System

Abstract

A system is provided.SOLUTION: A system comprising: means for using a generative model to input information in the form of questions; means for matching job candidates with adopters based on collected information; means for coordinating interview schedules between job candidates and adopters; means for awarding reward points to job candidates upon completion of an initial interview; and means for troubleshooting if an interview is not conducted.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] Currently, the main recruitment challenges faced by small and medium-sized businesses and job seekers include the cumbersome process of entering information, the inability to find suitable candidates, and the complex and expensive pricing structures of job boards and recruitment agencies. These challenges hinder the efficient recruitment and job search process and are a major problem, particularly for small and medium-sized businesses, that leads to wasted resources. [Means for solving the problem]

[0005] This invention simplifies information input by incorporating a means for using a generative model in which information is entered in the form of questions. Furthermore, a means for matching job seekers with employers based on collected information is provided, making it easier to find a suitable match. After a match is established, a means for arranging interview schedules between job seekers and employers is provided to support smooth communication. A means for awarding reward points to job seekers upon completion of the first interview increases the job seeker's motivation. Furthermore, a means for troubleshooting in the event that an interview does not take place increases the reliability of the system and user satisfaction. Furthermore, by incorporating a means for using a generative model to analyze and score conditions and a means for performing operations to arrange interviews between job seekers and employers based on notifications, the entire process can be operated efficiently.

[0006] "Information input" is the act of a user providing necessary data to a system.

[0007] The "question format" is a format in which the generation AI presents specific questions for the user to answer.

[0008] A "generative model" is a type of artificial intelligence that learns patterns from large amounts of data and automatically generates and analyzes the necessary information.

[0009] A "means" is a method, tool, or process used to achieve a particular end.

[0010] "Matching" is the process of finding the best match based on the requirements of the job seeker and the employer.

[0011] "Interview scheduling" refers to the act of setting a date and time that is convenient for both the job seeker and the employer, and finalizing the interview schedule.

[0012] "Reward points" are points awarded as an incentive for a specific action or achievement.

[0013] "Troubleshooting" refers to the actions or means taken to resolve unexpected problems or failures when they occur.

[0014] "Analysis and scoring" is the process of evaluating collected information, quantifying it, and ranking it.

[0015] "Notifications" are communications used to inform users of important information and updates. [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] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it uses generative AI to simplify information input, matches job seekers with employers, smoothly arranges interview schedules, awards reward points, and handles problems. This system consists of a server, terminals, and users (employers and job seekers).

[0038] Program processing overview

[0039] Enter information

[0040] The server launches the generative model and obtains the necessary information from the user in the form of a question. For example, the server might ask, "What position are you hiring for?" and the user (employer) might respond, "Sales manager." Or, the server might ask, "Tell me about your past work history," and the user (job seeker) might respond, "I have two years of sales experience." The information collected in this way is stored in a database by the server.

[0041] matching

[0042] The server analyzes the collected information and scores compatibility between job seekers and employers based on their criteria. For example, a generative model performs optimal matching based on information such as the job seeker's skill set, work experience, and preferred work location. A list of highly-scoring job seekers is generated and notified to the employer. Similarly, job openings that match the criteria are notified to the job seeker.

[0043] Notification and confirmation

[0044] When the user receives the notification, they click the "Ask for a meeting" button to indicate their intention to meet. The server confirms this intention and starts the process to coordinate the schedule for both parties.

[0045] First interview and reward

[0046] After the job seeker and employer conduct the first interview, the server confirms the completion of the interview and awards reward points to the job seeker, which can increase the job seeker's motivation.

[0047] Troubleshooting

[0048] If the server does not conduct an interview after a successful match, it will take appropriate action to resolve the issue, such as adding penalty points to the employer's account or providing a refund to the job seeker.

[0049] Specific examples

[0050] Example 1: When the recruiter inputs information

[0051] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[0052] 2. The server generates a question: The server asks a question through the generative model: "Tell me about the position you're hiring."

[0053] 3. The employer responds: "I'm the sales manager," the employer responds.

[0054] 4. Server saves the data: The server saves the answers in a database.

[0055] Example 2: Job seeker receives a match notification

[0056] 1. The server analyzes the conditions: The server analyzes the job seeker's conditions (skill set, location, experience, etc.) and scores them using a generative model.

[0057] 2. The server sends a notification: Based on the list of high-scoring employers, the server notifies the job seeker that "job information matching your criteria has been found."

[0058] 3. The job seeker requests an interview: The job seeker indicates their intention by pressing the "Interview" button.

[0059] As described above, this invention efficiently solves the problems of employers and job seekers through a system that includes a series of processes, such as inputting information in the form of questions using generative AI, matching through condition analysis and scoring, and providing rewards and troubleshooting. This system makes recruitment activities more efficient and reduces costs.

[0060] The processing flow will be explained below.

[0061] Program processing flow

[0062] Information input phase

[0063] Step 1:

[0064] The user logs into the application using a terminal. The server authenticates the account information and displays the main screen if the login is successful.

[0065] Step 2:

[0066] The server invokes the generative model to generate questions for the user (employer or job seeker), such as "What kind of job do you want?"

[0067] Step 3:

[0068] The user enters an answer to the question. If they are an employer, they might answer "sales manager," and if they are a job seeker, they might answer "sales position."

[0069] Step 4:

[0070] The server stores the user's answers in a database, which is used for subsequent analysis and matching.

[0071] Matching Process

[0072] Step 5:

[0073] The server analyzes all the information on job seekers and employers stored in the database. The generative model scores them based on the criteria and finds the optimal combination.

[0074] Step 6:

[0075] The server generates a list of high-scoring job seekers and sends notifications to employers.

[0076] Step 7:

[0077] The server also notifies the job seeker of a list of employers that match their criteria, with a message such as "We've found jobs that match your criteria."

[0078] Notification and confirmation phase

[0079] Step 8:

[0080] The user checks the notification and clicks the "Interview" button. If both the job seeker and the employer click the button, the process proceeds to the next step.

[0081] Step 9:

[0082] The server displays a screen for arranging the interview schedule between the two parties. The user enters the desired date and time.

[0083] Step 10:

[0084] The server will finalize the schedule and notify both parties of the interview details.

[0085] Initial Interview and Reward Phase

[0086] Step 11:

[0087] Users (job seekers and employers) conduct interviews at the specified date and time.

[0088] Step 12:

[0089] After the interview is completed, the server confirms the completion of the interview and gives reward points to the job seeker.

[0090] Troubleshooting phase

[0091] Step 13:

[0092] If an interview is not conducted, the server will recognize it as a problem and take appropriate action, such as giving penalty points to the recruit or refunding reward points to the job seeker.

[0093] The above is the specific processing flow of the system. This flow will enable efficient recruitment activities and solve the problems of small and medium-sized businesses and job seekers.

[0094] Example 1

[0095] 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."

[0096] There is a need for efficient methods to resolve the recruitment issues faced by small and medium-sized businesses and job seekers. Specifically, it is necessary to simplify the information entry process, ensure appropriate matching, smoothly arrange interview schedules, award reward points to motivate job seekers, and deal with problems when interviews are not conducted.

[0097] 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.

[0098] In this invention, the server includes a means for inputting information in the form of questions using a generative AI model, a means for matching job seekers with employers based on collected data, a means for sending a notification to the user and arranging an interview schedule between the job seeker and employer, a means for awarding reward points to the job seeker when the first interview is completed, and a means for dealing with problems when an interview does not take place. This makes recruitment activities more efficient and reduces costs, while also making it possible to improve job seeker motivation and quickly deal with problems when they occur.

[0099] A "generative AI model" is a model that uses artificial intelligence to automatically generate text and data.

[0100] "Information input" is the process by which the system obtains the necessary information from the user.

[0101] A "question format" is a method of gathering information by asking a user a series of questions.

[0102] "Data" means the collection of information provided by the user that the system uses for analysis and matching.

[0103] "Matching" is the process of finding the best match based on the requirements of the job seeker and the employer.

[0104] "User" refers to the employers and job seekers who use the system.

[0105] "Notification" is the act of the system sending information or messages to the user.

[0106] "Scheduling" is the process of setting up an interview date and time between a job seeker and an employer.

[0107] A "first interview" refers to the first meeting between a job seeker and an employer.

[0108] "Reward points" are points that the system awards to job seekers as motivation and reward.

[0109] "Troubleshooting" is the process for resolving problems that arise after a match is made.

[0110] The present invention is a system that uses a generative AI model to solve recruitment issues faced by small and medium-sized businesses and job seekers. Specifically, the system simplifies information input, matches job seekers with potential employers, arranges interview schedules, awards reward points, and handles problems. Detailed embodiments of the present invention are described below.

[0111] System Configuration

[0112] Hardware and Software Configuration

[0113] This system mainly consists of a server, terminals, and users (employers and job seekers).

[0114] Server: Responsible for the primary data processing and execution of generative AI models. For example, the server uses generative AI models such as OpenAI's GPT-3.

[0115] Terminal: A device where a user enters information and checks results. This includes computers, smartphones, tablets, etc.

[0116] Users: Employers and job seekers who use the system.

[0117] Specific examples of hardware use

[0118] The server uses a cloud server equipped with a high-performance processor and large memory capacity.

[0119] The terminal can be any device with a standard internet connection.

[0120] Specific examples of software use

[0121] Generative AI models: Use natural language generation models such as OpenAI's GPT-3.

[0122] Database Management Systems: RDBMS such as MySQL or PostgreSQL are used to store data.

[0123] Front-end: Building the user interface using JavaScript frameworks such as React or Vue.js.

[0124] Process Overview

[0125] The server launches the generative AI model and asks the user questions to obtain the necessary information. The collected information is stored in a database, and the server matches job seekers with employers based on that information. The matching results are sent to the user as a notification, and if the user indicates a desire for an interview, the server arranges the interview schedule. When the interview is completed, the server awards reward points to the job seeker, and if the interview does not take place, it handles any issues.

[0126] Example

[0127] Example 1: When the recruiter inputs information

[0128] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[0129] 2. The server generates a question: Using a generative AI model, the server generates a question such as, "Tell me about the position you're hiring."

[0130] 3. The recruiter answers: "I'm a sales manager."

[0131] 4. Server saves the data: The answers are saved in a database.

[0132] Example 2: When a job seeker receives a match notification

[0133] 1. The server analyzes the conditions: The job seeker's conditions (skill set, work location, experience, etc.) are analyzed using a generative AI model and a score is generated.

[0134] 2. The server sends a notification: "We've found a job that matches your criteria."

[0135] 3. The job seeker requests an interview: The job seeker indicates their intention by pressing the "Interview" button.

[0136] Prompt Sentence Examples

[0137] Here are some example prompts that the generative AI model might use:

[0138] 1. For employers: "Tell me about the position you're hiring."

[0139] 2. For job seekers: "Tell me about your past work experience."

[0140] In this way, the present invention is a system that uses a generative AI model to input information in the form of questions, and then comprehensively performs matching, notification, interview schedule adjustment, reward point allocation, and trouble shooting, thereby streamlining recruitment activities and reducing costs.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Program processing flow

[0143] Step 1: Start entering information

[0144] The server launches the generative AI model and obtains the necessary information from the user in the form of questions.

[0145] Specific behavior:

[0146] 1. The server launches a generative AI model: Launch a generative AI model (e.g., OpenAI GPT-3).

[0147] 2. Server generates questions: A generative AI model is used to generate questions, such as "What position are you hiring?"

[0148] 3. User enters information: Employers and job seekers answer questions and enter information.

[0149] 4. Input: Information entered by the user (e.g., position name, work history).

[0150] 5. Output: The information obtained by the server is stored in the server's database.

[0151] Step 2: Analyzing and matching information

[0152] The server analyzes the collected information and uses a generative AI model to score compatibility between job seekers and employers based on their criteria.

[0153] Specific behavior:

[0154] 1. The server collects data: The latest collected information is retrieved from the database.

[0155] 2. The server analyzes using the generative AI model: It runs the analysis algorithm and analyzes the collected information.

[0156] 3. The server performs scoring: A generative AI model is used to score the compatibility between job seekers and employers.

[0157] 4. Input: Job seeker and employer information stored on the server.

[0158] 5. Output: Calculate compatibility scores and generate a list of job seekers with high scores.

[0159] Step 3: Notification of match results

[0160] The server sends a notification to the user based on the matching results.

[0161] Specific behavior:

[0162] 1. Server generates notification content: A generative AI model is used to generate notification content, e.g., "We've found a job posting that matches your criteria."

[0163] 2. The server sends a notification: A notification is sent to the device.

[0164] 3. Users receive notifications: Job seekers and employers receive notifications.

[0165] 4. Input: Generated compatibility scores and a list of high-scoring job seekers.

[0166] 5. Output: Notification message sent to the user.

[0167] Step 4: Schedule an interview

[0168] When the user indicates a desire for an interview, the server arranges the interview schedule.

[0169] Specific behavior:

[0170] 1. User indicates desire for interview: The job seeker presses the "Interview" button.

[0171] 2. The server adjusts the schedules: The schedules of both parties are automatically adjusted and the date and time of the meeting is decided.

[0172] 3. Server sends notification again: Notifies the user of the adjusted schedule.

[0173] 4. Input: Job seeker and hire schedule information.

[0174] 5. Output: Confirmed interview date and time and notification message.

[0175] Step 5: First interview and reward points awarded

[0176] When the first interview is completed, the server awards reward points to the job seeker.

[0177] Specific behavior:

[0178] 1. Confirmation of interview completion: The recruiter presses the "Interview Completed" button.

[0179] 2. The server awards reward points: The server awards reward points to the job seeker and reflects them in the account.

[0180] 3. The server saves the data: The awarded reward points are saved in the database.

[0181] 4. Enter: Confirmation of interview completion.

[0182] 5. Output: Reward points are awarded and stored in the database.

[0183] Step 6: Perform troubleshooting

[0184] If the interview does not take place, the server will take action to troubleshoot.

[0185] Specific behavior:

[0186] 1. The server checks that the interview has not been conducted: It detects that the interview has not been conducted.

[0187] 2. Server assigns penalty: assigns penalty points to the adopter.

[0188] 3. The server processes the refund: The server processes the refund for the job seeker.

[0189] 4. Enter: Confirmation information for unsuccessful interviews.

[0190] 5. Output: Notification of penalty points being awarded and refund completion.

[0191] (Application example 1)

[0192] 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."

[0193] A major challenge for logistics centers is efficiently securing a large workforce. However, many small and medium-sized businesses lack the resources and technology to quickly and efficiently find job seekers, schedule interviews, and ultimately secure labor. This makes the recruitment process cumbersome and time-consuming, making it difficult to find suitable candidates. Scheduling interviews and dealing with issues when interviews are not conducted are also challenges.

[0194] 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.

[0195] In this invention, the server includes means for using a generative model in which information is input in the form of questions, means for matching job seekers with employers based on the collected information, means for arranging interview schedules between job seekers and employers, means for awarding reward points to job seekers when the first interview is completed, means for dealing with problems when the interview does not take place, means for automatically arranging schedules between job seekers and employers using an external service, and means for electronically confirming the completion of interviews. This enables the logistics center to quickly and efficiently secure labor.

[0196] "Means of using a generative model that inputs information in the form of a question" refers to a means of obtaining the necessary information from the user in the form of a question and securing that information using a generative AI model.

[0197] "Means of matching job seekers and employers based on collected information" refers to a means of analyzing collected information on job seekers and employers and appropriately connecting the two based on mutual conditions.

[0198] The "means for coordinating interview schedules between job seekers and employers" is a means for automatically setting the optimal interview date and time, taking into consideration the schedules of both the employer and the job seeker.

[0199] "Means for granting reward points to a job seeker upon completion of the first interview" refers to a means for granting reward points to a job seeker as an incentive after confirming that the first interview has ended.

[0200] "Measures to deal with problems when an interview is not conducted" refers to measures to provide appropriate compensation or penalties to users when an interview is canceled or not conducted.

[0201] "Means for automatically coordinating the schedules of job seekers and employers using external services" refers to means for automatically coordinating the schedules of job seekers and employers using external calendar and schedule management services.

[0202] "Means for confirming completion of interview by electronic means" refers to a means for reliably confirming that the interview has been completed using electronic means, such as scanning a QR code.

[0203] The system embodying this invention is designed to solve the problems of job recruitment efficiency and interviews that employers and job seekers face. This system is composed of a server, terminals, and users.

[0204] Server Roles

[0205] Hardware and software used

[0206] The server uses the following hardware and software:

[0207] Server-side hardware: AWS EC2

[0208] Database: DynamoDB

[0209] Generative AI model: OpenAI GPT-3

[0210] Backend: Node.js, Express

[0211] Communication method: REST API

[0212] Enter information

[0213] The server uses a generative AI model to prompt the user for information in the form of a question, such as "What position are you hiring for?", to which the candidate responds "Sales Manager." This information is stored in DynamoDB via a REST API.

[0214] matching

[0215] Based on the collected information, the generative AI model analyzes and scores the requirements of job seekers and employers. The scoring system makes an appropriate match, and the employer is notified of a list of job seekers with high scores.

[0216] Schedule adjustment

[0217] When a job seeker notifies the company that they wish to interview, the system automatically coordinates the schedules of both parties using the Google Calendar API, efficiently managing the schedules of both the job seeker and the employer through an external service.

[0218] Reward points awarded

[0219] Once the first interview is completed, the job seeker will scan the QR code to confirm the completion of the interview, after which reward points will be automatically awarded to the job seeker.

[0220] Troubleshooting

[0221] If an interview is not conducted, the server will provide appropriate compensation or penalties, such as adding penalty points to the employer's account or providing a refund to the job seeker.

[0222] Device Role

[0223] Hardware and software used

[0224] The terminal uses the following hardware and software:

[0225] Frontend: React Native (smartphone app)

[0226] Enter information

[0227] Users (employers, job seekers) use their devices to answer questions posed by the generative AI model, and this information is sent to the server in real time and stored in DynamoDB.

[0228] Check the schedule

[0229] When the request button is pressed, the appointment is automatically scheduled on the device, and the schedule is synchronized between the device and the server using the Google Calendar API.

[0230] User Roles

[0231] Information input and response

[0232] The user inputs information through a device, answers questions posed by the generative AI model, and performs other operations such as pressing a button to indicate a desire for an interview.

[0233] Conducting interviews

[0234] Once the interview is complete, job seekers confirm completion by scanning a QR code, which automatically awards reward points.

[0235] Specific examples

[0236] Example prompts to be input to the generative AI model:

[0237] (When the recruit logs in)

[0238] "Please tell me about the positions available at the logistics center."

[0239] User Answer: "Warehouse worker"

[0240] "What skills are required for the position?"

[0241] User Answer: "Forklift driving qualification"

[0242] (When job seeker logs in)

[0243] "Tell me about your past work history."

[0244] User Answer: "I have 3 years of warehouse experience."

[0245] "Please tell us where you would like to work."

[0246] User Answer: "Tokyo"

[0247] In this way, a single process is carried out, from inputting information to matching, arranging interview schedules, awarding reward points, and troubleshooting, enabling logistics centers to quickly and efficiently secure labor.

[0248] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0249] Step 1:

[0250] The server launches the generative AI model and generates questions for information input. The questions are sent to the device, and the user (employer or job seeker) enters the answers. The input includes information such as the position being filled and past work history. The server uses the generative AI model to create prompts to generate appropriate questions and presents them to the user. The user's answer data is sent from the device to the server and stored in DynamoDB.

[0251] Step 2:

[0252] The server executes a matching algorithm based on the information collected. First, the server retrieves the job seeker and employer information collected from DynamoDB. Then, it uses a generative AI model to analyze and score the conditions. The input for this step is the job seeker's skill set, work experience, preferred work location, etc., and the output is a compatibility score. A list of high-scoring job seekers is generated and notified to the employer's device.

[0253] Step 3:

[0254] The user (job seeker) receives the notification and presses the "Interview" button. This action registers the interview request. The server retrieves the schedules of the job seeker and employer using the Google Calendar API and automatically adjusts the schedules. The input for this step is the available time of the job seeker and employer, and the output is the adjusted interview date and time. The adjustment result is notified to the terminal.

[0255] Step 4:

[0256] A user (job seeker) attends an interview on the interview date. After completing the interview, the job seeker scans the QR code to report the completion of the interview. The device sends the scanned data to the server, which then confirms the completion of the interview. The input of this step is the scanned data of the QR code, and the output is confirmation of the completion of the interview. After confirmation, reward points are automatically awarded to the job seeker.

[0257] Step 5:

[0258] If the interview is not conducted, the server will automatically execute a troubleshooting process. First, it checks the actions of both parties at the scheduled interview date and time, and if the interview is not conducted, it starts the troubleshooting process. The input of this step is the log of the not conducted interview, and the output is the feedback of compensation or penalty. For example, penalty points are added to the employer's account and a refund is given to the job seeker.

[0259] 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.

[0260] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it uses generative AI to simplify information input, match job seekers with employers, smoothly arrange interview schedules, award reward points, and handle problems. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it is possible to provide more personalized responses. This system consists of a server, terminals, and users (employers and job seekers).

[0261] Program processing overview

[0262] Enter information

[0263] The server launches the generative model and obtains the necessary information from the user in the form of a question. For example, it displays a question such as, "What kind of job do you want?" As the user answers, the server simultaneously uses an emotion engine to analyze the user's emotions and stores this information in a database. For example, if the user is feeling stressed, that information is also recorded.

[0264] matching

[0265] The server analyzes the collected information and scores the compatibility between the job seeker and employer based on their criteria. A generative model evaluates the job seeker's skill set, work experience, preferred work location, etc., and an emotion engine adjusts the score based on the user's emotional state. A list of high-scoring job seekers is generated and notified to the employer. Similarly, job openings that match the criteria are notified to the job seeker. For example, if the job seeker is nervous, a message to ease their tension is sent.

[0266] Notification and confirmation

[0267] The user receives the notification and clicks the "Appoint" button. The server uses an emotion engine to analyze the user's emotional state and suggest an appropriate time and place. For example, if the user is tired, it suggests a time when they can relax.

[0268] First interview and reward

[0269] When users (job seekers and employers) conduct interviews, the server uses an emotion engine to record their emotional states before and after the interview. After the interview is over, the server confirms the completion of the interview and awards reward points to the job seeker. It also provides feedback based on the emotion engine. For example, if the job seeker is satisfied after the interview, this is displayed as feedback.

[0270] Troubleshooting

[0271] If the server does not conduct an interview after a successful match, it uses an emotion engine to analyze the emotional state behind the problem. It then takes appropriate action to resolve the issue, such as assigning penalty points to the hire or refunding reward points to the job seeker. For example, if the user expresses anger or dissatisfaction, the system takes that emotional state into consideration.

[0272] Specific examples

[0273] Example 1: When the recruiter inputs information

[0274] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[0275] 2. Server generates question: The server asks a question through the generative model, such as "Tell me about the position you're hiring for." At the same time, the emotion engine checks the emotional state of the recruit.

[0276] 3. Hire responds: "I'm a sales manager," the hire responds. The emotion engine records the hire's stress level.

[0277] 4. Server saves the data: The server saves the answers and emotion data in a database.

[0278] Example 2: Job seeker receives a match notification

[0279] 1. Server analyzes the job seeker's requirements (skill set, location, experience, etc.) and scores them using a generative model. At the same time, the emotion engine evaluates the job seeker's emotional state.

[0280] 2. Server sends notification: Based on the list of high-scoring employers, the server notifies the job seeker that "We have found a job posting that matches your criteria." If the job seeker is nervous, it also sends a relaxing message.

[0281] 3. The job seeker requests an interview: The job seeker clicks the "Interview" button to indicate their intention. The emotion engine analyzes the desired time slot and sends the results to the server.

[0282] As described above, this invention uses generative AI and an emotion engine to solve the problems of employers and job seekers in an efficient and personalized way through a system that includes a series of processes such as inputting information in the form of questions, matching through condition analysis and scoring, scheduling that takes emotions into account, and rewards and troubleshooting. This system makes recruitment activities more efficient and realizes an approach that takes users' emotions into consideration.

[0283] The processing flow will be explained below.

[0284] Program processing flow

[0285] Information input phase

[0286] Step 1:

[0287] The user logs into the application using a terminal. The server authenticates the user's account information and displays the main screen if the login is successful.

[0288] Step 2:

[0289] The server invokes the generative model to generate questions for the user (employer or job seeker), such as "What kind of job do you want?"

[0290] Step 3:

[0291] The user inputs answers to the questions. For example, an employer might answer "sales manager," and a job seeker might answer "sales position." At the same time, the server uses an emotion engine to analyze the user's emotional state and stores that information in the database.

[0292] Step 4:

[0293] The server stores the user's answers and emotion data in a database for the next step.

[0294] Matching Process

[0295] Step 5:

[0296] The server analyzes the information of all job seekers and employers stored in the database and uses a generative model to score them based on the conditions.

[0297] Step 6:

[0298] The emotion engine adjusts the score based on the user's emotional state, for example, appropriately adjusting the score of a job candidate who is stressed.

[0299] Step 7:

[0300] Based on the scoring results, a list of job seekers with high scores is generated, and the server notifies the employer of this list.

[0301] Step 8:

[0302] Similarly, the server notifies the job seeker of a list of employers that match the job search criteria, with the notification including the message "We have found jobs that match your criteria."

[0303] Notification and confirmation phase

[0304] Step 9:

[0305] The user checks the notification and clicks the "Ask for an interview" button in the notification. The server receives this decision and proceeds to the next step.

[0306] Step 10:

[0307] The server uses an emotion engine to analyze the user's emotional state and suggest the best time and place for the interview, for example, suggesting a relaxing time for a tired user.

[0308] Step 11:

[0309] Once the user reviews and agrees to the proposed schedule, the server notifies both parties of the interview details.

[0310] Initial Interview and Reward Phase

[0311] Step 12:

[0312] Users (job seekers and employers) conduct interviews at the specified date and time. The server uses an emotion engine to record the emotional state before and after the interview.

[0313] Step 13:

[0314] After the interview is completed, the server confirms the completion of the interview, awards reward points to the job seeker, and generates feedback based on the emotion engine to provide to the user.

[0315] Troubleshooting phase

[0316] Step 14:

[0317] If no interview is conducted, the server uses an emotion engine to analyze the emotional state behind the trouble.

[0318] Step 15:

[0319] The server then takes appropriate action to resolve the issue, such as assigning penalty points to the recruit or refunding reward points to the job seeker. If the user expresses anger or dissatisfaction, the server takes appropriate action, taking into consideration their emotional state.

[0320] This is the specific processing flow of the system. This flow not only enables efficient recruitment activities and solves the problems of small and medium-sized businesses and job seekers, but also realizes an approach that takes user feelings into full consideration.

[0321] Example 2

[0322] 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."

[0323] Currently, recruitment activities between small and medium-sized businesses and job seekers face several challenges, such as the time-consuming task of inputting information, inaccurate matching, difficulty in arranging interview schedules, and insufficient response to problems when interviews are not conducted.In addition, there is a lack of consideration for user feelings, so there is a need to improve satisfaction throughout the entire recruitment process.

[0324] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting information in the form of a question using a generative AI model, a means for analyzing the user's emotional state using an emotion analysis engine and saving the result together with the information, a means for matching job seekers with employers based on the collected information, a means for sending notifications to the job seeker and employer based on the matching results, a means for arranging interview schedules between the job seeker and employer, a means for awarding reward points to the job seeker when the first interview is completed, and a means for handling problems when the interview does not take place. This makes the entire hiring process more efficient and enables a personalized approach that takes user emotions into consideration.

[0325] A "generative AI model" is an artificial intelligence model that generates questions based on input from users and collects information.

[0326] An "emotion analysis engine" is an engine that analyzes the user's emotional state and optimizes the system's processing and response based on that information.

[0327] A "means for inputting information in the form of a question" is an interface or process for presenting a question to a user and collecting answers.

[0328] The "means for analyzing the user's emotional state and storing it together with the information" is the process of using an emotion analysis engine to collect the user's emotional data and storing it in a database together with the answers to the questions.

[0329] "Means of matching job seekers and employers based on collected information" refers to the process of analyzing collected data and comparing the conditions of job seekers and employers to make the best match.

[0330] The "means for sending notifications to job seekers and employers based on the matching results" refers to a communication process for notifying users of the matching results.

[0331] "Method of coordinating interview schedules between job seekers and employers" is the process for coordinating the date, time, and location of an interview.

[0332] "Means for awarding reward points to job seekers upon completion of the first interview" refers to the process of confirming the completion of the interview and awarding points to job seekers as an incentive.

[0333] "Measures for implementing troubleshooting measures when an interview is not conducted" refers to the process for analyzing the cause and taking appropriate measures when a scheduled interview is not conducted.

[0334] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it simplifies information input using a generative AI model and a sentiment analysis engine, and matches job seekers with employers, arranges interview schedules, awards reward points, and handles problems. This system consists of a server, terminals, and users (employers and job seekers).

[0335] First, the user logs in to the system via a terminal. The login information is authenticated on the server side, and the user begins using the system. The server then activates a generative AI model to present a question to the user. This prompt might include, for example, "What kind of job do you want?" The server also activates an emotion analysis engine to check the user's emotional state.

[0336] When a user answers a question from the server using a terminal, for example by entering "I'm an engineer," the emotion analysis engine detects the user's stress level and simultaneously collects that data. The server stores these responses and emotion data in a database, and then aggregates the information needed for the next processing step.

[0337] The server then analyzes the information stored in the database and uses a generative AI model to appropriately evaluate the job seeker's skill set, work experience, preferred location, etc. The sentiment analysis engine then takes into account the emotional data analyzed and adjusts the scoring to ensure optimal matching.

[0338] The server generates a compatibility score based on the data of job seekers and employers, and creates a list of job seekers with high scores. This list is notified to employers, and at the same time, job information that matches the job seeker's criteria is also notified to the job seeker. For example, if the job seeker is nervous, a message to calm them down is also sent.

[0339] Upon receiving the notification, the user clicks the "Consult" button on their device to notify the server of their request for a consultation. At this time, the emotion analysis engine analyzes the user's emotional state and sends this information to the server as a suggestion for the optimal consultation time. The server then takes the user's emotional state into consideration and suggests an appropriate time and place. For example, if the user is tired, it will suggest a time when they would be able to relax.

[0340] When the job seeker and employer conduct the interview at the agreed time, the server uses a sentiment analysis engine to record the job seeker's emotional state before and after the interview. After the interview is over, the server confirms the completion of the interview and awards reward points to the job seeker. These points are recorded in a database and can be used at a later date. Feedback is also provided based on the sentiment analysis engine. For example, if the job seeker is highly satisfied with the interview, this information is displayed as feedback.

[0341] If a scheduled interview does not take place, the server will detect this. The emotion analysis engine will analyze the user's emotional state and infer the cause of the problem. Appropriate measures will be taken to resolve the issue, such as assigning penalty points to the hired candidate and refunding reward points to the job seeker. For example, if the user is feeling dissatisfied or angry, the system will take their emotional state into consideration.

[0342] In this way, the system of the present invention uses a generative AI model and a sentiment analysis engine to streamline the entire recruitment process and provide a personalized approach that takes user emotions into consideration. For example, when a recruiter inputs information, the prompt "Tell us about the position you are hiring for" is presented, and the recruit replies "Sales Manager," and emotional data is also collected.

[0343] Furthermore, when a job seeker receives a matching notification, they will be notified that "We have found a job posting that matches your criteria," and if they are feeling nervous, they will also be sent a relaxing message. When a job seeker indicates their intention by pressing the "Interview" button, the sentiment analysis engine analyzes their desired time slot and sends the result to the server, which then suggests the optimal time for the interview.

[0344] The above functions will make recruitment activities more efficient and enable an approach that takes users' emotions into consideration.

[0345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0346] Step 1: User logs into the system

[0347] Input: The user enters login information (username and password) into the terminal.

[0348] How it works: The device sends login information to the server, which authenticates it and retrieves the user's profile information from a database.

[0349] Output: The server verifies the user's login and redirects them to a screen to enter their information.

[0350] Step 2: Server generates a question

[0351] Input: User is logged in.

[0352] How it works: The server launches the generative AI model to generate a question prompt to be displayed to the user. For example, it creates a prompt sentence such as, "What kind of job do you want?". It also launches an emotion analysis engine to analyze the user's initial emotional state.

[0353] Output: The generated question is displayed on the terminal, and the emotion data is kept as the initial state.

[0354] Step 3: User Enters Information

[0355] Input: The user answers the server's questions through the terminal. For example, the user enters "I'm an engineer."

[0356] Operation: The device sends user input data to the server, which uses an emotion analysis engine to analyze the user's emotional state (e.g., stress level) during the response.

[0357] Output: The server stores the user's response data and emotion data in a database.

[0358] Step 4: The server parses the information

[0359] Input: User response data and emotion data stored in a database.

[0360] How it works: The server uses the generated AI model to analyze skillsets, work experience, preferred work location, etc. At the same time, the sentiment analysis engine generates a sentiment score from the user's emotional data.

[0361] Output: The analysis results and sentiment scores are stored in a database, which is used for the subsequent matching process.

[0362] Step 5: Server generates compatibility score

[0363] Input: Parsed job candidate data and employer requirements data.

[0364] How it works: The server uses the generative AI model to generate a compatibility score based on the job seeker and employer criteria, and also takes into account the sentiment score from the sentiment analysis engine to calculate an overall compatibility score.

[0365] Output: The compatibility scores between job seekers and employers are stored in a database.

[0366] Step 6: The server sends a notification

[0367] Input: Generated compatibility scores and matching results.

[0368] How it works: The server creates a list of high-scoring job seekers and sends a notification to the employer. At the same time, job seekers are also notified of job postings that match their criteria. For example, a message may be sent to job seekers saying, "We've found a job posting that matches your criteria."

[0369] Output: A notification will be displayed on the employer and job seeker's devices.

[0370] Step 7: User confirms notification

[0371] Input: The user who received the notification (job seeker or employer).

[0372] How it works: The user checks the notification via their device. If the job seeker is nervous, the system also displays a message encouraging them to relax.

[0373] Output: The user confirms the notification and is ready to proceed to the next step.

[0374] Step 8: User selects appointment preference

[0375] Input: The user (job seeker or employer) who confirmed the notification.

[0376] How it works: The job seeker clicks the "Schedule an Interview" button to indicate their intention. The emotion analysis engine analyzes the user's emotional state and determines the desired interview time slot.

[0377] Output: The user's interview preference data and emotion data are sent to the server.

[0378] Step 9: Server suggests a meeting time

[0379] Input: User's interview preference data and emotion data.

[0380] How it works: The server uses an emotion analysis engine to suggest a time for a meeting that matches the user's emotional state. For example, if the user is tired, it will suggest a time when they are likely to relax.

[0381] Output: The server informs the user of the best time and place for the meeting.

[0382] Step 10: User conducts interview

[0383] Input: The interview time and location have been determined.

[0384] How it works: Job seekers and employers conduct interviews at designated times and locations. The server monitors the progress of the interviews in real time.

[0385] Output: The information about the completed interview is recorded on the server.

[0386] Step 11: Server confirms interview completion

[0387] Input: Interview completion information.

[0388] How it works: The server uses an emotion analysis engine to record the emotional state before and after the interview and to confirm the completion of the interview.

[0389] Output: Interview completion information and emotion data are saved in the database.

[0390] Step 12: Server awards reward points

[0391] Input: Interview completion information.

[0392] Operation: The server awards reward points to job seekers and records the points in a database.

[0393] Output: Reward points are reflected in the job seeker's account.

[0394] Step 13: The server detects that the interview has not been conducted.

[0395] Input: Information on interviews that have not been conducted after the scheduled interview time has passed.

[0396] How it works: The server detects that the interview was not conducted. The emotion analysis engine analyzes the user's emotional state and infers the cause of the problem.

[0397] Output: Uninterviewed information and emotional data are recorded in a database.

[0398] Step 14: Server Troubleshooting

[0399] Input: Uninterviewed information and emotional data.

[0400] Operation: The server takes appropriate action depending on the cause of the problem. For example, it assigns penalty points to the employer and refunds reward points to the job seeker.

[0401] Output: Changes in penalty points and reward points are reflected in the database.

[0402] Through these processing steps, the system can streamline the entire recruitment process and provide a personalized approach that takes into account the user's emotions.

[0403] (Application example 2)

[0404] 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."

[0405] Current recruitment processes and customer support systems lack efficiency in information entry, matching, scheduling, and troubleshooting. This often leaves small and medium-sized businesses, job seekers, and online shopping site customers feeling stressed and frustrated. Furthermore, the lack of a system that analyzes and responds to emotional states makes it difficult to provide personalized support. There is an urgent need to resolve these issues and provide efficient, emotionally sensitive support.

[0406] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0407] In this invention, the server includes means for using a generative model in which information is input in the form of questions, means for matching job seekers with employers based on the collected information, means for arranging interview schedules between job seekers and employers, means for awarding reward points to job seekers when the first interview is completed, means for handling problems when the interview does not take place, means for analyzing the emotional state of a user using emotion analysis means and taking appropriate action based on the data, means for analyzing customer inquiries in customer support for an online shopping site and proposing appropriate solutions, and means for providing reward points according to customer satisfaction based on the emotion analysis means. This enables more efficient recruitment activities and customer support, and personalized responses that take emotions into consideration.

[0408] The "information input" means the process by which a user provides information to the system in the form of a question.

[0409] A "generative model" refers to a system that uses AI technology to automatically generate questions and answers.

[0410] "Collected Information" refers to data entered by users or data automatically obtained by the system.

[0411] "Matching means" refers to the function of analyzing the conditions of job seekers and employers based on collected information and finding the optimal combination.

[0412] "Schedule adjustment means" refers to a function that automatically suggests and sets interview dates and times between job seekers and employers.

[0413] "Reward points" refer to points given to users as an incentive.

[0414] "Troubleshooting measures" refers to the function of taking measures when an interview is not conducted or other problems arise.

[0415] "Sentiment analysis means" refers to the function of analyzing emotions from a user's text or voice and adjusting the response based on the results.

[0416] "Customer inquiry" refers to the act of users of an online shopping site entering problems or questions they have into the system.

[0417] "Solution proposal means" refers to a function that automatically generates an appropriate solution based on the customer's inquiry.

[0418] "Customer satisfaction" refers to an indicator that measures the degree to which customers are satisfied with the services and solutions provided.

[0419] The embodiment of this invention is a system for solving recruitment issues faced by small and medium-sized businesses and job seekers. This system uses a generative AI model and sentiment analysis means to simplify information input, match job seekers with potential employers, smoothly schedule interviews, award reward points, and handle problems. Furthermore, the system can also be applied to customer support for online shopping sites, proposing appropriate solutions to customer inquiries and awarding reward points.

[0420] 1. Basic configuration

[0421] This system consists of a server, a terminal, and a user. The server runs a generative AI model and analyzes the user's emotional state using a sentiment analysis engine. Terminals can include smartphones, tablets, and PCs.

[0422] 2. Enter information

[0423] When a user logs in using a device, the server activates the generative AI model and collects information in the form of questions. For example, a question such as "What kind of job do you want?" is displayed, and as the user answers, the emotion engine analyzes the user's emotional state. As a result, if the user is nervous, for example, that information is stored in the database.

[0424] Specific examples

[0425] Example prompt: "Tell me more about your problem."

[0426] 3. Matching and Analysis

[0427] Based on the collected information, the server uses a generative AI model to analyze the requirements of job seekers and employers and generate scores. At the same time, an emotion engine evaluates the user's emotional state and adjusts the scoring, enabling more appropriate matching.

[0428] Specific examples

[0429] Example prompt: "We found a job posting that matches your criteria."

[0430] 4. Notice and Confirmation

[0431] Once a match is found, the server sends a notification and the user clicks the "Appoint" button to schedule the interview. The system uses an emotion engine to suggest a time and location that takes into account the user's emotional state.

[0432] Specific examples

[0433] Example prompt: "Please suggest a suitable time for the interview."

[0434] 5. Follow-up and rewards

[0435] When a user completes an interview or problem-solving follow-up, the server uses an emotion engine to record their emotional state and awards reward points. Depending on the user's satisfaction, further personalized messages are sent.

[0436] Specific examples

[0437] Example prompt: "Were you satisfied with our service?"

[0438] Hardware and Software Used

[0439] Hardware: Servers, smartphones, tablets, PCs

[0440] Software: Generative AI models, sentiment analysis engines, database management systems

[0441] Using these building blocks and prompts will enable efficient, personalized responses, improving the quality of your recruiting and customer support.

[0442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0443] Step 1:

[0444] The user logs in to the device and begins entering information. The device inputs and displays a prompt. At this point, the user's input (e.g., an answer to the question, "What kind of job do you want?") is sent to the generative AI model.

[0445] Step 2:

[0446] The server launches the generative AI model and receives the user's answer. The generative AI model analyzes the user's answer and dynamically generates the next required question. The input is the user's answer, and the output is the next question.

[0447] Step 3:

[0448] The server uses a sentiment analysis engine to analyze the emotional state of the user from the answers entered by the user, where the input is the user's answer and the output is emotional data, which is stored in a database.

[0449] Step 4:

[0450] The server matches job seekers with potential employers based on the information and emotional data collected. A generative AI model analyzes the information and scores the match that best meets the criteria. The input is user information and emotional data, and the output is a score for the matching result.

[0451] Step 5:

[0452] The server notifies the job seeker and employer of the matching results. The notification includes a prompt (e.g., "We have found a job posting that matches your criteria"), and when the user presses the "Interview" button, the next step is taken. The input at this time is the matching result, and the output is the notification message.

[0453] Step 6:

[0454] When a user clicks the "Interview" button on the device, the server proposes an appropriate interview time and location based on the user's emotional state. The input is the user's emotional data and schedule information, and the output is an interview proposal.

[0455] Step 7:

[0456] Users (job seekers and employers) conduct interviews and report the results to the server. The server uses an emotion engine to record the emotional state before and after the interview and awards reward points. The inputs are the interview results and emotional data, and the output is reward points.

[0457] Step 8:

[0458] If the interview is not conducted, the server will handle the problem based on the emotion analysis data. Specifically, it will propose appropriate countermeasures, such as imposing a penalty on the hired candidate or refunding reward points to the job seeker. The inputs are the emotion data and the interview results, and the output is the countermeasures.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] [Second embodiment]

[0463] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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).

[0469] 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. 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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.

[0474] 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."

[0475] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it uses generative AI to simplify information input, matches job seekers with employers, smoothly arranges interview schedules, awards reward points, and handles problems. This system consists of a server, terminals, and users (employers and job seekers).

[0476] Program processing overview

[0477] Enter information

[0478] The server launches the generative model and obtains the necessary information from the user in the form of a question. For example, the server might ask, "What position are you hiring for?" and the user (employer) might respond, "Sales manager." Or, the server might ask, "Tell me about your past work history," and the user (job seeker) might respond, "I have two years of sales experience." The information collected in this way is stored in a database by the server.

[0479] matching

[0480] The server analyzes the collected information and scores compatibility between job seekers and employers based on their criteria. For example, a generative model performs optimal matching based on information such as the job seeker's skill set, work experience, and preferred work location. A list of highly-scoring job seekers is generated and notified to the employer. Similarly, job openings that match the criteria are notified to the job seeker.

[0481] Notification and confirmation

[0482] When the user receives the notification, they click the "Ask for a meeting" button to indicate their intention to meet. The server confirms this intention and starts the process to coordinate the schedule for both parties.

[0483] First interview and reward

[0484] After the job seeker and employer conduct the first interview, the server confirms the completion of the interview and awards reward points to the job seeker, which can increase the job seeker's motivation.

[0485] Troubleshooting

[0486] If the server does not conduct an interview after a successful match, it will take appropriate action to resolve the issue, such as adding penalty points to the employer's account or providing a refund to the job seeker.

[0487] Specific examples

[0488] Example 1: When the recruiter inputs information

[0489] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[0490] 2. The server generates a question: The server asks a question through the generative model: "Tell me about the position you're hiring."

[0491] 3. The employer responds: "I'm the sales manager," the employer responds.

[0492] 4. Server saves the data: The server saves the answers in a database.

[0493] Example 2: Job seeker receives a match notification

[0494] 1. The server analyzes the conditions: The server analyzes the job seeker's conditions (skill set, location, experience, etc.) and scores them using a generative model.

[0495] 2. The server sends a notification: Based on the list of high-scoring employers, the server notifies the job seeker that "job information matching your criteria has been found."

[0496] 3. The job seeker requests an interview: The job seeker indicates their intention by pressing the "Interview" button.

[0497] As described above, this invention efficiently solves the problems of employers and job seekers through a system that includes a series of processes, such as inputting information in the form of questions using generative AI, matching through condition analysis and scoring, and providing rewards and troubleshooting. This system makes recruitment activities more efficient and reduces costs.

[0498] The processing flow will be explained below.

[0499] Program processing flow

[0500] Information input phase

[0501] Step 1:

[0502] The user logs into the application using a terminal. The server authenticates the account information and displays the main screen if the login is successful.

[0503] Step 2:

[0504] The server invokes the generative model to generate questions for the user (employer or job seeker), such as "What kind of job do you want?"

[0505] Step 3:

[0506] The user enters an answer to the question. If they are an employer, they might answer "sales manager," and if they are a job seeker, they might answer "sales position."

[0507] Step 4:

[0508] The server stores the user's answers in a database, which is used for subsequent analysis and matching.

[0509] Matching Process

[0510] Step 5:

[0511] The server analyzes all the information on job seekers and employers stored in the database. The generative model scores them based on the criteria and finds the optimal combination.

[0512] Step 6:

[0513] The server generates a list of high-scoring job seekers and sends notifications to employers.

[0514] Step 7:

[0515] The server also notifies the job seeker of a list of employers that match their criteria, with a message such as "We've found jobs that match your criteria."

[0516] Notification and confirmation phase

[0517] Step 8:

[0518] The user checks the notification and clicks the "Interview" button. If both the job seeker and the employer click the button, the process proceeds to the next step.

[0519] Step 9:

[0520] The server displays a screen for arranging the interview schedule between the two parties. The user enters the desired date and time.

[0521] Step 10:

[0522] The server will finalize the schedule and notify both parties of the interview details.

[0523] Initial Interview and Reward Phase

[0524] Step 11:

[0525] Users (job seekers and employers) conduct interviews at the specified date and time.

[0526] Step 12:

[0527] After the interview is completed, the server confirms the completion of the interview and gives reward points to the job seeker.

[0528] Troubleshooting phase

[0529] Step 13:

[0530] If an interview is not conducted, the server will recognize it as a problem and take appropriate action, such as giving penalty points to the recruit or refunding reward points to the job seeker.

[0531] The above is the specific processing flow of the system. This flow will enable efficient recruitment activities and solve the problems of small and medium-sized businesses and job seekers.

[0532] Example 1

[0533] 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."

[0534] There is a need for efficient methods to resolve the recruitment issues faced by small and medium-sized businesses and job seekers. Specifically, it is necessary to simplify the information entry process, ensure appropriate matching, smoothly arrange interview schedules, award reward points to motivate job seekers, and deal with problems when interviews are not conducted.

[0535] 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.

[0536] In this invention, the server includes a means for inputting information in the form of questions using a generative AI model, a means for matching job seekers with employers based on collected data, a means for sending a notification to the user and arranging an interview schedule between the job seeker and employer, a means for awarding reward points to the job seeker when the first interview is completed, and a means for dealing with problems when an interview does not take place. This makes recruitment activities more efficient and reduces costs, while also making it possible to improve job seeker motivation and quickly deal with problems when they occur.

[0537] A "generative AI model" is a model that uses artificial intelligence to automatically generate text and data.

[0538] "Information input" is the process by which the system obtains the necessary information from the user.

[0539] A "question format" is a method of gathering information by asking a user a series of questions.

[0540] "Data" means the collection of information provided by the user that the system uses for analysis and matching.

[0541] "Matching" is the process of finding the best match based on the requirements of the job seeker and the employer.

[0542] "User" refers to the employers and job seekers who use the system.

[0543] "Notification" is the act of the system sending information or messages to the user.

[0544] "Scheduling" is the process of setting up an interview date and time between a job seeker and an employer.

[0545] A "first interview" refers to the first meeting between a job seeker and an employer.

[0546] "Reward points" are points that the system awards to job seekers as motivation and reward.

[0547] "Troubleshooting" is the process for resolving problems that arise after a match is made.

[0548] The present invention is a system that uses a generative AI model to solve recruitment issues faced by small and medium-sized businesses and job seekers. Specifically, the system simplifies information input, matches job seekers with potential employers, arranges interview schedules, awards reward points, and handles problems. Detailed embodiments of the present invention are described below.

[0549] System Configuration

[0550] Hardware and Software Configuration

[0551] This system mainly consists of a server, terminals, and users (employers and job seekers).

[0552] Server: Responsible for the primary data processing and execution of generative AI models. For example, the server uses generative AI models such as OpenAI's GPT-3.

[0553] Terminal: A device where a user enters information and checks results. This includes computers, smartphones, tablets, etc.

[0554] Users: Employers and job seekers who use the system.

[0555] Specific examples of hardware use

[0556] The server uses a cloud server equipped with a high-performance processor and large memory capacity.

[0557] The terminal can be any device with a standard internet connection.

[0558] Specific examples of software use

[0559] Generative AI models: Use natural language generation models such as OpenAI's GPT-3.

[0560] Database Management Systems: RDBMS such as MySQL or PostgreSQL are used to store data.

[0561] Front-end: Building the user interface using JavaScript frameworks such as React or Vue.js.

[0562] Process Overview

[0563] The server launches the generative AI model and asks the user questions to obtain the necessary information. The collected information is stored in a database, and the server matches job seekers with employers based on that information. The matching results are sent to the user as a notification, and if the user indicates a desire for an interview, the server arranges the interview schedule. When the interview is completed, the server awards reward points to the job seeker, and if the interview does not take place, it handles any issues.

[0564] Example

[0565] Example 1: When the recruiter inputs information

[0566] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[0567] 2. The server generates a question: Using a generative AI model, the server generates a question such as, "Tell me about the position you're hiring."

[0568] 3. The recruiter answers: "I'm a sales manager."

[0569] 4. Server saves the data: The answers are saved in a database.

[0570] Example 2: When a job seeker receives a match notification

[0571] 1. The server analyzes the conditions: The job seeker's conditions (skill set, work location, experience, etc.) are analyzed using a generative AI model and a score is generated.

[0572] 2. The server sends a notification: "We've found a job that matches your criteria."

[0573] 3. The job seeker requests an interview: The job seeker indicates their intention by pressing the "Interview" button.

[0574] Prompt Sentence Examples

[0575] Here are some example prompts that the generative AI model might use:

[0576] 1. For employers: "Tell me about the position you're hiring."

[0577] 2. For job seekers: "Tell me about your past work experience."

[0578] In this way, the present invention is a system that uses a generative AI model to input information in the form of questions, and then comprehensively performs matching, notification, interview schedule adjustment, reward point allocation, and trouble shooting, thereby streamlining recruitment activities and reducing costs.

[0579] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0580] Program processing flow

[0581] Step 1: Start entering information

[0582] The server launches the generative AI model and obtains the necessary information from the user in the form of questions.

[0583] Specific behavior:

[0584] 1. The server launches a generative AI model: Launch a generative AI model (e.g., OpenAI GPT-3).

[0585] 2. Server generates questions: A generative AI model is used to generate questions, such as "What position are you hiring?"

[0586] 3. User enters information: Employers and job seekers answer questions and enter information.

[0587] 4. Input: Information entered by the user (e.g., position name, work history).

[0588] 5. Output: The information obtained by the server is stored in the server's database.

[0589] Step 2: Analyzing and matching information

[0590] The server analyzes the collected information and uses a generative AI model to score compatibility between job seekers and employers based on their criteria.

[0591] Specific behavior:

[0592] 1. The server collects data: The latest collected information is retrieved from the database.

[0593] 2. The server analyzes using the generative AI model: It runs the analysis algorithm and analyzes the collected information.

[0594] 3. The server performs scoring: A generative AI model is used to score the compatibility between job seekers and employers.

[0595] 4. Input: Job seeker and employer information stored on the server.

[0596] 5. Output: Calculate compatibility scores and generate a list of job seekers with high scores.

[0597] Step 3: Notification of match results

[0598] The server sends a notification to the user based on the matching results.

[0599] Specific behavior:

[0600] 1. Server generates notification content: A generative AI model is used to generate notification content, e.g., "We've found a job posting that matches your criteria."

[0601] 2. The server sends a notification: A notification is sent to the device.

[0602] 3. Users receive notifications: Job seekers and employers receive notifications.

[0603] 4. Input: Generated compatibility scores and a list of high-scoring job seekers.

[0604] 5. Output: Notification message sent to the user.

[0605] Step 4: Schedule an interview

[0606] When the user indicates a desire for an interview, the server arranges the interview schedule.

[0607] Specific behavior:

[0608] 1. User indicates desire for interview: The job seeker presses the "Interview" button.

[0609] 2. The server adjusts the schedules: The schedules of both parties are automatically adjusted and the date and time of the meeting is decided.

[0610] 3. Server sends notification again: Notifies the user of the adjusted schedule.

[0611] 4. Input: Job seeker and hire schedule information.

[0612] 5. Output: Confirmed interview date and time and notification message.

[0613] Step 5: First interview and reward points awarded

[0614] When the first interview is completed, the server awards reward points to the job seeker.

[0615] Specific behavior:

[0616] 1. Confirmation of interview completion: The recruiter presses the "Interview Completed" button.

[0617] 2. The server awards reward points: The server awards reward points to the job seeker and reflects them in the account.

[0618] 3. The server saves the data: The awarded reward points are saved in the database.

[0619] 4. Enter: Confirmation of interview completion.

[0620] 5. Output: Reward points are awarded and stored in the database.

[0621] Step 6: Perform troubleshooting

[0622] If the interview does not take place, the server will take action to troubleshoot.

[0623] Specific behavior:

[0624] 1. The server checks that the interview has not been conducted: It detects that the interview has not been conducted.

[0625] 2. Server assigns penalty: assigns penalty points to the adopter.

[0626] 3. The server processes the refund: The server processes the refund for the job seeker.

[0627] 4. Enter: Confirmation information for unsuccessful interviews.

[0628] 5. Output: Notification of penalty points being awarded and refund completion.

[0629] (Application example 1)

[0630] 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."

[0631] A major challenge for logistics centers is efficiently securing a large workforce. However, many small and medium-sized businesses lack the resources and technology to quickly and efficiently find job seekers, schedule interviews, and ultimately secure labor. This makes the recruitment process cumbersome and time-consuming, making it difficult to find suitable candidates. Scheduling interviews and dealing with issues when interviews are not conducted are also challenges.

[0632] 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.

[0633] In this invention, the server includes means for using a generative model in which information is input in the form of questions, means for matching job seekers with employers based on the collected information, means for arranging interview schedules between job seekers and employers, means for awarding reward points to job seekers when the first interview is completed, means for dealing with problems when the interview does not take place, means for automatically arranging schedules between job seekers and employers using an external service, and means for electronically confirming the completion of interviews. This enables the logistics center to quickly and efficiently secure labor.

[0634] "Means of using a generative model that inputs information in the form of a question" refers to a means of obtaining the necessary information from the user in the form of a question and securing that information using a generative AI model.

[0635] "Means of matching job seekers and employers based on collected information" refers to a means of analyzing collected information on job seekers and employers and appropriately connecting the two based on mutual conditions.

[0636] The "means for coordinating interview schedules between job seekers and employers" is a means for automatically setting the optimal interview date and time, taking into consideration the schedules of both the employer and the job seeker.

[0637] "Means for granting reward points to a job seeker upon completion of the first interview" refers to a means for granting reward points to a job seeker as an incentive after confirming that the first interview has ended.

[0638] "Measures to deal with problems when an interview is not conducted" refers to measures to provide appropriate compensation or penalties to users when an interview is canceled or not conducted.

[0639] "Means for automatically coordinating the schedules of job seekers and employers using external services" refers to means for automatically coordinating the schedules of job seekers and employers using external calendar and schedule management services.

[0640] "Means for confirming completion of interview by electronic means" refers to a means for reliably confirming that the interview has been completed using electronic means, such as scanning a QR code.

[0641] The system embodying this invention is designed to solve the problems of job recruitment efficiency and interviews that employers and job seekers face. This system is composed of a server, terminals, and users.

[0642] Server Roles

[0643] Hardware and software used

[0644] The server uses the following hardware and software:

[0645] Server-side hardware: AWS EC2

[0646] Database: DynamoDB

[0647] Generative AI model: OpenAI GPT-3

[0648] Backend: Node.js, Express

[0649] Communication method: REST API

[0650] Enter information

[0651] The server uses a generative AI model to prompt the user for information in the form of a question, such as "What position are you hiring for?", to which the candidate responds "Sales Manager." This information is stored in DynamoDB via a REST API.

[0652] matching

[0653] Based on the collected information, the generative AI model analyzes and scores the requirements of job seekers and employers. The scoring system makes an appropriate match, and the employer is notified of a list of job seekers with high scores.

[0654] Schedule adjustment

[0655] When a job seeker notifies the company that they wish to interview, the system automatically coordinates the schedules of both parties using the Google Calendar API, efficiently managing the schedules of both the job seeker and the employer through an external service.

[0656] Reward points awarded

[0657] Once the first interview is completed, the job seeker will scan the QR code to confirm the completion of the interview, after which reward points will be automatically awarded to the job seeker.

[0658] Troubleshooting

[0659] If an interview is not conducted, the server will provide appropriate compensation or penalties, such as adding penalty points to the employer's account or providing a refund to the job seeker.

[0660] Device Role

[0661] Hardware and software used

[0662] The terminal uses the following hardware and software:

[0663] Frontend: React Native (smartphone app)

[0664] Enter information

[0665] Users (employers, job seekers) use their devices to answer questions posed by the generative AI model, and this information is sent to the server in real time and stored in DynamoDB.

[0666] Check the schedule

[0667] When the request button is pressed, the appointment is automatically scheduled on the device, and the schedule is synchronized between the device and the server using the Google Calendar API.

[0668] User Roles

[0669] Information input and response

[0670] The user inputs information through a device, answers questions posed by the generative AI model, and performs other operations such as pressing a button to indicate a desire for an interview.

[0671] Conducting interviews

[0672] Once the interview is complete, job seekers confirm completion by scanning a QR code, which automatically awards reward points.

[0673] Specific examples

[0674] Example prompts to be input to the generative AI model:

[0675] (When the recruit logs in)

[0676] "Please tell me about the positions available at the logistics center."

[0677] User Answer: "Warehouse worker"

[0678] "What skills are required for the position?"

[0679] User Answer: "Forklift driving qualification"

[0680] (When job seeker logs in)

[0681] "Tell me about your past work history."

[0682] User Answer: "I have 3 years of warehouse experience."

[0683] "Please tell us where you would like to work."

[0684] User Answer: "Tokyo"

[0685] In this way, a single process is carried out, from inputting information to matching, arranging interview schedules, awarding reward points, and troubleshooting, enabling logistics centers to quickly and efficiently secure labor.

[0686] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0687] Step 1:

[0688] The server launches the generative AI model and generates questions for information input. The questions are sent to the device, and the user (employer or job seeker) enters the answers. The input includes information such as the position being filled and past work history. The server uses the generative AI model to create prompts to generate appropriate questions and presents them to the user. The user's answer data is sent from the device to the server and stored in DynamoDB.

[0689] Step 2:

[0690] The server executes a matching algorithm based on the information collected. First, the server retrieves the job seeker and employer information collected from DynamoDB. Then, it uses a generative AI model to analyze and score the conditions. The input for this step is the job seeker's skill set, work experience, preferred work location, etc., and the output is a compatibility score. A list of high-scoring job seekers is generated and notified to the employer's device.

[0691] Step 3:

[0692] The user (job seeker) receives the notification and presses the "Interview" button. This action registers the interview request. The server retrieves the schedules of the job seeker and employer using the Google Calendar API and automatically adjusts the schedules. The input for this step is the available time of the job seeker and employer, and the output is the adjusted interview date and time. The adjustment result is notified to the terminal.

[0693] Step 4:

[0694] A user (job seeker) attends an interview on the interview date. After completing the interview, the job seeker scans the QR code to report the completion of the interview. The device sends the scanned data to the server, which then confirms the completion of the interview. The input of this step is the scanned data of the QR code, and the output is confirmation of the completion of the interview. After confirmation, reward points are automatically awarded to the job seeker.

[0695] Step 5:

[0696] If the interview is not conducted, the server will automatically execute a troubleshooting process. First, it checks the actions of both parties at the scheduled interview date and time, and if the interview is not conducted, it starts the troubleshooting process. The input of this step is the log of the not conducted interview, and the output is the feedback of compensation or penalty. For example, penalty points are added to the employer's account and a refund is given to the job seeker.

[0697] 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.

[0698] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it uses generative AI to simplify information input, match job seekers with employers, smoothly arrange interview schedules, award reward points, and handle problems. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it is possible to provide more personalized responses. This system consists of a server, terminals, and users (employers and job seekers).

[0699] Program processing overview

[0700] Enter information

[0701] The server launches the generative model and obtains the necessary information from the user in the form of a question. For example, it displays a question such as, "What kind of job do you want?" As the user answers, the server simultaneously uses an emotion engine to analyze the user's emotions and stores this information in a database. For example, if the user is feeling stressed, that information is also recorded.

[0702] matching

[0703] The server analyzes the collected information and scores the compatibility between the job seeker and employer based on their criteria. A generative model evaluates the job seeker's skill set, work experience, preferred work location, etc., and an emotion engine adjusts the score based on the user's emotional state. A list of high-scoring job seekers is generated and notified to the employer. Similarly, job openings that match the criteria are notified to the job seeker. For example, if the job seeker is nervous, a message to ease their tension is sent.

[0704] Notification and confirmation

[0705] The user receives the notification and clicks the "Appoint" button. The server uses an emotion engine to analyze the user's emotional state and suggest an appropriate time and place. For example, if the user is tired, it suggests a time when they can relax.

[0706] First interview and reward

[0707] When users (job seekers and employers) conduct interviews, the server uses an emotion engine to record their emotional states before and after the interview. After the interview is over, the server confirms the completion of the interview and awards reward points to the job seeker. It also provides feedback based on the emotion engine. For example, if the job seeker is satisfied after the interview, this is displayed as feedback.

[0708] Troubleshooting

[0709] If the server does not conduct an interview after a successful match, it uses an emotion engine to analyze the emotional state behind the problem. It then takes appropriate action to resolve the issue, such as assigning penalty points to the hire or refunding reward points to the job seeker. For example, if the user expresses anger or dissatisfaction, the system takes that emotional state into consideration.

[0710] Specific examples

[0711] Example 1: When the recruiter inputs information

[0712] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[0713] 2. Server generates question: The server asks a question through the generative model, such as "Tell me about the position you're hiring for." At the same time, the emotion engine checks the emotional state of the recruit.

[0714] 3. Hire responds: "I'm a sales manager," the hire responds. The emotion engine records the hire's stress level.

[0715] 4. Server saves the data: The server saves the answers and emotion data in a database.

[0716] Example 2: Job seeker receives a match notification

[0717] 1. Server analyzes the job seeker's requirements (skill set, location, experience, etc.) and scores them using a generative model. At the same time, the emotion engine evaluates the job seeker's emotional state.

[0718] 2. Server sends notification: Based on the list of high-scoring employers, the server notifies the job seeker that "We have found a job posting that matches your criteria." If the job seeker is nervous, it also sends a relaxing message.

[0719] 3. The job seeker requests an interview: The job seeker clicks the "Interview" button to indicate their intention. The emotion engine analyzes the desired time slot and sends the results to the server.

[0720] As described above, this invention uses generative AI and an emotion engine to solve the problems of employers and job seekers in an efficient and personalized way through a system that includes a series of processes such as inputting information in the form of questions, matching through condition analysis and scoring, scheduling that takes emotions into account, and rewards and troubleshooting. This system makes recruitment activities more efficient and realizes an approach that takes users' emotions into consideration.

[0721] The processing flow will be explained below.

[0722] Program processing flow

[0723] Information input phase

[0724] Step 1:

[0725] The user logs into the application using a terminal. The server authenticates the user's account information and displays the main screen if the login is successful.

[0726] Step 2:

[0727] The server invokes the generative model to generate questions for the user (employer or job seeker), such as "What kind of job do you want?"

[0728] Step 3:

[0729] The user inputs answers to the questions. For example, an employer might answer "sales manager," and a job seeker might answer "sales position." At the same time, the server uses an emotion engine to analyze the user's emotional state and stores that information in the database.

[0730] Step 4:

[0731] The server stores the user's answers and emotion data in a database for the next step.

[0732] Matching Process

[0733] Step 5:

[0734] The server analyzes the information of all job seekers and employers stored in the database and uses a generative model to score them based on the conditions.

[0735] Step 6:

[0736] The emotion engine adjusts the score based on the user's emotional state, for example, appropriately adjusting the score of a job candidate who is stressed.

[0737] Step 7:

[0738] Based on the scoring results, a list of job seekers with high scores is generated, and the server notifies the employer of this list.

[0739] Step 8:

[0740] Similarly, the server notifies the job seeker of a list of employers that match the job search criteria, with the notification including the message "We have found jobs that match your criteria."

[0741] Notification and confirmation phase

[0742] Step 9:

[0743] The user checks the notification and clicks the "Ask for an interview" button in the notification. The server receives this decision and proceeds to the next step.

[0744] Step 10:

[0745] The server uses an emotion engine to analyze the user's emotional state and suggest the best time and place for the interview, for example, suggesting a relaxing time for a tired user.

[0746] Step 11:

[0747] Once the user reviews and agrees to the proposed schedule, the server notifies both parties of the interview details.

[0748] Initial Interview and Reward Phase

[0749] Step 12:

[0750] Users (job seekers and employers) conduct interviews at the specified date and time. The server uses an emotion engine to record the emotional state before and after the interview.

[0751] Step 13:

[0752] After the interview is completed, the server confirms the completion of the interview, awards reward points to the job seeker, and generates feedback based on the emotion engine to provide to the user.

[0753] Troubleshooting phase

[0754] Step 14:

[0755] If no interview is conducted, the server uses an emotion engine to analyze the emotional state behind the trouble.

[0756] Step 15:

[0757] The server then takes appropriate action to resolve the issue, such as assigning penalty points to the recruit or refunding reward points to the job seeker. If the user expresses anger or dissatisfaction, the server takes appropriate action, taking into consideration their emotional state.

[0758] This is the specific processing flow of the system. This flow not only enables efficient recruitment activities and solves the problems of small and medium-sized businesses and job seekers, but also realizes an approach that takes user feelings into full consideration.

[0759] Example 2

[0760] 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."

[0761] Currently, recruitment activities between small and medium-sized businesses and job seekers face several challenges, such as the time-consuming task of inputting information, inaccurate matching, difficulty in arranging interview schedules, and insufficient response to problems when interviews are not conducted.In addition, there is a lack of consideration for user feelings, so there is a need to improve satisfaction throughout the entire recruitment process.

[0762] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting information in the form of a question using a generative AI model, a means for analyzing the user's emotional state using an emotion analysis engine and saving the result together with the information, a means for matching job seekers with employers based on the collected information, a means for sending notifications to the job seeker and employer based on the matching results, a means for arranging interview schedules between the job seeker and employer, a means for awarding reward points to the job seeker when the first interview is completed, and a means for handling problems when the interview does not take place. This makes the entire hiring process more efficient and enables a personalized approach that takes user emotions into consideration.

[0763] A "generative AI model" is an artificial intelligence model that generates questions based on input from users and collects information.

[0764] An "emotion analysis engine" is an engine that analyzes the user's emotional state and optimizes the system's processing and response based on that information.

[0765] A "means for inputting information in the form of a question" is an interface or process for presenting a question to a user and collecting answers.

[0766] The "means for analyzing the user's emotional state and storing it together with the information" is the process of using an emotion analysis engine to collect the user's emotional data and storing it in a database together with the answers to the questions.

[0767] "Means of matching job seekers and employers based on collected information" refers to the process of analyzing collected data and comparing the conditions of job seekers and employers to make the best match.

[0768] The "means for sending notifications to job seekers and employers based on the matching results" refers to a communication process for notifying users of the matching results.

[0769] "Method of coordinating interview schedules between job seekers and employers" is the process for coordinating the date, time, and location of an interview.

[0770] "Means for awarding reward points to job seekers upon completion of the first interview" refers to the process of confirming the completion of the interview and awarding points to job seekers as an incentive.

[0771] "Measures for implementing troubleshooting measures when an interview is not conducted" refers to the process for analyzing the cause and taking appropriate measures when a scheduled interview is not conducted.

[0772] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it simplifies information input using a generative AI model and a sentiment analysis engine, and matches job seekers with employers, arranges interview schedules, awards reward points, and handles problems. This system consists of a server, terminals, and users (employers and job seekers).

[0773] First, the user logs in to the system via a terminal. The login information is authenticated on the server side, and the user begins using the system. The server then activates a generative AI model to present a question to the user. This prompt might include, for example, "What kind of job do you want?" The server also activates an emotion analysis engine to check the user's emotional state.

[0774] When a user answers a question from the server using a terminal, for example by entering "I'm an engineer," the emotion analysis engine detects the user's stress level and simultaneously collects that data. The server stores these responses and emotion data in a database, and then aggregates the information needed for the next processing step.

[0775] The server then analyzes the information stored in the database and uses a generative AI model to appropriately evaluate the job seeker's skill set, work experience, preferred location, etc. The sentiment analysis engine then takes into account the emotional data analyzed and adjusts the scoring to ensure optimal matching.

[0776] The server generates a compatibility score based on the data of job seekers and employers, and creates a list of job seekers with high scores. This list is notified to employers, and at the same time, job information that matches the job seeker's criteria is also notified to the job seeker. For example, if the job seeker is nervous, a message to calm them down is also sent.

[0777] Upon receiving the notification, the user clicks the "Consult" button on their device to notify the server of their request for a consultation. At this time, the emotion analysis engine analyzes the user's emotional state and sends this information to the server as a suggestion for the optimal consultation time. The server then takes the user's emotional state into consideration and suggests an appropriate time and place. For example, if the user is tired, it will suggest a time when they would be able to relax.

[0778] When the job seeker and employer conduct the interview at the agreed time, the server uses a sentiment analysis engine to record the job seeker's emotional state before and after the interview. After the interview is over, the server confirms the completion of the interview and awards reward points to the job seeker. These points are recorded in a database and can be used at a later date. Feedback is also provided based on the sentiment analysis engine. For example, if the job seeker is highly satisfied with the interview, this information is displayed as feedback.

[0779] If a scheduled interview does not take place, the server will detect this. The emotion analysis engine will analyze the user's emotional state and infer the cause of the problem. Appropriate measures will be taken to resolve the issue, such as assigning penalty points to the hired candidate and refunding reward points to the job seeker. For example, if the user is feeling dissatisfied or angry, the system will take their emotional state into consideration.

[0780] In this way, the system of the present invention uses a generative AI model and a sentiment analysis engine to streamline the entire recruitment process and provide a personalized approach that takes user emotions into consideration. For example, when a recruiter inputs information, the prompt "Tell us about the position you are hiring for" is presented, and the recruit replies "Sales Manager," and emotional data is also collected.

[0781] Furthermore, when a job seeker receives a matching notification, they will be notified that "We have found a job posting that matches your criteria," and if they are feeling nervous, they will also be sent a relaxing message. When a job seeker indicates their intention by pressing the "Interview" button, the sentiment analysis engine analyzes their desired time slot and sends the result to the server, which then suggests the optimal time for the interview.

[0782] The above functions will make recruitment activities more efficient and enable an approach that takes users' emotions into consideration.

[0783] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0784] Step 1: User logs into the system

[0785] Input: The user enters login information (username and password) into the terminal.

[0786] How it works: The device sends login information to the server, which authenticates it and retrieves the user's profile information from a database.

[0787] Output: The server verifies the user's login and redirects them to a screen to enter their information.

[0788] Step 2: Server generates a question

[0789] Input: User is logged in.

[0790] How it works: The server launches the generative AI model to generate a question prompt to be displayed to the user. For example, it creates a prompt sentence such as, "What kind of job do you want?". It also launches an emotion analysis engine to analyze the user's initial emotional state.

[0791] Output: The generated question is displayed on the terminal, and the emotion data is kept as the initial state.

[0792] Step 3: User Enters Information

[0793] Input: The user answers the server's questions through the terminal. For example, the user enters "I'm an engineer."

[0794] Operation: The device sends user input data to the server, which uses an emotion analysis engine to analyze the user's emotional state (e.g., stress level) during the response.

[0795] Output: The server stores the user's response data and emotion data in a database.

[0796] Step 4: The server parses the information

[0797] Input: User response data and emotion data stored in a database.

[0798] How it works: The server uses the generated AI model to analyze skillsets, work experience, preferred work location, etc. At the same time, the sentiment analysis engine generates a sentiment score from the user's emotional data.

[0799] Output: The analysis results and sentiment scores are stored in a database, which is used for the subsequent matching process.

[0800] Step 5: Server generates compatibility score

[0801] Input: Parsed job candidate data and employer requirements data.

[0802] How it works: The server uses the generative AI model to generate a compatibility score based on the job seeker and employer criteria, and also takes into account the sentiment score from the sentiment analysis engine to calculate an overall compatibility score.

[0803] Output: The compatibility scores between job seekers and employers are stored in a database.

[0804] Step 6: The server sends a notification

[0805] Input: Generated compatibility scores and matching results.

[0806] How it works: The server creates a list of high-scoring job seekers and sends a notification to the employer. At the same time, job seekers are also notified of job postings that match their criteria. For example, a message may be sent to job seekers saying, "We've found a job posting that matches your criteria."

[0807] Output: A notification will be displayed on the employer and job seeker's devices.

[0808] Step 7: User confirms notification

[0809] Input: The user who received the notification (job seeker or employer).

[0810] How it works: The user checks the notification via their device. If the job seeker is nervous, the system also displays a message encouraging them to relax.

[0811] Output: The user confirms the notification and is ready to proceed to the next step.

[0812] Step 8: User selects appointment preference

[0813] Input: The user (job seeker or employer) who confirmed the notification.

[0814] How it works: The job seeker clicks the "Schedule an Interview" button to indicate their intention. The emotion analysis engine analyzes the user's emotional state and determines the desired interview time slot.

[0815] Output: The user's interview preference data and emotion data are sent to the server.

[0816] Step 9: Server suggests a meeting time

[0817] Input: User's interview preference data and emotion data.

[0818] How it works: The server uses an emotion analysis engine to suggest a time for a meeting that matches the user's emotional state. For example, if the user is tired, it will suggest a time when they are likely to relax.

[0819] Output: The server informs the user of the best time and place for the meeting.

[0820] Step 10: User conducts interview

[0821] Input: The interview time and location have been determined.

[0822] How it works: Job seekers and employers conduct interviews at designated times and locations. The server monitors the progress of the interviews in real time.

[0823] Output: The information about the completed interview is recorded on the server.

[0824] Step 11: Server confirms interview completion

[0825] Input: Interview completion information.

[0826] How it works: The server uses an emotion analysis engine to record the emotional state before and after the interview and to confirm the completion of the interview.

[0827] Output: Interview completion information and emotion data are saved in the database.

[0828] Step 12: Server awards reward points

[0829] Input: Interview completion information.

[0830] Operation: The server awards reward points to job seekers and records the points in a database.

[0831] Output: Reward points are reflected in the job seeker's account.

[0832] Step 13: The server detects that the interview has not been conducted.

[0833] Input: Information on interviews that have not been conducted after the scheduled interview time has passed.

[0834] How it works: The server detects that the interview was not conducted. The emotion analysis engine analyzes the user's emotional state and infers the cause of the problem.

[0835] Output: Uninterviewed information and emotional data are recorded in a database.

[0836] Step 14: Server Troubleshooting

[0837] Input: Uninterviewed information and emotional data.

[0838] Operation: The server takes appropriate action depending on the cause of the problem. For example, it assigns penalty points to the employer and refunds reward points to the job seeker.

[0839] Output: Changes in penalty points and reward points are reflected in the database.

[0840] Through these processing steps, the system can streamline the entire recruitment process and provide a personalized approach that takes into account the user's emotions.

[0841] (Application example 2)

[0842] 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."

[0843] Current recruitment processes and customer support systems lack efficiency in information entry, matching, scheduling, and troubleshooting. This often leaves small and medium-sized businesses, job seekers, and online shopping site customers feeling stressed and frustrated. Furthermore, the lack of a system that analyzes and responds to emotional states makes it difficult to provide personalized support. There is an urgent need to resolve these issues and provide efficient, emotionally sensitive support.

[0844] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0845] In this invention, the server includes means for using a generative model in which information is input in the form of questions, means for matching job seekers with employers based on the collected information, means for arranging interview schedules between job seekers and employers, means for awarding reward points to job seekers when the first interview is completed, means for handling problems when the interview does not take place, means for analyzing the emotional state of a user using emotion analysis means and taking appropriate action based on the data, means for analyzing customer inquiries in customer support for an online shopping site and proposing appropriate solutions, and means for providing reward points according to customer satisfaction based on the emotion analysis means. This enables more efficient recruitment activities and customer support, and personalized responses that take emotions into consideration.

[0846] The "information input" means the process by which a user provides information to the system in the form of a question.

[0847] A "generative model" refers to a system that uses AI technology to automatically generate questions and answers.

[0848] "Collected Information" refers to data entered by users or data automatically obtained by the system.

[0849] "Matching means" refers to the function of analyzing the conditions of job seekers and employers based on collected information and finding the optimal combination.

[0850] "Schedule adjustment means" refers to a function that automatically suggests and sets interview dates and times between job seekers and employers.

[0851] "Reward points" refer to points given to users as an incentive.

[0852] "Troubleshooting measures" refers to the function of taking measures when an interview is not conducted or other problems arise.

[0853] "Sentiment analysis means" refers to the function of analyzing emotions from a user's text or voice and adjusting the response based on the results.

[0854] "Customer inquiry" refers to the act of users of an online shopping site entering problems or questions they have into the system.

[0855] "Solution proposal means" refers to a function that automatically generates an appropriate solution based on the customer's inquiry.

[0856] "Customer satisfaction" refers to an indicator that measures the degree to which customers are satisfied with the services and solutions provided.

[0857] The embodiment of this invention is a system for solving recruitment issues faced by small and medium-sized businesses and job seekers. This system uses a generative AI model and sentiment analysis means to simplify information input, match job seekers with potential employers, smoothly schedule interviews, award reward points, and handle problems. Furthermore, the system can also be applied to customer support for online shopping sites, proposing appropriate solutions to customer inquiries and awarding reward points.

[0858] 1. Basic configuration

[0859] This system consists of a server, a terminal, and a user. The server runs a generative AI model and analyzes the user's emotional state using a sentiment analysis engine. Terminals can include smartphones, tablets, and PCs.

[0860] 2. Enter information

[0861] When a user logs in using a device, the server activates the generative AI model and collects information in the form of questions. For example, a question such as "What kind of job do you want?" is displayed, and as the user answers, the emotion engine analyzes the user's emotional state. As a result, if the user is nervous, for example, that information is stored in the database.

[0862] Specific examples

[0863] Example prompt: "Tell me more about your problem."

[0864] 3. Matching and Analysis

[0865] Based on the collected information, the server uses a generative AI model to analyze the requirements of job seekers and employers and generate scores. At the same time, an emotion engine evaluates the user's emotional state and adjusts the scoring, enabling more appropriate matching.

[0866] Specific examples

[0867] Example prompt: "We found a job posting that matches your criteria."

[0868] 4. Notice and Confirmation

[0869] Once a match is found, the server sends a notification and the user clicks the "Appoint" button to schedule the interview. The system uses an emotion engine to suggest a time and location that takes into account the user's emotional state.

[0870] Specific examples

[0871] Example prompt: "Please suggest a suitable time for the interview."

[0872] 5. Follow-up and rewards

[0873] When a user completes an interview or problem-solving follow-up, the server uses an emotion engine to record their emotional state and awards reward points. Depending on the user's satisfaction, further personalized messages are sent.

[0874] Specific examples

[0875] Example prompt: "Were you satisfied with our service?"

[0876] Hardware and Software Used

[0877] Hardware: Servers, smartphones, tablets, PCs

[0878] Software: Generative AI models, sentiment analysis engines, database management systems

[0879] Using these building blocks and prompts will enable efficient, personalized responses, improving the quality of your recruiting and customer support.

[0880] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0881] Step 1:

[0882] The user logs in to the device and begins entering information. The device inputs and displays a prompt. At this point, the user's input (e.g., an answer to the question, "What kind of job do you want?") is sent to the generative AI model.

[0883] Step 2:

[0884] The server launches the generative AI model and receives the user's answer. The generative AI model analyzes the user's answer and dynamically generates the next required question. The input is the user's answer, and the output is the next question.

[0885] Step 3:

[0886] The server uses a sentiment analysis engine to analyze the emotional state of the user from the answers entered by the user, where the input is the user's answer and the output is emotional data, which is stored in a database.

[0887] Step 4:

[0888] The server matches job seekers with potential employers based on the information and emotional data collected. A generative AI model analyzes the information and scores the match that best meets the criteria. The input is user information and emotional data, and the output is a score for the matching result.

[0889] Step 5:

[0890] The server notifies the job seeker and employer of the matching results. The notification includes a prompt (e.g., "We have found a job posting that matches your criteria"), and when the user presses the "Interview" button, the next step is taken. The input at this time is the matching result, and the output is the notification message.

[0891] Step 6:

[0892] When a user clicks the "Interview" button on the device, the server proposes an appropriate interview time and location based on the user's emotional state. The input is the user's emotional data and schedule information, and the output is an interview proposal.

[0893] Step 7:

[0894] Users (job seekers and employers) conduct interviews and report the results to the server. The server uses an emotion engine to record the emotional state before and after the interview and awards reward points. The inputs are the interview results and emotional data, and the output is reward points.

[0895] Step 8:

[0896] If the interview is not conducted, the server will handle the problem based on the emotion analysis data. Specifically, it will propose appropriate countermeasures, such as imposing a penalty on the hired candidate or refunding reward points to the job seeker. The inputs are the emotion data and the interview results, and the output is the countermeasures.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] [Third embodiment]

[0901] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0902] 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.

[0903] 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).

[0904] 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.

[0905] 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.

[0906] 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).

[0907] 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. 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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."

[0913] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it uses generative AI to simplify information input, matches job seekers with employers, smoothly arranges interview schedules, awards reward points, and handles problems. This system consists of a server, terminals, and users (employers and job seekers).

[0914] Program processing overview

[0915] Enter information

[0916] The server launches the generative model and obtains the necessary information from the user in the form of a question. For example, the server might ask, "What position are you hiring for?" and the user (employer) might respond, "Sales manager." Or, the server might ask, "Tell me about your past work history," and the user (job seeker) might respond, "I have two years of sales experience." The information collected in this way is stored in a database by the server.

[0917] matching

[0918] The server analyzes the collected information and scores compatibility between job seekers and employers based on their criteria. For example, a generative model performs optimal matching based on information such as the job seeker's skill set, work experience, and preferred work location. A list of highly-scoring job seekers is generated and notified to the employer. Similarly, job openings that match the criteria are notified to the job seeker.

[0919] Notification and confirmation

[0920] When the user receives the notification, they click the "Ask for a meeting" button to indicate their intention to meet. The server confirms this intention and starts the process to coordinate the schedule for both parties.

[0921] First interview and reward

[0922] After the job seeker and employer conduct the first interview, the server confirms the completion of the interview and awards reward points to the job seeker, which can increase the job seeker's motivation.

[0923] Troubleshooting

[0924] If the server does not conduct an interview after a successful match, it will take appropriate action to resolve the issue, such as adding penalty points to the employer's account or providing a refund to the job seeker.

[0925] Specific examples

[0926] Example 1: When the recruiter inputs information

[0927] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[0928] 2. The server generates a question: The server asks a question through the generative model: "Tell me about the position you're hiring."

[0929] 3. The employer responds: "I'm the sales manager," the employer responds.

[0930] 4. Server saves the data: The server saves the answers in a database.

[0931] Example 2: Job seeker receives a match notification

[0932] 1. The server analyzes the conditions: The server analyzes the job seeker's conditions (skill set, location, experience, etc.) and scores them using a generative model.

[0933] 2. The server sends a notification: Based on the list of high-scoring employers, the server notifies the job seeker that "job information matching your criteria has been found."

[0934] 3. The job seeker requests an interview: The job seeker indicates their intention by pressing the "Interview" button.

[0935] As described above, this invention efficiently solves the problems of employers and job seekers through a system that includes a series of processes, such as inputting information in the form of questions using generative AI, matching through condition analysis and scoring, and providing rewards and troubleshooting. This system makes recruitment activities more efficient and reduces costs.

[0936] The processing flow will be explained below.

[0937] Program processing flow

[0938] Information input phase

[0939] Step 1:

[0940] The user logs into the application using a terminal. The server authenticates the account information and displays the main screen if the login is successful.

[0941] Step 2:

[0942] The server invokes the generative model to generate questions for the user (employer or job seeker), such as "What kind of job do you want?"

[0943] Step 3:

[0944] The user enters an answer to the question. If they are an employer, they might answer "sales manager," and if they are a job seeker, they might answer "sales position."

[0945] Step 4:

[0946] The server stores the user's answers in a database, which is used for subsequent analysis and matching.

[0947] Matching Process

[0948] Step 5:

[0949] The server analyzes all the information on job seekers and employers stored in the database. The generative model scores them based on the criteria and finds the optimal combination.

[0950] Step 6:

[0951] The server generates a list of high-scoring job seekers and sends notifications to employers.

[0952] Step 7:

[0953] The server also notifies the job seeker of a list of employers that match their criteria, with a message such as "We've found jobs that match your criteria."

[0954] Notification and confirmation phase

[0955] Step 8:

[0956] The user checks the notification and clicks the "Interview" button. If both the job seeker and the employer click the button, the process proceeds to the next step.

[0957] Step 9:

[0958] The server displays a screen for arranging the interview schedule between the two parties. The user enters the desired date and time.

[0959] Step 10:

[0960] The server will finalize the schedule and notify both parties of the interview details.

[0961] Initial Interview and Reward Phase

[0962] Step 11:

[0963] Users (job seekers and employers) conduct interviews at the specified date and time.

[0964] Step 12:

[0965] After the interview is completed, the server confirms the completion of the interview and gives reward points to the job seeker.

[0966] Troubleshooting phase

[0967] Step 13:

[0968] If an interview is not conducted, the server will recognize it as a problem and take appropriate action, such as giving penalty points to the recruit or refunding reward points to the job seeker.

[0969] The above is the specific processing flow of the system. This flow will enable efficient recruitment activities and solve the problems of small and medium-sized businesses and job seekers.

[0970] Example 1

[0971] 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."

[0972] There is a need for efficient methods to resolve the recruitment issues faced by small and medium-sized businesses and job seekers. Specifically, it is necessary to simplify the information entry process, ensure appropriate matching, smoothly arrange interview schedules, award reward points to motivate job seekers, and deal with problems when interviews are not conducted.

[0973] 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.

[0974] In this invention, the server includes a means for inputting information in the form of questions using a generative AI model, a means for matching job seekers with employers based on collected data, a means for sending a notification to the user and arranging an interview schedule between the job seeker and employer, a means for awarding reward points to the job seeker when the first interview is completed, and a means for dealing with problems when an interview does not take place. This makes recruitment activities more efficient and reduces costs, while also making it possible to improve job seeker motivation and quickly deal with problems when they occur.

[0975] A "generative AI model" is a model that uses artificial intelligence to automatically generate text and data.

[0976] "Information input" is the process by which the system obtains the necessary information from the user.

[0977] A "question format" is a method of gathering information by asking a user a series of questions.

[0978] "Data" means the collection of information provided by the user that the system uses for analysis and matching.

[0979] "Matching" is the process of finding the best match based on the requirements of the job seeker and the employer.

[0980] "User" refers to the employers and job seekers who use the system.

[0981] "Notification" is the act of the system sending information or messages to the user.

[0982] "Scheduling" is the process of setting up an interview date and time between a job seeker and an employer.

[0983] A "first interview" refers to the first meeting between a job seeker and an employer.

[0984] "Reward points" are points that the system awards to job seekers as motivation and reward.

[0985] "Troubleshooting" is the process for resolving problems that arise after a match is made.

[0986] The present invention is a system that uses a generative AI model to solve recruitment issues faced by small and medium-sized businesses and job seekers. Specifically, the system simplifies information input, matches job seekers with potential employers, arranges interview schedules, awards reward points, and handles problems. Detailed embodiments of the present invention are described below.

[0987] System Configuration

[0988] Hardware and Software Configuration

[0989] This system mainly consists of a server, terminals, and users (employers and job seekers).

[0990] Server: Responsible for the primary data processing and execution of generative AI models. For example, the server uses generative AI models such as OpenAI's GPT-3.

[0991] Terminal: A device where a user enters information and checks results. This includes computers, smartphones, tablets, etc.

[0992] Users: Employers and job seekers who use the system.

[0993] Specific examples of hardware use

[0994] The server uses a cloud server equipped with a high-performance processor and large memory capacity.

[0995] The terminal can be any device with a standard internet connection.

[0996] Specific examples of software use

[0997] Generative AI models: Use natural language generation models such as OpenAI's GPT-3.

[0998] Database Management Systems: RDBMS such as MySQL or PostgreSQL are used to store data.

[0999] Front-end: Building the user interface using JavaScript frameworks such as React or Vue.js.

[1000] Process Overview

[1001] The server launches the generative AI model and asks the user questions to obtain the necessary information. The collected information is stored in a database, and the server matches job seekers with employers based on that information. The matching results are sent to the user as a notification, and if the user indicates a desire for an interview, the server arranges the interview schedule. When the interview is completed, the server awards reward points to the job seeker, and if the interview does not take place, it handles any issues.

[1002] Example

[1003] Example 1: When the recruiter inputs information

[1004] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[1005] 2. The server generates a question: Using a generative AI model, the server generates a question such as, "Tell me about the position you're hiring."

[1006] 3. The recruiter answers: "I'm a sales manager."

[1007] 4. Server saves the data: The answers are saved in a database.

[1008] Example 2: When a job seeker receives a match notification

[1009] 1. The server analyzes the conditions: The job seeker's conditions (skill set, work location, experience, etc.) are analyzed using a generative AI model and a score is generated.

[1010] 2. The server sends a notification: "We've found a job that matches your criteria."

[1011] 3. The job seeker requests an interview: The job seeker indicates their intention by pressing the "Interview" button.

[1012] Prompt Sentence Examples

[1013] Here are some example prompts that the generative AI model might use:

[1014] 1. For employers: "Tell me about the position you're hiring."

[1015] 2. For job seekers: "Tell me about your past work experience."

[1016] In this way, the present invention is a system that uses a generative AI model to input information in the form of questions, and then comprehensively performs matching, notification, interview schedule adjustment, reward point allocation, and trouble shooting, thereby streamlining recruitment activities and reducing costs.

[1017] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1018] Program processing flow

[1019] Step 1: Start entering information

[1020] The server launches the generative AI model and obtains the necessary information from the user in the form of questions.

[1021] Specific behavior:

[1022] 1. The server launches a generative AI model: Launch a generative AI model (e.g., OpenAI GPT-3).

[1023] 2. Server generates questions: A generative AI model is used to generate questions, such as "What position are you hiring?"

[1024] 3. User enters information: Employers and job seekers answer questions and enter information.

[1025] 4. Input: Information entered by the user (e.g., position name, work history).

[1026] 5. Output: The information obtained by the server is stored in the server's database.

[1027] Step 2: Analyzing and matching information

[1028] The server analyzes the collected information and uses a generative AI model to score compatibility between job seekers and employers based on their criteria.

[1029] Specific behavior:

[1030] 1. The server collects data: The latest collected information is retrieved from the database.

[1031] 2. The server analyzes using the generative AI model: It runs the analysis algorithm and analyzes the collected information.

[1032] 3. The server performs scoring: A generative AI model is used to score the compatibility between job seekers and employers.

[1033] 4. Input: Job seeker and employer information stored on the server.

[1034] 5. Output: Calculate compatibility scores and generate a list of job seekers with high scores.

[1035] Step 3: Notification of match results

[1036] The server sends a notification to the user based on the matching results.

[1037] Specific behavior:

[1038] 1. Server generates notification content: A generative AI model is used to generate notification content, e.g., "We've found a job posting that matches your criteria."

[1039] 2. The server sends a notification: A notification is sent to the device.

[1040] 3. Users receive notifications: Job seekers and employers receive notifications.

[1041] 4. Input: Generated compatibility scores and a list of high-scoring job seekers.

[1042] 5. Output: Notification message sent to the user.

[1043] Step 4: Schedule an interview

[1044] When the user indicates a desire for an interview, the server arranges the interview schedule.

[1045] Specific behavior:

[1046] 1. User indicates desire for interview: The job seeker presses the "Interview" button.

[1047] 2. The server adjusts the schedules: The schedules of both parties are automatically adjusted and the date and time of the meeting is decided.

[1048] 3. Server sends notification again: Notifies the user of the adjusted schedule.

[1049] 4. Input: Job seeker and hire schedule information.

[1050] 5. Output: Confirmed interview date and time and notification message.

[1051] Step 5: First interview and reward points awarded

[1052] When the first interview is completed, the server awards reward points to the job seeker.

[1053] Specific behavior:

[1054] 1. Confirmation of interview completion: The recruiter presses the "Interview Completed" button.

[1055] 2. The server awards reward points: The server awards reward points to the job seeker and reflects them in the account.

[1056] 3. The server saves the data: The awarded reward points are saved in the database.

[1057] 4. Enter: Confirmation of interview completion.

[1058] 5. Output: Reward points are awarded and stored in the database.

[1059] Step 6: Perform troubleshooting

[1060] If the interview does not take place, the server will take action to troubleshoot.

[1061] Specific behavior:

[1062] 1. The server checks that the interview has not been conducted: It detects that the interview has not been conducted.

[1063] 2. Server assigns penalty: assigns penalty points to the adopter.

[1064] 3. The server processes the refund: The server processes the refund for the job seeker.

[1065] 4. Enter: Confirmation information for unsuccessful interviews.

[1066] 5. Output: Notification of penalty points being awarded and refund completion.

[1067] (Application example 1)

[1068] 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."

[1069] A major challenge for logistics centers is efficiently securing a large workforce. However, many small and medium-sized businesses lack the resources and technology to quickly and efficiently find job seekers, schedule interviews, and ultimately secure labor. This makes the recruitment process cumbersome and time-consuming, making it difficult to find suitable candidates. Scheduling interviews and dealing with issues when interviews are not conducted are also challenges.

[1070] 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.

[1071] In this invention, the server includes means for using a generative model in which information is input in the form of questions, means for matching job seekers with employers based on the collected information, means for arranging interview schedules between job seekers and employers, means for awarding reward points to job seekers when the first interview is completed, means for dealing with problems when the interview does not take place, means for automatically arranging schedules between job seekers and employers using an external service, and means for electronically confirming the completion of interviews. This enables the logistics center to quickly and efficiently secure labor.

[1072] "Means of using a generative model that inputs information in the form of a question" refers to a means of obtaining the necessary information from the user in the form of a question and securing that information using a generative AI model.

[1073] "Means of matching job seekers and employers based on collected information" refers to a means of analyzing collected information on job seekers and employers and appropriately connecting the two based on mutual conditions.

[1074] The "means for coordinating interview schedules between job seekers and employers" is a means for automatically setting the optimal interview date and time, taking into consideration the schedules of both the employer and the job seeker.

[1075] "Means for granting reward points to a job seeker upon completion of the first interview" refers to a means for granting reward points to a job seeker as an incentive after confirming that the first interview has ended.

[1076] "Measures to deal with problems when an interview is not conducted" refers to measures to provide appropriate compensation or penalties to users when an interview is canceled or not conducted.

[1077] "Means for automatically coordinating the schedules of job seekers and employers using external services" refers to means for automatically coordinating the schedules of job seekers and employers using external calendar and schedule management services.

[1078] "Means for confirming completion of interview by electronic means" refers to a means for reliably confirming that the interview has been completed using electronic means, such as scanning a QR code.

[1079] The system embodying this invention is designed to solve the problems of job recruitment efficiency and interviews that employers and job seekers face. This system is composed of a server, terminals, and users.

[1080] Server Roles

[1081] Hardware and software used

[1082] The server uses the following hardware and software:

[1083] Server-side hardware: AWS EC2

[1084] Database: DynamoDB

[1085] Generative AI model: OpenAI GPT-3

[1086] Backend: Node.js, Express

[1087] Communication method: REST API

[1088] Enter information

[1089] The server uses a generative AI model to prompt the user for information in the form of a question, such as "What position are you hiring for?", to which the candidate responds "Sales Manager." This information is stored in DynamoDB via a REST API.

[1090] matching

[1091] Based on the collected information, the generative AI model analyzes and scores the requirements of job seekers and employers. The scoring system makes an appropriate match, and the employer is notified of a list of job seekers with high scores.

[1092] Schedule adjustment

[1093] When a job seeker notifies the company that they wish to interview, the system automatically coordinates the schedules of both parties using the Google Calendar API, efficiently managing the schedules of both the job seeker and the employer through an external service.

[1094] Reward points awarded

[1095] Once the first interview is completed, the job seeker will scan the QR code to confirm the completion of the interview, after which reward points will be automatically awarded to the job seeker.

[1096] Troubleshooting

[1097] If an interview is not conducted, the server will provide appropriate compensation or penalties, such as adding penalty points to the employer's account or providing a refund to the job seeker.

[1098] Device Role

[1099] Hardware and software used

[1100] The terminal uses the following hardware and software:

[1101] Frontend: React Native (smartphone app)

[1102] Enter information

[1103] Users (employers, job seekers) use their devices to answer questions posed by the generative AI model, and this information is sent to the server in real time and stored in DynamoDB.

[1104] Check the schedule

[1105] When the request button is pressed, the appointment is automatically scheduled on the device, and the schedule is synchronized between the device and the server using the Google Calendar API.

[1106] User Roles

[1107] Information input and response

[1108] The user inputs information through a device, answers questions posed by the generative AI model, and performs other operations such as pressing a button to indicate a desire for an interview.

[1109] Conducting interviews

[1110] Once the interview is complete, job seekers confirm completion by scanning a QR code, which automatically awards reward points.

[1111] Specific examples

[1112] Example prompts to be input to the generative AI model:

[1113] (When the recruit logs in)

[1114] "Please tell me about the positions available at the logistics center."

[1115] User Answer: "Warehouse worker"

[1116] "What skills are required for the position?"

[1117] User Answer: "Forklift driving qualification"

[1118] (When job seeker logs in)

[1119] "Tell me about your past work history."

[1120] User Answer: "I have 3 years of warehouse experience."

[1121] "Please tell us where you would like to work."

[1122] User Answer: "Tokyo"

[1123] In this way, a single process is carried out, from inputting information to matching, arranging interview schedules, awarding reward points, and troubleshooting, enabling logistics centers to quickly and efficiently secure labor.

[1124] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1125] Step 1:

[1126] The server launches the generative AI model and generates questions for information input. The questions are sent to the device, and the user (employer or job seeker) enters the answers. The input includes information such as the position being filled and past work history. The server uses the generative AI model to create prompts to generate appropriate questions and presents them to the user. The user's answer data is sent from the device to the server and stored in DynamoDB.

[1127] Step 2:

[1128] The server executes a matching algorithm based on the information collected. First, the server retrieves the job seeker and employer information collected from DynamoDB. Then, it uses a generative AI model to analyze and score the conditions. The input for this step is the job seeker's skill set, work experience, preferred work location, etc., and the output is a compatibility score. A list of high-scoring job seekers is generated and notified to the employer's device.

[1129] Step 3:

[1130] The user (job seeker) receives the notification and presses the "Interview" button. This action registers the interview request. The server retrieves the schedules of the job seeker and employer using the Google Calendar API and automatically adjusts the schedules. The input for this step is the available time of the job seeker and employer, and the output is the adjusted interview date and time. The adjustment result is notified to the terminal.

[1131] Step 4:

[1132] A user (job seeker) attends an interview on the interview date. After completing the interview, the job seeker scans the QR code to report the completion of the interview. The device sends the scanned data to the server, which then confirms the completion of the interview. The input of this step is the scanned data of the QR code, and the output is confirmation of the completion of the interview. After confirmation, reward points are automatically awarded to the job seeker.

[1133] Step 5:

[1134] If the interview is not conducted, the server will automatically execute a troubleshooting process. First, it checks the actions of both parties at the scheduled interview date and time, and if the interview is not conducted, it starts the troubleshooting process. The input of this step is the log of the not conducted interview, and the output is the feedback of compensation or penalty. For example, penalty points are added to the employer's account and a refund is given to the job seeker.

[1135] 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.

[1136] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it uses generative AI to simplify information input, match job seekers with employers, smoothly arrange interview schedules, award reward points, and handle problems. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it is possible to provide more personalized responses. This system consists of a server, terminals, and users (employers and job seekers).

[1137] Program processing overview

[1138] Enter information

[1139] The server launches the generative model and obtains the necessary information from the user in the form of a question. For example, it displays a question such as, "What kind of job do you want?" As the user answers, the server simultaneously uses an emotion engine to analyze the user's emotions and stores this information in a database. For example, if the user is feeling stressed, that information is also recorded.

[1140] matching

[1141] The server analyzes the collected information and scores the compatibility between the job seeker and employer based on their criteria. A generative model evaluates the job seeker's skill set, work experience, preferred work location, etc., and an emotion engine adjusts the score based on the user's emotional state. A list of high-scoring job seekers is generated and notified to the employer. Similarly, job openings that match the criteria are notified to the job seeker. For example, if the job seeker is nervous, a message to ease their tension is sent.

[1142] Notification and confirmation

[1143] The user receives the notification and clicks the "Appoint" button. The server uses an emotion engine to analyze the user's emotional state and suggest an appropriate time and place. For example, if the user is tired, it suggests a time when they can relax.

[1144] First interview and reward

[1145] When users (job seekers and employers) conduct interviews, the server uses an emotion engine to record their emotional states before and after the interview. After the interview is over, the server confirms the completion of the interview and awards reward points to the job seeker. It also provides feedback based on the emotion engine. For example, if the job seeker is satisfied after the interview, this is displayed as feedback.

[1146] Troubleshooting

[1147] If the server does not conduct an interview after a successful match, it uses an emotion engine to analyze the emotional state behind the problem. It then takes appropriate action to resolve the issue, such as assigning penalty points to the hire or refunding reward points to the job seeker. For example, if the user expresses anger or dissatisfaction, the system takes that emotional state into consideration.

[1148] Specific examples

[1149] Example 1: When the recruiter inputs information

[1150] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[1151] 2. Server generates question: The server asks a question through the generative model, such as "Tell me about the position you're hiring for." At the same time, the emotion engine checks the emotional state of the recruit.

[1152] 3. Hire responds: "I'm a sales manager," the hire responds. The emotion engine records the hire's stress level.

[1153] 4. Server saves the data: The server saves the answers and emotion data in a database.

[1154] Example 2: Job seeker receives a match notification

[1155] 1. Server analyzes the job seeker's requirements (skill set, location, experience, etc.) and scores them using a generative model. At the same time, the emotion engine evaluates the job seeker's emotional state.

[1156] 2. Server sends notification: Based on the list of high-scoring employers, the server notifies the job seeker that "We have found a job posting that matches your criteria." If the job seeker is nervous, it also sends a relaxing message.

[1157] 3. The job seeker requests an interview: The job seeker clicks the "Interview" button to indicate their intention. The emotion engine analyzes the desired time slot and sends the results to the server.

[1158] As described above, this invention uses generative AI and an emotion engine to solve the problems of employers and job seekers in an efficient and personalized way through a system that includes a series of processes such as inputting information in the form of questions, matching through condition analysis and scoring, scheduling that takes emotions into account, and rewards and troubleshooting. This system makes recruitment activities more efficient and realizes an approach that takes users' emotions into consideration.

[1159] The processing flow will be explained below.

[1160] Program processing flow

[1161] Information input phase

[1162] Step 1:

[1163] The user logs into the application using a terminal. The server authenticates the user's account information and displays the main screen if the login is successful.

[1164] Step 2:

[1165] The server invokes the generative model to generate questions for the user (employer or job seeker), such as "What kind of job do you want?"

[1166] Step 3:

[1167] The user inputs answers to the questions. For example, an employer might answer "sales manager," and a job seeker might answer "sales position." At the same time, the server uses an emotion engine to analyze the user's emotional state and stores that information in the database.

[1168] Step 4:

[1169] The server stores the user's answers and emotion data in a database for the next step.

[1170] Matching Process

[1171] Step 5:

[1172] The server analyzes the information of all job seekers and employers stored in the database and uses a generative model to score them based on the conditions.

[1173] Step 6:

[1174] The emotion engine adjusts the score based on the user's emotional state, for example, appropriately adjusting the score of a job candidate who is stressed.

[1175] Step 7:

[1176] Based on the scoring results, a list of job seekers with high scores is generated, and the server notifies the employer of this list.

[1177] Step 8:

[1178] Similarly, the server notifies the job seeker of a list of employers that match the job search criteria, with the notification including the message "We have found jobs that match your criteria."

[1179] Notification and confirmation phase

[1180] Step 9:

[1181] The user checks the notification and clicks the "Ask for an interview" button in the notification. The server receives this decision and proceeds to the next step.

[1182] Step 10:

[1183] The server uses an emotion engine to analyze the user's emotional state and suggest the best time and place for the interview, for example, suggesting a relaxing time for a tired user.

[1184] Step 11:

[1185] Once the user reviews and agrees to the proposed schedule, the server notifies both parties of the interview details.

[1186] Initial Interview and Reward Phase

[1187] Step 12:

[1188] Users (job seekers and employers) conduct interviews at the specified date and time. The server uses an emotion engine to record the emotional state before and after the interview.

[1189] Step 13:

[1190] After the interview is completed, the server confirms the completion of the interview, awards reward points to the job seeker, and generates feedback based on the emotion engine to provide to the user.

[1191] Troubleshooting phase

[1192] Step 14:

[1193] If no interview is conducted, the server uses an emotion engine to analyze the emotional state behind the trouble.

[1194] Step 15:

[1195] The server then takes appropriate action to resolve the issue, such as assigning penalty points to the recruit or refunding reward points to the job seeker. If the user expresses anger or dissatisfaction, the server takes appropriate action, taking into consideration their emotional state.

[1196] This is the specific processing flow of the system. This flow not only enables efficient recruitment activities and solves the problems of small and medium-sized businesses and job seekers, but also realizes an approach that takes user feelings into full consideration.

[1197] Example 2

[1198] 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."

[1199] Currently, recruitment activities between small and medium-sized businesses and job seekers face several challenges, such as the time-consuming task of inputting information, inaccurate matching, difficulty in arranging interview schedules, and insufficient response to problems when interviews are not conducted.In addition, there is a lack of consideration for user feelings, so there is a need to improve satisfaction throughout the entire recruitment process.

[1200] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting information in the form of a question using a generative AI model, a means for analyzing the user's emotional state using an emotion analysis engine and saving the result together with the information, a means for matching job seekers with employers based on the collected information, a means for sending notifications to the job seeker and employer based on the matching results, a means for arranging interview schedules between the job seeker and employer, a means for awarding reward points to the job seeker when the first interview is completed, and a means for handling problems when the interview does not take place. This makes the entire hiring process more efficient and enables a personalized approach that takes user emotions into consideration.

[1201] A "generative AI model" is an artificial intelligence model that generates questions based on input from users and collects information.

[1202] An "emotion analysis engine" is an engine that analyzes the user's emotional state and optimizes the system's processing and response based on that information.

[1203] A "means for inputting information in the form of a question" is an interface or process for presenting a question to a user and collecting answers.

[1204] The "means for analyzing the user's emotional state and storing it together with the information" is the process of using an emotion analysis engine to collect the user's emotional data and storing it in a database together with the answers to the questions.

[1205] "Means of matching job seekers and employers based on collected information" refers to the process of analyzing collected data and comparing the conditions of job seekers and employers to make the best match.

[1206] The "means for sending notifications to job seekers and employers based on the matching results" refers to a communication process for notifying users of the matching results.

[1207] "Method of coordinating interview schedules between job seekers and employers" is the process for coordinating the date, time, and location of an interview.

[1208] "Means for awarding reward points to job seekers upon completion of the first interview" refers to the process of confirming the completion of the interview and awarding points to job seekers as an incentive.

[1209] "Measures for implementing troubleshooting measures when an interview is not conducted" refers to the process for analyzing the cause and taking appropriate measures when a scheduled interview is not conducted.

[1210] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it simplifies information input using a generative AI model and a sentiment analysis engine, and matches job seekers with employers, arranges interview schedules, awards reward points, and handles problems. This system consists of a server, terminals, and users (employers and job seekers).

[1211] First, the user logs in to the system via a terminal. The login information is authenticated on the server side, and the user begins using the system. The server then activates a generative AI model to present a question to the user. This prompt might include, for example, "What kind of job do you want?" The server also activates an emotion analysis engine to check the user's emotional state.

[1212] When a user answers a question from the server using a terminal, for example by entering "I'm an engineer," the emotion analysis engine detects the user's stress level and simultaneously collects that data. The server stores these responses and emotion data in a database, and then aggregates the information needed for the next processing step.

[1213] The server then analyzes the information stored in the database and uses a generative AI model to appropriately evaluate the job seeker's skill set, work experience, preferred location, etc. The sentiment analysis engine then takes into account the emotional data analyzed and adjusts the scoring to ensure optimal matching.

[1214] The server generates a compatibility score based on the data of job seekers and employers, and creates a list of job seekers with high scores. This list is notified to employers, and at the same time, job information that matches the job seeker's criteria is also notified to the job seeker. For example, if the job seeker is nervous, a message to calm them down is also sent.

[1215] Upon receiving the notification, the user clicks the "Consult" button on their device to notify the server of their request for a consultation. At this time, the emotion analysis engine analyzes the user's emotional state and sends this information to the server as a suggestion for the optimal consultation time. The server then takes the user's emotional state into consideration and suggests an appropriate time and place. For example, if the user is tired, it will suggest a time when they would be able to relax.

[1216] When the job seeker and employer conduct the interview at the agreed time, the server uses a sentiment analysis engine to record the job seeker's emotional state before and after the interview. After the interview is over, the server confirms the completion of the interview and awards reward points to the job seeker. These points are recorded in a database and can be used at a later date. Feedback is also provided based on the sentiment analysis engine. For example, if the job seeker is highly satisfied with the interview, this information is displayed as feedback.

[1217] If a scheduled interview does not take place, the server will detect this. The emotion analysis engine will analyze the user's emotional state and infer the cause of the problem. Appropriate measures will be taken to resolve the issue, such as assigning penalty points to the hired candidate and refunding reward points to the job seeker. For example, if the user is feeling dissatisfied or angry, the system will take their emotional state into consideration.

[1218] In this way, the system of the present invention uses a generative AI model and a sentiment analysis engine to streamline the entire recruitment process and provide a personalized approach that takes user emotions into consideration. For example, when a recruiter inputs information, the prompt "Tell us about the position you are hiring for" is presented, and the recruit replies "Sales Manager," and emotional data is also collected.

[1219] Furthermore, when a job seeker receives a matching notification, they will be notified that "We have found a job posting that matches your criteria," and if they are feeling nervous, they will also be sent a relaxing message. When a job seeker indicates their intention by pressing the "Interview" button, the sentiment analysis engine analyzes their desired time slot and sends the result to the server, which then suggests the optimal time for the interview.

[1220] The above functions will make recruitment activities more efficient and enable an approach that takes users' emotions into consideration.

[1221] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1222] Step 1: User logs into the system

[1223] Input: The user enters login information (username and password) into the terminal.

[1224] How it works: The device sends login information to the server, which authenticates it and retrieves the user's profile information from a database.

[1225] Output: The server verifies the user's login and redirects them to a screen to enter their information.

[1226] Step 2: Server generates a question

[1227] Input: User is logged in.

[1228] How it works: The server launches the generative AI model to generate a question prompt to be displayed to the user. For example, it creates a prompt sentence such as, "What kind of job do you want?". It also launches an emotion analysis engine to analyze the user's initial emotional state.

[1229] Output: The generated question is displayed on the terminal, and the emotion data is kept as the initial state.

[1230] Step 3: User Enters Information

[1231] Input: The user answers the server's questions through the terminal. For example, the user enters "I'm an engineer."

[1232] Operation: The device sends user input data to the server, which uses an emotion analysis engine to analyze the user's emotional state (e.g., stress level) during the response.

[1233] Output: The server stores the user's response data and emotion data in a database.

[1234] Step 4: The server parses the information

[1235] Input: User response data and emotion data stored in a database.

[1236] How it works: The server uses the generated AI model to analyze skillsets, work experience, preferred work location, etc. At the same time, the sentiment analysis engine generates a sentiment score from the user's emotional data.

[1237] Output: The analysis results and sentiment scores are stored in a database, which is used for the subsequent matching process.

[1238] Step 5: Server generates compatibility score

[1239] Input: Parsed job candidate data and employer requirements data.

[1240] How it works: The server uses the generative AI model to generate a compatibility score based on the job seeker and employer criteria, and also takes into account the sentiment score from the sentiment analysis engine to calculate an overall compatibility score.

[1241] Output: The compatibility scores between job seekers and employers are stored in a database.

[1242] Step 6: The server sends a notification

[1243] Input: Generated compatibility scores and matching results.

[1244] How it works: The server creates a list of high-scoring job seekers and sends a notification to the employer. At the same time, job seekers are also notified of job postings that match their criteria. For example, a message may be sent to job seekers saying, "We've found a job posting that matches your criteria."

[1245] Output: A notification will be displayed on the employer and job seeker's devices.

[1246] Step 7: User confirms notification

[1247] Input: The user who received the notification (job seeker or employer).

[1248] How it works: The user checks the notification via their device. If the job seeker is nervous, the system also displays a message encouraging them to relax.

[1249] Output: The user confirms the notification and is ready to proceed to the next step.

[1250] Step 8: User selects appointment preference

[1251] Input: The user (job seeker or employer) who confirmed the notification.

[1252] How it works: The job seeker clicks the "Schedule an Interview" button to indicate their intention. The emotion analysis engine analyzes the user's emotional state and determines the desired interview time slot.

[1253] Output: The user's interview preference data and emotion data are sent to the server.

[1254] Step 9: Server suggests a meeting time

[1255] Input: User's interview preference data and emotion data.

[1256] How it works: The server uses an emotion analysis engine to suggest a time for a meeting that matches the user's emotional state. For example, if the user is tired, it will suggest a time when they are likely to relax.

[1257] Output: The server informs the user of the best time and place for the meeting.

[1258] Step 10: User conducts interview

[1259] Input: The interview time and location have been determined.

[1260] How it works: Job seekers and employers conduct interviews at designated times and locations. The server monitors the progress of the interviews in real time.

[1261] Output: The information about the completed interview is recorded on the server.

[1262] Step 11: Server confirms interview completion

[1263] Input: Interview completion information.

[1264] How it works: The server uses an emotion analysis engine to record the emotional state before and after the interview and to confirm the completion of the interview.

[1265] Output: Interview completion information and emotion data are saved in the database.

[1266] Step 12: Server awards reward points

[1267] Input: Interview completion information.

[1268] Operation: The server awards reward points to job seekers and records the points in a database.

[1269] Output: Reward points are reflected in the job seeker's account.

[1270] Step 13: The server detects that the interview has not been conducted.

[1271] Input: Information on interviews that have not been conducted after the scheduled interview time has passed.

[1272] How it works: The server detects that the interview was not conducted. The emotion analysis engine analyzes the user's emotional state and infers the cause of the problem.

[1273] Output: Uninterviewed information and emotional data are recorded in a database.

[1274] Step 14: Server Troubleshooting

[1275] Input: Uninterviewed information and emotional data.

[1276] Operation: The server takes appropriate action depending on the cause of the problem. For example, it assigns penalty points to the employer and refunds reward points to the job seeker.

[1277] Output: Changes in penalty points and reward points are reflected in the database.

[1278] Through these processing steps, the system can streamline the entire recruitment process and provide a personalized approach that takes into account the user's emotions.

[1279] (Application example 2)

[1280] 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."

[1281] Current recruitment processes and customer support systems lack efficiency in information entry, matching, scheduling, and troubleshooting. This often leaves small and medium-sized businesses, job seekers, and online shopping site customers feeling stressed and frustrated. Furthermore, the lack of a system that analyzes and responds to emotional states makes it difficult to provide personalized support. There is an urgent need to resolve these issues and provide efficient, emotionally sensitive support.

[1282] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1283] In this invention, the server includes means for using a generative model in which information is input in the form of questions, means for matching job seekers with employers based on the collected information, means for arranging interview schedules between job seekers and employers, means for awarding reward points to job seekers when the first interview is completed, means for handling problems when the interview does not take place, means for analyzing the emotional state of a user using emotion analysis means and taking appropriate action based on the data, means for analyzing customer inquiries in customer support for an online shopping site and proposing appropriate solutions, and means for providing reward points according to customer satisfaction based on the emotion analysis means. This enables more efficient recruitment activities and customer support, and personalized responses that take emotions into consideration.

[1284] The "information input" means the process by which a user provides information to the system in the form of a question.

[1285] A "generative model" refers to a system that uses AI technology to automatically generate questions and answers.

[1286] "Collected Information" refers to data entered by users or data automatically obtained by the system.

[1287] "Matching means" refers to the function of analyzing the conditions of job seekers and employers based on collected information and finding the optimal combination.

[1288] "Schedule adjustment means" refers to a function that automatically suggests and sets interview dates and times between job seekers and employers.

[1289] "Reward points" refer to points given to users as an incentive.

[1290] "Troubleshooting measures" refers to the function of taking measures when an interview is not conducted or other problems arise.

[1291] "Sentiment analysis means" refers to the function of analyzing emotions from a user's text or voice and adjusting the response based on the results.

[1292] "Customer inquiry" refers to the act of users of an online shopping site entering problems or questions they have into the system.

[1293] "Solution proposal means" refers to a function that automatically generates an appropriate solution based on the customer's inquiry.

[1294] "Customer satisfaction" refers to an indicator that measures the degree to which customers are satisfied with the services and solutions provided.

[1295] The embodiment of this invention is a system for solving recruitment issues faced by small and medium-sized businesses and job seekers. This system uses a generative AI model and sentiment analysis means to simplify information input, match job seekers with potential employers, smoothly schedule interviews, award reward points, and handle problems. Furthermore, the system can also be applied to customer support for online shopping sites, proposing appropriate solutions to customer inquiries and awarding reward points.

[1296] 1. Basic configuration

[1297] This system consists of a server, a terminal, and a user. The server runs a generative AI model and analyzes the user's emotional state using a sentiment analysis engine. Terminals can include smartphones, tablets, and PCs.

[1298] 2. Enter information

[1299] When a user logs in using a device, the server activates the generative AI model and collects information in the form of questions. For example, a question such as "What kind of job do you want?" is displayed, and as the user answers, the emotion engine analyzes the user's emotional state. As a result, if the user is nervous, for example, that information is stored in the database.

[1300] Specific examples

[1301] Example prompt: "Tell me more about your problem."

[1302] 3. Matching and Analysis

[1303] Based on the collected information, the server uses a generative AI model to analyze the requirements of job seekers and employers and generate scores. At the same time, an emotion engine evaluates the user's emotional state and adjusts the scoring, enabling more appropriate matching.

[1304] Specific examples

[1305] Example prompt: "We found a job posting that matches your criteria."

[1306] 4. Notice and Confirmation

[1307] Once a match is found, the server sends a notification and the user clicks the "Appoint" button to schedule the interview. The system uses an emotion engine to suggest a time and location that takes into account the user's emotional state.

[1308] Specific examples

[1309] Example prompt: "Please suggest a suitable time for the interview."

[1310] 5. Follow-up and rewards

[1311] When a user completes an interview or problem-solving follow-up, the server uses an emotion engine to record their emotional state and awards reward points. Depending on the user's satisfaction, further personalized messages are sent.

[1312] Specific examples

[1313] Example prompt: "Were you satisfied with our service?"

[1314] Hardware and Software Used

[1315] Hardware: Servers, smartphones, tablets, PCs

[1316] Software: Generative AI models, sentiment analysis engines, database management systems

[1317] Using these building blocks and prompts will enable efficient, personalized responses, improving the quality of your recruiting and customer support.

[1318] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1319] Step 1:

[1320] The user logs in to the device and begins entering information. The device inputs and displays a prompt. At this point, the user's input (e.g., an answer to the question, "What kind of job do you want?") is sent to the generative AI model.

[1321] Step 2:

[1322] The server launches the generative AI model and receives the user's answer. The generative AI model analyzes the user's answer and dynamically generates the next required question. The input is the user's answer, and the output is the next question.

[1323] Step 3:

[1324] The server uses a sentiment analysis engine to analyze the emotional state of the user from the answers entered by the user, where the input is the user's answer and the output is emotional data, which is stored in a database.

[1325] Step 4:

[1326] The server matches job seekers with potential employers based on the information and emotional data collected. A generative AI model analyzes the information and scores the match that best meets the criteria. The input is user information and emotional data, and the output is a score for the matching result.

[1327] Step 5:

[1328] The server notifies the job seeker and employer of the matching results. The notification includes a prompt (e.g., "We have found a job posting that matches your criteria"), and when the user presses the "Interview" button, the next step is taken. The input at this time is the matching result, and the output is the notification message.

[1329] Step 6:

[1330] When a user clicks the "Interview" button on the device, the server proposes an appropriate interview time and location based on the user's emotional state. The input is the user's emotional data and schedule information, and the output is an interview proposal.

[1331] Step 7:

[1332] Users (job seekers and employers) conduct interviews and report the results to the server. The server uses an emotion engine to record the emotional state before and after the interview and awards reward points. The inputs are the interview results and emotional data, and the output is reward points.

[1333] Step 8:

[1334] If the interview is not conducted, the server will handle the problem based on the emotion analysis data. Specifically, it will propose appropriate countermeasures, such as imposing a penalty on the hired candidate or refunding reward points to the job seeker. The inputs are the emotion data and the interview results, and the output is the countermeasures.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] [Fourth embodiment]

[1339] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1340] 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.

[1341] 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).

[1342] 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.

[1343] 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.

[1344] 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).

[1345] 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. 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.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] 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.

[1350] 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.

[1351] 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."

[1352] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it uses generative AI to simplify information input, matches job seekers with employers, smoothly arranges interview schedules, awards reward points, and handles problems. This system consists of a server, terminals, and users (employers and job seekers).

[1353] Program processing overview

[1354] Enter information

[1355] The server launches the generative model and obtains the necessary information from the user in the form of a question. For example, the server might ask, "What position are you hiring for?" and the user (employer) might respond, "Sales manager." Or, the server might ask, "Tell me about your past work history," and the user (job seeker) might respond, "I have two years of sales experience." The information collected in this way is stored in a database by the server.

[1356] matching

[1357] The server analyzes the collected information and scores compatibility between job seekers and employers based on their criteria. For example, a generative model performs optimal matching based on information such as the job seeker's skill set, work experience, and preferred work location. A list of highly-scoring job seekers is generated and notified to the employer. Similarly, job openings that match the criteria are notified to the job seeker.

[1358] Notification and confirmation

[1359] When the user receives the notification, they click the "Ask for a meeting" button to indicate their intention to meet. The server confirms this intention and starts the process to coordinate the schedule for both parties.

[1360] First interview and reward

[1361] After the job seeker and employer conduct the first interview, the server confirms the completion of the interview and awards reward points to the job seeker, which can increase the job seeker's motivation.

[1362] Troubleshooting

[1363] If the server does not conduct an interview after a successful match, it will take appropriate action to resolve the issue, such as adding penalty points to the employer's account or providing a refund to the job seeker.

[1364] Specific examples

[1365] Example 1: When the recruiter inputs information

[1366] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[1367] 2. The server generates a question: The server asks a question through the generative model: "Tell me about the position you're hiring."

[1368] 3. The employer responds: "I'm the sales manager," the employer responds.

[1369] 4. Server saves the data: The server saves the answers in a database.

[1370] Example 2: Job seeker receives a match notification

[1371] 1. The server analyzes the conditions: The server analyzes the job seeker's conditions (skill set, location, experience, etc.) and scores them using a generative model.

[1372] 2. The server sends a notification: Based on the list of high-scoring employers, the server notifies the job seeker that "job information matching your criteria has been found."

[1373] 3. The job seeker requests an interview: The job seeker indicates their intention by pressing the "Interview" button.

[1374] As described above, this invention efficiently solves the problems of employers and job seekers through a system that includes a series of processes, such as inputting information in the form of questions using generative AI, matching through condition analysis and scoring, and providing rewards and troubleshooting. This system makes recruitment activities more efficient and reduces costs.

[1375] The processing flow will be explained below.

[1376] Program processing flow

[1377] Information input phase

[1378] Step 1:

[1379] The user logs into the application using a terminal. The server authenticates the account information and displays the main screen if the login is successful.

[1380] Step 2:

[1381] The server invokes the generative model to generate questions for the user (employer or job seeker), such as "What kind of job do you want?"

[1382] Step 3:

[1383] The user enters an answer to the question. If they are an employer, they might answer "sales manager," and if they are a job seeker, they might answer "sales position."

[1384] Step 4:

[1385] The server stores the user's answers in a database, which is used for subsequent analysis and matching.

[1386] Matching Process

[1387] Step 5:

[1388] The server analyzes all the information on job seekers and employers stored in the database. The generative model scores them based on the criteria and finds the optimal combination.

[1389] Step 6:

[1390] The server generates a list of high-scoring job seekers and sends notifications to employers.

[1391] Step 7:

[1392] The server also notifies the job seeker of a list of employers that match their criteria, with a message such as "We've found jobs that match your criteria."

[1393] Notification and confirmation phase

[1394] Step 8:

[1395] The user checks the notification and clicks the "Interview" button. If both the job seeker and the employer click the button, the process proceeds to the next step.

[1396] Step 9:

[1397] The server displays a screen for arranging the interview schedule between the two parties. The user enters the desired date and time.

[1398] Step 10:

[1399] The server will finalize the schedule and notify both parties of the interview details.

[1400] Initial Interview and Reward Phase

[1401] Step 11:

[1402] Users (job seekers and employers) conduct interviews at the specified date and time.

[1403] Step 12:

[1404] After the interview is completed, the server confirms the completion of the interview and gives reward points to the job seeker.

[1405] Troubleshooting phase

[1406] Step 13:

[1407] If an interview is not conducted, the server will recognize it as a problem and take appropriate action, such as giving penalty points to the recruit or refunding reward points to the job seeker.

[1408] The above is the specific processing flow of the system. This flow will enable efficient recruitment activities and solve the problems of small and medium-sized businesses and job seekers.

[1409] Example 1

[1410] 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."

[1411] There is a need for efficient methods to resolve the recruitment issues faced by small and medium-sized businesses and job seekers. Specifically, it is necessary to simplify the information entry process, ensure appropriate matching, smoothly arrange interview schedules, award reward points to motivate job seekers, and deal with problems when interviews are not conducted.

[1412] 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.

[1413] In this invention, the server includes a means for inputting information in the form of questions using a generative AI model, a means for matching job seekers with employers based on collected data, a means for sending a notification to the user and arranging an interview schedule between the job seeker and employer, a means for awarding reward points to the job seeker when the first interview is completed, and a means for dealing with problems when an interview does not take place. This makes recruitment activities more efficient and reduces costs, while also making it possible to improve job seeker motivation and quickly deal with problems when they occur.

[1414] A "generative AI model" is a model that uses artificial intelligence to automatically generate text and data.

[1415] "Information input" is the process by which the system obtains the necessary information from the user.

[1416] A "question format" is a method of gathering information by asking a user a series of questions.

[1417] "Data" means the collection of information provided by the user that the system uses for analysis and matching.

[1418] "Matching" is the process of finding the best match based on the requirements of the job seeker and the employer.

[1419] "User" refers to the employers and job seekers who use the system.

[1420] "Notification" is the act of the system sending information or messages to the user.

[1421] "Scheduling" is the process of setting up an interview date and time between a job seeker and an employer.

[1422] A "first interview" refers to the first meeting between a job seeker and an employer.

[1423] "Reward points" are points that the system awards to job seekers as motivation and reward.

[1424] "Troubleshooting" is the process for resolving problems that arise after a match is made.

[1425] The present invention is a system that uses a generative AI model to solve recruitment issues faced by small and medium-sized businesses and job seekers. Specifically, the system simplifies information input, matches job seekers with potential employers, arranges interview schedules, awards reward points, and handles problems. Detailed embodiments of the present invention are described below.

[1426] System Configuration

[1427] Hardware and Software Configuration

[1428] This system mainly consists of a server, terminals, and users (employers and job seekers).

[1429] Server: Responsible for the primary data processing and execution of generative AI models. For example, the server uses generative AI models such as OpenAI's GPT-3.

[1430] Terminal: A device where a user enters information and checks results. This includes computers, smartphones, tablets, etc.

[1431] Users: Employers and job seekers who use the system.

[1432] Specific examples of hardware use

[1433] The server uses a cloud server equipped with a high-performance processor and large memory capacity.

[1434] The terminal can be any device with a standard internet connection.

[1435] Specific examples of software use

[1436] Generative AI models: Use natural language generation models such as OpenAI's GPT-3.

[1437] Database Management Systems: RDBMS such as MySQL or PostgreSQL are used to store data.

[1438] Front-end: Building the user interface using JavaScript frameworks such as React or Vue.js.

[1439] Process Overview

[1440] The server launches the generative AI model and asks the user questions to obtain the necessary information. The collected information is stored in a database, and the server matches job seekers with employers based on that information. The matching results are sent to the user as a notification, and if the user indicates a desire for an interview, the server arranges the interview schedule. When the interview is completed, the server awards reward points to the job seeker, and if the interview does not take place, it handles any issues.

[1441] Example

[1442] Example 1: When the recruiter inputs information

[1443] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[1444] 2. The server generates a question: Using a generative AI model, the server generates a question such as, "Tell me about the position you're hiring."

[1445] 3. The recruiter answers: "I'm a sales manager."

[1446] 4. Server saves the data: The answers are saved in a database.

[1447] Example 2: When a job seeker receives a match notification

[1448] 1. The server analyzes the conditions: The job seeker's conditions (skill set, work location, experience, etc.) are analyzed using a generative AI model and a score is generated.

[1449] 2. The server sends a notification: "We've found a job that matches your criteria."

[1450] 3. The job seeker requests an interview: The job seeker indicates their intention by pressing the "Interview" button.

[1451] Prompt Sentence Examples

[1452] Here are some example prompts that the generative AI model might use:

[1453] 1. For employers: "Tell me about the position you're hiring."

[1454] 2. For job seekers: "Tell me about your past work experience."

[1455] In this way, the present invention is a system that uses a generative AI model to input information in the form of questions, and then comprehensively performs matching, notification, interview schedule adjustment, reward point allocation, and trouble shooting, thereby streamlining recruitment activities and reducing costs.

[1456] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1457] Program processing flow

[1458] Step 1: Start entering information

[1459] The server launches the generative AI model and obtains the necessary information from the user in the form of questions.

[1460] Specific behavior:

[1461] 1. The server launches a generative AI model: Launch a generative AI model (e.g., OpenAI GPT-3).

[1462] 2. Server generates questions: A generative AI model is used to generate questions, such as "What position are you hiring?"

[1463] 3. User enters information: Employers and job seekers answer questions and enter information.

[1464] 4. Input: Information entered by the user (e.g., position name, work history).

[1465] 5. Output: The information obtained by the server is stored in the server's database.

[1466] Step 2: Analyzing and matching information

[1467] The server analyzes the collected information and uses a generative AI model to score compatibility between job seekers and employers based on their criteria.

[1468] Specific behavior:

[1469] 1. The server collects data: The latest collected information is retrieved from the database.

[1470] 2. The server analyzes using the generative AI model: It runs the analysis algorithm and analyzes the collected information.

[1471] 3. The server performs scoring: A generative AI model is used to score the compatibility between job seekers and employers.

[1472] 4. Input: Job seeker and employer information stored on the server.

[1473] 5. Output: Calculate compatibility scores and generate a list of job seekers with high scores.

[1474] Step 3: Notification of match results

[1475] The server sends a notification to the user based on the matching results.

[1476] Specific behavior:

[1477] 1. Server generates notification content: A generative AI model is used to generate notification content, e.g., "We've found a job posting that matches your criteria."

[1478] 2. The server sends a notification: A notification is sent to the device.

[1479] 3. Users receive notifications: Job seekers and employers receive notifications.

[1480] 4. Input: Generated compatibility scores and a list of high-scoring job seekers.

[1481] 5. Output: Notification message sent to the user.

[1482] Step 4: Schedule an interview

[1483] When the user indicates a desire for an interview, the server arranges the interview schedule.

[1484] Specific behavior:

[1485] 1. User indicates desire for interview: The job seeker presses the "Interview" button.

[1486] 2. The server adjusts the schedules: The schedules of both parties are automatically adjusted and the date and time of the meeting is decided.

[1487] 3. Server sends notification again: Notifies the user of the adjusted schedule.

[1488] 4. Input: Job seeker and hire schedule information.

[1489] 5. Output: Confirmed interview date and time and notification message.

[1490] Step 5: First interview and reward points awarded

[1491] When the first interview is completed, the server awards reward points to the job seeker.

[1492] Specific behavior:

[1493] 1. Confirmation of interview completion: The recruiter presses the "Interview Completed" button.

[1494] 2. The server awards reward points: The server awards reward points to the job seeker and reflects them in the account.

[1495] 3. The server saves the data: The awarded reward points are saved in the database.

[1496] 4. Enter: Confirmation of interview completion.

[1497] 5. Output: Reward points are awarded and stored in the database.

[1498] Step 6: Perform troubleshooting

[1499] If the interview does not take place, the server will take action to troubleshoot.

[1500] Specific behavior:

[1501] 1. The server checks that the interview has not been conducted: It detects that the interview has not been conducted.

[1502] 2. Server assigns penalty: assigns penalty points to the adopter.

[1503] 3. The server processes the refund: The server processes the refund for the job seeker.

[1504] 4. Enter: Confirmation information for unsuccessful interviews.

[1505] 5. Output: Notification of penalty points being awarded and refund completion.

[1506] (Application example 1)

[1507] 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."

[1508] A major challenge for logistics centers is efficiently securing a large workforce. However, many small and medium-sized businesses lack the resources and technology to quickly and efficiently find job seekers, schedule interviews, and ultimately secure labor. This makes the recruitment process cumbersome and time-consuming, making it difficult to find suitable candidates. Scheduling interviews and dealing with issues when interviews are not conducted are also challenges.

[1509] 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.

[1510] In this invention, the server includes means for using a generative model in which information is input in the form of questions, means for matching job seekers with employers based on the collected information, means for arranging interview schedules between job seekers and employers, means for awarding reward points to job seekers when the first interview is completed, means for dealing with problems when the interview does not take place, means for automatically arranging schedules between job seekers and employers using an external service, and means for electronically confirming the completion of interviews. This enables the logistics center to quickly and efficiently secure labor.

[1511] "Means of using a generative model that inputs information in the form of a question" refers to a means of obtaining the necessary information from the user in the form of a question and securing that information using a generative AI model.

[1512] "Means of matching job seekers and employers based on collected information" refers to a means of analyzing collected information on job seekers and employers and appropriately connecting the two based on mutual conditions.

[1513] The "means for coordinating interview schedules between job seekers and employers" is a means for automatically setting the optimal interview date and time, taking into consideration the schedules of both the employer and the job seeker.

[1514] "Means for granting reward points to a job seeker upon completion of the first interview" refers to a means for granting reward points to a job seeker as an incentive after confirming that the first interview has ended.

[1515] "Measures to deal with problems when an interview is not conducted" refers to measures to provide appropriate compensation or penalties to users when an interview is canceled or not conducted.

[1516] "Means for automatically coordinating the schedules of job seekers and employers using external services" refers to means for automatically coordinating the schedules of job seekers and employers using external calendar and schedule management services.

[1517] "Means for confirming completion of interview by electronic means" refers to a means for reliably confirming that the interview has been completed using electronic means, such as scanning a QR code.

[1518] The system embodying this invention is designed to solve the problems of job recruitment efficiency and interviews that employers and job seekers face. This system is composed of a server, terminals, and users.

[1519] Server Roles

[1520] Hardware and software used

[1521] The server uses the following hardware and software:

[1522] Server-side hardware: AWS EC2

[1523] Database: DynamoDB

[1524] Generative AI model: OpenAI GPT-3

[1525] Backend: Node.js, Express

[1526] Communication method: REST API

[1527] Enter information

[1528] The server uses a generative AI model to prompt the user for information in the form of a question, such as "What position are you hiring for?", to which the candidate responds "Sales Manager." This information is stored in DynamoDB via a REST API.

[1529] matching

[1530] Based on the collected information, the generative AI model analyzes and scores the requirements of job seekers and employers. The scoring system makes an appropriate match, and the employer is notified of a list of job seekers with high scores.

[1531] Schedule adjustment

[1532] When a job seeker notifies the company that they wish to interview, the system automatically coordinates the schedules of both parties using the Google Calendar API, efficiently managing the schedules of both the job seeker and the employer through an external service.

[1533] Reward points awarded

[1534] Once the first interview is completed, the job seeker will scan the QR code to confirm the completion of the interview, after which reward points will be automatically awarded to the job seeker.

[1535] Troubleshooting

[1536] If an interview is not conducted, the server will provide appropriate compensation or penalties, such as adding penalty points to the employer's account or providing a refund to the job seeker.

[1537] Device Role

[1538] Hardware and software used

[1539] The terminal uses the following hardware and software:

[1540] Frontend: React Native (smartphone app)

[1541] Enter information

[1542] Users (employers, job seekers) use their devices to answer questions posed by the generative AI model, and this information is sent to the server in real time and stored in DynamoDB.

[1543] Check the schedule

[1544] When the request button is pressed, the appointment is automatically scheduled on the device, and the schedule is synchronized between the device and the server using the Google Calendar API.

[1545] User Roles

[1546] Information input and response

[1547] The user inputs information through a device, answers questions posed by the generative AI model, and performs other operations such as pressing a button to indicate a desire for an interview.

[1548] Conducting interviews

[1549] Once the interview is complete, job seekers confirm completion by scanning a QR code, which automatically awards reward points.

[1550] Specific examples

[1551] Example prompts to be input to the generative AI model:

[1552] (When the recruit logs in)

[1553] "Please tell me about the positions available at the logistics center."

[1554] User Answer: "Warehouse worker"

[1555] "What skills are required for the position?"

[1556] User Answer: "Forklift driving qualification"

[1557] (When job seeker logs in)

[1558] "Tell me about your past work history."

[1559] User Answer: "I have 3 years of warehouse experience."

[1560] "Please tell us where you would like to work."

[1561] User Answer: "Tokyo"

[1562] In this way, a single process is carried out, from inputting information to matching, arranging interview schedules, awarding reward points, and troubleshooting, enabling logistics centers to quickly and efficiently secure labor.

[1563] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1564] Step 1:

[1565] The server launches the generative AI model and generates questions for information input. The questions are sent to the device, and the user (employer or job seeker) enters the answers. The input includes information such as the position being filled and past work history. The server uses the generative AI model to create prompts to generate appropriate questions and presents them to the user. The user's answer data is sent from the device to the server and stored in DynamoDB.

[1566] Step 2:

[1567] The server executes a matching algorithm based on the information collected. First, the server retrieves the job seeker and employer information collected from DynamoDB. Then, it uses a generative AI model to analyze and score the conditions. The input for this step is the job seeker's skill set, work experience, preferred work location, etc., and the output is a compatibility score. A list of high-scoring job seekers is generated and notified to the employer's device.

[1568] Step 3:

[1569] The user (job seeker) receives the notification and presses the "Interview" button. This action registers the interview request. The server retrieves the schedules of the job seeker and employer using the Google Calendar API and automatically adjusts the schedules. The input for this step is the available time of the job seeker and employer, and the output is the adjusted interview date and time. The adjustment result is notified to the terminal.

[1570] Step 4:

[1571] A user (job seeker) attends an interview on the interview date. After completing the interview, the job seeker scans the QR code to report the completion of the interview. The device sends the scanned data to the server, which then confirms the completion of the interview. The input of this step is the scanned data of the QR code, and the output is confirmation of the completion of the interview. After confirmation, reward points are automatically awarded to the job seeker.

[1572] Step 5:

[1573] If the interview is not conducted, the server will automatically execute a troubleshooting process. First, it checks the actions of both parties at the scheduled interview date and time, and if the interview is not conducted, it starts the troubleshooting process. The input of this step is the log of the not conducted interview, and the output is the feedback of compensation or penalty. For example, penalty points are added to the employer's account and a refund is given to the job seeker.

[1574] 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.

[1575] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it uses generative AI to simplify information input, match job seekers with employers, smoothly arrange interview schedules, award reward points, and handle problems. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it is possible to provide more personalized responses. This system consists of a server, terminals, and users (employers and job seekers).

[1576] Program processing overview

[1577] Enter information

[1578] The server launches the generative model and obtains the necessary information from the user in the form of a question. For example, it displays a question such as, "What kind of job do you want?" As the user answers, the server simultaneously uses an emotion engine to analyze the user's emotions and stores this information in a database. For example, if the user is feeling stressed, that information is also recorded.

[1579] matching

[1580] The server analyzes the collected information and scores the compatibility between the job seeker and employer based on their criteria. A generative model evaluates the job seeker's skill set, work experience, preferred work location, etc., and an emotion engine adjusts the score based on the user's emotional state. A list of high-scoring job seekers is generated and notified to the employer. Similarly, job openings that match the criteria are notified to the job seeker. For example, if the job seeker is nervous, a message to ease their tension is sent.

[1581] Notification and confirmation

[1582] The user receives the notification and clicks the "Appoint" button. The server uses an emotion engine to analyze the user's emotional state and suggest an appropriate time and place. For example, if the user is tired, it suggests a time when they can relax.

[1583] First interview and reward

[1584] When users (job seekers and employers) conduct interviews, the server uses an emotion engine to record their emotional states before and after the interview. After the interview is over, the server confirms the completion of the interview and awards reward points to the job seeker. It also provides feedback based on the emotion engine. For example, if the job seeker is satisfied after the interview, this is displayed as feedback.

[1585] Troubleshooting

[1586] If the server does not conduct an interview after a successful match, it uses an emotion engine to analyze the emotional state behind the problem. It then takes appropriate action to resolve the issue, such as assigning penalty points to the hire or refunding reward points to the job seeker. For example, if the user expresses anger or dissatisfaction, the system takes that emotional state into consideration.

[1587] Specific examples

[1588] Example 1: When the recruiter inputs information

[1589] 1. Employee logs in: The employee logs into the application and the server verifies their basic information.

[1590] 2. Server generates question: The server asks a question through the generative model, such as "Tell me about the position you're hiring for." At the same time, the emotion engine checks the emotional state of the recruit.

[1591] 3. Hire responds: "I'm a sales manager," the hire responds. The emotion engine records the hire's stress level.

[1592] 4. Server saves the data: The server saves the answers and emotion data in a database.

[1593] Example 2: Job seeker receives a match notification

[1594] 1. Server analyzes the job seeker's requirements (skill set, location, experience, etc.) and scores them using a generative model. At the same time, the emotion engine evaluates the job seeker's emotional state.

[1595] 2. Server sends notification: Based on the list of high-scoring employers, the server notifies the job seeker that "We have found a job posting that matches your criteria." If the job seeker is nervous, it also sends a relaxing message.

[1596] 3. The job seeker requests an interview: The job seeker clicks the "Interview" button to indicate their intention. The emotion engine analyzes the desired time slot and sends the results to the server.

[1597] As described above, this invention uses generative AI and an emotion engine to solve the problems of employers and job seekers in an efficient and personalized way through a system that includes a series of processes such as inputting information in the form of questions, matching through condition analysis and scoring, scheduling that takes emotions into account, and rewards and troubleshooting. This system makes recruitment activities more efficient and realizes an approach that takes users' emotions into consideration.

[1598] The processing flow will be explained below.

[1599] Program processing flow

[1600] Information input phase

[1601] Step 1:

[1602] The user logs into the application using a terminal. The server authenticates the user's account information and displays the main screen if the login is successful.

[1603] Step 2:

[1604] The server invokes the generative model to generate questions for the user (employer or job seeker), such as "What kind of job do you want?"

[1605] Step 3:

[1606] The user inputs answers to the questions. For example, an employer might answer "sales manager," and a job seeker might answer "sales position." At the same time, the server uses an emotion engine to analyze the user's emotional state and stores that information in the database.

[1607] Step 4:

[1608] The server stores the user's answers and emotion data in a database for the next step.

[1609] Matching Process

[1610] Step 5:

[1611] The server analyzes the information of all job seekers and employers stored in the database and uses a generative model to score them based on the conditions.

[1612] Step 6:

[1613] The emotion engine adjusts the score based on the user's emotional state, for example, appropriately adjusting the score of a job candidate who is stressed.

[1614] Step 7:

[1615] Based on the scoring results, a list of job seekers with high scores is generated, and the server notifies the employer of this list.

[1616] Step 8:

[1617] Similarly, the server notifies the job seeker of a list of employers that match the job search criteria, with the notification including the message "We have found jobs that match your criteria."

[1618] Notification and confirmation phase

[1619] Step 9:

[1620] The user checks the notification and clicks the "Ask for an interview" button in the notification. The server receives this decision and proceeds to the next step.

[1621] Step 10:

[1622] The server uses an emotion engine to analyze the user's emotional state and suggest the best time and place for the interview, for example, suggesting a relaxing time for a tired user.

[1623] Step 11:

[1624] Once the user reviews and agrees to the proposed schedule, the server notifies both parties of the interview details.

[1625] Initial Interview and Reward Phase

[1626] Step 12:

[1627] Users (job seekers and employers) conduct interviews at the specified date and time. The server uses an emotion engine to record the emotional state before and after the interview.

[1628] Step 13:

[1629] After the interview is completed, the server confirms the completion of the interview, awards reward points to the job seeker, and generates feedback based on the emotion engine to provide to the user.

[1630] Troubleshooting phase

[1631] Step 14:

[1632] If no interview is conducted, the server uses an emotion engine to analyze the emotional state behind the trouble.

[1633] Step 15:

[1634] The server then takes appropriate action to resolve the issue, such as assigning penalty points to the recruit or refunding reward points to the job seeker. If the user expresses anger or dissatisfaction, the server takes appropriate action, taking into consideration their emotional state.

[1635] This is the specific processing flow of the system. This flow not only enables efficient recruitment activities and solves the problems of small and medium-sized businesses and job seekers, but also realizes an approach that takes user feelings into full consideration.

[1636] Example 2

[1637] 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."

[1638] Currently, recruitment activities between small and medium-sized businesses and job seekers face several challenges, such as the time-consuming task of inputting information, inaccurate matching, difficulty in arranging interview schedules, and insufficient response to problems when interviews are not conducted.In addition, there is a lack of consideration for user feelings, so there is a need to improve satisfaction throughout the entire recruitment process.

[1639] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for inputting information in the form of a question using a generative AI model, a means for analyzing the user's emotional state using an emotion analysis engine and saving the result together with the information, a means for matching job seekers with employers based on the collected information, a means for sending notifications to the job seeker and employer based on the matching results, a means for arranging interview schedules between the job seeker and employer, a means for awarding reward points to the job seeker when the first interview is completed, and a means for handling problems when the interview does not take place. This makes the entire hiring process more efficient and enables a personalized approach that takes user emotions into consideration.

[1640] A "generative AI model" is an artificial intelligence model that generates questions based on input from users and collects information.

[1641] An "emotion analysis engine" is an engine that analyzes the user's emotional state and optimizes the system's processing and response based on that information.

[1642] A "means for inputting information in the form of a question" is an interface or process for presenting a question to a user and collecting answers.

[1643] The "means for analyzing the user's emotional state and storing it together with the information" is the process of using an emotion analysis engine to collect the user's emotional data and storing it in a database together with the answers to the questions.

[1644] "Means of matching job seekers and employers based on collected information" refers to the process of analyzing collected data and comparing the conditions of job seekers and employers to make the best match.

[1645] The "means for sending notifications to job seekers and employers based on the matching results" refers to a communication process for notifying users of the matching results.

[1646] "Method of coordinating interview schedules between job seekers and employers" is the process for coordinating the date, time, and location of an interview.

[1647] "Means for awarding reward points to job seekers upon completion of the first interview" refers to the process of confirming the completion of the interview and awarding points to job seekers as an incentive.

[1648] "Measures for implementing troubleshooting measures when an interview is not conducted" refers to the process for analyzing the cause and taking appropriate measures when a scheduled interview is not conducted.

[1649] This invention is a system for solving recruitment issues for small and medium-sized businesses and job seekers. Specifically, it simplifies information input using a generative AI model and a sentiment analysis engine, and matches job seekers with employers, arranges interview schedules, awards reward points, and handles problems. This system consists of a server, terminals, and users (employers and job seekers).

[1650] First, the user logs in to the system via a terminal. The login information is authenticated on the server side, and the user begins using the system. The server then activates a generative AI model to present a question to the user. This prompt might include, for example, "What kind of job do you want?" The server also activates an emotion analysis engine to check the user's emotional state.

[1651] When a user answers a question from the server using a terminal, for example by entering "I'm an engineer," the emotion analysis engine detects the user's stress level and simultaneously collects that data. The server stores these responses and emotion data in a database, and then aggregates the information needed for the next processing step.

[1652] The server then analyzes the information stored in the database and uses a generative AI model to appropriately evaluate the job seeker's skill set, work experience, preferred location, etc. The sentiment analysis engine then takes into account the emotional data analyzed and adjusts the scoring to ensure optimal matching.

[1653] The server generates a compatibility score based on the data of job seekers and employers, and creates a list of job seekers with high scores. This list is notified to employers, and at the same time, job information that matches the job seeker's criteria is also notified to the job seeker. For example, if the job seeker is nervous, a message to calm them down is also sent.

[1654] Upon receiving the notification, the user clicks the "Consult" button on their device to notify the server of their request for a consultation. At this time, the emotion analysis engine analyzes the user's emotional state and sends this information to the server as a suggestion for the optimal consultation time. The server then takes the user's emotional state into consideration and suggests an appropriate time and place. For example, if the user is tired, it will suggest a time when they would be able to relax.

[1655] When the job seeker and employer conduct the interview at the agreed time, the server uses a sentiment analysis engine to record the job seeker's emotional state before and after the interview. After the interview is over, the server confirms the completion of the interview and awards reward points to the job seeker. These points are recorded in a database and can be used at a later date. Feedback is also provided based on the sentiment analysis engine. For example, if the job seeker is highly satisfied with the interview, this information is displayed as feedback.

[1656] If a scheduled interview does not take place, the server will detect this. The emotion analysis engine will analyze the user's emotional state and infer the cause of the problem. Appropriate measures will be taken to resolve the issue, such as assigning penalty points to the hired candidate and refunding reward points to the job seeker. For example, if the user is feeling dissatisfied or angry, the system will take their emotional state into consideration.

[1657] In this way, the system of the present invention uses a generative AI model and a sentiment analysis engine to streamline the entire recruitment process and provide a personalized approach that takes user emotions into consideration. For example, when a recruiter inputs information, the prompt "Tell us about the position you are hiring for" is presented, and the recruit replies "Sales Manager," and emotional data is also collected.

[1658] Furthermore, when a job seeker receives a matching notification, they will be notified that "We have found a job posting that matches your criteria," and if they are feeling nervous, they will also be sent a relaxing message. When a job seeker indicates their intention by pressing the "Interview" button, the sentiment analysis engine analyzes their desired time slot and sends the result to the server, which then suggests the optimal time for the interview.

[1659] The above functions will make recruitment activities more efficient and enable an approach that takes users' emotions into consideration.

[1660] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1661] Step 1: User logs into the system

[1662] Input: The user enters login information (username and password) into the terminal.

[1663] How it works: The device sends login information to the server, which authenticates it and retrieves the user's profile information from a database.

[1664] Output: The server verifies the user's login and redirects them to a screen to enter their information.

[1665] Step 2: Server generates a question

[1666] Input: User is logged in.

[1667] How it works: The server launches the generative AI model to generate a question prompt to be displayed to the user. For example, it creates a prompt sentence such as, "What kind of job do you want?". It also launches an emotion analysis engine to analyze the user's initial emotional state.

[1668] Output: The generated question is displayed on the terminal, and the emotion data is kept as the initial state.

[1669] Step 3: User Enters Information

[1670] Input: The user answers the server's questions through the terminal. For example, the user enters "I'm an engineer."

[1671] Operation: The device sends user input data to the server, which uses an emotion analysis engine to analyze the user's emotional state (e.g., stress level) during the response.

[1672] Output: The server stores the user's response data and emotion data in a database.

[1673] Step 4: The server parses the information

[1674] Input: User response data and emotion data stored in a database.

[1675] How it works: The server uses the generated AI model to analyze skillsets, work experience, preferred work location, etc. At the same time, the sentiment analysis engine generates a sentiment score from the user's emotional data.

[1676] Output: The analysis results and sentiment scores are stored in a database, which is used for the subsequent matching process.

[1677] Step 5: Server generates compatibility score

[1678] Input: Parsed job candidate data and employer requirements data.

[1679] How it works: The server uses the generative AI model to generate a compatibility score based on the job seeker and employer criteria, and also takes into account the sentiment score from the sentiment analysis engine to calculate an overall compatibility score.

[1680] Output: The compatibility scores between job seekers and employers are stored in a database.

[1681] Step 6: The server sends a notification

[1682] Input: Generated compatibility scores and matching results.

[1683] How it works: The server creates a list of high-scoring job seekers and sends a notification to the employer. At the same time, job seekers are also notified of job postings that match their criteria. For example, a message may be sent to job seekers saying, "We've found a job posting that matches your criteria."

[1684] Output: A notification will be displayed on the employer and job seeker's devices.

[1685] Step 7: User confirms notification

[1686] Input: The user who received the notification (job seeker or employer).

[1687] How it works: The user checks the notification via their device. If the job seeker is nervous, the system also displays a message encouraging them to relax.

[1688] Output: The user confirms the notification and is ready to proceed to the next step.

[1689] Step 8: User selects appointment preference

[1690] Input: The user (job seeker or employer) who confirmed the notification.

[1691] How it works: The job seeker clicks the "Schedule an Interview" button to indicate their intention. The emotion analysis engine analyzes the user's emotional state and determines the desired interview time slot.

[1692] Output: The user's interview preference data and emotion data are sent to the server.

[1693] Step 9: Server suggests a meeting time

[1694] Input: User's interview preference data and emotion data.

[1695] How it works: The server uses an emotion analysis engine to suggest a time for a meeting that matches the user's emotional state. For example, if the user is tired, it will suggest a time when they are likely to relax.

[1696] Output: The server informs the user of the best time and place for the meeting.

[1697] Step 10: User conducts interview

[1698] Input: The interview time and location have been determined.

[1699] How it works: Job seekers and employers conduct interviews at designated times and locations. The server monitors the progress of the interviews in real time.

[1700] Output: The information about the completed interview is recorded on the server.

[1701] Step 11: Server confirms interview completion

[1702] Input: Interview completion information.

[1703] How it works: The server uses an emotion analysis engine to record the emotional state before and after the interview and to confirm the completion of the interview.

[1704] Output: Interview completion information and emotion data are saved in the database.

[1705] Step 12: Server awards reward points

[1706] Input: Interview completion information.

[1707] Operation: The server awards reward points to job seekers and records the points in a database.

[1708] Output: Reward points are reflected in the job seeker's account.

[1709] Step 13: The server detects that the interview has not been conducted.

[1710] Input: Information on interviews that have not been conducted after the scheduled interview time has passed.

[1711] How it works: The server detects that the interview was not conducted. The emotion analysis engine analyzes the user's emotional state and infers the cause of the problem.

[1712] Output: Uninterviewed information and emotional data are recorded in a database.

[1713] Step 14: Server Troubleshooting

[1714] Input: Uninterviewed information and emotional data.

[1715] Operation: The server takes appropriate action depending on the cause of the problem. For example, it assigns penalty points to the employer and refunds reward points to the job seeker.

[1716] Output: Changes in penalty points and reward points are reflected in the database.

[1717] Through these processing steps, the system can streamline the entire recruitment process and provide a personalized approach that takes into account the user's emotions.

[1718] (Application example 2)

[1719] 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."

[1720] Current recruitment processes and customer support systems lack efficiency in information entry, matching, scheduling, and troubleshooting. This often leaves small and medium-sized businesses, job seekers, and online shopping site customers feeling stressed and frustrated. Furthermore, the lack of a system that analyzes and responds to emotional states makes it difficult to provide personalized support. There is an urgent need to resolve these issues and provide efficient, emotionally sensitive support.

[1721] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1722] In this invention, the server includes means for using a generative model in which information is input in the form of questions, means for matching job seekers with employers based on the collected information, means for arranging interview schedules between job seekers and employers, means for awarding reward points to job seekers when the first interview is completed, means for handling problems when the interview does not take place, means for analyzing the emotional state of a user using emotion analysis means and taking appropriate action based on the data, means for analyzing customer inquiries in customer support for an online shopping site and proposing appropriate solutions, and means for providing reward points according to customer satisfaction based on the emotion analysis means. This enables more efficient recruitment activities and customer support, and personalized responses that take emotions into consideration.

[1723] The "information input" means the process by which a user provides information to the system in the form of a question.

[1724] A "generative model" refers to a system that uses AI technology to automatically generate questions and answers.

[1725] "Collected Information" refers to data entered by users or data automatically obtained by the system.

[1726] "Matching means" refers to the function of analyzing the conditions of job seekers and employers based on collected information and finding the optimal combination.

[1727] "Schedule adjustment means" refers to a function that automatically suggests and sets interview dates and times between job seekers and employers.

[1728] "Reward points" refer to points given to users as an incentive.

[1729] "Troubleshooting measures" refers to the function of taking measures when an interview is not conducted or other problems arise.

[1730] "Sentiment analysis means" refers to the function of analyzing emotions from a user's text or voice and adjusting the response based on the results.

[1731] "Customer inquiry" refers to the act of users of an online shopping site entering problems or questions they have into the system.

[1732] "Solution proposal means" refers to a function that automatically generates an appropriate solution based on the customer's inquiry.

[1733] "Customer satisfaction" refers to an indicator that measures the degree to which customers are satisfied with the services and solutions provided.

[1734] The embodiment of this invention is a system for solving recruitment issues faced by small and medium-sized businesses and job seekers. This system uses a generative AI model and sentiment analysis means to simplify information input, match job seekers with potential employers, smoothly schedule interviews, award reward points, and handle problems. Furthermore, the system can also be applied to customer support for online shopping sites, proposing appropriate solutions to customer inquiries and awarding reward points.

[1735] 1. Basic configuration

[1736] This system consists of a server, a terminal, and a user. The server runs a generative AI model and analyzes the user's emotional state using a sentiment analysis engine. Terminals can include smartphones, tablets, and PCs.

[1737] 2. Enter information

[1738] When a user logs in using a device, the server activates the generative AI model and collects information in the form of questions. For example, a question such as "What kind of job do you want?" is displayed, and as the user answers, the emotion engine analyzes the user's emotional state. As a result, if the user is nervous, for example, that information is stored in the database.

[1739] Specific examples

[1740] Example prompt: "Tell me more about your problem."

[1741] 3. Matching and Analysis

[1742] Based on the collected information, the server uses a generative AI model to analyze the requirements of job seekers and employers and generate scores. At the same time, an emotion engine evaluates the user's emotional state and adjusts the scoring, enabling more appropriate matching.

[1743] Specific examples

[1744] Example prompt: "We found a job posting that matches your criteria."

[1745] 4. Notice and Confirmation

[1746] Once a match is found, the server sends a notification and the user clicks the "Appoint" button to schedule the interview. The system uses an emotion engine to suggest a time and location that takes into account the user's emotional state.

[1747] Specific examples

[1748] Example prompt: "Please suggest a suitable time for the interview."

[1749] 5. Follow-up and rewards

[1750] When a user completes an interview or problem-solving follow-up, the server uses an emotion engine to record their emotional state and awards reward points. Depending on the user's satisfaction, further personalized messages are sent.

[1751] Specific examples

[1752] Example prompt: "Were you satisfied with our service?"

[1753] Hardware and Software Used

[1754] Hardware: Servers, smartphones, tablets, PCs

[1755] Software: Generative AI models, sentiment analysis engines, database management systems

[1756] Using these building blocks and prompts will enable efficient, personalized responses, improving the quality of your recruiting and customer support.

[1757] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1758] Step 1:

[1759] The user logs in to the device and begins entering information. The device inputs and displays a prompt. At this point, the user's input (e.g., an answer to the question, "What kind of job do you want?") is sent to the generative AI model.

[1760] Step 2:

[1761] The server launches the generative AI model and receives the user's answer. The generative AI model analyzes the user's answer and dynamically generates the next required question. The input is the user's answer, and the output is the next question.

[1762] Step 3:

[1763] The server uses a sentiment analysis engine to analyze the emotional state of the user from the answers entered by the user, where the input is the user's answer and the output is emotional data, which is stored in a database.

[1764] Step 4:

[1765] The server matches job seekers with potential employers based on the information and emotional data collected. A generative AI model analyzes the information and scores the match that best meets the criteria. The input is user information and emotional data, and the output is a score for the matching result.

[1766] Step 5:

[1767] The server notifies the job seeker and employer of the matching results. The notification includes a prompt (e.g., "We have found a job posting that matches your criteria"), and when the user presses the "Interview" button, the next step is taken. The input at this time is the matching result, and the output is the notification message.

[1768] Step 6:

[1769] When a user clicks the "Interview" button on the device, the server proposes an appropriate interview time and location based on the user's emotional state. The input is the user's emotional data and schedule information, and the output is an interview proposal.

[1770] Step 7:

[1771] Users (job seekers and employers) conduct interviews and report the results to the server. The server uses an emotion engine to record the emotional state before and after the interview and awards reward points. The inputs are the interview results and emotional data, and the output is reward points.

[1772] Step 8:

[1773] If the interview is not conducted, the server will handle the problem based on the emotion analysis data. Specifically, it will propose appropriate countermeasures, such as imposing a penalty on the hired candidate or refunding reward points to the job seeker. The inputs are the emotion data and the interview results, and the output is the countermeasures.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] 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.

[1779] 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.

[1780] 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).

[1781] 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.

[1782] 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."

[1783] 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.

[1784] 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).

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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.

[1790] 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.

[1791] 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.

[1792] 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.

[1793] 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.

[1794] 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.

[1795] The following is further disclosed regarding the above embodiment.

[1796] (Claim 1)

[1797] A means for using a generative model in which information is input in the form of a question;

[1798] A means of matching job seekers with employers based on the collected information,

[1799] A means of coordinating interview schedules between job seekers and employers;

[1800] A means of awarding job seekers reward points upon completion of the first interview;

[1801] How to handle issues if an interview does not take place, and

[1802] A system including:

[1803] (Claim 2)

[1804] 10. The system of claim 1, further comprising means for using a generative model to analyze and score requirements of job seekers and employers.

[1805] (Claim 3)

[1806] 2. The system according to claim 1, further comprising means for performing an operation for the job seeker and the employer to meet based on the notification.

[1807] "Example 1"

[1808] (Claim 1)

[1809] A means for inputting information in the form of questions using a generative AI model;

[1810] A means of matching job seekers with employers based on the collected data,

[1811] a means for sending notifications to users and coordinating interview schedules between job seekers and employers;

[1812] A means of awarding job seekers reward points upon completion of the first interview;

[1813] How to handle issues if an interview does not take place, and

[1814] A system including:

[1815] (Claim 2)

[1816] 10. The system of claim 1, further comprising means for using a generative AI model to analyze and score job seeker and employer requirements.

[1817] (Claim 3)

[1818] 2. The system according to claim 1, further comprising means for performing an operation for the job seeker and the employer to meet based on the notification.

[1819] "Application Example 1"

[1820] (Claim 1)

[1821] A means for using a generative model in which information is input in the form of a question;

[1822] A means of matching job seekers with employers based on the collected information,

[1823] A means of coordinating interview schedules between job seekers and employers;

[1824] A means of awarding job seekers reward points upon completion of the first interview;

[1825] How to handle issues if an interview does not take place, and

[1826] A means to automatically coordinate the schedules of job seekers and employers using external services,

[1827] A means of electronically confirming the completion of the interview;

[1828] A system including:

[1829] (Claim 2)

[1830] 10. The system of claim 1, further comprising means for using a generative model to analyze and score requirements of job seekers and employers.

[1831] (Claim 3)

[1832] 2. The system according to claim 1, further comprising means for performing an operation for the job seeker and the employer to meet based on the notification.

[1833] "Example 2: Combining Emotion Engines"

[1834] (Claim 1)

[1835] A means of inputting information in the form of questions using a generative AI model;

[1836] means for analyzing the user's emotional state using an emotion analysis engine and storing the information together with the emotional state;

[1837] A means of matching job seekers with employers based on the collected information,

[1838] a means for sending notifications to job seekers and employers based on the matching results;

[1839] A means of coordinating interview schedules between job seekers and employers;

[1840] A means of awarding job seekers reward points upon completion of the first interview;

[1841] How to handle issues if an interview does not take place, and

[1842] A system including:

[1843] (Claim 2)

[1844] The system of claim 1, further comprising means for using a generative AI model to analyze the collected information and score the requirements of job seekers and employers to perform matching.

[1845] (Claim 3)

[1846] 2. The system according to claim 1, further comprising means for performing an operation for the job seeker and the employer to meet based on the notification.

[1847] "Application example 2 when combining emotion engines"

[1848] (Claim 1)

[1849] A means for using a generative model in which information is input in the form of a question;

[1850] A means of matching job seekers with employers based on the collected information,

[1851] A means of coordinating interview schedules between job seekers and employers;

[1852] A means of awarding job seekers reward points upon completion of the first interview;

[1853] How to handle issues if an interview does not take place, and

[1854] a means for analyzing the user's emotional state using a sentiment analysis means and taking appropriate action based on that data;

[1855] In customer support for online shopping sites, a means of analyzing customer inquiries and proposing appropriate solutions,

[1856] means for providing reward points according to customer satisfaction based on the sentiment analysis means;

[1857] A system including:

[1858] (Claim 2)

[1859] 10. The system of claim 1, further comprising means for using a generative model to analyze and score requirements of job seekers and employers.

[1860] (Claim 3)

[1861] 2. The system according to claim 1, further comprising means for performing an operation for the job seeker and the employer to meet based on the notification. [Explanation of symbols]

[1862] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for using a generative model in which information is input in the form of a question; A means of matching job seekers with employers based on the collected information, A means of coordinating interview schedules between job seekers and employers; A means of awarding job seekers reward points upon completion of the first interview; How to handle issues if an interview does not take place, and A system including:

2. 10. The system of claim 1, further comprising means for using generative models to analyze and score requirements of job seekers and employers.

3. 2. The system according to claim 1, further comprising means for performing an operation for the job seeker and the employer to interview based on the notification.

Images