System

Abstract

A system is provided.SOLUTION: A system includes means for using a generative AI model in which participants answer simple questions in advance and generate self-introduction profiles on the basis of the answers in a networking event, means for collecting and analyzing the generated self-introduction profiles and automatically generating a group on the basis of a purpose or an interest of each participant, and means for tracking location information and conversation content of the participants in real time during the event and optimizing arrangement or progress of the event.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] People who attend networking events often face challenges in meeting the people they want to reach and making valuable connections within a limited time frame. This challenge often results in event participants not achieving the results they expected. It's also difficult to effectively introduce yourself in an unfamiliar environment, and limited start times often lead to conversations stalling. Furthermore, dynamic conversations and group placements during the event can be poorly coordinated, which can detract from the overall effectiveness of the event. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides a system that includes: a means for using a generative AI model to generate a self-introduction profile based on the answers of participants to simple questions in advance at a networking event, a means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose and interests of each participant, and a means for tracking the location information and conversation content of participants in real time during the event to optimize the layout and progress of the event.

[0006] Specifically, participants fill out a questionnaire in the system, and the generative AI model creates a self-introduction profile based on their responses. This profile is then collected and analyzed by the server, and optimal groups are automatically generated based on each participant's goals and interests. During the event, participants' locations and conversations are tracked in real time, and the progress of the event is dynamically adjusted to achieve more effective networking.

[0007] This allows participants to efficiently access the demographic they want to reach within a limited time frame and ensures beneficial connections. The generated profile also eliminates the need for self-introductions, allowing for smooth conversations even when meeting for the first time. Furthermore, the dynamic adjustment function during the event promotes event activity and improves overall participant satisfaction.

[0008] A "networking event" is an event where participants gather physically or online for business or personal purposes to exchange information and network.

[0009] "Participant" means an individual or representative of a business entity who participates in a networking event and engages in activities consistent with the purpose of the event.

[0010] A "self-introduction profile" is a document that lists the participant's basic information, occupation, interests, and networking goals, and is a tool to promote interaction with other participants.

[0011] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to automatically generate specific information (in this case, a self-introduction profile) from input data.

[0012] The "group generation means" is a technical means for automatically dividing participants into optimal groups based on their self-introduction profiles and interests.

[0013] "Location information" is data that indicates the physical location of participants and is used to understand their movements and placement within the event venue.

[0014] "Conversation content" refers to the comments and topics exchanged between participants during the event, and is data that is analyzed to improve the progress of the event and the quality of networking.

[0015] "Tracking" is the act of following the movements of a specific object (in this case, a participant) in real time and collecting and analyzing that data.

[0016] "Real-time" refers to the immediate processing and reflection of ongoing events and situations. [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] Overall system overview

[0039] This invention is a system for streamlining networking events. Participants can generate self-introduction profiles by simply answering a few simple questions in advance, and dynamically create and coordinate optimal groups during the event. The system is divided into three main phases: a pre-preparation phase, an automatic group creation phase, and an event-in-progress phase.

[0040] Preparation Phase

[0041] User Action:

[0042] To participate in a networking event, users log in to the system and apply for participation. After logging in, they answer a questionnaire displayed by the system, which includes information about their job, their skills, interests, and the purpose of networking.

[0043] Device behavior:

[0044] It receives user input data and sends it to the server.

[0045] Server behavior:

[0046] The server runs a generative AI model based on the input data to automatically generate a self-introduction profile. The generated profile information is sent to the user's device, where the user can review the content and make any necessary edits.

[0047] Automatic group creation phase

[0048] Server behavior:

[0049] Self-introduction profile information for all participants is stored in a database. The stored profile information is analyzed using natural language processing (NLP) technology to identify participants' interests and goals. Based on the analysis results, an optimal matching algorithm is used to group participants by goal. The generated group information is sent to each user's device on the day of the event.

[0050] User Action:

[0051] Check your session schedule on your device before the event.

[0052] Event Phase

[0053] User Action:

[0054] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0055] Device behavior:

[0056] It tracks users' location information in real time, collects data based on their conversations and interests, and sends it to a server.

[0057] Server behavior:

[0058] The system analyzes the collected location and conversation data to understand the current group arrangement and conversation progress. It detects when a particular group is inactive or has low topic agreement, and generates optimal new networking suggestions. These suggestions are sent to the user's device, notifying them of new group and table arrangements.

[0059] Specific examples

[0060] 1. Specific examples of the preparation phase

[0061] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." When the device sends the data to the server, the server uses a generative AI model to generate a self-introduction profile for the user, describing him as an "IT engineer with a strong marketing background," and provides it to the user.

[0062] 2. Example of the automatic group creation phase

[0063] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[0064] 3. Specific examples of event phases

[0065] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[0066] As described above, this system maximizes the networking effect of participants throughout the entire event process, contributing to the success of the event.

[0067] The processing flow will be explained below.

[0068] Preparation Phase

[0069] Step 1:

[0070] User:

[0071] Log in to the event system and register.

[0072] Step 2:

[0073] server:

[0074] Users are presented with a survey that includes questions about the participant's job, skills, interests, and networking goals.

[0075] Step 3:

[0076] User:

[0077] Answer the survey and submit your answers.

[0078] Step 4:

[0079] Device:

[0080] The submitted questionnaire responses are relayed to the server.

[0081] Step 5:

[0082] server:

[0083] A generative AI model is run based on the received response data to generate a self-introduction profile.

[0084] Step 6:

[0085] server:

[0086] Send the generated profile to the device.

[0087] Step 7:

[0088] User:

[0089] Check your profile and make any necessary changes.

[0090] Automatic group creation phase

[0091] Step 8:

[0092] server:

[0093] All participants' self-introduction profiles are stored in a database.

[0094] Step 9:

[0095] server:

[0096] The stored profile information is analyzed using natural language processing (NLP) technology to identify each participant's interests and networking goals.

[0097] Step 10:

[0098] server:

[0099] Based on the analysis results, participants are grouped by purpose using an optimal matching algorithm.

[0100] Step 11:

[0101] server:

[0102] The grouped information and a session schedule are generated and transmitted to each user's terminal.

[0103] Event Phase

[0104] Step 12:

[0105] User:

[0106] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0107] Step 13:

[0108] Device:

[0109] It tracks users' locations in real time and collects data based on their conversations and interests.

[0110] Step 14:

[0111] Device:

[0112] The collected data is sent to the server.

[0113] Step 15:

[0114] server:

[0115] The collected location information and conversation data is analyzed to understand the current group arrangement and conversation progress.

[0116] Step 16:

[0117] server:

[0118] It detects when certain groups are inactive or have low topical alignment and generates new networking suggestions.

[0119] Step 17:

[0120] server:

[0121] Send the new proposal to the device.

[0122] Step 18:

[0123] Device:

[0124] Notify users of new group and table placements.

[0125] Step 19:

[0126] User:

[0127] Follow the proposed new arrangement and move to your designated new table or group.

[0128] This series of steps allows for efficient and beneficial networking even in a limited amount of time.

[0129] Example 1

[0130] 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."

[0131] To enable participants to interact more effectively at networking events, it is important to create detailed profiles in advance and meet suitable people during the event. However, with conventional systems, creating self-introduction profiles and grouping participants is often done manually, which is time-consuming and labor-intensive and may not result in optimal matching. It is also difficult to grasp and adjust real-time interaction situations during the event, making it difficult for participants to network effectively.

[0132] 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.

[0133] In this invention, the server includes: means for using a generative AI model in which participants answer simple questions in advance and generate a self-introduction profile based on the answers; means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose and interests of each participant; means for tracking participants' location information and conversation content in real time during the event to optimize the progress of the event; and means for monitoring specific activity levels within groups and generating and notifying new networking suggestions in the event of inactive groups or low topic matches. This allows participants to easily create effective self-introduction profiles and continue to meet suitable people even during the event.

[0134] A "generative AI model" is a program that uses artificial intelligence technology to automatically generate a self-introduction profile based on participants' responses.

[0135] "Natural language processing technology" is a field of computer science that deals with understanding and processing human language, and is a technology used to analyze and generate text data.

[0136] A "self-introduction profile" is a digital document that organizes personal information about participants, including their job, skills, interests, concerns, and networking goals.

[0137] The "group generation method" is an algorithm that automatically creates appropriate groups based on participants' self-introduction profiles and interests according to the purpose of networking.

[0138] "Location Information" means data obtained using GPS or other technologies that indicates where a Participant is located within an Event.

[0139] "Conversation content" is data including topics and keywords of verbal communication exchanged between participants during the event.

[0140] "Real-time tracking" refers to a system that instantly acquires participants' location information and conversation content while the event is in progress, sends it to a server, and dynamically analyzes it.

[0141] "Networking Suggestions" are notifications from the system that recommend new suitable networking partners and groups based on participants' current group placement and conversation content.

[0142] The "means for monitoring specific activity levels within a group" refers to an algorithm that monitors the activity status and conversation progress of participants within a group and evaluates the activity level of the group.

[0143] This invention is a system for streamlining networking events, allowing participants to generate self-introduction profiles by answering simple questions in advance, and dynamically creating and adjusting optimal groups during the event.

[0144] Overall system overview

[0145] The system combines generative AI models and natural language processing technology to automatically generate participant profiles and dynamically create and coordinate groups during the event. The system is basically divided into the following phases: pre-preparation phase, automatic group creation phase, and in-event phase.

[0146] Preparation Phase

[0147] User Actions

[0148] To participate in an event, users log in to the system and apply for participation. After logging in, they answer a questionnaire that appears. This questionnaire includes questions about their job, their skills, interests, and networking goals.

[0149] Device behavior

[0150] The terminal receives the user's input data and sends it to the server.

[0151] Server Operation

[0152] The server uses a generative AI model (e.g., GPT-4 (registered trademark)) to generate a self-introduction profile from the user's input data. The generated profile information is sent to the device, where the user can review the content and make any necessary corrections.

[0153] Automatic group creation phase

[0154] Server Operation

[0155] The server stores the self-introduction profile information of all participants in a database (e.g., MySQL (registered trademark)). It then analyzes the data using natural language processing (NLP) technology (e.g., SpaCy) to identify participants' interests and goals. Based on the identified information, it uses an optimal matching algorithm (e.g., K-means clustering) to group participants by purpose. The generated group information is sent to each user's device.

[0156] Event Phase

[0157] User Actions

[0158] On the day of the event, users check the session schedule on their device and head to their designated group or table.

[0159] Device behavior

[0160] The device tracks the user's location in real time using GPS, collects conversation content through a microphone, and sends the data to a server.

[0161] Server Operation

[0162] The server analyzes the collected data to understand the group placement and conversation progress, and if a particular group is inactive or has low topic agreement, it generates optimal new networking proposals and sends them to the user's device.

[0163] Specific examples

[0164] 1. Specific examples of the preparation phase

[0165] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." When the device sends the data to the server, the server uses a generative AI model (e.g., "GPT-4") to generate a self-introduction profile for the user, describing the user as an "IT engineer with expertise in marketing," and provides it to the user.

[0166] 2. Example of the automatic group creation phase

[0167] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[0168] 3. Specific examples of event phases

[0169] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[0170] Prompt Sentence Examples

[0171] "My area of ​​interest is marketing and I currently work as an IT engineer. Please create a profile to introduce myself."

[0172] Through these phases, the present invention can maximize the networking effect of participants and improve the outcome of the event.

[0173] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0174] Step 1: Log in and complete the survey

[0175] User Actions

[0176] Users log in to the system and answer a questionnaire. After entering their ID and password on the login page and being authenticated, the questionnaire screen appears. Users answer questions about their work, skills, interests, networking goals, etc.

[0177] Device behavior

[0178] The terminal receives the user's input data from the input form, performs error checks (e.g., checking required fields, checking data format), and then sends the data to the server in JSON format.

[0179] Input: Data entered by the user into the survey form (e.g., job, skills, interests)

[0180] Output: Data after error checking is sent to the server

[0181] Step 2: Create your profile

[0182] Server Operation

[0183] The server uses a generative AI model (e.g., GPT-4) to generate a self-introduction profile from the received input data. The generated profile reflects the user's interests and skills. Natural language processing technology is used to generate the profile.

[0184] Input: User survey data sent from the device

[0185] Data processing: AI models analyze data, perform natural language processing, and generate profiles

[0186] Output: Generated self-introduction profile

[0187] Device behavior

[0188] The generated profile information is sent to the user's device, which displays the profile and prompts the user to confirm and make any necessary corrections.

[0189] Input: Self-introduction profile sent from the server

[0190] Output: The profile screen that the user sees

[0191] Step 3: Check and modify your profile

[0192] User Actions

[0193] The user checks their self-introduction profile and makes any necessary corrections. The corrections are then sent back to the server.

[0194] Input: Initially generated profile

[0195] Output: Corrected profile data

[0196] Device behavior

[0197] The terminal receives the user's modifications and sends them back to the server.

[0198] Input: Corrected profile data

[0199] Output: Modifications sent to the server

[0200] Step 4: Store profile information in a database

[0201] Server Operation

[0202] The server stores the modified profile in a database using a fast relational database (e.g., MySQL).

[0203] Input: Corrected profile data

[0204] Data processing: Insert / update data into database based on data format

[0205] Output: Profile information stored in the database

[0206] Step 5: Analyze and group profiles

[0207] Server Operation

[0208] The server analyzes the stored profile information using natural language processing (NLP) techniques (e.g., SpaCy) to identify participants' interests and goals, and then groups them based on the identified information using an optimal matching algorithm (e.g., K-means clustering).

[0209] Input: Profile information stored in the database

[0210] Data processing: Natural language processing technology is used to identify interests and purposes, and matching algorithms are used to group them.

[0211] Output: Group information

[0212] Step 6: Generate and distribute session schedules

[0213] Server Operation

[0214] The server generates a session schedule for the event based on the generated group information, and transmits the session schedule to each user's device.

[0215] Input: Group information

[0216] Data processing: Create a session schedule using a schedule generation algorithm

[0217] Output: Generated session schedule

[0218] Device behavior

[0219] The terminal receives the session schedule sent from the server and displays it to the user.

[0220] Input: Session schedule sent from the server

[0221] Output: The schedule screen displayed to the user

[0222] Step 7: Collect location and conversation data during the event

[0223] Device behavior

[0224] The device tracks the user's location in real time using GPS and collects conversations through a microphone, which is then periodically sent to a server.

[0225] Input: User location and conversation data

[0226] Output: Collected data is sent to the server

[0227] Step 8: Data analysis and networking proposals

[0228] Server Operation

[0229] The server analyzes the collected location information and conversation data to evaluate the activity level of the group and the degree of topic agreement. If the group is inactive or the degree of topic agreement is low, it generates new networking suggestions and notifies the user's device.

[0230] Input: Location and conversation data

[0231] Data processing: Analyze the data using an analytical algorithm to evaluate activity and consistency

[0232] Output: Networking suggestions are sent to the user's device.

[0233] Step 9: Implementing a Networking Proposal

[0234] User Actions

[0235] Users will move to new groups and tables according to new networking suggestions notified to their devices, resulting in more effective networking.

[0236] Input: Networking suggestions from the server

[0237] Output: Move to new group or table

[0238] This step allows the system to maximize the networking effect of participants throughout the event, contributing to the success of the event.

[0239] (Application example 1)

[0240] 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."

[0241] In conventional networking events, it is difficult to efficiently match participants based on their goals and interests. Furthermore, while real-time optimization of participant placement and progress, as well as dynamic group adjustment, is required during the event, no method exists to achieve this. The present invention aims to solve these problems and maximize the effectiveness of networking events.

[0242] 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.

[0243] In this invention, the server includes a means for using a generative AI model that generates a self-introduction profile based on participants' answers to simple questions in advance, a means for collecting and analyzing the self-introduction profiles generated by the generative AI model and automatically generating groups based on the goals and interests of each participant, a means for tracking participants' location information and conversation content in real time during the event and optimizing and dynamically adjusting the placement and progress of the event, and a means for participants to participate in the virtual networking event using smartphones, smart glasses, or head-mounted displays, thereby maximizing the effectiveness of the networking event and enabling participants to be matched with each other and their placement to be adjusted in real time.

[0244] A "networking event" is an event where participants gather to exchange information and explore business opportunities.

[0245] "Quick Questions" are a set of short, easy-to-answer questions used to understand participants' basic information, interests, skills, and goals.

[0246] A "self-introduction profile" is electronic data that is generated based on information provided by participants in advance and comprehensively indicates a person's characteristics, interests, skills, goals, etc.

[0247] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to make predictions or generate results from input information.

[0248] A "means" is a method or process used to achieve a particular function or purpose.

[0249] "Collection" is the act of gathering data or information in one place.

[0250] "Analysis" is the process of examining collected data and information in detail to derive specific patterns and meanings.

[0251] "Purpose" refers to the specific reason participants are attending the networking event or what they hope to achieve.

[0252] "Interests" are topics or themes that participants have a personal interest in.

[0253] "Automatic group generation" refers to using artificial intelligence techniques to categorize participants into appropriate groups without manual intervention.

[0254] "Location information" is geographical data that indicates where a participant is currently located.

[0255] "Conversation content" refers to the words and topics exchanged between participants during the event.

[0256] "Real-time tracking" refers to the instantaneous monitoring and recording of ongoing situations.

[0257] "Optimizing progress" means adjusting the flow of events and plans to proceed most efficiently.

[0258] "Dynamic adjustment" means changing the settings and plans as appropriate depending on the event situation and the status of the participants.

[0259] A "virtual networking event" is an event held in an online environment for the purpose of networking.

[0260] A "smartphone" is a highly functional mobile phone that can connect to the Internet and run applications.

[0261] "Smart glasses" are glasses-type electronic devices with a built-in display that displays information.

[0262] A "head-mounted display" is a device that displays images by being worn on the head.

[0263] Overall system overview

[0264] The present invention is a system for streamlining networking events, allowing participants to create self-introduction profiles by simply answering simple questions in advance, and dynamically creating and adjusting optimal groups during the event, thereby maximizing the networking effect of participants throughout the entire event process.

[0265] System Configuration

[0266] The system is divided into three main phases:

[0267] 1. Preparation Phase

[0268] 2. Automatic group creation phase

[0269] 3. Event Phase

[0270] Preparation Phase

[0271] User Action:

[0272] To participate in a networking event, users log in to the system and apply for participation. After logging in, they answer a questionnaire displayed by the system, which includes information about their job, their skills, interests, and the purpose of networking.

[0273] Device behavior:

[0274] It receives user input data and sends it to the server.

[0275] Server behavior:

[0276] The server runs a generative AI model based on the input data to automatically generate a self-introduction profile. The generated profile information is sent to the user's device, where the user can review the content and make any necessary edits.

[0277] Automatic group creation phase

[0278] Server behavior:

[0279] Self-introduction profile information for all participants is stored in a database. The stored profile information is analyzed using natural language processing (NLP) technology to identify participants' interests and goals. Based on the analysis results, an optimal matching algorithm is used to group participants by goal. The generated group information is sent to each user's device on the day of the event.

[0280] User Action:

[0281] Check your session schedule on your device before the event.

[0282] Event Phase

[0283] User Action:

[0284] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0285] Device behavior:

[0286] It tracks users' location information in real time, collects data based on their conversations and interests, and sends it to a server.

[0287] Server behavior:

[0288] The system analyzes the collected location and conversation data to understand the current group arrangement and conversation progress. It detects when a particular group is inactive or has low topic agreement, and generates optimal new networking suggestions. These suggestions are sent to the user's device, notifying them of new group and table arrangements.

[0289] Hardware and software used

[0290] Hardware:

[0291] Smartphones, smart glasses, head-mounted displays

[0292] software:

[0293] Python, OpenAI (registered trademark) API, Geopy

[0294] Specific examples

[0295] 1. Examples of the preparatory phase:

[0296] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." The server uses a generative AI model to generate a self-introduction profile for the user, describing him as an "IT engineer with a strong marketing background," and provides it to the user.

[0297] 2. Example of automatic group creation phase:

[0298] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[0299] 3. Examples of event phases:

[0300] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[0301] Examples of prompt statements

[0302] text

[0303] User information: Interested in marketing, working as an IT engineer

[0304] Use this information to create your profile.

[0305] The above is a specific embodiment of the present invention. This system maximizes the effectiveness of networking events, enabling participants to be matched and allocated in real time.

[0306] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0307] Step 1:

[0308] To participate in an event, users log in to the system and answer a questionnaire. The user's input data includes information about their job, skills, interests, and networking goals. This input data is sent from the terminal to the server.

[0309] Step 2:

[0310] The server runs a generative AI model based on the received input data to generate a self-introduction profile. The server then sends the generated profile to the user's device, allowing the user to review the content and make any necessary corrections. Input: Survey response data. Output: Self-introduction profile.

[0311] Step 3:

[0312] The server stores the self-introduction profile information of all participants in a database. The server analyzes the stored profile information using natural language processing (NLP) techniques to identify participants' interests and goals. Input: Self-introduction profile. Output: Analysis results.

[0313] Step 4:

[0314] The server uses the optimal matching algorithm based on the analysis results to group participants by purpose. The server sends the generated group information to each user's device on the day of the event. Input: Analysis results. Output: Group information.

[0315] Step 5:

[0316] Before the event, users check their own session schedules on their terminals. The terminals display the user's session schedule based on the group information received from the server. Input: Group information. Output: Session schedule.

[0317] Step 6:

[0318] On the day of the event, users check the session schedule on their device and head to their designated group or table. The device tracks the user's location information in real time and sends it to the server. Input: User's location information. Output: Real-time data sent to the server.

[0319] Step 7:

[0320] The server analyzes the collected location information and conversation data to understand the current group arrangement and conversation progress. If a particular group is inactive or has low topic agreement, it detects this and generates optimal new networking proposals. Input: Location information, conversation data. Output: Networking proposals.

[0321] Step 8:

[0322] The server sends a new networking proposal to the user's terminal, notifying them of the new group and table placement. The user moves to the specified new table according to the new proposal and continues networking. Input: Networking proposal. Output: New group placement notification.

[0323] 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.

[0324] Overall system overview

[0325] This invention is a system for promoting efficient matching and interaction among participants at networking events, incorporating an emotion engine to improve accuracy. Participants answer simple questions in advance, and optimal matching is performed based on an automatically generated self-introduction profile. Furthermore, participants' emotional data is tracked in real time during the event, and necessary adjustments are made.

[0326] Preparation Phase

[0327] User Action:

[0328] Users log in to the system and register to attend the event. After registering, they answer a questionnaire displayed by the system, which includes questions about their job, skills, interests, networking goals, and even their emotional state when introducing themselves.

[0329] Device behavior:

[0330] It receives user input data and sends it to the server.

[0331] Server behavior:

[0332] The server runs a generative AI model based on the received response data to automatically generate a self-introduction profile. The generated profile also includes emotional data generated by an emotion engine. This profile is then sent to the user's device, where the user can review the content and make any necessary changes.

[0333] Automatic group creation phase

[0334] Server behavior:

[0335] All participants' self-introductory profiles are stored in a database, which is then analyzed using natural language processing (NLP) techniques and an emotion engine to identify participants' interests, goals, and emotional states.

[0336] Server behavior:

[0337] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm. The generated group information and session schedule are sent to each user's device.

[0338] User Action:

[0339] Check your session schedule on your device before the event.

[0340] Event Phase

[0341] User Action:

[0342] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0343] Device behavior:

[0344] It tracks users' location and emotional state data in real time, and also collects data based on conversations and interests during the event.

[0345] Device behavior:

[0346] All collected data is sent to the server.

[0347] Server behavior:

[0348] The collected location information, conversation data, and emotion data are analyzed to understand the current group arrangement and the progress of the conversation.

[0349] Server behavior:

[0350] It detects when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generates optimal new networking suggestions to solve these problems.

[0351] Server behavior:

[0352] Send the new proposal to the device.

[0353] Device behavior:

[0354] Notify users of new group and table placements.

[0355] User Action:

[0356] Follow the proposed new arrangement and move to your designated new table or group.

[0357] Specific examples

[0358] 1. Specific examples of the preparation phase

[0359] A user registers with the system to participate in an event, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The device sends the data to the server, which uses the generative AI model and emotion engine to generate a self-introduction profile for "an IT engineer with a deep understanding of marketing," and provides it to the user with the profile including emotion data.

[0360] 2. Example of the automatic group creation phase

[0361] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account participants' emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[0362] 3. Specific examples of event phases

[0363] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests more suitable people. Based on this suggestion, the user moves to the designated new table, enabling more effective networking.

[0364] This system will maximize the networking effect of participants throughout the entire event process, contributing to the success of the event.

[0365] The processing flow will be explained below.

[0366] Preparation Phase

[0367] Step 1:

[0368] User:

[0369] Log in to the event system and register to participate in the event.

[0370] Step 2:

[0371] server:

[0372] Users are presented with a survey that includes questions about their job, skills, interests, networking goals, and emotional state.

[0373] Step 3:

[0374] User:

[0375] Answer the survey and submit your answers.

[0376] Step 4:

[0377] Device:

[0378] The submitted questionnaire responses are relayed to the server.

[0379] Step 5:

[0380] server:

[0381] A generative AI model is run based on the received response data to automatically generate a self-introduction profile.

[0382] Step 6:

[0383] server:

[0384] An emotion engine is used to add emotion data to the generated profile.

[0385] Step 7:

[0386] server:

[0387] Send the completed profile to the device.

[0388] Step 8:

[0389] User:

[0390] Check your profile and make any necessary changes.

[0391] Automatic group creation phase

[0392] Step 9:

[0393] server:

[0394] The self-introduction profiles and emotional data of all participants are stored in a database.

[0395] Step 10:

[0396] server:

[0397] The stored profile information is analyzed using natural language processing (NLP) technology and an emotion engine to identify each participant's interests, goals, and emotional state.

[0398] Step 11:

[0399] server:

[0400] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm.

[0401] Step 12:

[0402] server:

[0403] The grouped information and a session schedule are generated and transmitted to each user's terminal.

[0404] Event Phase

[0405] Step 13:

[0406] User:

[0407] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0408] Step 14:

[0409] Device:

[0410] It tracks users' location and emotional state data in real time, and collects data based on their conversations and interests.

[0411] Step 15:

[0412] Device:

[0413] All collected data is sent to the server.

[0414] Step 16:

[0415] server:

[0416] The collected location information, conversation data, and emotion data are analyzed to understand the current group arrangement and the progress of the conversation.

[0417] Step 17:

[0418] server:

[0419] Detect when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generate optimal new networking proposals to address these challenges.

[0420] Step 18:

[0421] server:

[0422] Send the new proposal to the device.

[0423] Step 19:

[0424] Device:

[0425] Notify users of new group and table placements.

[0426] Step 20:

[0427] User:

[0428] Follow the proposed new arrangement and move to your designated new table or group.

[0429] Specific examples

[0430] Specific examples of the preparation phase

[0431] A user logs in to the system to participate in an event, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The user's device sends the data to the server, which uses the generative AI model and emotion engine to generate a self-introduction profile called "IT engineer with expertise in marketing," and provides it to the user with emotional data attached.

[0432] A concrete example of the automatic group creation phase

[0433] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account participants' emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[0434] Specific examples of phases during an event

[0435] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests more suitable people. Based on this suggestion, the user moves to the designated new table, enabling more effective networking.

[0436] Example 2

[0437] 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."

[0438] Promoting effective matching and interaction between participants is a key challenge at modern networking events. Traditional methods often fail to match participants based on their interests and goals, resulting in stagnant interactions and ineffective networking. Furthermore, they often fail to take into account participants' emotional states, often resulting in an unsatisfactory experience. Therefore, a system is needed that can grasp participants' emotional states and interaction situations in real time and provide optimal networking.

[0439] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for using a generative AI model in which participants answer simple questions in advance and generate a self-introduction profile based on the answers; a means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose, interests, and emotional state of each participant; a means for tracking the location information, conversation content, and emotional state of participants in real time during the event and optimizing the placement and progress of the event; and a means for generating an optimal new networking proposal and relocating participants when a problem is detected. This enables effective matching and promotion of interaction between participants.

[0440] A "generative AI model" is an algorithm used by a computer to automatically generate a self-introduction profile based on a large dataset.

[0441] A "profile" is information about a participant that describes their occupation, skills, interests, networking goals, and emotional state.

[0442] An "emotion engine" is a technology for extracting and evaluating emotions from text and audio data.

[0443] "Natural language processing technology" is a technology that allows computers to understand and process the language that humans use on a daily basis.

[0444] The "group generation means" is a function within the system that automatically creates optimal groups based on participants' goals, interests, and emotional states.

[0445] "Location information" is information that indicates the geographical location of a participant within the event venue.

[0446] "Conversation content" refers to the content of the dialogue between participants, and is text or audio data.

[0447] "Real-time tracking" means instantly tracking ongoing situations and collecting and analyzing data.

[0448] "Networking suggestions" are suggestions for new group and table arrangements based on participants' interests and emotional state.

[0449] "Optimizing" means maximizing the performance and efficiency of a system.

[0450] This invention is a system for facilitating efficient matching and interaction among participants at networking events, and uses a generative AI model and an emotion engine to improve accuracy. Specific embodiments of this system are described below.

[0451] Overall system overview

[0452] This invention allows users participating in a networking event to answer simple questions in advance, and then automatically generates a self-introduction profile based on the answers using a generative AI model. The generated profile includes emotional data for optimal matching. Furthermore, during the event, the system tracks users' location information and emotional state in real time and makes networking suggestions as needed.

[0453] Hardware and Software Configuration

[0454] 1. Server

[0455] The server receives the survey data and runs a generative AI model (e.g., OpenAI GPT-3®). The server uses an emotion engine to extract emotional data and generate profiles. The server then stores the profiles of all participants in a database and uses natural language processing (NLP) technology (e.g., NLTK or SpaCy) to analyze the profiles and generate optimal groups. The server analyzes the stored data and data collected in real time, and generates optimal networking suggestions if problems are detected.

[0456] 2. Terminal

[0457] The device primarily functions as an interface with the user, transmitting user input data to the server. During the event, the device also collects the user's location information (e.g., GPS) and emotional state data (e.g., biometric sensors) and transmits them to the server. The device then displays the data and suggestions sent from the server to the user.

[0458] Specific examples

[0459] Specific examples of the preparation phase

[0460] A user registers with the system, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The device sends this data to the server, which uses a generative AI model and emotion engine to generate a self-introduction profile for the user, calling them "an IT engineer with a strong marketing background," and provides this profile to the user, including their emotion data.

[0461] Example prompt sentence:

[0462] "Generate a self-introduction profile based on the user's occupation, skills, interests, networking goals and emotional state."

[0463] A concrete example of the automatic group creation phase

[0464] The server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[0465] Specific examples of phases during an event

[0466] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests new, more suitable people. The user follows the suggestions and moves to a new table, resulting in more effective networking.

[0467] In this way, the system can consistently collect and analyze data, providing optimal networking and contributing to the success of the event.

[0468] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0469] Step 1:

[0470] A user logs in to the system and registers to participate in an event. The terminal sends the input data to the server for authentication using the "email address" and "password" entered by the user. The server verifies the received login information, and if authentication is successful, redirects the user to the dashboard screen. The input in this step is the user's login information, and the output is the dashboard screen.

[0471] Step 2:

[0472] The user answers the displayed questionnaire. When the user answers questions about "job content," "skills," "interests," "networking goals," and "emotional state," the device records this answer data and sends it to the server. The server stores the received questionnaire data. The input in this step is the user's questionnaire answers, and the output is the stored questionnaire data.

[0473] Step 3:

[0474] The server runs a generative AI model using the received survey data. Based on the prompt, the "generative AI model" generates a self-introduction profile, and then uses an emotion engine to extract emotional data and include it in the profile. For example, the prompt might read, "Generate a self-introduction profile based on the user's occupation, skills, interests, networking goals, and emotional state." The input in this step is the survey data and the prompt, and the output is a self-introduction profile.

[0475] Step 4:

[0476] The server sends the generated self-introduction profile to the user's device. The user can review the profile on the device and modify it if necessary. The input in this step is the generated profile, and the output is the profile provided to the user.

[0477] Step 5:

[0478] The server stores the self-introduction profiles of all participants in a database. It uses natural language processing technology (e.g., NLTK or SpaCy) and an emotion engine to analyze participants' interests, goals, and emotional states from the stored profile information. The input in this step is the stored profile information, and the output is the analyzed data of interests, goals, and emotional states.

[0479] Step 6:

[0480] Based on the analysis results, the server uses an optimal matching algorithm (e.g., "K-means clustering") to group participants by purpose and emotional state. The generated group information and session schedule are sent to the user's device. The input in this step is the analysis results, and the output is the grouped information and session schedule.

[0481] Step 7:

[0482] On the day of the event, users check the session schedule on their devices and head to their assigned groups and tables. As users move, the devices collect location information (e.g., GPS) and emotional state data (e.g., biometric sensors) in real time and send them to the server. The inputs in this step are the user's movements and real-time data, and the output is the real-time data sent to the server.

[0483] Step 8:

[0484] The server analyzes the collected location, conversation, and emotion data to understand the current group arrangement and conversation progress. The server detects when a particular group is inactive, when there is low topic agreement, or when a particular participant is in a negative emotional state. The input in this step is the collected real-time data, and the output is the analysis results.

[0485] Step 9:

[0486] Based on the analysis results, the server generates an optimal new networking proposal to solve the problem and sends it to the user's device. The device notifies the user of this proposal, and the user moves to a new table or group specified based on the new proposal. The inputs in this step are the analysis results and the proposal generation algorithm, and the output is a new networking proposal provided to the user.

[0487] (Application example 2)

[0488] 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."

[0489] Conventional networking events and autonomous vehicles have faced challenges in providing optimal matching and comfort based on the emotional state and interests of participants and passengers. In particular, the lack of a mechanism for tracking and analyzing real-time emotional data and adjusting environmental settings based on this data has made it difficult to maximize the networking effect of participants and the comfort of passengers.

[0490] 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.

[0491] In this invention, the server includes: means for using a generative AI model that generates a self-introduction profile based on participants' answers to simple questions in advance; means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on each participant's purpose and interests; means for tracking participants' location information and conversation content in real time during the event to optimize the event layout and progress; means for collecting passengers' location information, emotional state, and purpose of the ride; means for using the collected data to analyze emotional data in real time and adjust music, lighting, and temperature; and means for presenting appropriate information and re-suggesting a ride route based on the collected emotional data. This maximizes the effectiveness of interactions at networking events and improves passenger comfort in autonomous vehicles.

[0492] A "generative AI model" is an artificial intelligence algorithm that automatically generates participant profiles from responses to surveys and questions.

[0493] A "self-introduction profile" is an introduction that includes the participant's personal information, interests, and goals, automatically generated by a generative AI model.

[0494] "Natural language processing technology" is an information processing technology for understanding, analyzing, and generating human language.

[0495] "Real-time tracking" is a technology that collects and tracks current information in a timely manner.

[0496] "Emotional data" refers to data that represents the emotional state of a participant or passenger, including positive, negative, neutral, and other emotional states.

[0497] "Location information" is data used to identify the current location of a person or object.

[0498] "Purpose of ride" refers to the passenger's main purpose or reason for using an autonomous vehicle.

[0499] "Adjusting music, lighting, and temperature" refers to a means of enhancing passenger comfort by appropriately setting and changing environmental elements inside an autonomous vehicle.

[0500] "Information presentation means" refers to a means for providing passengers with appropriate information visually or audibly.

[0501] "Route re-proposition" is a means of reconsidering and proposing the optimal route based on the current riding situation and destination.

[0502] The system according to the present invention can facilitate effective matching and interaction between participants at networking events, and can also improve the comfort of passengers in autonomous vehicles.

[0503] Preparation Phase

[0504] User Actions

[0505] Users log in to the system and register to participate in the event. After registering, they answer a questionnaire displayed by the system. The questionnaire includes questions about their interests, work, skills, networking goals, riding goals, and even their emotional state when introducing themselves.

[0506] Device behavior

[0507] The terminal receives the user's input data and transmits it to the server.

[0508] Server Operation

[0509] The server runs a generative AI model based on the received response data to automatically generate a self-introduction profile. The generated profile also includes emotional data generated by an emotion engine. This profile is then sent to the user's device, where the user can review and modify it as needed.

[0510] Automatic group creation phase

[0511] Server Operation

[0512] The server stores all participants' self-introduction profiles in a database, which are then analyzed using natural language processing (NLP) techniques and an emotion engine to identify participants' interests, goals, and emotional states.

[0513] Server Operation

[0514] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm. The generated group information and session schedule are sent to each user's device.

[0515] User Actions

[0516] Before the event, the user checks his / her session schedule on the terminal.

[0517] Event Phase

[0518] User Actions

[0519] On the day of the event, users check the session schedule on their device and head to their designated group or table.

[0520] Device behavior

[0521] The device tracks users' location and emotional state data in real time, and also collects data based on conversations and interests during the event.

[0522] Server Operation

[0523] The server analyzes the collected location information, conversation data, and emotion data to understand the current group arrangement and the progress of the conversation.

[0524] Server Operation

[0525] The server detects when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generates optimal new networking proposals to resolve these issues.

[0526] Device behavior

[0527] The terminal notifies the user of the new proposals that have been generated.

[0528] User Actions

[0529] The user follows the proposed new arrangement and moves to the specified new table or group.

[0530] Specific examples

[0531] For example, if a user answers a questionnaire when registering for an event with "I'm interested in marketing and work as an IT engineer" and selects "expecting" as their emotion, the device will send that data to the server, which will then use the generative AI model and emotion engine to generate a self-introduction profile for "an IT engineer with extensive experience in marketing" and provide it to the user with the profile including their emotion data.

[0532] On the day of the event, if a user participates in a session and their emotional state becomes negative, the system will detect this in real time and suggest more appropriate networking partners. The user can then follow the suggestions and move to a new table or group, ensuring effective networking.

[0533] Example of a prompt sentence for an application example

[0534] For example, a prompt for improving comfort in a self-driving vehicle:

[0535] "My current objective is a work presentation. My emotional state is tense."

[0536] This invention allows for maximizing the social impact of networking events and improving passenger comfort in autonomous vehicles.

[0537] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0538] Step 1:

[0539] User Actions

[0540] Users log in to the system and register to participate in the event. As input, they provide information in the form of a questionnaire about their interests, jobs, skills, networking goals, riding goals, emotional state, etc. The output is that this data is sent to the terminal.

[0541] Step 2:

[0542] Device behavior

[0543] The terminal receives the user's input data and sends it to the server. It receives the user's survey results as input and generates a data package to send to the server as output.

[0544] Step 3:

[0545] Server Operation

[0546] The server runs a generative AI model based on the received user data to generate a self-introduction profile. The input is the user's questionnaire response data, and the output is the generated self-introduction profile and emotion data. Specifically, the AI ​​model analyzes the text data using natural language processing technology and generates an appropriate profile.

[0547] Step 4:

[0548] Server Operation

[0549] The generated self-introduction profile and emotion data are sent to the user's terminal. The input is the generated self-introduction profile and emotion data, and this is sent to the user's terminal as output.

[0550] Step 5:

[0551] User Actions

[0552] The user checks the received profile and modifies it if necessary. The input is the self-introduction profile that was just received, and the output is the modified profile. This modified data is sent back to the server.

[0553] Step 6:

[0554] Server Operation

[0555] The server stores the self-introduction profiles of all participants in a database and analyzes them using natural language processing technology and an emotion engine. The input is the self-introduction profiles of all participants, and the output is data on each participant's interests, goals, and emotional state.

[0556] Step 7:

[0557] Server Operation

[0558] Based on the analysis results, the server uses an optimal matching algorithm to group participants by purpose and emotional state. The input is the analyzed participant data, and the output is optimal group information and session schedule.

[0559] Step 8:

[0560] Server Operation

[0561] The generated group information and session schedule are sent to each user's terminal. The input is the group information and session schedule, and the output is to send them to the user's terminal.

[0562] Step 9:

[0563] User Actions

[0564] Before an event, a user checks their own session schedule on a terminal. The input is the session schedule sent from the server, and the output is to view and check it.

[0565] Step 10:

[0566] Device behavior

[0567] On the day of the event, the device tracks the user's location and emotional state data in real time. The input is the user's current location and emotional state, and the output is the data tracking them in real time.

[0568] Step 11:

[0569] Server Operation

[0570] The server analyzes the collected location information, conversation data, and emotion data to understand the current group arrangement and conversation progress. The input is the data collected in real time, and the output is the analysis results.

[0571] Step 12:

[0572] Server Operation

[0573] The server detects when a particular group is inactive, when topic agreement is low, or when a particular participant is in a negative emotional state, and generates optimal new networking proposals based on this.The input is the analyzed group data and emotional data, and the output is new networking proposals.

[0574] Step 13:

[0575] Device behavior

[0576] The terminal notifies the user of the new proposals it generates. The input is the networking proposal sent by the server, and the output is the notification to the user.

[0577] Step 14:

[0578] User Actions

[0579] The user moves to the specified new table or group according to the proposed new arrangement. The input is the new group arrangement information, and the output is the behavior according to that instruction.

[0580] 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.

[0581] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0582] 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.

[0583] [Second embodiment]

[0584] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0585] 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.

[0586] 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).

[0587] 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.

[0588] 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.

[0589] 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).

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0595] 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."

[0596] Overall system overview

[0597] This invention is a system for streamlining networking events. Participants can generate self-introduction profiles by simply answering a few simple questions in advance, and dynamically create and coordinate optimal groups during the event. The system is divided into three main phases: a pre-preparation phase, an automatic group creation phase, and an event-in-progress phase.

[0598] Preparation Phase

[0599] User Action:

[0600] To participate in a networking event, users log in to the system and apply for participation. After logging in, they answer a questionnaire displayed by the system, which includes information about their job, their skills, interests, and the purpose of networking.

[0601] Device behavior:

[0602] It receives user input data and sends it to the server.

[0603] Server behavior:

[0604] The server runs a generative AI model based on the input data to automatically generate a self-introduction profile. The generated profile information is sent to the user's device, where the user can review the content and make any necessary edits.

[0605] Automatic group creation phase

[0606] Server behavior:

[0607] Self-introduction profile information for all participants is stored in a database. The stored profile information is analyzed using natural language processing (NLP) technology to identify participants' interests and goals. Based on the analysis results, an optimal matching algorithm is used to group participants by goal. The generated group information is sent to each user's device on the day of the event.

[0608] User Action:

[0609] Check your session schedule on your device before the event.

[0610] Event Phase

[0611] User Action:

[0612] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0613] Device behavior:

[0614] It tracks users' location information in real time, collects data based on their conversations and interests, and sends it to a server.

[0615] Server behavior:

[0616] The system analyzes the collected location and conversation data to understand the current group arrangement and conversation progress. It detects when a particular group is inactive or has low topic agreement, and generates optimal new networking suggestions. These suggestions are sent to the user's device, notifying them of new group and table arrangements.

[0617] Specific examples

[0618] 1. Specific examples of the preparation phase

[0619] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." When the device sends the data to the server, the server uses a generative AI model to generate a self-introduction profile for the user, describing him as an "IT engineer with a strong marketing background," and provides it to the user.

[0620] 2. Example of the automatic group creation phase

[0621] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[0622] 3. Specific examples of event phases

[0623] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[0624] As described above, this system maximizes the networking effect of participants throughout the entire event process, contributing to the success of the event.

[0625] The processing flow will be explained below.

[0626] Preparation Phase

[0627] Step 1:

[0628] User:

[0629] Log in to the event system and register.

[0630] Step 2:

[0631] server:

[0632] Users are presented with a survey that includes questions about the participant's job, skills, interests, and networking goals.

[0633] Step 3:

[0634] User:

[0635] Answer the survey and submit your answers.

[0636] Step 4:

[0637] Device:

[0638] The submitted questionnaire responses are relayed to the server.

[0639] Step 5:

[0640] server:

[0641] A generative AI model is run based on the received response data to generate a self-introduction profile.

[0642] Step 6:

[0643] server:

[0644] Send the generated profile to the device.

[0645] Step 7:

[0646] User:

[0647] Check your profile and make any necessary changes.

[0648] Automatic group creation phase

[0649] Step 8:

[0650] server:

[0651] All participants' self-introduction profiles are stored in a database.

[0652] Step 9:

[0653] server:

[0654] The stored profile information is analyzed using natural language processing (NLP) technology to identify each participant's interests and networking goals.

[0655] Step 10:

[0656] server:

[0657] Based on the analysis results, participants are grouped by purpose using an optimal matching algorithm.

[0658] Step 11:

[0659] server:

[0660] The grouped information and a session schedule are generated and transmitted to each user's terminal.

[0661] Event Phase

[0662] Step 12:

[0663] User:

[0664] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0665] Step 13:

[0666] Device:

[0667] It tracks users' locations in real time and collects data based on their conversations and interests.

[0668] Step 14:

[0669] Device:

[0670] The collected data is sent to the server.

[0671] Step 15:

[0672] server:

[0673] The collected location information and conversation data is analyzed to understand the current group arrangement and conversation progress.

[0674] Step 16:

[0675] server:

[0676] It detects when certain groups are inactive or have low topical alignment and generates new networking suggestions.

[0677] Step 17:

[0678] server:

[0679] Send the new proposal to the device.

[0680] Step 18:

[0681] Device:

[0682] Notify users of new group and table placements.

[0683] Step 19:

[0684] User:

[0685] Follow the proposed new arrangement and move to your designated new table or group.

[0686] This series of steps allows for efficient and beneficial networking even in a limited amount of time.

[0687] Example 1

[0688] 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."

[0689] To enable participants to interact more effectively at networking events, it is important to create detailed profiles in advance and meet suitable people during the event. However, with conventional systems, creating self-introduction profiles and grouping participants is often done manually, which is time-consuming and labor-intensive and may not result in optimal matching. It is also difficult to grasp and adjust real-time interaction situations during the event, making it difficult for participants to network effectively.

[0690] 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.

[0691] In this invention, the server includes: means for using a generative AI model in which participants answer simple questions in advance and generate a self-introduction profile based on the answers; means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose and interests of each participant; means for tracking participants' location information and conversation content in real time during the event to optimize the progress of the event; and means for monitoring specific activity levels within groups and generating and notifying new networking suggestions in the event of inactive groups or low topic matches. This allows participants to easily create effective self-introduction profiles and continue to meet suitable people even during the event.

[0692] A "generative AI model" is a program that uses artificial intelligence technology to automatically generate a self-introduction profile based on participants' responses.

[0693] "Natural language processing technology" is a field of computer science that deals with understanding and processing human language, and is a technology used to analyze and generate text data.

[0694] A "self-introduction profile" is a digital document that organizes personal information about participants, including their job, skills, interests, concerns, and networking goals.

[0695] The "group generation method" is an algorithm that automatically creates appropriate groups based on participants' self-introduction profiles and interests according to the purpose of networking.

[0696] "Location Information" means data obtained using GPS or other technologies that indicates where a Participant is located within an Event.

[0697] "Conversation content" is data including topics and keywords of verbal communication exchanged between participants during the event.

[0698] "Real-time tracking" refers to a system that instantly acquires participants' location information and conversation content while the event is in progress, sends it to a server, and dynamically analyzes it.

[0699] "Networking Suggestions" are notifications from the system that recommend new suitable networking partners and groups based on participants' current group placement and conversation content.

[0700] The "means for monitoring specific activity levels within a group" refers to an algorithm that monitors the activity status and conversation progress of participants within a group and evaluates the activity level of the group.

[0701] This invention is a system for streamlining networking events, allowing participants to generate self-introduction profiles by answering simple questions in advance, and dynamically creating and adjusting optimal groups during the event.

[0702] Overall system overview

[0703] The system combines generative AI models and natural language processing technology to automatically generate participant profiles and dynamically create and coordinate groups during the event. The system is basically divided into the following phases: pre-preparation phase, automatic group creation phase, and in-event phase.

[0704] Preparation Phase

[0705] User Actions

[0706] To participate in an event, users log in to the system and apply for participation. After logging in, they answer a questionnaire that appears. This questionnaire includes questions about their job, their skills, interests, and networking goals.

[0707] Device behavior

[0708] The terminal receives the user's input data and sends it to the server.

[0709] Server Operation

[0710] The server uses a generative AI model (e.g., GPT-4) to generate a self-introduction profile from the user's input data. The generated profile information is sent to the device, where the user can review the content and make any necessary corrections.

[0711] Automatic group creation phase

[0712] Server Operation

[0713] The server stores the self-introduction profile information of all participants in a database (e.g., MySQL). It then analyzes the data using natural language processing (NLP) technology (e.g., SpaCy) to identify participants' interests and goals. Based on this information, it uses an optimal matching algorithm (e.g., K-means clustering) to group participants by purpose. The generated group information is sent to each user's device.

[0714] Event Phase

[0715] User Actions

[0716] On the day of the event, users check the session schedule on their device and head to their designated group or table.

[0717] Device behavior

[0718] The device tracks the user's location in real time using GPS, collects conversation content through a microphone, and sends the data to a server.

[0719] Server Operation

[0720] The server analyzes the collected data to understand the group placement and conversation progress, and if a particular group is inactive or has low topic agreement, it generates optimal new networking proposals and sends them to the user's device.

[0721] Specific examples

[0722] 1. Specific examples of the preparation phase

[0723] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." When the device sends the data to the server, the server uses a generative AI model (e.g., "GPT-4") to generate a self-introduction profile for the user, describing the user as an "IT engineer with expertise in marketing," and provides it to the user.

[0724] 2. Example of the automatic group creation phase

[0725] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[0726] 3. Specific examples of event phases

[0727] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[0728] Prompt Sentence Examples

[0729] "My area of ​​interest is marketing and I currently work as an IT engineer. Please create a profile to introduce myself."

[0730] Through these phases, the present invention can maximize the networking effect of participants and improve the outcome of the event.

[0731] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0732] Step 1: Log in and complete the survey

[0733] User Actions

[0734] Users log in to the system and answer a questionnaire. After entering their ID and password on the login page and being authenticated, the questionnaire screen appears. Users answer questions about their work, skills, interests, networking goals, etc.

[0735] Device behavior

[0736] The terminal receives the user's input data from the input form, performs error checks (e.g., checking required fields, checking data format), and then sends the data to the server in JSON format.

[0737] Input: Data entered by the user into the survey form (e.g., job, skills, interests)

[0738] Output: Data after error checking is sent to the server

[0739] Step 2: Create your profile

[0740] Server Operation

[0741] The server uses a generative AI model (e.g., GPT-4) to generate a self-introduction profile from the received input data. The generated profile reflects the user's interests and skills. Natural language processing technology is used to generate the profile.

[0742] Input: User survey data sent from the device

[0743] Data processing: AI models analyze data, perform natural language processing, and generate profiles

[0744] Output: Generated self-introduction profile

[0745] Device behavior

[0746] The generated profile information is sent to the user's device, which displays the profile and prompts the user to confirm and make any necessary corrections.

[0747] Input: Self-introduction profile sent from the server

[0748] Output: The profile screen that the user sees

[0749] Step 3: Check and modify your profile

[0750] User Actions

[0751] The user checks their self-introduction profile and makes any necessary corrections. The corrections are then sent back to the server.

[0752] Input: Initially generated profile

[0753] Output: Corrected profile data

[0754] Device behavior

[0755] The terminal receives the user's modifications and sends them back to the server.

[0756] Input: Corrected profile data

[0757] Output: Modifications sent to the server

[0758] Step 4: Store profile information in a database

[0759] Server Operation

[0760] The server stores the modified profile in a database using a fast relational database (e.g., MySQL).

[0761] Input: Corrected profile data

[0762] Data processing: Insert / update data into database based on data format

[0763] Output: Profile information stored in the database

[0764] Step 5: Analyze and group profiles

[0765] Server Operation

[0766] The server analyzes the stored profile information using natural language processing (NLP) techniques (e.g., SpaCy) to identify participants' interests and goals, and then groups them based on the identified information using an optimal matching algorithm (e.g., K-means clustering).

[0767] Input: Profile information stored in the database

[0768] Data processing: Natural language processing technology is used to identify interests and purposes, and matching algorithms are used to group them.

[0769] Output: Group information

[0770] Step 6: Generate and distribute session schedules

[0771] Server Operation

[0772] The server generates a session schedule for the event based on the generated group information, and transmits the session schedule to each user's device.

[0773] Input: Group information

[0774] Data processing: Create a session schedule using a schedule generation algorithm

[0775] Output: Generated session schedule

[0776] Device behavior

[0777] The terminal receives the session schedule sent from the server and displays it to the user.

[0778] Input: Session schedule sent from the server

[0779] Output: The schedule screen displayed to the user

[0780] Step 7: Collect location and conversation data during the event

[0781] Device behavior

[0782] The device tracks the user's location in real time using GPS and collects conversations through a microphone, which is then periodically sent to a server.

[0783] Input: User location and conversation data

[0784] Output: Collected data is sent to the server

[0785] Step 8: Data analysis and networking proposals

[0786] Server Operation

[0787] The server analyzes the collected location information and conversation data to evaluate the activity level of the group and the degree of topic agreement. If the group is inactive or the degree of topic agreement is low, it generates new networking suggestions and notifies the user's device.

[0788] Input: Location and conversation data

[0789] Data processing: Analyze the data using an analytical algorithm to evaluate activity and consistency

[0790] Output: Networking suggestions are sent to the user's device.

[0791] Step 9: Implementing a Networking Proposal

[0792] User Actions

[0793] Users will move to new groups and tables according to new networking suggestions notified to their devices, resulting in more effective networking.

[0794] Input: Networking suggestions from the server

[0795] Output: Move to new group or table

[0796] This step allows the system to maximize the networking effect of participants throughout the event, contributing to the success of the event.

[0797] (Application example 1)

[0798] 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."

[0799] In conventional networking events, it is difficult to efficiently match participants based on their goals and interests. Furthermore, while real-time optimization of participant placement and progress, as well as dynamic group adjustment, is required during the event, no method exists to achieve this. The present invention aims to solve these problems and maximize the effectiveness of networking events.

[0800] 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.

[0801] In this invention, the server includes a means for using a generative AI model that generates a self-introduction profile based on participants' answers to simple questions in advance, a means for collecting and analyzing the self-introduction profiles generated by the generative AI model and automatically generating groups based on the goals and interests of each participant, a means for tracking participants' location information and conversation content in real time during the event and optimizing and dynamically adjusting the placement and progress of the event, and a means for participants to participate in the virtual networking event using smartphones, smart glasses, or head-mounted displays, thereby maximizing the effectiveness of the networking event and enabling participants to be matched with each other and their placement to be adjusted in real time.

[0802] A "networking event" is an event where participants gather to exchange information and explore business opportunities.

[0803] "Quick Questions" are a set of short, easy-to-answer questions used to understand participants' basic information, interests, skills, and goals.

[0804] A "self-introduction profile" is electronic data that is generated based on information provided by participants in advance and comprehensively indicates a person's characteristics, interests, skills, goals, etc.

[0805] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to make predictions or generate results from input information.

[0806] A "means" is a method or process used to achieve a particular function or purpose.

[0807] "Collection" is the act of gathering data or information in one place.

[0808] "Analysis" is the process of examining collected data and information in detail to derive specific patterns and meanings.

[0809] "Purpose" refers to the specific reason participants are attending the networking event or what they hope to achieve.

[0810] "Interests" are topics or themes that participants have a personal interest in.

[0811] "Automatic group generation" refers to using artificial intelligence techniques to categorize participants into appropriate groups without manual intervention.

[0812] "Location information" is geographical data that indicates where a participant is currently located.

[0813] "Conversation content" refers to the words and topics exchanged between participants during the event.

[0814] "Real-time tracking" refers to the instantaneous monitoring and recording of ongoing situations.

[0815] "Optimizing progress" means adjusting the flow of events and plans to proceed most efficiently.

[0816] "Dynamic adjustment" means changing the settings and plans as appropriate depending on the event situation and the status of the participants.

[0817] A "virtual networking event" is an event held in an online environment for the purpose of networking.

[0818] A "smartphone" is a highly functional mobile phone that can connect to the Internet and run applications.

[0819] "Smart glasses" are glasses-type electronic devices with a built-in display that displays information.

[0820] A "head-mounted display" is a device that displays images by being worn on the head.

[0821] Overall system overview

[0822] The present invention is a system for streamlining networking events, allowing participants to create self-introduction profiles by simply answering simple questions in advance, and dynamically creating and adjusting optimal groups during the event, thereby maximizing the networking effect of participants throughout the entire event process.

[0823] System Configuration

[0824] The system is divided into three main phases:

[0825] 1. Preparation Phase

[0826] 2. Automatic group creation phase

[0827] 3. Event Phase

[0828] Preparation Phase

[0829] User Action:

[0830] To participate in a networking event, users log in to the system and apply for participation. After logging in, they answer a questionnaire displayed by the system, which includes information about their job, their skills, interests, and the purpose of networking.

[0831] Device behavior:

[0832] It receives user input data and sends it to the server.

[0833] Server behavior:

[0834] The server runs a generative AI model based on the input data to automatically generate a self-introduction profile. The generated profile information is sent to the user's device, where the user can review the content and make any necessary edits.

[0835] Automatic group creation phase

[0836] Server behavior:

[0837] Self-introduction profile information for all participants is stored in a database. The stored profile information is analyzed using natural language processing (NLP) technology to identify participants' interests and goals. Based on the analysis results, an optimal matching algorithm is used to group participants by goal. The generated group information is sent to each user's device on the day of the event.

[0838] User Action:

[0839] Check your session schedule on your device before the event.

[0840] Event Phase

[0841] User Action:

[0842] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0843] Device behavior:

[0844] It tracks users' location information in real time, collects data based on their conversations and interests, and sends it to a server.

[0845] Server behavior:

[0846] The system analyzes the collected location and conversation data to understand the current group arrangement and conversation progress. It detects when a particular group is inactive or has low topic agreement, and generates optimal new networking suggestions. These suggestions are sent to the user's device, notifying them of new group and table arrangements.

[0847] Hardware and software used

[0848] Hardware:

[0849] Smartphones, smart glasses, head-mounted displays

[0850] software:

[0851] Python, OpenAI API, Geopy

[0852] Specific examples

[0853] 1. Examples of the preparatory phase:

[0854] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." The server uses a generative AI model to generate a self-introduction profile for the user, describing him as an "IT engineer with a strong marketing background," and provides it to the user.

[0855] 2. Example of automatic group creation phase:

[0856] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[0857] 3. Examples of event phases:

[0858] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[0859] Examples of prompt statements

[0860] text

[0861] User information: Interested in marketing, working as an IT engineer

[0862] Use this information to create your profile.

[0863] The above is a specific embodiment of the present invention. This system maximizes the effectiveness of networking events, enabling participants to be matched and allocated in real time.

[0864] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0865] Step 1:

[0866] To participate in an event, users log in to the system and answer a questionnaire. The user's input data includes information about their job, skills, interests, and networking goals. This input data is sent from the terminal to the server.

[0867] Step 2:

[0868] The server runs a generative AI model based on the received input data to generate a self-introduction profile. The server then sends the generated profile to the user's device, allowing the user to review the content and make any necessary corrections. Input: Survey response data. Output: Self-introduction profile.

[0869] Step 3:

[0870] The server stores the self-introduction profile information of all participants in a database. The server analyzes the stored profile information using natural language processing (NLP) techniques to identify participants' interests and goals. Input: Self-introduction profile. Output: Analysis results.

[0871] Step 4:

[0872] The server uses the optimal matching algorithm based on the analysis results to group participants by purpose. The server sends the generated group information to each user's device on the day of the event. Input: Analysis results. Output: Group information.

[0873] Step 5:

[0874] Before the event, users check their own session schedules on their terminals. The terminals display the user's session schedule based on the group information received from the server. Input: Group information. Output: Session schedule.

[0875] Step 6:

[0876] On the day of the event, users check the session schedule on their device and head to their designated group or table. The device tracks the user's location information in real time and sends it to the server. Input: User's location information. Output: Real-time data sent to the server.

[0877] Step 7:

[0878] The server analyzes the collected location information and conversation data to understand the current group arrangement and conversation progress. If a particular group is inactive or has low topic agreement, it detects this and generates optimal new networking proposals. Input: Location information, conversation data. Output: Networking proposals.

[0879] Step 8:

[0880] The server sends a new networking proposal to the user's terminal, notifying them of the new group and table placement. The user moves to the specified new table according to the new proposal and continues networking. Input: Networking proposal. Output: New group placement notification.

[0881] 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.

[0882] Overall system overview

[0883] This invention is a system for promoting efficient matching and interaction among participants at networking events, incorporating an emotion engine to improve accuracy. Participants answer simple questions in advance, and optimal matching is performed based on an automatically generated self-introduction profile. Furthermore, participants' emotional data is tracked in real time during the event, and necessary adjustments are made.

[0884] Preparation Phase

[0885] User Action:

[0886] Users log in to the system and register to attend the event. After registering, they answer a questionnaire displayed by the system, which includes questions about their job, skills, interests, networking goals, and even their emotional state when introducing themselves.

[0887] Device behavior:

[0888] It receives user input data and sends it to the server.

[0889] Server behavior:

[0890] The server runs a generative AI model based on the received response data to automatically generate a self-introduction profile. The generated profile also includes emotional data generated by an emotion engine. This profile is then sent to the user's device, where the user can review the content and make any necessary changes.

[0891] Automatic group creation phase

[0892] Server behavior:

[0893] All participants' self-introductory profiles are stored in a database, which is then analyzed using natural language processing (NLP) techniques and an emotion engine to identify participants' interests, goals, and emotional states.

[0894] Server behavior:

[0895] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm. The generated group information and session schedule are sent to each user's device.

[0896] User Action:

[0897] Check your session schedule on your device before the event.

[0898] Event Phase

[0899] User Action:

[0900] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0901] Device behavior:

[0902] It tracks users' location and emotional state data in real time, and also collects data based on conversations and interests during the event.

[0903] Device behavior:

[0904] All collected data is sent to the server.

[0905] Server behavior:

[0906] The collected location information, conversation data, and emotion data are analyzed to understand the current group arrangement and the progress of the conversation.

[0907] Server behavior:

[0908] It detects when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generates optimal new networking suggestions to solve these problems.

[0909] Server behavior:

[0910] Send the new proposal to the device.

[0911] Device behavior:

[0912] Notify users of new group and table placements.

[0913] User Action:

[0914] Follow the proposed new arrangement and move to your designated new table or group.

[0915] Specific examples

[0916] 1. Specific examples of the preparation phase

[0917] A user registers with the system to participate in an event, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The device sends the data to the server, which uses the generative AI model and emotion engine to generate a self-introduction profile for "an IT engineer with a deep understanding of marketing," and provides it to the user with the profile including emotion data.

[0918] 2. Example of the automatic group creation phase

[0919] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account participants' emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[0920] 3. Specific examples of event phases

[0921] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests more suitable people. Based on this suggestion, the user moves to the designated new table, enabling more effective networking.

[0922] This system will maximize the networking effect of participants throughout the entire event process, contributing to the success of the event.

[0923] The processing flow will be explained below.

[0924] Preparation Phase

[0925] Step 1:

[0926] User:

[0927] Log in to the event system and register to participate in the event.

[0928] Step 2:

[0929] server:

[0930] Users are presented with a survey that includes questions about their job, skills, interests, networking goals, and emotional state.

[0931] Step 3:

[0932] User:

[0933] Answer the survey and submit your answers.

[0934] Step 4:

[0935] Device:

[0936] The submitted questionnaire responses are relayed to the server.

[0937] Step 5:

[0938] server:

[0939] A generative AI model is run based on the received response data to automatically generate a self-introduction profile.

[0940] Step 6:

[0941] server:

[0942] An emotion engine is used to add emotion data to the generated profile.

[0943] Step 7:

[0944] server:

[0945] Send the completed profile to the device.

[0946] Step 8:

[0947] User:

[0948] Check your profile and make any necessary changes.

[0949] Automatic group creation phase

[0950] Step 9:

[0951] server:

[0952] The self-introduction profiles and emotional data of all participants are stored in a database.

[0953] Step 10:

[0954] server:

[0955] The stored profile information is analyzed using natural language processing (NLP) technology and an emotion engine to identify each participant's interests, goals, and emotional state.

[0956] Step 11:

[0957] server:

[0958] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm.

[0959] Step 12:

[0960] server:

[0961] The grouped information and a session schedule are generated and transmitted to each user's terminal.

[0962] Event Phase

[0963] Step 13:

[0964] User:

[0965] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[0966] Step 14:

[0967] Device:

[0968] It tracks users' location and emotional state data in real time, and collects data based on their conversations and interests.

[0969] Step 15:

[0970] Device:

[0971] All collected data is sent to the server.

[0972] Step 16:

[0973] server:

[0974] The collected location information, conversation data, and emotion data are analyzed to understand the current group arrangement and the progress of the conversation.

[0975] Step 17:

[0976] server:

[0977] Detect when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generate optimal new networking proposals to address these challenges.

[0978] Step 18:

[0979] server:

[0980] Send the new proposal to the device.

[0981] Step 19:

[0982] Device:

[0983] Notify users of new group and table placements.

[0984] Step 20:

[0985] User:

[0986] Follow the proposed new arrangement and move to your designated new table or group.

[0987] Specific examples

[0988] Specific examples of the preparation phase

[0989] A user logs in to the system to participate in an event, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The user's device sends the data to the server, which uses the generative AI model and emotion engine to generate a self-introduction profile called "IT engineer with expertise in marketing," and provides it to the user with emotional data attached.

[0990] A concrete example of the automatic group creation phase

[0991] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account participants' emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[0992] Specific examples of phases during an event

[0993] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests more suitable people. Based on this suggestion, the user moves to the designated new table, enabling more effective networking.

[0994] Example 2

[0995] 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."

[0996] Promoting effective matching and interaction between participants is a key challenge at modern networking events. Traditional methods often fail to match participants based on their interests and goals, resulting in stagnant interactions and ineffective networking. Furthermore, they often fail to take into account participants' emotional states, often resulting in an unsatisfactory experience. Therefore, a system is needed that can grasp participants' emotional states and interaction situations in real time and provide optimal networking.

[0997] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for using a generative AI model in which participants answer simple questions in advance and generate a self-introduction profile based on the answers; a means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose, interests, and emotional state of each participant; a means for tracking the location information, conversation content, and emotional state of participants in real time during the event and optimizing the placement and progress of the event; and a means for generating an optimal new networking proposal and relocating participants when a problem is detected. This enables effective matching and promotion of interaction between participants.

[0998] A "generative AI model" is an algorithm used by a computer to automatically generate a self-introduction profile based on a large dataset.

[0999] A "profile" is information about a participant that describes their occupation, skills, interests, networking goals, and emotional state.

[1000] An "emotion engine" is a technology for extracting and evaluating emotions from text and audio data.

[1001] "Natural language processing technology" is a technology that allows computers to understand and process the language that humans use on a daily basis.

[1002] The "group generation means" is a function within the system that automatically creates optimal groups based on participants' goals, interests, and emotional states.

[1003] "Location information" is information that indicates the geographical location of a participant within the event venue.

[1004] "Conversation content" refers to the content of the dialogue between participants, and is text or audio data.

[1005] "Real-time tracking" means instantly tracking ongoing situations and collecting and analyzing data.

[1006] "Networking suggestions" are suggestions for new group and table arrangements based on participants' interests and emotional state.

[1007] "Optimizing" means maximizing the performance and efficiency of a system.

[1008] This invention is a system for facilitating efficient matching and interaction among participants at networking events, and uses a generative AI model and an emotion engine to improve accuracy. Specific embodiments of this system are described below.

[1009] Overall system overview

[1010] This invention allows users participating in a networking event to answer simple questions in advance, and then automatically generates a self-introduction profile based on the answers using a generative AI model. The generated profile includes emotional data for optimal matching. Furthermore, during the event, the system tracks users' location information and emotional state in real time and makes networking suggestions as needed.

[1011] Hardware and Software Configuration

[1012] 1. Server

[1013] The server receives the survey data and runs a generative AI model (e.g., OpenAI GPT-3). The server uses an emotion engine to extract emotional data and generate profiles. The server then stores all participant profiles in a database and uses natural language processing (NLP) techniques (e.g., NLTK and SpaCy) to analyze the profiles and generate optimal groups. The server analyzes the stored data and data collected in real time, and generates optimal networking suggestions if problems are detected.

[1014] 2. Terminal

[1015] The device primarily functions as an interface with the user, transmitting user input data to the server. During the event, the device also collects the user's location information (e.g., GPS) and emotional state data (e.g., biometric sensors) and transmits them to the server. The device then displays the data and suggestions sent from the server to the user.

[1016] Specific examples

[1017] Specific examples of the preparation phase

[1018] A user registers with the system, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The device sends this data to the server, which uses a generative AI model and emotion engine to generate a self-introduction profile for the user, calling them "an IT engineer with a strong marketing background," and provides this profile to the user, including their emotion data.

[1019] Example prompt sentence:

[1020] "Generate a self-introduction profile based on the user's occupation, skills, interests, networking goals and emotional state."

[1021] A concrete example of the automatic group creation phase

[1022] The server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[1023] Specific examples of phases during an event

[1024] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests new, more suitable people. The user follows the suggestions and moves to a new table, resulting in more effective networking.

[1025] In this way, the system can consistently collect and analyze data, providing optimal networking and contributing to the success of the event.

[1026] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1027] Step 1:

[1028] A user logs in to the system and registers to participate in an event. The terminal sends the input data to the server for authentication using the "email address" and "password" entered by the user. The server verifies the received login information, and if authentication is successful, redirects the user to the dashboard screen. The input in this step is the user's login information, and the output is the dashboard screen.

[1029] Step 2:

[1030] The user answers the displayed questionnaire. When the user answers questions about "job content," "skills," "interests," "networking goals," and "emotional state," the device records this answer data and sends it to the server. The server stores the received questionnaire data. The input in this step is the user's questionnaire answers, and the output is the stored questionnaire data.

[1031] Step 3:

[1032] The server runs a generative AI model using the received survey data. Based on the prompt, the "generative AI model" generates a self-introduction profile, and then uses an emotion engine to extract emotional data and include it in the profile. For example, the prompt might read, "Generate a self-introduction profile based on the user's occupation, skills, interests, networking goals, and emotional state." The input in this step is the survey data and the prompt, and the output is a self-introduction profile.

[1033] Step 4:

[1034] The server sends the generated self-introduction profile to the user's device. The user can review the profile on the device and modify it if necessary. The input in this step is the generated profile, and the output is the profile provided to the user.

[1035] Step 5:

[1036] The server stores the self-introduction profiles of all participants in a database. It uses natural language processing technology (e.g., NLTK or SpaCy) and an emotion engine to analyze participants' interests, goals, and emotional states from the stored profile information. The input in this step is the stored profile information, and the output is the analyzed data of interests, goals, and emotional states.

[1037] Step 6:

[1038] Based on the analysis results, the server uses an optimal matching algorithm (e.g., "K-means clustering") to group participants by purpose and emotional state. The generated group information and session schedule are sent to the user's device. The input in this step is the analysis results, and the output is the grouped information and session schedule.

[1039] Step 7:

[1040] On the day of the event, users check the session schedule on their devices and head to their assigned groups and tables. As users move, the devices collect location information (e.g., GPS) and emotional state data (e.g., biometric sensors) in real time and send them to the server. The inputs in this step are the user's movements and real-time data, and the output is the real-time data sent to the server.

[1041] Step 8:

[1042] The server analyzes the collected location, conversation, and emotion data to understand the current group arrangement and conversation progress. The server detects when a particular group is inactive, when there is low topic agreement, or when a particular participant is in a negative emotional state. The input in this step is the collected real-time data, and the output is the analysis results.

[1043] Step 9:

[1044] Based on the analysis results, the server generates an optimal new networking proposal to solve the problem and sends it to the user's device. The device notifies the user of this proposal, and the user moves to a new table or group specified based on the new proposal. The inputs in this step are the analysis results and the proposal generation algorithm, and the output is a new networking proposal provided to the user.

[1045] (Application example 2)

[1046] 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."

[1047] Conventional networking events and autonomous vehicles have faced challenges in providing optimal matching and comfort based on the emotional state and interests of participants and passengers. In particular, the lack of a mechanism for tracking and analyzing real-time emotional data and adjusting environmental settings based on this data has made it difficult to maximize the networking effect of participants and the comfort of passengers.

[1048] 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.

[1049] In this invention, the server includes: means for using a generative AI model that generates a self-introduction profile based on participants' answers to simple questions in advance; means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on each participant's purpose and interests; means for tracking participants' location information and conversation content in real time during the event to optimize the event layout and progress; means for collecting passengers' location information, emotional state, and purpose of the ride; means for using the collected data to analyze emotional data in real time and adjust music, lighting, and temperature; and means for presenting appropriate information and re-suggesting a ride route based on the collected emotional data. This maximizes the effectiveness of interactions at networking events and improves passenger comfort in autonomous vehicles.

[1050] A "generative AI model" is an artificial intelligence algorithm that automatically generates participant profiles from responses to surveys and questions.

[1051] A "self-introduction profile" is an introduction that includes the participant's personal information, interests, and goals, automatically generated by a generative AI model.

[1052] "Natural language processing technology" is an information processing technology for understanding, analyzing, and generating human language.

[1053] "Real-time tracking" is a technology that collects and tracks current information in a timely manner.

[1054] "Emotional data" refers to data that represents the emotional state of a participant or passenger, including positive, negative, neutral, and other emotional states.

[1055] "Location information" is data used to identify the current location of a person or object.

[1056] "Purpose of ride" refers to the passenger's main purpose or reason for using an autonomous vehicle.

[1057] "Adjusting music, lighting, and temperature" refers to a means of enhancing passenger comfort by appropriately setting and changing environmental elements inside an autonomous vehicle.

[1058] "Information presentation means" refers to a means for providing passengers with appropriate information visually or audibly.

[1059] "Route re-proposition" is a means of reconsidering and proposing the optimal route based on the current riding situation and destination.

[1060] The system according to the present invention can facilitate effective matching and interaction between participants at networking events, and can also improve the comfort of passengers in autonomous vehicles.

[1061] Preparation Phase

[1062] User Actions

[1063] Users log in to the system and register to participate in the event. After registering, they answer a questionnaire displayed by the system. The questionnaire includes questions about their interests, work, skills, networking goals, riding goals, and even their emotional state when introducing themselves.

[1064] Device behavior

[1065] The terminal receives the user's input data and transmits it to the server.

[1066] Server Operation

[1067] The server runs a generative AI model based on the received response data to automatically generate a self-introduction profile. The generated profile also includes emotional data generated by an emotion engine. This profile is then sent to the user's device, where the user can review and modify it as needed.

[1068] Automatic group creation phase

[1069] Server Operation

[1070] The server stores all participants' self-introduction profiles in a database, which are then analyzed using natural language processing (NLP) techniques and an emotion engine to identify participants' interests, goals, and emotional states.

[1071] Server Operation

[1072] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm. The generated group information and session schedule are sent to each user's device.

[1073] User Actions

[1074] Before the event, the user checks his / her session schedule on the terminal.

[1075] Event Phase

[1076] User Actions

[1077] On the day of the event, users check the session schedule on their device and head to their designated group or table.

[1078] Device behavior

[1079] The device tracks users' location and emotional state data in real time, and also collects data based on conversations and interests during the event.

[1080] Server Operation

[1081] The server analyzes the collected location information, conversation data, and emotion data to understand the current group arrangement and the progress of the conversation.

[1082] Server Operation

[1083] The server detects when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generates optimal new networking proposals to resolve these issues.

[1084] Device behavior

[1085] The terminal notifies the user of the new proposals that have been generated.

[1086] User Actions

[1087] The user follows the proposed new arrangement and moves to the specified new table or group.

[1088] Specific examples

[1089] For example, if a user answers a questionnaire when registering for an event with "I'm interested in marketing and work as an IT engineer" and selects "expecting" as their emotion, the device will send that data to the server, which will then use the generative AI model and emotion engine to generate a self-introduction profile for "an IT engineer with extensive experience in marketing" and provide it to the user with the profile including their emotion data.

[1090] On the day of the event, if a user participates in a session and their emotional state becomes negative, the system will detect this in real time and suggest more appropriate networking partners. The user can then follow the suggestions and move to a new table or group, ensuring effective networking.

[1091] Example of a prompt sentence for an application example

[1092] For example, a prompt for improving comfort in a self-driving vehicle:

[1093] "My current objective is a work presentation. My emotional state is tense."

[1094] This invention allows for maximizing the social impact of networking events and improving passenger comfort in autonomous vehicles.

[1095] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1096] Step 1:

[1097] User Actions

[1098] Users log in to the system and register to participate in the event. As input, they provide information in the form of a questionnaire about their interests, jobs, skills, networking goals, riding goals, emotional state, etc. The output is that this data is sent to the terminal.

[1099] Step 2:

[1100] Device behavior

[1101] The terminal receives the user's input data and sends it to the server. It receives the user's survey results as input and generates a data package to send to the server as output.

[1102] Step 3:

[1103] Server Operation

[1104] The server runs a generative AI model based on the received user data to generate a self-introduction profile. The input is the user's questionnaire response data, and the output is the generated self-introduction profile and emotion data. Specifically, the AI ​​model analyzes the text data using natural language processing technology and generates an appropriate profile.

[1105] Step 4:

[1106] Server Operation

[1107] The generated self-introduction profile and emotion data are sent to the user's terminal. The input is the generated self-introduction profile and emotion data, and this is sent to the user's terminal as output.

[1108] Step 5:

[1109] User Actions

[1110] The user checks the received profile and modifies it if necessary. The input is the self-introduction profile that was just received, and the output is the modified profile. This modified data is sent back to the server.

[1111] Step 6:

[1112] Server Operation

[1113] The server stores the self-introduction profiles of all participants in a database and analyzes them using natural language processing technology and an emotion engine. The input is the self-introduction profiles of all participants, and the output is data on each participant's interests, goals, and emotional state.

[1114] Step 7:

[1115] Server Operation

[1116] Based on the analysis results, the server uses an optimal matching algorithm to group participants by purpose and emotional state. The input is the analyzed participant data, and the output is optimal group information and session schedule.

[1117] Step 8:

[1118] Server Operation

[1119] The generated group information and session schedule are sent to each user's terminal. The input is the group information and session schedule, and the output is to send them to the user's terminal.

[1120] Step 9:

[1121] User Actions

[1122] Before an event, a user checks their own session schedule on a terminal. The input is the session schedule sent from the server, and the output is to view and check it.

[1123] Step 10:

[1124] Device behavior

[1125] On the day of the event, the device tracks the user's location and emotional state data in real time. The input is the user's current location and emotional state, and the output is the data tracking them in real time.

[1126] Step 11:

[1127] Server Operation

[1128] The server analyzes the collected location information, conversation data, and emotion data to understand the current group arrangement and conversation progress. The input is the data collected in real time, and the output is the analysis results.

[1129] Step 12:

[1130] Server Operation

[1131] The server detects when a particular group is inactive, when topic agreement is low, or when a particular participant is in a negative emotional state, and generates optimal new networking proposals based on this.The input is the analyzed group data and emotional data, and the output is new networking proposals.

[1132] Step 13:

[1133] Device behavior

[1134] The terminal notifies the user of the new proposals it generates. The input is the networking proposal sent by the server, and the output is the notification to the user.

[1135] Step 14:

[1136] User Actions

[1137] The user moves to the specified new table or group according to the proposed new arrangement. The input is the new group arrangement information, and the output is the behavior according to that instruction.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] [Third embodiment]

[1142] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1143] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1144] 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).

[1145] 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.

[1146] 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.

[1147] 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).

[1148] 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.

[1149] 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.

[1150] 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.

[1151] 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.

[1152] 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.

[1153] 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."

[1154] Overall system overview

[1155] This invention is a system for streamlining networking events. Participants can generate self-introduction profiles by simply answering a few simple questions in advance, and dynamically create and coordinate optimal groups during the event. The system is divided into three main phases: a pre-preparation phase, an automatic group creation phase, and an event-in-progress phase.

[1156] Preparation Phase

[1157] User Action:

[1158] To participate in a networking event, users log in to the system and apply for participation. After logging in, they answer a questionnaire displayed by the system, which includes information about their job, their skills, interests, and the purpose of networking.

[1159] Device behavior:

[1160] It receives user input data and sends it to the server.

[1161] Server behavior:

[1162] The server runs a generative AI model based on the input data to automatically generate a self-introduction profile. The generated profile information is sent to the user's device, where the user can review the content and make any necessary edits.

[1163] Automatic group creation phase

[1164] Server behavior:

[1165] Self-introduction profile information for all participants is stored in a database. The stored profile information is analyzed using natural language processing (NLP) technology to identify participants' interests and goals. Based on the analysis results, an optimal matching algorithm is used to group participants by goal. The generated group information is sent to each user's device on the day of the event.

[1166] User Action:

[1167] Check your session schedule on your device before the event.

[1168] Event Phase

[1169] User Action:

[1170] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[1171] Device behavior:

[1172] It tracks users' location information in real time, collects data based on their conversations and interests, and sends it to a server.

[1173] Server behavior:

[1174] The system analyzes the collected location and conversation data to understand the current group arrangement and conversation progress. It detects when a particular group is inactive or has low topic agreement, and generates optimal new networking suggestions. These suggestions are sent to the user's device, notifying them of new group and table arrangements.

[1175] Specific examples

[1176] 1. Specific examples of the preparation phase

[1177] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." When the device sends the data to the server, the server uses a generative AI model to generate a self-introduction profile for the user, describing him as an "IT engineer with a strong marketing background," and provides it to the user.

[1178] 2. Example of the automatic group creation phase

[1179] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[1180] 3. Specific examples of event phases

[1181] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[1182] As described above, this system maximizes the networking effect of participants throughout the entire event process, contributing to the success of the event.

[1183] The processing flow will be explained below.

[1184] Preparation Phase

[1185] Step 1:

[1186] User:

[1187] Log in to the event system and register.

[1188] Step 2:

[1189] server:

[1190] Users are presented with a survey that includes questions about the participant's job, skills, interests, and networking goals.

[1191] Step 3:

[1192] User:

[1193] Answer the survey and submit your answers.

[1194] Step 4:

[1195] Device:

[1196] The submitted questionnaire responses are relayed to the server.

[1197] Step 5:

[1198] server:

[1199] A generative AI model is run based on the received response data to generate a self-introduction profile.

[1200] Step 6:

[1201] server:

[1202] Send the generated profile to the device.

[1203] Step 7:

[1204] User:

[1205] Check your profile and make any necessary changes.

[1206] Automatic group creation phase

[1207] Step 8:

[1208] server:

[1209] All participants' self-introduction profiles are stored in a database.

[1210] Step 9:

[1211] server:

[1212] The stored profile information is analyzed using natural language processing (NLP) technology to identify each participant's interests and networking goals.

[1213] Step 10:

[1214] server:

[1215] Based on the analysis results, participants are grouped by purpose using an optimal matching algorithm.

[1216] Step 11:

[1217] server:

[1218] The grouped information and a session schedule are generated and transmitted to each user's terminal.

[1219] Event Phase

[1220] Step 12:

[1221] User:

[1222] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[1223] Step 13:

[1224] Device:

[1225] It tracks users' locations in real time and collects data based on their conversations and interests.

[1226] Step 14:

[1227] Device:

[1228] The collected data is sent to the server.

[1229] Step 15:

[1230] server:

[1231] The collected location information and conversation data is analyzed to understand the current group arrangement and conversation progress.

[1232] Step 16:

[1233] server:

[1234] It detects when certain groups are inactive or have low topical alignment and generates new networking suggestions.

[1235] Step 17:

[1236] server:

[1237] Send the new proposal to the device.

[1238] Step 18:

[1239] Device:

[1240] Notify users of new group and table placements.

[1241] Step 19:

[1242] User:

[1243] Follow the proposed new arrangement and move to your designated new table or group.

[1244] This series of steps allows for efficient and beneficial networking even in a limited amount of time.

[1245] Example 1

[1246] 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."

[1247] To enable participants to interact more effectively at networking events, it is important to create detailed profiles in advance and meet suitable people during the event. However, with conventional systems, creating self-introduction profiles and grouping participants is often done manually, which is time-consuming and labor-intensive and may not result in optimal matching. It is also difficult to grasp and adjust real-time interaction situations during the event, making it difficult for participants to network effectively.

[1248] 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.

[1249] In this invention, the server includes: means for using a generative AI model in which participants answer simple questions in advance and generate a self-introduction profile based on the answers; means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose and interests of each participant; means for tracking participants' location information and conversation content in real time during the event to optimize the progress of the event; and means for monitoring specific activity levels within groups and generating and notifying new networking suggestions in the event of inactive groups or low topic matches. This allows participants to easily create effective self-introduction profiles and continue to meet suitable people even during the event.

[1250] A "generative AI model" is a program that uses artificial intelligence technology to automatically generate a self-introduction profile based on participants' responses.

[1251] "Natural language processing technology" is a field of computer science that deals with understanding and processing human language, and is a technology used to analyze and generate text data.

[1252] A "self-introduction profile" is a digital document that organizes personal information about participants, including their job, skills, interests, concerns, and networking goals.

[1253] The "group generation method" is an algorithm that automatically creates appropriate groups based on participants' self-introduction profiles and interests according to the purpose of networking.

[1254] "Location Information" means data obtained using GPS or other technologies that indicates where a Participant is located within an Event.

[1255] "Conversation content" is data including topics and keywords of verbal communication exchanged between participants during the event.

[1256] "Real-time tracking" refers to a system that instantly acquires participants' location information and conversation content while the event is in progress, sends it to a server, and dynamically analyzes it.

[1257] "Networking Suggestions" are notifications from the system that recommend new suitable networking partners and groups based on participants' current group placement and conversation content.

[1258] The "means for monitoring specific activity levels within a group" refers to an algorithm that monitors the activity status and conversation progress of participants within a group and evaluates the activity level of the group.

[1259] This invention is a system for streamlining networking events, allowing participants to generate self-introduction profiles by answering simple questions in advance, and dynamically creating and adjusting optimal groups during the event.

[1260] Overall system overview

[1261] The system combines generative AI models and natural language processing technology to automatically generate participant profiles and dynamically create and coordinate groups during the event. The system is basically divided into the following phases: pre-preparation phase, automatic group creation phase, and in-event phase.

[1262] Preparation Phase

[1263] User Actions

[1264] To participate in an event, users log in to the system and apply for participation. After logging in, they answer a questionnaire that appears. This questionnaire includes questions about their job, their skills, interests, and networking goals.

[1265] Device behavior

[1266] The terminal receives the user's input data and sends it to the server.

[1267] Server Operation

[1268] The server uses a generative AI model (e.g., GPT-4) to generate a self-introduction profile from the user's input data. The generated profile information is sent to the device, where the user can review the content and make any necessary corrections.

[1269] Automatic group creation phase

[1270] Server Operation

[1271] The server stores the self-introduction profile information of all participants in a database (e.g., MySQL). It then analyzes the data using natural language processing (NLP) technology (e.g., SpaCy) to identify participants' interests and goals. Based on this information, it uses an optimal matching algorithm (e.g., K-means clustering) to group participants by purpose. The generated group information is sent to each user's device.

[1272] Event Phase

[1273] User Actions

[1274] On the day of the event, users check the session schedule on their device and head to their designated group or table.

[1275] Device behavior

[1276] The device tracks the user's location in real time using GPS, collects conversation content through a microphone, and sends the data to a server.

[1277] Server Operation

[1278] The server analyzes the collected data to understand the group placement and conversation progress, and if a particular group is inactive or has low topic agreement, it generates optimal new networking proposals and sends them to the user's device.

[1279] Specific examples

[1280] 1. Specific examples of the preparation phase

[1281] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." When the device sends the data to the server, the server uses a generative AI model (e.g., "GPT-4") to generate a self-introduction profile for the user, describing the user as an "IT engineer with expertise in marketing," and provides it to the user.

[1282] 2. Example of the automatic group creation phase

[1283] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[1284] 3. Specific examples of event phases

[1285] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[1286] Prompt Sentence Examples

[1287] "My area of ​​interest is marketing and I currently work as an IT engineer. Please create a profile to introduce myself."

[1288] Through these phases, the present invention can maximize the networking effect of participants and improve the outcome of the event.

[1289] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1290] Step 1: Log in and complete the survey

[1291] User Actions

[1292] Users log in to the system and answer a questionnaire. After entering their ID and password on the login page and being authenticated, the questionnaire screen appears. Users answer questions about their work, skills, interests, networking goals, etc.

[1293] Device behavior

[1294] The terminal receives the user's input data from the input form, performs error checks (e.g., checking required fields, checking data format), and then sends the data to the server in JSON format.

[1295] Input: Data entered by the user into the survey form (e.g., job, skills, interests)

[1296] Output: Data after error checking is sent to the server

[1297] Step 2: Create your profile

[1298] Server Operation

[1299] The server uses a generative AI model (e.g., GPT-4) to generate a self-introduction profile from the received input data. The generated profile reflects the user's interests and skills. Natural language processing technology is used to generate the profile.

[1300] Input: User survey data sent from the device

[1301] Data processing: AI models analyze data, perform natural language processing, and generate profiles

[1302] Output: Generated self-introduction profile

[1303] Device behavior

[1304] The generated profile information is sent to the user's device, which displays the profile and prompts the user to confirm and make any necessary corrections.

[1305] Input: Self-introduction profile sent from the server

[1306] Output: The profile screen that the user sees

[1307] Step 3: Check and modify your profile

[1308] User Actions

[1309] The user checks their self-introduction profile and makes any necessary corrections. The corrections are then sent back to the server.

[1310] Input: Initially generated profile

[1311] Output: Corrected profile data

[1312] Device behavior

[1313] The terminal receives the user's modifications and sends them back to the server.

[1314] Input: Corrected profile data

[1315] Output: Modifications sent to the server

[1316] Step 4: Store profile information in a database

[1317] Server Operation

[1318] The server stores the modified profile in a database using a fast relational database (e.g., MySQL).

[1319] Input: Corrected profile data

[1320] Data processing: Insert / update data into database based on data format

[1321] Output: Profile information stored in the database

[1322] Step 5: Analyze and group profiles

[1323] Server Operation

[1324] The server analyzes the stored profile information using natural language processing (NLP) techniques (e.g., SpaCy) to identify participants' interests and goals, and then groups them based on the identified information using an optimal matching algorithm (e.g., K-means clustering).

[1325] Input: Profile information stored in the database

[1326] Data processing: Natural language processing technology is used to identify interests and purposes, and matching algorithms are used to group them.

[1327] Output: Group information

[1328] Step 6: Generate and distribute session schedules

[1329] Server Operation

[1330] The server generates a session schedule for the event based on the generated group information, and transmits the session schedule to each user's device.

[1331] Input: Group information

[1332] Data processing: Create a session schedule using a schedule generation algorithm

[1333] Output: Generated session schedule

[1334] Device behavior

[1335] The terminal receives the session schedule sent from the server and displays it to the user.

[1336] Input: Session schedule sent from the server

[1337] Output: The schedule screen displayed to the user

[1338] Step 7: Collect location and conversation data during the event

[1339] Device behavior

[1340] The device tracks the user's location in real time using GPS and collects conversations through a microphone, which is then periodically sent to a server.

[1341] Input: User location and conversation data

[1342] Output: Collected data is sent to the server

[1343] Step 8: Data analysis and networking proposals

[1344] Server Operation

[1345] The server analyzes the collected location information and conversation data to evaluate the activity level of the group and the degree of topic agreement. If the group is inactive or the degree of topic agreement is low, it generates new networking suggestions and notifies the user's device.

[1346] Input: Location and conversation data

[1347] Data processing: Analyze the data using an analytical algorithm to evaluate activity and consistency

[1348] Output: Networking suggestions are sent to the user's device.

[1349] Step 9: Implementing a Networking Proposal

[1350] User Actions

[1351] Users will move to new groups and tables according to new networking suggestions notified to their devices, resulting in more effective networking.

[1352] Input: Networking suggestions from the server

[1353] Output: Move to new group or table

[1354] This step allows the system to maximize the networking effect of participants throughout the event, contributing to the success of the event.

[1355] (Application example 1)

[1356] 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."

[1357] In conventional networking events, it is difficult to efficiently match participants based on their goals and interests. Furthermore, while real-time optimization of participant placement and progress, as well as dynamic group adjustment, is required during the event, no method exists to achieve this. The present invention aims to solve these problems and maximize the effectiveness of networking events.

[1358] 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.

[1359] In this invention, the server includes a means for using a generative AI model that generates a self-introduction profile based on participants' answers to simple questions in advance, a means for collecting and analyzing the self-introduction profiles generated by the generative AI model and automatically generating groups based on the goals and interests of each participant, a means for tracking participants' location information and conversation content in real time during the event and optimizing and dynamically adjusting the placement and progress of the event, and a means for participants to participate in the virtual networking event using smartphones, smart glasses, or head-mounted displays, thereby maximizing the effectiveness of the networking event and enabling participants to be matched with each other and their placement to be adjusted in real time.

[1360] A "networking event" is an event where participants gather to exchange information and explore business opportunities.

[1361] "Quick Questions" are a set of short, easy-to-answer questions used to understand participants' basic information, interests, skills, and goals.

[1362] A "self-introduction profile" is electronic data that is generated based on information provided by participants in advance and comprehensively indicates a person's characteristics, interests, skills, goals, etc.

[1363] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to make predictions or generate results from input information.

[1364] A "means" is a method or process used to achieve a particular function or purpose.

[1365] "Collection" is the act of gathering data or information in one place.

[1366] "Analysis" is the process of examining collected data and information in detail to derive specific patterns and meanings.

[1367] "Purpose" refers to the specific reason participants are attending the networking event or what they hope to achieve.

[1368] "Interests" are topics or themes that participants have a personal interest in.

[1369] "Automatic group generation" refers to using artificial intelligence techniques to categorize participants into appropriate groups without manual intervention.

[1370] "Location information" is geographical data that indicates where a participant is currently located.

[1371] "Conversation content" refers to the words and topics exchanged between participants during the event.

[1372] "Real-time tracking" refers to the instantaneous monitoring and recording of ongoing situations.

[1373] "Optimizing progress" means adjusting the flow of events and plans to proceed most efficiently.

[1374] "Dynamic adjustment" means changing the settings and plans as appropriate depending on the event situation and the status of the participants.

[1375] A "virtual networking event" is an event held in an online environment for the purpose of networking.

[1376] A "smartphone" is a highly functional mobile phone that can connect to the Internet and run applications.

[1377] "Smart glasses" are glasses-type electronic devices with a built-in display that displays information.

[1378] A "head-mounted display" is a device that displays images by being worn on the head.

[1379] Overall system overview

[1380] The present invention is a system for streamlining networking events, allowing participants to create self-introduction profiles by simply answering simple questions in advance, and dynamically creating and adjusting optimal groups during the event, thereby maximizing the networking effect of participants throughout the entire event process.

[1381] System Configuration

[1382] The system is divided into three main phases:

[1383] 1. Preparation Phase

[1384] 2. Automatic group creation phase

[1385] 3. Event Phase

[1386] Preparation Phase

[1387] User Action:

[1388] To participate in a networking event, users log in to the system and apply for participation. After logging in, they answer a questionnaire displayed by the system, which includes information about their job, their skills, interests, and the purpose of networking.

[1389] Device behavior:

[1390] It receives user input data and sends it to the server.

[1391] Server behavior:

[1392] The server runs a generative AI model based on the input data to automatically generate a self-introduction profile. The generated profile information is sent to the user's device, where the user can review the content and make any necessary edits.

[1393] Automatic group creation phase

[1394] Server behavior:

[1395] Self-introduction profile information for all participants is stored in a database. The stored profile information is analyzed using natural language processing (NLP) technology to identify participants' interests and goals. Based on the analysis results, an optimal matching algorithm is used to group participants by goal. The generated group information is sent to each user's device on the day of the event.

[1396] User Action:

[1397] Check your session schedule on your device before the event.

[1398] Event Phase

[1399] User Action:

[1400] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[1401] Device behavior:

[1402] It tracks users' location information in real time, collects data based on their conversations and interests, and sends it to a server.

[1403] Server behavior:

[1404] The system analyzes the collected location and conversation data to understand the current group arrangement and conversation progress. It detects when a particular group is inactive or has low topic agreement, and generates optimal new networking suggestions. These suggestions are sent to the user's device, notifying them of new group and table arrangements.

[1405] Hardware and software used

[1406] Hardware:

[1407] Smartphones, smart glasses, head-mounted displays

[1408] software:

[1409] Python, OpenAI API, Geopy

[1410] Specific examples

[1411] 1. Examples of the preparatory phase:

[1412] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." The server uses a generative AI model to generate a self-introduction profile for the user, describing him as an "IT engineer with a strong marketing background," and provides it to the user.

[1413] 2. Example of automatic group creation phase:

[1414] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[1415] 3. Examples of event phases:

[1416] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[1417] Examples of prompt statements

[1418] text

[1419] User information: Interested in marketing, working as an IT engineer

[1420] Use this information to create your profile.

[1421] The above is a specific embodiment of the present invention. This system maximizes the effectiveness of networking events, enabling participants to be matched and allocated in real time.

[1422] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1423] Step 1:

[1424] To participate in an event, users log in to the system and answer a questionnaire. The user's input data includes information about their job, skills, interests, and networking goals. This input data is sent from the terminal to the server.

[1425] Step 2:

[1426] The server runs a generative AI model based on the received input data to generate a self-introduction profile. The server then sends the generated profile to the user's device, allowing the user to review the content and make any necessary corrections. Input: Survey response data. Output: Self-introduction profile.

[1427] Step 3:

[1428] The server stores the self-introduction profile information of all participants in a database. The server analyzes the stored profile information using natural language processing (NLP) techniques to identify participants' interests and goals. Input: Self-introduction profile. Output: Analysis results.

[1429] Step 4:

[1430] The server uses the optimal matching algorithm based on the analysis results to group participants by purpose. The server sends the generated group information to each user's device on the day of the event. Input: Analysis results. Output: Group information.

[1431] Step 5:

[1432] Before the event, users check their own session schedules on their terminals. The terminals display the user's session schedule based on the group information received from the server. Input: Group information. Output: Session schedule.

[1433] Step 6:

[1434] On the day of the event, users check the session schedule on their device and head to their designated group or table. The device tracks the user's location information in real time and sends it to the server. Input: User's location information. Output: Real-time data sent to the server.

[1435] Step 7:

[1436] The server analyzes the collected location information and conversation data to understand the current group arrangement and conversation progress. If a particular group is inactive or has low topic agreement, it detects this and generates optimal new networking proposals. Input: Location information, conversation data. Output: Networking proposals.

[1437] Step 8:

[1438] The server sends a new networking proposal to the user's terminal, notifying them of the new group and table placement. The user moves to the specified new table according to the new proposal and continues networking. Input: Networking proposal. Output: New group placement notification.

[1439] 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.

[1440] Overall system overview

[1441] This invention is a system for promoting efficient matching and interaction among participants at networking events, incorporating an emotion engine to improve accuracy. Participants answer simple questions in advance, and optimal matching is performed based on an automatically generated self-introduction profile. Furthermore, participants' emotional data is tracked in real time during the event, and necessary adjustments are made.

[1442] Preparation Phase

[1443] User Action:

[1444] Users log in to the system and register to attend the event. After registering, they answer a questionnaire displayed by the system, which includes questions about their job, skills, interests, networking goals, and even their emotional state when introducing themselves.

[1445] Device behavior:

[1446] It receives user input data and sends it to the server.

[1447] Server behavior:

[1448] The server runs a generative AI model based on the received response data to automatically generate a self-introduction profile. The generated profile also includes emotional data generated by an emotion engine. This profile is then sent to the user's device, where the user can review the content and make any necessary changes.

[1449] Automatic group creation phase

[1450] Server behavior:

[1451] All participants' self-introductory profiles are stored in a database, which is then analyzed using natural language processing (NLP) techniques and an emotion engine to identify participants' interests, goals, and emotional states.

[1452] Server behavior:

[1453] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm. The generated group information and session schedule are sent to each user's device.

[1454] User Action:

[1455] Check your session schedule on your device before the event.

[1456] Event Phase

[1457] User Action:

[1458] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[1459] Device behavior:

[1460] It tracks users' location and emotional state data in real time, and also collects data based on conversations and interests during the event.

[1461] Device behavior:

[1462] All collected data is sent to the server.

[1463] Server behavior:

[1464] The collected location information, conversation data, and emotion data are analyzed to understand the current group arrangement and the progress of the conversation.

[1465] Server behavior:

[1466] It detects when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generates optimal new networking suggestions to solve these problems.

[1467] Server behavior:

[1468] Send the new proposal to the device.

[1469] Device behavior:

[1470] Notify users of new group and table placements.

[1471] User Action:

[1472] Follow the proposed new arrangement and move to your designated new table or group.

[1473] Specific examples

[1474] 1. Specific examples of the preparation phase

[1475] A user registers with the system to participate in an event, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The device sends the data to the server, which uses the generative AI model and emotion engine to generate a self-introduction profile for "an IT engineer with a deep understanding of marketing," and provides it to the user with the profile including emotion data.

[1476] 2. Example of the automatic group creation phase

[1477] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account participants' emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[1478] 3. Specific examples of event phases

[1479] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests more suitable people. Based on this suggestion, the user moves to the designated new table, enabling more effective networking.

[1480] This system will maximize the networking effect of participants throughout the entire event process, contributing to the success of the event.

[1481] The processing flow will be explained below.

[1482] Preparation Phase

[1483] Step 1:

[1484] User:

[1485] Log in to the event system and register to participate in the event.

[1486] Step 2:

[1487] server:

[1488] Users are presented with a survey that includes questions about their job, skills, interests, networking goals, and emotional state.

[1489] Step 3:

[1490] User:

[1491] Answer the survey and submit your answers.

[1492] Step 4:

[1493] Device:

[1494] The submitted questionnaire responses are relayed to the server.

[1495] Step 5:

[1496] server:

[1497] A generative AI model is run based on the received response data to automatically generate a self-introduction profile.

[1498] Step 6:

[1499] server:

[1500] An emotion engine is used to add emotion data to the generated profile.

[1501] Step 7:

[1502] server:

[1503] Send the completed profile to the device.

[1504] Step 8:

[1505] User:

[1506] Check your profile and make any necessary changes.

[1507] Automatic group creation phase

[1508] Step 9:

[1509] server:

[1510] The self-introduction profiles and emotional data of all participants are stored in a database.

[1511] Step 10:

[1512] server:

[1513] The stored profile information is analyzed using natural language processing (NLP) technology and an emotion engine to identify each participant's interests, goals, and emotional state.

[1514] Step 11:

[1515] server:

[1516] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm.

[1517] Step 12:

[1518] server:

[1519] The grouped information and a session schedule are generated and transmitted to each user's terminal.

[1520] Event Phase

[1521] Step 13:

[1522] User:

[1523] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[1524] Step 14:

[1525] Device:

[1526] It tracks users' location and emotional state data in real time, and collects data based on their conversations and interests.

[1527] Step 15:

[1528] Device:

[1529] All collected data is sent to the server.

[1530] Step 16:

[1531] server:

[1532] The collected location information, conversation data, and emotion data are analyzed to understand the current group arrangement and the progress of the conversation.

[1533] Step 17:

[1534] server:

[1535] Detect when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generate optimal new networking proposals to address these challenges.

[1536] Step 18:

[1537] server:

[1538] Send the new proposal to the device.

[1539] Step 19:

[1540] Device:

[1541] Notify users of new group and table placements.

[1542] Step 20:

[1543] User:

[1544] Follow the proposed new arrangement and move to your designated new table or group.

[1545] Specific examples

[1546] Specific examples of the preparation phase

[1547] A user logs in to the system to participate in an event, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The user's device sends the data to the server, which uses the generative AI model and emotion engine to generate a self-introduction profile called "IT engineer with expertise in marketing," and provides it to the user with emotional data attached.

[1548] A concrete example of the automatic group creation phase

[1549] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account participants' emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[1550] Specific examples of phases during an event

[1551] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests more suitable people. Based on this suggestion, the user moves to the designated new table, enabling more effective networking.

[1552] Example 2

[1553] 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."

[1554] Promoting effective matching and interaction between participants is a key challenge at modern networking events. Traditional methods often fail to match participants based on their interests and goals, resulting in stagnant interactions and ineffective networking. Furthermore, they often fail to take into account participants' emotional states, often resulting in an unsatisfactory experience. Therefore, a system is needed that can grasp participants' emotional states and interaction situations in real time and provide optimal networking.

[1555] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for using a generative AI model in which participants answer simple questions in advance and generate a self-introduction profile based on the answers; a means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose, interests, and emotional state of each participant; a means for tracking the location information, conversation content, and emotional state of participants in real time during the event and optimizing the placement and progress of the event; and a means for generating an optimal new networking proposal and relocating participants when a problem is detected. This enables effective matching and promotion of interaction between participants.

[1556] A "generative AI model" is an algorithm used by a computer to automatically generate a self-introduction profile based on a large dataset.

[1557] A "profile" is information about a participant that describes their occupation, skills, interests, networking goals, and emotional state.

[1558] An "emotion engine" is a technology for extracting and evaluating emotions from text and audio data.

[1559] "Natural language processing technology" is a technology that allows computers to understand and process the language that humans use on a daily basis.

[1560] The "group generation means" is a function within the system that automatically creates optimal groups based on participants' goals, interests, and emotional states.

[1561] "Location information" is information that indicates the geographical location of a participant within the event venue.

[1562] "Conversation content" refers to the content of the dialogue between participants, and is text or audio data.

[1563] "Real-time tracking" means instantly tracking ongoing situations and collecting and analyzing data.

[1564] "Networking suggestions" are suggestions for new group and table arrangements based on participants' interests and emotional state.

[1565] "Optimizing" means maximizing the performance and efficiency of a system.

[1566] This invention is a system for facilitating efficient matching and interaction among participants at networking events, and uses a generative AI model and an emotion engine to improve accuracy. Specific embodiments of this system are described below.

[1567] Overall system overview

[1568] This invention allows users participating in a networking event to answer simple questions in advance, and then automatically generates a self-introduction profile based on the answers using a generative AI model. The generated profile includes emotional data for optimal matching. Furthermore, during the event, the system tracks users' location information and emotional state in real time and makes networking suggestions as needed.

[1569] Hardware and Software Configuration

[1570] 1. Server

[1571] The server receives the survey data and runs a generative AI model (e.g., OpenAI GPT-3). The server uses an emotion engine to extract emotional data and generate profiles. The server then stores all participant profiles in a database and uses natural language processing (NLP) techniques (e.g., NLTK and SpaCy) to analyze the profiles and generate optimal groups. The server analyzes the stored data and data collected in real time, and generates optimal networking suggestions if problems are detected.

[1572] 2. Terminal

[1573] The device primarily functions as an interface with the user, transmitting user input data to the server. During the event, the device also collects the user's location information (e.g., GPS) and emotional state data (e.g., biometric sensors) and transmits them to the server. The device then displays the data and suggestions sent from the server to the user.

[1574] Specific examples

[1575] Specific examples of the preparation phase

[1576] A user registers with the system, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The device sends this data to the server, which uses a generative AI model and emotion engine to generate a self-introduction profile for the user, calling them "an IT engineer with a strong marketing background," and provides this profile to the user, including their emotion data.

[1577] Example prompt sentence:

[1578] "Generate a self-introduction profile based on the user's occupation, skills, interests, networking goals and emotional state."

[1579] A concrete example of the automatic group creation phase

[1580] The server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[1581] Specific examples of phases during an event

[1582] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests new, more suitable people. The user follows the suggestions and moves to a new table, resulting in more effective networking.

[1583] In this way, the system can consistently collect and analyze data, providing optimal networking and contributing to the success of the event.

[1584] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1585] Step 1:

[1586] A user logs in to the system and registers to participate in an event. The terminal sends the input data to the server for authentication using the "email address" and "password" entered by the user. The server verifies the received login information, and if authentication is successful, redirects the user to the dashboard screen. The input in this step is the user's login information, and the output is the dashboard screen.

[1587] Step 2:

[1588] The user answers the displayed questionnaire. When the user answers questions about "job content," "skills," "interests," "networking goals," and "emotional state," the device records this answer data and sends it to the server. The server stores the received questionnaire data. The input in this step is the user's questionnaire answers, and the output is the stored questionnaire data.

[1589] Step 3:

[1590] The server runs a generative AI model using the received survey data. Based on the prompt, the "generative AI model" generates a self-introduction profile, and then uses an emotion engine to extract emotional data and include it in the profile. For example, the prompt might read, "Generate a self-introduction profile based on the user's occupation, skills, interests, networking goals, and emotional state." The input in this step is the survey data and the prompt, and the output is a self-introduction profile.

[1591] Step 4:

[1592] The server sends the generated self-introduction profile to the user's device. The user can review the profile on the device and modify it if necessary. The input in this step is the generated profile, and the output is the profile provided to the user.

[1593] Step 5:

[1594] The server stores the self-introduction profiles of all participants in a database. It uses natural language processing technology (e.g., NLTK or SpaCy) and an emotion engine to analyze participants' interests, goals, and emotional states from the stored profile information. The input in this step is the stored profile information, and the output is the analyzed data of interests, goals, and emotional states.

[1595] Step 6:

[1596] Based on the analysis results, the server uses an optimal matching algorithm (e.g., "K-means clustering") to group participants by purpose and emotional state. The generated group information and session schedule are sent to the user's device. The input in this step is the analysis results, and the output is the grouped information and session schedule.

[1597] Step 7:

[1598] On the day of the event, users check the session schedule on their devices and head to their assigned groups and tables. As users move, the devices collect location information (e.g., GPS) and emotional state data (e.g., biometric sensors) in real time and send them to the server. The inputs in this step are the user's movements and real-time data, and the output is the real-time data sent to the server.

[1599] Step 8:

[1600] The server analyzes the collected location, conversation, and emotion data to understand the current group arrangement and conversation progress. The server detects when a particular group is inactive, when there is low topic agreement, or when a particular participant is in a negative emotional state. The input in this step is the collected real-time data, and the output is the analysis results.

[1601] Step 9:

[1602] Based on the analysis results, the server generates an optimal new networking proposal to solve the problem and sends it to the user's device. The device notifies the user of this proposal, and the user moves to a new table or group specified based on the new proposal. The inputs in this step are the analysis results and the proposal generation algorithm, and the output is a new networking proposal provided to the user.

[1603] (Application example 2)

[1604] 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."

[1605] Conventional networking events and autonomous vehicles have faced challenges in providing optimal matching and comfort based on the emotional state and interests of participants and passengers. In particular, the lack of a mechanism for tracking and analyzing real-time emotional data and adjusting environmental settings based on this data has made it difficult to maximize the networking effect of participants and the comfort of passengers.

[1606] 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.

[1607] In this invention, the server includes: means for using a generative AI model that generates a self-introduction profile based on participants' answers to simple questions in advance; means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on each participant's purpose and interests; means for tracking participants' location information and conversation content in real time during the event to optimize the event layout and progress; means for collecting passengers' location information, emotional state, and purpose of the ride; means for using the collected data to analyze emotional data in real time and adjust music, lighting, and temperature; and means for presenting appropriate information and re-suggesting a ride route based on the collected emotional data. This maximizes the effectiveness of interactions at networking events and improves passenger comfort in autonomous vehicles.

[1608] A "generative AI model" is an artificial intelligence algorithm that automatically generates participant profiles from responses to surveys and questions.

[1609] A "self-introduction profile" is an introduction that includes the participant's personal information, interests, and goals, automatically generated by a generative AI model.

[1610] "Natural language processing technology" is an information processing technology for understanding, analyzing, and generating human language.

[1611] "Real-time tracking" is a technology that collects and tracks current information in a timely manner.

[1612] "Emotional data" refers to data that represents the emotional state of a participant or passenger, including positive, negative, neutral, and other emotional states.

[1613] "Location information" is data used to identify the current location of a person or object.

[1614] "Purpose of ride" refers to the passenger's main purpose or reason for using an autonomous vehicle.

[1615] "Adjusting music, lighting, and temperature" refers to a means of enhancing passenger comfort by appropriately setting and changing environmental elements inside an autonomous vehicle.

[1616] "Information presentation means" refers to a means for providing passengers with appropriate information visually or audibly.

[1617] "Route re-proposition" is a means of reconsidering and proposing the optimal route based on the current riding situation and destination.

[1618] The system according to the present invention can facilitate effective matching and interaction between participants at networking events, and can also improve the comfort of passengers in autonomous vehicles.

[1619] Preparation Phase

[1620] User Actions

[1621] Users log in to the system and register to participate in the event. After registering, they answer a questionnaire displayed by the system. The questionnaire includes questions about their interests, work, skills, networking goals, riding goals, and even their emotional state when introducing themselves.

[1622] Device behavior

[1623] The terminal receives the user's input data and transmits it to the server.

[1624] Server Operation

[1625] The server runs a generative AI model based on the received response data to automatically generate a self-introduction profile. The generated profile also includes emotional data generated by an emotion engine. This profile is then sent to the user's device, where the user can review and modify it as needed.

[1626] Automatic group creation phase

[1627] Server Operation

[1628] The server stores all participants' self-introduction profiles in a database, which are then analyzed using natural language processing (NLP) techniques and an emotion engine to identify participants' interests, goals, and emotional states.

[1629] Server Operation

[1630] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm. The generated group information and session schedule are sent to each user's device.

[1631] User Actions

[1632] Before the event, the user checks his / her session schedule on the terminal.

[1633] Event Phase

[1634] User Actions

[1635] On the day of the event, users check the session schedule on their device and head to their designated group or table.

[1636] Device behavior

[1637] The device tracks users' location and emotional state data in real time, and also collects data based on conversations and interests during the event.

[1638] Server Operation

[1639] The server analyzes the collected location information, conversation data, and emotion data to understand the current group arrangement and the progress of the conversation.

[1640] Server Operation

[1641] The server detects when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generates optimal new networking proposals to resolve these issues.

[1642] Device behavior

[1643] The terminal notifies the user of the new proposals that have been generated.

[1644] User Actions

[1645] The user follows the proposed new arrangement and moves to the specified new table or group.

[1646] Specific examples

[1647] For example, if a user answers a questionnaire when registering for an event with "I'm interested in marketing and work as an IT engineer" and selects "expecting" as their emotion, the device will send that data to the server, which will then use the generative AI model and emotion engine to generate a self-introduction profile for "an IT engineer with extensive experience in marketing" and provide it to the user with the profile including their emotion data.

[1648] On the day of the event, if a user participates in a session and their emotional state becomes negative, the system will detect this in real time and suggest more appropriate networking partners. The user can then follow the suggestions and move to a new table or group, ensuring effective networking.

[1649] Example of a prompt sentence for an application example

[1650] For example, a prompt for improving comfort in a self-driving vehicle:

[1651] "My current objective is a work presentation. My emotional state is tense."

[1652] This invention allows for maximizing the social impact of networking events and improving passenger comfort in autonomous vehicles.

[1653] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1654] Step 1:

[1655] User Actions

[1656] Users log in to the system and register to participate in the event. As input, they provide information in the form of a questionnaire about their interests, jobs, skills, networking goals, riding goals, emotional state, etc. The output is that this data is sent to the terminal.

[1657] Step 2:

[1658] Device behavior

[1659] The terminal receives the user's input data and sends it to the server. It receives the user's survey results as input and generates a data package to send to the server as output.

[1660] Step 3:

[1661] Server Operation

[1662] The server runs a generative AI model based on the received user data to generate a self-introduction profile. The input is the user's questionnaire response data, and the output is the generated self-introduction profile and emotion data. Specifically, the AI ​​model analyzes the text data using natural language processing technology and generates an appropriate profile.

[1663] Step 4:

[1664] Server Operation

[1665] The generated self-introduction profile and emotion data are sent to the user's terminal. The input is the generated self-introduction profile and emotion data, and this is sent to the user's terminal as output.

[1666] Step 5:

[1667] User Actions

[1668] The user checks the received profile and modifies it if necessary. The input is the self-introduction profile that was just received, and the output is the modified profile. This modified data is sent back to the server.

[1669] Step 6:

[1670] Server Operation

[1671] The server stores the self-introduction profiles of all participants in a database and analyzes them using natural language processing technology and an emotion engine. The input is the self-introduction profiles of all participants, and the output is data on each participant's interests, goals, and emotional state.

[1672] Step 7:

[1673] Server Operation

[1674] Based on the analysis results, the server uses an optimal matching algorithm to group participants by purpose and emotional state. The input is the analyzed participant data, and the output is optimal group information and session schedule.

[1675] Step 8:

[1676] Server Operation

[1677] The generated group information and session schedule are sent to each user's terminal. The input is the group information and session schedule, and the output is to send them to the user's terminal.

[1678] Step 9:

[1679] User Actions

[1680] Before an event, a user checks their own session schedule on a terminal. The input is the session schedule sent from the server, and the output is to view and check it.

[1681] Step 10:

[1682] Device behavior

[1683] On the day of the event, the device tracks the user's location and emotional state data in real time. The input is the user's current location and emotional state, and the output is the data tracking them in real time.

[1684] Step 11:

[1685] Server Operation

[1686] The server analyzes the collected location information, conversation data, and emotion data to understand the current group arrangement and conversation progress. The input is the data collected in real time, and the output is the analysis results.

[1687] Step 12:

[1688] Server Operation

[1689] The server detects when a particular group is inactive, when topic agreement is low, or when a particular participant is in a negative emotional state, and generates optimal new networking proposals based on this.The input is the analyzed group data and emotional data, and the output is new networking proposals.

[1690] Step 13:

[1691] Device behavior

[1692] The terminal notifies the user of the new proposals it generates. The input is the networking proposal sent by the server, and the output is the notification to the user.

[1693] Step 14:

[1694] User Actions

[1695] The user moves to the specified new table or group according to the proposed new arrangement. The input is the new group arrangement information, and the output is the behavior according to that instruction.

[1696] 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.

[1697] 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.

[1698] 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.

[1699] [Fourth embodiment]

[1700] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1701] 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.

[1702] 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).

[1703] 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.

[1704] 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.

[1705] 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).

[1706] 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.

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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."

[1713] Overall system overview

[1714] This invention is a system for streamlining networking events. Participants can generate self-introduction profiles by simply answering a few simple questions in advance, and dynamically create and coordinate optimal groups during the event. The system is divided into three main phases: a pre-preparation phase, an automatic group creation phase, and an event phase.

[1715] Preparation Phase

[1716] User Action:

[1717] To participate in a networking event, users log in to the system and apply for participation. After logging in, they answer a questionnaire displayed by the system, which includes information about their job, their skills, interests, and the purpose of networking.

[1718] Device behavior:

[1719] It receives user input data and sends it to the server.

[1720] Server behavior:

[1721] The server runs a generative AI model based on the input data to automatically generate a self-introduction profile. The generated profile information is sent to the user's device, where the user can review the content and make any necessary edits.

[1722] Automatic group creation phase

[1723] Server behavior:

[1724] Self-introduction profile information for all participants is stored in a database. The stored profile information is analyzed using natural language processing (NLP) technology to identify participants' interests and goals. Based on the analysis results, an optimal matching algorithm is used to group participants by goal. The generated group information is sent to each user's device on the day of the event.

[1725] User Action:

[1726] Check your session schedule on your device before the event.

[1727] Event Phase

[1728] User Action:

[1729] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[1730] Device behavior:

[1731] It tracks users' location information in real time, collects data based on their conversations and interests, and sends it to a server.

[1732] Server behavior:

[1733] The system analyzes the collected location and conversation data to understand the current group arrangement and conversation progress. It detects when a particular group is inactive or has low topic agreement, and generates optimal new networking suggestions. These suggestions are sent to the user's device, notifying them of new group and table arrangements.

[1734] Specific examples

[1735] 1. Specific examples of the preparation phase

[1736] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." When the device sends the data to the server, the server uses a generative AI model to generate a self-introduction profile for the user, describing him as an "IT engineer with a strong marketing background," and provides it to the user.

[1737] 2. Example of the automatic group creation phase

[1738] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[1739] 3. Specific examples of event phases

[1740] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[1741] As described above, this system maximizes the networking effect of participants throughout the entire event process, contributing to the success of the event.

[1742] The processing flow will be explained below.

[1743] Preparation Phase

[1744] Step 1:

[1745] User:

[1746] Log in to the event system and register.

[1747] Step 2:

[1748] server:

[1749] Users are presented with a survey that includes questions about the participant's job, skills, interests, and networking goals.

[1750] Step 3:

[1751] User:

[1752] Answer the survey and submit your answers.

[1753] Step 4:

[1754] Device:

[1755] The submitted questionnaire responses are relayed to the server.

[1756] Step 5:

[1757] server:

[1758] A generative AI model is run based on the received response data to generate a self-introduction profile.

[1759] Step 6:

[1760] server:

[1761] Send the generated profile to the device.

[1762] Step 7:

[1763] User:

[1764] Check your profile and make any necessary changes.

[1765] Automatic group creation phase

[1766] Step 8:

[1767] server:

[1768] All participants' self-introduction profiles are stored in a database.

[1769] Step 9:

[1770] server:

[1771] The stored profile information is analyzed using natural language processing (NLP) technology to identify each participant's interests and networking goals.

[1772] Step 10:

[1773] server:

[1774] Based on the analysis results, participants are grouped by purpose using an optimal matching algorithm.

[1775] Step 11:

[1776] server:

[1777] The grouped information and a session schedule are generated and transmitted to each user's terminal.

[1778] Event Phase

[1779] Step 12:

[1780] User:

[1781] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[1782] Step 13:

[1783] Device:

[1784] It tracks users' locations in real time and collects data based on their conversations and interests.

[1785] Step 14:

[1786] Device:

[1787] The collected data is sent to the server.

[1788] Step 15:

[1789] server:

[1790] The collected location information and conversation data is analyzed to understand the current group arrangement and conversation progress.

[1791] Step 16:

[1792] server:

[1793] It detects when certain groups are inactive or have low topical alignment and generates new networking suggestions.

[1794] Step 17:

[1795] server:

[1796] Send the new proposal to the device.

[1797] Step 18:

[1798] Device:

[1799] Notify users of new group and table placements.

[1800] Step 19:

[1801] User:

[1802] Follow the proposed new arrangement and move to your designated new table or group.

[1803] This series of steps allows for efficient and beneficial networking even in a limited amount of time.

[1804] Example 1

[1805] 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."

[1806] To enable participants to interact more effectively at networking events, it is important to create detailed profiles in advance and meet suitable people during the event. However, with conventional systems, creating self-introduction profiles and grouping participants is often done manually, which is time-consuming and labor-intensive and may not result in optimal matching. It is also difficult to grasp and adjust real-time interaction situations during the event, making it difficult for participants to network effectively.

[1807] 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.

[1808] In this invention, the server includes: means for using a generative AI model in which participants answer simple questions in advance and generate a self-introduction profile based on the answers; means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose and interests of each participant; means for tracking participants' location information and conversation content in real time during the event to optimize the progress of the event; and means for monitoring specific activity levels within groups and generating and notifying new networking suggestions in the event of inactive groups or low topic matches. This allows participants to easily create effective self-introduction profiles and continue to meet suitable people even during the event.

[1809] A "generative AI model" is a program that uses artificial intelligence technology to automatically generate a self-introduction profile based on participants' responses.

[1810] "Natural language processing technology" is a field of computer science that deals with understanding and processing human language, and is a technology used to analyze and generate text data.

[1811] A "self-introduction profile" is a digital document that organizes personal information about participants, including their job, skills, interests, concerns, and networking goals.

[1812] The "group generation method" is an algorithm that automatically creates appropriate groups based on participants' self-introduction profiles and interests according to the purpose of networking.

[1813] "Location Information" means data obtained using GPS or other technologies that indicates where a Participant is located within an Event.

[1814] "Conversation content" is data including topics and keywords of verbal communication exchanged between participants during the event.

[1815] "Real-time tracking" refers to a system that instantly acquires participants' location information and conversation content while the event is in progress, sends it to a server, and dynamically analyzes it.

[1816] "Networking Suggestions" are notifications from the system that recommend new suitable networking partners and groups based on participants' current group placement and conversation content.

[1817] The "means for monitoring specific activity levels within a group" refers to an algorithm that monitors the activity status and conversation progress of participants within a group and evaluates the activity level of the group.

[1818] This invention is a system for streamlining networking events, allowing participants to generate self-introduction profiles by answering simple questions in advance, and dynamically creating and adjusting optimal groups during the event.

[1819] Overall system overview

[1820] The system combines generative AI models and natural language processing technology to automatically generate participant profiles and dynamically create and coordinate groups during the event. The system is basically divided into the following phases: pre-preparation phase, automatic group creation phase, and in-event phase.

[1821] Preparation Phase

[1822] User Actions

[1823] To participate in an event, users log in to the system and apply for participation. After logging in, they answer a questionnaire that appears. This questionnaire includes questions about their job, their skills, interests, and networking goals.

[1824] Device behavior

[1825] The terminal receives the user's input data and sends it to the server.

[1826] Server Operation

[1827] The server uses a generative AI model (e.g., GPT-4) to generate a self-introduction profile from the user's input data. The generated profile information is sent to the device, where the user can review the content and make any necessary corrections.

[1828] Automatic group creation phase

[1829] Server Operation

[1830] The server stores the self-introduction profile information of all participants in a database (e.g., MySQL). It then analyzes the data using natural language processing (NLP) technology (e.g., SpaCy) to identify participants' interests and goals. Based on this information, it uses an optimal matching algorithm (e.g., K-means clustering) to group participants by purpose. The generated group information is sent to each user's device.

[1831] Event Phase

[1832] User Actions

[1833] On the day of the event, users check the session schedule on their device and head to their designated group or table.

[1834] Device behavior

[1835] The device tracks the user's location in real time using GPS, collects conversation content through a microphone, and sends the data to a server.

[1836] Server Operation

[1837] The server analyzes the collected data to understand the group placement and conversation progress, and if a particular group is inactive or has low topic agreement, it generates optimal new networking proposals and sends them to the user's device.

[1838] Specific examples

[1839] 1. Specific examples of the preparation phase

[1840] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." When the device sends the data to the server, the server uses a generative AI model (e.g., "GPT-4") to generate a self-introduction profile for the user, describing the user as an "IT engineer with expertise in marketing," and provides it to the user.

[1841] 2. Example of the automatic group creation phase

[1842] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[1843] 3. Specific examples of event phases

[1844] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[1845] Prompt Sentence Examples

[1846] "My area of ​​interest is marketing and I currently work as an IT engineer. Please create a profile to introduce myself."

[1847] Through these phases, the present invention can maximize the networking effect of participants and improve the outcome of the event.

[1848] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1849] Step 1: Log in and complete the survey

[1850] User Actions

[1851] Users log in to the system and answer a questionnaire. After entering their ID and password on the login page and being authenticated, the questionnaire screen appears. Users answer questions about their work, skills, interests, networking goals, etc.

[1852] Device behavior

[1853] The terminal receives the user's input data from the input form, performs error checks (e.g., checking required fields, checking data format), and then sends the data to the server in JSON format.

[1854] Input: Data entered by the user into the survey form (e.g., job, skills, interests)

[1855] Output: Data after error checking is sent to the server

[1856] Step 2: Create your profile

[1857] Server Operation

[1858] The server uses a generative AI model (e.g., GPT-4) to generate a self-introduction profile from the received input data. The generated profile reflects the user's interests and skills. Natural language processing technology is used to generate the profile.

[1859] Input: User survey data sent from the device

[1860] Data processing: AI models analyze data, perform natural language processing, and generate profiles

[1861] Output: Generated self-introduction profile

[1862] Device behavior

[1863] The generated profile information is sent to the user's device, which displays the profile and prompts the user to confirm and make any necessary corrections.

[1864] Input: Self-introduction profile sent from the server

[1865] Output: The profile screen that the user sees

[1866] Step 3: Check and modify your profile

[1867] User Actions

[1868] The user checks their self-introduction profile and makes any necessary corrections. The corrections are then sent back to the server.

[1869] Input: Initially generated profile

[1870] Output: Corrected profile data

[1871] Device behavior

[1872] The terminal receives the user's modifications and sends them back to the server.

[1873] Input: Corrected profile data

[1874] Output: Modifications sent to the server

[1875] Step 4: Store profile information in a database

[1876] Server Operation

[1877] The server stores the modified profile in a database using a fast relational database (e.g., MySQL).

[1878] Input: Corrected profile data

[1879] Data processing: Insert / update data into database based on data format

[1880] Output: Profile information stored in the database

[1881] Step 5: Analyze and group profiles

[1882] Server Operation

[1883] The server analyzes the stored profile information using natural language processing (NLP) techniques (e.g., SpaCy) to identify participants' interests and goals, and then groups them based on the identified information using an optimal matching algorithm (e.g., K-means clustering).

[1884] Input: Profile information stored in the database

[1885] Data processing: Natural language processing technology is used to identify interests and purposes, and matching algorithms are used to group them.

[1886] Output: Group information

[1887] Step 6: Generate and distribute session schedules

[1888] Server Operation

[1889] The server generates a session schedule for the event based on the generated group information, and transmits the session schedule to each user's device.

[1890] Input: Group information

[1891] Data processing: Create a session schedule using a schedule generation algorithm

[1892] Output: Generated session schedule

[1893] Device behavior

[1894] The terminal receives the session schedule sent from the server and displays it to the user.

[1895] Input: Session schedule sent from the server

[1896] Output: The schedule screen displayed to the user

[1897] Step 7: Collect location and conversation data during the event

[1898] Device behavior

[1899] The device tracks the user's location in real time using GPS and collects conversations through a microphone, which is then periodically sent to a server.

[1900] Input: User location and conversation data

[1901] Output: Collected data is sent to the server

[1902] Step 8: Data analysis and networking proposals

[1903] Server Operation

[1904] The server analyzes the collected location information and conversation data to evaluate the activity level of the group and the degree of topic agreement. If the group is inactive or the degree of topic agreement is low, it generates new networking suggestions and notifies the user's device.

[1905] Input: Location and conversation data

[1906] Data processing: Analyze the data using an analytical algorithm to evaluate activity and consistency

[1907] Output: Networking suggestions are sent to the user's device.

[1908] Step 9: Implementing a Networking Proposal

[1909] User Actions

[1910] Users will move to new groups and tables according to new networking suggestions notified to their devices, resulting in more effective networking.

[1911] Input: Networking suggestions from the server

[1912] Output: Move to new group or table

[1913] This step allows the system to maximize the networking effect of participants throughout the event, contributing to the success of the event.

[1914] (Application example 1)

[1915] 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."

[1916] In conventional networking events, it is difficult to efficiently match participants based on their goals and interests. Furthermore, while real-time optimization of participant placement and progress, as well as dynamic group adjustment, is required during the event, no method exists to achieve this. The present invention aims to solve these problems and maximize the effectiveness of networking events.

[1917] 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.

[1918] In this invention, the server includes a means for using a generative AI model that generates a self-introduction profile based on participants' answers to simple questions in advance, a means for collecting and analyzing the self-introduction profiles generated by the generative AI model and automatically generating groups based on the goals and interests of each participant, a means for tracking participants' location information and conversation content in real time during the event and optimizing and dynamically adjusting the placement and progress of the event, and a means for participants to participate in the virtual networking event using smartphones, smart glasses, or head-mounted displays, thereby maximizing the effectiveness of the networking event and enabling participants to be matched with each other and their placement to be adjusted in real time.

[1919] A "networking event" is an event where participants gather to exchange information and explore business opportunities.

[1920] "Quick Questions" are a set of short, easy-to-answer questions used to understand participants' basic information, interests, skills, and goals.

[1921] A "self-introduction profile" is electronic data that is generated based on information provided by participants in advance and comprehensively indicates a person's characteristics, interests, skills, goals, etc.

[1922] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to make predictions or generate results from input information.

[1923] A "means" is a method or process used to achieve a particular function or purpose.

[1924] "Collection" is the act of gathering data or information in one place.

[1925] "Analysis" is the process of examining collected data and information in detail to derive specific patterns and meanings.

[1926] "Purpose" refers to the specific reason participants are attending the networking event or what they hope to achieve.

[1927] "Interests" are topics or themes that participants have a personal interest in.

[1928] "Automatic group generation" refers to using artificial intelligence techniques to categorize participants into appropriate groups without manual intervention.

[1929] "Location information" is geographical data that indicates where a participant is currently located.

[1930] "Conversation content" refers to the words and topics exchanged between participants during the event.

[1931] "Real-time tracking" refers to the instantaneous monitoring and recording of ongoing situations.

[1932] "Optimizing progress" means adjusting the flow of events and plans to proceed most efficiently.

[1933] "Dynamic adjustment" means changing the settings and plans as appropriate depending on the event situation and the status of the participants.

[1934] A "virtual networking event" is an event held in an online environment for the purpose of networking.

[1935] A "smartphone" is a highly functional mobile phone that can connect to the Internet and run applications.

[1936] "Smart glasses" are glasses-type electronic devices with a built-in display that displays information.

[1937] A "head-mounted display" is a device that displays images by being worn on the head.

[1938] Overall system overview

[1939] The present invention is a system for streamlining networking events, allowing participants to create self-introduction profiles by simply answering simple questions in advance, and dynamically creating and adjusting optimal groups during the event, thereby maximizing the networking effect of participants throughout the entire event process.

[1940] System Configuration

[1941] The system is divided into three main phases:

[1942] 1. Preparation Phase

[1943] 2. Automatic group creation phase

[1944] 3. Event Phase

[1945] Preparation Phase

[1946] User Action:

[1947] To participate in a networking event, users log in to the system and apply for participation. After logging in, they answer a questionnaire displayed by the system, which includes information about their job, their skills, interests, and the purpose of networking.

[1948] Device behavior:

[1949] It receives user input data and sends it to the server.

[1950] Server behavior:

[1951] The server runs a generative AI model based on the input data to automatically generate a self-introduction profile. The generated profile information is sent to the user's device, where the user can review the content and make any necessary edits.

[1952] Automatic group creation phase

[1953] Server behavior:

[1954] Self-introduction profile information for all participants is stored in a database. The stored profile information is analyzed using natural language processing (NLP) technology to identify participants' interests and goals. Based on the analysis results, an optimal matching algorithm is used to group participants by goal. The generated group information is sent to each user's device on the day of the event.

[1955] User Action:

[1956] Check your session schedule on your device before the event.

[1957] Event Phase

[1958] User Action:

[1959] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[1960] Device behavior:

[1961] It tracks users' location information in real time, collects data based on their conversations and interests, and sends it to a server.

[1962] Server behavior:

[1963] The system analyzes the collected location and conversation data to understand the current group arrangement and conversation progress. It detects when a particular group is inactive or has low topic agreement, and generates optimal new networking suggestions. These suggestions are sent to the user's device, notifying them of new group and table arrangements.

[1964] Hardware and software used

[1965] Hardware:

[1966] Smartphones, smart glasses, head-mounted displays

[1967] software:

[1968] Python, OpenAI API, Geopy

[1969] Specific examples

[1970] 1. Examples of the preparatory phase:

[1971] A user registers with the system to participate in an event and answers a questionnaire stating, "I'm interested in marketing and work as an IT engineer." The server uses a generative AI model to generate a self-introduction profile for the user, describing him as an "IT engineer with a strong marketing background," and provides it to the user.

[1972] 2. Example of automatic group creation phase:

[1973] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing together, creates a session schedule for this group, and sends it to each user.

[1974] 3. Examples of event phases:

[1975] On the day of the event, a user attends a designated session. However, at some point, it becomes clear that the people he is talking to have different interests. The system analyzes this information in real time and suggests more suitable people. The user follows the new suggestions and moves to the designated new table, enabling more effective networking.

[1976] Examples of prompt statements

[1977] text

[1978] User information: Interested in marketing, working as an IT engineer

[1979] Use this information to create your profile.

[1980] The above is a specific embodiment of the present invention. This system maximizes the effectiveness of networking events, enabling participants to be matched and allocated in real time.

[1981] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1982] Step 1:

[1983] To participate in an event, users log in to the system and answer a questionnaire. The user's input data includes information about their job, skills, interests, and networking goals. This input data is sent from the terminal to the server.

[1984] Step 2:

[1985] The server runs a generative AI model based on the received input data to generate a self-introduction profile. The server then sends the generated profile to the user's device, allowing the user to review the content and make any necessary corrections. Input: Survey response data. Output: Self-introduction profile.

[1986] Step 3:

[1987] The server stores the self-introduction profile information of all participants in a database. The server analyzes the stored profile information using natural language processing (NLP) techniques to identify participants' interests and goals. Input: Self-introduction profile. Output: Analysis results.

[1988] Step 4:

[1989] The server uses the optimal matching algorithm based on the analysis results to group participants by purpose. The server sends the generated group information to each user's device on the day of the event. Input: Analysis results. Output: Group information.

[1990] Step 5:

[1991] Before the event, users check their own session schedules on their terminals. The terminals display the user's session schedule based on the group information received from the server. Input: Group information. Output: Session schedule.

[1992] Step 6:

[1993] On the day of the event, users check the session schedule on their device and head to their designated group or table. The device tracks the user's location information in real time and sends it to the server. Input: User's location information. Output: Real-time data sent to the server.

[1994] Step 7:

[1995] The server analyzes the collected location information and conversation data to understand the current group arrangement and conversation progress. If a particular group is inactive or has low topic agreement, it detects this and generates optimal new networking proposals. Input: Location information, conversation data. Output: Networking proposals.

[1996] Step 8:

[1997] The server sends a new networking proposal to the user's terminal, notifying them of the new group and table placement. The user moves to the specified new table according to the new proposal and continues networking. Input: Networking proposal. Output: New group placement notification.

[1998] 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.

[1999] Overall system overview

[2000] This invention is a system for promoting efficient matching and interaction among participants at networking events, incorporating an emotion engine to improve accuracy. Participants answer simple questions in advance, and optimal matching is performed based on an automatically generated self-introduction profile. Furthermore, participants' emotional data is tracked in real time during the event, and necessary adjustments are made.

[2001] Preparation Phase

[2002] User Action:

[2003] Users log in to the system and register to attend the event. After registering, they answer a questionnaire displayed by the system, which includes questions about their job, skills, interests, networking goals, and even their emotional state when introducing themselves.

[2004] Device behavior:

[2005] It receives user input data and sends it to the server.

[2006] Server behavior:

[2007] The server runs a generative AI model based on the received response data to automatically generate a self-introduction profile. The generated profile also includes emotional data generated by an emotion engine. This profile is then sent to the user's device, where the user can review the content and make any necessary changes.

[2008] Automatic group creation phase

[2009] Server behavior:

[2010] All participants' self-introductory profiles are stored in a database, which is then analyzed using natural language processing (NLP) techniques and an emotion engine to identify participants' interests, goals, and emotional states.

[2011] Server behavior:

[2012] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm. The generated group information and session schedule are sent to each user's device.

[2013] User Action:

[2014] Check your session schedule on your device before the event.

[2015] Event Phase

[2016] User Action:

[2017] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[2018] Device behavior:

[2019] It tracks users' location and emotional state data in real time, and also collects data based on conversations and interests during the event.

[2020] Device behavior:

[2021] All collected data is sent to the server.

[2022] Server behavior:

[2023] The collected location information, conversation data, and emotion data are analyzed to understand the current group arrangement and the progress of the conversation.

[2024] Server behavior:

[2025] It detects when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generates optimal new networking suggestions to solve these problems.

[2026] Server behavior:

[2027] Send the new proposal to the device.

[2028] Device behavior:

[2029] Notify users of new group and table placements.

[2030] User Action:

[2031] Follow the proposed new arrangement and move to your designated new table or group.

[2032] Specific examples

[2033] 1. Specific examples of the preparation phase

[2034] A user registers with the system to participate in an event, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The device sends the data to the server, which uses the generative AI model and emotion engine to generate a self-introduction profile for "an IT engineer with a deep understanding of marketing," and provides it to the user with the profile including emotion data.

[2035] 2. Example of the automatic group creation phase

[2036] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account participants' emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[2037] 3. Specific examples of event phases

[2038] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests more suitable people. Based on this suggestion, the user moves to the designated new table, enabling more effective networking.

[2039] This system will maximize the networking effect of participants throughout the entire event process, contributing to the success of the event.

[2040] The processing flow will be explained below.

[2041] Preparation Phase

[2042] Step 1:

[2043] User:

[2044] Log in to the event system and register to participate in the event.

[2045] Step 2:

[2046] server:

[2047] Users are presented with a survey that includes questions about their job, skills, interests, networking goals, and emotional state.

[2048] Step 3:

[2049] User:

[2050] Answer the survey and submit your answers.

[2051] Step 4:

[2052] Device:

[2053] The submitted questionnaire responses are relayed to the server.

[2054] Step 5:

[2055] server:

[2056] A generative AI model is run based on the received response data to automatically generate a self-introduction profile.

[2057] Step 6:

[2058] server:

[2059] An emotion engine is used to add emotion data to the generated profile.

[2060] Step 7:

[2061] server:

[2062] Send the completed profile to the device.

[2063] Step 8:

[2064] User:

[2065] Check your profile and make any necessary changes.

[2066] Automatic group creation phase

[2067] Step 9:

[2068] server:

[2069] The self-introduction profiles and emotional data of all participants are stored in a database.

[2070] Step 10:

[2071] server:

[2072] The stored profile information is analyzed using natural language processing (NLP) technology and an emotion engine to identify each participant's interests, goals, and emotional state.

[2073] Step 11:

[2074] server:

[2075] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm.

[2076] Step 12:

[2077] server:

[2078] The grouped information and a session schedule are generated and transmitted to each user's terminal.

[2079] Event Phase

[2080] Step 13:

[2081] User:

[2082] On the day of the event, check the session schedule on the terminal and head to your designated group or table.

[2083] Step 14:

[2084] Device:

[2085] It tracks users' location and emotional state data in real time, and collects data based on their conversations and interests.

[2086] Step 15:

[2087] Device:

[2088] All collected data is sent to the server.

[2089] Step 16:

[2090] server:

[2091] The collected location information, conversation data, and emotion data are analyzed to understand the current group arrangement and the progress of the conversation.

[2092] Step 17:

[2093] server:

[2094] Detect when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generate optimal new networking proposals to address these challenges.

[2095] Step 18:

[2096] server:

[2097] Send the new proposal to the device.

[2098] Step 19:

[2099] Device:

[2100] Notify users of new group and table placements.

[2101] Step 20:

[2102] User:

[2103] Follow the proposed new arrangement and move to your designated new table or group.

[2104] Specific examples

[2105] Specific examples of the preparation phase

[2106] A user logs in to the system to participate in an event, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The user's device sends the data to the server, which uses the generative AI model and emotion engine to generate a self-introduction profile called "IT engineer with expertise in marketing," and provides it to the user with emotional data attached.

[2107] A concrete example of the automatic group creation phase

[2108] Just before the event, the server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account participants' emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[2109] Specific examples of phases during an event

[2110] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests more suitable people. Based on this suggestion, the user moves to the designated new table, enabling more effective networking.

[2111] Example 2

[2112] 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."

[2113] Promoting effective matching and interaction between participants is a key challenge at modern networking events. Traditional methods often fail to match participants based on their interests and goals, resulting in stagnant interactions and ineffective networking. Furthermore, they often fail to take into account participants' emotional states, often resulting in an unsatisfactory experience. Therefore, a system is needed that can grasp participants' emotional states and interaction situations in real time and provide optimal networking.

[2114] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for using a generative AI model in which participants answer simple questions in advance and generate a self-introduction profile based on the answers; a means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose, interests, and emotional state of each participant; a means for tracking the location information, conversation content, and emotional state of participants in real time during the event and optimizing the placement and progress of the event; and a means for generating an optimal new networking proposal and relocating participants when a problem is detected. This enables effective matching and promotion of interaction between participants.

[2115] A "generative AI model" is an algorithm used by a computer to automatically generate a self-introduction profile based on a large dataset.

[2116] A "profile" is information about a participant that describes their occupation, skills, interests, networking goals, and emotional state.

[2117] An "emotion engine" is a technology for extracting and evaluating emotions from text and audio data.

[2118] "Natural language processing technology" is a technology that allows computers to understand and process the language that humans use on a daily basis.

[2119] The "group generation means" is a function within the system that automatically creates optimal groups based on participants' goals, interests, and emotional states.

[2120] "Location information" is information that indicates the geographical location of a participant within the event venue.

[2121] "Conversation content" refers to the content of the dialogue between participants, and is text or audio data.

[2122] "Real-time tracking" means instantly tracking ongoing situations and collecting and analyzing data.

[2123] "Networking suggestions" are suggestions for new group and table arrangements based on participants' interests and emotional state.

[2124] "Optimizing" means maximizing the performance and efficiency of a system.

[2125] This invention is a system for facilitating efficient matching and interaction among participants at networking events, and uses a generative AI model and an emotion engine to improve accuracy. Specific embodiments of this system are described below.

[2126] Overall system overview

[2127] This invention allows users participating in a networking event to answer simple questions in advance, and then automatically generates a self-introduction profile based on the answers using a generative AI model. The generated profile includes emotional data for optimal matching. Furthermore, during the event, the system tracks users' location information and emotional state in real time and makes networking suggestions as needed.

[2128] Hardware and Software Configuration

[2129] 1. Server

[2130] The server receives the survey data and runs a generative AI model (e.g., OpenAI GPT-3). The server uses an emotion engine to extract emotional data and generate profiles. The server then stores all participant profiles in a database and uses natural language processing (NLP) techniques (e.g., NLTK and SpaCy) to analyze the profiles and generate optimal groups. The server analyzes the stored data and data collected in real time, and generates optimal networking suggestions if problems are detected.

[2131] 2. Terminal

[2132] The device primarily functions as an interface with the user, transmitting user input data to the server. During the event, the device also collects the user's location information (e.g., GPS) and emotional state data (e.g., biometric sensors) and transmits them to the server. The device then displays the data and suggestions sent from the server to the user.

[2133] Specific examples

[2134] Specific examples of the preparation phase

[2135] A user registers with the system, answers a questionnaire saying "I'm interested in marketing and work as an IT engineer," and selects "expectations" as their emotion. The device sends this data to the server, which uses a generative AI model and emotion engine to generate a self-introduction profile for the user, calling them "an IT engineer with a strong marketing background," and provides this profile to the user, including their emotion data.

[2136] Example prompt sentence:

[2137] "Generate a self-introduction profile based on the user's occupation, skills, interests, networking goals and emotional state."

[2138] A concrete example of the automatic group creation phase

[2139] The server analyzes the profiles of all participants and groups engineers who are interested in marketing. It also takes into account emotional data and groups participants with similar emotional states. It also generates a session schedule and sends it to each user.

[2140] Specific examples of phases during an event

[2141] On the day of the event, a user attends a designated session. However, their emotional state becomes negative and they discover that the people they are talking to have different interests. The system analyzes this information in real time and suggests new, more suitable people. The user follows the suggestions and moves to a new table, resulting in more effective networking.

[2142] In this way, the system can consistently collect and analyze data, providing optimal networking and contributing to the success of the event.

[2143] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2144] Step 1:

[2145] A user logs in to the system and registers to participate in an event. The terminal sends the input data to the server for authentication using the "email address" and "password" entered by the user. The server verifies the received login information, and if authentication is successful, redirects the user to the dashboard screen. The input in this step is the user's login information, and the output is the dashboard screen.

[2146] Step 2:

[2147] The user answers the displayed questionnaire. When the user answers questions about "job content," "skills," "interests," "networking goals," and "emotional state," the device records this answer data and sends it to the server. The server stores the received questionnaire data. The input in this step is the user's questionnaire answers, and the output is the stored questionnaire data.

[2148] Step 3:

[2149] The server runs a generative AI model using the received survey data. Based on the prompt, the "generative AI model" generates a self-introduction profile, and then uses an emotion engine to extract emotional data and include it in the profile. For example, the prompt might read, "Generate a self-introduction profile based on the user's occupation, skills, interests, networking goals, and emotional state." The input in this step is the survey data and the prompt, and the output is a self-introduction profile.

[2150] Step 4:

[2151] The server sends the generated self-introduction profile to the user's device. The user can review the profile on the device and modify it if necessary. The input in this step is the generated profile, and the output is the profile provided to the user.

[2152] Step 5:

[2153] The server stores the self-introduction profiles of all participants in a database. It uses natural language processing technology (e.g., NLTK or SpaCy) and an emotion engine to analyze participants' interests, goals, and emotional states from the stored profile information. The input in this step is the stored profile information, and the output is the analyzed data of interests, goals, and emotional states.

[2154] Step 6:

[2155] Based on the analysis results, the server uses an optimal matching algorithm (e.g., "K-means clustering") to group participants by purpose and emotional state. The generated group information and session schedule are sent to the user's device. The input in this step is the analysis results, and the output is the grouped information and session schedule.

[2156] Step 7:

[2157] On the day of the event, users check the session schedule on their devices and head to their assigned groups and tables. As users move, the devices collect location information (e.g., GPS) and emotional state data (e.g., biometric sensors) in real time and send them to the server. The inputs in this step are the user's movements and real-time data, and the output is the real-time data sent to the server.

[2158] Step 8:

[2159] The server analyzes the collected location, conversation, and emotion data to understand the current group arrangement and conversation progress. The server detects when a particular group is inactive, when there is low topic agreement, or when a particular participant is in a negative emotional state. The input in this step is the collected real-time data, and the output is the analysis results.

[2160] Step 9:

[2161] Based on the analysis results, the server generates an optimal new networking proposal to solve the problem and sends it to the user's device. The device notifies the user of this proposal, and the user moves to a new table or group specified based on the new proposal. The inputs in this step are the analysis results and the proposal generation algorithm, and the output is a new networking proposal provided to the user.

[2162] (Application example 2)

[2163] 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."

[2164] Conventional networking events and autonomous vehicles have faced challenges in providing optimal matching and comfort based on the emotional state and interests of participants and passengers. In particular, the lack of a mechanism for tracking and analyzing real-time emotional data and adjusting environmental settings based on this data has made it difficult to maximize the networking effect of participants and the comfort of passengers.

[2165] 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.

[2166] In this invention, the server includes: means for using a generative AI model that generates a self-introduction profile based on participants' answers to simple questions in advance; means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on each participant's purpose and interests; means for tracking participants' location information and conversation content in real time during the event to optimize the event layout and progress; means for collecting passengers' location information, emotional state, and purpose of the ride; means for using the collected data to analyze emotional data in real time and adjust music, lighting, and temperature; and means for presenting appropriate information and re-suggesting a ride route based on the collected emotional data. This maximizes the effectiveness of interactions at networking events and improves passenger comfort in autonomous vehicles.

[2167] A "generative AI model" is an artificial intelligence algorithm that automatically generates participant profiles from responses to surveys and questions.

[2168] A "self-introduction profile" is an introduction that includes the participant's personal information, interests, and goals, automatically generated by a generative AI model.

[2169] "Natural language processing technology" is an information processing technology for understanding, analyzing, and generating human language.

[2170] "Real-time tracking" is a technology that collects and tracks current information in a timely manner.

[2171] "Emotional data" refers to data that represents the emotional state of a participant or passenger, including positive, negative, neutral, and other emotional states.

[2172] "Location information" is data used to identify the current location of a person or object.

[2173] "Purpose of ride" refers to the passenger's main purpose or reason for using an autonomous vehicle.

[2174] "Adjusting music, lighting, and temperature" refers to a means of enhancing passenger comfort by appropriately setting and changing environmental elements inside an autonomous vehicle.

[2175] "Information presentation means" refers to a means for providing passengers with appropriate information visually or audibly.

[2176] "Route re-proposition" is a means of reconsidering and proposing the optimal route based on the current riding situation and destination.

[2177] The system according to the present invention can facilitate effective matching and interaction between participants at networking events, and can also improve the comfort of passengers in autonomous vehicles.

[2178] Preparation Phase

[2179] User Actions

[2180] Users log in to the system and register to participate in the event. After registering, they answer a questionnaire displayed by the system. The questionnaire includes questions about their interests, work, skills, networking goals, riding goals, and even their emotional state when introducing themselves.

[2181] Device behavior

[2182] The terminal receives the user's input data and transmits it to the server.

[2183] Server Operation

[2184] The server runs a generative AI model based on the received response data to automatically generate a self-introduction profile. The generated profile also includes emotional data generated by an emotion engine. This profile is then sent to the user's device, where the user can review and modify it as needed.

[2185] Automatic group creation phase

[2186] Server Operation

[2187] The server stores all participants' self-introduction profiles in a database, which are then analyzed using natural language processing (NLP) techniques and an emotion engine to identify participants' interests, goals, and emotional states.

[2188] Server Operation

[2189] Based on the analysis results, participants are grouped by purpose and emotional state using an optimal matching algorithm. The generated group information and session schedule are sent to each user's device.

[2190] User Actions

[2191] Before the event, the user checks his / her session schedule on the terminal.

[2192] Event Phase

[2193] User Actions

[2194] On the day of the event, users check the session schedule on their device and head to their designated group or table.

[2195] Device behavior

[2196] The device tracks users' location and emotional state data in real time, and also collects data based on conversations and interests during the event.

[2197] Server Operation

[2198] The server analyzes the collected location information, conversation data, and emotion data to understand the current group arrangement and the progress of the conversation.

[2199] Server Operation

[2200] The server detects when certain groups are inactive, when topic alignment is low, or when certain participants are in a negative emotional state, and generates optimal new networking proposals to resolve these issues.

[2201] Device behavior

[2202] The terminal notifies the user of the new proposals that have been generated.

[2203] User Actions

[2204] The user follows the proposed new arrangement and moves to the specified new table or group.

[2205] Specific examples

[2206] For example, if a user answers a questionnaire when registering for an event with "I'm interested in marketing and work as an IT engineer" and selects "expecting" as their emotion, the device will send that data to the server, which will then use the generative AI model and emotion engine to generate a self-introduction profile for "an IT engineer with extensive experience in marketing" and provide it to the user with the profile including their emotion data.

[2207] On the day of the event, if a user participates in a session and their emotional state becomes negative, the system will detect this in real time and suggest more appropriate networking partners. The user can then follow the suggestions and move to a new table or group, ensuring effective networking.

[2208] Example of a prompt sentence for an application example

[2209] For example, a prompt for improving comfort in a self-driving vehicle:

[2210] "My current objective is a work presentation. My emotional state is tense."

[2211] This invention allows for maximizing the social impact of networking events and improving passenger comfort in autonomous vehicles.

[2212] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2213] Step 1:

[2214] User Actions

[2215] Users log in to the system and register to participate in the event. As input, they provide information in the form of a questionnaire about their interests, jobs, skills, networking goals, riding goals, emotional state, etc. The output is that this data is sent to the terminal.

[2216] Step 2:

[2217] Device behavior

[2218] The terminal receives the user's input data and sends it to the server. It receives the user's survey results as input and generates a data package to send to the server as output.

[2219] Step 3:

[2220] Server Operation

[2221] The server runs a generative AI model based on the received user data to generate a self-introduction profile. The input is the user's questionnaire response data, and the output is the generated self-introduction profile and emotion data. Specifically, the AI ​​model analyzes the text data using natural language processing technology and generates an appropriate profile.

[2222] Step 4:

[2223] Server Operation

[2224] The generated self-introduction profile and emotion data are sent to the user's terminal. The input is the generated self-introduction profile and emotion data, and this is sent to the user's terminal as output.

[2225] Step 5:

[2226] User Actions

[2227] The user checks the received profile and modifies it if necessary. The input is the self-introduction profile that was just received, and the output is the modified profile. This modified data is sent back to the server.

[2228] Step 6:

[2229] Server Operation

[2230] The server stores the self-introduction profiles of all participants in a database and analyzes them using natural language processing technology and an emotion engine. The input is the self-introduction profiles of all participants, and the output is data on each participant's interests, goals, and emotional state.

[2231] Step 7:

[2232] Server Operation

[2233] Based on the analysis results, the server uses an optimal matching algorithm to group participants by purpose and emotional state. The input is the analyzed participant data, and the output is optimal group information and session schedule.

[2234] Step 8:

[2235] Server Operation

[2236] The generated group information and session schedule are sent to each user's terminal. The input is the group information and session schedule, and the output is to send them to the user's terminal.

[2237] Step 9:

[2238] User Actions

[2239] Before an event, a user checks their own session schedule on a terminal. The input is the session schedule sent from the server, and the output is to view and check it.

[2240] Step 10:

[2241] Device behavior

[2242] On the day of the event, the device tracks the user's location and emotional state data in real time. The input is the user's current location and emotional state, and the output is the data tracking them in real time.

[2243] Step 11:

[2244] Server Operation

[2245] The server analyzes the collected location information, conversation data, and emotion data to understand the current group arrangement and conversation progress. The input is the data collected in real time, and the output is the analysis results.

[2246] Step 12:

[2247] Server Operation

[2248] The server detects when a particular group is inactive, when topic agreement is low, or when a particular participant is in a negative emotional state, and generates optimal new networking proposals based on this.The input is the analyzed group data and emotional data, and the output is new networking proposals.

[2249] Step 13:

[2250] Device behavior

[2251] The terminal notifies the user of the new proposals it generates. The input is the networking proposal sent by the server, and the output is the notification to the user.

[2252] Step 14:

[2253] User Actions

[2254] The user moves to the specified new table or group according to the proposed new arrangement. The input is the new group arrangement information, and the output is the behavior according to that instruction.

[2255] 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.

[2256] 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.

[2257] 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.

[2258] 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.

[2259] 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.

[2260] 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.

[2261] 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).

[2262] 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.

[2263] 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."

[2264] 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.

[2265] 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).

[2266] 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.

[2267] 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.

[2268] 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.

[2269] 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.

[2270] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[2271] 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.

[2272] 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.

[2273] 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.

[2274] 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.

[2275] 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.

[2276] The following is further disclosed regarding the above embodiment.

[2277] (Claim 1)

[2278] A method of using a generative AI model to generate a self-introduction profile based on participants' answers to simple questions in advance at a networking event;

[2279] A means for ...

Claims

1. A method of using a generative AI model to generate a self-introduction profile based on participants' answers to simple questions in advance at a networking event; A means for collecting and analyzing the generated self-introduction profiles and automatically generating groups based on the purpose and interests of each participant; A means of tracking the location information and conversation content of participants in real time during the event to optimize the arrangement and progress of the event; A system including:

2. The system of claim 1 , wherein the generative AI model uses natural language processing techniques to generate profiles from participants' responses.

3. 2. The system according to claim 1, wherein the group generating means automatically creates an optimal group for a networking purpose based on the self-introduction profiles and interests of participants.

Images