System

Abstract

A system is provided.SOLUTION: A system including input means for a user to input his / her social experience, life experience, field of interest, and hobby, transmission means for transmitting information from the input means to a server, data preprocessing means for cleaning, normalizing, and categorizing information transmitted from the transmission means, generation AI model application means for applying a generation AI model to specify an optimal industry or company based on information preprocessed by the data preprocessing means, and result display means for displaying a recommendation result of the optimal industry or company obtained from the generation AI model application means to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Modern working people face many challenges when considering a career change. For example, it can be difficult to find the company or industry that best suits them, or to gain a deep understanding of the industry or company they want to work in. Furthermore, many people feel hesitant to step into a new field because they are not clear about how they can utilize their skills and experience. These challenges significantly reduce the effectiveness and efficiency of job hunting. The present invention aims to solve these challenges and help users efficiently and effectively find the company and job type that best suits them. [Means for solving the problem]

[0005] The present invention is a system that includes the following means: An input means is provided for a user to input their work experience, life experience, areas of interest, and hobbies and preferences; a transmission means is provided for transmitting information from the input means to a server; a data preprocessing means is provided for cleaning, normalizing, and categorizing the information transmitted from the transmission means; and a generative AI model application means is provided for applying a generative AI model to identify optimal industries and companies based on the information preprocessed by the data preprocessing means. Furthermore, a result display means is provided for displaying to the user the recommended results of optimal industries and companies obtained from the generative AI model application means. This enables users to find optimal companies and job types that match their experience and interests.

[0006] "Users" refer to working adults who use the system to search for new industries or companies.

[0007] "Input means" refers to an interface that allows a user to input information such as their work experience, life experience, areas of interest, hobbies, and preferences into the system.

[0008] The "transmission means" refers to a function for transmitting information input by the input means to the server.

[0009] "Server" refers to the computer system that processes data for the entire system and applies generative AI models to identify the most suitable industries and companies.

[0010] "Data Pre-Processing Means" refers to processing functions for cleaning, normalizing, and categorizing information transmitted from the Transmission Means.

[0011] A "generative AI model" refers to an algorithmic model that uses machine learning technology to analyze and identify the most suitable industries and companies from input data.

[0012] "Means for applying generative AI models" refers to the processing function for inputting preprocessed data into generative AI models to identify the most suitable industries and companies.

[0013] "Result display means" refers to an interface for displaying to the user the optimal industry and company recommendation results obtained by the generative AI model application means.

[0014] "Guideline display function" refers to a function that displays instructions and explanations to assist and guide the user when entering information through an input means.

[0015] "Scoring" refers to the process by which the generative AI model application means evaluates and ranks the suitability of an industry or company based on the user's preferences and experience. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The system according to the present invention is designed to help users find the most suitable company or industry when job hunting. A specific embodiment of this system will be described below.

[0038] User input of information

[0039] First, the user accesses a dedicated form using a terminal and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), hobbies and preferences (e.g., photography, reading), etc. This input method has a guideline display function that allows the user to easily enter the required information.

[0040] Data transmission by the terminal

[0041] The terminal converts the information input by the user into a data packet and transmits it to the server via the transmission means.

[0042] Data preprocessing by the server

[0043] The server receives the data packets sent from the terminal and performs data preprocessing. The data preprocessing means performs the following processes:

[0044] Cleaning the data (removing unnecessary spaces and special characters)

[0045] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0046] Categorization (e.g., classifying "photography" as a creative skill)

[0047] Applying generative AI models

[0048] The server inputs the preprocessed data into a generative AI model. The generative AI model uses machine learning technology to reference past job-changing data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies and preferences. Specifically, it takes into account the user's hobbies and preferences (e.g., creative skills) and scores the suitability to rank the most suitable industries and companies.

[0049] Generating and displaying recommendations

[0050] The server receives the recommendation results obtained from the generative AI model application means, organizes them appropriately, converts them into data packets, and sends them to the terminal. The terminal receives them and displays a list of recommended industries and companies to the user. The user can check the recommendation results and obtain detailed information about each company and job type. For example, specific companies and job types such as "Marketing Department of XX Co., Ltd." and "Creative Director of XX Solutions Co., Ltd." are displayed.

[0051] Specific examples

[0052] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," the generative AI model will use this information to generate recommendations such as "marketing department of an e-commerce company" or "creative director of an IT solutions company" and present them to the user.

[0053] In this way, the system according to the present invention efficiently and effectively supports users in searching for the most suitable company or job type based on their own experience and interests.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] Users use a terminal to access a dedicated input form and enter their work experience, life experience, areas of interest, and hobbies and preferences, including detailed information such as marketing experience, leadership experience, interest in IT and e-commerce, and hobbies (e.g., photography).

[0057] Step 2:

[0058] The terminal converts the information entered by the user into data packets and transmits them to the server in a manner designed to preserve the consistency and integrity of the data.

[0059] Step 3:

[0060] The server receives data packets sent from the device and performs data preprocessing. Three main processes are performed: cleaning, normalization, and categorization. For example, "5 years of marketing experience" can be converted into "Marketing position, 5 years of experience," and "Photography" can be classified as a creative skill.

[0061] Step 4:

[0062] The server inputs the preprocessed data into a generative AI model, which uses machine learning technology to analyze the user's information and identify the most suitable industry and company by referencing past job change data and a database of company characteristics.

[0063] Step 5:

[0064] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. At this time, the suitability is scored taking into account the user's hobbies and preferences. For example, for a user with creative skills, positions in the creative department will be displayed with a high score.

[0065] Step 6:

[0066] The server organizes the generated recommendation results, converts them into a format that is easy for the user to understand, assembles them into a data packet, and transmits the data packet to the terminal.

[0067] Step 7:

[0068] The device receives the data packet sent from the server and displays a list of recommended industries and companies to the user, including specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[0069] Step 8:

[0070] Users can check the recommendations displayed on their device, obtain detailed information about each company and job type, and take actions such as going to the details page of a company they are interested in and applying for a job.

[0071] Example 1

[0072] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0073] In today's job market, job seekers face the challenge of finding the best job based on their work experience, life experience, areas of interest, and personal preferences. Conventional job change support systems often lack recommendation accuracy by not taking user information into sufficient consideration. In particular, there is a lack of systems that can properly evaluate users' hobbies and personal preferences to recommend the most suitable job type or industry, so there is a need to improve the user experience.

[0074] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0075] In this invention, the server includes an input means for a user to input their work experience, life experience, areas of interest, and personal preferences, a transmission means for transmitting the information from the input means, a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means, a generative AI model application means for identifying the most suitable job type or industry by applying a generative AI model, and a result display means for displaying to the user the recommended job type or industry obtained from the generative AI model application means. This makes it easier for the user to identify the most suitable job type or industry taking into consideration their work experience, life experience, areas of interest, and personal preferences.

[0076] "Work experience" refers to the accumulation of knowledge and skills related to the job or work one has performed.

[0077] "Life experiences" refers to the totality of events, activities, and roles that an individual experiences throughout their life.

[0078] "Areas of interest" refers to areas of study, career, or activity in which an individual has a particular interest.

[0079] "Personal preferences" refers to an individual's hobbies, particular tastes, and activities of interest.

[0080] "Input means" refers to an interface that allows a user to directly input information into the system.

[0081] "Transmission means" refers to a method or protocol for transmitting information acquired from an input means to a server.

[0082] "Data Pre-Processing Means" refers to methods or processes for cleaning, normalizing, and categorizing data transmitted by the Transmission Means.

[0083] "Means for applying generative AI models" refers to a method for applying and analyzing generative AI models based on preprocessed data to identify the most suitable job types and industries.

[0084] "Result display means" refers to an interface for visually presenting to the user the recommendation results obtained from the generative AI model application means.

[0085] The system according to the present invention uses a generative AI model to help users find the most suitable job type and industry when searching for a new job. A specific embodiment of this system will be described.

[0086] User input of information

[0087] First, the user accesses a dedicated form using their device, which contains fields for entering the following information:

[0088] Work experience (e.g., 5 years of marketing experience)

[0089] Life experiences (e.g., leadership experiences)

[0090] Area of ​​interest (e.g. IT, E-commerce)

[0091] Personal preferences (e.g., photography, reading)

[0092] The form uses text boxes and drop-down menus on the device browser to allow users to easily enter information. The form is equipped with a guideline display function to assist users when entering information.

[0093] Data transmission by the terminal

[0094] When the user completes the form and hits the submit button, the device does the following:

[0095] Convert the input information into JSON format.

[0096] The converted data is sent to the server via an HTTPS request.

[0097] This data transmission can be done using JavaScript or other client-side languages, for example, using Ajax to send the data asynchronously.

[0098] Data preprocessing by the server

[0099] The server receives the data sent from the terminal and performs data preprocessing. Specifically, it performs the following processes:

[0100] Cleaning the data: For example, removing unnecessary whitespace and special characters.

[0101] Data normalization: For example, converting "5 years of marketing experience" to "Marketing position, 5 years of experience."

[0102] Categorize: For example, categorize "photography" under "creative skills."

[0103] This preprocessing is performed using a server-side language such as Python or Node.js.

[0104] Applying generative AI models

[0105] The server inputs the preprocessed data into a generative AI model, built using TensorFlow and PyTorch, which performs the following tasks:

[0106] User data is analyzed and compared with past job change data and a database of company characteristics.

[0107] Score your suitability and rank the jobs and industries that best suit you.

[0108] Generate optimal recommendation results taking into account the user's preferences and experience.

[0109] Generating and displaying recommendations

[0110] The server converts the recommendation results obtained from the generative AI model back into data packets and sends them to the device, which then displays the following information to the user:

[0111] A list of recommended companies (e.g., "Marketing Department of Company A")

[0112] A list of recommended job titles (e.g., "Creative Director at Company B")

[0113] Users can view the recommendations and click on links to get more information. The on-device user interface is built using front-end technologies such as React and Vue.js.

[0114] Specific examples

[0115] For example, if a user enters the following information:

[0116] 30s

[0117] 5 years of marketing experience

[0118] My hobby is photography

[0119] His areas of interest are IT and e-commerce.

[0120] In this case, the generative AI model generates recommendations such as "the marketing department of an e-commerce company" or "the creative director of an IT solutions company" and presents them to the user.

[0121] Prompt Sentence Examples

[0122] Examples of prompts:

[0123] "The user is in his 30s, has 5 years of marketing experience, enjoys photography as a hobby, and is interested in IT and e-commerce. Please recommend the most suitable company and job."

[0124] In this way, the system of the present invention helps users identify the most suitable job type and industry based on their work experience, life experience, areas of interest, and personal preferences, thereby enabling users to efficiently find a suitable new job.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1: User enters information

[0127] The user accesses a dedicated form using a terminal and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and personal preferences (e.g., photography, reading). After completing the input, the user presses the submit button. This input data becomes the initial input to the system, and each data field is converted to JSON format.

[0128] Input: User's work experience, life experience, areas of interest, personal preferences

[0129] Output: Converts input data to JSON format

[0130] Step 2: Send data by device

[0131] The device converts the input data into JSON format and sends it to the server via an HTTPS request. This process uses JavaScript and Ajax to send the data to the server asynchronously.

[0132] Input: Input data converted to JSON format

[0133] Output: Data sent to the server via the HTTPS request

[0134] Step 3: Data preprocessing on the server

[0135] The server analyzes the received data, cleans it (removes unnecessary spaces and special characters), normalizes it (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes it (e.g., classifies "photography" as a "creative skill"). Server-side languages ​​such as Python and Node.js are used for these processes.

[0136] Input: Data sent to the server

[0137] Output: Cleaned, normalized, and categorized data

[0138] Step 4: Applying the generative AI model

[0139] The server inputs the preprocessed data into a generative AI model. The generative AI model is built using TensorFlow and PyTorch, and analyzes the user's data and compares it with past job-changing data and a database of company characteristics. This allows it to identify the most suitable job type and industry, taking into account the user's preferences and experience, and then scores and ranks the suitability.

[0140] Input: Preprocessed data

[0141] Output: Generative AI model recommends the best job type and industry

[0142] Step 5: Generate and display recommendations

[0143] The server organizes the recommendation results obtained from the generative AI model, encodes them in JSON format, and sends them to the device. The device receives the recommendation results and visually displays them to the user. Specifically, it uses front-end technologies such as React and Vue.js to display a list of recommended companies and job types. The user can review this information and click links to obtain more information.

[0144] Input: Recommendation results from a generative AI model

[0145] Output: Recommendation results encoded in JSON format, visually displayed to the user

[0146] This process realizes a system that generates and provides users with recommendations for the most suitable job types and industries based on the information they input. This system allows users to find the best job opportunities that reflect their experience and interests.

[0147] (Application example 1)

[0148] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0149] In the past, job-hunting methods have been difficult for users to find the best companies and industries based on their experience and interests. Furthermore, there has been a lack of systems that can effectively process the information entered and provide users with appropriate recommendations. In particular, there has been a demand for a solution that allows users to easily conduct job hunting using devices such as smartphones and smart glasses.

[0150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0151] In this invention, the server includes an input means for a user to input their work experience, life experience, areas of interest, and hobbies and interests, a transmission means for transmitting the information from the input means to the server, a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means, a generative AI model application means for applying a generative AI model to identify optimal industries and companies, a result display means for displaying to the user the optimal industry and company recommendation results obtained from the generative AI model application means, and a virtual career consultant means for displaying the recommendation results to the user via a smartphone or smart glasses and providing further detailed information. This enables a user to easily conduct a job search using their own device and find optimal companies and industries effectively and efficiently.

[0152] The "input means" is a means for a user to input his / her work experience, life experience, areas of interest, and hobbies and interests.

[0153] The "transmission means" is a means for transmitting information from the input means to the server.

[0154] The "data preprocessing means" is a means for cleaning, normalizing, and categorizing the information transmitted from the transmission means.

[0155] The "generative AI model application means" is a means for applying a generative AI model based on information preprocessed by the data preprocessing means to identify the most suitable industries and companies.

[0156] The "means for displaying results" is a means for displaying to the user the optimal industry and company recommendation results obtained from the means for applying the generative AI model.

[0157] The "virtual career consultant means" is a means for displaying recommendation results to users via smartphones or smart glasses, and providing further detailed information.

[0158] The system according to the present invention is designed to allow users to find the most suitable company or industry. A specific embodiment of this system will be described below.

[0159] User input of information

[0160] First, a user accesses a dedicated form using a smartphone or smart glasses and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography, reading). This input method has a guideline display function that allows users to easily enter the required information.

[0161] Data transmission by the terminal

[0162] The user's terminal converts the input information into a data packet and transmits it to the server via a transmission means.

[0163] Data preprocessing by the server

[0164] The server receives data packets sent from the device and cleans the data (removes unnecessary spaces and special characters), normalizes the data (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes it (e.g., classifies "photography" as a creative skill).

[0165] Applying generative AI models

[0166] The server inputs the preprocessed data into a generative AI model. The generative AI model uses machine learning technology to reference past job change data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, fields of interest, and hobbies. Specifically, it takes into account the user's hobbies and interests (e.g., creative skills) and scores the degree of suitability to rank the most suitable industries and companies.

[0167] Generating and displaying recommendations

[0168] The server appropriately organizes the recommendation results obtained from the generative AI model application means, converts them into data packets, and sends them to the terminal. The terminal receives them and displays a list of recommended industries and companies to the user via a smartphone or smart glasses. The user can check the recommendation results and obtain detailed information about each company and job type. For example, specific companies and job types such as "Marketing Department of Co., Ltd. A" and "Creative Director of Co., Ltd. B" are displayed.

[0169] Specific examples

[0170] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," the generative AI model will use this information to generate recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company" and present them to the user. Based on this specific example, the following prompt is input into the generative AI model: "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce."

[0171] In this way, the system according to the present invention efficiently and effectively supports users in searching for the most suitable company or job type based on their own experience and interests.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] Users access a dedicated form using a smartphone or smart glasses. Here, they enter information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography, reading). The input means has a guideline display function to help users easily enter the required information. Input: User's work experience, life experience, areas of interest, and hobbies. Output: Entered user data.

[0175] Step 2:

[0176] The terminal converts the data entered by the user into data packets, which organizes the information into a series of data formats so that the server can process them.The terminal then sends the data packets to the server using a transmission means.Input: User input data.Output: Data packets.

[0177] Step 3:

[0178] The server receives data packets sent from the device. First, it cleans the data and removes unnecessary spaces and special characters. Then it normalizes the data, converting "5 years of marketing experience" to "Marketing position, 5 years of experience". Finally, it categorizes the data and tags "Photography" as a creative skill. Input: Data packet. Output: Preprocessed data.

[0179] Step 4:

[0180] The server inputs the preprocessed data into a generative AI model. This generative AI model references past job change data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies. The generative AI model scores these factors and ranks the most suitable industries and companies for the user. Input: Preprocessed data. Output: Ranked list of industries and companies.

[0181] Step 5:

[0182] The server converts the recommendation results from the generative AI model into a data packet, which is in an organized format and easy for the device to process. The server then sends the data packet to the device. Input: A list of ranked industries and companies. Output: A data packet of recommendation data.

[0183] Step 6:

[0184] The device receives the data packet sent from the server and displays a list of industries and companies recommended to the user. Specific company and job information such as "Marketing Department of Company A" or "Creative Director of Company B" is displayed on the screen of the smartphone or smart glasses. A virtual career consultant means is also used to provide even more detailed information. Input: Data packet of recommendation data. Output: List of recommended companies and industries and detailed information.

[0185] In this way, users can search for the most suitable company and job type based on their experience and interests, enabling them to conduct an efficient and effective job search.

[0186] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0187] The system according to the present invention supports users in finding the most suitable company or industry when job hunting, and further combines it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[0188] User input of information

[0189] First, the user uses a terminal to access a dedicated input form and enters information such as their work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This input method is equipped with a guideline display function to make it easy for users to enter the required information.

[0190] Incorporating an emotion engine

[0191] While the user is entering information, an emotion engine is activated, analyzing the user's facial expressions and voice in real time using the device's built-in camera and microphone. The emotion engine analyzes the user's emotions (e.g., joy, surprise, anxiety, etc.) while they are entering information and collects that data.

[0192] Data transmission and preprocessing

[0193] The terminal converts the information input by the user and the emotion data analyzed by the emotion engine into a data packet and transmits it to the server. The server receives the transmitted data packet and first performs data preprocessing. The data preprocessing means performs the following processes:

[0194] Cleaning the data (removing unnecessary spaces and special characters)

[0195] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0196] Categorization (e.g., classifying "photography" as a creative skill)

[0197] Applying generative AI models

[0198] The server inputs the preprocessed data and emotional data into a generative AI model, which uses machine learning techniques to analyze the input data and references past job change data and a database of company characteristics to identify the most suitable industry and company based on the user's work experience, life experience, areas of interest, and emotional data.

[0199] Generating and displaying recommendations

[0200] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. It also takes the user's emotional data into account and makes adjustments accordingly. For example, if the emotional data confirms that the user is interested in a certain job or company, it will give the relevant job type or company a higher score.

[0201] Organizing and displaying results

[0202] The server organizes the generated recommendations, converts them into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives this and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[0203] Specific examples

[0204] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," and the emotion engine detects that the user is excited or interested when entering information, the generative AI model will interpret this as a positive indicator and generate and present recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company." Based on this user's emotional data, appropriate adjustments are made, resulting in results that are more personally relevant and relevant.

[0205] In this way, the system according to the present invention takes into consideration the user's experience, interests, and even emotional data, and helps the user efficiently and effectively find the most suitable company or job type.

[0206] The processing flow will be explained below.

[0207] Step 1:

[0208] Users use a terminal to access a dedicated input form and enter their work experience, life experience, areas of interest, and hobbies and preferences. For example, they can enter information such as "5 years of marketing experience," "Leadership experience," "Interest in IT and e-commerce," and "Photography is a hobby."

[0209] Step 2:

[0210] The device's built-in camera and microphone capture the user's facial expressions and voice in real time as they type. The emotion engine analyzes these and collects data on the emotions the user is expressing (e.g., joy, excitement, anxiety, etc.).

[0211] Step 3:

[0212] The terminal converts the information input by the user and the emotion data collected by the emotion engine into data packets and transmits them to the server.

[0213] Step 4:

[0214] The server receives the data packets sent from the terminal and performs data pre-processing. The data pre-processing means performs the following processes:

[0215] Cleaning the data (e.g. removing unnecessary whitespace and special characters)

[0216] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0217] Categorization (e.g., classifying "photography" as a creative skill)

[0218] Step 5:

[0219] The server inputs the preprocessed data and emotional data into a generative AI model. The generative AI model uses machine learning techniques to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies and preferences. The model also takes emotional data into account, and if the emotion is positive, it increases the score for that industry or company.

[0220] Step 6:

[0221] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. For example, if a user is interested in IT and e-commerce and has positive feelings about them, the marketing department of an e-commerce company or the creative director of an IT solutions company will be recommended with a high score.

[0222] Step 7:

[0223] The server organizes the generated recommendation results, converts them into an appropriate format, assembles them into a data packet, and transmits it to the terminal.

[0224] Step 8:

[0225] The device receives the data packet sent from the server and displays a list of recommended industries and companies to the user, including specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[0226] Step 9:

[0227] Users can check the recommendations displayed on their device, obtain detailed information about each company and job type, and take actions such as going to the details page of a company they are interested in and applying for a job.

[0228] Through the above processing steps, the system takes into consideration the user's experience, interests, and even emotional data, helping them find the most suitable company or job type efficiently and effectively.

[0229] Example 2

[0230] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0231] Conventional career change support systems have the problem of being unable to provide personalized recommendations that are based not only on the user's work history and areas of interest, but also on the emotions expressed by the user when entering information. This makes it difficult to find jobs and organizations that match the user's true interests and aptitudes.

[0232] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input their work history, life experience, areas of interest, and hobbies; a transmission means for transmitting information from the input means to the processing device; a data preprocessing means for data cleansing, normalizing, and classifying the information transmitted from the transmission means; a generative AI model application means for applying a generative AI model based on the information preprocessed by the data preprocessing means to identify the most suitable job type or organization; a result display means for displaying to the user the recommendation results of the most suitable job type or organization obtained from the generative AI model application means; and an emotion recognition means for collecting emotion data input by the user using an emotion recognition device and reflecting the data in the generative AI model. This enables personalized recommendations that take into account not only the user's experience and areas of interest but also the emotion data.

[0233] "Input means" refers to devices and software that allow users to input their work history, life experiences, areas of interest, and hobbies into the system.

[0234] The "transmission means" refers to a communication function for transmitting information acquired from the input means to a processing device or a server.

[0235] "Data Pre-Processing Means" refers to algorithms and programs for data cleansing, normalizing, and classifying information transmitted from the Transmission Means.

[0236] "Means for applying generative AI models" refers to programs and processes for applying generative AI models based on preprocessed information to identify optimal job types and organizations.

[0237] "Result display means" refers to a device and software for displaying the recommendation results obtained by the generative AI model application means to the user.

[0238] "Emotion recognition means" refers to an emotion recognition device and software for collecting and analyzing emotion data expressed by a user during input.

[0239] "Generative AI models" refer to algorithms and models that use machine learning techniques to analyze user data and identify the most suitable jobs and organizations.

[0240] "Guideline display function" refers to an interface function that provides instructions and hints to assist the user when entering information.

[0241] MODE FOR CARRYING OUT THE INVENTION

[0242] The system according to the present invention supports users in finding the most suitable company or industry when job hunting, and further includes emotion recognition means for recognizing the emotions of the user. Specific embodiments of this system are described below.

[0243] User input of information

[0244] The user uses a terminal to access a dedicated input form and enters information such as work history, life experience, areas of interest, and hobbies. This input method is equipped with a guideline display function to allow the user to easily enter the required information. For example, the user can start a web browser (e.g., Google Chrome or Mozilla Firefox) and access the input form via its URL. Following the input fields, the user enters the following information:

[0245] Work history (e.g., 5 years of marketing experience)

[0246] Life experience (e.g. leadership experience)

[0247] Area of ​​interest (e.g. IT, E-commerce)

[0248] Hobbies (e.g. photography)

[0249] Incorporating emotion recognition measures

[0250] While the user is entering information, the device's built-in camera and microphone are activated to record the user's facial expressions and voice in real time. This allows the emotion recognition means to analyze and collect the user's emotional data (happiness, surprise, anxiety, etc.). This emotion recognition is performed using software such as Amazon Rekognition and Microsoft Azure's Emotion API.

[0251] Data submission and preprocessing

[0252] The terminal converts the information input by the user and the emotion data analyzed by the emotion recognition device into data packets and sends them to the server. This transmission uses Internet protocols (e.g., HTTP, HTTPS). The server receives the transmitted data packets and first performs data preprocessing. The data preprocessing means performs the following processes:

[0253] Data cleansing: Removing unnecessary whitespace and special characters.

[0254] Data normalization: Convert "5 years of marketing experience" to "Marketing position, 5 years of experience."

[0255] Categorization: Classify "photography" as a creative skill.

[0256] Applying generative AI models

[0257] The server inputs the preprocessed data and emotion data into a generative AI model. This generative AI model uses, for example, GPT-4 (OpenAI's language model) or BERT (Google's language understanding model). The server uses these models to analyze the input data and references past job change data and a database of company characteristics. This allows it to identify the most suitable job type and organization based on the user's experience, areas of interest, and emotion data.

[0258] Generating and displaying recommendations

[0259] The generative AI model application means ranks the most suitable jobs and organizations based on the analysis results and generates recommendation results. In doing so, it also takes into account the user's emotional data and adjusts the score accordingly. The server organizes the generated recommendation results, converts them into a user-friendly format, compiles them into a data packet, and sends it to the terminal. The terminal receives this and displays a list of recommended jobs and organizations to the user. This list includes specific company names and job types (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[0260] Specific examples

[0261] For example, if a user inputs information such as "30s, 5 years of marketing experience, hobby is photography, interest areas are IT and e-commerce," and the emotion recognition means indicates that the user is excited or interested when entering information, the generative AI model will consider this as a favorable indicator. As a result, it will generate and present to the user recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company."

[0262] Prompt Sentence Examples

[0263] Here are some example prompts to input to a generative AI model:

[0264] User profile:

[0265] Age: 30s

[0266] Experience: 5 years of marketing experience

[0267] Areas of interest: IT, E-commerce

[0268] Hobbies: Photography

[0269] Emotional Data:

[0270] Excitement: High

[0271] Interest: High

[0272] Based on the information above and sentiment data, identify the industry, company, and job type that would be a perfect fit for this user.

[0273] In this way, the system according to the present invention takes into consideration the user's experience, areas of interest, and even emotional data, and helps the user efficiently and effectively find the most suitable job or organization.

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1:

[0276] The user accesses a dedicated input form using a terminal. They launch a web browser, enter the URL of the input form, and display the screen. The user enters information such as work history, life experience, areas of interest, and hobbies. The input content includes work history (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This information is collected as input data.

[0277] Step 2:

[0278] While the user is entering information, the device's built-in camera and microphone are activated, recording the user's facial expressions and voice in real time. The emotion recognition device analyzes this recorded data and generates emotion data such as joy, surprise, and anxiety. This emotion data is temporarily stored in the device.

[0279] Step 3:

[0280] The device combines the information entered by the user and the emotional data analyzed by the emotion recognition device into a single data packet. The data packet is formatted in JSON or XML format. The user input information and emotional data are packetized.

[0281] Step 4:

[0282] The device sends the generated data packets to the server via the Internet. The data packets are delivered to the server using the HTTP or HTTPS protocol. The server receives the data packets.

[0283] Step 5:

[0284] The server processes the received data packets and performs data cleansing, normalization, and categorization. Data cleansing removes unnecessary spaces and special characters, normalization converts "5 years of marketing experience" to "Marketing position, 5 years of experience," and categorization classifies "photography" as a creative skill. The preprocessed data is generated.

[0285] Step 6:

[0286] The server inputs the preprocessed data and emotion data into a generative AI model. This generative AI model uses, for example, GPT-4 or BERT. The generative AI model analyzes the input data and references past job change data and a database of company characteristics. The analysis results in identifying the most suitable job type and organization.

[0287] Step 7:

[0288] The generative AI model application means ranks the most suitable jobs and organizations based on the analysis results and generates recommendation results. At this time, it also takes into account the user's emotional data and adjusts the scores of related jobs and organizations. The generated recommendation results are compiled into a data packet.

[0289] Step 8:

[0290] The server converts the generated recommendations into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives it and displays a list of recommended jobs and organizations on the screen. The displayed list includes specific company names and job types (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[0291] (Application example 2)

[0292] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0293] In today's job-hunting environment, it is not easy for users to find the perfect company or industry. In particular, there is a need for matching that takes into account not only skills and experience, but also the user's personal interests and emotions. However, conventional systems do not utilize users' emotional data for matching, which hinders efficient and effective job hunting.

[0294] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: an input means for the user to input their work experience, life experience, areas of interest, and hobbies and preferences; an emotion analysis means for analyzing the user's emotions during input and generating user emotion data; a transmission means for transmitting information from the input means and the user emotion data collected by the emotion analysis means to the server; a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means; a generative AI model application means for applying a generative AI model to the information and emotion data preprocessed by the data preprocessing means to identify optimal industries and companies; and a result display means for displaying to the user the recommended industries and companies obtained from the generative AI model application means. This enables more personalized job recommendations that take the user's interests and emotions into consideration.

[0295] The "input means" is a mechanism for allowing a user to input his / her own work experience, life experience, areas of interest, hobbies and preferences.

[0296] The "transmission means" is a mechanism for transmitting information and emotion data from the input means to the server.

[0297] "Data pre-processing means" is a mechanism for cleaning, normalizing, and categorizing information transmitted from a transmission means.

[0298] The "generative AI model application means" is a mechanism for applying a generative AI model to identify the most suitable industries and companies based on the information and emotion data preprocessed by the data preprocessing means.

[0299] The "result display means" is a mechanism for displaying to the user the optimal industry and company recommendation results obtained from the generative AI model application means.

[0300] The "emotion analysis means" is a mechanism for analyzing the user's emotions during input and generating user emotion data.

[0301] The "emotion data transmission means" is a mechanism for transmitting the user's emotion data collected by the emotion analysis means to the server.

[0302] The system according to the present invention assists users in finding the most suitable company or industry when job hunting, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[0303] User input of information

[0304] First, the user uses a terminal to access a dedicated input form and enters information such as their work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This input method is equipped with a guideline display function to make it easy for users to enter the required information.

[0305] emotion recognition

[0306] While the user is entering information, an emotion analysis means operates, which analyzes the user's facial expressions and voice in real time using the camera and microphone installed in the terminal. The emotion analysis means analyzes the emotions (e.g., joy, excitement, anxiety, etc.) while the user is entering information and collects that data.

[0307] Data transmission

[0308] The transmitting means converts the information input by the user and the emotion data collected by the emotion analyzing means into data packets and transmits them to the server.

[0309] Data Preprocessing

[0310] The server receives the transmitted data packet and first performs data pre-processing. The data pre-processing means performs the following processes:

[0311] Cleaning the data (removing unnecessary spaces and special characters)

[0312] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0313] Categorization (e.g., classifying "photography" as a creative skill)

[0314] Applying generative AI models

[0315] The server inputs the preprocessed data and emotional data into a generative AI model, which uses machine learning techniques to analyze the input data and references past job change data and a database of company characteristics to identify the most suitable industry and company based on the user's work experience, life experience, areas of interest, and emotional data.

[0316] Generating and displaying recommendations

[0317] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. It also takes the user's emotional data into account and makes adjustments accordingly. For example, if the emotional data confirms that the user is interested in a certain job or company, it will give the relevant job type or company a higher score.

[0318] Displaying the results

[0319] The server organizes the generated recommendations, converts them into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives the data and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[0320] Specific examples

[0321] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," and sentiment analysis reveals that the user expresses excitement or interest during input, the generative AI model will interpret this as a positive indicator and generate and present recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company." Based on this user's sentiment data, appropriate adjustments are made, resulting in results that are more personally relevant and relevant.

[0322] Prompt Sentence Examples

[0323] "User data: Experience: 5 years of marketing experience, Life experience: Leadership experience, Interests: IT, e-commerce, Hobbies: Photography, Emotions: happy. Please recommend companies and jobs that would be a good fit for this user."

[0324] As described above, this system takes into account the user's experience, interests, and even emotional data to help them find the company and job that best suits them efficiently and effectively.

[0325] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0326] Step 1:

[0327] The user uses a terminal to access a dedicated input form and enters their work experience, life experience, areas of interest, hobbies, and preferences. The input means is equipped with a guideline display function that guides the user to easily enter the necessary information. The input data at this stage is user information such as work experience and hobbies.

[0328] Step 2:

[0329] While the user is inputting information, the device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The emotion analysis means analyzes the user's emotions (e.g., joy, excitement, anxiety, etc.) at the time of input and collects the data. The input is the user's facial expressions and voice information, and the output is analyzed emotional data.

[0330] Step 3:

[0331] The transmitting means of the terminal converts the information input by the user and the emotion data collected by the emotion analysis means into data packets and transmits them to the server. In this step, the input data is the user information and emotion data, and the output data is the transmitted data packets.

[0332] Step 4:

[0333] The server receives the data packet and first performs data preprocessing. The data preprocessing method cleans the data (removes unnecessary spaces and special characters), normalizes the data (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes the data (e.g., classifies "photography" as a creative skill). The input is the raw data sent, and the output is the cleaned and normalized data.

[0334] Step 5:

[0335] The server inputs the preprocessed data and emotion data into the generative AI model. The generative AI model application means uses machine learning technology to analyze the preprocessed user data and emotion data, and identifies the most suitable industry and company by referencing past job change data and a database of company characteristics. The input is the preprocessed user data and emotion data, and the output is the identified industry and company information.

[0336] Step 6:

[0337] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. At this time, emotional data is also taken into consideration and adjustments are made. For example, if emotional data confirms that the user is interested in a particular field, related job types and companies will be given higher scores. The input is company information identified by the model, and the output is ranked recommendation results.

[0338] Step 7:

[0339] The server organizes the generated recommendation results, converts them into a user-friendly format, packages them into data packets, and sends them to the terminal. The input is the ranked recommendation results, and the output is the data packets to be sent.

[0340] Step 8:

[0341] The device receives the data packet and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department at a certain company" or "Creative Director at a certain solutions company"). The input is the data packet, and the output is the recommendation results displayed to the user.

[0342] The above are the specific processing steps of this system.

[0343] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0344] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0345] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0346] [Second embodiment]

[0347] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0348] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0349] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0350] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0351] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0352] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0353] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0354] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0355] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0356] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0357] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0358] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0359] The system according to the present invention is designed to help users find the most suitable company or industry when job hunting. A specific embodiment of this system will be described below.

[0360] User input of information

[0361] First, the user accesses a dedicated form using a terminal and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), hobbies and preferences (e.g., photography, reading), etc. This input method has a guideline display function that allows the user to easily enter the required information.

[0362] Data transmission by the terminal

[0363] The terminal converts the information input by the user into a data packet and transmits it to the server via the transmission means.

[0364] Data preprocessing by the server

[0365] The server receives the data packets sent from the terminal and performs data preprocessing. The data preprocessing means performs the following processes:

[0366] Cleaning the data (removing unnecessary spaces and special characters)

[0367] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0368] Categorization (e.g., classifying "photography" as a creative skill)

[0369] Applying generative AI models

[0370] The server inputs the preprocessed data into a generative AI model. The generative AI model uses machine learning technology to reference past job-changing data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies and preferences. Specifically, it takes into account the user's hobbies and preferences (e.g., creative skills) and scores the suitability to rank the most suitable industries and companies.

[0371] Generating and displaying recommendations

[0372] The server receives the recommendation results obtained from the generative AI model application means, organizes them appropriately, converts them into data packets, and sends them to the terminal. The terminal receives them and displays a list of recommended industries and companies to the user. The user can check the recommendation results and obtain detailed information about each company and job type. For example, specific companies and job types such as "Marketing Department of XX Co., Ltd." and "Creative Director of XX Solutions Co., Ltd." are displayed.

[0373] Specific examples

[0374] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," the generative AI model will use this information to generate recommendations such as "marketing department of an e-commerce company" or "creative director of an IT solutions company" and present them to the user.

[0375] In this way, the system according to the present invention efficiently and effectively supports users in searching for the most suitable company or job type based on their own experience and interests.

[0376] The processing flow will be explained below.

[0377] Step 1:

[0378] Users use a terminal to access a dedicated input form and enter their work experience, life experience, areas of interest, and hobbies and preferences, including detailed information such as marketing experience, leadership experience, interest in IT and e-commerce, and hobbies (e.g., photography).

[0379] Step 2:

[0380] The terminal converts the information entered by the user into data packets and transmits them to the server in a manner designed to preserve the consistency and integrity of the data.

[0381] Step 3:

[0382] The server receives data packets sent from the device and performs data preprocessing. Three main processes are performed: cleaning, normalization, and categorization. For example, "5 years of marketing experience" can be converted into "Marketing position, 5 years of experience," and "Photography" can be classified as a creative skill.

[0383] Step 4:

[0384] The server inputs the preprocessed data into a generative AI model, which uses machine learning technology to analyze the user's information and identifies the most suitable industry and company by referencing past job change data and a database of company characteristics.

[0385] Step 5:

[0386] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. At this time, the suitability is scored taking into account the user's hobbies and preferences. For example, for a user with creative skills, positions in the creative department will be displayed with a high score.

[0387] Step 6:

[0388] The server organizes the generated recommendation results, converts them into a format that is easy for the user to understand, assembles them into a data packet, and transmits the data packet to the terminal.

[0389] Step 7:

[0390] The device receives the data packet sent from the server and displays a list of recommended industries and companies to the user, including specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[0391] Step 8:

[0392] Users can check the recommendations displayed on their device, obtain detailed information about each company and job type, and take actions such as going to the details page of a company they are interested in and applying for a job.

[0393] Example 1

[0394] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0395] In today's job market, job seekers face the challenge of finding the best job based on their work experience, life experience, areas of interest, and personal preferences. Conventional job change support systems often lack recommendation accuracy by not taking user information into sufficient consideration. In particular, there is a lack of systems that can properly evaluate users' hobbies and personal preferences to recommend the most suitable job type or industry, so there is a need to improve the user experience.

[0396] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0397] In this invention, the server includes an input means for a user to input their work experience, life experience, areas of interest, and personal preferences, a transmission means for transmitting the information from the input means, a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means, a generative AI model application means for identifying the most suitable job type or industry by applying a generative AI model, and a result display means for displaying to the user the recommended job type or industry obtained from the generative AI model application means. This makes it easier for the user to identify the most suitable job type or industry taking into consideration their work experience, life experience, areas of interest, and personal preferences.

[0398] "Work experience" refers to the accumulation of knowledge and skills related to the job or work one has performed.

[0399] "Life experiences" refers to the totality of events, activities, and roles that an individual experiences throughout their life.

[0400] "Areas of interest" refers to areas of study, career, or activity in which an individual has a particular interest.

[0401] "Personal preferences" refers to an individual's hobbies, particular tastes, and activities of interest.

[0402] "Input means" refers to an interface that allows a user to directly input information into the system.

[0403] "Transmission means" refers to a method or protocol for transmitting information acquired from an input means to a server.

[0404] "Data Pre-Processing Means" refers to methods or processes for cleaning, normalizing, and categorizing data transmitted by the Transmission Means.

[0405] "Means for applying generative AI models" refers to a method for applying and analyzing generative AI models based on preprocessed data to identify the most suitable job types and industries.

[0406] "Result display means" refers to an interface for visually presenting to the user the recommendation results obtained from the generative AI model application means.

[0407] The system according to the present invention uses a generative AI model to help users find the most suitable job type and industry when searching for a new job. A specific embodiment of this system will be described.

[0408] User input of information

[0409] First, the user accesses a dedicated form using their device, which contains fields for entering the following information:

[0410] Work experience (e.g., 5 years of marketing experience)

[0411] Life experiences (e.g., leadership experiences)

[0412] Area of ​​interest (e.g. IT, E-commerce)

[0413] Personal preferences (e.g., photography, reading)

[0414] The form uses text boxes and drop-down menus on the device browser to allow users to easily enter information. The form is equipped with a guideline display function to assist users when entering information.

[0415] Data transmission by the terminal

[0416] When the user completes the form and hits the submit button, the device does the following:

[0417] Convert the input information into JSON format.

[0418] The converted data is sent to the server via an HTTPS request.

[0419] This data transmission can be done using JavaScript or other client-side languages, for example, using Ajax to send the data asynchronously.

[0420] Data preprocessing by the server

[0421] The server receives the data sent from the terminal and performs data preprocessing. Specifically, it performs the following processes:

[0422] Cleaning the data: For example, removing unnecessary whitespace and special characters.

[0423] Data normalization: For example, converting "5 years of marketing experience" to "Marketing position, 5 years of experience."

[0424] Categorize: For example, categorize "photography" under "creative skills."

[0425] This preprocessing is performed using a server-side language such as Python or Node.js.

[0426] Applying generative AI models

[0427] The server inputs the preprocessed data into a generative AI model, built using TensorFlow and PyTorch, which performs the following tasks:

[0428] User data is analyzed and compared with past job change data and a database of company characteristics.

[0429] Score your suitability and rank the jobs and industries that best suit you.

[0430] Generate optimal recommendation results taking into account the user's preferences and experience.

[0431] Generating and displaying recommendations

[0432] The server converts the recommendation results obtained from the generative AI model back into data packets and sends them to the device, which then displays the following information to the user:

[0433] A list of recommended companies (e.g., "Marketing Department of Company A")

[0434] A list of recommended job titles (e.g., "Creative Director at Company B")

[0435] Users can view the recommendations and click on links to get more information. The on-device user interface is built using front-end technologies such as React and Vue.js.

[0436] Specific examples

[0437] For example, if a user enters the following information:

[0438] 30s

[0439] 5 years of marketing experience

[0440] My hobby is photography

[0441] His areas of interest are IT and e-commerce.

[0442] In this case, the generative AI model generates recommendations such as "the marketing department of an e-commerce company" or "the creative director of an IT solutions company" and presents them to the user.

[0443] Prompt Sentence Examples

[0444] Examples of prompts:

[0445] "The user is in his 30s, has 5 years of marketing experience, enjoys photography as a hobby, and is interested in IT and e-commerce. Please recommend the most suitable company and job."

[0446] In this way, the system of the present invention helps users identify the most suitable job type and industry based on their work experience, life experience, areas of interest, and personal preferences, thereby enabling users to efficiently find a suitable new job.

[0447] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0448] Step 1: User enters information

[0449] The user accesses a dedicated form using a terminal and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and personal preferences (e.g., photography, reading). After completing the input, the user presses the submit button. This input data becomes the initial input to the system, and each data field is converted to JSON format.

[0450] Input: User's work experience, life experience, areas of interest, personal preferences

[0451] Output: Converts input data to JSON format

[0452] Step 2: Send data by device

[0453] The device converts the input data into JSON format and sends it to the server via an HTTPS request. This process uses JavaScript and Ajax to send the data to the server asynchronously.

[0454] Input: Input data converted to JSON format

[0455] Output: Data sent to the server via the HTTPS request

[0456] Step 3: Data preprocessing on the server

[0457] The server analyzes the received data, cleans it (removes unnecessary spaces and special characters), normalizes it (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes it (e.g., classifies "photography" as a "creative skill"). Server-side languages ​​such as Python and Node.js are used for these processes.

[0458] Input: Data sent to the server

[0459] Output: Cleaned, normalized, and categorized data

[0460] Step 4: Applying the generative AI model

[0461] The server inputs the preprocessed data into a generative AI model. The generative AI model is built using TensorFlow and PyTorch, and analyzes the user's data and compares it with past job-changing data and a database of company characteristics. This allows it to identify the most suitable job type and industry, taking into account the user's preferences and experience, and then scores and ranks the suitability.

[0462] Input: Preprocessed data

[0463] Output: Generative AI model recommends the best job type and industry

[0464] Step 5: Generate and display recommendations

[0465] The server organizes the recommendation results obtained from the generative AI model, encodes them in JSON format, and sends them to the device. The device receives the recommendation results and visually displays them to the user. Specifically, it uses front-end technologies such as React and Vue.js to display a list of recommended companies and job types. The user can review this information and click links to obtain more information.

[0466] Input: Recommendation results from a generative AI model

[0467] Output: Recommendation results encoded in JSON format, visually displayed to the user

[0468] This process realizes a system that generates and provides users with recommendations for the most suitable job types and industries based on the information they input. This system allows users to find the best job opportunities that reflect their experience and interests.

[0469] (Application example 1)

[0470] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0471] In the past, job-hunting methods have been difficult for users to find the best companies and industries based on their experience and interests. Furthermore, there has been a lack of systems that can effectively process the information entered and provide users with appropriate recommendations. In particular, there has been a demand for a solution that allows users to easily conduct job hunting using devices such as smartphones and smart glasses.

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

[0473] In this invention, the server includes an input means for a user to input their work experience, life experience, areas of interest, and hobbies and interests, a transmission means for transmitting the information from the input means to the server, a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means, a generative AI model application means for applying a generative AI model to identify optimal industries and companies, a result display means for displaying to the user the optimal industry and company recommendation results obtained from the generative AI model application means, and a virtual career consultant means for displaying the recommendation results to the user via a smartphone or smart glasses and providing further detailed information. This enables a user to easily conduct a job search using their own device and find optimal companies and industries effectively and efficiently.

[0474] The "input means" is a means for a user to input his / her work experience, life experience, areas of interest, and hobbies and interests.

[0475] The "transmission means" is a means for transmitting information from the input means to the server.

[0476] The "data preprocessing means" is a means for cleaning, normalizing, and categorizing the information transmitted from the transmission means.

[0477] The "generative AI model application means" is a means for applying a generative AI model based on information preprocessed by the data preprocessing means to identify the most suitable industries and companies.

[0478] The "means for displaying results" is a means for displaying to the user the optimal industry and company recommendation results obtained from the means for applying the generative AI model.

[0479] The "virtual career consultant means" is a means for displaying recommendation results to users via smartphones or smart glasses, and providing further detailed information.

[0480] The system according to the present invention is designed to help users find the most suitable company or industry. A specific embodiment of this system will be described below.

[0481] User input of information

[0482] First, a user accesses a dedicated form using a smartphone or smart glasses and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography, reading). This input method has a guideline display function that allows users to easily enter the required information.

[0483] Data transmission by the terminal

[0484] The user's terminal converts the input information into a data packet and transmits it to the server via a transmission means.

[0485] Data preprocessing by the server

[0486] The server receives data packets sent from the device and cleans the data (removes unnecessary spaces and special characters), normalizes the data (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes it (e.g., classifies "photography" as a creative skill).

[0487] Applying generative AI models

[0488] The server inputs the preprocessed data into a generative AI model. The generative AI model uses machine learning technology to reference past job change data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, fields of interest, and hobbies. Specifically, it takes into account the user's hobbies and interests (e.g., creative skills) and scores the degree of suitability to rank the most suitable industries and companies.

[0489] Generating and displaying recommendations

[0490] The server appropriately organizes the recommendation results obtained from the generative AI model application means, converts them into data packets, and sends them to the terminal. The terminal receives them and displays a list of recommended industries and companies to the user via a smartphone or smart glasses. The user can check the recommendation results and obtain detailed information about each company and job type. For example, specific companies and job types such as "Marketing Department of Co., Ltd. A" and "Creative Director of Co., Ltd. B" are displayed.

[0491] Specific examples

[0492] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," the generative AI model will use this information to generate recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company" and present them to the user. Based on this specific example, the following prompt is input into the generative AI model: "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce."

[0493] In this way, the system according to the present invention efficiently and effectively supports users in searching for the most suitable company or job type based on their own experience and interests.

[0494] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0495] Step 1:

[0496] Users access a dedicated form using a smartphone or smart glasses. Here, they enter information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography, reading). The input means has a guideline display function to help users easily enter the required information. Input: User's work experience, life experience, areas of interest, and hobbies. Output: Entered user data.

[0497] Step 2:

[0498] The terminal converts the data entered by the user into data packets, which organizes the information into a series of data formats so that the server can process them.The terminal then sends the data packets to the server using a transmission means.Input: User input data.Output: Data packets.

[0499] Step 3:

[0500] The server receives data packets sent from the device. First, it cleans the data and removes unnecessary spaces and special characters. Then it normalizes the data, converting "5 years of marketing experience" to "Marketing position, 5 years of experience". Finally, it categorizes the data and tags "Photography" as a creative skill. Input: Data packet. Output: Preprocessed data.

[0501] Step 4:

[0502] The server inputs the preprocessed data into a generative AI model. This generative AI model references past job change data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies. The generative AI model scores these factors and ranks the most suitable industries and companies for the user. Input: Preprocessed data. Output: Ranked list of industries and companies.

[0503] Step 5:

[0504] The server converts the recommendation results from the generative AI model into a data packet, which is in an organized format and easy for the device to process. The server then sends the data packet to the device. Input: A list of ranked industries and companies. Output: A data packet of recommendation data.

[0505] Step 6:

[0506] The device receives the data packet sent from the server and displays a list of industries and companies recommended to the user. Specific company and job information such as "Marketing Department of Company A" or "Creative Director of Company B" is displayed on the screen of the smartphone or smart glasses. A virtual career consultant means is also used to provide even more detailed information. Input: Data packet of recommendation data. Output: List of recommended companies and industries and detailed information.

[0507] In this way, users can search for the most suitable company and job type based on their experience and interests, enabling them to conduct an efficient and effective job search.

[0508] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0509] The system according to the present invention supports users in finding the most suitable company or industry when job hunting, and further combines it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[0510] User input of information

[0511] First, the user uses a terminal to access a dedicated input form and enters information such as their work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This input method is equipped with a guideline display function to make it easy for users to enter the required information.

[0512] Incorporating an emotion engine

[0513] While the user is entering information, an emotion engine is activated, analyzing the user's facial expressions and voice in real time using the device's built-in camera and microphone. The emotion engine analyzes the user's emotions (e.g., joy, surprise, anxiety, etc.) while they are entering information and collects that data.

[0514] Data transmission and preprocessing

[0515] The terminal converts the information input by the user and the emotion data analyzed by the emotion engine into a data packet and transmits it to the server. The server receives the transmitted data packet and first performs data preprocessing. The data preprocessing means performs the following processes:

[0516] Cleaning the data (removing unnecessary spaces and special characters)

[0517] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0518] Categorization (e.g., classifying "photography" as a creative skill)

[0519] Applying generative AI models

[0520] The server inputs the preprocessed data and emotional data into a generative AI model, which uses machine learning techniques to analyze the input data and references past job change data and a database of company characteristics to identify the most suitable industry and company based on the user's work experience, life experience, areas of interest, and emotional data.

[0521] Generating and displaying recommendations

[0522] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. It also takes the user's emotional data into account and makes adjustments accordingly. For example, if the emotional data confirms that the user is interested in a certain job or company, it will give the relevant job type or company a higher score.

[0523] Organizing and displaying results

[0524] The server organizes the generated recommendations, converts them into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives this and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[0525] Specific examples

[0526] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," and the emotion engine detects that the user is excited or interested when entering information, the generative AI model will interpret this as a positive indicator and generate and present recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company." Based on this user's emotional data, appropriate adjustments are made, resulting in results that are more personally relevant and relevant.

[0527] In this way, the system according to the present invention takes into consideration the user's experience, interests, and even emotional data, and helps the user efficiently and effectively find the most suitable company or job type.

[0528] The processing flow will be explained below.

[0529] Step 1:

[0530] Users use a terminal to access a dedicated input form and enter their work experience, life experience, areas of interest, and hobbies and preferences. For example, they can enter information such as "5 years of marketing experience," "has leadership experience," "interest in IT and e-commerce," or "photography is my hobby."

[0531] Step 2:

[0532] The device's built-in camera and microphone capture the user's facial expressions and voice in real time as they type. The emotion engine analyzes these and collects data on the emotions the user is expressing (e.g., joy, excitement, anxiety, etc.).

[0533] Step 3:

[0534] The terminal converts the information input by the user and the emotion data collected by the emotion engine into data packets and transmits them to the server.

[0535] Step 4:

[0536] The server receives the data packets sent from the terminal and performs data pre-processing. The data pre-processing means performs the following processes:

[0537] Cleaning the data (e.g. removing unnecessary whitespace and special characters)

[0538] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0539] Categorization (e.g., classifying "photography" as a creative skill)

[0540] Step 5:

[0541] The server inputs the preprocessed data and emotional data into a generative AI model. The generative AI model uses machine learning techniques to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies and preferences. The model also takes emotional data into account, and if the emotion is positive, it increases the score for that industry or company.

[0542] Step 6:

[0543] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. For example, if a user is interested in IT and e-commerce and has positive feelings about them, the marketing department of an e-commerce company or the creative director of an IT solutions company will be recommended with a high score.

[0544] Step 7:

[0545] The server organizes the generated recommendation results, converts them into an appropriate format, assembles them into a data packet, and transmits it to the terminal.

[0546] Step 8:

[0547] The device receives the data packet sent from the server and displays a list of recommended industries and companies to the user, including specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[0548] Step 9:

[0549] Users can check the recommendations displayed on their device, obtain detailed information about each company and job type, and take actions such as going to the details page of a company they are interested in and applying for a job.

[0550] Through the above processing steps, the system takes into consideration the user's experience, interests, and even emotional data, helping them find the most suitable company or job type efficiently and effectively.

[0551] Example 2

[0552] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0553] Conventional career change support systems have the problem of being unable to provide personalized recommendations that are based not only on the user's work history and areas of interest, but also on the emotions expressed by the user when entering information. This makes it difficult to find jobs and organizations that match the user's true interests and aptitudes.

[0554] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input their work history, life experience, areas of interest, and hobbies; a transmission means for transmitting information from the input means to the processing device; a data preprocessing means for data cleansing, normalizing, and classifying the information transmitted from the transmission means; a generative AI model application means for applying a generative AI model based on the information preprocessed by the data preprocessing means to identify the most suitable job type or organization; a result display means for displaying to the user the recommendation results of the most suitable job type or organization obtained from the generative AI model application means; and an emotion recognition means for collecting emotion data input by the user using an emotion recognition device and reflecting the data in the generative AI model. This enables personalized recommendations that take into account not only the user's experience and areas of interest but also the emotion data.

[0555] "Input means" refers to devices and software that allow users to input their work history, life experiences, areas of interest, and hobbies into the system.

[0556] The "transmission means" refers to a communication function for transmitting information acquired from the input means to a processing device or a server.

[0557] "Data Pre-Processing Means" refers to algorithms and programs for data cleansing, normalizing, and classifying information transmitted from the Transmission Means.

[0558] "Means for applying a generative AI model" refers to the program and process for applying a generative AI model based on preprocessed information to identify the most suitable job type or organization.

[0559] "Result display means" refers to a device and software for displaying the recommendation results obtained by the generative AI model application means to the user.

[0560] "Emotion recognition means" refers to an emotion recognition device and software for collecting and analyzing emotion data expressed by a user during input.

[0561] "Generative AI models" refer to algorithms and models that use machine learning techniques to analyze user data and identify the most suitable jobs and organizations.

[0562] "Guideline display function" refers to an interface function that provides instructions and hints to assist the user when entering information.

[0563] MODE FOR CARRYING OUT THE INVENTION

[0564] The system according to the present invention supports users in finding the most suitable company or industry when job hunting, and further includes emotion recognition means for recognizing the emotions of the user. Specific embodiments of this system are described below.

[0565] User input of information

[0566] The user uses a terminal to access a dedicated input form and enters information such as work history, life experience, areas of interest, and hobbies. This input method is equipped with a guideline display function to allow the user to easily enter the required information. For example, the user can start a web browser (e.g., Google Chrome or Mozilla Firefox) and access the input form via its URL. Following the input fields, the user enters the following information:

[0567] Work history (e.g., 5 years of marketing experience)

[0568] Life experience (e.g. leadership experience)

[0569] Area of ​​interest (e.g. IT, E-commerce)

[0570] Hobbies (e.g. photography)

[0571] Incorporating emotion recognition measures

[0572] While the user is entering information, the device's built-in camera and microphone are activated to record the user's facial expressions and voice in real time. This allows the emotion recognition means to analyze and collect the user's emotional data (happiness, surprise, anxiety, etc.). This emotion recognition is performed using software such as Amazon Rekognition and Microsoft Azure's Emotion API.

[0573] Data submission and preprocessing

[0574] The terminal converts the information input by the user and the emotion data analyzed by the emotion recognition device into data packets and sends them to the server. This transmission uses Internet protocols (e.g., HTTP, HTTPS). The server receives the transmitted data packets and first performs data preprocessing. The data preprocessing means performs the following processes:

[0575] Data cleansing: Removing unnecessary whitespace and special characters.

[0576] Data normalization: Convert "5 years of marketing experience" to "Marketing position, 5 years of experience."

[0577] Categorization: Classify "photography" as a creative skill.

[0578] Applying generative AI models

[0579] The server inputs the preprocessed data and emotion data into a generative AI model. This generative AI model uses, for example, GPT-4 (OpenAI's language model) or BERT (Google's language understanding model). The server uses these models to analyze the input data and references past job change data and a database of company characteristics. This allows it to identify the most suitable job type and organization based on the user's experience, areas of interest, and emotion data.

[0580] Generating and displaying recommendations

[0581] The generative AI model application means ranks the most suitable jobs and organizations based on the analysis results and generates recommendation results. In doing so, it also takes into account the user's emotional data and adjusts the score accordingly. The server organizes the generated recommendation results, converts them into a user-friendly format, compiles them into a data packet, and sends it to the terminal. The terminal receives this and displays a list of recommended jobs and organizations to the user. This list includes specific company names and job types (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[0582] Specific examples

[0583] For example, if a user inputs information such as "30s, 5 years of marketing experience, hobby is photography, interest areas are IT and e-commerce," and the emotion recognition means indicates that the user is excited or interested when entering information, the generative AI model will consider this as a favorable indicator. As a result, it will generate and present to the user recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company."

[0584] Prompt Sentence Examples

[0585] Here are some example prompts to input to a generative AI model:

[0586] User profile:

[0587] Age: 30s

[0588] Experience: 5 years of marketing experience

[0589] Areas of interest: IT, E-commerce

[0590] Hobbies: Photography

[0591] Emotional Data:

[0592] Excitement: High

[0593] Interest: High

[0594] Based on the information above and sentiment data, identify the industry, company, and job type that would be a perfect fit for this user.

[0595] In this way, the system according to the present invention takes into consideration the user's experience, areas of interest, and even emotional data, and helps the user efficiently and effectively find the most suitable job or organization.

[0596] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0597] Step 1:

[0598] The user accesses a dedicated input form using a terminal. They launch a web browser, enter the URL of the input form, and display the screen. The user enters information such as work history, life experience, areas of interest, and hobbies. The input content includes work history (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This information is collected as input data.

[0599] Step 2:

[0600] While the user is entering information, the device's built-in camera and microphone are activated, recording the user's facial expressions and voice in real time. The emotion recognition device analyzes this recorded data and generates emotion data such as joy, surprise, and anxiety. This emotion data is temporarily stored in the device.

[0601] Step 3:

[0602] The device combines the information entered by the user and the emotional data analyzed by the emotion recognition device into a single data packet. The data packet is formatted in JSON or XML format. The user input information and emotional data are packetized.

[0603] Step 4:

[0604] The device sends the generated data packets to a server over the Internet. The data packets are delivered to the server using the HTTP or HTTPS protocol. The server receives the data packets.

[0605] Step 5:

[0606] The server processes the received data packets and performs data cleansing, normalization, and categorization. Data cleansing removes unnecessary spaces and special characters, normalization converts "5 years of marketing experience" to "Marketing position, 5 years of experience," and categorization classifies "photography" as a creative skill. The preprocessed data is generated.

[0607] Step 6:

[0608] The server inputs the preprocessed data and emotion data into a generative AI model. This generative AI model uses, for example, GPT-4 or BERT. The generative AI model analyzes the input data and references past job change data and a database of company characteristics. The analysis results in identifying the most suitable job type and organization.

[0609] Step 7:

[0610] The generative AI model application means ranks the most suitable jobs and organizations based on the analysis results and generates recommendation results. At this time, it also takes into account the user's emotional data and adjusts the scores of related jobs and organizations. The generated recommendation results are compiled into a data packet.

[0611] Step 8:

[0612] The server converts the generated recommendations into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives it and displays a list of recommended jobs and organizations on the screen. The displayed list includes specific company names and job types (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[0613] (Application example 2)

[0614] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0615] In today's job-hunting environment, it is not easy for users to find the perfect company or industry. In particular, there is a need for matching that takes into account not only skills and experience, but also the user's personal interests and emotions. However, conventional systems do not utilize users' emotional data for matching, which hinders efficient and effective job hunting.

[0616] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: an input means for the user to input their work experience, life experience, areas of interest, and hobbies and preferences; an emotion analysis means for analyzing the user's emotions during input and generating user emotion data; a transmission means for transmitting information from the input means and the user emotion data collected by the emotion analysis means to the server; a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means; a generative AI model application means for applying a generative AI model to the information and emotion data preprocessed by the data preprocessing means to identify optimal industries and companies; and a result display means for displaying to the user the recommended industries and companies obtained from the generative AI model application means. This enables more personalized job recommendations that take the user's interests and emotions into consideration.

[0617] The "input means" is a mechanism for allowing a user to input his / her own work experience, life experience, areas of interest, hobbies and preferences.

[0618] The "transmission means" is a mechanism for transmitting information and emotion data from the input means to the server.

[0619] "Data pre-processing means" is a mechanism for cleaning, normalizing, and categorizing information transmitted from a transmission means.

[0620] The "generative AI model application means" is a mechanism for applying a generative AI model to identify the most suitable industries and companies based on the information and emotion data preprocessed by the data preprocessing means.

[0621] The "result display means" is a mechanism for displaying to the user the optimal industry and company recommendation results obtained from the generative AI model application means.

[0622] The "emotion analysis means" is a mechanism for analyzing the user's emotions during input and generating user emotion data.

[0623] The "emotion data transmission means" is a mechanism for transmitting the user's emotion data collected by the emotion analysis means to the server.

[0624] The system according to the present invention assists users in finding the most suitable company or industry when job hunting, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[0625] User input of information

[0626] First, the user uses a terminal to access a dedicated input form and enters information such as their work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This input method is equipped with a guideline display function to make it easy for users to enter the required information.

[0627] emotion recognition

[0628] While the user is entering information, an emotion analysis means operates, which analyzes the user's facial expressions and voice in real time using the camera and microphone installed in the terminal. The emotion analysis means analyzes the emotions (e.g., joy, excitement, anxiety, etc.) while the user is entering information and collects that data.

[0629] Data transmission

[0630] The transmitting means converts the information input by the user and the emotion data collected by the emotion analyzing means into data packets and transmits them to the server.

[0631] Data Preprocessing

[0632] The server receives the transmitted data packet and first performs data pre-processing. The data pre-processing means performs the following processes:

[0633] Cleaning the data (removing unnecessary spaces and special characters)

[0634] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0635] Categorization (e.g., classifying "photography" as a creative skill)

[0636] Applying generative AI models

[0637] The server inputs the preprocessed data and emotional data into a generative AI model, which uses machine learning techniques to analyze the input data and references past job change data and a database of company characteristics to identify the most suitable industry and company based on the user's work experience, life experience, areas of interest, and emotional data.

[0638] Generating and displaying recommendations

[0639] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. It also takes the user's emotional data into account and makes adjustments accordingly. For example, if the emotional data confirms that the user is interested in a certain job or company, it will give the relevant job type or company a higher score.

[0640] Displaying the results

[0641] The server organizes the generated recommendations, converts them into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives the data and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[0642] Specific examples

[0643] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," and sentiment analysis reveals that the user expresses excitement or interest during input, the generative AI model will interpret this as a positive indicator and generate and present recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company." Based on this user's sentiment data, appropriate adjustments are made, resulting in results that are more personally relevant and relevant.

[0644] Prompt Sentence Examples

[0645] "User data: Experience: 5 years of marketing experience, Life experience: Leadership experience, Interests: IT, e-commerce, Hobbies: Photography, Emotions: happy. Please recommend companies and jobs that would be a good fit for this user."

[0646] As described above, this system takes into account the user's experience, interests, and even emotional data to help them find the company and job that best suits them efficiently and effectively.

[0647] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0648] Step 1:

[0649] The user uses a terminal to access a dedicated input form and enters their work experience, life experience, areas of interest, hobbies, and preferences. The input means is equipped with a guideline display function that guides the user to easily enter the necessary information. The input data at this stage is user information such as work experience and hobbies.

[0650] Step 2:

[0651] While the user is inputting information, the device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The emotion analysis means analyzes the user's emotions (e.g., joy, excitement, anxiety, etc.) at the time of input and collects the data. The input is the user's facial expressions and voice information, and the output is analyzed emotional data.

[0652] Step 3:

[0653] The transmitting means of the terminal converts the information input by the user and the emotion data collected by the emotion analysis means into data packets and transmits them to the server. In this step, the input data is the user information and emotion data, and the output data is the transmitted data packets.

[0654] Step 4:

[0655] The server receives the data packet and first performs data preprocessing. The data preprocessing method cleans the data (removes unnecessary spaces and special characters), normalizes the data (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes the data (e.g., classifies "photography" as a creative skill). The input is the raw data sent, and the output is the cleaned and normalized data.

[0656] Step 5:

[0657] The server inputs the preprocessed data and emotion data into the generative AI model. The generative AI model application means uses machine learning technology to analyze the preprocessed user data and emotion data, and identifies the most suitable industry and company by referencing past job change data and a database of company characteristics. The input is the preprocessed user data and emotion data, and the output is the identified industry and company information.

[0658] Step 6:

[0659] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. At this time, emotional data is also taken into consideration and adjustments are made. For example, if emotional data confirms that the user is interested in a particular field, related job types and companies will be given higher scores. The input is company information identified by the model, and the output is ranked recommendation results.

[0660] Step 7:

[0661] The server organizes the generated recommendation results, converts them into a user-friendly format, packages them into data packets, and sends them to the terminal. The input is the ranked recommendation results, and the output is the data packets to be sent.

[0662] Step 8:

[0663] The device receives the data packet and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department at a certain company" or "Creative Director at a certain solutions company"). The input is the data packet, and the output is the recommendation results displayed to the user.

[0664] The above are the specific processing steps of this system.

[0665] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0666] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0667] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0668] [Third embodiment]

[0669] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0670] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0671] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0672] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0673] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0674] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0675] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0676] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0677] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0678] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0679] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0680] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0681] The system according to the present invention is designed to help users find the most suitable company or industry when job hunting. A specific embodiment of this system will be described below.

[0682] User input of information

[0683] First, the user accesses a dedicated form using a terminal and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), hobbies and preferences (e.g., photography, reading), etc. This input method has a guideline display function that allows the user to easily enter the required information.

[0684] Data transmission by the terminal

[0685] The terminal converts the information input by the user into a data packet and transmits it to the server via the transmission means.

[0686] Data preprocessing by the server

[0687] The server receives the data packets sent from the terminal and performs data preprocessing. The data preprocessing means performs the following processes:

[0688] Cleaning the data (removing unnecessary spaces and special characters)

[0689] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0690] Categorization (e.g., classifying "photography" as a creative skill)

[0691] Applying generative AI models

[0692] The server inputs the preprocessed data into a generative AI model. The generative AI model uses machine learning technology to reference past job-changing data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies and preferences. Specifically, it takes into account the user's hobbies and preferences (e.g., creative skills) and scores the suitability to rank the most suitable industries and companies.

[0693] Generating and displaying recommendations

[0694] The server receives the recommendation results obtained from the generative AI model application means, organizes them appropriately, converts them into data packets, and sends them to the terminal. The terminal receives them and displays a list of recommended industries and companies to the user. The user can check the recommendation results and obtain detailed information about each company and job type. For example, specific companies and job types such as "Marketing Department of XX Co., Ltd." and "Creative Director of XX Solutions Co., Ltd." are displayed.

[0695] Specific examples

[0696] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," the generative AI model will use this information to generate recommendations such as "marketing department of an e-commerce company" or "creative director of an IT solutions company" and present them to the user.

[0697] In this way, the system according to the present invention efficiently and effectively supports users in searching for the most suitable company or job type based on their own experience and interests.

[0698] The processing flow will be explained below.

[0699] Step 1:

[0700] Users use a terminal to access a dedicated input form and enter their work experience, life experience, areas of interest, and hobbies and preferences, including detailed information such as marketing experience, leadership experience, interest in IT and e-commerce, and hobbies (e.g., photography).

[0701] Step 2:

[0702] The terminal converts the information entered by the user into data packets and transmits them to the server in a manner designed to preserve the consistency and integrity of the data.

[0703] Step 3:

[0704] The server receives data packets sent from the device and performs data preprocessing. Three main processes are performed: cleaning, normalization, and categorization. For example, "5 years of marketing experience" can be converted into "Marketing position, 5 years of experience," and "Photography" can be classified as a creative skill.

[0705] Step 4:

[0706] The server inputs the preprocessed data into a generative AI model, which uses machine learning technology to analyze the user's information and identifies the most suitable industry and company by referencing past job change data and a database of company characteristics.

[0707] Step 5:

[0708] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. At this time, the suitability is scored taking into account the user's hobbies and preferences. For example, for a user with creative skills, positions in the creative department will be displayed with a high score.

[0709] Step 6:

[0710] The server organizes the generated recommendation results, converts them into a format that is easy for the user to understand, assembles them into a data packet, and transmits the data packet to the terminal.

[0711] Step 7:

[0712] The device receives the data packet sent from the server and displays a list of recommended industries and companies to the user, including specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[0713] Step 8:

[0714] Users can check the recommendations displayed on their device, obtain detailed information about each company and job type, and take actions such as going to the details page of a company they are interested in and applying for a job.

[0715] Example 1

[0716] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0717] In today's job market, job seekers face the challenge of finding the best job based on their work experience, life experience, areas of interest, and personal preferences. Conventional job change support systems often lack recommendation accuracy by not taking user information into sufficient consideration. In particular, there is a lack of systems that can properly evaluate users' hobbies and personal preferences to recommend the most suitable job type or industry, so there is a need to improve the user experience.

[0718] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0719] In this invention, the server includes an input means for a user to input their work experience, life experience, areas of interest, and personal preferences, a transmission means for transmitting the information from the input means, a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means, a generative AI model application means for identifying the most suitable job type or industry by applying a generative AI model, and a result display means for displaying to the user the recommended job type or industry obtained from the generative AI model application means. This makes it easier for the user to identify the most suitable job type or industry taking into consideration their work experience, life experience, areas of interest, and personal preferences.

[0720] "Work experience" refers to the accumulation of knowledge and skills related to the job or work one has performed.

[0721] "Life experiences" refers to the totality of events, activities, and roles that an individual experiences throughout their life.

[0722] "Areas of interest" refers to areas of study, career, or activity in which an individual has a particular interest.

[0723] "Personal preferences" refers to an individual's hobbies, particular tastes, and activities of interest.

[0724] "Input means" refers to an interface that allows a user to directly input information into the system.

[0725] "Transmission means" refers to a method or protocol for transmitting information acquired from an input means to a server.

[0726] "Data Pre-Processing Means" refers to methods or processes for cleaning, normalizing, and categorizing data transmitted by the Transmission Means.

[0727] "Means for applying generative AI models" refers to a method for applying and analyzing generative AI models based on preprocessed data to identify the most suitable job types and industries.

[0728] "Result display means" refers to an interface for visually presenting to the user the recommendation results obtained from the generative AI model application means.

[0729] The system according to the present invention uses a generative AI model to help users find the most suitable job type and industry when searching for a new job. A specific embodiment of this system will be described.

[0730] User input of information

[0731] First, the user accesses a dedicated form using their device, which contains fields for entering the following information:

[0732] Work experience (e.g., 5 years of marketing experience)

[0733] Life experiences (e.g., leadership experiences)

[0734] Area of ​​interest (e.g. IT, E-commerce)

[0735] Personal preferences (e.g., photography, reading)

[0736] The form uses text boxes and drop-down menus on the device browser to allow users to easily enter information. The form is equipped with a guideline display function to assist users when entering information.

[0737] Data transmission by the terminal

[0738] When the user completes the form and hits the submit button, the device does the following:

[0739] Convert the input information into JSON format.

[0740] The converted data is sent to the server via an HTTPS request.

[0741] This data transmission can be done using JavaScript or other client-side languages, for example, using Ajax to send the data asynchronously.

[0742] Data preprocessing by the server

[0743] The server receives the data sent from the terminal and performs data preprocessing. Specifically, it performs the following processes:

[0744] Cleaning the data: For example, removing unnecessary whitespace and special characters.

[0745] Data normalization: For example, converting "5 years of marketing experience" to "Marketing position, 5 years of experience."

[0746] Categorize: For example, categorize "photography" under "creative skills."

[0747] This preprocessing is performed using a server-side language such as Python or Node.js.

[0748] Applying generative AI models

[0749] The server inputs the preprocessed data into a generative AI model, built using TensorFlow and PyTorch, which performs the following tasks:

[0750] User data is analyzed and compared with past job change data and a database of company characteristics.

[0751] Score your suitability and rank the jobs and industries that best suit you.

[0752] Generate optimal recommendation results taking into account the user's preferences and experience.

[0753] Generating and displaying recommendations

[0754] The server converts the recommendation results obtained from the generative AI model back into data packets and sends them to the device, which then displays the following information to the user:

[0755] A list of recommended companies (e.g., "Marketing Department of Company A")

[0756] A list of recommended job titles (e.g., "Creative Director at Company B")

[0757] Users can view the recommendations and click on links to get more information. The on-device user interface is built using front-end technologies such as React and Vue.js.

[0758] Specific examples

[0759] For example, if a user enters the following information:

[0760] 30s

[0761] 5 years of marketing experience

[0762] My hobby is photography

[0763] His areas of interest are IT and e-commerce.

[0764] In this case, the generative AI model generates recommendations such as "the marketing department of an e-commerce company" or "the creative director of an IT solutions company" and presents them to the user.

[0765] Prompt Sentence Examples

[0766] Examples of prompts:

[0767] "The user is in his 30s, has 5 years of marketing experience, enjoys photography as a hobby, and is interested in IT and e-commerce. Please recommend the most suitable company and job."

[0768] In this way, the system of the present invention helps users identify the most suitable job type and industry based on their work experience, life experience, areas of interest, and personal preferences, thereby enabling users to efficiently find a suitable new job.

[0769] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0770] Step 1: User enters information

[0771] The user accesses a dedicated form using a terminal and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and personal preferences (e.g., photography, reading). After completing the input, the user presses the submit button. This input data becomes the initial input to the system, and each data field is converted to JSON format.

[0772] Input: User's work experience, life experience, areas of interest, personal preferences

[0773] Output: Converts input data to JSON format

[0774] Step 2: Send data by device

[0775] The device converts the input data into JSON format and sends it to the server via an HTTPS request. This process uses JavaScript and Ajax to send the data to the server asynchronously.

[0776] Input: Input data converted to JSON format

[0777] Output: Data sent to the server via the HTTPS request

[0778] Step 3: Data preprocessing on the server

[0779] The server analyzes the received data, cleans it (removes unnecessary spaces and special characters), normalizes it (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes it (e.g., classifies "photography" as a "creative skill"). Server-side languages ​​such as Python and Node.js are used for these processes.

[0780] Input: Data sent to the server

[0781] Output: Cleaned, normalized, and categorized data

[0782] Step 4: Applying the generative AI model

[0783] The server inputs the preprocessed data into a generative AI model. The generative AI model is built using TensorFlow and PyTorch, and analyzes the user's data and compares it with past job-changing data and a database of company characteristics. This allows it to identify the most suitable job type and industry, taking into account the user's preferences and experience, and then scores and ranks the suitability.

[0784] Input: Preprocessed data

[0785] Output: Generative AI model recommends the best job type and industry

[0786] Step 5: Generate and display recommendations

[0787] The server organizes the recommendation results obtained from the generative AI model, encodes them in JSON format, and sends them to the device. The device receives the recommendation results and visually displays them to the user. Specifically, it uses front-end technologies such as React and Vue.js to display a list of recommended companies and job types. The user can review this information and click links to obtain more information.

[0788] Input: Recommendation results from a generative AI model

[0789] Output: Recommendation results encoded in JSON format, visually displayed to the user

[0790] This process realizes a system that generates and provides users with recommendations for the most suitable job types and industries based on the information they input. This system allows users to find the best job opportunities that reflect their experience and interests.

[0791] (Application example 1)

[0792] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0793] In the past, job-hunting methods have been difficult for users to find the best companies and industries based on their experience and interests. Furthermore, there has been a lack of systems that can effectively process the information entered and provide users with appropriate recommendations. In particular, there has been a demand for a solution that allows users to easily conduct job hunting using devices such as smartphones and smart glasses.

[0794] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0795] In this invention, the server includes an input means for a user to input their work experience, life experience, areas of interest, and hobbies and interests, a transmission means for transmitting the information from the input means to the server, a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means, a generative AI model application means for applying a generative AI model to identify optimal industries and companies, a result display means for displaying to the user the optimal industry and company recommendation results obtained from the generative AI model application means, and a virtual career consultant means for displaying the recommendation results to the user via a smartphone or smart glasses and providing further detailed information. This enables a user to easily conduct a job search using their own device and find optimal companies and industries effectively and efficiently.

[0796] The "input means" is a means for a user to input his / her work experience, life experience, areas of interest, and hobbies and interests.

[0797] The "transmission means" is a means for transmitting information from the input means to the server.

[0798] The "data preprocessing means" is a means for cleaning, normalizing, and categorizing the information transmitted from the transmission means.

[0799] The "generative AI model application means" is a means for applying a generative AI model based on information preprocessed by the data preprocessing means to identify the most suitable industries and companies.

[0800] The "means for displaying results" is a means for displaying to the user the optimal industry and company recommendation results obtained from the means for applying the generative AI model.

[0801] The "virtual career consultant means" is a means for displaying recommendation results to users via smartphones or smart glasses, and providing further detailed information.

[0802] The system according to the present invention is designed to help users find the most suitable company or industry. A specific embodiment of this system will be described below.

[0803] User input of information

[0804] First, a user accesses a dedicated form using a smartphone or smart glasses and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography, reading). This input method has a guideline display function that allows users to easily enter the required information.

[0805] Data transmission by the terminal

[0806] The user's terminal converts the input information into a data packet and transmits it to the server via a transmission means.

[0807] Data preprocessing by the server

[0808] The server receives data packets sent from the device and cleans the data (removes unnecessary spaces and special characters), normalizes the data (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes it (e.g., classifies "photography" as a creative skill).

[0809] Applying generative AI models

[0810] The server inputs the preprocessed data into a generative AI model. The generative AI model uses machine learning technology to reference past job change data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, fields of interest, and hobbies. Specifically, it takes into account the user's hobbies and interests (e.g., creative skills) and scores the degree of suitability to rank the most suitable industries and companies.

[0811] Generating and displaying recommendations

[0812] The server appropriately organizes the recommendation results obtained from the generative AI model application means, converts them into data packets, and sends them to the terminal. The terminal receives them and displays a list of recommended industries and companies to the user via a smartphone or smart glasses. The user can check the recommendation results and obtain detailed information about each company and job type. For example, specific companies and job types such as "Marketing Department of Co., Ltd. A" and "Creative Director of Co., Ltd. B" are displayed.

[0813] Specific examples

[0814] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," the generative AI model will use this information to generate recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company" and present them to the user. Based on this specific example, the following prompt is input into the generative AI model: "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce."

[0815] In this way, the system according to the present invention efficiently and effectively supports users in searching for the most suitable company or job type based on their own experience and interests.

[0816] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0817] Step 1:

[0818] Users access a dedicated form using a smartphone or smart glasses. Here, they enter information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography, reading). The input means has a guideline display function to help users easily enter the required information. Input: User's work experience, life experience, areas of interest, and hobbies. Output: Entered user data.

[0819] Step 2:

[0820] The terminal converts the data entered by the user into data packets, which organizes the information into a series of data formats so that the server can process them.The terminal then sends the data packets to the server using a transmission means.Input: User input data.Output: Data packets.

[0821] Step 3:

[0822] The server receives data packets sent from the device. First, it cleans the data and removes unnecessary spaces and special characters. Then it normalizes the data, converting "5 years of marketing experience" to "Marketing position, 5 years of experience". Finally, it categorizes the data and tags "Photography" as a creative skill. Input: Data packet. Output: Preprocessed data.

[0823] Step 4:

[0824] The server inputs the preprocessed data into a generative AI model. This generative AI model references past job change data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies. The generative AI model scores these factors and ranks the most suitable industries and companies for the user. Input: Preprocessed data. Output: Ranked list of industries and companies.

[0825] Step 5:

[0826] The server converts the recommendation results from the generative AI model into a data packet, which is in an organized format and easy for the device to process. The server then sends the data packet to the device. Input: A list of ranked industries and companies. Output: A data packet of recommendation data.

[0827] Step 6:

[0828] The device receives the data packet sent from the server and displays a list of industries and companies recommended to the user. Specific company and job information such as "Marketing Department of Company A" or "Creative Director of Company B" is displayed on the screen of the smartphone or smart glasses. A virtual career consultant means is also used to provide even more detailed information. Input: Data packet of recommendation data. Output: List of recommended companies and industries and detailed information.

[0829] In this way, users can search for the most suitable company and job type based on their experience and interests, enabling them to conduct an efficient and effective job search.

[0830] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0831] The system according to the present invention supports users in finding the most suitable company or industry when job hunting, and further combines it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[0832] User input of information

[0833] First, the user uses a terminal to access a dedicated input form and enters information such as their work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This input method is equipped with a guideline display function to make it easy for users to enter the required information.

[0834] Incorporating an emotion engine

[0835] While the user is entering information, an emotion engine is activated, analyzing the user's facial expressions and voice in real time using the device's built-in camera and microphone. The emotion engine analyzes the user's emotions (e.g., joy, surprise, anxiety, etc.) while they are entering information and collects that data.

[0836] Data transmission and preprocessing

[0837] The terminal converts the information input by the user and the emotion data analyzed by the emotion engine into a data packet and transmits it to the server. The server receives the transmitted data packet and first performs data preprocessing. The data preprocessing means performs the following processes:

[0838] Cleaning the data (removing unnecessary spaces and special characters)

[0839] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0840] Categorization (e.g., classifying "photography" as a creative skill)

[0841] Applying generative AI models

[0842] The server inputs the preprocessed data and emotional data into a generative AI model, which uses machine learning techniques to analyze the input data and references past job change data and a database of company characteristics to identify the most suitable industry and company based on the user's work experience, life experience, areas of interest, and emotional data.

[0843] Generating and displaying recommendations

[0844] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. It also takes the user's emotional data into account and makes adjustments accordingly. For example, if the emotional data confirms that the user is interested in a certain job or company, it will give the relevant job type or company a higher score.

[0845] Organizing and displaying results

[0846] The server organizes the generated recommendations, converts them into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives this and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[0847] Specific examples

[0848] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," and the emotion engine detects that the user is excited or interested when entering information, the generative AI model will interpret this as a positive indicator and generate and present recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company." Based on this user's emotional data, appropriate adjustments are made, resulting in results that are more personally relevant and relevant.

[0849] In this way, the system according to the present invention takes into consideration the user's experience, interests, and even emotional data, and helps the user efficiently and effectively find the most suitable company or job type.

[0850] The processing flow will be explained below.

[0851] Step 1:

[0852] Users use a terminal to access a dedicated input form and enter their work experience, life experience, areas of interest, and hobbies and preferences. For example, they can enter information such as "5 years of marketing experience," "has leadership experience," "interest in IT and e-commerce," or "photography is my hobby."

[0853] Step 2:

[0854] The device's built-in camera and microphone capture the user's facial expressions and voice in real time as they type. The emotion engine analyzes these and collects data on the emotions the user is expressing (e.g., joy, excitement, anxiety, etc.).

[0855] Step 3:

[0856] The terminal converts the information input by the user and the emotion data collected by the emotion engine into data packets and transmits them to the server.

[0857] Step 4:

[0858] The server receives the data packets sent from the terminal and performs data pre-processing. The data pre-processing means performs the following processes:

[0859] Cleaning the data (e.g. removing unnecessary whitespace and special characters)

[0860] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0861] Categorization (e.g., classifying "photography" as a creative skill)

[0862] Step 5:

[0863] The server inputs the preprocessed data and emotional data into a generative AI model. The generative AI model uses machine learning techniques to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies and preferences. The model also takes emotional data into account, and if the emotion is positive, it increases the score for that industry or company.

[0864] Step 6:

[0865] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. For example, if a user is interested in IT and e-commerce and has positive feelings about them, the marketing department of an e-commerce company or the creative director of an IT solutions company will be recommended with a high score.

[0866] Step 7:

[0867] The server organizes the generated recommendation results, converts them into an appropriate format, assembles them into a data packet, and transmits it to the terminal.

[0868] Step 8:

[0869] The device receives the data packet sent from the server and displays a list of recommended industries and companies to the user, including specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[0870] Step 9:

[0871] Users can check the recommendations displayed on their device, obtain detailed information about each company and job type, and take actions such as going to the details page of a company they are interested in and applying for a job.

[0872] Through the above processing steps, the system takes into consideration the user's experience, interests, and even emotional data, helping them find the most suitable company or job type efficiently and effectively.

[0873] Example 2

[0874] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0875] Conventional career change support systems have the problem of being unable to provide personalized recommendations that are based not only on the user's work history and areas of interest, but also on the emotions expressed by the user when entering information. This makes it difficult to find jobs and organizations that match the user's true interests and aptitudes.

[0876] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input their work history, life experience, areas of interest, and hobbies; a transmission means for transmitting information from the input means to the processing device; a data preprocessing means for data cleansing, normalizing, and classifying the information transmitted from the transmission means; a generative AI model application means for applying a generative AI model based on the information preprocessed by the data preprocessing means to identify the most suitable job type or organization; a result display means for displaying to the user the recommendation results of the most suitable job type or organization obtained from the generative AI model application means; and an emotion recognition means for collecting emotion data input by the user using an emotion recognition device and reflecting the data in the generative AI model. This enables personalized recommendations that take into account not only the user's experience and areas of interest but also the emotion data.

[0877] "Input means" refers to devices and software that allow users to input their work history, life experiences, areas of interest, and hobbies into the system.

[0878] The "transmission means" refers to a communication function for transmitting information acquired from the input means to a processing device or a server.

[0879] "Data Pre-Processing Means" refers to algorithms and programs for data cleansing, normalizing, and classifying information transmitted from the Transmission Means.

[0880] "Means for applying a generative AI model" refers to the program and process for applying a generative AI model based on preprocessed information to identify the most suitable job type or organization.

[0881] "Result display means" refers to a device and software for displaying the recommendation results obtained by the generative AI model application means to the user.

[0882] "Emotion recognition means" refers to an emotion recognition device and software for collecting and analyzing emotion data expressed by a user during input.

[0883] "Generative AI models" refer to algorithms and models that use machine learning techniques to analyze user data and identify the most suitable jobs and organizations.

[0884] "Guideline display function" refers to an interface function that provides instructions and hints to assist the user when entering information.

[0885] MODE FOR CARRYING OUT THE INVENTION

[0886] The system according to the present invention supports users in finding the most suitable company or industry when job hunting, and further includes emotion recognition means for recognizing the emotions of the user. Specific embodiments of this system are described below.

[0887] User input of information

[0888] The user uses a terminal to access a dedicated input form and enters information such as work history, life experience, areas of interest, and hobbies. This input method is equipped with a guideline display function to allow the user to easily enter the required information. For example, the user can start a web browser (e.g., Google Chrome or Mozilla Firefox) and access the input form via its URL. Following the input fields, the user enters the following information:

[0889] Work history (e.g., 5 years of marketing experience)

[0890] Life experience (e.g. leadership experience)

[0891] Area of ​​interest (e.g. IT, E-commerce)

[0892] Hobbies (e.g. photography)

[0893] Incorporating emotion recognition measures

[0894] While the user is entering information, the device's built-in camera and microphone are activated to record the user's facial expressions and voice in real time. This allows the emotion recognition means to analyze and collect the user's emotional data (happiness, surprise, anxiety, etc.). This emotion recognition is performed using software such as Amazon Rekognition and Microsoft Azure's Emotion API.

[0895] Data submission and preprocessing

[0896] The terminal converts the information input by the user and the emotion data analyzed by the emotion recognition device into data packets and sends them to the server. This transmission uses Internet protocols (e.g., HTTP, HTTPS). The server receives the transmitted data packets and first performs data preprocessing. The data preprocessing means performs the following processes:

[0897] Data cleansing: Removing unnecessary whitespace and special characters.

[0898] Data normalization: Convert "5 years of marketing experience" to "Marketing position, 5 years of experience."

[0899] Categorization: Classify "photography" as a creative skill.

[0900] Applying generative AI models

[0901] The server inputs the preprocessed data and emotion data into a generative AI model. This generative AI model uses, for example, GPT-4 (OpenAI's language model) or BERT (Google's language understanding model). The server uses these models to analyze the input data and references past job change data and a database of company characteristics. This allows it to identify the most suitable job type and organization based on the user's experience, areas of interest, and emotion data.

[0902] Generating and displaying recommendations

[0903] The generative AI model application means ranks the most suitable jobs and organizations based on the analysis results and generates recommendation results. In doing so, it also takes into account the user's emotional data and adjusts the score accordingly. The server organizes the generated recommendation results, converts them into a user-friendly format, compiles them into a data packet, and sends it to the terminal. The terminal receives this and displays a list of recommended jobs and organizations to the user. This list includes specific company names and job types (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[0904] Specific examples

[0905] For example, if a user inputs information such as "30s, 5 years of marketing experience, hobby is photography, interest areas are IT and e-commerce," and the emotion recognition means indicates that the user is excited or interested when entering information, the generative AI model will consider this as a favorable indicator. As a result, it will generate and present to the user recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company."

[0906] Prompt Sentence Examples

[0907] Here are some example prompts to input to a generative AI model:

[0908] User profile:

[0909] Age: 30s

[0910] Experience: 5 years of marketing experience

[0911] Areas of interest: IT, E-commerce

[0912] Hobbies: Photography

[0913] Emotional Data:

[0914] Excitement: High

[0915] Interest: High

[0916] Based on the information above and sentiment data, identify the industry, company, and job type that would be a perfect fit for this user.

[0917] In this way, the system according to the present invention takes into consideration the user's experience, areas of interest, and even emotional data, and helps the user efficiently and effectively find the most suitable job or organization.

[0918] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0919] Step 1:

[0920] The user accesses a dedicated input form using a terminal. They launch a web browser, enter the URL of the input form, and display the screen. The user enters information such as work history, life experience, areas of interest, and hobbies. The input content includes work history (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This information is collected as input data.

[0921] Step 2:

[0922] While the user is entering information, the device's built-in camera and microphone are activated, recording the user's facial expressions and voice in real time. The emotion recognition device analyzes this recorded data and generates emotion data such as joy, surprise, and anxiety. This emotion data is temporarily stored in the device.

[0923] Step 3:

[0924] The device combines the information entered by the user and the emotional data analyzed by the emotion recognition device into a single data packet. The data packet is formatted in JSON or XML format. The user input information and emotional data are packetized.

[0925] Step 4:

[0926] The device sends the generated data packets to a server over the Internet. The data packets are delivered to the server using the HTTP or HTTPS protocol. The server receives the data packets.

[0927] Step 5:

[0928] The server processes the received data packets and performs data cleansing, normalization, and categorization. Data cleansing removes unnecessary spaces and special characters, normalization converts "5 years of marketing experience" to "Marketing position, 5 years of experience," and categorization classifies "photography" as a creative skill. The preprocessed data is generated.

[0929] Step 6:

[0930] The server inputs the preprocessed data and emotion data into a generative AI model. This generative AI model uses, for example, GPT-4 or BERT. The generative AI model analyzes the input data and references past job change data and a database of company characteristics. The analysis results in identifying the most suitable job type and organization.

[0931] Step 7:

[0932] The generative AI model application means ranks the most suitable jobs and organizations based on the analysis results and generates recommendation results. At this time, it also takes into account the user's emotional data and adjusts the scores of related jobs and organizations. The generated recommendation results are compiled into a data packet.

[0933] Step 8:

[0934] The server converts the generated recommendations into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives it and displays a list of recommended jobs and organizations on the screen. The displayed list includes specific company names and job types (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[0935] (Application example 2)

[0936] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0937] In today's job-hunting environment, it is not easy for users to find the perfect company or industry. In particular, there is a need for matching that takes into account not only skills and experience, but also the user's personal interests and emotions. However, conventional systems do not utilize users' emotional data for matching, which hinders efficient and effective job hunting.

[0938] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: an input means for the user to input their work experience, life experience, areas of interest, and hobbies and preferences; an emotion analysis means for analyzing the user's emotions during input and generating user emotion data; a transmission means for transmitting information from the input means and the user emotion data collected by the emotion analysis means to the server; a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means; a generative AI model application means for applying a generative AI model to the information and emotion data preprocessed by the data preprocessing means to identify optimal industries and companies; and a result display means for displaying to the user the recommended industries and companies obtained from the generative AI model application means. This enables more personalized job recommendations that take the user's interests and emotions into consideration.

[0939] The "input means" is a mechanism for allowing a user to input his / her own work experience, life experience, areas of interest, hobbies and preferences.

[0940] The "transmission means" is a mechanism for transmitting information and emotion data from the input means to the server.

[0941] "Data pre-processing means" is a mechanism for cleaning, normalizing, and categorizing information transmitted from a transmission means.

[0942] The "generative AI model application means" is a mechanism for applying a generative AI model to identify the most suitable industries and companies based on the information and emotion data preprocessed by the data preprocessing means.

[0943] The "result display means" is a mechanism for displaying to the user the optimal industry and company recommendation results obtained from the generative AI model application means.

[0944] The "emotion analysis means" is a mechanism for analyzing the user's emotions during input and generating user emotion data.

[0945] The "emotion data transmission means" is a mechanism for transmitting the user's emotion data collected by the emotion analysis means to the server.

[0946] The system according to the present invention assists users in finding the most suitable company or industry when job hunting, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[0947] User input of information

[0948] First, the user uses a terminal to access a dedicated input form and enters information such as their work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This input method is equipped with a guideline display function to make it easy for users to enter the required information.

[0949] emotion recognition

[0950] While the user is entering information, an emotion analysis means operates, which analyzes the user's facial expressions and voice in real time using the camera and microphone installed in the terminal. The emotion analysis means analyzes the emotions (e.g., joy, excitement, anxiety, etc.) while the user is entering information and collects that data.

[0951] Data transmission

[0952] The transmitting means converts the information input by the user and the emotion data collected by the emotion analyzing means into data packets and transmits them to the server.

[0953] Data Preprocessing

[0954] The server receives the transmitted data packet and first performs data pre-processing. The data pre-processing means performs the following processes:

[0955] Cleaning the data (removing unnecessary spaces and special characters)

[0956] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[0957] Categorization (e.g., classifying "photography" as a creative skill)

[0958] Applying generative AI models

[0959] The server inputs the preprocessed data and emotional data into a generative AI model, which uses machine learning techniques to analyze the input data and references past job change data and a database of company characteristics to identify the most suitable industry and company based on the user's work experience, life experience, areas of interest, and emotional data.

[0960] Generating and displaying recommendations

[0961] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. It also takes the user's emotional data into account and makes adjustments accordingly. For example, if the emotional data confirms that the user is interested in a certain job or company, it will give the relevant job type or company a higher score.

[0962] Displaying the results

[0963] The server organizes the generated recommendations, converts them into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives the data and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[0964] Specific examples

[0965] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," and sentiment analysis reveals that the user expresses excitement or interest during input, the generative AI model will interpret this as a positive indicator and generate and present recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company." Based on this user's sentiment data, appropriate adjustments are made, resulting in results that are more personally relevant and relevant.

[0966] Prompt Sentence Examples

[0967] "User data: Experience: 5 years of marketing experience, Life experience: Leadership experience, Interests: IT, e-commerce, Hobbies: Photography, Emotions: happy. Please recommend companies and jobs that would be a good fit for this user."

[0968] As described above, this system takes into account the user's experience, interests, and even emotional data to help them find the company and job that best suits them efficiently and effectively.

[0969] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0970] Step 1:

[0971] The user uses a terminal to access a dedicated input form and enters their work experience, life experience, areas of interest, hobbies, and preferences. The input means is equipped with a guideline display function that guides the user to easily enter the necessary information. The input data at this stage is user information such as work experience and hobbies.

[0972] Step 2:

[0973] While the user is inputting information, the device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The emotion analysis means analyzes the user's emotions (e.g., joy, excitement, anxiety, etc.) at the time of input and collects the data. The input is the user's facial expressions and voice information, and the output is analyzed emotional data.

[0974] Step 3:

[0975] The transmitting means of the terminal converts the information input by the user and the emotion data collected by the emotion analysis means into data packets and transmits them to the server. In this step, the input data is the user information and emotion data, and the output data is the transmitted data packets.

[0976] Step 4:

[0977] The server receives the data packet and first performs data preprocessing. The data preprocessing method cleans the data (removes unnecessary spaces and special characters), normalizes the data (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes the data (e.g., classifies "photography" as a creative skill). The input is the raw data sent, and the output is the cleaned and normalized data.

[0978] Step 5:

[0979] The server inputs the preprocessed data and emotion data into the generative AI model. The generative AI model application means uses machine learning technology to analyze the preprocessed user data and emotion data, and identifies the most suitable industry and company by referencing past job change data and a database of company characteristics. The input is the preprocessed user data and emotion data, and the output is the identified industry and company information.

[0980] Step 6:

[0981] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. At this time, emotional data is also taken into consideration and adjustments are made. For example, if emotional data confirms that the user is interested in a particular field, related job types and companies will be given higher scores. The input is company information identified by the model, and the output is ranked recommendation results.

[0982] Step 7:

[0983] The server organizes the generated recommendation results, converts them into a user-friendly format, packages them into data packets, and sends them to the terminal. The input is the ranked recommendation results, and the output is the data packets to be sent.

[0984] Step 8:

[0985] The device receives the data packet and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department at a certain company" or "Creative Director at a certain solutions company"). The input is the data packet, and the output is the recommendation results displayed to the user.

[0986] The above are the specific processing steps of this system.

[0987] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0988] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0989] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0990] [Fourth embodiment]

[0991] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0992] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0993] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0994] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0995] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0996] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0997] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0998] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0999] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1000] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1001] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1002] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1003] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1004] The system according to the present invention is designed to help users find the most suitable company or industry when job hunting. A specific embodiment of this system will be described below.

[1005] User input of information

[1006] First, the user accesses a dedicated form using a terminal and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), hobbies and preferences (e.g., photography, reading), etc. This input method has a guideline display function that allows the user to easily enter the required information.

[1007] Data transmission by the terminal

[1008] The terminal converts the information input by the user into a data packet and transmits it to the server via the transmission means.

[1009] Data preprocessing by the server

[1010] The server receives the data packets sent from the terminal and performs data preprocessing. The data preprocessing means performs the following processes:

[1011] Cleaning the data (removing unnecessary spaces and special characters)

[1012] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[1013] Categorization (e.g., classifying "photography" as a creative skill)

[1014] Applying generative AI models

[1015] The server inputs the preprocessed data into a generative AI model. The generative AI model uses machine learning technology to reference past job-changing data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies and preferences. Specifically, it takes into account the user's hobbies and preferences (e.g., creative skills) and scores the suitability to rank the most suitable industries and companies.

[1016] Generating and displaying recommendations

[1017] The server receives the recommendation results obtained from the generative AI model application means, organizes them appropriately, converts them into data packets, and sends them to the terminal. The terminal receives them and displays a list of recommended industries and companies to the user. The user can check the recommendation results and obtain detailed information about each company and job type. For example, specific companies and job types such as "Marketing Department of XX Co., Ltd." and "Creative Director of XX Solutions Co., Ltd." are displayed.

[1018] Specific examples

[1019] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," the generative AI model will use this information to generate recommendations such as "marketing department of an e-commerce company" or "creative director of an IT solutions company" and present them to the user.

[1020] In this way, the system according to the present invention efficiently and effectively supports users in finding the most suitable company or job type based on their own experience and interests.

[1021] The processing flow will be explained below.

[1022] Step 1:

[1023] Users use a terminal to access a dedicated input form and enter their work experience, life experience, areas of interest, and hobbies and preferences, including detailed information such as marketing experience, leadership experience, interest in IT and e-commerce, and hobbies (e.g., photography).

[1024] Step 2:

[1025] The terminal converts the information entered by the user into data packets and transmits them to the server in a manner designed to preserve the consistency and integrity of the data.

[1026] Step 3:

[1027] The server receives data packets sent from the device and performs data preprocessing. Three main processes are performed: cleaning, normalization, and categorization. For example, "5 years of marketing experience" can be converted into "Marketing position, 5 years of experience," and "Photography" can be classified as a creative skill.

[1028] Step 4:

[1029] The server inputs the preprocessed data into a generative AI model, which uses machine learning technology to analyze the user's information and identify the most suitable industry and company by referencing past job change data and a database of company characteristics.

[1030] Step 5:

[1031] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. At this time, the suitability is scored taking into account the user's hobbies and preferences. For example, for a user with creative skills, positions in the creative department will be displayed with a high score.

[1032] Step 6:

[1033] The server organizes the generated recommendation results, converts them into a format that is easy for the user to understand, assembles them into a data packet, and transmits the data packet to the terminal.

[1034] Step 7:

[1035] The device receives the data packet sent from the server and displays a list of recommended industries and companies to the user, including specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[1036] Step 8:

[1037] Users can check the recommendations displayed on their device, obtain detailed information about each company and job type, and take actions such as going to the details page of a company they are interested in and applying for a job.

[1038] Example 1

[1039] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1040] In today's job market, job seekers face the challenge of finding the best job based on their work experience, life experience, areas of interest, and personal preferences. Conventional job change support systems often lack recommendation accuracy by not taking user information into sufficient consideration. In particular, there is a lack of systems that can properly evaluate users' hobbies and personal preferences to recommend the most suitable job type or industry, so there is a need to improve the user experience.

[1041] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1042] In this invention, the server includes an input means for a user to input their work experience, life experience, areas of interest, and personal preferences, a transmission means for transmitting the information from the input means, a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means, a generative AI model application means for identifying the most suitable job type or industry by applying a generative AI model, and a result display means for displaying to the user the recommended job type or industry obtained from the generative AI model application means. This makes it easier for the user to identify the most suitable job type or industry taking into consideration their work experience, life experience, areas of interest, and personal preferences.

[1043] "Work experience" refers to the accumulation of knowledge and skills related to the job or work one has performed.

[1044] "Life experiences" refers to the totality of events, activities, and roles that an individual experiences throughout their life.

[1045] "Areas of interest" refers to areas of study, career, or activity in which an individual has a particular interest.

[1046] "Personal preferences" refers to an individual's hobbies, particular tastes, and activities of interest.

[1047] "Input means" refers to an interface that allows a user to directly input information into the system.

[1048] "Transmission means" refers to a method or protocol for transmitting information acquired from an input means to a server.

[1049] "Data Pre-Processing Means" refers to methods or processes for cleaning, normalizing, and categorizing data transmitted by the Transmission Means.

[1050] "Means for applying generative AI models" refers to a method for applying and analyzing generative AI models based on preprocessed data to identify the most suitable job types and industries.

[1051] "Result display means" refers to an interface for visually presenting to the user the recommendation results obtained from the generative AI model application means.

[1052] The system according to the present invention uses a generative AI model to help users find the most suitable job type and industry when searching for a new job. A specific embodiment of this system will be described.

[1053] User input of information

[1054] First, the user accesses a dedicated form using their device, which contains fields for entering the following information:

[1055] Work experience (e.g., 5 years of marketing experience)

[1056] Life experiences (e.g., leadership experiences)

[1057] Area of ​​interest (e.g. IT, E-commerce)

[1058] Personal preferences (e.g., photography, reading)

[1059] The form uses text boxes and drop-down menus on the device browser to allow users to easily enter information. The form is equipped with a guideline display function to assist users when entering information.

[1060] Data transmission by the terminal

[1061] When the user completes the form and hits the submit button, the device does the following:

[1062] Convert the input information into JSON format.

[1063] The converted data is sent to the server via an HTTPS request.

[1064] This data transmission can be done using JavaScript or other client-side languages, for example, using Ajax to send the data asynchronously.

[1065] Data preprocessing by the server

[1066] The server receives the data sent from the terminal and performs data preprocessing. Specifically, it performs the following processes:

[1067] Cleaning the data: For example, removing unnecessary whitespace and special characters.

[1068] Data normalization: For example, converting "5 years of marketing experience" to "Marketing position, 5 years of experience."

[1069] Categorize: For example, categorize "photography" under "creative skills."

[1070] This preprocessing is performed using a server-side language such as Python or Node.js.

[1071] Applying generative AI models

[1072] The server inputs the preprocessed data into a generative AI model, built using TensorFlow and PyTorch, which performs the following tasks:

[1073] User data is analyzed and compared with past job change data and a database of company characteristics.

[1074] Score your suitability and rank the jobs and industries that best suit you.

[1075] Generate optimal recommendation results taking into account the user's preferences and experience.

[1076] Generating and displaying recommendations

[1077] The server converts the recommendation results obtained from the generative AI model back into data packets and sends them to the device, which then displays the following information to the user:

[1078] A list of recommended companies (e.g., "Marketing Department of Company A")

[1079] A list of recommended job titles (e.g., "Creative Director at Company B")

[1080] Users can view the recommendations and click on links to get more information. The on-device user interface is built using front-end technologies such as React and Vue.js.

[1081] Specific examples

[1082] For example, if a user enters the following information:

[1083] 30s

[1084] 5 years of marketing experience

[1085] My hobby is photography

[1086] His areas of interest are IT and e-commerce.

[1087] In this case, the generative AI model generates recommendations such as "the marketing department of an e-commerce company" or "the creative director of an IT solutions company" and presents them to the user.

[1088] Prompt Sentence Examples

[1089] Examples of prompts:

[1090] "The user is in his 30s, has 5 years of marketing experience, enjoys photography as a hobby, and is interested in IT and e-commerce. Please recommend the most suitable company and job."

[1091] In this way, the system of the present invention helps users identify the most suitable job type and industry based on their work experience, life experience, areas of interest, and personal preferences, thereby enabling users to efficiently find a suitable new job.

[1092] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1093] Step 1: User enters information

[1094] The user accesses a dedicated form using a terminal and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and personal preferences (e.g., photography, reading). After completing the input, the user presses the submit button. This input data becomes the initial input to the system, and each data field is converted to JSON format.

[1095] Input: User's work experience, life experience, areas of interest, personal preferences

[1096] Output: Converts input data to JSON format

[1097] Step 2: Send data by device

[1098] The device converts the input data into JSON format and sends it to the server via an HTTPS request. This process uses JavaScript and Ajax to send the data to the server asynchronously.

[1099] Input: Input data converted to JSON format

[1100] Output: Data sent to the server via the HTTPS request

[1101] Step 3: Data preprocessing on the server

[1102] The server analyzes the received data, cleans it (removes unnecessary spaces and special characters), normalizes it (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes it (e.g., classifies "photography" as a "creative skill"). Server-side languages ​​such as Python and Node.js are used for these processes.

[1103] Input: Data sent to the server

[1104] Output: Cleaned, normalized, and categorized data

[1105] Step 4: Applying the generative AI model

[1106] The server inputs the preprocessed data into a generative AI model. The generative AI model is built using TensorFlow and PyTorch, and analyzes the user's data and compares it with past job-changing data and a database of company characteristics. This allows it to identify the most suitable job type and industry, taking into account the user's preferences and experience, and then scores and ranks the suitability.

[1107] Input: Preprocessed data

[1108] Output: Generative AI model recommends the best job type and industry

[1109] Step 5: Generate and display recommendations

[1110] The server organizes the recommendation results obtained from the generative AI model, encodes them in JSON format, and sends them to the device. The device receives the recommendation results and visually displays them to the user. Specifically, it uses front-end technologies such as React and Vue.js to display a list of recommended companies and job types. The user can review this information and click links to obtain more information.

[1111] Input: Recommendation results from a generative AI model

[1112] Output: Recommendation results encoded in JSON format, visually displayed to the user

[1113] This process realizes a system that generates and provides users with recommendations for the most suitable job types and industries based on the information they input. This system allows users to find the best job opportunities that reflect their experience and interests.

[1114] (Application example 1)

[1115] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1116] In the past, job-hunting methods have been difficult for users to find the best companies and industries based on their experience and interests. Furthermore, there has been a lack of systems that can effectively process the information entered and provide users with appropriate recommendations. In particular, there has been a demand for a solution that allows users to easily conduct job hunting using devices such as smartphones and smart glasses.

[1117] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1118] In this invention, the server includes an input means for a user to input their work experience, life experience, areas of interest, and hobbies and interests, a transmission means for transmitting the information from the input means to the server, a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means, a generative AI model application means for applying a generative AI model to identify optimal industries and companies, a result display means for displaying to the user the optimal industry and company recommendation results obtained from the generative AI model application means, and a virtual career consultant means for displaying the recommendation results to the user via a smartphone or smart glasses and providing further detailed information. This enables a user to easily conduct a job search using their own device and find optimal companies and industries effectively and efficiently.

[1119] The "input means" is a means for a user to input his / her work experience, life experience, areas of interest, and hobbies and interests.

[1120] The "transmission means" is a means for transmitting information from the input means to the server.

[1121] The "data preprocessing means" is a means for cleaning, normalizing, and categorizing the information transmitted from the transmission means.

[1122] The "generative AI model application means" is a means for applying a generative AI model based on information preprocessed by the data preprocessing means to identify the most suitable industries and companies.

[1123] The "means for displaying results" is a means for displaying to the user the optimal industry and company recommendation results obtained from the means for applying the generative AI model.

[1124] The "virtual career consultant means" is a means for displaying recommendation results to users via smartphones or smart glasses, and providing further detailed information.

[1125] The system according to the present invention is designed to help users find the most suitable company or industry. A specific embodiment of this system will be described below.

[1126] User input of information

[1127] First, a user accesses a dedicated form using a smartphone or smart glasses and enters information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography, reading). This input method has a guideline display function that allows users to easily enter the required information.

[1128] Data transmission by the terminal

[1129] The user's terminal converts the input information into a data packet and transmits it to the server via a transmission means.

[1130] Data preprocessing by the server

[1131] The server receives data packets sent from the device and cleans the data (removes unnecessary spaces and special characters), normalizes the data (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes it (e.g., classifies "photography" as a creative skill).

[1132] Applying generative AI models

[1133] The server inputs the preprocessed data into a generative AI model. The generative AI model uses machine learning technology to reference past job change data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, fields of interest, and hobbies. Specifically, it takes into account the user's hobbies and interests (e.g., creative skills) and scores the degree of suitability to rank the most suitable industries and companies.

[1134] Generating and displaying recommendations

[1135] The server appropriately organizes the recommendation results obtained from the generative AI model application means, converts them into data packets, and sends them to the terminal. The terminal receives them and displays a list of recommended industries and companies to the user via a smartphone or smart glasses. The user can check the recommendation results and obtain detailed information about each company and job type. For example, specific companies and job types such as "Marketing Department of Co., Ltd. A" and "Creative Director of Co., Ltd. B" are displayed.

[1136] Specific examples

[1137] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," the generative AI model will use this information to generate recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company" and present them to the user. Based on this specific example, the following prompt is input into the generative AI model: "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce."

[1138] In this way, the system according to the present invention efficiently and effectively supports users in searching for the most suitable company or job type based on their own experience and interests.

[1139] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1140] Step 1:

[1141] Users access a dedicated form using a smartphone or smart glasses. Here, they enter information such as work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography, reading). The input means has a guideline display function to help users easily enter the required information. Input: User's work experience, life experience, areas of interest, and hobbies. Output: Entered user data.

[1142] Step 2:

[1143] The terminal converts the data entered by the user into data packets, which organizes the information into a series of data formats so that the server can process them.The terminal then sends the data packets to the server using a transmission means.Input: User input data.Output: Data packets.

[1144] Step 3:

[1145] The server receives data packets sent from the device. First, it cleans the data and removes unnecessary spaces and special characters. Then it normalizes the data, converting "5 years of marketing experience" to "Marketing position, 5 years of experience". Finally, it categorizes the data and tags "Photography" as a creative skill. Input: Data packet. Output: Preprocessed data.

[1146] Step 4:

[1147] The server inputs the preprocessed data into a generative AI model. This generative AI model references past job change data and a database of company characteristics to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies. The generative AI model scores these factors and ranks the most suitable industries and companies for the user. Input: Preprocessed data. Output: Ranked list of industries and companies.

[1148] Step 5:

[1149] The server converts the recommendation results from the generative AI model into a data packet, which is in an organized format and easy for the device to process. The server then sends the data packet to the device. Input: A list of ranked industries and companies. Output: A data packet of recommendation data.

[1150] Step 6:

[1151] The device receives the data packet sent from the server and displays a list of industries and companies recommended to the user. Specific company and job information such as "Marketing Department of Company A" or "Creative Director of Company B" is displayed on the screen of the smartphone or smart glasses. A virtual career consultant means is also used to provide even more detailed information. Input: Data packet of recommendation data. Output: List of recommended companies and industries and detailed information.

[1152] In this way, users can search for the most suitable company and job type based on their experience and interests, enabling them to conduct an efficient and effective job search.

[1153] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1154] The system according to the present invention supports users in finding the most suitable company or industry when job hunting, and further combines it with an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described below.

[1155] User input of information

[1156] First, the user uses a terminal to access a dedicated input form and enters information such as their work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This input method is equipped with a guideline display function to make it easy for users to enter the required information.

[1157] Incorporating an emotion engine

[1158] While the user is entering information, an emotion engine is activated, analyzing the user's facial expressions and voice in real time using the device's built-in camera and microphone. The emotion engine analyzes the user's emotions (e.g., joy, surprise, anxiety, etc.) while they are entering information and collects that data.

[1159] Data transmission and preprocessing

[1160] The terminal converts the information input by the user and the emotion data analyzed by the emotion engine into a data packet and transmits it to the server. The server receives the transmitted data packet and first performs data preprocessing. The data preprocessing means performs the following processes:

[1161] Cleaning the data (removing unnecessary spaces and special characters)

[1162] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[1163] Categorization (e.g., classifying "photography" as a creative skill)

[1164] Applying generative AI models

[1165] The server inputs the preprocessed data and emotional data into a generative AI model, which uses machine learning techniques to analyze the input data and references past job change data and a database of company characteristics to identify the most suitable industry and company based on the user's work experience, life experience, areas of interest, and emotional data.

[1166] Generating and displaying recommendations

[1167] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. It also takes the user's emotional data into account and makes adjustments accordingly. For example, if the emotional data confirms that the user is interested in a certain job or company, it will give the relevant job type or company a higher score.

[1168] Organizing and displaying results

[1169] The server organizes the generated recommendations, converts them into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives this and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[1170] Specific examples

[1171] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," and the emotion engine detects that the user is excited or interested when entering information, the generative AI model will interpret this as a positive indicator and generate and present recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company." Based on this user's emotional data, appropriate adjustments are made, resulting in results that are more personally relevant and relevant.

[1172] In this way, the system according to the present invention takes into consideration the user's experience, interests, and even emotional data, and helps the user efficiently and effectively find the most suitable company or job type.

[1173] The processing flow will be explained below.

[1174] Step 1:

[1175] Users use a terminal to access a dedicated input form and enter their work experience, life experience, areas of interest, and hobbies and preferences. For example, they can enter information such as "5 years of marketing experience," "has leadership experience," "interest in IT and e-commerce," or "photography is my hobby."

[1176] Step 2:

[1177] The device's built-in camera and microphone capture the user's facial expressions and voice in real time as they type. The emotion engine analyzes these and collects data on the emotions the user is expressing (e.g., joy, excitement, anxiety, etc.).

[1178] Step 3:

[1179] The terminal converts the information input by the user and the emotion data collected by the emotion engine into data packets and transmits them to the server.

[1180] Step 4:

[1181] The server receives the data packets sent from the terminal and performs data pre-processing. The data pre-processing means performs the following processes:

[1182] Cleaning the data (e.g. removing unnecessary whitespace and special characters)

[1183] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[1184] Categorization (e.g., classifying "photography" as a creative skill)

[1185] Step 5:

[1186] The server inputs the preprocessed data and emotional data into a generative AI model. The generative AI model uses machine learning techniques to identify the most suitable industries and companies based on the user's work experience, life experience, areas of interest, and hobbies and preferences. The model also takes emotional data into account, and if the emotion is positive, it increases the score for that industry or company.

[1187] Step 6:

[1188] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. For example, if a user is interested in IT and e-commerce and has positive feelings about them, the marketing department of an e-commerce company or the creative director of an IT solutions company will be recommended with a high score.

[1189] Step 7:

[1190] The server organizes the generated recommendation results, converts them into an appropriate format, assembles them into a data packet, and transmits it to the terminal.

[1191] Step 8:

[1192] The device receives the data packet sent from the server and displays a list of recommended industries and companies to the user, including specific company names and job titles (e.g., "Marketing Department at XX Corporation" or "Creative Director at XX Solutions Corporation").

[1193] Step 9:

[1194] Users can check the recommendations displayed on their device, obtain detailed information about each company and job type, and take actions such as going to the details page of a company they are interested in and applying for a job.

[1195] Through the above processing steps, the system takes into consideration the user's experience, interests, and even emotional data, helping them find the most suitable company or job type efficiently and effectively.

[1196] Example 2

[1197] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1198] Conventional career change support systems have the problem of being unable to provide personalized recommendations that are based not only on the user's work history and areas of interest, but also on the emotions expressed by the user when entering information. This makes it difficult to find jobs and organizations that match the user's true interests and aptitudes.

[1199] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input their work history, life experience, areas of interest, and hobbies; a transmission means for transmitting information from the input means to the processing device; a data preprocessing means for data cleansing, normalizing, and classifying the information transmitted from the transmission means; a generative AI model application means for applying a generative AI model based on the information preprocessed by the data preprocessing means to identify the most suitable job type or organization; a result display means for displaying to the user the recommendation results of the most suitable job type or organization obtained from the generative AI model application means; and an emotion recognition means for collecting emotion data input by the user using an emotion recognition device and reflecting the data in the generative AI model. This enables personalized recommendations that take into account not only the user's experience and areas of interest but also the emotion data.

[1200] "Input means" refers to devices and software that allow users to input their work history, life experiences, areas of interest, and hobbies into the system.

[1201] The "transmission means" refers to a communication function for transmitting information acquired from the input means to a processing device or a server.

[1202] "Data Pre-Processing Means" refers to algorithms and programs for data cleansing, normalizing, and classifying information transmitted from the Transmission Means.

[1203] "Means for applying a generative AI model" refers to the program and process for applying a generative AI model based on preprocessed information to identify the most suitable job type or organization.

[1204] "Result display means" refers to a device and software for displaying the recommendation results obtained by the generative AI model application means to the user.

[1205] "Emotion recognition means" refers to an emotion recognition device and software for collecting and analyzing emotion data expressed by a user during input.

[1206] "Generative AI models" refer to algorithms and models that use machine learning techniques to analyze user data and identify the most suitable jobs and organizations.

[1207] "Guideline display function" refers to an interface function that provides instructions and hints to assist the user when entering information.

[1208] MODE FOR CARRYING OUT THE INVENTION

[1209] The system according to the present invention supports users in finding the most suitable company or industry when job hunting, and further includes emotion recognition means for recognizing the emotions of the user. Specific embodiments of this system are described below.

[1210] User input of information

[1211] The user uses a terminal to access a dedicated input form and enters information such as work history, life experience, areas of interest, and hobbies. This input method is equipped with a guideline display function to allow the user to easily enter the required information. For example, the user can start a web browser (e.g., Google Chrome or Mozilla Firefox) and access the input form via its URL. Following the input fields, the user enters the following information:

[1212] Work history (e.g., 5 years of marketing experience)

[1213] Life experience (e.g. leadership experience)

[1214] Area of ​​interest (e.g. IT, E-commerce)

[1215] Hobbies (e.g. photography)

[1216] Incorporating emotion recognition measures

[1217] While the user is entering information, the device's built-in camera and microphone are activated to record the user's facial expressions and voice in real time. This allows the emotion recognition means to analyze and collect the user's emotional data (happiness, surprise, anxiety, etc.). This emotion recognition is performed using software such as Amazon Rekognition and Microsoft Azure's Emotion API.

[1218] Data submission and preprocessing

[1219] The terminal converts the information input by the user and the emotion data analyzed by the emotion recognition device into data packets and sends them to the server. This transmission uses Internet protocols (e.g., HTTP, HTTPS). The server receives the transmitted data packets and first performs data preprocessing. The data preprocessing means performs the following processes:

[1220] Data cleansing: Removing unnecessary whitespace and special characters.

[1221] Data normalization: Convert "5 years of marketing experience" to "Marketing position, 5 years of experience."

[1222] Categorization: Classify "photography" as a creative skill.

[1223] Applying generative AI models

[1224] The server inputs the preprocessed data and emotion data into a generative AI model. This generative AI model uses, for example, GPT-4 (OpenAI's language model) or BERT (Google's language understanding model). The server uses these models to analyze the input data and references past job change data and a database of company characteristics. This allows it to identify the most suitable job type and organization based on the user's experience, areas of interest, and emotion data.

[1225] Generating and displaying recommendations

[1226] The generative AI model application means ranks the most suitable jobs and organizations based on the analysis results and generates recommendation results. In doing so, it also takes into account the user's emotional data and adjusts the score accordingly. The server organizes the generated recommendation results, converts them into a user-friendly format, compiles them into a data packet, and sends it to the terminal. The terminal receives this and displays a list of recommended jobs and organizations to the user. This list includes specific company names and job types (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[1227] Specific examples

[1228] For example, if a user inputs information such as "30s, 5 years of marketing experience, hobby is photography, interest areas are IT and e-commerce," and the emotion recognition means indicates that the user is excited or interested when entering information, the generative AI model will consider this as a favorable indicator. As a result, it will generate and present to the user recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company."

[1229] Prompt Sentence Examples

[1230] Here are some example prompts to input to a generative AI model:

[1231] User profile:

[1232] Age: 30s

[1233] Experience: 5 years of marketing experience

[1234] Areas of interest: IT, E-commerce

[1235] Hobbies: Photography

[1236] Emotional Data:

[1237] Excitement: High

[1238] Interest: High

[1239] Based on the information above and sentiment data, identify the industry, company, and job type that would be a perfect fit for this user.

[1240] In this way, the system according to the present invention takes into consideration the user's experience, areas of interest, and even emotional data, and helps the user efficiently and effectively find the most suitable job or organization.

[1241] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1242] Step 1:

[1243] The user accesses a dedicated input form using a terminal. They launch a web browser, enter the URL of the input form, and display the screen. The user enters information such as work history, life experience, areas of interest, and hobbies. The input content includes work history (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This information is collected as input data.

[1244] Step 2:

[1245] While the user is entering information, the device's built-in camera and microphone are activated, recording the user's facial expressions and voice in real time. The emotion recognition device analyzes this recorded data and generates emotion data such as joy, surprise, and anxiety. This emotion data is temporarily stored in the device.

[1246] Step 3:

[1247] The device combines the information entered by the user and the emotional data analyzed by the emotion recognition device into a single data packet. The data packet is formatted in JSON or XML format. The user input information and emotional data are packetized.

[1248] Step 4:

[1249] The device sends the generated data packets to a server over the Internet. The data packets are delivered to the server using the HTTP or HTTPS protocol. The server receives the data packets.

[1250] Step 5:

[1251] The server processes the received data packets and performs data cleansing, normalization, and categorization. Data cleansing removes unnecessary spaces and special characters, normalization converts "5 years of marketing experience" to "Marketing position, 5 years of experience," and categorization classifies "photography" as a creative skill. The preprocessed data is generated.

[1252] Step 6:

[1253] The server inputs the preprocessed data and emotion data into a generative AI model. This generative AI model uses, for example, GPT-4 or BERT. The generative AI model analyzes the input data and references past job change data and a database of company characteristics. The analysis results in identifying the most suitable job type and organization.

[1254] Step 7:

[1255] The generative AI model application means ranks the most suitable jobs and organizations based on the analysis results and generates recommendation results. At this time, it also takes into account the user's emotional data and adjusts the scores of related jobs and organizations. The generated recommendation results are compiled into a data packet.

[1256] Step 8:

[1257] The server converts the generated recommendations into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives it and displays a list of recommended jobs and organizations on the screen. The displayed list includes specific company names and job types (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[1258] (Application example 2)

[1259] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1260] In today's job-hunting environment, it is not easy for users to find the perfect company or industry. In particular, there is a need for matching that takes into account not only skills and experience, but also the user's personal interests and emotions. However, conventional systems do not utilize users' emotional data for matching, which hinders efficient and effective job hunting.

[1261] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: an input means for the user to input their work experience, life experience, areas of interest, and hobbies and preferences; an emotion analysis means for analyzing the user's emotions during input and generating user emotion data; a transmission means for transmitting information from the input means and the user emotion data collected by the emotion analysis means to the server; a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted from the transmission means; a generative AI model application means for applying a generative AI model to the information and emotion data preprocessed by the data preprocessing means to identify optimal industries and companies; and a result display means for displaying to the user the recommended industries and companies obtained from the generative AI model application means. This enables more personalized job recommendations that take the user's interests and emotions into consideration.

[1262] The "input means" is a mechanism for allowing a user to input his / her own work experience, life experience, areas of interest, hobbies and preferences.

[1263] The "transmission means" is a mechanism for transmitting information and emotion data from the input means to the server.

[1264] "Data pre-processing means" is a mechanism for cleaning, normalizing, and categorizing information transmitted from a transmission means.

[1265] The "generative AI model application means" is a mechanism for applying a generative AI model to identify the most suitable industries and companies based on the information and emotion data preprocessed by the data preprocessing means.

[1266] The "result display means" is a mechanism for displaying to the user the optimal industry and company recommendation results obtained from the generative AI model application means.

[1267] The "emotion analysis means" is a mechanism for analyzing the user's emotions during input and generating user emotion data.

[1268] The "emotion data transmission means" is a mechanism for transmitting the user's emotion data collected by the emotion analysis means to the server.

[1269] The system according to the present invention assists users in finding the most suitable company or industry when job hunting, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[1270] User input of information

[1271] First, the user uses a terminal to access a dedicated input form and enters information such as their work experience (e.g., 5 years of marketing experience), life experience (e.g., leadership experience), areas of interest (e.g., IT, e-commerce), and hobbies (e.g., photography). This input method is equipped with a guideline display function to make it easy for users to enter the required information.

[1272] emotion recognition

[1273] While the user is entering information, an emotion analysis means operates, which analyzes the user's facial expressions and voice in real time using the camera and microphone installed in the terminal. The emotion analysis means analyzes the emotions (e.g., joy, excitement, anxiety, etc.) while the user is entering information and collects that data.

[1274] Data transmission

[1275] The transmitting means converts the information input by the user and the emotion data collected by the emotion analyzing means into data packets and transmits them to the server.

[1276] Data Preprocessing

[1277] The server receives the transmitted data packet and first performs data pre-processing. The data pre-processing means performs the following processes:

[1278] Cleaning the data (removing unnecessary spaces and special characters)

[1279] Data normalization (e.g., converting "5 years of marketing experience" to "Marketing position, 5 years of experience")

[1280] Categorization (e.g., classifying "photography" as a creative skill)

[1281] Applying generative AI models

[1282] The server inputs the preprocessed data and emotional data into a generative AI model, which uses machine learning techniques to analyze the input data and references past job change data and a database of company characteristics to identify the most suitable industry and company based on the user's work experience, life experience, areas of interest, and emotional data.

[1283] Generating and displaying recommendations

[1284] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. It also takes the user's emotional data into account and makes adjustments accordingly. For example, if the emotional data confirms that the user is interested in a certain job or company, it will give the relevant job type or company a higher score.

[1285] Displaying the results

[1286] The server organizes the generated recommendations, converts them into a user-friendly format, assembles them into a data packet, and sends it to the device. The device receives the data and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department of a Certain Corporation" or "Creative Director of a Certain Solutions Corporation").

[1287] Specific examples

[1288] For example, if a user enters information such as "30s, 5 years of marketing experience, hobby is photography, areas of interest are IT and e-commerce," and sentiment analysis reveals that the user expresses excitement or interest during input, the generative AI model will interpret this as a positive indicator and generate and present recommendations such as "Marketing department of an e-commerce company" or "Creative director of an IT solutions company." Based on this user's sentiment data, appropriate adjustments are made, resulting in results that are more personally relevant and relevant.

[1289] Prompt Sentence Examples

[1290] "User data: Experience: 5 years of marketing experience, Life experience: Leadership experience, Interests: IT, e-commerce, Hobbies: Photography, Emotions: happy. Please recommend companies and jobs that would be a good fit for this user."

[1291] As described above, this system takes into account the user's experience, interests, and even emotional data to help them find the company and job that best suits them efficiently and effectively.

[1292] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1293] Step 1:

[1294] The user uses a terminal to access a dedicated input form and enters their work experience, life experience, areas of interest, hobbies, and preferences. The input means is equipped with a guideline display function that guides the user to easily enter the necessary information. The input data at this stage is user information such as work experience and hobbies.

[1295] Step 2:

[1296] While the user is inputting information, the device uses a camera and microphone to analyze the user's facial expressions and voice in real time. The emotion analysis means analyzes the user's emotions (e.g., joy, excitement, anxiety, etc.) at the time of input and collects the data. The input is the user's facial expressions and voice information, and the output is analyzed emotional data.

[1297] Step 3:

[1298] The transmitting means of the terminal converts the information input by the user and the emotion data collected by the emotion analysis means into data packets and transmits them to the server. In this step, the input data is the user information and emotion data, and the output data is the transmitted data packets.

[1299] Step 4:

[1300] The server receives the data packet and first performs data preprocessing. The data preprocessing method cleans the data (removes unnecessary spaces and special characters), normalizes the data (e.g., converts "5 years of marketing experience" to "Marketing position, 5 years of experience"), and categorizes the data (e.g., classifies "photography" as a creative skill). The input is the raw data sent, and the output is the cleaned and normalized data.

[1301] Step 5:

[1302] The server inputs the preprocessed data and emotion data into the generative AI model. The generative AI model application means uses machine learning technology to analyze the preprocessed user data and emotion data, and identifies the most suitable industry and company by referencing past job change data and a database of company characteristics. The input is the preprocessed user data and emotion data, and the output is the identified industry and company information.

[1303] Step 6:

[1304] The generative AI model application method ranks the most suitable industries and companies based on the analysis results and generates recommendation results. At this time, emotional data is also taken into consideration and adjustments are made. For example, if emotional data confirms that the user is interested in a particular field, related job types and companies will be given higher scores. The input is company information identified by the model, and the output is ranked recommendation results.

[1305] Step 7:

[1306] The server organizes the generated recommendation results, converts them into a user-friendly format, packages them into data packets, and sends them to the terminal. The input is the ranked recommendation results, and the output is the data packets to be sent.

[1307] Step 8:

[1308] The device receives the data packet and displays a list of recommended industries and companies to the user. This list includes specific company names and job titles (e.g., "Marketing Department at a certain company" or "Creative Director at a certain solutions company"). The input is the data packet, and the output is the recommendation results displayed to the user.

[1309] The above are the specific processing steps of this system.

[1310] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1311] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1312] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1313] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1314] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1315] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1316] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1317] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1318] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1319] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1320] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1321] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1322] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1323] 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.

[1324] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1325] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1326] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1327] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1328] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1329] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1330] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1331] The following is further disclosed regarding the above embodiment.

[1332] (Claim 1)

[1333] An input means for a user to input his / her work experience, life experience, areas of interest, hobbies and preferences;

[1334] a transmitting means for transmitting information from the input means to a server;

[1335] a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted by the transmitting means;

[1336] A generative AI model application means for applying a generative AI model to identify the most suitable industry or company based on the information preprocessed by the data preprocessing means;

[1337] a result display means for displaying to the user the optimal industry and company recommendation results obtained from the generation AI model application means;

[1338] A system including:

[1339] (Claim 2)

[1340] 2. The system according to claim 1, wherein the input means has a guideline display function for assisting the user in inputting information.

[1341] (Claim 3)

[1342] The system according to claim 1, characterized in that the generating AI model application means has a function of scoring the suitability of the most suitable industry or company taking into account the user's preferences.

[1343] "Example 1"

[1344] (Claim 1)

[1345] input means for the user to input his / her work experience, life experience, areas of interest, and personal preferences;

[1346] a transmitting means for transmitting information from the input means to a server;

[1347] a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted by the transmitting means;

[1348] A generative AI model application means for applying a generative AI model to identify the most suitable job type and industry based on the information preprocessed by the data preprocessing means;

[1349] a result display means for displaying to the user the optimal job type and industry recommendation results obtained from the generating AI model application means;

[1350] A system including:

[1351] (Claim 2)

[1352] 2. The system according to claim 1, wherein the input means has a guideline display function for assisting a user in inputting information.

[1353] (Claim 3)

[1354] The system according to claim 1, characterized in that the generating AI model application means has a function of evaluating the suitability of the optimal job type and industry taking into account the user's personal preferences.

[1355] "Application Example 1"

[1356] (Claim 1)

[1357] An input means for a user to input his / her work experience, life experience, areas of interest, and hobbies and interests;

[1358] a transmitting means for transmitting information from the input means to a server;

[1359] a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted by the transmitting means;

[1360] A generative AI model application means for applying a generative AI model to identify the most suitable industry or company based on the information preprocessed by the data preprocessing means;

[1361] a result display means for displaying to the user the optimal industry and company recommendation results obtained from the generation AI model application means;

[1362] a virtual career consultant means for displaying the recommendation results and providing further details to the user via a smartphone or smart glasses;

[1363] A system including:

[1364] (Claim 2)

[1365] 2. The system according to claim 1, wherein the input means has a guideline display function for assisting the user in inputting information.

[1366] (Claim 3)

[1367] The system according to claim 1, characterized in that the generating AI model application means has a function of scoring the suitability of the most suitable industry or company taking into account the user's hobbies and interests.

[1368] "Example 2: Combining Emotion Engines"

[1369] (Claim 1)

[1370] input means for the user to input his / her work history, life experiences, areas of interest, and hobbies;

[1371] a transmitting means for transmitting information from the input means to the processing device;

[1372] a data preprocessing means for data cleansing, normalizing, and classifying the information transmitted from the transmitting means;

[1373] A generative AI model application means for applying a generative AI model to identify the most suitable job type and organization based on the information preprocessed by the data preprocessing means;

[1374] a result display means for displaying to the user the optimal job type and organization recommendation results obtained from the generation AI model application means;

[1375] An emotion recognition means for collecting emotion data input by a user using an emotion recognition device and reflecting the data in a generative AI model;

[1376] A system including:

[1377] (Claim 2)

[1378] 2. The system according to claim 1, wherein the input means has a guideline display function for assisting a user in inputting information.

[1379] (Claim 3)

[1380] The system according to claim 1, characterized in that the generative AI model application means has a function of scoring the suitability of the user for the most suitable job or organization by taking into account the collected emotional data in addition to the user's hobbies and areas of interest.

[1381] "Application example 2 when combining emotion engines"

[1382] (Claim 1)

[1383] An input means for a user to input his / her work experience, life experience, areas of interest, hobbies and preferences;

[1384] a transmitting means for transmitting information from the input means to a server;

[1385] a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted by the transmitting means;

[1386] A generative AI model application means for applying a generative AI model to identify the most suitable industry or company based on the information preprocessed by the data preprocessing means;

[1387] emotion analysis means for analyzing the user's emotion during input and generating emotion data of the user;

[1388] emotion data transmission means for transmitting the user emotion data collected by the emotion analysis means to a server;

[1389] The generative AI model application means includes a function to identify the most suitable industry or company by taking into account the user's emotional data,

[1390] a result display means for displaying to the user the optimal industry and company recommendation results obtained from the generation AI model application means;

[1391] A system including:

[1392] (Claim 2)

[1393] 2. The system according to claim 1, wherein the input means has a guideline display function for assisting the user in inputting information.

[1394] (Claim 3)

[1395] The system according to claim 1, characterized in that the generating AI model application means has a function of scoring the suitability of the most suitable industry or company by taking into account the user's hobbies, preferences and emotional data. [Explanation of symbols]

[1396] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. An input means for a user to input his / her work experience, life experience, areas of interest, hobbies and preferences; a transmitting means for transmitting information from the input means to a server; a data preprocessing means for cleaning, normalizing, and categorizing the information transmitted by the transmitting means; A generative AI model application means for applying a generative AI model to identify the most suitable industry or company based on the information preprocessed by the data preprocessing means; a result display means for displaying to the user the optimal industry and company recommendation results obtained from the generation AI model application means; A system including:

2. 2. The system according to claim 1, wherein the input means has a guideline display function for assisting the user in inputting information.

3. The system according to claim 1, characterized in that the generating AI model application means has a function of scoring the suitability of the most suitable industry or company taking into account the user's preferences.

Images