system

Abstract

We provide the system. [Solution] A database that stores information provided by users, A processing unit using generative artificial intelligence to analyze the skills and background of the aforementioned user, A system including a matching mechanism that presents a suitable expert to the user based on the content of their consultation.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] <9000017>

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern information technology industry, with the progress of digital transformation, there is a problem that it is difficult to secure appropriate IT personnel, especially in small and medium-sized enterprises and individual business owners. In addition, there is a need for the ability to accurately grasp the skills and experience of personnel and quickly match personnel that meet the needs of clients. However, in the conventional method, the utilization efficiency of human resources is poor, and as a result, the shortage of IT personnel has become prominent. In such a background, in order to efficiently utilize limited resources, it has become an urgent task to effectively utilize available personnel.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that includes a database for storing information provided by users and a processing unit that uses generative artificial intelligence to analyze the user's skills and experience. Specifically, the generative artificial intelligence analyzes the user's information, generates skill tags, and provides a matching means that presents a suitable expert to the user according to the content of the consultation. This enables efficient personnel matching and can alleviate the problem of personnel shortages. Furthermore, by having the generative AI further improve the matching accuracy based on feedback after matching, it is possible to continuously improve the quality of the service.

[0006] A "user" is an individual or organization that provides information through the system and seeks to be matched with experts who meet their specific needs.

[0007] A "database" is a recording device that systematically stores information provided by users and allows for searching and updating as needed.

[0008] "Generative artificial intelligence" refers to algorithms and models that learn patterns from large amounts of data and have the ability to analyze or predict a user's skills and background.

[0009] A "processing device" is a machine or a part thereof that uses generative artificial intelligence to analyze data and generate or transform necessary information.

[0010] A "skill tag" is an identifier assigned by a generating artificial intelligence to represent the knowledge and skills a user possesses.

[0011] A "matching method" refers to a process or mechanism for identifying experts who are suitable for the user's needs and connecting them with the user.

[0012] A "specialist" is a professional or expert who possesses advanced knowledge and skills in a specific field and is able to meet the needs of users.

[0013] "Feedback" refers to information collected from users' evaluations and opinions after a service has been provided, and is used to improve future services. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The system according to the present invention is for efficiently matching users with experts who possess the necessary IT skills, and an embodiment thereof is shown below.

[0036] At the heart of the system is a processing unit utilizing a database and generative artificial intelligence. Users first input their own information into the system, which is then stored in the database. This information includes skill sets, work experience, and desired conditions.

[0037] Next, the server sends this information to a generating artificial intelligence (AI) that analyzes the user's skills and background and generates skill tags. These skill tags are a crucial element for visually and mechanically identifying the user's expertise and experience.

[0038] The system extracts the necessary skills based on the user's input of their consultation request and searches for a suitable expert. Specific consultation requests entered via the terminal are described in a format such as "improving the UI / UX design of a mobile application." The server then uses AI generation to create a list of optimal experts and presents them to the candidates.

[0039] If a selected expert is deemed capable of meeting the user's requirements, the user (client and expert) can conduct an online consultation. This process can be conducted, for example, through a video conferencing system or messaging platform. Smooth communication between both parties will enable the user to obtain the desired solution.

[0040] Finally, after the consultation ends, users provide feedback, which the server saves to a database. This feedback is analyzed by a generative AI and used to improve future matching accuracy. For example, based on the information obtained from the feedback, the system learns to provide better support in the next matching.

[0041] This allows the system to provide users with a sustainable and efficient matching service, enabling them to make effective use of their free time.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] Users access the platform using their devices and fill out the registration form with the required information, including skills, work history, email address, and password.

[0045] Step 2:

[0046] The server verifies the registration information received from the user, checking the format and data integrity. Once verification is complete, the information is saved to the database.

[0047] Step 3:

[0048] The server uses artificial intelligence to analyze stored user information and generate specific skill tags. This clarifies the user's expertise and past experience.

[0049] Step 4:

[0050] The user (client) enters specific consultation details via their terminal. These details include specifics of the problem they want to solve and the skills they require.

[0051] Step 5:

[0052] The server analyzes the input consultation content, and the generating AI sets criteria for extracting experts with the appropriate skills and experience from the database.

[0053] Step 6:

[0054] The server uses artificial intelligence to generate a list of experts best suited to the client's needs and presents it to the client. The list includes the experts' profiles and skill sets.

[0055] Step 7:

[0056] The user (client) selects a suitable expert from the presented list and schedules a consultation.

[0057] Step 8:

[0058] The server notifies the selected expert, confirms both parties' schedules, and then schedules a session using methods such as video chat.

[0059] Step 9:

[0060] Users (clients and experts) conduct consultations via terminals using specified methods and engage in concrete discussions toward resolving the problem.

[0061] Step 10:

[0062] The user (client) enters feedback regarding the content and results of the consultation.

[0063] Step 11:

[0064] The server stores the feedback in a database, and the generated artificial intelligence uses that feedback to perform analysis to improve future matching accuracy.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] In today's business environment, efficiently finding and matching IT professionals with the required skills is a significant challenge. While it's essential to quickly select the most suitable professionals to meet diverse user needs and ensure smooth communication, traditional systems have been insufficient in this regard.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes information storage means, processing means using artificial intelligence, matching means, label generation means, and communication means. This enables the rapid and accurate matching of the most suitable expert based on the information provided by the user, and facilitates online consultations, thereby smoothing the expert selection process and subsequent communication.

[0070] An "information storage means" is a device or mechanism that stores information provided by users in a database and allows it to be retrieved as needed.

[0071] "Processing means using artificial intelligence" refers to a device or system that uses artificial intelligence technology to analyze the skills and background of a user.

[0072] A "matching method" is a device or process that has the function of selecting and presenting an appropriate expert based on the content of the user's consultation.

[0073] A "label generation means" is a device or mechanism that analyzes the characteristics of users and experts to generate skill tags and stores them in a database.

[0074] "Communication means" refers to devices with communication technologies, such as video conferencing systems and messaging platforms, used by users and experts to conduct online consultations.

[0075] This invention is a system for efficiently matching users with suitable experts, and is implemented using information storage means, processing means using artificial intelligence, matching means, label generation means, and communication means. In the implementation of the system, the server, terminal, and user each play their respective roles.

[0076] The server stores personal information, skill sets, work history, and desired conditions entered by users through their terminals in an information storage device. This information is stored in a database and retrieved as needed.

[0077] Next, the server utilizes artificial intelligence-based processing to analyze the user's skills and experience using a generative AI model called "SkillTagger." This analysis generates skill tags, which are then stored in a database as a label generation tool. An example of a specific prompt message is, "Generate skill tags from this information."

[0078] When a user enters their consultation details from their device, the server uses a matching mechanism to send the details to the AI ​​model "SkillMatcher," prompting it with the message, "Please list the appropriate experts for this consultation." This process generates a list of the most suitable experts, which are then presented to the user.

[0079] Users utilize communication methods to conduct online consultations based on a list of candidates. Specifically, they directly consult with experts via video conferencing systems and messaging platforms. This method allows users to communicate efficiently with experts and seek the necessary solutions.

[0080] As described above, this invention enables the rapid and accurate matching of users with the experts they require, and facilitates the smooth operation of the entire system.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] Users use a terminal to input data such as personal information, skill sets, work history, and desired conditions. This data is sent to a data storage device. The server then uses the data storage device to store the entered data in a database. Specifically, the system works to ensure that the information entered by the user is accurately stored in the corresponding field in the database.

[0084] Step 2:

[0085] The server retrieves user information from the database and sends it to the generating AI model "SkillTagger" to generate skill tags. The input is user information from the database, and the output is skill tags. The generating AI model analyzes the user information via a prompt message, "Generate skill tags from this information," and generates skill tags as a result of the analysis. The generated skill tags are then saved back into the database.

[0086] Step 3:

[0087] Users input specific consultation details via their devices. Examples include "improving the UI / UX design of a new mobile app." This input data is sent to a server and processed using a matching system.

[0088] Step 4:

[0089] The server sends the consultation details to the generating AI model "SkillMatcher" to list appropriate experts. The input is the user's consultation details, and the output is a list of appropriate experts. The generating AI model uses the prompt "Please list the appropriate experts for this consultation" to analyze the skills required for the consultation and select the corresponding experts.

[0090] Step 5:

[0091] The server presents the user with a list of experts. The user can then select a suitable expert from the presented list. In this step, the human interface used is crucial; it must be designed to allow the user to easily navigate the list.

[0092] Step 6:

[0093] The user and the selected expert initiate an online consultation using communication methods. Specifically, they communicate directly using video conferencing systems or messaging platforms. The inputs here are the user's and expert's schedules and the selected communication methods, while the output is the actual communication activity.

[0094] Step 7:

[0095] After the consultation is complete, the user sends feedback from their device to the server. This feedback is recorded as evaluation information.

[0096] Step 8:

[0097] The server passes the feedback to the AI ​​model "FeedbackAnalyzer," which performs analysis to improve matching accuracy. The input is feedback information, and the output is an extraction of areas for improvement to be used in future matching. The analyzed results will be used to improve future processes.

[0098] (Application Example 1)

[0099] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0100] Currently, there are limited systems that efficiently match users with experts possessing specific expertise related to information technology. Furthermore, there is a lack of mechanisms to provide users with information on experts that match their interests and preferences, as well as to stream videos to aid understanding. This makes it difficult for users to quickly access the specific knowledge and solutions they seek.

[0101] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0102] In this invention, the server includes information storage means for storing information provided by the user, analysis means using a generative AI model for analyzing the user's skills and background, suitable expert display means for presenting experts suitable for the user based on the consultation content, and output means for presenting the expert's communication content via video distribution. This enables the user to quickly access relevant expertise according to their interests and preferences.

[0103] An "information storage means" is a technological device for efficiently storing and managing information provided by users.

[0104] A "generative AI model" is an artificial intelligence model used to analyze a user's skills and background and match them with the appropriate expert.

[0105] An "analysis tool" is a device used to deeply understand and classify the user's technical characteristics and background based on the provided data.

[0106] A "suitability indicator" is a visual or mechanical device for presenting a specialist who meets the user's needs.

[0107] An "information supply device" is a device equipped with the function of providing relevant information from experts based on the user's interests.

[0108] "Output means" refers to a technological device for distributing information provided by experts as video and presenting it to recipients.

[0109] To implement this invention, a server-centric information processing system is constructed. The server first stores information provided by users in a database using an information storage means. This information includes data on the user's technical background, career history, and areas of particular interest. A high-performance server is recommended as hardware, and a database management system such as MySQL® or MongoDB is used as software.

[0110] Next, the server uses a generated AI model to analyze user information and perform skill matching. For example, OpenAI's (registered trademark) generated AI model is used. This allows the expert best suited to the user's technical needs to be presented via a match display mechanism.

[0111] On the device, information delivery means provide relevant specialized content based on the user's interests, utilizing the knowledge and skills provided by experts. In particular, by distributing information from experts via video output, users can receive information visually. Video distribution is carried out through a streaming service, and the user interface is built using React Native.

[0112] As a concrete example, let's consider a scenario where a user wants to learn about "AI-powered marketing optimization." Upon receiving this input, the generative AI model suggests relevant experts and content related to their expertise. The user can then select and view this content via video streaming. The generative AI model uses prompts such as the following:

[0113] "Please suggest an expert on AI-powered marketing optimization."

[0114] "Find top creators in data science and share their relevant content."

[0115] In this way, the server, terminal, and user work together as a unified system, enabling efficient and effective information delivery to users.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] Users input their technical interests and learning goals using their devices. The input includes specific topics such as "AI-driven marketing optimization." This information is sent to the server. The frontend is built with React Native to analyze the input data.

[0119] Step 2:

[0120] The server stores the received user input in a database using an information storage mechanism. The database used here is a common database management system such as MySQL or MongoDB. The stored information is then used in the next analysis step.

[0121] Step 3:

[0122] The server sends user input to a generative AI model, which analyzes the registration information of experts with relevant skills and experience. The generative AI model assumes an OpenAI model and searches for expert candidates using prompts. Here, a prompt such as "Please suggest experts suitable for AI-driven marketing optimization" is passed to the generative AI model. As output for the data input, a list of suitable experts is created.

[0123] Step 4:

[0124] The server receives the output from the generated AI model and presents a list of experts through a qualified expert display system. On the terminal, this information is displayed on the user's screen, and the user can select the content they want to view from the list of experts.

[0125] Step 5:

[0126] When a user selects content to watch, the server delivers the video content provided by the selected expert through the output device. A video streaming service is used for video delivery, enabling real-time viewing. Users can learn directly from creators and experts with specialized knowledge through a smartphone application.

[0127] This series of steps enables users to smoothly acquire knowledge and access expert information and content related to their areas of interest, creating a system that facilitates this process.

[0128] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0129] The system according to the present invention not only facilitates the matching of users with appropriate experts, but also incorporates an emotion engine to recognize the user's emotional state and optimize the process.

[0130] The system's basic configuration includes a database for storing user input, a processing unit that analyzes skills and experience using generative artificial intelligence, and a matching mechanism equipped with an emotion engine. Users first input their skills, work history, and desired conditions into the system. The server then stores this information in the database, and the generative artificial intelligence generates skill tags.

[0131] When users input their consultation details, their emotional state is recognized by an emotion engine via the device. This emotion recognition is performed by analyzing the user's facial expressions, voice tone, input speed, etc. The server then adds the most suitable expert to the matching list, taking the user's emotional state into consideration. This ensures psychological consideration, for example, suggesting an expert skilled in relaxing communication to a nervous user.

[0132] Even during consultations with matched experts, the emotion engine monitors the user's emotions in real time. If the user's stress level or understanding decreases, the server can recommend additional resources or support to improve the quality of the consultation. For example, if the emotion engine determines that the user is struggling with technical jargon, it will prompt the expert to use simpler language or provide additional materials.

[0133] After the consultation is complete, the server collects feedback from the user and stores this information in a database. The emotion engine also analyzes this feedback and works in conjunction with generative artificial intelligence to improve the accuracy of future matching and consultations. This allows the system to achieve more personalized matching and increase user satisfaction.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] Users access the platform through their devices and enter the information required for registration. This includes their name, email address, skills, work history, and self-introduction.

[0137] Step 2:

[0138] The server stores the information received from the user in a database and checks for format consistency. It then sends the data to a generating AI to analyze the entered skills and work history.

[0139] Step 3:

[0140] The server uses AI generation to analyze the user's skills and work history, and generates relevant skill tags. This clarifies the user's area of ​​expertise.

[0141] Step 4:

[0142] The user (client) enters the details of their consultation request via their terminal. The consultation details specifically describe the technical support or advice they require.

[0143] Step 5:

[0144] The server activates the emotion engine based on the user's inputted consultation content and skill tags. The emotion engine collects the user's emotional data from the device (e.g., facial expressions, voice tone, mouse movements).

[0145] Step 6:

[0146] The server uses the results of the emotion engine analysis to determine the user's current emotional state and extracts experts from the database who can provide an appropriate approach. For example, a user who is feeling anxious will be matched with an expert who is skilled at providing calm and gentle support.

[0147] Step 7:

[0148] The server presents the user with a list of the most suitable experts. Expert profiles and past ratings are displayed, and the user selects from the list.

[0149] Step 8:

[0150] The user confirms their chosen expert and schedules a consultation date, time, and format (video chat, voice call, etc.).

[0151] Step 9:

[0152] The server sends a notification to the expert, synchronizing both parties' schedules. They share the necessary preparation information for the consultation.

[0153] Step 10:

[0154] The user (client and expert) initiates the consultation via a terminal at a designated time. The emotion engine monitors the user's emotional state in real time and provides that information to the expert.

[0155] Step 11:

[0156] The server uses the emotion engine data to recommend additional support and resources as needed, thereby enhancing the effectiveness of the consultation.

[0157] Step 12:

[0158] After the consultation is complete, the user (client) provides feedback on the services provided.

[0159] Step 13:

[0160] The server stores the feedback in a database, and the generative AI and emotion engine use it for analysis to improve the accuracy of future matches.

[0161] (Example 2)

[0162] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0163] To ensure that users are smoothly matched with experts and receive the most appropriate support for their needs, matching must consider not only the user's skills and history, but also their emotional state. Furthermore, to improve the quality of consultations, real-time emotional recognition and improved matching accuracy for subsequent consultations based on feedback are required. The current system lacks process optimization that takes users' emotions into account, and improving the user experience is a challenge.

[0164] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0165] In this invention, the server includes means for storing information provided by the user using a recording device, means for analyzing the user's skills and history using generative artificial intelligence, and means for analyzing the user's emotional state using an emotion engine. This enables matching the user with an appropriate expert that takes into account their skills and emotions, and provides individually optimized support.

[0166] A "recording device" is a data storage method for efficiently and securely storing information provided by users.

[0167] "Generative artificial intelligence" is an artificial intelligence technology that analyzes a user's skills and history and generates skill tags based on that analysis.

[0168] "Selection method" refers to a function that executes a process to present the most suitable expert based on the user's requirements.

[0169] An "emotion engine" is a technology that analyzes a user's emotional state and monitors their emotions using data such as facial expressions and voice tone.

[0170] "Methods for improving matching accuracy" refer to data processing techniques that analyze past feedback to improve matching accuracy in subsequent attempts.

[0171] This invention relates to a system that enables users to be effectively matched with experts and receive optimal support.

[0172] Users first enter information such as their skills, experience, and desired conditions into the system. This input is done via a computer terminal using a web form. Once the information is entered, the server saves it to a storage device. For example, the storage device can use MySQL, which is widely used as a database management system.

[0173] Next, the server uses a generative AI model to analyze the stored user information. This analysis utilizes the Python Transformers library, a natural language processing library. The AI ​​model analyzes the user's skills and history and generates skill tags based on that information.

[0174] The terminal collects data on facial expressions and voice tone as the user enters additional information about their consultation. From this data, an emotion engine analyzes the user's emotional state. This process utilizes software that monitors emotions in real time using a video camera and microphone.

[0175] Next, the server considers the generated skill tags and emotional data to select the most suitable expert for the user and create a matching list. At this stage, for users who are emotionally stressed, the system is designed to select a calm and approachable expert.

[0176] For example, if a user asks for advice because they are having trouble communicating with their boss at their new workplace, a specialist will be recommended. An example of a prompt used in this case might be, "Based on the user's skills information and emotional state, add the most suitable specialist to the matching list and provide the best match for the user's needs."

[0177] This method allows users to receive more personalized service, which can increase their satisfaction.

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] Users enter their skills, experience, and preferences into a web form on a computer terminal. The entered data includes skills, work history, and desired fields. This information is sent to the server when the user clicks the submit button.

[0181] Step 2:

[0182] The server stores information received from users in a storage device. This storage device is a database management system such as MySQL. The information is stored and placed in storage so that it can be quickly accessed when needed.

[0183] Step 3:

[0184] The server analyzes stored user information using a generation AI model. This analysis utilizes the Python Transformers library. Specifically, it analyzes skill and history data using natural language processing techniques to generate skill tags such as "project management" and "data analysis." These skill tags are used as output information to improve matching accuracy.

[0185] Step 4:

[0186] The device collects facial expressions and voice tone in real time via a video camera and microphone as the user enters their consultation details. This provides user emotional data. This emotional data is analyzed by an emotion engine, which helps visualize the user's emotional state.

[0187] Step 5:

[0188] The server selects the most suitable expert based on the generated skill tags and sentiment data. This includes a process of evaluating suitability from an existing expert database. Specifically, for a stressed user, it prioritizes selecting an expert who excels at relaxed communication. The selection results are presented to the user as a matching list.

[0189] Step 6:

[0190] The terminal continuously monitors the user's emotions even during the consultation. Based on the collected emotional data, the server analyzes the user's state. Based on the results, if, for example, it is determined that the user's level of understanding is low, additional resources or support will be provided. Specifically, relevant educational materials may be presented.

[0191] Step 7:

[0192] After the consultation, the user enters feedback. This feedback includes an evaluation of the service and suggestions for future improvements. The server stores this feedback in a database and analyzes it using a generative AI model and an emotion engine. The analysis results are used to improve matching accuracy in future sessions.

[0193] (Application Example 2)

[0194] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0195] Conventional information distribution systems have struggled to recommend optimal content based on user emotions. As a result, personalized content that takes into account the user's psychological state has not been adequately provided, limiting the user experience. This invention aims to provide a system that improves the user experience by analyzing the user's emotional state in real time and recommending appropriate content based on the results.

[0196] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0197] In this invention, the server includes information management means for storing information provided by the user, analysis means using generative artificial intelligence for analyzing the user's skills and history, matching means equipped with an emotion analysis engine for recognizing the user's emotional state, and recommendation means for recommending optimal content based on the user's emotions. This enables appropriate content recommendations according to the user's emotional state.

[0198] An "information management system" is a module that has the function of receiving information provided by users and appropriately storing and managing it.

[0199] The "analysis means" is a module that uses generative artificial intelligence to analyze the user's skills and history, and generates and evaluates related data.

[0200] The "emotion analysis engine" is a module that analyzes data such as facial expressions and voice tone in order to recognize the user's emotional state in real time.

[0201] A "matching tool" is a module that has the function of presenting the optimal combination based on the results of analysis and sentiment recognition in order to connect users with experts or appropriate content.

[0202] A "recommendation tool" is a module that has the function of selecting and presenting the most suitable content to the user based on the user's emotions and interests.

[0203] This invention relates to a system that recognizes a user's emotional state and recommends optimal content based on that state. The system includes information management means, analysis means, an emotion analysis engine, matching means, and recommendation means.

[0204] The server acquires information provided by the user and stores it using information management means. Users input information and interface with the system through devices such as smartphones and smart glasses. The analysis means uses generative artificial intelligence to analyze the user's skills and history and generate relevant skill tags.

[0205] The emotion analysis engine uses the device's camera and microphone to recognize the user's emotional state in real time. This includes the user's facial expressions and voice tone. Based on the emotional state data, the server utilizes recommendation tools to suggest the most suitable content. These recommendation tools select content that matches the user's mood and needs, aiming to improve the user experience.

[0206] For example, if a user enters into the system that they want to relax after work, the emotion analysis engine will interpret that request as emotion data and recommend music or videos suitable for relaxation. A concrete example of a prompt would be, "I'm very tired right now. Please recommend some relaxing content."

[0207] In this way, by using generative AI models, it becomes possible to provide content that responds to the individual emotional state of users, which is expected to improve the overall system performance and increase user satisfaction.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The user enters information through their device and sends it to the server. This information includes the user's technical skills, history, and desired content criteria. The server receives this information and stores it in a database using its information management system.

[0211] Step 2:

[0212] The server analyzes the stored information using analytical tools. Generative artificial intelligence is used to generate relevant skill tags from the user's skills and history. The generated skill tags are stored as reference data for matching.

[0213] Step 3:

[0214] The device uses its built-in camera and microphone to capture the user's facial expressions and voice in real time. This data is sent to a server, where an emotion analysis engine recognizes the user's emotional state. The input data used is the user's facial image and voice, and the type and intensity of emotion are output.

[0215] Step 4:

[0216] The server uses matching mechanisms to select content appropriate to the user's emotional state, based on the output of the emotion analysis engine. This selection takes into account emotions and skill tags. A list of optimal content is generated and passed to the recommendation mechanism.

[0217] Step 5:

[0218] The recommendation system presents selected content to the user. The recommended content becomes viewable on the user's device. For example, relaxing music or videos are displayed, and in response to a prompt such as, "I'm very tired right now. Can you recommend some relaxing content?", the system suggests the most suitable options for the user.

[0219] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0220] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0221] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0225] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0226] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0227] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0228] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0229] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0230] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0231] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0232] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0233] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0234] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0235] The system according to the present invention is for efficiently matching users with experts who possess the necessary IT skills, and an embodiment thereof is shown below.

[0236] At the heart of the system is a processing unit utilizing a database and generative artificial intelligence. Users first input their own information into the system, which is then stored in the database. This information includes skill sets, work experience, and desired conditions.

[0237] Next, the server sends this information to a generating artificial intelligence (AI) that analyzes the user's skills and background and generates skill tags. These skill tags are a crucial element for visually and mechanically identifying the user's expertise and experience.

[0238] The system extracts the necessary skills based on the user's input of their consultation request and searches for a suitable expert. Specific consultation requests entered via the terminal are described in a format such as "improving the UI / UX design of a mobile application." The server then uses AI generation to create a list of optimal experts and presents them to the candidates.

[0239] If a selected expert is deemed capable of meeting the user's requirements, the user (client and expert) can conduct an online consultation. This process can be conducted, for example, through a video conferencing system or messaging platform. Smooth communication between both parties will enable the user to obtain the desired solution.

[0240] Finally, after the consultation ends, users provide feedback, which the server saves to a database. This feedback is analyzed by a generative AI and used to improve future matching accuracy. For example, based on the information obtained from the feedback, the system learns to provide better support in the next matching.

[0241] This allows the system to provide users with a sustainable and efficient matching service, enabling them to make effective use of their free time.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] Users access the platform using their devices and fill out the registration form with the required information, including skills, work history, email address, and password.

[0245] Step 2:

[0246] The server verifies the registration information received from the user, checking the format and data integrity. Once verification is complete, the information is saved to the database.

[0247] Step 3:

[0248] The server uses artificial intelligence to analyze stored user information and generate specific skill tags. This clarifies the user's expertise and past experience.

[0249] Step 4:

[0250] The user (client) enters specific consultation details via their terminal. These details include specifics of the problem they want to solve and the skills they require.

[0251] Step 5:

[0252] The server analyzes the input consultation content, and the generating AI sets criteria for extracting experts with the appropriate skills and experience from the database.

[0253] Step 6:

[0254] The server uses artificial intelligence to generate a list of experts best suited to the client's needs and presents it to the client. The list includes the experts' profiles and skill sets.

[0255] Step 7:

[0256] The user (client) selects a suitable expert from the presented list and schedules a consultation.

[0257] Step 8:

[0258] The server notifies the selected expert, confirms both parties' schedules, and then schedules a session using methods such as video chat.

[0259] Step 9:

[0260] Users (clients and experts) conduct consultations via terminals using specified methods and engage in concrete discussions toward resolving the problem.

[0261] Step 10:

[0262] The user (client) enters feedback regarding the content and results of the consultation.

[0263] Step 11:

[0264] The server stores the feedback in a database, and the generated artificial intelligence uses that feedback to perform analysis to improve future matching accuracy.

[0265] (Example 1)

[0266] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0267] In today's business environment, efficiently finding and matching IT professionals with the required skills is a significant challenge. While it's essential to quickly select the most suitable professionals to meet diverse user needs and ensure smooth communication, traditional systems have been insufficient in this regard.

[0268] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0269] In this invention, the server includes information storage means, processing means using artificial intelligence, matching means, label generation means, and communication means. This enables the rapid and accurate matching of the most suitable expert based on the information provided by the user, and facilitates online consultations, thereby smoothing the expert selection process and subsequent communication.

[0270] An "information storage means" is a device or mechanism that stores information provided by users in a database and allows it to be retrieved as needed.

[0271] "Processing means using artificial intelligence" refers to a device or system that uses artificial intelligence technology to analyze the skills and background of a user.

[0272] A "matching method" is a device or process that has the function of selecting and presenting an appropriate expert based on the content of the user's consultation.

[0273] A "label generation means" is a device or mechanism that analyzes the characteristics of users and experts to generate skill tags and stores them in a database.

[0274] "Communication means" refers to devices with communication technologies, such as video conferencing systems and messaging platforms, used by users and experts to conduct online consultations.

[0275] This invention is a system for efficiently matching users with suitable experts, and is implemented using information storage means, processing means using artificial intelligence, matching means, label generation means, and communication means. In the implementation of the system, the server, terminal, and user each play their respective roles.

[0276] The server stores personal information, skill sets, work history, and desired conditions entered by users through their terminals in an information storage device. This information is stored in a database and retrieved as needed.

[0277] Next, the server utilizes processing means using artificial intelligence and analyzes the user's skills and experience using a generative AI model called "SkillTagger". Skill tags are generated through this analysis, and the tags are saved in the database as label generation means. As an example of a specific prompt sentence, there is "Please generate skill tags from this information".

[0278] When the user inputs the consultation content from the terminal, the server uses matching means to send the consultation content to the generative AI model "SkillMatcher", and uses a prompt sentence "Please list up suitable experts for this consultation". Through this process, a list of optimal experts is created and presented to the user.

[0279] Based on the candidate list, the user uses communication means to conduct an online consultation. Specifically, the user directly consults with the expert through a video conferencing system or a messaging platform. By using this means, the user can efficiently communicate with the expert and seek necessary solutions.

[0280] As described above, this invention enables quick and accurate matching with the experts required by the user, and smoothly progresses the operation of the entire system.

[0281] The flow of specific processing in Example 1 will be described using FIG. 11.

[0282] Step 1:

[0283] The user uses the terminal to input data such as personal information, skill set, work experience, and desired conditions. This is sent to the information storage means. The input data is saved in the database by the server using the information storage means. Specifically, an operation is performed to accurately save the information input by the user in the corresponding fields of the database.

[0284] Step 2:

[0285] The server retrieves user information from the database and sends it to the generative AI model "SkillTagger" to generate skill tags. The input is the user information from the database, and the output is the skill tags. The generative AI model analyzes the user information via a prompt sentence "Please generate skill tags from this information" and generates skill tags as the analysis result. The generated skill tags are saved in the database again.

[0286] Step 3:

[0287] The user inputs specific consultation content via the terminal. Examples include "Improvement of the UI / UX design of a new mobile app", etc. This input data is sent to the server and processed using matching means.

[0288] Step 4:

[0289] The server sends the consultation content to the generative AI model "SkillMatcher" to list appropriate experts. The input is the user's consultation content, and the output is a list of appropriate experts. The generative AI model uses a prompt sentence "Please list appropriate experts for this consultation" to analyze the skills required for the consultation content and select corresponding experts.

[0290] Step 5:

[0291] The server presents the list of experts to the user. The user can select a suitable expert from the presented list. In this step, the human interface used is important and is designed so that the user can easily navigate the list.

[0292] Step 6:

[0293] The user and the selected expert initiate an online consultation using communication methods. Specifically, they communicate directly using video conferencing systems or messaging platforms. The inputs here are the user's and expert's schedules and the selected communication methods, while the output is the actual communication activity.

[0294] Step 7:

[0295] After the consultation is complete, the user sends feedback from their device to the server. This feedback is recorded as evaluation information.

[0296] Step 8:

[0297] The server passes the feedback to the AI ​​model "FeedbackAnalyzer," which performs analysis to improve matching accuracy. The input is feedback information, and the output is an extraction of areas for improvement to be used in future matching. The analyzed results will be used to improve future processes.

[0298] (Application Example 1)

[0299] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0300] Currently, there are limited systems that efficiently match users with experts possessing specific expertise related to information technology. Furthermore, there is a lack of mechanisms to provide users with information on experts that match their interests and preferences, as well as to stream videos to aid understanding. This makes it difficult for users to quickly access the specific knowledge and solutions they seek.

[0301] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0302] In this invention, the server includes an information storage means for storing information provided by the user, an analysis means using a generative AI model for analyzing the user's technology and experience, a compatible person display means for presenting an expert compatible with the user based on the consultation content, and an output means for presenting the transmitted content of the expert by video distribution. As a result, the user can quickly access relevant expertise according to their interests and wishes.

[0303] The "information storage means" is a technical device for efficiently storing and managing information provided by the user.

[0304] The "generative AI model" is an artificial intelligence model used to analyze the user's technology and experience and match appropriate experts.

[0305] The "analysis means" is a device for deeply understanding and classifying the user's technical characteristics and experience based on the provided data.

[0306] The "compatible person display means" is a visual or mechanical device for presenting an expert that matches the user's needs.

[0307] The "information supply means" is a device equipped with a function for providing relevant information of an expert based on the user's interests.

[0308] The "output means" is a technical device for distributing the information provided by the expert as a video and presenting it to the recipient.

[0309] To implement this invention, a system centered around the server for information processing is constructed. The server first stores the information provided by the user in a database using the information storage means. This information includes data on the user's technical background, experience, and particularly the fields of interest. As hardware, a high-performance server is recommended, and as software, a database management system such as MySQL or MongoDB is used.

[0310] Next, the server uses a generative AI model to analyze the user's information and perform skill matching. For example, OpenAI's generative AI model is used. This allows the expert best suited to the user's technical needs to be presented through a match display system.

[0311] On the device, information delivery means provide relevant specialized content based on the user's interests, utilizing the knowledge and skills provided by experts. In particular, by distributing information from experts via video output, users can receive information visually. Video distribution is carried out through a streaming service, and the user interface is built using React Native.

[0312] As a concrete example, let's consider a scenario where a user wants to learn about "AI-powered marketing optimization." Upon receiving this input, the generative AI model suggests relevant experts and content related to their expertise. The user can then select and view this content via video streaming. The generative AI model uses prompts such as the following:

[0313] "Please suggest an expert on AI-powered marketing optimization."

[0314] "Find top creators in data science and share their relevant content."

[0315] In this way, the server, terminal, and user work together as a unified system, enabling efficient and effective information delivery to users.

[0316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0317] Step 1:

[0318] Users input their technical interests and learning goals using their devices. The input includes specific topics such as "AI-driven marketing optimization." This information is sent to the server. The frontend is built with React Native to analyze the input data.

[0319] Step 2:

[0320] The server stores the received user input in a database using an information storage mechanism. The database used here is a common database management system such as MySQL or MongoDB. The stored information is then used in the next analysis step.

[0321] Step 3:

[0322] The server sends user input to a generative AI model, which analyzes the registration information of experts with relevant skills and experience. The generative AI model assumes an OpenAI model and searches for expert candidates using prompts. Here, a prompt such as "Please suggest experts suitable for AI-driven marketing optimization" is passed to the generative AI model. As output for the data input, a list of suitable experts is created.

[0323] Step 4:

[0324] The server receives the output from the generated AI model and presents a list of experts through a qualified expert display system. On the terminal, this information is displayed on the user's screen, and the user can select the content they want to view from the list of experts.

[0325] Step 5:

[0326] When a user selects content to watch, the server delivers the video content provided by the selected expert through the output device. A video streaming service is used for video delivery, enabling real-time viewing. Users can learn directly from creators and experts with specialized knowledge through a smartphone application.

[0327] This series of steps enables users to smoothly acquire knowledge and access expert information and content related to their areas of interest, creating a system that facilitates this process.

[0328] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0329] The system according to the present invention not only facilitates the matching of users with appropriate experts, but also incorporates an emotion engine to recognize the user's emotional state and optimize the process.

[0330] The system's basic configuration includes a database for storing user input, a processing unit that analyzes skills and experience using generative artificial intelligence, and a matching mechanism equipped with an emotion engine. Users first input their skills, work history, and desired conditions into the system. The server then stores this information in the database, and the generative artificial intelligence generates skill tags.

[0331] When users input their consultation details, their emotional state is recognized by an emotion engine via the device. This emotion recognition is performed by analyzing the user's facial expressions, voice tone, input speed, etc. The server then adds the most suitable expert to the matching list, taking the user's emotional state into consideration. This ensures psychological consideration, for example, suggesting an expert skilled in relaxing communication to a nervous user.

[0332] Even during consultations with matched experts, the emotion engine monitors the user's emotions in real time. If the user's stress level or understanding decreases, the server can recommend additional resources or support to improve the quality of the consultation. For example, if the emotion engine determines that the user is struggling with technical jargon, it will prompt the expert to use simpler language or provide additional materials.

[0333] After the consultation is complete, the server collects feedback from the user and stores this information in a database. The emotion engine also analyzes this feedback and works in conjunction with generative artificial intelligence to improve the accuracy of future matching and consultations. This allows the system to achieve more personalized matching and increase user satisfaction.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] Users access the platform through their devices and enter the information required for registration. This includes their name, email address, skills, work history, and self-introduction.

[0337] Step 2:

[0338] The server stores the information received from the user in a database and checks for format consistency. It then sends the data to a generating AI to analyze the entered skills and work history.

[0339] Step 3:

[0340] The server uses AI generation to analyze the user's skills and work history, and generates relevant skill tags. This clarifies the user's area of ​​expertise.

[0341] Step 4:

[0342] The user (client) enters the details of their consultation request via their terminal. The consultation details specifically describe the technical support or advice they require.

[0343] Step 5:

[0344] The server activates the emotion engine based on the user's inputted consultation content and skill tags. The emotion engine collects the user's emotional data from the device (e.g., facial expressions, voice tone, mouse movements).

[0345] Step 6:

[0346] The server uses the results of the emotion engine analysis to determine the user's current emotional state and extracts experts from the database who can provide an appropriate approach. For example, a user who is feeling anxious will be matched with an expert who is skilled at providing calm and gentle support.

[0347] Step 7:

[0348] The server presents the user with a list of the most suitable experts. Expert profiles and past ratings are displayed, and the user selects from the list.

[0349] Step 8:

[0350] The user confirms their chosen expert and schedules a consultation date, time, and format (video chat, voice call, etc.).

[0351] Step 9:

[0352] The server sends a notification to the expert, synchronizing both parties' schedules. They share the necessary preparation information for the consultation.

[0353] Step 10:

[0354] The user (client and expert) initiates the consultation via a terminal at a designated time. The emotion engine monitors the user's emotional state in real time and provides that information to the expert.

[0355] Step 11:

[0356] The server uses the emotion engine data to recommend additional support and resources as needed, thereby enhancing the effectiveness of the consultation.

[0357] Step 12:

[0358] After the consultation is complete, the user (client) provides feedback on the services provided.

[0359] Step 13:

[0360] The server stores the feedback in a database, and the generative AI and emotion engine use it for analysis to improve the accuracy of future matches.

[0361] (Example 2)

[0362] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0363] To ensure that users are smoothly matched with experts and receive the most appropriate support for their needs, matching must consider not only the user's skills and history, but also their emotional state. Furthermore, to improve the quality of consultations, real-time emotional recognition and improved matching accuracy for subsequent consultations based on feedback are required. The current system lacks process optimization that takes users' emotions into account, and improving the user experience is a challenge.

[0364] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0365] In this invention, the server includes means for storing information provided by the user using a recording device, means for analyzing the user's skills and history using generative artificial intelligence, and means for analyzing the user's emotional state using an emotion engine. This enables matching the user with an appropriate expert that takes into account their skills and emotions, and provides individually optimized support.

[0366] A "recording device" is a data storage method for efficiently and securely storing information provided by users.

[0367] "Generative artificial intelligence" is an artificial intelligence technology that analyzes a user's skills and history and generates skill tags based on that analysis.

[0368] "Selection method" refers to a function that executes a process to present the most suitable expert based on the user's requirements.

[0369] An "emotion engine" is a technology that analyzes a user's emotional state and monitors their emotions using data such as facial expressions and voice tone.

[0370] "Methods for improving matching accuracy" refer to data processing techniques that analyze past feedback to improve matching accuracy in subsequent attempts.

[0371] This invention relates to a system that enables users to be effectively matched with experts and receive optimal support.

[0372] Users first enter information such as their skills, experience, and desired conditions into the system. This input is done via a computer terminal using a web form. Once the information is entered, the server saves it to a storage device. For example, the storage device can use MySQL, which is widely used as a database management system.

[0373] Next, the server uses a generative AI model to analyze the stored user information. This analysis utilizes the Python Transformers library, a natural language processing library. The AI ​​model analyzes the user's skills and history and generates skill tags based on that information.

[0374] The terminal collects data on facial expressions and voice tone as the user enters additional information about their consultation. From this data, an emotion engine analyzes the user's emotional state. This process utilizes software that monitors emotions in real time using a video camera and microphone.

[0375] Next, the server considers the generated skill tags and emotional data to select the most suitable expert for the user and create a matching list. At this stage, for users who are emotionally stressed, the system is designed to select a calm and approachable expert.

[0376] For example, if a user asks for advice because they are having trouble communicating with their boss at their new workplace, a specialist will be recommended. An example of a prompt used in this case might be, "Based on the user's skills information and emotional state, add the most suitable specialist to the matching list and provide the best match for the user's needs."

[0377] This method allows users to receive more personalized service, which can increase their satisfaction.

[0378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0379] Step 1:

[0380] Users enter their skills, experience, and preferences into a web form on a computer terminal. The entered data includes skills, work history, and desired fields. This information is sent to the server when the user clicks the submit button.

[0381] Step 2:

[0382] The server stores information received from users in a storage device. This storage device is a database management system such as MySQL. The information is stored and placed in storage so that it can be quickly accessed when needed.

[0383] Step 3:

[0384] The server analyzes stored user information using a generation AI model. This analysis utilizes the Python Transformers library. Specifically, it analyzes skill and history data using natural language processing techniques to generate skill tags such as "project management" and "data analysis." These skill tags are used as output information to improve matching accuracy.

[0385] Step 4:

[0386] The device collects facial expressions and voice tone in real time via a video camera and microphone as the user enters their consultation details. This provides user emotional data. This emotional data is analyzed by an emotion engine, which helps visualize the user's emotional state.

[0387] Step 5:

[0388] The server selects the most suitable expert based on the generated skill tags and sentiment data. This includes a process of evaluating suitability from an existing expert database. Specifically, for a stressed user, it prioritizes selecting an expert who excels at relaxed communication. The selection results are presented to the user as a matching list.

[0389] Step 6:

[0390] The terminal continuously monitors the user's emotions even during the consultation. Based on the collected emotional data, the server analyzes the user's state. Based on the results, if, for example, it is determined that the user's level of understanding is low, additional resources or support will be provided. Specifically, relevant educational materials may be presented.

[0391] Step 7:

[0392] After the consultation, the user enters feedback. This feedback includes an evaluation of the service and suggestions for future improvements. The server stores this feedback in a database and analyzes it using a generative AI model and an emotion engine. The analysis results are used to improve matching accuracy in future sessions.

[0393] (Application Example 2)

[0394] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0395] Conventional information distribution systems have struggled to recommend optimal content based on user emotions. As a result, personalized content that takes into account the user's psychological state has not been adequately provided, limiting the user experience. This invention aims to provide a system that improves the user experience by analyzing the user's emotional state in real time and recommending appropriate content based on the results.

[0396] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0397] In this invention, the server includes information management means for storing information provided by the user, analysis means using generative artificial intelligence for analyzing the user's skills and history, matching means equipped with an emotion analysis engine for recognizing the user's emotional state, and recommendation means for recommending optimal content based on the user's emotions. This enables appropriate content recommendations according to the user's emotional state.

[0398] An "information management system" is a module that has the function of receiving information provided by users and appropriately storing and managing it.

[0399] The "analysis means" is a module that uses generative artificial intelligence to analyze the user's skills and history, and generates and evaluates related data.

[0400] The "emotion analysis engine" is a module that analyzes data such as facial expressions and voice tone in order to recognize the user's emotional state in real time.

[0401] A "matching tool" is a module that has the function of presenting the optimal combination based on the results of analysis and sentiment recognition in order to connect users with experts or appropriate content.

[0402] A "recommendation tool" is a module that has the function of selecting and presenting the most suitable content to the user based on the user's emotions and interests.

[0403] This invention relates to a system that recognizes a user's emotional state and recommends optimal content based on that state. The system includes information management means, analysis means, an emotion analysis engine, matching means, and recommendation means.

[0404] The server acquires information provided by the user and stores it using information management means. Users input information and interface with the system through devices such as smartphones and smart glasses. The analysis means uses generative artificial intelligence to analyze the user's skills and history and generate relevant skill tags.

[0405] The emotion analysis engine uses the device's camera and microphone to recognize the user's emotional state in real time. This includes the user's facial expressions and voice tone. Based on the emotional state data, the server utilizes recommendation tools to suggest the most suitable content. These recommendation tools select content that matches the user's mood and needs, aiming to improve the user experience.

[0406] For example, if a user enters into the system that they want to relax after work, the emotion analysis engine will interpret that request as emotion data and recommend music or videos suitable for relaxation. A concrete example of a prompt would be, "I'm very tired right now. Please recommend some relaxing content."

[0407] In this way, by using generative AI models, it becomes possible to provide content that responds to the individual emotional state of users, which is expected to improve the overall system performance and increase user satisfaction.

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The user enters information through their device and sends it to the server. This information includes the user's technical skills, history, and desired content criteria. The server receives this information and stores it in a database using its information management system.

[0411] Step 2:

[0412] The server analyzes the stored information using analytical tools. Generative artificial intelligence is used to generate relevant skill tags from the user's skills and history. The generated skill tags are stored as reference data for matching.

[0413] Step 3:

[0414] The device uses its built-in camera and microphone to capture the user's facial expressions and voice in real time. This data is sent to a server, where an emotion analysis engine recognizes the user's emotional state. The input data used is the user's facial image and voice, and the type and intensity of emotion are output.

[0415] Step 4:

[0416] The server uses matching mechanisms to select content appropriate to the user's emotional state, based on the output of the emotion analysis engine. This selection takes into account emotions and skill tags. A list of optimal content is generated and passed to the recommendation mechanism.

[0417] Step 5:

[0418] The recommendation system presents selected content to the user. The recommended content becomes viewable on the user's device. For example, relaxing music or videos are displayed, and in response to a prompt such as, "I'm very tired right now. Can you recommend some relaxing content?", the system suggests the most suitable options for the user.

[0419] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0420] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0421] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0422] [Third Embodiment]

[0423] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0424] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0425] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0426] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0427] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0428] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0429] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0430] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0431] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0432] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0433] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0434] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0435] The system according to the present invention is for efficiently matching users with experts who possess the necessary IT skills, and an embodiment thereof is shown below.

[0436] At the heart of the system is a processing unit utilizing a database and generative artificial intelligence. Users first input their own information into the system, which is then stored in the database. This information includes skill sets, work experience, and desired conditions.

[0437] Next, the server sends this information to a generating artificial intelligence (AI) that analyzes the user's skills and background and generates skill tags. These skill tags are a crucial element for visually and mechanically identifying the user's expertise and experience.

[0438] The system extracts the necessary skills based on the user's input of their consultation request and searches for a suitable expert. Specific consultation requests entered via the terminal are described in a format such as "improving the UI / UX design of a mobile application." The server then uses AI generation to create a list of optimal experts and presents them to the candidates.

[0439] If a selected expert is deemed capable of meeting the user's requirements, the user (client and expert) can conduct an online consultation. This process can be conducted, for example, through a video conferencing system or messaging platform. Smooth communication between both parties will enable the user to obtain the desired solution.

[0440] Finally, after the consultation ends, users provide feedback, which the server saves to a database. This feedback is analyzed by a generative AI and used to improve future matching accuracy. For example, based on the information obtained from the feedback, the system learns to provide better support in the next matching.

[0441] This allows the system to provide users with a sustainable and efficient matching service, enabling them to make effective use of their free time.

[0442] The following describes the processing flow.

[0443] Step 1:

[0444] Users access the platform using their devices and fill out the registration form with the required information, including skills, work history, email address, and password.

[0445] Step 2:

[0446] The server verifies the registration information received from the user, checking the format and data integrity. Once verification is complete, the information is saved to the database.

[0447] Step 3:

[0448] The server uses artificial intelligence to analyze stored user information and generate specific skill tags. This clarifies the user's expertise and past experience.

[0449] Step 4:

[0450] The user (client) enters specific consultation details via their terminal. These details include specifics of the problem they want to solve and the skills they require.

[0451] Step 5:

[0452] The server analyzes the input consultation content, and the generating AI sets criteria for extracting experts with the appropriate skills and experience from the database.

[0453] Step 6:

[0454] The server uses artificial intelligence to generate a list of experts best suited to the client's needs and presents it to the client. The list includes the experts' profiles and skill sets.

[0455] Step 7:

[0456] The user (client) selects a suitable expert from the presented list and schedules a consultation.

[0457] Step 8:

[0458] The server notifies the selected expert, confirms both parties' schedules, and then schedules a session using methods such as video chat.

[0459] Step 9:

[0460] Users (clients and experts) conduct consultations via terminals using specified methods and engage in concrete discussions toward resolving the problem.

[0461] Step 10:

[0462] The user (client) enters feedback regarding the content and results of the consultation.

[0463] Step 11:

[0464] The server stores the feedback in a database, and the generated artificial intelligence uses that feedback to perform analysis to improve future matching accuracy.

[0465] (Example 1)

[0466] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0467] In today's business environment, efficiently finding and matching IT professionals with the required skills is a significant challenge. While it's essential to quickly select the most suitable professionals to meet diverse user needs and ensure smooth communication, traditional systems have been insufficient in this regard.

[0468] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0469] In this invention, the server includes information storage means, processing means using artificial intelligence, matching means, label generation means, and communication means. This enables the rapid and accurate matching of the most suitable expert based on the information provided by the user, and facilitates online consultations, thereby smoothing the expert selection process and subsequent communication.

[0470] An "information storage means" is a device or mechanism that stores information provided by users in a database and allows it to be retrieved as needed.

[0471] "Processing means using artificial intelligence" refers to a device or system that uses artificial intelligence technology to analyze the skills and background of a user.

[0472] A "matching method" is a device or process that has the function of selecting and presenting an appropriate expert based on the content of the user's consultation.

[0473] A "label generation means" is a device or mechanism that analyzes the characteristics of users and experts to generate skill tags and stores them in a database.

[0474] "Communication means" refers to devices with communication technologies, such as video conferencing systems and messaging platforms, used by users and experts to conduct online consultations.

[0475] This invention is a system for efficiently matching users with suitable experts, and is implemented using information storage means, processing means using artificial intelligence, matching means, label generation means, and communication means. In the implementation of the system, the server, terminal, and user each play their respective roles.

[0476] The server stores personal information, skill sets, work history, and desired conditions entered by users through their terminals in an information storage device. This information is stored in a database and retrieved as needed.

[0477] Next, the server utilizes artificial intelligence-based processing to analyze the user's skills and experience using a generative AI model called "SkillTagger." This analysis generates skill tags, which are then stored in a database as a label generation tool. An example of a specific prompt message is, "Generate skill tags from this information."

[0478] When a user enters their consultation details from their device, the server uses a matching mechanism to send the details to the AI ​​model "SkillMatcher," prompting it with the message, "Please list the appropriate experts for this consultation." This process generates a list of the most suitable experts, which are then presented to the user.

[0479] Users utilize communication methods to conduct online consultations based on a list of candidates. Specifically, they directly consult with experts via video conferencing systems and messaging platforms. This method allows users to communicate efficiently with experts and seek the necessary solutions.

[0480] As described above, this invention enables the rapid and accurate matching of users with the experts they require, and facilitates the smooth operation of the entire system.

[0481] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0482] Step 1:

[0483] Users use a terminal to input data such as personal information, skill sets, work history, and desired conditions. This data is sent to a data storage device. The server then uses the data storage device to store the entered data in a database. Specifically, the system works to ensure that the information entered by the user is accurately stored in the corresponding field in the database.

[0484] Step 2:

[0485] The server retrieves user information from the database and sends it to the generating AI model "SkillTagger" to generate skill tags. The input is user information from the database, and the output is skill tags. The generating AI model analyzes the user information via a prompt message, "Generate skill tags from this information," and generates skill tags as a result of the analysis. The generated skill tags are then saved back into the database.

[0486] Step 3:

[0487] Users input specific consultation details via their devices. Examples include "improving the UI / UX design of a new mobile app." This input data is sent to a server and processed using a matching system.

[0488] Step 4:

[0489] The server sends the consultation details to the generating AI model "SkillMatcher" to list appropriate experts. The input is the user's consultation details, and the output is a list of appropriate experts. The generating AI model uses the prompt "Please list the appropriate experts for this consultation" to analyze the skills required for the consultation and select the corresponding experts.

[0490] Step 5:

[0491] The server presents the user with a list of experts. The user can then select a suitable expert from the presented list. In this step, the human interface used is crucial; it must be designed to allow the user to easily navigate the list.

[0492] Step 6:

[0493] The user and the selected expert initiate an online consultation using communication methods. Specifically, they communicate directly using video conferencing systems or messaging platforms. The inputs here are the user's and expert's schedules and the selected communication methods, while the output is the actual communication activity.

[0494] Step 7:

[0495] After the consultation is complete, the user sends feedback from their device to the server. This feedback is recorded as evaluation information.

[0496] Step 8:

[0497] The server passes the feedback to the AI ​​model "FeedbackAnalyzer," which performs analysis to improve matching accuracy. The input is feedback information, and the output is an extraction of areas for improvement to be used in future matching. The analyzed results will be used to improve future processes.

[0498] (Application Example 1)

[0499] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0500] Currently, there are limited systems that efficiently match users with experts possessing specific expertise related to information technology. Furthermore, there is a lack of mechanisms to provide users with information on experts that match their interests and preferences, as well as to stream videos to aid understanding. This makes it difficult for users to quickly access the specific knowledge and solutions they seek.

[0501] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0502] In this invention, the server includes information storage means for storing information provided by the user, analysis means using a generative AI model for analyzing the user's skills and background, suitable expert display means for presenting experts suitable for the user based on the consultation content, and output means for presenting the expert's communication content via video distribution. This enables the user to quickly access relevant expertise according to their interests and preferences.

[0503] An "information storage means" is a technological device for efficiently storing and managing information provided by users.

[0504] A "generative AI model" is an artificial intelligence model used to analyze a user's skills and background and match them with the appropriate expert.

[0505] An "analysis tool" is a device used to deeply understand and classify the user's technical characteristics and background based on the provided data.

[0506] A "suitability indicator" is a visual or mechanical device for presenting a specialist who meets the user's needs.

[0507] An "information supply device" is a device equipped with the function of providing relevant information from experts based on the user's interests.

[0508] "Output means" refers to a technological device for distributing information provided by experts as video and presenting it to recipients.

[0509] To implement this invention, a server-centric information processing system is constructed. The server first stores information provided by users in a database using an information storage means. This information includes data on the user's technical background, career history, and areas of particular interest. A high-performance server is recommended as hardware, and a database management system such as MySQL or MongoDB is used as software.

[0510] Next, the server uses a generative AI model to analyze the user's information and perform skill matching. For example, OpenAI's generative AI model is used. This allows the expert best suited to the user's technical needs to be presented through a match display system.

[0511] On the device, information delivery means provide relevant specialized content based on the user's interests, utilizing the knowledge and skills provided by experts. In particular, by distributing information from experts via video output, users can receive information visually. Video distribution is carried out through a streaming service, and the user interface is built using React Native.

[0512] As a concrete example, let's consider a scenario where a user wants to learn about "AI-powered marketing optimization." Upon receiving this input, the generative AI model suggests relevant experts and content related to their expertise. The user can then select and view this content via video streaming. The generative AI model uses prompts such as the following:

[0513] "Please suggest an expert on AI-powered marketing optimization."

[0514] "Find top creators in data science and share their relevant content."

[0515] In this way, the server, terminal, and user work together as a unified system, enabling efficient and effective information delivery to users.

[0516] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0517] Step 1:

[0518] Users input their technical interests and learning goals using their devices. The input includes specific topics such as "AI-driven marketing optimization." This information is sent to the server. The frontend is built with React Native to analyze the input data.

[0519] Step 2:

[0520] The server stores the received user input in a database using an information storage mechanism. The database used here is a common database management system such as MySQL or MongoDB. The stored information is then used in the next analysis step.

[0521] Step 3:

[0522] The server sends user input to a generative AI model, which analyzes the registration information of experts with relevant skills and experience. The generative AI model assumes an OpenAI model and searches for expert candidates using prompts. Here, a prompt such as "Please suggest experts suitable for AI-driven marketing optimization" is passed to the generative AI model. As output for the data input, a list of suitable experts is created.

[0523] Step 4:

[0524] The server receives the output from the generated AI model and presents a list of experts through a qualified expert display system. On the terminal, this information is displayed on the user's screen, and the user can select the content they want to view from the list of experts.

[0525] Step 5:

[0526] When a user selects content to watch, the server delivers the video content provided by the selected expert through the output device. A video streaming service is used for video delivery, enabling real-time viewing. Users can learn directly from creators and experts with specialized knowledge through a smartphone application.

[0527] This series of steps enables users to smoothly acquire knowledge and access expert information and content related to their areas of interest, creating a system that facilitates this process.

[0528] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0529] The system according to the present invention not only facilitates the matching of users with appropriate experts, but also incorporates an emotion engine to recognize the user's emotional state and optimize the process.

[0530] The system's basic configuration includes a database for storing user input, a processing unit that analyzes skills and experience using generative artificial intelligence, and a matching mechanism equipped with an emotion engine. Users first input their skills, work history, and desired conditions into the system. The server then stores this information in the database, and the generative artificial intelligence generates skill tags.

[0531] When users input their consultation details, their emotional state is recognized by an emotion engine via the device. This emotion recognition is performed by analyzing the user's facial expressions, voice tone, input speed, etc. The server then adds the most suitable expert to the matching list, taking the user's emotional state into consideration. This ensures psychological consideration, for example, suggesting an expert skilled in relaxing communication to a nervous user.

[0532] Even during consultations with matched experts, the emotion engine monitors the user's emotions in real time. If the user's stress level or understanding decreases, the server can recommend additional resources or support to improve the quality of the consultation. For example, if the emotion engine determines that the user is struggling with technical jargon, it will prompt the expert to use simpler language or provide additional materials.

[0533] After the consultation is complete, the server collects feedback from the user and stores this information in a database. The emotion engine also analyzes this feedback and works in conjunction with generative artificial intelligence to improve the accuracy of future matching and consultations. This allows the system to achieve more personalized matching and increase user satisfaction.

[0534] The following describes the processing flow.

[0535] Step 1:

[0536] Users access the platform through their devices and enter the information required for registration. This includes their name, email address, skills, work history, and self-introduction.

[0537] Step 2:

[0538] The server stores the information received from the user in a database and checks for format consistency. It then sends the data to a generating AI to analyze the entered skills and work history.

[0539] Step 3:

[0540] The server uses AI generation to analyze the user's skills and work history, and generates relevant skill tags. This clarifies the user's area of ​​expertise.

[0541] Step 4:

[0542] The user (client) enters the details of their consultation request via their terminal. The consultation details specifically describe the technical support or advice they require.

[0543] Step 5:

[0544] The server activates the emotion engine based on the user's inputted consultation content and skill tags. The emotion engine collects the user's emotional data from the device (e.g., facial expressions, voice tone, mouse movements).

[0545] Step 6:

[0546] The server uses the results of the emotion engine analysis to determine the user's current emotional state and extracts experts from the database who can provide an appropriate approach. For example, a user who is feeling anxious will be matched with an expert who is skilled at providing calm and gentle support.

[0547] Step 7:

[0548] The server presents the user with a list of the most suitable experts. Expert profiles and past ratings are displayed, and the user selects from the list.

[0549] Step 8:

[0550] The user confirms their chosen expert and schedules a consultation date, time, and format (video chat, voice call, etc.).

[0551] Step 9:

[0552] The server sends a notification to the expert, synchronizing both parties' schedules. They share the necessary preparation information for the consultation.

[0553] Step 10:

[0554] The user (client and expert) initiates the consultation via a terminal at a designated time. The emotion engine monitors the user's emotional state in real time and provides that information to the expert.

[0555] Step 11:

[0556] The server uses the emotion engine data to recommend additional support and resources as needed, thereby enhancing the effectiveness of the consultation.

[0557] Step 12:

[0558] After the consultation is complete, the user (client) provides feedback on the services provided.

[0559] Step 13:

[0560] The server stores the feedback in a database, and the generative AI and emotion engine use it for analysis to improve the accuracy of future matches.

[0561] (Example 2)

[0562] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0563] To ensure that users are smoothly matched with experts and receive the most appropriate support for their needs, matching must consider not only the user's skills and history, but also their emotional state. Furthermore, to improve the quality of consultations, real-time emotional recognition and improved matching accuracy for subsequent consultations based on feedback are required. The current system lacks process optimization that takes users' emotions into account, and improving the user experience is a challenge.

[0564] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0565] In this invention, the server includes means for storing information provided by the user using a recording device, means for analyzing the user's skills and history using generative artificial intelligence, and means for analyzing the user's emotional state using an emotion engine. This enables matching the user with an appropriate expert that takes into account their skills and emotions, and provides individually optimized support.

[0566] A "recording device" is a data storage method for efficiently and securely storing information provided by users.

[0567] "Generative artificial intelligence" is an artificial intelligence technology that analyzes a user's skills and history and generates skill tags based on that analysis.

[0568] "Selection method" refers to a function that executes a process to present the most suitable expert based on the user's requirements.

[0569] An "emotion engine" is a technology that analyzes a user's emotional state and monitors their emotions using data such as facial expressions and voice tone.

[0570] "Methods for improving matching accuracy" refer to data processing techniques that analyze past feedback to improve matching accuracy in subsequent attempts.

[0571] This invention relates to a system that enables users to be effectively matched with experts and receive optimal support.

[0572] Users first enter information such as their skills, experience, and desired conditions into the system. This input is done via a computer terminal using a web form. Once the information is entered, the server saves it to a storage device. For example, the storage device can use MySQL, which is widely used as a database management system.

[0573] Next, the server uses a generative AI model to analyze the stored user information. This analysis utilizes the Python Transformers library, a natural language processing library. The AI ​​model analyzes the user's skills and history and generates skill tags based on that information.

[0574] The terminal collects data on facial expressions and voice tone as the user enters additional information about their consultation. From this data, an emotion engine analyzes the user's emotional state. This process utilizes software that monitors emotions in real time using a video camera and microphone.

[0575] Next, the server considers the generated skill tags and emotional data to select the most suitable expert for the user and create a matching list. At this stage, for users who are emotionally stressed, the system is designed to select a calm and approachable expert.

[0576] For example, if a user asks for advice because they are having trouble communicating with their boss at their new workplace, a specialist will be recommended. An example of a prompt used in this case might be, "Based on the user's skills information and emotional state, add the most suitable specialist to the matching list and provide the best match for the user's needs."

[0577] This method allows users to receive more personalized service, which can increase their satisfaction.

[0578] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0579] Step 1:

[0580] Users enter their skills, experience, and preferences into a web form on a computer terminal. The entered data includes skills, work history, and desired fields. This information is sent to the server when the user clicks the submit button.

[0581] Step 2:

[0582] The server stores information received from users in a storage device. This storage device is a database management system such as MySQL. The information is stored and placed in storage so that it can be quickly accessed when needed.

[0583] Step 3:

[0584] The server analyzes stored user information using a generation AI model. This analysis utilizes the Python Transformers library. Specifically, it analyzes skill and history data using natural language processing techniques to generate skill tags such as "project management" and "data analysis." These skill tags are used as output information to improve matching accuracy.

[0585] Step 4:

[0586] The device collects facial expressions and voice tone in real time via a video camera and microphone as the user enters their consultation details. This provides user emotional data. This emotional data is analyzed by an emotion engine, which helps visualize the user's emotional state.

[0587] Step 5:

[0588] The server selects the most suitable expert based on the generated skill tags and sentiment data. This includes a process of evaluating suitability from an existing expert database. Specifically, for a stressed user, it prioritizes selecting an expert who excels at relaxed communication. The selection results are presented to the user as a matching list.

[0589] Step 6:

[0590] The terminal continuously monitors the user's emotions even during the consultation. Based on the collected emotional data, the server analyzes the user's state. Based on the results, if, for example, it is determined that the user's level of understanding is low, additional resources or support will be provided. Specifically, relevant educational materials may be presented.

[0591] Step 7:

[0592] After the consultation, the user enters feedback. This feedback includes an evaluation of the service and suggestions for future improvements. The server stores this feedback in a database and analyzes it using a generative AI model and an emotion engine. The analysis results are used to improve matching accuracy in future sessions.

[0593] (Application Example 2)

[0594] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0595] Conventional information distribution systems have struggled to recommend optimal content based on user emotions. As a result, personalized content that takes into account the user's psychological state has not been adequately provided, limiting the user experience. This invention aims to provide a system that improves the user experience by analyzing the user's emotional state in real time and recommending appropriate content based on the results.

[0596] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0597] In this invention, the server includes information management means for storing information provided by the user, analysis means using generative artificial intelligence for analyzing the user's skills and history, matching means equipped with an emotion analysis engine for recognizing the user's emotional state, and recommendation means for recommending optimal content based on the user's emotions. This enables appropriate content recommendations according to the user's emotional state.

[0598] An "information management system" is a module that has the function of receiving information provided by users and appropriately storing and managing it.

[0599] The "analysis means" is a module that uses generative artificial intelligence to analyze the user's skills and history, and generates and evaluates related data.

[0600] The "emotion analysis engine" is a module that analyzes data such as facial expressions and voice tone in order to recognize the user's emotional state in real time.

[0601] A "matching tool" is a module that has the function of presenting the optimal combination based on the results of analysis and sentiment recognition in order to connect users with experts or appropriate content.

[0602] A "recommendation tool" is a module that has the function of selecting and presenting the most suitable content to the user based on the user's emotions and interests.

[0603] This invention relates to a system that recognizes a user's emotional state and recommends optimal content based on that state. The system includes information management means, analysis means, an emotion analysis engine, matching means, and recommendation means.

[0604] The server acquires information provided by the user and stores it using information management means. Users input information and interface with the system through devices such as smartphones and smart glasses. The analysis means uses generative artificial intelligence to analyze the user's skills and history and generate relevant skill tags.

[0605] The emotion analysis engine uses the device's camera and microphone to recognize the user's emotional state in real time. This includes the user's facial expressions and voice tone. Based on the emotional state data, the server utilizes recommendation tools to suggest the most suitable content. These recommendation tools select content that matches the user's mood and needs, aiming to improve the user experience.

[0606] For example, if a user enters into the system that they want to relax after work, the emotion analysis engine will interpret that request as emotion data and recommend music or videos suitable for relaxation. A concrete example of a prompt would be, "I'm very tired right now. Please recommend some relaxing content."

[0607] In this way, by using generative AI models, it becomes possible to provide content that responds to the individual emotional state of users, which is expected to improve the overall system performance and increase user satisfaction.

[0608] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0609] Step 1:

[0610] The user enters information through their device and sends it to the server. This information includes the user's technical skills, history, and desired content criteria. The server receives this information and stores it in a database using its information management system.

[0611] Step 2:

[0612] The server analyzes the stored information using analytical tools. Generative artificial intelligence is used to generate relevant skill tags from the user's skills and history. The generated skill tags are stored as reference data for matching.

[0613] Step 3:

[0614] The device uses its built-in camera and microphone to capture the user's facial expressions and voice in real time. This data is sent to a server, where an emotion analysis engine recognizes the user's emotional state. The input data used is the user's facial image and voice, and the type and intensity of emotion are output.

[0615] Step 4:

[0616] The server uses matching mechanisms to select content appropriate to the user's emotional state, based on the output of the emotion analysis engine. This selection takes into account emotions and skill tags. A list of optimal content is generated and passed to the recommendation mechanism.

[0617] Step 5:

[0618] The recommendation system presents selected content to the user. The recommended content becomes viewable on the user's device. For example, relaxing music or videos are displayed, and in response to a prompt such as, "I'm very tired right now. Can you recommend some relaxing content?", the system suggests the most suitable options for the user.

[0619] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0620] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0621] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0622] [Fourth Embodiment]

[0623] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0624] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0625] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0626] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0627] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0628] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0629] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0630] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0631] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0632] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0633] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0634] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0635] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0636] The system according to the present invention is for efficiently matching users with experts who possess the necessary IT skills, and an embodiment thereof is shown below.

[0637] At the heart of the system is a processing unit utilizing a database and generative artificial intelligence. Users first input their own information into the system, which is then stored in the database. This information includes skill sets, work experience, and desired conditions.

[0638] Next, the server sends this information to a generating artificial intelligence (AI) that analyzes the user's skills and background and generates skill tags. These skill tags are a crucial element for visually and mechanically identifying the user's expertise and experience.

[0639] The system extracts the necessary skills based on the user's input of their consultation request and searches for a suitable expert. Specific consultation requests entered via the terminal are described in a format such as "improving the UI / UX design of a mobile application." The server then uses AI generation to create a list of optimal experts and presents them to the candidates.

[0640] If a selected expert is deemed capable of meeting the user's requirements, the user (client and expert) can conduct an online consultation. This process can be conducted, for example, through a video conferencing system or messaging platform. Smooth communication between both parties will enable the user to obtain the desired solution.

[0641] Finally, after the consultation ends, users provide feedback, which the server saves to a database. This feedback is analyzed by a generative AI and used to improve future matching accuracy. For example, based on the information obtained from the feedback, the system learns to provide better support in the next matching.

[0642] This allows the system to provide users with a sustainable and efficient matching service, enabling them to make effective use of their free time.

[0643] The following describes the processing flow.

[0644] Step 1:

[0645] Users access the platform using their devices and fill out the registration form with the required information, including skills, work history, email address, and password.

[0646] Step 2:

[0647] The server verifies the registration information received from the user, checking the format and data integrity. Once verification is complete, the information is saved to the database.

[0648] Step 3:

[0649] The server uses artificial intelligence to analyze stored user information and generate specific skill tags. This clarifies the user's expertise and past experience.

[0650] Step 4:

[0651] The user (client) enters specific consultation details via their terminal. These details include specifics of the problem they want to solve and the skills they require.

[0652] Step 5:

[0653] The server analyzes the input consultation content, and the generating AI sets criteria for extracting experts with the appropriate skills and experience from the database.

[0654] Step 6:

[0655] The server uses artificial intelligence to generate a list of experts best suited to the client's needs and presents it to the client. The list includes the experts' profiles and skill sets.

[0656] Step 7:

[0657] The user (client) selects a suitable expert from the presented list and schedules a consultation.

[0658] Step 8:

[0659] The server notifies the selected expert, confirms both parties' schedules, and then schedules a session using methods such as video chat.

[0660] Step 9:

[0661] Users (clients and experts) conduct consultations via terminals using specified methods and engage in concrete discussions toward resolving the problem.

[0662] Step 10:

[0663] The user (client) enters feedback regarding the content and results of the consultation.

[0664] Step 11:

[0665] The server stores the feedback in a database, and the generated artificial intelligence uses that feedback to perform analysis to improve future matching accuracy.

[0666] (Example 1)

[0667] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0668] In today's business environment, efficiently finding and matching IT professionals with the required skills is a significant challenge. While it's essential to quickly select the most suitable professionals to meet diverse user needs and ensure smooth communication, traditional systems have been insufficient in this regard.

[0669] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0670] In this invention, the server includes information storage means, processing means using artificial intelligence, matching means, label generation means, and communication means. This enables the rapid and accurate matching of the most suitable expert based on the information provided by the user, and facilitates online consultations, thereby smoothing the expert selection process and subsequent communication.

[0671] An "information storage means" is a device or mechanism that stores information provided by users in a database and allows it to be retrieved as needed.

[0672] "Processing means using artificial intelligence" refers to a device or system that uses artificial intelligence technology to analyze the skills and background of a user.

[0673] A "matching method" is a device or process that has the function of selecting and presenting an appropriate expert based on the content of the user's consultation.

[0674] A "label generation means" is a device or mechanism that analyzes the characteristics of users and experts to generate skill tags and stores them in a database.

[0675] "Communication means" refers to devices with communication technologies, such as video conferencing systems and messaging platforms, used by users and experts to conduct online consultations.

[0676] This invention is a system for efficiently matching users with suitable experts, and is implemented using information storage means, processing means using artificial intelligence, matching means, label generation means, and communication means. In the implementation of the system, the server, terminal, and user each play their respective roles.

[0677] The server stores personal information, skill sets, work history, and desired conditions entered by users through their terminals in an information storage device. This information is stored in a database and retrieved as needed.

[0678] Next, the server utilizes artificial intelligence-based processing to analyze the user's skills and experience using a generative AI model called "SkillTagger." This analysis generates skill tags, which are then stored in a database as a label generation tool. An example of a specific prompt message is, "Generate skill tags from this information."

[0679] When a user enters their consultation details from their device, the server uses a matching mechanism to send the details to the AI ​​model "SkillMatcher," prompting it with the message, "Please list the appropriate experts for this consultation." This process generates a list of the most suitable experts, which are then presented to the user.

[0680] Users utilize communication methods to conduct online consultations based on a list of candidates. Specifically, they directly consult with experts via video conferencing systems and messaging platforms. This method allows users to communicate efficiently with experts and seek the necessary solutions.

[0681] As described above, this invention enables the rapid and accurate matching of users with the experts they require, and facilitates the smooth operation of the entire system.

[0682] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0683] Step 1:

[0684] Users use a terminal to input data such as personal information, skill sets, work history, and desired conditions. This data is sent to a data storage device. The server then uses the data storage device to store the entered data in a database. Specifically, the system works to ensure that the information entered by the user is accurately stored in the corresponding field in the database.

[0685] Step 2:

[0686] The server retrieves user information from the database and sends it to the generating AI model "SkillTagger" to generate skill tags. The input is user information from the database, and the output is skill tags. The generating AI model analyzes the user information via a prompt message, "Generate skill tags from this information," and generates skill tags as a result of the analysis. The generated skill tags are then saved back into the database.

[0687] Step 3:

[0688] Users input specific consultation details via their devices. Examples include "improving the UI / UX design of a new mobile app." This input data is sent to a server and processed using a matching system.

[0689] Step 4:

[0690] The server sends the consultation details to the generating AI model "SkillMatcher" to list appropriate experts. The input is the user's consultation details, and the output is a list of appropriate experts. The generating AI model uses the prompt "Please list the appropriate experts for this consultation" to analyze the skills required for the consultation and select the corresponding experts.

[0691] Step 5:

[0692] The server presents the user with a list of experts. The user can then select a suitable expert from the presented list. In this step, the human interface used is crucial; it must be designed to allow the user to easily navigate the list.

[0693] Step 6:

[0694] The user and the selected expert initiate an online consultation using communication methods. Specifically, they communicate directly using video conferencing systems or messaging platforms. The inputs here are the user's and expert's schedules and the selected communication methods, while the output is the actual communication activity.

[0695] Step 7:

[0696] After the consultation is complete, the user sends feedback from their device to the server. This feedback is recorded as evaluation information.

[0697] Step 8:

[0698] The server passes the feedback to the AI ​​model "FeedbackAnalyzer," which performs analysis to improve matching accuracy. The input is feedback information, and the output is an extraction of areas for improvement to be used in future matching. The analyzed results will be used to improve future processes.

[0699] (Application Example 1)

[0700] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0701] Currently, there are limited systems that efficiently match users with experts possessing specific expertise related to information technology. Furthermore, there is a lack of mechanisms to provide users with information on experts that match their interests and preferences, as well as to stream videos to aid understanding. This makes it difficult for users to quickly access the specific knowledge and solutions they seek.

[0702] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0703] In this invention, the server includes information storage means for storing information provided by the user, analysis means using a generative AI model for analyzing the user's skills and background, suitable expert display means for presenting experts suitable for the user based on the consultation content, and output means for presenting the expert's communication content via video distribution. This enables the user to quickly access relevant expertise according to their interests and preferences.

[0704] An "information storage means" is a technological device for efficiently storing and managing information provided by users.

[0705] A "generative AI model" is an artificial intelligence model used to analyze a user's skills and background and match them with the appropriate expert.

[0706] An "analysis tool" is a device used to deeply understand and classify the user's technical characteristics and background based on the provided data.

[0707] A "suitability indicator" is a visual or mechanical device for presenting a specialist who meets the user's needs.

[0708] An "information supply device" is a device equipped with the function of providing relevant information from experts based on the user's interests.

[0709] "Output means" refers to a technological device for distributing information provided by experts as video and presenting it to recipients.

[0710] To implement this invention, a server-centric information processing system is constructed. The server first stores information provided by users in a database using an information storage means. This information includes data on the user's technical background, career history, and areas of particular interest. A high-performance server is recommended as hardware, and a database management system such as MySQL or MongoDB is used as software.

[0711] Next, the server uses a generative AI model to analyze the user's information and perform skill matching. For example, OpenAI's generative AI model is used. This allows the expert best suited to the user's technical needs to be presented through a match display system.

[0712] On the device, information delivery means provide relevant specialized content based on the user's interests, utilizing the knowledge and skills provided by experts. In particular, by distributing information from experts via video output, users can receive information visually. Video distribution is carried out through a streaming service, and the user interface is built using React Native.

[0713] As a concrete example, let's consider a scenario where a user wants to learn about "AI-powered marketing optimization." Upon receiving this input, the generative AI model suggests relevant experts and content related to their expertise. The user can then select and view this content via video streaming. The generative AI model uses prompts such as the following:

[0714] "Please suggest an expert on AI-powered marketing optimization."

[0715] "Find top creators in data science and share their relevant content."

[0716] In this way, the server, terminal, and user work together as a unified system, enabling efficient and effective information delivery to users.

[0717] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0718] Step 1:

[0719] Users input their technical interests and learning goals using their devices. The input includes specific topics such as "AI-driven marketing optimization." This information is sent to the server. The frontend is built with React Native to analyze the input data.

[0720] Step 2:

[0721] The server stores the received user input in a database using an information storage mechanism. The database used here is a common database management system such as MySQL or MongoDB. The stored information is then used in the next analysis step.

[0722] Step 3:

[0723] The server sends user input to a generative AI model, which analyzes the registration information of experts with relevant skills and experience. The generative AI model assumes an OpenAI model and searches for expert candidates using prompts. Here, a prompt such as "Please suggest experts suitable for AI-driven marketing optimization" is passed to the generative AI model. As output for the data input, a list of suitable experts is created.

[0724] Step 4:

[0725] The server receives the output from the generated AI model and presents a list of experts through a qualified expert display system. On the terminal, this information is displayed on the user's screen, and the user can select the content they want to view from the list of experts.

[0726] Step 5:

[0727] When a user selects content to watch, the server delivers the video content provided by the selected expert through the output device. A video streaming service is used for video delivery, enabling real-time viewing. Users can learn directly from creators and experts with specialized knowledge through a smartphone application.

[0728] This series of steps enables users to smoothly acquire knowledge and access expert information and content related to their areas of interest, creating a system that facilitates this process.

[0729] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0730] The system according to the present invention not only facilitates the matching of users with appropriate experts, but also incorporates an emotion engine to recognize the user's emotional state and optimize the process.

[0731] The system's basic configuration includes a database for storing user input, a processing unit that analyzes skills and experience using generative artificial intelligence, and a matching mechanism equipped with an emotion engine. Users first input their skills, work history, and desired conditions into the system. The server then stores this information in the database, and the generative artificial intelligence generates skill tags.

[0732] When users input their consultation details, their emotional state is recognized by an emotion engine via the device. This emotion recognition is performed by analyzing the user's facial expressions, voice tone, input speed, etc. The server then adds the most suitable expert to the matching list, taking the user's emotional state into consideration. This ensures psychological consideration, for example, suggesting an expert skilled in relaxing communication to a nervous user.

[0733] Even during consultations with matched experts, the emotion engine monitors the user's emotions in real time. If the user's stress level or understanding decreases, the server can recommend additional resources or support to improve the quality of the consultation. For example, if the emotion engine determines that the user is struggling with technical jargon, it will prompt the expert to use simpler language or provide additional materials.

[0734] After the consultation is complete, the server collects feedback from the user and stores this information in a database. The emotion engine also analyzes this feedback and works in conjunction with generative artificial intelligence to improve the accuracy of future matching and consultations. This allows the system to achieve more personalized matching and increase user satisfaction.

[0735] The following describes the processing flow.

[0736] Step 1:

[0737] Users access the platform through their devices and enter the information required for registration. This includes their name, email address, skills, work history, and self-introduction.

[0738] Step 2:

[0739] The server stores the information received from the user in a database and checks for format consistency. It then sends the data to a generating AI to analyze the entered skills and work history.

[0740] Step 3:

[0741] The server uses AI generation to analyze the user's skills and work history, and generates relevant skill tags. This clarifies the user's area of ​​expertise.

[0742] Step 4:

[0743] The user (client) enters the details of their consultation request via their terminal. The consultation details specifically describe the technical support or advice they require.

[0744] Step 5:

[0745] The server activates the emotion engine based on the user's inputted consultation content and skill tags. The emotion engine collects the user's emotional data from the device (e.g., facial expressions, voice tone, mouse movements).

[0746] Step 6:

[0747] The server uses the results of the emotion engine analysis to determine the user's current emotional state and extracts experts from the database who can provide an appropriate approach. For example, a user who is feeling anxious will be matched with an expert who is skilled at providing calm and gentle support.

[0748] Step 7:

[0749] The server presents the user with a list of the most suitable experts. Expert profiles and past ratings are displayed, and the user selects from the list.

[0750] Step 8:

[0751] The user confirms their chosen expert and schedules a consultation date, time, and format (video chat, voice call, etc.).

[0752] Step 9:

[0753] The server sends a notification to the expert, synchronizing both parties' schedules. They share the necessary preparation information for the consultation.

[0754] Step 10:

[0755] The user (client and expert) initiates the consultation via a terminal at a designated time. The emotion engine monitors the user's emotional state in real time and provides that information to the expert.

[0756] Step 11:

[0757] The server uses the emotion engine data to recommend additional support and resources as needed, thereby enhancing the effectiveness of the consultation.

[0758] Step 12:

[0759] After the consultation is complete, the user (client) provides feedback on the services provided.

[0760] Step 13:

[0761] The server stores the feedback in a database, and the generative AI and emotion engine use it for analysis to improve the accuracy of future matches.

[0762] (Example 2)

[0763] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0764] To ensure that users are smoothly matched with experts and receive the most appropriate support for their needs, matching must consider not only the user's skills and history, but also their emotional state. Furthermore, to improve the quality of consultations, real-time emotional recognition and improved matching accuracy for subsequent consultations based on feedback are required. The current system lacks process optimization that takes users' emotions into account, and improving the user experience is a challenge.

[0765] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0766] In this invention, the server includes means for storing information provided by the user using a recording device, means for analyzing the user's skills and history using generative artificial intelligence, and means for analyzing the user's emotional state using an emotion engine. This enables matching the user with an appropriate expert that takes into account their skills and emotions, and provides individually optimized support.

[0767] A "recording device" is a data storage method for efficiently and securely storing information provided by users.

[0768] "Generative artificial intelligence" is an artificial intelligence technology that analyzes a user's skills and history and generates skill tags based on that analysis.

[0769] "Selection method" refers to a function that executes a process to present the most suitable expert based on the user's requirements.

[0770] An "emotion engine" is a technology that analyzes a user's emotional state and monitors their emotions using data such as facial expressions and voice tone.

[0771] "Methods for improving matching accuracy" refer to data processing techniques that analyze past feedback to improve matching accuracy in subsequent attempts.

[0772] This invention relates to a system that enables users to be effectively matched with experts and receive optimal support.

[0773] Users first enter information such as their skills, experience, and desired conditions into the system. This input is done via a computer terminal using a web form. Once the information is entered, the server saves it to a storage device. For example, the storage device can use MySQL, which is widely used as a database management system.

[0774] Next, the server uses a generative AI model to analyze the stored user information. This analysis utilizes the Python Transformers library, a natural language processing library. The AI ​​model analyzes the user's skills and history and generates skill tags based on that information.

[0775] The terminal collects data on facial expressions and voice tone as the user enters additional information about their consultation. From this data, an emotion engine analyzes the user's emotional state. This process utilizes software that monitors emotions in real time using a video camera and microphone.

[0776] Next, the server considers the generated skill tags and emotional data to select the most suitable expert for the user and create a matching list. At this stage, for users who are emotionally stressed, the system is designed to select a calm and approachable expert.

[0777] For example, if a user asks for advice because they are having trouble communicating with their boss at their new workplace, a specialist will be recommended. An example of a prompt used in this case might be, "Based on the user's skills information and emotional state, add the most suitable specialist to the matching list and provide the best match for the user's needs."

[0778] This method allows users to receive more personalized service, which can increase their satisfaction.

[0779] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0780] Step 1:

[0781] Users enter their skills, experience, and preferences into a web form on a computer terminal. The entered data includes skills, work history, and desired fields. This information is sent to the server when the user clicks the submit button.

[0782] Step 2:

[0783] The server stores information received from users in a storage device. This storage device is a database management system such as MySQL. The information is stored and placed in storage so that it can be quickly accessed when needed.

[0784] Step 3:

[0785] The server analyzes stored user information using a generation AI model. This analysis utilizes the Python Transformers library. Specifically, it analyzes skill and history data using natural language processing techniques to generate skill tags such as "project management" and "data analysis." These skill tags are used as output information to improve matching accuracy.

[0786] Step 4:

[0787] The device collects facial expressions and voice tone in real time via a video camera and microphone as the user enters their consultation details. This provides user emotional data. This emotional data is analyzed by an emotion engine, which helps visualize the user's emotional state.

[0788] Step 5:

[0789] The server selects the most suitable expert based on the generated skill tags and sentiment data. This includes a process of evaluating suitability from an existing expert database. Specifically, for a stressed user, it prioritizes selecting an expert who excels at relaxed communication. The selection results are presented to the user as a matching list.

[0790] Step 6:

[0791] The terminal continuously monitors the user's emotions even during the consultation. Based on the collected emotional data, the server analyzes the user's state. Based on the results, if, for example, it is determined that the user's level of understanding is low, additional resources or support will be provided. Specifically, relevant educational materials may be presented.

[0792] Step 7:

[0793] After the consultation, the user enters feedback. This feedback includes an evaluation of the service and suggestions for future improvements. The server stores this feedback in a database and analyzes it using a generative AI model and an emotion engine. The analysis results are used to improve matching accuracy in future sessions.

[0794] (Application Example 2)

[0795] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0796] Conventional information distribution systems have struggled to recommend optimal content based on user emotions. As a result, personalized content that takes into account the user's psychological state has not been adequately provided, limiting the user experience. This invention aims to provide a system that improves the user experience by analyzing the user's emotional state in real time and recommending appropriate content based on the results.

[0797] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0798] In this invention, the server includes information management means for storing information provided by the user, analysis means using generative artificial intelligence for analyzing the user's skills and history, matching means equipped with an emotion analysis engine for recognizing the user's emotional state, and recommendation means for recommending optimal content based on the user's emotions. This enables appropriate content recommendations according to the user's emotional state.

[0799] An "information management system" is a module that has the function of receiving information provided by users and appropriately storing and managing it.

[0800] The "analysis means" is a module that uses generative artificial intelligence to analyze the user's skills and history, and generates and evaluates related data.

[0801] The "emotion analysis engine" is a module that analyzes data such as facial expressions and voice tone in order to recognize the user's emotional state in real time.

[0802] A "matching tool" is a module that has the function of presenting the optimal combination based on the results of analysis and sentiment recognition in order to connect users with experts or appropriate content.

[0803] A "recommendation tool" is a module that has the function of selecting and presenting the most suitable content to the user based on the user's emotions and interests.

[0804] This invention relates to a system that recognizes a user's emotional state and recommends optimal content based on that state. The system includes information management means, analysis means, an emotion analysis engine, matching means, and recommendation means.

[0805] The server acquires information provided by the user and stores it using information management means. Users input information and interface with the system through devices such as smartphones and smart glasses. The analysis means uses generative artificial intelligence to analyze the user's skills and history and generate relevant skill tags.

[0806] The emotion analysis engine uses the device's camera and microphone to recognize the user's emotional state in real time. This includes the user's facial expressions and voice tone. Based on the emotional state data, the server utilizes recommendation tools to suggest the most suitable content. These recommendation tools select content that matches the user's mood and needs, aiming to improve the user experience.

[0807] For example, if a user enters into the system that they want to relax after work, the emotion analysis engine will interpret that request as emotion data and recommend music or videos suitable for relaxation. A concrete example of a prompt would be, "I'm very tired right now. Please recommend some relaxing content."

[0808] In this way, by using generative AI models, it becomes possible to provide content that responds to the individual emotional state of users, which is expected to improve the overall system performance and increase user satisfaction.

[0809] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0810] Step 1:

[0811] The user enters information through their device and sends it to the server. This information includes the user's technical skills, history, and desired content criteria. The server receives this information and stores it in a database using its information management system.

[0812] Step 2:

[0813] The server analyzes the stored information using analytical tools. Generative artificial intelligence is used to generate relevant skill tags from the user's skills and history. The generated skill tags are stored as reference data for matching.

[0814] Step 3:

[0815] The device uses its built-in camera and microphone to capture the user's facial expressions and voice in real time. This data is sent to a server, where an emotion analysis engine recognizes the user's emotional state. The input data used is the user's facial image and voice, and the type and intensity of emotion are output.

[0816] Step 4:

[0817] The server uses matching mechanisms to select content appropriate to the user's emotional state, based on the output of the emotion analysis engine. This selection takes into account emotions and skill tags. A list of optimal content is generated and passed to the recommendation mechanism.

[0818] Step 5:

[0819] The recommendation system presents selected content to the user. The recommended content becomes viewable on the user's device. For example, relaxing music or videos are displayed, and in response to a prompt such as, "I'm very tired right now. Can you recommend some relaxing content?", the system suggests the most suitable options for the user.

[0820] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0821] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0822] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0823] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0824] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0825] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0826] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0827] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0828] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0829] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0830] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0831] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0832] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0833] 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.

[0834] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0835] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0836] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0837] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0838] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0839] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0840] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0841] The following is further disclosed regarding the embodiments described above.

[0842] (Claim 1)

[0843] A database that stores information provided by users,

[0844] A processing unit using generative artificial intelligence to analyze the skills and background of the aforementioned user,

[0845] A system including a matching mechanism that presents a suitable expert to the user based on the content of their consultation.

[0846] (Claim 2)

[0847] The system according to claim 1, comprising a generating artificial intelligence with means for generating skill tags for users and experts.

[0848] (Claim 3)

[0849] The system according to claim 1, wherein, after matching, the user collects feedback on the services provided by the expert, and the generated artificial intelligence has an analysis means to improve the matching accuracy based on that feedback.

[0850] "Example 1"

[0851] (Claim 1)

[0852] Information storage means for storing information provided by users,

[0853] Processing means using artificial intelligence to analyze the skills and background of the aforementioned user,

[0854] A matching means that presents a suitable expert to the user based on the content of the consultation,

[0855] A label generation method for saving the generated skill tags to a database,

[0856] A system that includes communication methods to enable online consultations.

[0857] (Claim 2)

[0858] The system according to claim 1, comprising means for artificial intelligence to generate skill tags for users and experts and to associate said skill tags with a database.

[0859] (Claim 3)

[0860] The system according to claim 1, which, after matching, collects evaluation information from the user regarding the services provided by the expert, and includes an analysis means for artificial intelligence to improve the matching accuracy based on that evaluation information.

[0861] "Application Example 1"

[0862] (Claim 1)

[0863] Information storage means for storing information provided by users,

[0864] An analysis means using a generative AI model to analyze the user's skills and background,

[0865] A means for indicating a suitable expert for the user based on the content of the consultation,

[0866] An information supply means that provides expert-submitted information that takes into account the interests of users,

[0867] An output method that presents the content of expert communications via video streaming,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, wherein the generating AI model includes a generating means for generating user and expert technical tags.

[0871] (Claim 3)

[0872] The system according to claim 1, wherein, after matching, the user collects responses to the submitted content provided by the expert, and the generating AI model includes an analysis means for improving the matching accuracy based on those responses.

[0873] "Example 2 of combining an emotion engine"

[0874] (Claim 1)

[0875] A recording device that stores information provided by users,

[0876] A processing device using generative artificial intelligence that analyzes the skills and history of the aforementioned user,

[0877] A selection method that presents a suitable expert for the user related to the content of the consultation,

[0878] An emotion engine that analyzes the emotional state of the user,

[0879] A means of presenting an expert selected based on the aforementioned emotional state,

[0880] A means to continuously monitor the emotions of clients during consultations and optimize support,

[0881] Analyzing past feedback to improve future matching,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, comprising a generating artificial intelligence with means for generating user and expert skill tags.

[0885] (Claim 3)

[0886] The system according to claim 1, wherein, after matching, the user collects feedback on the services provided by the expert, and the generated artificial intelligence has an analysis means to improve the selection accuracy based on that feedback.

[0887] "Application example 2 of combining emotional engines"

[0888] (Claim 1)

[0889] Information management means for storing information provided by users,

[0890] Analysis means using generative artificial intelligence to analyze the user's technology and history,

[0891] A matching method equipped with an emotion analysis engine that recognizes the emotional state of the user,

[0892] A recommendation system that suggests the most suitable content based on the user's emotions,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, comprising a generating artificial intelligence with means for generating user and expert technical tags.

[0896] (Claim 3)

[0897] The system according to claim 1, wherein, after matching, the user's evaluation of the support provided by the expert is collected, and the generated artificial intelligence has an analysis means to improve the matching accuracy based on that evaluation. [Explanation of Symbols]

[0898] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A database that stores information provided by users, A processing unit using generative artificial intelligence to analyze the skills and background of the aforementioned user, A system including a matching mechanism that presents a suitable expert to the user based on the content of their consultation.

2. The system according to claim 1, wherein the generating artificial intelligence includes means for generating skill tags for users and experts.

3. The system according to claim 1, wherein, after matching, the user collects feedback on the services provided by the expert, and the generated artificial intelligence has an analysis means to improve the matching accuracy based on that feedback.

Images