial setting data such as name, age, gender, and hobbies that a user enters when registering with the system.

[0608] "Conversational Data" refers to the textual content of the dialogue between a user and a generative AI model.

[0609] "Database" refers to a storage device for storing basic user information, conversation data, analysis results, etc.

[0610] A "generative AI model" refers to an artificial intelligence algorithm that generates natural conversations and engages in dialogue with users.

[0611] A "natural language processing engine" refers to software that analyzes text data and extracts keywords and sentiment information.

[0612] A "user profile" refers to data that compiles information such as a user's values, behavioral patterns, interests, and thought patterns.

[0613] "Matching candidates" refer to other users who share common values ​​and interests based on analyzed user information.

[0614] A "prompt sentence" is an instruction sentence input to a generative AI model to start or manage a dialogue.

[0615] "Analysis results" refers to the keywords and sentiment information extracted by the natural language processing engine by analyzing the conversation data.

[0616] The present invention is a system that collects in-depth information such as a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on this information. The configuration and operation of this system are described in detail below.

[0617] System configuration

[0618] The system consists of the following main components:

[0619] 1. User terminal: Users access the system using internet-connected devices such as smartphones and personal computers.

[0620] 2. Server: The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, and matching algorithm.

[0621] Specific processing of the program

[0622] 1. User registration and initial setup:

[0623] A user accesses the system and enters basic information such as name, age, gender, and hobbies, using a web form or mobile application as the interface.

[0624] The device receives this basic information and sends it to the server using an HTTP request.

[0625] The server stores the received information in a database and notifies the terminal that the initial settings are complete.

[0626] 2. Natural conversation starters:

[0627] The server invokes the generative AI model to generate an initial message to initiate a natural conversation with the user, for example, using a prompt such as "Hello, how are you doing today?"

[0628] The terminal displays the initial message received from the server to the user.

[0629] The user responds to the displayed message by inputting content such as "Today I went to a cafe with a friend and relaxed."

[0630] The terminal sends the user's response to the server.

[0631] 3. Information Collection and Analysis:

[0632] The server analyzes the received conversation data using a natural language processing engine (such as NLTK or SpaCy) to extract keywords and sentiment information. Specifically, it identifies the keywords "friends," "cafe," and "relax."

[0633] Based on these keywords and sentiment information, the user profile is updated.

[0634] The updated profile is stored in a database, improving the accuracy of the user's values ​​and behavioral patterns.

[0635] 4. Generate match candidates:

[0636] The server analyzes the accumulated conversation data and user profiles to generate optimal matching candidates between other users who share common values ​​and interests.

[0637] The generated matching candidates include specific information such as, "User B (ID: 67890) and you share common interests in 'outdoor activities' and 'cafe hopping'."

[0638] 5. Presentation of results:

[0639] The terminal displays details of the generated match candidates, as well as commonalities and reasons for matching, to the user.

[0640] The user can review the presented matching candidates and select an option, for example, "Would you like to send a message to User B?"

[0641] Specific examples

[0642] For example, when User A registers with the system and begins a conversation with the generative AI model, it is learned through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and presents User A with this matching candidate. User A receives this information, and if he or she becomes interested in User B, he or she can send a direct message to the other person.

[0643] As described above, the present invention collects and analyzes in-depth information about users and provides optimal matching based on that information, thereby achieving encounters that are highly satisfying for users.

[0644] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0645] Step 1:

[0646] User registration and initial settings

[0647] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[0648] Input: Name (e.g., Taro), Age (e.g., 30 years old), Gender (e.g., male), Hobbies (e.g., reading, running)

[0649] What it does: Enter information using a web form or mobile application.

[0650] Output: Basic information entered.

[0651] The device receives this basic information and sends it to the server using an HTTP request.

[0652] Input: Basic information entered by the user.

[0653] What it does: Creates an HTTP POST request and sends it to the server.

[0654] Output: The request with basic information.

[0655] The server stores the received information in a database and notifies the terminal that the initial settings are complete.

[0656] Input: Basic information sent from the device.

[0657] Data processing: Basic information is stored in a database.

[0658] Output: Notification that initial setup is complete.

[0659] Step 2:

[0660] Natural conversation starters

[0661] The server launches the generative AI model and generates an initial message to initiate a natural conversation with the user.

[0662] Input: User information after initial setup is complete.

[0663] Data calculation: The generative AI model is given the prompt, "Hello, how are you doing today?"

[0664] Output: Initial message.

[0665] The terminal displays the initial message received from the server to the user.

[0666] Input: The initial message sent by the server.

[0667] Behavior: Displays a message in the chat box or other UI.

[0668] Output: Start of user interaction.

[0669] The user responds to the displayed message by inputting content such as "Today I went to a cafe with a friend and relaxed."

[0670] Input: The user's response message.

[0671] Action: Type something into the chat box.

[0672] Output: The user's response data.

[0673] The terminal sends the user's response to the server.

[0674] Input: User response data.

[0675] What it does: Creates an HTTP POST request and sends it to the server.

[0676] Output: The response data sent to the server.

[0677] Step 3:

[0678] Information collection and analysis

[0679] The server analyzes the received conversation data using a natural language processing engine (e.g., NLTK or SpaCy) to extract keywords and sentiment information.

[0680] Input: User conversation data.

[0681] Data calculation: A natural language processing engine performs text analysis to extract important keywords (e.g., "friends," "cafe," "relax") and sentiment information.

[0682] Output: Extracted keywords and sentiment information.

[0683] The extracted keywords and sentiment information are used to update the user profile.

[0684] Input: Keywords and sentiment information.

[0685] Data processing: Add and update keywords and sentiment data to user profile information.

[0686] Output: The updated user profile.

[0687] The updated profile information is saved in the database.

[0688] Input: The updated user profile.

[0689] What it does: Saves information to a database.

[0690] Output: Profiles stored in a database.

[0691] Step 4:

[0692] Generating match candidates

[0693] The server analyzes the accumulated conversation data and user profiles to generate optimal matching candidates between other users who share common values ​​and interests.

[0694] Input: User profile and conversation data.

[0695] Data calculation: Matching candidates are extracted using analytical algorithms.

[0696] Output: A list of potential matches.

[0697] Step 5:

[0698] Presentation of results

[0699] The server sends the matching candidates to the terminal.

[0700] Input: Match candidates.

[0701] Operation: Sends match candidate information to the device.

[0702] Output: Match candidates sent to the device.

[0703] The terminal displays details of the generated match candidates, as well as commonalities and reasons for matching, to the user.

[0704] Input: Submitted match candidate information.

[0705] Operation: Displays matching candidates and commonalities information on the display screen.

[0706] Output: The matching details displayed to the user.

[0707] The user can review the presented matching candidates and select an option, for example, "Would you like to send a message to User B?"

[0708] Input: User actions based on presented information.

[0709] Action: Choice selection operation.

[0710] Output: The user's next action (e.g., send a message).

[0711] (Application example 1)

[0712] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0713] Conventional food delivery applications make recommendations based solely on user preferences and past ordering history, without adequately collecting and analyzing in-depth user information. As a result, they are unable to provide truly personalized suggestions based on the user's values ​​and daily behavioral patterns, and are unable to fully increase user satisfaction. The objective of this invention is to provide a system that collects in-depth information, such as values, behavioral patterns, interests, and thought patterns, through natural conversations with users, and recommends optimal food delivery options based on this information.

[0714] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0715] In this invention, the server includes a means for a user to input basic information, a means for saving the generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for generating optimal match candidates and proposals based on the extracted user information, and a means for presenting the generated match candidates and proposals to the user, thereby making it possible to propose optimal food delivery options based on the user's in-depth information.

[0716] "Basic information" is data entered by the user, such as name, age, gender, allergy information, and favorite dishes.

[0717] The "generated conversation data" is text data obtained through natural conversation with the user.

[0718] "Storage means" refers to the technology used to store conversation data in a database or server.

[0719] The "means of analysis" refers to natural language processing engines and algorithms that extract values, behavioral patterns, interests, and thought patterns from stored conversation data.

[0720] "User information" refers to data such as the user's values, behavioral patterns, interests, and thought patterns obtained through analysis.

[0721] "Matching suggestions" are suitable food delivery options and other recommendations based on the user's in-depth information.

[0722] The "presenting means" refers to a technique for displaying the generated match candidates and suggestions on the user's device.

[0723] A "generative AI model" is an artificial intelligence technology for generating natural conversations with users.

[0724] "Keywords" are important words and phrases extracted from conversation data.

[0725] "Sentiment information" is information about emotions and evaluations obtained from conversation data.

[0726] "Food delivery options" are meal delivery options recommended based on a user's preferences and behavioral patterns.

[0727] This invention is a personalized recommendation system that utilizes in-depth user information in the food delivery field. The system collects information such as values, behavioral patterns, interests, and thought patterns through natural conversation with the user, and provides optimal food delivery options based on this information.

[0728] System configuration

[0729] 1. User Device:

[0730] Users access the system using a smartphone, which has an application installed and an interface for users to enter basic information.

[0731] 2. Server:

[0732] The server is a platform for processing data sent from user devices, and is equipped with a database, a natural language processing engine, a generative AI model, and a matching algorithm.

[0733] Program processing

[0734] 1. User registration and initial setup:

[0735] Users download and launch the app and enter basic information such as their name, age, gender, allergies, and favorite dishes. This data is sent from the device to a server and stored in a database.

[0736] 2. Natural conversation starters:

[0737] The server runs a generative AI model (e.g., GPT-4) and sends prompts to the user, such as, "What kind of food have you liked recently?" The user's response data is sent from the device to the server and stored in a database.

[0738] Examples:

[0739] Example prompt: "What kind of food have you been enjoying lately?"

[0740] 3. Information Collection and Analysis:

[0741] A natural language processing engine (e.g., spaCy) on the server analyzes user response data and extracts and updates values, behavioral patterns, interests, thought patterns, etc. This data is stored in a database as a user profile.

[0742] 4. Present options:

[0743] The server's matching algorithm (e.g., TensorFlow) generates optimal food delivery options based on accumulated user information. The generated options are sent to the device and presented to the user. Specific suggestions are made, such as, "How about having dinner with your family today?"

[0744] Hardware and software used

[0745] Hardware: Smartphone (user device)

[0746] software:

[0747] Firebase (database): Used to store basic user information and conversation data

[0748] GPT-4 (generative AI model): Generates natural conversations with users

[0749] spaCy (natural language processing engine): Used to analyze conversation data

[0750] TensorFlow (Matching Algorithm): Generating Food Delivery Options

[0751] Specific examples

[0752] For example, if a user types into the app, "I've been craving curry lately," the generative AI model might respond, "That's great! What kind of curry do you like?" If the user responds, "I like spicy Indian curry," the server might use this information to suggest the best Indian curry delivery options. An example prompt might be, "What kind of food have you been enjoying lately?"

[0753] As described above, the present invention is a system that collects and analyzes in-depth information about users and provides optimal food delivery options based on that information, thereby increasing user satisfaction.

[0754] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0755] Step 1:

[0756] A user downloads and launches a food delivery application. The user enters basic information (such as name, age, gender, allergy information, and favorite dishes). This data is sent from the device to the server and stored in the Firebase database. The input is the user's basic information, and the output is the user's basic information data sent to the server.

[0757] Step 2:

[0758] The server launches a generative AI model (e.g., GPT-4) and sends the user an initial prompt: "What kind of food have you liked recently?" This prompt encourages the user to start a natural conversation. The input is the prompt, and the output is the prompt displayed on the user's device.

[0759] Step 3:

[0760] The user responds to the prompt by typing "I've been craving curry lately." This response data is sent from the device to the server and stored in the Firebase database. The input is the user's response data, and the output is the response data stored on the server.

[0761] Step 4:

[0762] The server uses a natural language processing engine (e.g., spaCy) to analyze the user's response data. This analysis extracts keywords and sentiment information such as values, behavioral patterns, interests, and thought patterns, and updates the user profile. The input is the user's response data, and the output is the updated user profile data.

[0763] Step 5:

[0764] The server uses a matching algorithm (e.g., TensorFlow) to generate optimal food delivery options based on the updated user profile, which match the user's preferences and behavioral patterns. The input is the updated user profile data, and the output is the food delivery options.

[0765] Step 6:

[0766] The generated food delivery options are sent from the server to the user's device and presented to the user. Specifically, suggestions such as "How about this curry for dinner with your family today?" are displayed to the user. The input is the food delivery options, and the output is the options presented on the user's device.

[0767] Step 7:

[0768] The user reviews the proposed options and places an order if they like them. This order information is again sent to the server and stored in a database. The input is the user's order information, and the output is the order data stored on the server.

[0769] Through the above processing steps, personalized food delivery suggestions based on the user's in-depth information are realized, which can increase user satisfaction.

[0770] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0771] The present invention aims to improve matching accuracy by combining an emotion engine with a system that collects a user's values, behavioral patterns, interests, and thought patterns through natural conversation and provides highly accurate matching based on that information, thereby generating a more accurate profile based on the user's emotions.

[0772] System configuration

[0773] 1. User Device:

[0774] Users access the system using internet-connected devices such as smartphones and personal computers.

[0775] 2. Server:

[0776] The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, emotion engine, and matching algorithm.

[0777] Program processing

[0778] 1. User registration and initial setup:

[0779] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[0780] The terminal sends the input information to the server.

[0781] The server stores the received information in a database.

[0782] 2. Natural conversation starters:

[0783] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[0784] The terminal displays this message to the user.

[0785] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[0786] The terminal sends the user's reply to the server.

[0787] 3. Information Collection and Analysis:

[0788] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[0789] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the analyzed conversation data.

[0790] The server uses an emotion engine to recognize the user's emotion from the conversation data.

[0791] The user profile is updated based on the recognized emotion information and keywords.

[0792] The updated profile information is saved in a database.

[0793] 4. Continue the conversation and refine your profile:

[0794] The server then has the generative AI model generate the next question and send it to the device.

[0795] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[0796] The user replies, "I went to Starbucks."

[0797] The terminal sends the user's reply back to the server.

[0798] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine user profiles.

[0799] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[0800] 5. Generate candidate matches:

[0801] The server uses the analyzed emotion information and the user profile to match other user profiles.

[0802] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[0803] The server lists the best matching candidates and sends them to the device.

[0804] 6. Presentation of results:

[0805] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'loving cafes' and 'relaxing'."

[0806] Users can check the details of the presented matching candidates and select their next action, such as "View more" or "Send a message."

[0807] The terminal communicates the user's actions to the server and takes the next action.

[0808] Specific examples

[0809] For example, when User A registers with the system and begins a conversation with the generative AI model, it becomes clear through daily conversation that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that User A feels "spending time at cafes is very relaxing." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and further confirms that there are many similarities in terms of emotions. User A is presented with a matching candidate and notified, "We've found someone who suits you. You share common interests of 'cafe-loving' and 'relaxing,' as well as similar emotions." User A receives this information and, if he or she becomes interested in User B, can send a direct message.

[0810] The present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about users into the analysis, thereby providing highly satisfying encounters that could not be achieved with conventional systems.

[0811] The processing flow will be explained below.

[0812] Step 1:

[0813] A user accesses the system and enters basic information (name, age, gender, hobbies, etc.).

[0814] The terminal sends the input information to the server.

[0815] The server stores the received information in a database.

[0816] Step 2:

[0817] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[0818] The terminal displays this message to the user.

[0819] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[0820] The terminal sends the user's reply to the server.

[0821] Step 3:

[0822] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[0823] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data.

[0824] The server uses an emotion engine to recognize the user's emotion from the conversation data.

[0825] The server updates the user profile based on the recognized emotion information and keywords.

[0826] The updated profile information is saved in a database.

[0827] Step 4:

[0828] The server then has the generative AI model generate the next question and send it to the device.

[0829] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[0830] The user replies, "I went to Starbucks."

[0831] The terminal sends the user's reply back to the server.

[0832] Step 5:

[0833] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine user profiles.

[0834] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[0835] Step 6:

[0836] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[0837] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[0838] The server lists the best matching candidates and sends them to the device.

[0839] Step 7:

[0840] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'love cafes' and 'relaxation-oriented'."

[0841] The user reviews the details of the proposed match and selects the next action, such as "Learn more" or "Send a message."

[0842] The terminal communicates the user's actions to the server and takes the next action.

[0843] Examples:

[0844] For example, user A registers with the system and begins a conversation with the generative AI model. Through daily conversations, it becomes clear that user A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that user A finds "spending time at cafes very relaxing." Based on this information, the server analyzes that another user, user B, likes outdoor activities and enjoys cafe hopping, and further confirms that there are many similarities in terms of emotions. The server presents user A with matching candidates and notifies him / her, "We've found someone who suits you. You share common interests of 'cafe-loving' and 'relaxing,' as well as similar emotions." User A receives this information, and if he / she becomes interested in user B, he / she can send a direct message to the other person.

[0845] The present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about users into the analysis, thereby providing highly satisfying encounters that could not be achieved with conventional systems.

[0846] Example 2

[0847] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0848] Conventional matching systems have difficulty creating profiles that consider not only basic user information but also deeper values ​​and emotions. This results in low matching accuracy and fails to sufficiently increase user satisfaction. Furthermore, they are unable to reflect the continually changing interests and emotions of users, meaning that once a profile is created, it easily becomes outdated.

[0849] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for a user to input basic information, a means for saving generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for analyzing the user's emotional information using a sentiment analysis engine, and a means for causing the generative AI model to generate the next prompt and continuously collect conversation data. This makes it possible to keep a profile containing in-depth information of the user always up-to-date, enabling highly accurate matching that takes emotional information into consideration.

[0850] The "means for users to input basic information" is a function that provides an interface that allows users to input basic information such as name, age, sex, and hobbies.

[0851] The "means for saving generated conversation data" is a function for saving data generated from a conversation with a user in a storage device such as a database.

[0852] "Means of analyzing saved conversation data to extract a user's values, behavioral patterns, interests, and thought patterns" refers to a function that analyzes saved conversation data using natural language processing technology, etc., to extract a user's personal characteristics and patterns.

[0853] The "means for generating optimal matching candidates based on extracted user information" is a function for generating optimal matching candidates with other users using the characteristic information of the user obtained by analysis.

[0854] The "means for presenting generated match candidates to the user" is a function for displaying detailed information about the generated match candidates to the user.

[0855] The "means for analyzing user emotional information using an emotion analysis engine" is a function for analyzing user emotions from conversation data and extracting the emotional information.

[0856] "Means for having the generative AI model generate the next prompt and continuously collect conversation data" is a function that uses the generative AI model to generate the next question or message, and collects data while encouraging the continuation of the conversation with the user.

[0857] This invention relates to a system that collects a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on the collected information. The system aims to improve matching accuracy by combining an emotion engine to generate a highly accurate profile based on the user's emotions.

[0858] The system consists of the following:

[0859] 1. User Device:

[0860] Users access the system using internet-connected devices such as smartphones and personal computers.

[0861] 2. Server:

[0862] The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, emotion engine, and matching algorithm.

[0863] Specific embodiments of the invention are set out below:

[0864] 1. User registration and initial setup:

[0865] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[0866] The terminal sends the input information to the server.

[0867] The server stores the received information in a database.

[0868] 2. Natural conversation starters:

[0869] The server launches the generative AI model, generates the initial message "How was your day today?" and sends it to the device.

[0870] The terminal displays this message to the user.

[0871] The user replies, "Today I went to a cafe with a friend to relax."

[0872] The terminal sends this reply to the server.

[0873] 3. Information Collection and Analysis:

[0874] The server analyzes the received conversation data using a natural language processing (NLP) engine, such as Google Natural Language or Amazon Comprehend.

[0875] Keywords such as "friends," "cafe," and "relaxation" and emotional information are extracted from the analyzed data.

[0876] The server uses an emotion engine, such as IBM Watson Tone Analyzer, to recognize the user's emotions from the conversation data.

[0877] The user profile is updated based on the recognized emotion information and keywords.

[0878] The updated profile is saved in the database.

[0879] 4. Continue the conversation and refine your profile:

[0880] The server then has the generative AI model generate the next question, for example, "Which cafe did you go to?", and sends it to the device.

[0881] The terminal displays the generated question to the user.

[0882] The user replies, "I went to Starbucks."

[0883] The terminal sends this reply back to the server.

[0884] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine the user profile. Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep values, behavioral patterns, interests, and thought patterns.

[0885] 5. Generate candidate matches:

[0886] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[0887] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[0888] The server lists the best matching candidates and sends them to the device.

[0889] 6. Presentation of results:

[0890] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'liking cafes' and 'relaxing'."

[0891] Users can review the details of the proposed matches and select their next action, such as "View more" or "Send a message."

[0892] The terminal communicates the user's actions to the server and takes the next action (e.g., prepares to send a message).

[0893] To explain how it works in detail, when User A registers with the system and begins a conversation with the generative AI model, it is discovered through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that User A feels that "spending time at cafes is very relaxing." Based on this information, the server analyzes that User B is also a person who likes outdoor activities and enjoys cafe hopping. It also confirms that there are many similarities in terms of emotions. For example, the server may notify User A that "We've found someone who suits you. Common interests include a love of cafes and a desire to relax." If User A receives this information and becomes more interested in User B, he or she can send a direct message to the other person.

[0894] Examples of prompts include:

[0895] "How was your day today?"

[0896] "Which cafe did you go to?"

[0897] "What was the most memorable thing that happened today?"

[0898] As described above, the present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about the user into the analysis.

[0899] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0900] Step 1: User registration and initial setup

[0901] Specific behavior:

[0902] Users access the system using a smartphone or computer.

[0903] The server displays a form for the user to enter basic information such as name, age, sex, and hobbies.

[0904] The user fills in the required information in the form and clicks the "Submit" button.

[0905] Input: Basic information entered by the user (name, age, gender, hobbies, etc.)

[0906] Output: The input information is sent to the server and stored in a database.

[0907] Data processing: The server checks the format of the information it receives and converts it into the required format before storing it in the database.

[0908] Step 2: Start a natural conversation

[0909] Specific behavior:

[0910] The server launches the generative AI model and generates the first message: "How was your day?"

[0911] The server sends this message to the terminal, which displays the message to the user.

[0912] The user replies, "Today I went to a cafe with a friend to relax."

[0913] The terminal sends the user's reply to the server.

[0914] Input: Basic information about the user, the initial message generated by the generative AI model

[0915] Output: The user's reply is sent to the server.

[0916] Data processing: The generative AI model generates the initial message and sends the user's response to the server.

[0917] Step 3: Collect and analyze information

[0918] Specific behavior:

[0919] The server analyzes the received conversation data using a natural language processing (NLP) engine, such as Google Natural Language.

[0920] The NLP engine extracts keywords such as "friends," "cafe," and "relaxation" as well as emotional information from the conversation data.

[0921] The server uses an emotion engine, such as IBM Watson Tone Analyzer, to recognize the user's emotions from the conversation data.

[0922] Update user profiles based on keywords and recognized emotion information.

[0923] The server saves the updated profile in the database.

[0924] Input: User conversation data

[0925] Output: Extracted keywords and sentiment information, updated user profile

[0926] Data processing: The NLP engine analyzes the conversation data and extracts keywords and emotional information. The emotional engine recognizes the emotional information and updates the user profile accordingly.

[0927] Step 4: Continue the conversation and refine your profile

[0928] Specific behavior:

[0929] The server then asks the generative AI model to generate the next question, for example, "Which cafe did you go to?"

[0930] The server sends the generated question to the terminal, which displays it to the user.

[0931] The user replies, "I went to Starbucks."

[0932] The terminal sends this reply to the server.

[0933] The server then analyzes the received data using an NLP engine and also uses an emotion engine to further refine the user profile.

[0934] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[0935] Input: Previous conversation data and the next prompt to generate

[0936] Output: New answers from the user and an updated profile

[0937] Data processing: Generative AI models generate new questions and continue the conversation based on them, analyzing incoming data to refine profiles.

[0938] Step 5: Generate candidate matches

[0939] Specific behavior:

[0940] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[0941] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[0942] The server lists the best matching candidates and sends this information to the device.

[0943] Input: Parsed user profile and emotional information

[0944] Output: A list of potential matches

[0945] Data processing: Matching user profiles with other user profiles to extract the best possible matches.

[0946] Step 6: Presenting the results

[0947] Specific behavior:

[0948] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'liking cafes' and 'relaxing'."

[0949] The user checks the details of the presented match candidates and selects the next action, such as "View more" or "Send a message."

[0950] The terminal communicates the user's actions to the server and takes the next action.

[0951] Input: A list of potential matches and user actions

[0952] Output: Details of the match candidate and the user's selected next action

[0953] Data processing: Displaying information about potential matches to the user and communicating the user's selected action to the server.

[0954] (Application example 2)

[0955] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0956] Conventional ad delivery systems often present uniform ads because they are unable to fully understand users' interests. This results in problems such as users not being presented with ads that are beneficial to them, resulting in reduced advertising effectiveness. Furthermore, because ad delivery does not take into account user emotions, the user experience does not improve and the accuracy of ad targeting also decreases.

[0957] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0958] In this invention, the server includes a means for a user to input basic information, a means for saving the generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for selecting an optimal advertisement based on the extracted user information, and a means for presenting the selected advertisement to the user, thereby enabling highly accurate advertisement delivery based on the user's individual interests and emotions.

[0959] A "user" is an individual who uses the system.

[0960] "Basic information" refers to information such as name, age, sex, and hobbies that the user inputs during initial setup.

[0961] "Conversation data" is text data generated from natural interactions with the user.

[0962] "Means of storage" refers to the process of recording the generated conversation data in storage such as a database.

[0963] The "analysis means" is a process of analyzing saved conversation data using a natural language processing engine or the like to extract the user's values, behavioral patterns, interests, and thought patterns.

[0964] "Extracted user information" refers to data such as the user's values, behavioral patterns, interests, and thought patterns obtained through the analysis of conversation data.

[0965] The "means for selecting the most suitable advertisement" is an algorithm that automatically selects the advertisement that is most relevant to the user based on the extracted user information.

[0966] "Selected Advertisement" refers to the most suitable advertisement based on user information.

[0967] "Presenting means" refers to the process of displaying the selected advertisement on the screen of the device used by the user.

[0968] A "generative AI model" is an artificial intelligence model used to engage in natural conversations with users.

[0969] "Emotion information" is data relating to the user's emotions extracted from conversation data.

[0970] A "user profile" is a set of detailed information that includes a user's values, behavioral patterns, interests, thought patterns, emotional information, and so on.

[0971] "Advertisement" is information for advertising products or services to users.

[0972] An "advertising distribution system" is a system that uses user information to select the most suitable advertisement and present it to the user.

[0973] MODE FOR CARRYING OUT THE INVENTION

[0974] This invention is a system for optimizing advertisements based on a user's values, behavioral patterns, interests, thought patterns, and emotional information. This system operates when a user accesses it via the Internet using a device such as a smartphone or smart glasses.

[0975] Hardware and software used

[0976] Hardware:

[0977] Smartphone

[0978] Smart Glasses

[0979] head-mounted display

[0980] software:

[0981] Python

[0982] SQLite

[0983] TextBlob

[0984] Transformers pipeline(Hugging Face)

[0985] System Configuration

[0986] 1. User registration and initial setup:

[0987] Users access the system and enter basic information such as their name, age, gender, hobbies, etc. The terminal sends the entered information to the server, which then stores the received information in a database.

[0988] 2. Natural conversation starters:

[0989] The server uses the generative AI model to initiate a natural conversation with the user. For example, it might send an initial message like, "How was your day today?", to which the user replies, "Today I went to a cafe with a friend to relax." The device then sends this reply to the server.

[0990] 3. Information Collection and Analysis:

[0991] The server analyzes the received conversation data and uses an NLP engine (TextBlob) to extract keywords and sentiment information. It also performs sentiment analysis using a Transformers pipeline. Based on this information, it updates the user profile and saves it in the database.

[0992] 4. Ad optimization:

[0993] The server selects the most suitable advertisements based on the updated user profile. The selection algorithm takes into account the user's values, behavioral patterns, interests, thought patterns, and emotional information.

[0994] 5. Advertising Presentation:

[0995] The server sends the selected advertisement to the device, which then presents it to the user, allowing the user to receive advertisements that match their interests and emotions.

[0996] Specific examples

[0997] For example, if a user replies, "Today I went to a cafe with friends and relaxed," the server extracts the keywords "friends," "cafe," and "relaxation," and recognizes the emotion as "positive." Based on this information, it presents the user with advertisements related to cafes and products related to relaxation.

[0998] Prompt Sentence Examples

[0999] A generative AI model that allows a system to generate questions for a user could use prompts like this:

[1000] "You are a model for an ad selection engine. Please identify your interests from the following conversation and select the most suitable ad. Conversation: Today I went to a cafe with a friend to relax."

[1001] This invention makes it possible to realize highly accurate advertisement distribution based on the individual interests and emotions of users.

[1002] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1003] Step 1: User registration and initial setup

[1004] A user accesses the system and enters basic information such as name, age, gender, hobbies, etc. The terminal sends the entered information to the server, which then stores the received information in a database.

[1005] Input: Basic information entered by the user (name, age, gender, hobbies)

[1006] Output: Basic information is saved to the database

[1007] Step 2: Start a natural conversation

[1008] The server uses the generative AI model to initiate a natural conversation with the user. For example, it might send an initial message like, "How was your day today?" The user might reply, "Today I went to a cafe with a friend to relax." The device then sends this reply to the server.

[1009] Input: A conversational prompt sent by the server to the user ("How was your day?")

[1010] Output: User response ("Today I went to a cafe with a friend to relax.")

[1011] Step 3: Collect and analyze information

[1012] The server analyzes the received conversation data and uses an NLP engine (TextBlob) to extract keywords and sentiment information. It also performs sentiment analysis using a Transformers pipeline. Based on this information, it updates the user profile and saves it in the database.

[1013] Input: User conversation data ("Today I went to a cafe with a friend to relax.")

[1014] Output: Extracted keywords ("friends", "cafe", "relax") and sentiment information (positive)

[1015] Step 4: Optimize your ads

[1016] The server selects the most suitable advertisements based on the updated user profile. The selection algorithm takes into account the user's values, behavioral patterns, interests, thought patterns, and emotional information.

[1017] Input: Updated user profile (specific values, behavioral patterns, interests, thought patterns, emotional information)

[1018] Output: Selection of the best ad

[1019] Step 5: Present your ad

[1020] The server sends the selected advertisement to the device, which then presents it to the user, allowing the user to receive advertisements that match their interests and emotions.

[1021] Input: Best ad selection results

[1022] Output: The ad is displayed on the user's device

[1023] Through the above steps, highly accurate advertisement delivery based on the individual interests and emotions of each user is realized.

[1024] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1025] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1026] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1027] [Third embodiment]

[1028] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1029] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1031] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1032] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1033] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1035] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1036] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1038] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1039] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1040] The present invention is a system that collects in-depth information such as a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on this information. How this system is implemented will be explained below.

[1041] System configuration

[1042] 1. User Device:

[1043] Users access the system using internet-connected devices such as smartphones and personal computers.

[1044] 2. Server:

[1045] The server is a platform for processing data sent from user devices, and is equipped with a database, a natural language processing engine, a generative AI model, and a matching algorithm.

[1046] Program processing

[1047] 1. User registration and initial setup:

[1048] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[1049] The terminal transmits the input information to the server.

[1050] The server stores the information in a database and notifies the terminal that the initial setup is complete.

[1051] 2. Natural conversation starters:

[1052] The server launches the generative AI model and sends an initial message to the device to initiate a natural conversation with the user.

[1053] The device will prompt the user with questions such as "How was your day today?"

[1054] Users can freely respond to everyday topics through conversations with the generative AI model.

[1055] For example, if the user replies, "Today I went to a cafe with a friend to relax," the terminal sends this to the server.

[1056] 3. Information Collection and Analysis:

[1057] The server analyzes the received conversation data using a natural language processing engine.

[1058] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data and the user profile is updated.

[1059] The updated profile information is saved in a database.

[1060] 4. Generate match candidates:

[1061] The server accumulates conversation data over a certain period of time (usually one week) and analyzes the user's values, behavioral patterns, interests, and thought patterns.

[1062] Based on the analysis results, the profile is compared with other users' profiles to generate matching candidates with common values ​​and interests.

[1063] The server lists the best matching candidates and sends them to the device.

[1064] 5. Presentation of results:

[1065] The device will display details of potential matches, commonalities, and reasons for the match to the user, providing specific information such as, "We've found someone who's perfect for you. We share common interests of 'loving cafes' and 'relaxing'."

[1066] The user can review the details of the presented match and proceed to the next step (e.g., sending a message or starting a conversation).

[1067] Specific examples

[1068] For example, when User A registers with the system and starts a conversation with the generative AI model, it is learned through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and presents User A with this matching candidate. User A receives this information, and if he or she becomes interested in User B, he or she can send a direct message to the other person.

[1069] As described above, the present invention is a system that collects and analyzes in-depth information about users and provides optimal matches based on that information, thereby providing more satisfying encounters.

[1070] The processing flow will be explained below.

[1071] Step 1:

[1072] A user accesses the system and enters basic information (name, age, gender, hobbies, etc.).

[1073] The terminal sends the input information to the server.

[1074] The server stores the received information in a database.

[1075] Step 2:

[1076] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[1077] The terminal displays this message to the user.

[1078] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[1079] The terminal sends the user's reply to the server.

[1080] Step 3:

[1081] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[1082] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data.

[1083] The server reflects the extracted information in the user profile and stores it in a database.

[1084] Step 4:

[1085] The generative AI model generates the next question for the user and sends it to the device.

[1086] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[1087] The user replies, "I went to Starbucks."

[1088] The terminal sends the user's reply back to the server.

[1089] Step 5:

[1090] The server continuously collects and analyzes conversation data and updates user profiles accordingly.

[1091] Data accumulated over a certain period (usually one week) is comprehensively analyzed.

[1092] Clarify the user's values, behavioral patterns, interests, and thought patterns.

[1093] Step 6:

[1094] The server uses the parsed user profile to match it with other user profiles.

[1095] Extract matching candidates with common values ​​and interests.

[1096] The server lists the best matching candidates and sends them to the device.

[1097] Step 7:

[1098] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'love cafes' and 'relaxation-oriented'."

[1099] The user reviews the details of the proposed match and selects the next action, such as "Learn more" or "Send a message."

[1100] The terminal communicates the user's actions to the server and takes the next action.

[1101] The above are the processing steps of the program in the present invention. This series of processes makes it possible to achieve highly accurate matching based on the user's values ​​and behavioral patterns.

[1102] Example 1

[1103] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1104] Conventional matching systems perform matching based only on basic user information and simple hobbies and preferences, making it difficult to achieve highly accurate matching that reflects deeper values ​​and behavioral patterns. Furthermore, there was a lack of means to collect deeper information through natural conversation, which resulted in low accuracy of user profiles and made it difficult to provide highly satisfying encounters.

[1105] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1106] In this invention, the server includes means for a user to input basic information, means for saving generated conversation data, means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, means for generating optimal match candidates based on the extracted user information, means for presenting the generated match candidates to the user, means for starting a conversation with the user using a generative AI model and receiving user input, and means for analyzing the received conversation data with a natural language processing engine and updating the user profile. This enables the collection and analysis of in-depth information and highly accurate matching based on the user's values ​​and behavioral patterns.

[1107] "User" refers to a person who accesses the system and enters personal information and conversation data.

[1108] "Basic information" refers to the initial setting data such as name, age, gender, and hobbies that a user enters when registering with the system.

[1109] "Conversational Data" refers to the textual content of the dialogue between a user and a generative AI model.

[1110] "Database" refers to a storage device for storing basic user information, conversation data, analysis results, etc.

[1111] A "generative AI model" refers to an artificial intelligence algorithm that generates natural conversations and engages in dialogue with users.

[1112] A "natural language processing engine" refers to software that analyzes text data and extracts keywords and sentiment information.

[1113] A "user profile" refers to data that compiles information such as a user's values, behavioral patterns, interests, and thought patterns.

[1114] "Matching candidates" refer to other users who share common values ​​and interests based on analyzed user information.

[1115] A "prompt sentence" is an instruction sentence input to a generative AI model to start or manage a dialogue.

[1116] "Analysis results" refers to the keywords and sentiment information extracted by the natural language processing engine by analyzing the conversation data.

[1117] The present invention is a system that collects in-depth information such as a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on this information. The configuration and operation of this system are described in detail below.

[1118] System configuration

[1119] The system consists of the following main components:

[1120] 1. User terminal: Users access the system using internet-connected devices such as smartphones and personal computers.

[1121] 2. Server: The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, and matching algorithm.

[1122] Specific processing of the program

[1123] 1. User registration and initial setup:

[1124] A user accesses the system and enters basic information such as name, age, gender, and hobbies, using a web form or mobile application as the interface.

[1125] The device receives this basic information and sends it to the server using an HTTP request.

[1126] The server stores the received information in a database and notifies the terminal that the initial settings are complete.

[1127] 2. Natural conversation starters:

[1128] The server invokes the generative AI model to generate an initial message to initiate a natural conversation with the user, for example, using a prompt such as "Hello, how are you doing today?"

[1129] The terminal displays the initial message received from the server to the user.

[1130] The user responds to the displayed message by inputting content such as "Today I went to a cafe with a friend and relaxed."

[1131] The terminal sends the user's response to the server.

[1132] 3. Information Collection and Analysis:

[1133] The server analyzes the received conversation data using a natural language processing engine (such as NLTK or SpaCy) to extract keywords and sentiment information. Specifically, it identifies the keywords "friends," "cafe," and "relax."

[1134] Based on these keywords and sentiment information, the user profile is updated.

[1135] The updated profile is stored in a database, improving the accuracy of the user's values ​​and behavioral patterns.

[1136] 4. Generate match candidates:

[1137] The server analyzes the accumulated conversation data and user profiles to generate optimal matching candidates between other users who share common values ​​and interests.

[1138] The generated matching candidates include specific information such as, "User B (ID: 67890) and you share common interests in 'outdoor activities' and 'cafe hopping'."

[1139] 5. Presentation of results:

[1140] The terminal displays details of the generated match candidates, as well as commonalities and reasons for matching, to the user.

[1141] The user can review the presented matching candidates and select an option, for example, "Would you like to send a message to User B?"

[1142] Specific examples

[1143] For example, when User A registers with the system and begins a conversation with the generative AI model, it is learned through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and presents User A with this matching candidate. User A receives this information, and if he or she becomes interested in User B, he or she can send a direct message to the other person.

[1144] As described above, the present invention collects and analyzes in-depth information about users and provides optimal matching based on that information, thereby achieving encounters that are highly satisfying for users.

[1145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1146] Step 1:

[1147] User registration and initial settings

[1148] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[1149] Input: Name (e.g., Taro), Age (e.g., 30 years old), Gender (e.g., male), Hobbies (e.g., reading, running)

[1150] What it does: Enter information using a web form or mobile application.

[1151] Output: Basic information entered.

[1152] The device receives this basic information and sends it to the server using an HTTP request.

[1153] Input: Basic information entered by the user.

[1154] What it does: Creates an HTTP POST request and sends it to the server.

[1155] Output: The request with basic information.

[1156] The server stores the received information in a database and notifies the terminal that the initial settings are complete.

[1157] Input: Basic information sent from the device.

[1158] Data processing: Basic information is stored in a database.

[1159] Output: Notification that initial setup is complete.

[1160] Step 2:

[1161] Natural conversation starters

[1162] The server launches the generative AI model and generates an initial message to initiate a natural conversation with the user.

[1163] Input: User information after initial setup is complete.

[1164] Data calculation: The generative AI model is given the prompt, "Hello, how are you doing today?"

[1165] Output: Initial message.

[1166] The terminal displays the initial message received from the server to the user.

[1167] Input: The initial message sent by the server.

[1168] Behavior: Displays a message in the chat box or other UI.

[1169] Output: Start of user interaction.

[1170] The user responds to the displayed message by inputting content such as "Today I went to a cafe with a friend and relaxed."

[1171] Input: The user's response message.

[1172] Action: Type something into the chat box.

[1173] Output: The user's response data.

[1174] The terminal sends the user's response to the server.

[1175] Input: User response data.

[1176] What it does: Creates an HTTP POST request and sends it to the server.

[1177] Output: The response data sent to the server.

[1178] Step 3:

[1179] Information collection and analysis

[1180] The server analyzes the received conversation data using a natural language processing engine (e.g., NLTK or SpaCy) to extract keywords and sentiment information.

[1181] Input: User conversation data.

[1182] Data calculation: A natural language processing engine performs text analysis to extract important keywords (e.g., "friends," "cafe," "relax") and sentiment information.

[1183] Output: Extracted keywords and sentiment information.

[1184] The extracted keywords and sentiment information are used to update the user profile.

[1185] Input: Keywords and sentiment information.

[1186] Data processing: Add and update keywords and sentiment data to user profile information.

[1187] Output: The updated user profile.

[1188] The updated profile information is saved in the database.

[1189] Input: The updated user profile.

[1190] What it does: Saves information to a database.

[1191] Output: Profiles stored in a database.

[1192] Step 4:

[1193] Generating match candidates

[1194] The server analyzes the accumulated conversation data and user profiles to generate optimal matching candidates between other users who share common values ​​and interests.

[1195] Input: User profile and conversation data.

[1196] Data calculation: Matching candidates are extracted using analytical algorithms.

[1197] Output: A list of potential matches.

[1198] Step 5:

[1199] Presentation of results

[1200] The server sends the matching candidates to the terminal.

[1201] Input: Match candidates.

[1202] Operation: Sends match candidate information to the device.

[1203] Output: Match candidates sent to the device.

[1204] The terminal displays details of the generated match candidates, as well as commonalities and reasons for matching, to the user.

[1205] Input: Submitted match candidate information.

[1206] Operation: Displays matching candidates and commonalities information on the display screen.

[1207] Output: The matching details displayed to the user.

[1208] The user can review the presented matching candidates and select an option, for example, "Would you like to send a message to User B?"

[1209] Input: User actions based on presented information.

[1210] Action: Choice selection operation.

[1211] Output: The user's next action (e.g., send a message).

[1212] (Application example 1)

[1213] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1214] Conventional food delivery applications make recommendations based solely on user preferences and past ordering history, without adequately collecting and analyzing in-depth user information. As a result, they are unable to provide truly personalized suggestions based on the user's values ​​and daily behavioral patterns, and are unable to fully increase user satisfaction. The objective of this invention is to provide a system that collects in-depth information, such as values, behavioral patterns, interests, and thought patterns, through natural conversations with users, and recommends optimal food delivery options based on this information.

[1215] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1216] In this invention, the server includes a means for a user to input basic information, a means for saving the generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for generating optimal match candidates and proposals based on the extracted user information, and a means for presenting the generated match candidates and proposals to the user, thereby making it possible to propose optimal food delivery options based on the user's in-depth information.

[1217] "Basic information" is data entered by the user, such as name, age, gender, allergy information, and favorite dishes.

[1218] The "generated conversation data" is text data obtained through natural conversation with the user.

[1219] "Storage means" refers to the technology used to store conversation data in a database or server.

[1220] The "means of analysis" refers to natural language processing engines and algorithms that extract values, behavioral patterns, interests, and thought patterns from stored conversation data.

[1221] "User information" refers to data such as the user's values, behavioral patterns, interests, and thought patterns obtained through analysis.

[1222] "Matching suggestions" are suitable food delivery options and other recommendations based on the user's in-depth information.

[1223] The "presenting means" refers to a technique for displaying the generated match candidates and suggestions on the user's device.

[1224] A "generative AI model" is an artificial intelligence technology for generating natural conversations with users.

[1225] "Keywords" are important words and phrases extracted from conversation data.

[1226] "Sentiment information" is information about emotions and evaluations obtained from conversation data.

[1227] "Food delivery options" are meal delivery options recommended based on a user's preferences and behavioral patterns.

[1228] This invention is a personalized recommendation system that utilizes in-depth user information in the food delivery field. The system collects information such as values, behavioral patterns, interests, and thought patterns through natural conversation with the user, and provides optimal food delivery options based on this information.

[1229] System configuration

[1230] 1. User Device:

[1231] Users access the system using a smartphone, which has an application installed and an interface for users to enter basic information.

[1232] 2. Server:

[1233] The server is a platform for processing data sent from user devices, and is equipped with a database, a natural language processing engine, a generative AI model, and a matching algorithm.

[1234] Program processing

[1235] 1. User registration and initial setup:

[1236] Users download and launch the app and enter basic information such as their name, age, gender, allergies, and favorite dishes. This data is sent from the device to a server and stored in a database.

[1237] 2. Natural conversation starters:

[1238] The server runs a generative AI model (e.g., GPT-4) and sends prompts to the user, such as, "What kind of food have you liked recently?" The user's response data is sent from the device to the server and stored in a database.

[1239] Examples:

[1240] Example prompt: "What kind of food have you been enjoying lately?"

[1241] 3. Information Collection and Analysis:

[1242] A natural language processing engine (e.g., spaCy) on the server analyzes user response data and extracts and updates values, behavioral patterns, interests, thought patterns, etc. This data is stored in a database as a user profile.

[1243] 4. Present options:

[1244] The server's matching algorithm (e.g., TensorFlow) generates optimal food delivery options based on accumulated user information. The generated options are sent to the device and presented to the user. Specific suggestions are made, such as, "How about having dinner with your family today?"

[1245] Hardware and software used

[1246] Hardware: Smartphone (user device)

[1247] software:

[1248] Firebase (database): Used to store basic user information and conversation data

[1249] GPT-4 (generative AI model): Generates natural conversations with users

[1250] spaCy (natural language processing engine): Used to analyze conversation data

[1251] TensorFlow (Matching Algorithm): Generating Food Delivery Options

[1252] Specific examples

[1253] For example, if a user types into the app, "I've been craving curry lately," the generative AI model might respond, "That's great! What kind of curry do you like?" If the user responds, "I like spicy Indian curry," the server might use this information to suggest the best Indian curry delivery options. An example prompt might be, "What kind of food have you been enjoying lately?"

[1254] As described above, the present invention is a system that collects and analyzes in-depth information about users and provides optimal food delivery options based on that information, thereby increasing user satisfaction.

[1255] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1256] Step 1:

[1257] A user downloads and launches a food delivery application. The user enters basic information (such as name, age, gender, allergy information, and favorite dishes). This data is sent from the device to the server and stored in the Firebase database. The input is the user's basic information, and the output is the user's basic information data sent to the server.

[1258] Step 2:

[1259] The server launches a generative AI model (e.g., GPT-4) and sends the user an initial prompt: "What kind of food have you liked recently?" This prompt encourages the user to start a natural conversation. The input is the prompt, and the output is the prompt displayed on the user's device.

[1260] Step 3:

[1261] The user responds to the prompt by typing "I've been craving curry lately." This response data is sent from the device to the server and stored in the Firebase database. The input is the user's response data, and the output is the response data stored on the server.

[1262] Step 4:

[1263] The server uses a natural language processing engine (e.g., spaCy) to analyze the user's response data. This analysis extracts keywords and sentiment information such as values, behavioral patterns, interests, and thought patterns, and updates the user profile. The input is the user's response data, and the output is the updated user profile data.

[1264] Step 5:

[1265] The server uses a matching algorithm (e.g., TensorFlow) to generate optimal food delivery options based on the updated user profile, which match the user's preferences and behavioral patterns. The input is the updated user profile data, and the output is the food delivery options.

[1266] Step 6:

[1267] The generated food delivery options are sent from the server to the user's device and presented to the user. Specifically, suggestions such as "How about this curry for dinner with your family today?" are displayed to the user. The input is the food delivery options, and the output is the options presented on the user's device.

[1268] Step 7:

[1269] The user reviews the proposed options and places an order if they like them. This order information is again sent to the server and stored in a database. The input is the user's order information, and the output is the order data stored on the server.

[1270] Through the above processing steps, personalized food delivery suggestions based on the user's in-depth information are realized, which can increase user satisfaction.

[1271] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1272] The present invention aims to improve matching accuracy by combining an emotion engine with a system that collects a user's values, behavioral patterns, interests, and thought patterns through natural conversation and provides highly accurate matching based on that information, thereby generating a more accurate profile based on the user's emotions.

[1273] System configuration

[1274] 1. User Device:

[1275] Users access the system using internet-connected devices such as smartphones and personal computers.

[1276] 2. Server:

[1277] The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, emotion engine, and matching algorithm.

[1278] Program processing

[1279] 1. User registration and initial setup:

[1280] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[1281] The terminal sends the input information to the server.

[1282] The server stores the received information in a database.

[1283] 2. Natural conversation starters:

[1284] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[1285] The terminal displays this message to the user.

[1286] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[1287] The terminal sends the user's reply to the server.

[1288] 3. Information Collection and Analysis:

[1289] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[1290] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the analyzed conversation data.

[1291] The server uses an emotion engine to recognize the user's emotion from the conversation data.

[1292] The user profile is updated based on the recognized emotion information and keywords.

[1293] The updated profile information is saved in a database.

[1294] 4. Continue the conversation and refine your profile:

[1295] The server then has the generative AI model generate the next question and send it to the device.

[1296] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[1297] The user replies, "I went to Starbucks."

[1298] The terminal sends the user's reply back to the server.

[1299] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine user profiles.

[1300] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[1301] 5. Generate candidate matches:

[1302] The server uses the analyzed emotion information and the user profile to match other user profiles.

[1303] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[1304] The server lists the best matching candidates and sends them to the device.

[1305] 6. Presentation of results:

[1306] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'loving cafes' and 'relaxing'."

[1307] Users can check the details of the presented matching candidates and select their next action, such as "View more" or "Send a message."

[1308] The terminal communicates the user's actions to the server and takes the next action.

[1309] Specific examples

[1310] For example, when User A registers with the system and begins a conversation with the generative AI model, it becomes clear through daily conversation that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that User A feels "spending time at cafes is very relaxing." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and further confirms that there are many similarities in terms of emotions. User A is presented with a matching candidate and notified, "We've found someone who suits you. You share common interests of 'cafe-loving' and 'relaxing,' as well as similar emotions." User A receives this information and, if he or she becomes interested in User B, can send a direct message.

[1311] The present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about users into the analysis, thereby providing highly satisfying encounters that could not be achieved with conventional systems.

[1312] The processing flow will be explained below.

[1313] Step 1:

[1314] A user accesses the system and enters basic information (name, age, gender, hobbies, etc.).

[1315] The terminal sends the input information to the server.

[1316] The server stores the received information in a database.

[1317] Step 2:

[1318] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[1319] The terminal displays this message to the user.

[1320] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[1321] The terminal sends the user's reply to the server.

[1322] Step 3:

[1323] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[1324] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data.

[1325] The server uses an emotion engine to recognize the user's emotion from the conversation data.

[1326] The server updates the user profile based on the recognized emotion information and keywords.

[1327] The updated profile information is saved in a database.

[1328] Step 4:

[1329] The server then has the generative AI model generate the next question and send it to the device.

[1330] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[1331] The user replies, "I went to Starbucks."

[1332] The terminal sends the user's reply back to the server.

[1333] Step 5:

[1334] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine user profiles.

[1335] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[1336] Step 6:

[1337] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[1338] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[1339] The server lists the best matching candidates and sends them to the device.

[1340] Step 7:

[1341] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'love cafes' and 'relaxation-oriented'."

[1342] The user reviews the details of the proposed match and selects the next action, such as "Learn more" or "Send a message."

[1343] The terminal communicates the user's actions to the server and takes the next action.

[1344] Examples:

[1345] For example, user A registers with the system and begins a conversation with the generative AI model. Through daily conversations, it becomes clear that user A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that user A finds "spending time at cafes very relaxing." Based on this information, the server analyzes that another user, user B, likes outdoor activities and enjoys cafe hopping, and further confirms that there are many similarities in terms of emotions. The server presents user A with matching candidates and notifies him / her, "We've found someone who suits you. You share common interests of 'cafe-loving' and 'relaxing,' as well as similar emotions." User A receives this information, and if he / she becomes interested in user B, he / she can send a direct message to the other person.

[1346] The present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about users into the analysis, thereby providing highly satisfying encounters that could not be achieved with conventional systems.

[1347] Example 2

[1348] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1349] Conventional matching systems have difficulty creating profiles that consider not only basic user information but also deeper values ​​and emotions. This results in low matching accuracy and fails to sufficiently increase user satisfaction. Furthermore, they are unable to reflect the continually changing interests and emotions of users, meaning that once a profile is created, it easily becomes outdated.

[1350] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for a user to input basic information, a means for saving generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for analyzing the user's emotional information using a sentiment analysis engine, and a means for causing the generative AI model to generate the next prompt and continuously collect conversation data. This makes it possible to keep a profile containing in-depth information of the user always up-to-date, enabling highly accurate matching that takes emotional information into consideration.

[1351] The "means for users to input basic information" is a function that provides an interface that allows users to input basic information such as name, age, sex, and hobbies.

[1352] The "means for saving generated conversation data" is a function for saving data generated from a conversation with a user in a storage device such as a database.

[1353] "Means of analyzing saved conversation data to extract a user's values, behavioral patterns, interests, and thought patterns" refers to a function that analyzes saved conversation data using natural language processing technology, etc., to extract a user's personal characteristics and patterns.

[1354] The "means for generating optimal matching candidates based on extracted user information" is a function for generating optimal matching candidates with other users using the characteristic information of the user obtained by analysis.

[1355] The "means for presenting generated match candidates to the user" is a function for displaying detailed information about the generated match candidates to the user.

[1356] The "means for analyzing user emotional information using an emotion analysis engine" is a function for analyzing user emotions from conversation data and extracting the emotional information.

[1357] "Means for having the generative AI model generate the next prompt and continuously collect conversation data" is a function that uses the generative AI model to generate the next question or message, and collects data while encouraging the continuation of the conversation with the user.

[1358] This invention relates to a system that collects a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on the collected information. The system aims to improve matching accuracy by combining an emotion engine to generate a highly accurate profile based on the user's emotions.

[1359] The system consists of the following:

[1360] 1. User Device:

[1361] Users access the system using internet-connected devices such as smartphones and personal computers.

[1362] 2. Server:

[1363] The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, emotion engine, and matching algorithm.

[1364] Specific embodiments of the invention are set out below:

[1365] 1. User registration and initial setup:

[1366] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[1367] The terminal sends the input information to the server.

[1368] The server stores the received information in a database.

[1369] 2. Natural conversation starters:

[1370] The server launches the generative AI model, generates the initial message "How was your day today?" and sends it to the device.

[1371] The terminal displays this message to the user.

[1372] The user replies, "Today I went to a cafe with a friend to relax."

[1373] The terminal sends this reply to the server.

[1374] 3. Information Collection and Analysis:

[1375] The server analyzes the received conversation data using a natural language processing (NLP) engine, such as Google Natural Language or Amazon Comprehend.

[1376] Keywords such as "friends," "cafe," and "relaxation" and emotional information are extracted from the analyzed data.

[1377] The server uses an emotion engine, such as IBM Watson Tone Analyzer, to recognize the user's emotions from the conversation data.

[1378] The user profile is updated based on the recognized emotion information and keywords.

[1379] The updated profile is saved in the database.

[1380] 4. Continue the conversation and refine your profile:

[1381] The server then has the generative AI model generate the next question, for example, "Which cafe did you go to?", and sends it to the device.

[1382] The terminal displays the generated question to the user.

[1383] The user replies, "I went to Starbucks."

[1384] The terminal sends this reply back to the server.

[1385] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine the user profile. Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep values, behavioral patterns, interests, and thought patterns.

[1386] 5. Generate candidate matches:

[1387] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[1388] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[1389] The server lists the best matching candidates and sends them to the device.

[1390] 6. Presentation of results:

[1391] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'liking cafes' and 'relaxing'."

[1392] Users can review the details of the proposed matches and select their next action, such as "View more" or "Send a message."

[1393] The terminal communicates the user's actions to the server and takes the next action (e.g., prepares to send a message).

[1394] To explain how it works in detail, when User A registers with the system and begins a conversation with the generative AI model, it is discovered through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that User A feels that "spending time at cafes is very relaxing." Based on this information, the server analyzes that User B is also a person who likes outdoor activities and enjoys cafe hopping. It also confirms that there are many similarities in terms of emotions. For example, the server may notify User A that "We've found someone who suits you. Common interests include a love of cafes and a desire to relax." If User A receives this information and becomes more interested in User B, he or she can send a direct message to the other person.

[1395] Examples of prompts include:

[1396] "How was your day today?"

[1397] "Which cafe did you go to?"

[1398] "What was the most memorable thing that happened today?"

[1399] As described above, the present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about the user into the analysis.

[1400] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1401] Step 1: User registration and initial setup

[1402] Specific behavior:

[1403] Users access the system using a smartphone or computer.

[1404] The server displays a form for the user to enter basic information such as name, age, sex, and hobbies.

[1405] The user fills in the required information in the form and clicks the "Submit" button.

[1406] Input: Basic information entered by the user (name, age, gender, hobbies, etc.)

[1407] Output: The input information is sent to the server and stored in a database.

[1408] Data processing: The server checks the format of the information it receives and converts it into the required format before storing it in the database.

[1409] Step 2: Start a natural conversation

[1410] Specific behavior:

[1411] The server launches the generative AI model and generates the first message: "How was your day?"

[1412] The server sends this message to the terminal, which displays the message to the user.

[1413] The user replies, "Today I went to a cafe with a friend to relax."

[1414] The terminal sends the user's reply to the server.

[1415] Input: Basic information about the user, the initial message generated by the generative AI model

[1416] Output: The user's reply is sent to the server.

[1417] Data processing: The generative AI model generates the initial message and sends the user's response to the server.

[1418] Step 3: Collect and analyze information

[1419] Specific behavior:

[1420] The server analyzes the received conversation data using a natural language processing (NLP) engine, such as Google Natural Language.

[1421] The NLP engine extracts keywords such as "friends," "cafe," and "relaxation" as well as emotional information from the conversation data.

[1422] The server uses an emotion engine, such as IBM Watson Tone Analyzer, to recognize the user's emotions from the conversation data.

[1423] Update user profiles based on keywords and recognized emotion information.

[1424] The server saves the updated profile in the database.

[1425] Input: User conversation data

[1426] Output: Extracted keywords and sentiment information, updated user profile

[1427] Data processing: The NLP engine analyzes the conversation data and extracts keywords and emotional information. The emotional engine recognizes the emotional information and updates the user profile accordingly.

[1428] Step 4: Continue the conversation and refine your profile

[1429] Specific behavior:

[1430] The server then asks the generative AI model to generate the next question, for example, "Which cafe did you go to?"

[1431] The server sends the generated question to the terminal, which displays it to the user.

[1432] The user replies, "I went to Starbucks."

[1433] The terminal sends this reply to the server.

[1434] The server then analyzes the received data using an NLP engine and also uses an emotion engine to further refine the user profile.

[1435] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[1436] Input: Previous conversation data and the next prompt to generate

[1437] Output: New answers from the user and an updated profile

[1438] Data processing: Generative AI models generate new questions and continue the conversation based on them, analyzing incoming data to refine profiles.

[1439] Step 5: Generate candidate matches

[1440] Specific behavior:

[1441] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[1442] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[1443] The server lists the best matching candidates and sends this information to the device.

[1444] Input: Parsed user profile and emotional information

[1445] Output: A list of potential matches

[1446] Data processing: Matching user profiles with other user profiles to extract the best possible matches.

[1447] Step 6: Presenting the results

[1448] Specific behavior:

[1449] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'liking cafes' and 'relaxing'."

[1450] The user checks the details of the presented match candidates and selects the next action, such as "View more" or "Send a message."

[1451] The terminal communicates the user's actions to the server and takes the next action.

[1452] Input: A list of potential matches and user actions

[1453] Output: Details of the match candidate and the user's selected next action

[1454] Data processing: Displaying information about potential matches to the user and communicating the user's selected action to the server.

[1455] (Application example 2)

[1456] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1457] Conventional ad delivery systems often present uniform ads because they are unable to fully understand users' interests. This results in problems such as users not being presented with ads that are beneficial to them, resulting in reduced advertising effectiveness. Furthermore, because ad delivery does not take into account user emotions, the user experience does not improve and the accuracy of ad targeting also decreases.

[1458] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1459] In this invention, the server includes a means for a user to input basic information, a means for saving the generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for selecting an optimal advertisement based on the extracted user information, and a means for presenting the selected advertisement to the user, thereby enabling highly accurate advertisement delivery based on the user's individual interests and emotions.

[1460] A "user" is an individual who uses the system.

[1461] "Basic information" refers to information such as name, age, sex, and hobbies that the user inputs during initial setup.

[1462] "Conversation data" is text data generated from natural interactions with the user.

[1463] "Means of storage" refers to the process of recording the generated conversation data in storage such as a database.

[1464] The "analysis means" is a process of analyzing saved conversation data using a natural language processing engine or the like to extract the user's values, behavioral patterns, interests, and thought patterns.

[1465] "Extracted user information" refers to data such as the user's values, behavioral patterns, interests, and thought patterns obtained through the analysis of conversation data.

[1466] The "means for selecting the most suitable advertisement" is an algorithm that automatically selects the advertisement that is most relevant to the user based on the extracted user information.

[1467] "Selected Advertisement" refers to the most suitable advertisement based on user information.

[1468] "Presenting means" refers to the process of displaying the selected advertisement on the screen of the device used by the user.

[1469] A "generative AI model" is an artificial intelligence model used to engage in natural conversations with users.

[1470] "Emotion information" is data relating to the user's emotions extracted from conversation data.

[1471] A "user profile" is a set of detailed information that includes a user's values, behavioral patterns, interests, thought patterns, emotional information, and so on.

[1472] "Advertisement" is information for advertising products or services to users.

[1473] An "advertising distribution system" is a system that uses user information to select the most suitable advertisement and present it to the user.

[1474] MODE FOR CARRYING OUT THE INVENTION

[1475] This invention is a system for optimizing advertisements based on a user's values, behavioral patterns, interests, thought patterns, and emotional information. This system operates when a user accesses it via the Internet using a device such as a smartphone or smart glasses.

[1476] Hardware and software used

[1477] Hardware:

[1478] Smartphone

[1479] Smart Glasses

[1480] head-mounted display

[1481] software:

[1482] Python

[1483] SQLite

[1484] TextBlob

[1485] Transformers pipeline(Hugging Face)

[1486] System Configuration

[1487] 1. User registration and initial setup:

[1488] Users access the system and enter basic information such as their name, age, gender, hobbies, etc. The terminal sends the entered information to the server, which then stores the received information in a database.

[1489] 2. Natural conversation starters:

[1490] The server uses the generative AI model to initiate a natural conversation with the user. For example, it might send an initial message like, "How was your day today?", to which the user replies, "Today I went to a cafe with a friend to relax." The device then sends this reply to the server.

[1491] 3. Information Collection and Analysis:

[1492] The server analyzes the received conversation data and uses an NLP engine (TextBlob) to extract keywords and sentiment information. It also performs sentiment analysis using a Transformers pipeline. Based on this information, it updates the user profile and saves it in the database.

[1493] 4. Ad optimization:

[1494] The server selects the most suitable advertisements based on the updated user profile. The selection algorithm takes into account the user's values, behavioral patterns, interests, thought patterns, and emotional information.

[1495] 5. Advertising Presentation:

[1496] The server sends the selected advertisement to the device, which then presents it to the user, allowing the user to receive advertisements that match their interests and emotions.

[1497] Specific examples

[1498] For example, if a user replies, "Today I went to a cafe with friends and relaxed," the server extracts the keywords "friends," "cafe," and "relaxation," and recognizes the emotion as "positive." Based on this information, it presents the user with advertisements related to cafes and products related to relaxation.

[1499] Prompt Sentence Examples

[1500] A generative AI model that allows a system to generate questions for a user could use prompts like this:

[1501] "You are a model for an ad selection engine. Please identify your interests from the following conversation and select the most suitable ad. Conversation: Today I went to a cafe with a friend to relax."

[1502] This invention makes it possible to realize highly accurate advertisement distribution based on the individual interests and emotions of users.

[1503] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1504] Step 1: User registration and initial setup

[1505] A user accesses the system and enters basic information such as name, age, gender, hobbies, etc. The terminal sends the entered information to the server, which then stores the received information in a database.

[1506] Input: Basic information entered by the user (name, age, gender, hobbies)

[1507] Output: Basic information is saved to the database

[1508] Step 2: Start a natural conversation

[1509] The server uses the generative AI model to initiate a natural conversation with the user. For example, it might send an initial message like, "How was your day today?" The user might reply, "Today I went to a cafe with a friend to relax." The device then sends this reply to the server.

[1510] Input: A conversational prompt sent by the server to the user ("How was your day?")

[1511] Output: User response ("Today I went to a cafe with a friend to relax.")

[1512] Step 3: Collect and analyze information

[1513] The server analyzes the received conversation data and uses an NLP engine (TextBlob) to extract keywords and sentiment information. It also performs sentiment analysis using a Transformers pipeline. Based on this information, it updates the user profile and saves it in the database.

[1514] Input: User conversation data ("Today I went to a cafe with a friend to relax.")

[1515] Output: Extracted keywords ("friends", "cafe", "relax") and sentiment information (positive)

[1516] Step 4: Optimize your ads

[1517] The server selects the most suitable advertisements based on the updated user profile. The selection algorithm takes into account the user's values, behavioral patterns, interests, thought patterns, and emotional information.

[1518] Input: Updated user profile (specific values, behavioral patterns, interests, thought patterns, emotional information)

[1519] Output: Selection of the best ad

[1520] Step 5: Present your ad

[1521] The server sends the selected advertisement to the device, which then presents it to the user, allowing the user to receive advertisements that match their interests and emotions.

[1522] Input: Best ad selection results

[1523] Output: The ad is displayed on the user's device

[1524] Through the above steps, highly accurate advertisement delivery based on the individual interests and emotions of each user is realized.

[1525] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1526] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1527] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1528] [Fourth embodiment]

[1529] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1530] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1531] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1532] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1533] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1534] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1535] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1536] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1537] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1538] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1539] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1540] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1541] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1542] The present invention is a system that collects in-depth information such as a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on this information. How this system is implemented will be explained below.

[1543] System configuration

[1544] 1. User Device:

[1545] Users access the system using internet-connected devices such as smartphones and personal computers.

[1546] 2. Server:

[1547] The server is a platform for processing data sent from user devices, and is equipped with a database, a natural language processing engine, a generative AI model, and a matching algorithm.

[1548] Program processing

[1549] 1. User registration and initial setup:

[1550] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[1551] The terminal transmits the input information to the server.

[1552] The server stores the information in a database and notifies the terminal that the initial setup is complete.

[1553] 2. Natural conversation starters:

[1554] The server launches the generative AI model and sends an initial message to the device to initiate a natural conversation with the user.

[1555] The device will prompt the user with questions such as "How was your day today?"

[1556] Users can freely respond to everyday topics through conversations with the generative AI model.

[1557] For example, if the user replies, "Today I went to a cafe with a friend to relax," the terminal sends this to the server.

[1558] 3. Information Collection and Analysis:

[1559] The server analyzes the received conversation data using a natural language processing engine.

[1560] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data and the user profile is updated.

[1561] The updated profile information is saved in a database.

[1562] 4. Generate match candidates:

[1563] The server accumulates conversation data over a certain period of time (usually one week) and analyzes the user's values, behavioral patterns, interests, and thought patterns.

[1564] Based on the analysis results, the profile is compared with other users' profiles to generate matching candidates with common values ​​and interests.

[1565] The server lists the best matching candidates and sends them to the device.

[1566] 5. Presentation of results:

[1567] The device will display details of potential matches, commonalities, and reasons for the match to the user, providing specific information such as, "We've found someone who's perfect for you. We share common interests of 'loving cafes' and 'relaxing'."

[1568] The user can review the details of the presented match and proceed to the next step (e.g., sending a message or starting a conversation).

[1569] Specific examples

[1570] For example, when User A registers with the system and starts a conversation with the generative AI model, it is learned through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and presents User A with this matching candidate. User A receives this information, and if he or she becomes interested in User B, he or she can send a direct message to the other person.

[1571] As described above, the present invention is a system that collects and analyzes in-depth information about users and provides optimal matches based on that information, thereby providing more satisfying encounters.

[1572] The processing flow will be explained below.

[1573] Step 1:

[1574] A user accesses the system and enters basic information (name, age, gender, hobbies, etc.).

[1575] The terminal sends the input information to the server.

[1576] The server stores the received information in a database.

[1577] Step 2:

[1578] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[1579] The terminal displays this message to the user.

[1580] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[1581] The terminal sends the user's reply to the server.

[1582] Step 3:

[1583] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[1584] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data.

[1585] The server reflects the extracted information in the user profile and stores it in a database.

[1586] Step 4:

[1587] The generative AI model generates the next question for the user and sends it to the device.

[1588] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[1589] The user replies, "I went to Starbucks."

[1590] The terminal sends the user's reply back to the server.

[1591] Step 5:

[1592] The server continuously collects and analyzes conversation data and updates user profiles accordingly.

[1593] Data accumulated over a certain period (usually one week) is comprehensively analyzed.

[1594] Clarify the user's values, behavioral patterns, interests, and thought patterns.

[1595] Step 6:

[1596] The server uses the parsed user profile to match it with other user profiles.

[1597] Extract matching candidates with common values ​​and interests.

[1598] The server lists the best matching candidates and sends them to the device.

[1599] Step 7:

[1600] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'love cafes' and 'relaxation-oriented'."

[1601] The user reviews the details of the proposed match and selects the next action, such as "Learn more" or "Send a message."

[1602] The terminal communicates the user's actions to the server and takes the next action.

[1603] The above are the processing steps of the program in the present invention. This series of processes makes it possible to achieve highly accurate matching based on the user's values ​​and behavioral patterns.

[1604] Example 1

[1605] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1606] Conventional matching systems perform matching based only on basic user information and simple hobbies and preferences, making it difficult to achieve highly accurate matching that reflects deeper values ​​and behavioral patterns. Furthermore, there was a lack of means to collect deeper information through natural conversation, which resulted in low accuracy of user profiles and made it difficult to provide highly satisfying encounters.

[1607] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1608] In this invention, the server includes means for a user to input basic information, means for saving generated conversation data, means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, means for generating optimal match candidates based on the extracted user information, means for presenting the generated match candidates to the user, means for starting a conversation with the user using a generative AI model and receiving user input, and means for analyzing the received conversation data with a natural language processing engine and updating the user profile. This enables the collection and analysis of in-depth information and highly accurate matching based on the user's values ​​and behavioral patterns.

[1609] "User" refers to a person who accesses the system and enters personal information and conversation data.

[1610] "Basic information" refers to the initial setting data such as name, age, gender, and hobbies that a user enters when registering with the system.

[1611] "Conversational Data" refers to the textual content of the dialogue between a user and a generative AI model.

[1612] "Database" refers to a storage device for storing basic user information, conversation data, analysis results, etc.

[1613] A "generative AI model" refers to an artificial intelligence algorithm that generates natural conversations and engages in dialogue with users.

[1614] A "natural language processing engine" refers to software that analyzes text data and extracts keywords and sentiment information.

[1615] A "user profile" refers to data that compiles information such as a user's values, behavioral patterns, interests, and thought patterns.

[1616] "Matching candidates" refer to other users who share common values ​​and interests based on analyzed user information.

[1617] A "prompt sentence" is an instruction sentence input to a generative AI model to start or manage a dialogue.

[1618] "Analysis results" refers to the keywords and sentiment information extracted by the natural language processing engine by analyzing the conversation data.

[1619] The present invention is a system that collects in-depth information such as a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on this information. The configuration and operation of this system are described in detail below.

[1620] System configuration

[1621] The system consists of the following main components:

[1622] 1. User terminal: Users access the system using internet-connected devices such as smartphones and personal computers.

[1623] 2. Server: The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, and matching algorithm.

[1624] Specific processing of the program

[1625] 1. User registration and initial setup:

[1626] A user accesses the system and enters basic information such as name, age, gender, and hobbies, using a web form or mobile application as the interface.

[1627] The device receives this basic information and sends it to the server using an HTTP request.

[1628] The server stores the received information in a database and notifies the terminal that the initial settings are complete.

[1629] 2. Natural conversation starters:

[1630] The server invokes the generative AI model to generate an initial message to initiate a natural conversation with the user, for example, using a prompt such as "Hello, how are you doing today?"

[1631] The terminal displays the initial message received from the server to the user.

[1632] The user responds to the displayed message by inputting content such as "Today I went to a cafe with a friend and relaxed."

[1633] The terminal sends the user's response to the server.

[1634] 3. Information Collection and Analysis:

[1635] The server analyzes the received conversation data using a natural language processing engine (such as NLTK or SpaCy) to extract keywords and sentiment information. Specifically, it identifies the keywords "friends," "cafe," and "relax."

[1636] Based on these keywords and sentiment information, the user profile is updated.

[1637] The updated profile is stored in a database, improving the accuracy of the user's values ​​and behavioral patterns.

[1638] 4. Generate match candidates:

[1639] The server analyzes the accumulated conversation data and user profiles to generate optimal matching candidates between other users who share common values ​​and interests.

[1640] The generated matching candidates include specific information such as, "User B (ID: 67890) and you share common interests in 'outdoor activities' and 'cafe hopping'."

[1641] 5. Presentation of results:

[1642] The terminal displays details of the generated match candidates, as well as commonalities and reasons for matching, to the user.

[1643] The user can review the presented matching candidates and select an option, for example, "Would you like to send a message to User B?"

[1644] Specific examples

[1645] For example, when User A registers with the system and begins a conversation with the generative AI model, it is learned through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and presents User A with this matching candidate. User A receives this information, and if he or she becomes interested in User B, he or she can send a direct message to the other person.

[1646] As described above, the present invention collects and analyzes in-depth information about users and provides optimal matching based on that information, thereby achieving encounters that are highly satisfying for users.

[1647] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1648] Step 1:

[1649] User registration and initial settings

[1650] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[1651] Input: Name (e.g., Taro), Age (e.g., 30 years old), Gender (e.g., male), Hobbies (e.g., reading, running)

[1652] What it does: Enter information using a web form or mobile application.

[1653] Output: Basic information entered.

[1654] The device receives this basic information and sends it to the server using an HTTP request.

[1655] Input: Basic information entered by the user.

[1656] What it does: Creates an HTTP POST request and sends it to the server.

[1657] Output: The request with basic information.

[1658] The server stores the received information in a database and notifies the terminal that the initial settings are complete.

[1659] Input: Basic information sent from the device.

[1660] Data processing: Basic information is stored in a database.

[1661] Output: Notification that initial setup is complete.

[1662] Step 2:

[1663] Natural conversation starters

[1664] The server launches the generative AI model and generates an initial message to initiate a natural conversation with the user.

[1665] Input: User information after initial setup is complete.

[1666] Data calculation: The generative AI model is given the prompt, "Hello, how are you doing today?"

[1667] Output: Initial message.

[1668] The terminal displays the initial message received from the server to the user.

[1669] Input: The initial message sent by the server.

[1670] Behavior: Displays a message in the chat box or other UI.

[1671] Output: Start of user interaction.

[1672] The user responds to the displayed message by inputting content such as "Today I went to a cafe with a friend and relaxed."

[1673] Input: The user's response message.

[1674] Action: Type something into the chat box.

[1675] Output: The user's response data.

[1676] The terminal sends the user's response to the server.

[1677] Input: User response data.

[1678] What it does: Creates an HTTP POST request and sends it to the server.

[1679] Output: The response data sent to the server.

[1680] Step 3:

[1681] Information collection and analysis

[1682] The server analyzes the received conversation data using a natural language processing engine (e.g., NLTK or SpaCy) to extract keywords and sentiment information.

[1683] Input: User conversation data.

[1684] Data calculation: A natural language processing engine performs text analysis to extract important keywords (e.g., "friends," "cafe," "relax") and sentiment information.

[1685] Output: Extracted keywords and sentiment information.

[1686] The extracted keywords and sentiment information are used to update the user profile.

[1687] Input: Keywords and sentiment information.

[1688] Data processing: Add and update keywords and sentiment data to user profile information.

[1689] Output: The updated user profile.

[1690] The updated profile information is saved in the database.

[1691] Input: The updated user profile.

[1692] What it does: Saves information to a database.

[1693] Output: Profiles stored in a database.

[1694] Step 4:

[1695] Generating match candidates

[1696] The server analyzes the accumulated conversation data and user profiles to generate optimal matching candidates between other users who share common values ​​and interests.

[1697] Input: User profile and conversation data.

[1698] Data calculation: Matching candidates are extracted using analytical algorithms.

[1699] Output: A list of potential matches.

[1700] Step 5:

[1701] Presentation of results

[1702] The server sends the matching candidates to the terminal.

[1703] Input: Match candidates.

[1704] Operation: Sends match candidate information to the device.

[1705] Output: Match candidates sent to the device.

[1706] The terminal displays details of the generated match candidates, as well as commonalities and reasons for matching, to the user.

[1707] Input: Submitted match candidate information.

[1708] Operation: Displays matching candidates and commonalities information on the display screen.

[1709] Output: The matching details displayed to the user.

[1710] The user can review the presented matching candidates and select an option, for example, "Would you like to send a message to User B?"

[1711] Input: User actions based on presented information.

[1712] Action: Choice selection operation.

[1713] Output: The user's next action (e.g., send a message).

[1714] (Application example 1)

[1715] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1716] Conventional food delivery applications make recommendations based solely on user preferences and past ordering history, without adequately collecting and analyzing in-depth user information. As a result, they are unable to provide truly personalized suggestions based on the user's values ​​and daily behavioral patterns, and are unable to fully increase user satisfaction. The objective of this invention is to provide a system that collects in-depth information, such as values, behavioral patterns, interests, and thought patterns, through natural conversations with users, and recommends optimal food delivery options based on this information.

[1717] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1718] In this invention, the server includes a means for a user to input basic information, a means for saving the generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for generating optimal match candidates and proposals based on the extracted user information, and a means for presenting the generated match candidates and proposals to the user, thereby making it possible to propose optimal food delivery options based on the user's in-depth information.

[1719] "Basic information" is data entered by the user, such as name, age, gender, allergy information, and favorite dishes.

[1720] The "generated conversation data" is text data obtained through natural conversation with the user.

[1721] "Storage means" refers to the technology used to store conversation data in a database or server.

[1722] The "means of analysis" refers to natural language processing engines and algorithms that extract values, behavioral patterns, interests, and thought patterns from stored conversation data.

[1723] "User information" refers to data such as the user's values, behavioral patterns, interests, and thought patterns obtained through analysis.

[1724] "Matching suggestions" are suitable food delivery options and other recommendations based on the user's in-depth information.

[1725] The "presenting means" refers to a technique for displaying the generated match candidates and suggestions on the user's device.

[1726] A "generative AI model" is an artificial intelligence technology for generating natural conversations with users.

[1727] "Keywords" are important words and phrases extracted from conversation data.

[1728] "Sentiment information" is information about emotions and evaluations obtained from conversation data.

[1729] "Food delivery options" are meal delivery options recommended based on a user's preferences and behavioral patterns.

[1730] This invention is a personalized recommendation system that utilizes in-depth user information in the food delivery field. The system collects information such as values, behavioral patterns, interests, and thought patterns through natural conversation with the user, and provides optimal food delivery options based on this information.

[1731] System configuration

[1732] 1. User Device:

[1733] Users access the system using a smartphone, which has an application installed and an interface for users to enter basic information.

[1734] 2. Server:

[1735] The server is a platform for processing data sent from user devices, and is equipped with a database, a natural language processing engine, a generative AI model, and a matching algorithm.

[1736] Program processing

[1737] 1. User registration and initial setup:

[1738] Users download and launch the app and enter basic information such as their name, age, gender, allergies, and favorite dishes. This data is sent from the device to a server and stored in a database.

[1739] 2. Natural conversation starters:

[1740] The server runs a generative AI model (e.g., GPT-4) and sends prompts to the user, such as, "What kind of food have you liked recently?" The user's response data is sent from the device to the server and stored in a database.

[1741] Examples:

[1742] Example prompt: "What kind of food have you been enjoying lately?"

[1743] 3. Information Collection and Analysis:

[1744] A natural language processing engine (e.g., spaCy) on the server analyzes user response data and extracts and updates values, behavioral patterns, interests, thought patterns, etc. This data is stored in a database as a user profile.

[1745] 4. Present options:

[1746] The server's matching algorithm (e.g., TensorFlow) generates optimal food delivery options based on accumulated user information. The generated options are sent to the device and presented to the user. Specific suggestions are made, such as, "How about having dinner with your family today?"

[1747] Hardware and software used

[1748] Hardware: Smartphone (user device)

[1749] software:

[1750] Firebase (database): Used to store basic user information and conversation data

[1751] GPT-4 (generative AI model): Generates natural conversations with users

[1752] spaCy (natural language processing engine): Used to analyze conversation data

[1753] TensorFlow (Matching Algorithm): Generating Food Delivery Options

[1754] Specific examples

[1755] For example, if a user types into the app, "I've been craving curry lately," the generative AI model might respond, "That's great! What kind of curry do you like?" If the user responds, "I like spicy Indian curry," the server might use this information to suggest the best Indian curry delivery options. An example prompt might be, "What kind of food have you been enjoying lately?"

[1756] As described above, the present invention is a system that collects and analyzes in-depth information about users and provides optimal food delivery options based on that information, thereby increasing user satisfaction.

[1757] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1758] Step 1:

[1759] A user downloads and launches a food delivery application. The user enters basic information (such as name, age, gender, allergy information, and favorite dishes). This data is sent from the device to the server and stored in the Firebase database. The input is the user's basic information, and the output is the user's basic information data sent to the server.

[1760] Step 2:

[1761] The server launches a generative AI model (e.g., GPT-4) and sends the user an initial prompt: "What kind of food have you liked recently?" This prompt encourages the user to start a natural conversation. The input is the prompt, and the output is the prompt displayed on the user's device.

[1762] Step 3:

[1763] The user responds to the prompt by typing "I've been craving curry lately." This response data is sent from the device to the server and stored in the Firebase database. The input is the user's response data, and the output is the response data stored on the server.

[1764] Step 4:

[1765] The server uses a natural language processing engine (e.g., spaCy) to analyze the user's response data. This analysis extracts keywords and sentiment information such as values, behavioral patterns, interests, and thought patterns, and updates the user profile. The input is the user's response data, and the output is the updated user profile data.

[1766] Step 5:

[1767] The server uses a matching algorithm (e.g., TensorFlow) to generate optimal food delivery options based on the updated user profile, which match the user's preferences and behavioral patterns. The input is the updated user profile data, and the output is the food delivery options.

[1768] Step 6:

[1769] The generated food delivery options are sent from the server to the user's device and presented to the user. Specifically, suggestions such as "How about this curry for dinner with your family today?" are displayed to the user. The input is the food delivery options, and the output is the options presented on the user's device.

[1770] Step 7:

[1771] The user reviews the proposed options and places an order if they like them. This order information is again sent to the server and stored in a database. The input is the user's order information, and the output is the order data stored on the server.

[1772] Through the above processing steps, personalized food delivery suggestions based on the user's in-depth information are realized, which can increase user satisfaction.

[1773] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1774] The present invention aims to improve matching accuracy by combining an emotion engine with a system that collects a user's values, behavioral patterns, interests, and thought patterns through natural conversation and provides highly accurate matching based on that information, thereby generating a more accurate profile based on the user's emotions.

[1775] System configuration

[1776] 1. User Device:

[1777] Users access the system using internet-connected devices such as smartphones and personal computers.

[1778] 2. Server:

[1779] The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, emotion engine, and matching algorithm.

[1780] Program processing

[1781] 1. User registration and initial setup:

[1782] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[1783] The terminal sends the input information to the server.

[1784] The server stores the received information in a database.

[1785] 2. Natural conversation starters:

[1786] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[1787] The terminal displays this message to the user.

[1788] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[1789] The terminal sends the user's reply to the server.

[1790] 3. Information Collection and Analysis:

[1791] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[1792] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the analyzed conversation data.

[1793] The server uses an emotion engine to recognize the user's emotion from the conversation data.

[1794] The user profile is updated based on the recognized emotion information and keywords.

[1795] The updated profile information is saved in a database.

[1796] 4. Continue the conversation and refine your profile:

[1797] The server then has the generative AI model generate the next question and send it to the device.

[1798] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[1799] The user replies, "I went to Starbucks."

[1800] The terminal sends the user's reply back to the server.

[1801] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine user profiles.

[1802] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[1803] 5. Generate candidate matches:

[1804] The server uses the analyzed emotion information and the user profile to match other user profiles.

[1805] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[1806] The server lists the best matching candidates and sends them to the device.

[1807] 6. Presentation of results:

[1808] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'loving cafes' and 'relaxing'."

[1809] Users can check the details of the presented matching candidates and select their next action, such as "View more" or "Send a message."

[1810] The terminal communicates the user's actions to the server and takes the next action.

[1811] Specific examples

[1812] For example, when User A registers with the system and begins a conversation with the generative AI model, it becomes clear through daily conversation that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that User A feels "spending time at cafes is very relaxing." Based on this information, the server analyzes that User B also likes outdoor activities and enjoys cafe hopping, and further confirms that there are many similarities in terms of emotions. User A is presented with a matching candidate and notified, "We've found someone who suits you. You share common interests of 'cafe-loving' and 'relaxing,' as well as similar emotions." User A receives this information and, if he or she becomes interested in User B, can send a direct message.

[1813] The present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about users into the analysis, thereby providing highly satisfying encounters that could not be achieved with conventional systems.

[1814] The processing flow will be explained below.

[1815] Step 1:

[1816] A user accesses the system and enters basic information (name, age, gender, hobbies, etc.).

[1817] The terminal sends the input information to the server.

[1818] The server stores the received information in a database.

[1819] Step 2:

[1820] The server launches the generative AI model and sends the initial message to the device: "How was your day?"

[1821] The terminal displays this message to the user.

[1822] The user replies to the generative AI model, "Today I went to a cafe with a friend to relax."

[1823] The terminal sends the user's reply to the server.

[1824] Step 3:

[1825] The server analyzes the received conversation data using a natural language processing (NLP) engine.

[1826] Keywords such as "friends," "cafe," and "relaxation" and sentiment information are extracted from the conversation data.

[1827] The server uses an emotion engine to recognize the user's emotion from the conversation data.

[1828] The server updates the user profile based on the recognized emotion information and keywords.

[1829] The updated profile information is saved in a database.

[1830] Step 4:

[1831] The server then has the generative AI model generate the next question and send it to the device.

[1832] The device displays a question from the generated AI model to the user, such as "Which cafe did you go to?"

[1833] The user replies, "I went to Starbucks."

[1834] The terminal sends the user's reply back to the server.

[1835] Step 5:

[1836] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine user profiles.

[1837] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[1838] Step 6:

[1839] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[1840] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[1841] The server lists the best matching candidates and sends them to the device.

[1842] Step 7:

[1843] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'love cafes' and 'relaxation-oriented'."

[1844] The user reviews the details of the proposed match and selects the next action, such as "Learn more" or "Send a message."

[1845] The terminal communicates the user's actions to the server and takes the next action.

[1846] Examples:

[1847] For example, user A registers with the system and begins a conversation with the generative AI model. Through daily conversations, it becomes clear that user A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that user A finds "spending time at cafes very relaxing." Based on this information, the server analyzes that another user, user B, likes outdoor activities and enjoys cafe hopping, and further confirms that there are many similarities in terms of emotions. The server presents user A with matching candidates and notifies him / her, "We've found someone who suits you. You share common interests of 'cafe-loving' and 'relaxing,' as well as similar emotions." User A receives this information, and if he / she becomes interested in user B, he / she can send a direct message to the other person.

[1848] The present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about users into the analysis, thereby providing highly satisfying encounters that could not be achieved with conventional systems.

[1849] Example 2

[1850] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1851] Conventional matching systems have difficulty creating profiles that consider not only basic user information but also deeper values ​​and emotions. This results in low matching accuracy and fails to sufficiently increase user satisfaction. Furthermore, they are unable to reflect the continually changing interests and emotions of users, meaning that once a profile is created, it easily becomes outdated.

[1852] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for a user to input basic information, a means for saving generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for analyzing the user's emotional information using a sentiment analysis engine, and a means for causing the generative AI model to generate the next prompt and continuously collect conversation data. This makes it possible to keep a profile containing in-depth information of the user always up-to-date, enabling highly accurate matching that takes emotional information into consideration.

[1853] The "means for users to input basic information" is a function that provides an interface that allows users to input basic information such as name, age, sex, and hobbies.

[1854] The "means for saving generated conversation data" is a function for saving data generated from a conversation with a user in a storage device such as a database.

[1855] "Means of analyzing saved conversation data to extract a user's values, behavioral patterns, interests, and thought patterns" refers to a function that analyzes saved conversation data using natural language processing technology, etc., to extract a user's personal characteristics and patterns.

[1856] The "means for generating optimal matching candidates based on extracted user information" is a function for generating optimal matching candidates with other users using the characteristic information of the user obtained by analysis.

[1857] The "means for presenting generated match candidates to the user" is a function for displaying detailed information about the generated match candidates to the user.

[1858] The "means for analyzing user emotional information using an emotion analysis engine" is a function for analyzing user emotions from conversation data and extracting the emotional information.

[1859] "Means for having the generative AI model generate the next prompt and continuously collect conversation data" is a function that uses the generative AI model to generate the next question or message, and collects data while encouraging the continuation of the conversation with the user.

[1860] This invention relates to a system that collects a user's values, behavioral patterns, interests, and thought patterns through natural conversations and provides highly accurate matching based on the collected information. The system aims to improve matching accuracy by combining an emotion engine to generate a highly accurate profile based on the user's emotions.

[1861] The system consists of the following:

[1862] 1. User Device:

[1863] Users access the system using internet-connected devices such as smartphones and personal computers.

[1864] 2. Server:

[1865] The server is a platform for processing data sent from user devices and is equipped with a database, natural language processing engine, generative AI model, emotion engine, and matching algorithm.

[1866] Specific embodiments of the invention are set out below:

[1867] 1. User registration and initial setup:

[1868] A user accesses the system and enters basic information such as name, age, gender, and hobbies.

[1869] The terminal sends the input information to the server.

[1870] The server stores the received information in a database.

[1871] 2. Natural conversation starters:

[1872] The server launches the generative AI model, generates the initial message "How was your day today?" and sends it to the device.

[1873] The terminal displays this message to the user.

[1874] The user replies, "Today I went to a cafe with a friend to relax."

[1875] The terminal sends this reply to the server.

[1876] 3. Information Collection and Analysis:

[1877] The server analyzes the received conversation data using a natural language processing (NLP) engine, such as Google Natural Language or Amazon Comprehend.

[1878] Keywords such as "friends," "cafe," and "relaxation" and emotional information are extracted from the analyzed data.

[1879] The server uses an emotion engine, such as IBM Watson Tone Analyzer, to recognize the user's emotions from the conversation data.

[1880] The user profile is updated based on the recognized emotion information and keywords.

[1881] The updated profile is saved in the database.

[1882] 4. Continue the conversation and refine your profile:

[1883] The server then has the generative AI model generate the next question, for example, "Which cafe did you go to?", and sends it to the device.

[1884] The terminal displays the generated question to the user.

[1885] The user replies, "I went to Starbucks."

[1886] The terminal sends this reply back to the server.

[1887] The server continuously collects and analyzes conversation data, and uses an emotion engine to refine the user profile. Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep values, behavioral patterns, interests, and thought patterns.

[1888] 5. Generate candidate matches:

[1889] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[1890] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[1891] The server lists the best matching candidates and sends them to the device.

[1892] 6. Presentation of results:

[1893] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'liking cafes' and 'relaxing'."

[1894] Users can review the details of the proposed matches and select their next action, such as "View more" or "Send a message."

[1895] The terminal communicates the user's actions to the server and takes the next action (e.g., prepares to send a message).

[1896] To explain how it works in detail, when User A registers with the system and begins a conversation with the generative AI model, it is discovered through daily conversations that User A likes "outdoor activities" and has the habit of "going to cafes on weekends." Furthermore, by using the emotion engine, it becomes clear that User A feels that "spending time at cafes is very relaxing." Based on this information, the server analyzes that User B is also a person who likes outdoor activities and enjoys cafe hopping. It also confirms that there are many similarities in terms of emotions. For example, the server may notify User A that "We've found someone who suits you. Common interests include a love of cafes and a desire to relax." If User A receives this information and becomes more interested in User B, he or she can send a direct message to the other person.

[1897] Examples of prompts include:

[1898] "How was your day today?"

[1899] "Which cafe did you go to?"

[1900] "What was the most memorable thing that happened today?"

[1901] As described above, the present invention is a system that achieves more accurate matching by incorporating emotional information in addition to in-depth information about the user into the analysis.

[1902] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1903] Step 1: User registration and initial setup

[1904] Specific behavior:

[1905] Users access the system using a smartphone or computer.

[1906] The server displays a form for the user to enter basic information such as name, age, sex, and hobbies.

[1907] The user fills in the required information in the form and clicks the "Submit" button.

[1908] Input: Basic information entered by the user (name, age, gender, hobbies, etc.)

[1909] Output: The input information is sent to the server and stored in a database.

[1910] Data processing: The server checks the format of the information it receives and converts it into the required format before storing it in the database.

[1911] Step 2: Start a natural conversation

[1912] Specific behavior:

[1913] The server launches the generative AI model and generates the first message: "How was your day?"

[1914] The server sends this message to the terminal, which displays the message to the user.

[1915] The user replies, "Today I went to a cafe with a friend to relax."

[1916] The terminal sends the user's reply to the server.

[1917] Input: Basic information about the user, the initial message generated by the generative AI model

[1918] Output: The user's reply is sent to the server.

[1919] Data processing: The generative AI model generates the initial message and sends the user's response to the server.

[1920] Step 3: Collect and analyze information

[1921] Specific behavior:

[1922] The server analyzes the received conversation data using a natural language processing (NLP) engine, such as Google Natural Language.

[1923] The NLP engine extracts keywords such as "friends," "cafe," and "relaxation" as well as emotional information from the conversation data.

[1924] The server uses an emotion engine, such as IBM Watson Tone Analyzer, to recognize the user's emotions from the conversation data.

[1925] Update user profiles based on keywords and recognized emotion information.

[1926] The server saves the updated profile in the database.

[1927] Input: User conversation data

[1928] Output: Extracted keywords and sentiment information, updated user profile

[1929] Data processing: The NLP engine analyzes the conversation data and extracts keywords and emotional information. The emotional engine recognizes the emotional information and updates the user profile accordingly.

[1930] Step 4: Continue the conversation and refine your profile

[1931] Specific behavior:

[1932] The server then asks the generative AI model to generate the next question, for example, "Which cafe did you go to?"

[1933] The server sends the generated question to the terminal, which displays it to the user.

[1934] The user replies, "I went to Starbucks."

[1935] The terminal sends this reply to the server.

[1936] The server then analyzes the received data using an NLP engine and also uses an emotion engine to further refine the user profile.

[1937] Data accumulated over a certain period (usually one week) is comprehensively analyzed to clarify the user's deep-seated values, behavioral patterns, interests, and thought patterns.

[1938] Input: Previous conversation data and the next prompt to generate

[1939] Output: New answers from the user and an updated profile

[1940] Data processing: Generative AI models generate new questions and continue the conversation based on them, analyzing incoming data to refine profiles.

[1941] Step 5: Generate candidate matches

[1942] Specific behavior:

[1943] The server uses the analyzed emotion information and the user profile to match it with other user profiles.

[1944] It extracts matching candidates with common values ​​and interests, and generates optimal candidates by taking emotional information into consideration.

[1945] The server lists the best matching candidates and sends this information to the device.

[1946] Input: Parsed user profile and emotional information

[1947] Output: A list of potential matches

[1948] Data processing: Matching user profiles with other user profiles to extract the best possible matches.

[1949] Step 6: Presenting the results

[1950] Specific behavior:

[1951] The device will then display detailed information about the potential match to the user, such as, "We've found someone who's perfect for you. We share common interests of 'liking cafes' and 'relaxing'."

[1952] The user checks the details of the presented match candidates and selects the next action, such as "View more" or "Send a message."

[1953] The terminal communicates the user's actions to the server and takes the next action.

[1954] Input: A list of potential matches and user actions

[1955] Output: Details of the match candidate and the user's selected next action

[1956] Data processing: Displaying information about potential matches to the user and communicating the user's selected action to the server.

[1957] (Application example 2)

[1958] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1959] Conventional ad delivery systems often present uniform ads because they are unable to fully understand users' interests. This results in problems such as users not being presented with ads that are beneficial to them, resulting in reduced advertising effectiveness. Furthermore, because ad delivery does not take into account user emotions, the user experience does not improve and the accuracy of ad targeting also decreases.

[1960] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1961] In this invention, the server includes a means for a user to input basic information, a means for saving the generated conversation data, a means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns, a means for selecting an optimal advertisement based on the extracted user information, and a means for presenting the selected advertisement to the user, thereby enabling highly accurate advertisement delivery based on the user's individual interests and emotions.

[1962] A "user" is an individual who uses the system.

[1963] "Basic information" refers to information such as name, age, sex, and hobbies that the user inputs during initial setup.

[1964] "Conversation data" is text data generated from natural interactions with the user.

[1965] "Means of storage" refers to the process of recording the generated conversation data in storage such as a database.

[1966] The "analysis means" is a process of analyzing saved conversation data using a natural language processing engine or the like to extract the user's values, behavioral patterns, interests, and thought patterns.

[1967] "Extracted user information" refers to data such as the user's values, behavioral patterns, interests, and thought patterns obtained through the analysis of conversation data.

[1968] The "means for selecting the most suitable advertisement" is an algorithm that automatically selects the advertisement that is most relevant to the user based on the extracted user information.

[1969] "Selected Advertisement" refers to the most suitable advertisement based on user information.

[1970] "Presenting means" refers to the process of displaying the selected advertisement on the screen of the device used by the user.

[1971] A "generative AI model" is an artificial intelligence model used to engage in natural conversations with users.

[1972] "Emotion information" is data relating to the user's emotions extracted from conversation data.

[1973] A "user profile" is a set of detailed information that includes a user's values, behavioral patterns, interests, thought patterns, emotional information, and so on.

[1974] "Advertisement" is information for advertising products or services to users.

[1975] An "advertising distribution system" is a system that uses user information to select the most suitable advertisement and present it to the user.

[1976] MODE FOR CARRYING OUT THE INVENTION

[1977] This invention is a system for optimizing advertisements based on a user's values, behavioral patterns, interests, thought patterns, and emotional information. This system operates when a user accesses it via the Internet using a device such as a smartphone or smart glasses.

[1978] Hardware and software used

[1979] Hardware:

[1980] Smartphone

[1981] Smart Glasses

[1982] head-mounted display

[1983] software:

[1984] Python

[1985] SQLite

[1986] TextBlob

[1987] Transformers pipeline(Hugging Face)

[1988] System Configuration

[1989] 1. User registration and initial setup:

[1990] Users access the system and enter basic information such as their name, age, gender, hobbies, etc. The terminal sends the entered information to the server, which then stores the received information in a database.

[1991] 2. Natural conversation starters:

[1992] The server uses the generative AI model to initiate a natural conversation with the user. For example, it might send an initial message like, "How was your day today?", to which the user replies, "Today I went to a cafe with a friend to relax." The device then sends this reply to the server.

[1993] 3. Information Collection and Analysis:

[1994] The server analyzes the received conversation data and uses an NLP engine (TextBlob) to extract keywords and sentiment information. It also performs sentiment analysis using a Transformers pipeline. Based on this information, it updates the user profile and saves it in the database.

[1995] 4. Ad optimization:

[1996] The server selects the most suitable advertisements based on the updated user profile. The selection algorithm takes into account the user's values, behavioral patterns, interests, thought patterns, and emotional information.

[1997] 5. Advertising Presentation:

[1998] The server sends the selected advertisement to the device, which then presents it to the user, allowing the user to receive advertisements that match their interests and emotions.

[1999] Specific examples

[2000] For example, if a user replies, "Today I went to a cafe with friends and relaxed," the server extracts the keywords "friends," "cafe," and "relaxation," and recognizes the emotion as "positive." Based on this information, it presents the user with advertisements related to cafes and products related to relaxation.

[2001] Prompt Sentence Examples

[2002] A generative AI model that allows a system to generate questions for a user could use prompts like this:

[2003] "You are a model for an ad selection engine. Please identify your interests from the following conversation and select the most suitable ad. Conversation: Today I went to a cafe with a friend to relax."

[2004] This invention makes it possible to realize highly accurate advertisement distribution based on the individual interests and emotions of users.

[2005] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2006] Step 1: User registration and initial setup

[2007] A user accesses the system and enters basic information such as name, age, gender, hobbies, etc. The terminal sends the entered information to the server, which then stores the received information in a database.

[2008] Input: Basic information entered by the user (name, age, gender, hobbies)

[2009] Output: Basic information is saved to the database

[2010] Step 2: Start a natural conversation

[2011] The server uses the generative AI model to initiate a natural conversation with the user. For example, it might send an initial message like, "How was your day today?" The user might reply, "Today I went to a cafe with a friend to relax." The device then sends this reply to the server.

[2012] Input: A conversational prompt sent by the server to the user ("How was your day?")

[2013] Output: User response ("Today I went to a cafe with a friend to relax.")

[2014] Step 3: Collect and analyze information

[2015] The server analyzes the received conversation data and uses an NLP engine (TextBlob) to extract keywords and sentiment information. It also performs sentiment analysis using a Transformers pipeline. Based on this information, it updates the user profile and saves it in the database.

[2016] Input: User conversation data ("Today I went to a cafe with a friend to relax.")

[2017] Output: Extracted keywords ("friends", "cafe", "relax") and sentiment information (positive)

[2018] Step 4: Optimize your ads

[2019] The server selects the most suitable advertisements based on the updated user profile. The selection algorithm takes into account the user's values, behavioral patterns, interests, thought patterns, and emotional information.

[2020] Input: Updated user profile (specific values, behavioral patterns, interests, thought patterns, emotional information)

[2021] Output: Selection of the best ad

[2022] Step 5: Present your ad

[2023] The server sends the selected advertisement to the device, which then presents it to the user, allowing the user to receive advertisements that match their interests and emotions.

[2024] Input: Best ad selection results

[2025] Output: The ad is displayed on the user's device

[2026] Through the above steps, highly accurate advertisement delivery based on the individual interests and emotions of each user is realized.

[2027] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2028] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2029] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2030] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2031] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2032] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2033] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2034] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2035] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2036] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2037] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2038] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2039] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2040] 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.

[2041] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2042] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2043] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2044] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2045] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2046] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2047] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2048] The following is further disclosed regarding the above embodiment.

[2049] (Claim 1)

[2050] a means for a user to input basic information;

[2051] A means for storing the generated conversation data;

[2052] A means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns;

[2053] A means for generating optimal matching candidates based on the extracted user information;

[2054] means for presenting the generated matching candidates to a user;

[2055] A system including:

[2056] (Claim 2)

[2057] 10. The system of claim 1, wherein the system uses a generative AI model to engage in natural conversation with a user.

[2058] (Claim 3)

[2059] 10. The system of claim 1, further comprising means for updating a user profile with keywords and sentiment information extracted from the conversation data.

[2060] "Example 1"

[2061] (Claim 1)

[2062] a means for a user to input basic information;

[2063] A means for storing the generated conversation data;

[2064] A means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns;

[2065] A means for generating optimal matching candidates based on the extracted user information;

[2066] means for presenting the generated matching candidates to a user;

[2067] a means for initiating a conversation with a user using the generative AI model and receiving user input;

[2068] A means for analyzing the received conversation data using a natural language processing engine and updating a user profile;

[2069] A system including:

[2070] (Claim 2)

[2071] 10. The system of claim 1, wherein the system uses a generative AI model to engage in natural conversation with the user and generate dialogue based on prompt sentences.

[2072] (Claim 3)

[2073] 10. The system of claim 1, further comprising means for updating a user profile and generating match candidates using keywords and sentiment information extracted from the conversation data.

[2074] "Application Example 1"

[2075] (Claim 1)

[2076] a means for a user to input basic information;

[2077] A means for storing the generated conversation data;

[2078] A means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns;

[2079] means for generating optimal matching candidates and suggestions based on the extracted user information;

[2080] means for presenting the generated match candidates and suggestions to a user;

[2081] A system including:

[2082] (Claim 2)

[2083] 10. The system of claim 1, wherein the system uses a generative AI model to engage in natural conversation with a user.

[2084] (Claim 3)

[2085] 10. The system of claim 1, further comprising means for updating a user profile and suggesting optimal food delivery options using keywords and sentiment information extracted from the conversation data.

[2086] "Example 2: Combining Emotion Engines"

[2087] (Claim 1)

[2088] a means for a user to input basic information;

[2089] A means for storing the generated conversation data;

[2090] A means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns;

[2091] A means for generating optimal matching candidates based on the extracted user information;

[2092] means for presenting the generated matching candidates to a user;

[2093] A means for analyzing user emotional information using a sentiment analysis engine;

[2094] means for updating a user profile to include the analyzed emotion information;

[2095] A means to generate the next prompt from the generative AI model and continuously collect conversational data; and

[2096] A system including:

[2097] (Claim 2)

[2098] 10. The system of claim 1, wherein the generative AI model is used to engage in natural conversation with the user.

[2099] (Claim 3)

[2100] 10. The system of claim 1, further comprising means for updating a user profile using keywords and sentiment information extracted from the conversation data.

[2101] "Application example 2 when combining emotion engines"

[2102] (Claim 1)

[2103] a means for a user to input basic information;

[2104] A means for storing the generated conversation data;

[2105] A means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns;

[2106] A means for selecting an optimal advertisement based on the extracted user information;

[2107] means for presenting the selected advertisement to the user;

[2108] A system including:

[2109] (Claim 2)

[2110] 10. The system of claim 1, comprising means for using the generative AI model to engage in natural conversation with a user.

[2111] (Claim 3)

[2112] 10. The system of claim 1, further comprising means for updating a user profile using keywords and sentiment information extracted from the conversation data and optimizing advertisements based on the profile. [Explanation of symbols]

[2113] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input basic information; A means for storing the generated conversation data; A means for analyzing the saved conversation data to extract the user's values, behavioral patterns, interests, and thought patterns; A means for generating optimal matching candidates based on the extracted user information; means for presenting the generated matching candidates to a user; A system including:

2. The system of claim 1 , wherein the system uses a generative AI model to engage in natural conversation with the user.

3. 10. The system of claim 1, further comprising means for updating a user profile with keywords and sentiment information extracted from the conversation data.

Images