System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting questionnaire response information related to a task desired by a graduate and an existing employee; means for transmitting the questionnaire response information to a server; means for preprocessing the collected questionnaire response information and converting the questionnaire response information into a format suitable for analysis; means for inputting the preprocessed information into a generative AI model and generating a task proposal; means for evaluating the generated task proposal and selecting an appropriate proposal; means for presenting the selected task proposal to a user; and means for storing the user's selection in the server.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] New graduates and existing employees are not assigned to work that suits them within a company, resulting in a mismatch in work content, leading to early retirement and a decline in motivation. As a result, companies face challenges in securing and developing long-term human resources. Existing employees also face the problem of difficulty finding the perfect transfer destination when they wish to advance their careers or transfer. A system is needed to resolve these mismatches and support employees so that they can thrive at a company in the long term. [Means for solving the problem]

[0005] The present invention provides a system that solves the above problems by the following means.

[0006] First, the system has a means for collecting survey response data regarding the work desired by new graduates and existing employees. Next, it has a means for transmitting the survey response data to a server. It has a means for preprocessing the collected survey response data and converting it into a format suitable for analysis, and a means for inputting the preprocessed data into a generative AI model to generate work proposals. It also has a means for evaluating the generated work proposals and selecting appropriate proposals, and a means for presenting the selected work proposals to the user. Finally, the system includes a means for saving the user's selections on the server.

[0007] In addition, the system is provided with a means for collecting questionnaire response data based on existing employees' transfer preferences, thereby generating internship exam proposals and presenting them to the user. It also has a means for collecting feedback data during the internship period, and includes a means for analyzing the collected feedback data and generating a final transfer proposal. Furthermore, by including a means for displaying the generated work proposals and transfer proposals on a user interface and a means for updating the career plan to reflect the work or transfer destination selected by the user, the system provides a support system that places employees in work that suits them and enables them to contribute to the company over the long term.

[0008] "Questionnaire response data" refers to data including information about questions about work answered by new graduates and existing employees based on their own preferences and aptitudes.

[0009] A "generative AI model" is an artificial intelligence model equipped with an algorithm that analyzes data and generates optimal business proposals based on collected survey response data.

[0010] "Preprocessing" refers to a series of processes such as data cleansing, normalization, and tokenization to convert collected questionnaire response data into a format suitable for analysis.

[0011] "Job proposals" are proposed information regarding the most suitable jobs and departments presented to new graduates and existing employees based on the results of analysis by the generative AI model.

[0012] An "internship exam proposal" is a proposal for existing employees who wish to transfer to a new department or job on a trial basis.

[0013] "Feedback data" refers to data that includes evaluations and opinions of existing employees collected during the internship period.

[0014] A "user interface" is a screen or GUI (graphical user interface) that allows a user to operate a system or visually check information.

[0015] A "career plan" is a plan for employees to plan how they will build their careers through their work and experiences within the company.

[0016] "Server" is a computer system for storing and analyzing collected data and processing generated business proposals.

[0017] A "terminal" is a device such as a PC or smartphone that a user uses to access the system and answer questionnaires or confirm business proposals. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, and a user interface.

[0040] System operation and program processing

[0041] 1. Survey collection

[0042] User: A new graduate or existing employee logs into the system and accesses the designated survey page.

[0043] Terminal: The user answers the questions in the survey and presses the send button to send the answer data to the server. Examples of questions include "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[0044] Example: Mr. Tanaka says he is interested in sales and marketing positions and notes that he has prior sales experience.

[0045] 2. Data reception and preparation for analysis

[0046] Server: Receives the survey response data and stores it in a database.

[0047] Server: Cleanses and normalizes the received data, and converts text data into a format suitable for analysis by tokenizing it, for example. For example, it converts the contents of a survey into specific keywords so that the model can easily understand them.

[0048] 3. Data analysis and business proposal generation

[0049] Server: The preprocessed data is input into a generative AI model (such as GPT-3) to generate optimal job suggestions. The model outputs multiple job suggestions based on the user's preferences and aptitude.

[0050] Server: Evaluates the generated job proposals and selects the most appropriate one. For example, "sales position" and "marketing position" are selected from the generated proposals.

[0051] 4. Presentation of business proposal

[0052] Server: Generates the selected business proposals in JSON format and sends them to the user's device.

[0053] Terminal: Parses the JSON data sent and displays it in the user interface. The user can then review and select the business proposals presented.

[0054] Example: Tanaka's screen shows the suggestions "Sales" and "Marketing", and she chooses Sales.

[0055] 5. Propose an internship test and collect feedback

[0056] Server: For existing employees, the server analyzes the questionnaire responses based on their transfer preferences and generates and presents internship proposals. It also includes a function to collect feedback data during the internship period.

[0057] Example: Mr. Sato wants to transfer to the marketing department and will take an internship exam. After the internship period ends, Mr. Sato will submit his opinion through the feedback form.

[0058] 6. Generate and present the final transfer proposal

[0059] Server: After the internship ends, the collected feedback data is analyzed and a final transfer proposal is generated. The generated proposal is sent to the user's device and displayed on the user interface.

[0060] Example: After analyzing Sato's feedback, it is determined that a formal transfer to the Marketing department is appropriate, and a final proposal is made.

[0061] Example of a system

[0062] Example 1: Tanaka-san (new graduate):

[0063] In the survey, he indicated that he wanted to work in "sales" and "marketing" and that he had previous experience in sales work.

[0064] The server analyzes the data and generates suggestions for "sales jobs" and "marketing jobs."

[0065] Tanaka chooses "sales" and this is reflected in his career plan.

[0066] Example 2: Sato-san (existing employee):

[0067] In the survey, I expressed a desire to be transferred to the marketing department.

[0068] I accepted the internship offer and experienced working in the marketing department for one month.

[0069] After completing the course, he provided feedback and was eventually offered a permanent transfer to the Marketing department, which he accepted.

[0070] This system allows new graduates and existing employees to be assigned to tasks that best suit them, reducing job mismatches and supporting long-term career development within the company.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] User: New graduates or existing employees log in to the system and access the survey page. To log in, they must enter their user ID and password.

[0074] Terminal: Sends the login information entered by the user to the server.

[0075] Step 2:

[0076] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[0077] On the device: After successful authentication, the survey page is displayed to the user.

[0078] Step 3:

[0079] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[0080] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[0081] Step 4:

[0082] Server: Receives the survey response data and stores it in the database using an INSERT query.

[0083] Server: Preprocesses the received data and converts it into a format suitable for analysis by performing text normalization, tokenization, etc.

[0084] Step 5:

[0085] Server: Inputs the preprocessed data into the generative AI model, which receives the data via an API.

[0086] Server: The generative AI model generates business proposals and returns the results to the server.

[0087] Step 6:

[0088] Server: Evaluates the generated business proposals and selects the most appropriate one. The proposals are scored and the one with the highest score is selected.

[0089] Server: Generates the selected business proposals in JSON format.

[0090] Step 7:

[0091] Server: The generated JSON data is sent to the user's device as a REST API response.

[0092] Step 8:

[0093] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[0094] User: Review the proposed work and select the work they wish to do.

[0095] Step 9:

[0096] Terminal: Sends the user's selection to the server.

[0097] Server: Receives the selections and stores them in the database, updating the user's career plan.

[0098] Step 10:

[0099] Server: For existing employees, a means is provided to collect questionnaire response data based on transfer preferences and generate internship trial proposals. Proposals for internship trials are generated and displayed on the user interface as well.

[0100] User: Confirms and accepts the internship attempt and also completes and submits feedback during the internship period.

[0101] Step 11:

[0102] Server: After the internship ends, analyze the collected feedback data and generate a final transfer proposal.

[0103] Server: Sends the final proposal to the user and displays it in the user interface.

[0104] Step 12:

[0105] User: Review the final proposal and choose whether to accept it.

[0106] The above is the specific processing flow of the "JoB Match GPT" system.

[0107] Example 1

[0108] 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."

[0109] Modern companies require both new graduates and existing employees to be assigned to the most appropriate jobs based on their preferences and aptitudes. However, traditional manual job assignment methods are prone to mismatches and are labor-intensive and time-consuming, so a system that efficiently and effectively proposes jobs is needed. Furthermore, there is a lack of effective methods for proposing internships based on employee transfer requests and for collecting and analyzing subsequent feedback. This makes it difficult to optimize transfers and career plans, and to support long-term career development within the company.

[0110] 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.

[0111] In this invention, the server includes means for cleansing and normalizing survey data, means for tokenizing the data and converting it into a format suitable for analysis, means for sending the generated job proposals to the user's device in JSON format and displaying them on a user interface, means for preprocessing the survey response data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate job proposals, means for evaluating the generated job proposals and selecting an appropriate proposal, means for presenting the selected job proposal to the user, and means for saving the user's selections on the server. This makes it possible to efficiently collect and analyze data on the jobs desired by new graduates and existing employees, and to generate and present optimal job proposals and transfer proposals. This reduces job mismatches and supports long-term career development within the company.

[0112] "Survey response data" refers to data that includes information provided by new graduates and existing employees regarding the work they would like to do.

[0113] A "server" is a computer system that receives, stores, analyzes, and generates proposals from survey response data.

[0114] "Preprocessing" refers to the process of cleansing, normalizing, and converting collected survey response data into a format suitable for analysis.

[0115] A "generative AI model" is an artificial intelligence model used to analyze survey response data and generate business proposals.

[0116] "Business proposals" are optimal business operations proposed by the generative AI model based on the user's wishes and aptitude.

[0117] An "internship exam" refers to a trial period during which existing employees gain experience in the work they wish to transfer to.

[0118] "Feedback data" refers to data that includes the opinions and impressions of existing employees, collected during the internship test period.

[0119] "User interface" refers to the screen and operating environment through which users operate the system and confirm business proposals and internship exam proposals.

[0120] "Cleansing" is the process of removing duplicates and errors from survey response data and organizing the data.

[0121] "Normalization" is the process of standardizing the format of survey response data and converting it into a form suitable for analysis.

[0122] "Tokenization" is the process of breaking down text data into words and phrases, making it easier to analyze.

[0123] "JSON format" is a data format used to structure data and send it to a user's device.

[0124] A "user terminal" is a device such as a computer or smartphone that a user uses to access the system and respond to business proposals and questionnaires.

[0125] MODE FOR CARRYING OUT THE INVENTION

[0126] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, and a user interface.

[0127] Survey collection

[0128] Users log in to the system as new graduates or existing employees. A dedicated ID and password are used to log in. After logging in, they are redirected to a survey page where they answer specified questions. For example, questions include "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?" After the user has finished answering, they press the send button to send the survey response data to the server.

[0129] Data reception and preparation for analysis

[0130] The server receives the survey response data sent by users and stores it in a database. Next, the data is cleansed (removing duplicates and errors) and normalized (standardizing the format). Furthermore, the text data is tokenized and converted into a format that can be analyzed by a generative AI model (e.g., GPT-3).

[0131] Data analysis and business proposal generation

[0132] The server inputs the preprocessed data into the generative AI model to generate the optimal job proposal. For example, the prompt statement could be "Please generate the optimal job proposal for Tanaka. Tanaka has experience in sales and marketing." Based on this prompt, the generative AI model outputs job proposals such as "sales position" and "marketing position." The multiple job proposals generated are evaluated, and the most appropriate proposal is selected.

[0133] Presenting business proposals

[0134] The server generates the selected business proposals in JSON format and sends them to the user's device. The device parses the received JSON data and displays it on the user interface, allowing the user to check and select from the presented business proposals.

[0135] Internship test proposal and feedback collection

[0136] The system analyzes questionnaire responses from existing employees based on their transfer preferences and generates internship exam proposals. The server stores and analyzes feedback data collected during the internship period. For example, if Mr. Sato requests a transfer to the marketing department, he takes the internship exam and submits his feedback after completing it.

[0137] Generate and present the final transfer proposal

[0138] The server analyzes the collected feedback data after the internship period and generates a final transfer proposal, which is sent to the user's device and displayed on the user interface.

[0139] Specific examples

[0140] Example 1: Mr. Tanaka, a new graduate

[0141] In the questionnaire, Tanaka indicated that he would like to work in "sales" and "marketing" and that he has experience in sales work.

[0142] The server analyzes this and generates job proposals for "sales positions" and "marketing positions."

[0143] Tanaka chose a sales position, which is reflected in his career plan.

[0144] Example 2: Existing employee Sato

[0145] In the survey, Sato expressed a desire to be transferred to the marketing department.

[0146] He accepted the internship offer and gained experience working in the marketing department for one month.

[0147] After completing the internship, the employee submits feedback, which is then analyzed by the server, who then makes a formal proposal for transfer to the marketing department.

[0148] This system allows new graduates and existing employees to be assigned to jobs that best suit them, reducing job mismatches and supporting long-term career development within the company.

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Program processing flow

[0151] Step 1: Survey collection

[0152] 1. A user logs into the system

[0153] Input: User ID and password

[0154] Output: The user is redirected to the survey page after successful login.

[0155] Specific operation: The user enters their ID and password and clicks the login button. For example, Mr. Tanaka logs in by entering his ID "tanaka123" and password.

[0156] 2. Visit the survey page and answer the questions

[0157] Input: User's survey response

[0158] Output: User survey response data

[0159] Specific operation: The user answers the survey questions and presses the submit button. For example, Mr. Tanaka answers that he is interested in "sales and marketing positions" and has experience in sales work.

[0160] 3. Send the survey response data to the server

[0161] Input: User survey response data

[0162] Output: Survey data sent to the server

[0163] Specific operation: The user clicks the send button and the survey data is sent to the server. For example, Tanaka's survey data is recorded in the server's database.

[0164] Step 2: Receive data and prepare for analysis

[0165] 1. Receive survey response data

[0166] Input: Survey data sent to the server

[0167] Output: Survey data stored in a database

[0168] Specific operation: The server receives the survey data and stores it in a database. For example, Tanaka's survey response data is recorded in the database.

[0169] 2. Cleanse and normalize the data

[0170] Input: Survey data in the database

[0171] Output: Cleansed and normalized data

[0172] What it does: The server removes duplicates and errors from data and standardizes formats. For example, it automatically corrects data inconsistencies like "Tanaka" and "Tanaka."

[0173] 3. Tokenize the data

[0174] Input: Cleansed and normalized data

[0175] Output: Tokenized data

[0176] Specific operation: Text data is divided into words and phrases and converted into a format that can be understood by the generative AI model. For example, keywords such as "sales job" and "sales work" are tokenized.

[0177] Step 3: Data analysis and business proposal generation

[0178] 1. Feed preprocessed data into a generative AI model

[0179] Input: Tokenized data

[0180] Output: Multiple business proposals

[0181] Specific operation: The cleansed and normalized data is input into a generative AI model (e.g., GPT-3). The prompt sentence is "Please generate the optimal business proposal for Mr. Tanaka. Mr. Tanaka has experience in sales and marketing."

[0182] 2. Generate optimal business proposals

[0183] Input: Output data from a generative AI model

[0184] Output: Multiple business proposals

[0185] Specific operation: The server receives the job proposals generated by the generative AI model. For example, job proposals for "sales positions" and "marketing positions" are output.

[0186] 3. Evaluate and select the generated business proposals

[0187] Input: Generated business proposal

[0188] Output: Selected business proposals

[0189] Specific operation: The server evaluates job proposals based on multiple evaluation criteria and selects the most appropriate proposal. For example, "sales position" and "marketing position" are evaluated and selected as the most suitable.

[0190] Step 4: Present the business proposal

[0191] 1. Generate a business proposal in JSON format

[0192] Input: Selected business proposal

[0193] Output: JSON format data

[0194] Specific operation: The selected job proposals are generated in JSON format and sent to the user's device. For example, proposals for "sales positions" and "marketing positions" are generated as JSON format data.

[0195] 2. Parse and display the proposal data on the device

[0196] Input: JSON format data

[0197] Output: Data displayed in the user interface

[0198] Specific operation: The device parses the received JSON data and displays it in the user interface. For example, Tanaka's screen will display suggestions for "sales" and "marketing."

[0199] 3. The user selects a business proposal

[0200] Input: Business proposal displayed on the user interface

[0201] Output: User's selection

[0202] Specific operation: The user checks the presented job proposals and selects one. For example, Mr. Tanaka selects "Sales position."

[0203] Step 5: Propose an internship test and gather feedback

[0204] 1. Generate internship exam proposals

[0205] Input: Survey data based on transfer preferences

[0206] Output: Internship Exam Proposal

[0207] Specific operation: The server analyzes the transfer request data of existing employees and generates an internship exam proposal. For example, it generates an internship exam proposal for Mr. Sato in the marketing department.

[0208] 2. Gather feedback during the internship

[0209] Input: Feedback data during internship period

[0210] Output: Collected feedback data

[0211] Specific operation: The server stores the feedback data collected during the internship. For example, Mr. Sato sends feedback about the work of the marketing department.

[0212] Step 6: Generate and present the final transfer proposal

[0213] 1. Analyze feedback data

[0214] Input: Collected feedback data

[0215] Output: Analysis results

[0216] Specific operation: The server analyzes the feedback data and generates the optimal transfer proposal. For example, Sato-san's feedback is analyzed.

[0217] 2. Generate the final transfer proposal

[0218] Input: Analysis results

[0219] Output: Final transfer proposal

[0220] Specific operation: The server generates a final transfer proposal based on the analysis results. For example, a "formal transfer proposal to the marketing department" is generated for Sato-san.

[0221] 3. Send the final proposal to the device and present it

[0222] Input: Final Transfer Proposal

[0223] Output: The final proposal displayed in the user interface

[0224] Specific operation: The server sends the final proposal to the user's device and displays it on the user interface. For example, "Formal transfer proposal to the marketing department" is displayed on Mr. Sato's screen.

[0225] (Application example 1)

[0226] 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."

[0227] With conventional personnel allocation systems, it is difficult to assign the right people to new graduates and existing employees, leading to job mismatches. Furthermore, automated equipment in factories is rarely allocated to the most appropriate departments, making it difficult to improve productivity. Furthermore, there is a lack of effective means for providing work proposals and managing feedback. This creates challenges that make it difficult to efficiently manage employees and automated equipment and optimally assign them to work.

[0228] 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.

[0229] In this invention, the server includes means for collecting survey response data regarding the work desired by new graduates and existing employees, means for transmitting the survey response data to the server, means for preprocessing the collected survey response data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate work proposals, means for evaluating the generated work proposals and selecting an appropriate proposal, means for presenting the selected work proposals to the user, means for saving the user's selections on the server, means for collecting data from the automated device and analyzing the work assigned to the device, means for presenting optimal work proposals to the automated device based on the generative AI model, means for collecting feedback on the presented work proposals, and means for analyzing the feedback data to improve work efficiency. This enables optimal work assignments for new graduates and existing employees as well as efficient department allocation of automated devices, thereby improving overall work efficiency.

[0230] "New graduates" refer to people who have recently graduated from an educational institution and are entering the workforce for the first time.

[0231] "Existing employees" refers to employees who are already employed by a company or organization and are currently working.

[0232] "Survey response data" refers to information obtained from new graduates and existing employees answering questions about their work.

[0233] "Server" refers to a computer system that collects, stores, analyzes, transmits, etc. data.

[0234] A "generative AI model" refers to a machine learning model that performs natural language processing and generates appropriate business proposals from input data.

[0235] "Work proposals" refer to proposals for work that the generative AI model determines to be most suitable for new graduates and existing employees.

[0236] "Feedback data" refers to information that indicates the results and opinions of users or automated devices when they perform a proposed task.

[0237] "Automated equipment" refers to machines and robots used to automate tasks in factories and other operating environments.

[0238] "Analysis" refers to the process of using collected data to extract information and identify patterns and trends.

[0239] "User" refers to new graduates, existing employees, or anyone authorized to review and decide on business proposals from these individuals.

[0240] "Work efficiency" refers to the ratio between the effectiveness of the work provided and the time it takes, and is a concept that aims to achieve high results in a short amount of time.

[0241] A "department" or "placement" refers to a position within a company or organization that is responsible for a specific task.

[0242] An "internship test" refers to an exam given to those seeking transfer to experience new work and confirm their suitability.

[0243] "Efficiency" refers to high productivity in carrying out designated tasks.

[0244] This invention relates to a system for assigning new graduates and existing employees to optimal work, and a system for efficiently allocating automated equipment within a factory to different departments. This system uses the following hardware and software to process data and perform calculations.

[0245] Hardware and Software

[0246] Server: A computer system for collecting, storing, analyzing, and transmitting data.

[0247] User device: A device (PC, smartphone, tablet, etc.) used to display survey responses and business proposals.

[0248] Generative AI model: A machine learning model (e.g., GPT-3) used to perform natural language processing and generate relevant business suggestions from input data.

[0249] API: Application Program Interface for sending, receiving, and processing data.

[0250] Overall system flow

[0251] 1. Collection of survey response data

[0252] New graduates and existing employees use user terminals to answer a questionnaire about the work they would like to do, which includes specific questions based on prompts.

[0253] For example, answer questions such as, "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[0254] 2. Data transmission to the server and pre-processing

[0255] The user terminal transmits the survey response data to the server, which cleanses and normalizes the received data and converts it into a format suitable for analysis.

[0256] 3. Generate business proposals

[0257] The server inputs the preprocessed data into a generative AI model to generate job suggestions. The generative AI model (e.g., GPT-3) generates optimal job suggestions, such as "sales positions" or "marketing positions," based on the input data.

[0258] 4. Presentation and selection of business proposals

[0259] The server sends the generated business proposals in JSON format to the user's device, which parses them and displays them on the user interface. The user then checks the presented business proposals and selects one.

[0260] 5. Feedback Data Collection

[0261] After the proposed work is performed, feedback data is collected, which is analyzed by the server and used to generate more efficient work suggestions.

[0262] Specific examples

[0263] Example 1: New graduates

[0264] New graduates say they are interested in sales jobs.

[0265] The server analyzes the response data and generates a business proposal for a sales position.

[0266] "Sales position" is displayed on the user terminal, and the new graduate selects it.

[0267] The sales staff will work according to the suggestions made by the sales staff and send their feedback to the server at a later date.

[0268] Example 2: Existing employees

[0269] An existing employee expressed a desire to transfer to the marketing department and responded to a survey.

[0270] The server analyzes the transfer request data and generates an internship proposal.

[0271] Existing employees agree to the internship proposal and gain experience working in the marketing department for a certain period of time.

[0272] After the internship ends, feedback is collected and a final transfer proposal is generated.

[0273] Prompt Sentence Examples

[0274] "Here is the robot's data. Please provide the optimal business proposal.

[0275] {'current_task': 'welding', 'skills': ['welding', 'cutting'], 'experience': {'welding': 200, 'cutting': 100}}"

[0276] This system will enable optimal job assignments for new graduates and existing employees, as well as efficient allocation of automated equipment within the factory, thereby improving overall operational efficiency.

[0277] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0278] Program processing flow

[0279] Step 1:

[0280] Collection of survey response data

[0281] Input: Users (new graduates and existing employees) answer a job-related survey. The survey includes questions such as "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[0282] Operation: The user terminal sends the entered answer data to the server.

[0283] Output: Survey response data is stored on the server.

[0284] Step 2:

[0285] Transmission of data to the server and pre-processing

[0286] Input: Survey response data sent from the user's device.

[0287] Operation:

[0288] The server cleanses the received data (removes unnecessary data and fills in missing values) and normalizes it (standardizes the data format).

[0289] After cleansing and normalization, the data is tokenized and converted into a format that is easy for the GPT-3 model to parse.

[0290] Output: Preprocessed data.

[0291] Step 3:

[0292] Generate business proposals

[0293] Input: Preprocessed data.

[0294] Operation:

[0295] The server inputs the preprocessed data into a generative AI model (such as GPT-3) to generate business proposals.

[0296] For example, the following prompt could be input to a generative AI model: "Here is the robot's data. Please suggest the best task for it: {'current_task': 'welding', 'skills': ['welding', 'cutting'], 'experience': {'welding': 200, 'cutting': 100}}"

[0297] Output: The generated business proposal.

[0298] Step 4:

[0299] Presentation and selection of business proposals

[0300] Input: The generated business proposal.

[0301] Operation:

[0302] The server converts the generated business proposal into JSON format and sends it to the user's terminal.

[0303] The user terminal parses the JSON data and displays it on the user interface.

[0304] The user checks the presented business proposals and makes a selection.

[0305] Output: The business proposal selected by the user.

[0306] Step 5:

[0307] Feedback data collection

[0308] Input: Feedback on the job selected by the user.

[0309] Operation:

[0310] After carrying out the proposed work, the user enters feedback.

[0311] Feedback includes the difficulty of the task, the degree of accomplishment, and suggestions for improvement.

[0312] The server collects feedback data from the user terminals and stores it in a database.

[0313] Output: Collected feedback data.

[0314] Step 6:

[0315] Analyzing feedback data and generating improvement suggestions

[0316] Input: Collected feedback data.

[0317] Operation:

[0318] The server analyzes the feedback data and re-inputs it into the generative AI model to generate even more efficient business proposals.

[0319] Through this loop, the accuracy of business proposals is improved.

[0320] Output: A new and improved business proposal.

[0321] The above steps will enable new graduates and existing employees to be assigned to the right jobs, as well as enable the efficient allocation of automated equipment within the factory, thereby improving overall work efficiency.

[0322] 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.

[0323] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis using an emotion engine, and a user interface.

[0324] System operation and program processing

[0325] 1. Survey collection

[0326] User: New graduates or existing employees log in to the system and access the designated survey page. To log in, they must enter their user ID and password.

[0327] Terminal: Sends the login information entered by the user to the server.

[0328] 2. Data reception and preparation for analysis

[0329] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[0330] On the device: After successful authentication, the survey page is displayed to the user.

[0331] 3. Survey responses

[0332] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[0333] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[0334] 4. Collecting survey and sentiment data

[0335] Server: Receives the survey response data and stores it in the database using an INSERT query.

[0336] On the device: While the user is answering the survey, the emotion engine analyzes the user's facial expressions, tone of voice, and the emotion of the text in real time to generate emotion data.

[0337] Server: Receives emotion data and stores it together with the survey response data.

[0338] 5. Data Preprocessing and Analysis

[0339] Server: Preprocesses the received survey response data and sentiment data, converting them into a format suitable for analysis, including data normalization and text tokenization.

[0340] Server: Inputs the preprocessed data into the generative AI model.

[0341] 6. Business proposal generation and emotional feedback

[0342] Server: The generative AI model generates business proposals and returns the results to the server.

[0343] Server: Analyzes real-time user sentiment data regarding the proposal content and evaluates the suitability of the business proposal.

[0344] Server: Selects the appropriate proposal and generates it in JSON format.

[0345] 7. Presentation of business proposal

[0346] Server: The generated JSON data is sent to the user's device as a REST API response.

[0347] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[0348] User: Review the proposed work and select the work they wish to do.

[0349] 8. Transfer Requests and Internship Exams

[0350] Server: For existing employees, the server also collects questionnaire responses based on transfer preferences and generates internship exam proposals. It also has a means of acquiring emotional data and analyzing it in real time.

[0351] Terminal: The proposal is displayed in the user interface and the user is asked to confirm whether or not to accept the internship attempt.

[0352] 9. Gathering feedback and final proposal

[0353] Server: Analyzes the feedback and sentiment data collected during the internship and generates the final transfer proposal.

[0354] Server: Presents the final proposal to the user and displays it in the user interface.

[0355] User: Review the final proposal and choose whether to accept it.

[0356] Example of a system

[0357] Example 1: Tanaka-san (new graduate):

[0358] In the survey, participants indicated that they wanted to work in sales and marketing and had previous experience in sales. Real-time emotional data was also collected.

[0359] The server analyzes the data and generates suggestions for "sales jobs" and "marketing jobs," taking into account sentiment data regarding the suggestions.

[0360] Tanaka chooses "sales" and this is reflected in his career plan.

[0361] Example 2: Sato-san (existing employee):

[0362] They will then be asked to fill out a questionnaire to request a transfer to the marketing department and take an internship exam. Feedback, including sentiment data, will be collected during the internship.

[0363] After completing the training, the feedback is analyzed and a formal transfer to the marketing department is proposed.

[0364] This allows the system to assign new graduates and existing employees to tasks that are best suited to them, reducing job mismatches, and also provides more accurate suggestions by taking into account users' emotional data.

[0365] The processing flow will be explained below.

[0366] Step 1:

[0367] User: New graduates or existing employees log in to the system and access the survey page. To log in, they must enter their user ID and password.

[0368] Terminal: Sends the login information entered by the user to the server.

[0369] Step 2:

[0370] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[0371] On the device: After successful authentication, the survey page is displayed to the user.

[0372] Step 3:

[0373] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[0374] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[0375] Step 4:

[0376] On the device: While the user is answering the survey, the emotion engine analyzes the user's facial expressions, tone of voice, and the sentiment of the text in real time.

[0377] Terminal: The emotion engine analyzes emotion data in real time and sends it to the server.

[0378] Step 5:

[0379] Server: Receives the survey response data and sentiment data and stores them in the database using an INSERT query.

[0380] Step 6:

[0381] Server: Preprocesses the received survey response data and sentiment data, cleansing and normalizing the data, and tokenizing the text data.

[0382] Step 7:

[0383] Server: Inputs the preprocessed data into the generative AI model to generate optimal business proposals.

[0384] Server: The generative AI model generates business proposals and returns the results to the server.

[0385] Step 8:

[0386] Server: Evaluates the collected emotional data for the proposed work content and selects work proposals with positive user emotional data.

[0387] Server: Generates the selected business proposals in JSON format.

[0388] Step 9:

[0389] Server: The generated JSON data is sent to the user's device as a REST API response.

[0390] Step 10:

[0391] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[0392] User: Review the proposed work and select the work they wish to do.

[0393] Step 11:

[0394] Terminal: Sends the task selected by the user to the server.

[0395] Server: Saves the user's selection in the database and updates the user's career plan.

[0396] Step 12:

[0397] Users: Existing employees answer a questionnaire based on their transfer preferences, including questions about their preferred department, past work experience, and skill set.

[0398] Terminal: Sends the survey response data and emotion data to the server.

[0399] Step 13:

[0400] Server: Receives the survey response data and sentiment data and performs preprocessing, such as data cleansing, normalization, and tokenization of text data.

[0401] Step 14:

[0402] Server: The preprocessed data is fed into a generative AI model to generate internship exam suggestions, taking into account emotional data.

[0403] Server: Generates the proposed content in JSON format and sends it to the user's device.

[0404] Step 15:

[0405] Terminal: The submitted proposal is displayed on the user interface and the user is asked whether or not to carry out the internship trial.

[0406] User: Choose whether to conduct an internship trial.

[0407] Step 16:

[0408] Server: Collects user feedback and sentiment data during the internship period. The collected data is stored in a database.

[0409] Step 17:

[0410] Server: After the internship period ends, the feedback data and sentiment data are analyzed to generate a final transfer proposal.

[0411] Server: Generates the final proposal in JSON format and sends it to the user's device.

[0412] Step 18:

[0413] Terminal: The final proposal is displayed in the user interface.

[0414] User: Review the final proposal and choose whether to accept it.

[0415] Example 2

[0416] 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."

[0417] It is important to accurately understand the preferences and aptitudes of new graduates and existing employees to reduce job mismatches, but conventional methods have the problem of low accuracy in proposals because they do not take into account user emotional data. Furthermore, when it comes to transfers for existing employees, feedback data from internships has not been effectively utilized, resulting in a lack of appropriateness in transfer proposals. There is a need to solve these issues.

[0418] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0419] In this invention, the server includes means for collecting and analyzing emotional data of the user while answering the questionnaire, means for evaluating the suitability of a job proposal using the emotional data, and means for analyzing the feedback data and emotional data during the internship period and generating a final transfer proposal, thereby enabling highly accurate job proposals and transfer proposals that take the user's emotional data into consideration.

[0420] "Questionnaire response data" refers to response information to questions entered by users into the system.

[0421] A "server" is a computer system connected to a network that processes and stores data and manages communications with other terminals.

[0422] A "generative AI model" refers to an artificial intelligence model that uses deep learning technology to analyze data and make predictions.

[0423] "Emotional data" refers to data that represents the user's emotional state analyzed from facial expressions, tone of voice, text content, etc.

[0424] "Preprocessing" refers to a series of operations that normalize and organize data prior to analysis, converting it into a format suitable for analysis.

[0425] "Business proposal" refers to the industry, job content, career plan, etc. proposed to the user.

[0426] An "internship test" refers to an experiment in which an existing employee undergoes work experience for a certain period of time in the department to which they wish to be transferred, and the results are evaluated.

[0427] "Feedback Data" refers to data regarding user opinions, evaluations, and performance collected during the internship period.

[0428] "User interface" refers to the screens and operating means provided for the user and the system to exchange information.

[0429] This invention relates to a system for allocating new graduates and existing employees to the most suitable jobs and reducing job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis, and a user interface.

[0430] Hardware and software used

[0431] Server: A device that processes and stores data and manages communications with other terminals, and is equipped with multiple high-performance processors and large-capacity memory.

[0432] Database: Uses an RDBMS such as MySQL or PostgreSQL.

[0433] Generative AI model: Uses OpenAI's GPT-3 or similar deep learning models.

[0434] Sentiment analysis engine: Use facial recognition APIs such as Amazon Rekognition and speech analysis APIs such as Google Cloud Speech-to-Text.

[0435] Terminal: A device used by users to answer questionnaires or take internship exams, and is typically a personal computer or tablet equipped with a camera and microphone.

[0436] Browser: Use a web browser such as Chrome or Firefox.

[0437] System operation and concrete examples

[0438] Survey collection

[0439] Users log in to the system and access the questionnaire page. A user ID and password are required to log in. Users answer questions such as "jobs they are interested in," "past experience," "strengths and weaknesses," and "desired career path."

[0440] The terminal sends the user's login information to the server, and if authentication is successful, a questionnaire page is displayed.

[0441] Data storage and sentiment analysis

[0442] The server stores the received survey data in a database. Using facial expression recognition APIs and voice analysis APIs, it analyzes emotional data from the user's facial expressions and tone of voice in real time and stores the data in the database.

[0443] Data preprocessing and analysis using generative AI models

[0444] The server normalizes the survey data and sentiment data, tokenizes the text data, and inputs this into a generative AI model to generate business proposals. For example, OpenAI's GPT-3 model is used.

[0445] The generated business proposals are evaluated for suitability using emotional data, and appropriate proposals are selected.

[0446] Presentation of business proposals and user selection

[0447] The server converts the selected business proposal into JSON format and sends it to the terminal via REST API.

[0448] The device parses the JSON data and displays the proposed tasks on the user interface. The user can then review the proposed tasks and select the desired task.

[0449] Specific examples

[0450] Example 1: A new graduate logs into the system and submits a questionnaire indicating their preference for "sales" and "marketing." The server uses a generative AI model and sentiment analysis to create proposals for both "sales" and "marketing." After evaluating the suitability, it is determined that sales is the most suitable. Based on this proposal, the new graduate selects a sales position.

[0451] Example 2: An existing employee requests a transfer to the marketing department and conducts an internship test. During the internship, sentiment data and feedback data are collected, and a transfer proposal to the marketing department is finally generated.

[0452] Prompt Sentence Examples

[0453] 1. "A new graduate indicated that he / she would like to work in sales and marketing and has experience in sales. Please explain what kind of business proposals will be generated, including emotional data."

[0454] 2. "When an existing employee requests a transfer to the marketing department, explain how feedback data is collected through an intern exam and a final proposal is generated."

[0455] As a result, this system makes job and transfer proposals that take into maximum consideration the wishes and aptitudes of new graduates and existing employees, thereby reducing job mismatches.

[0456] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0457] Step 1:

[0458] The user logs in to the system. The user enters their user ID and password on the login screen and clicks the "Login" button.

[0459] Input: User ID, Password

[0460] Output: Login request

[0461] Step 2:

[0462] The device sends the user's login information to the server. The login request is sent using the HTTPS protocol.

[0463] Input: Login request

[0464] Output: Authentication request to the server

[0465] Step 3:

[0466] The server authenticates the received login information by checking it against its database, and if authentication is successful, starts a user session.

[0467] Input: Authentication request (user ID, password)

[0468] Output: Authentication result (success or failure)

[0469] Step 4:

[0470] After successful authentication, the device displays the survey page to the user. The survey form is rendered using HTML and CSS.

[0471] Input: Authentication result (success)

[0472] Output: Survey page

[0473] Step 5:

[0474] Users access the survey page and answer questions, entering information such as "interesting work," "past experience," "strengths and weaknesses," and "desired career path."

[0475] Input: Survey response

[0476] Output: Survey data

[0477] Step 6:

[0478] The device uses a camera and microphone to capture facial expressions and tone of voice in real time while the user answers the survey.

[0479] Input: Real-time facial expressions and voice of the user

[0480] Output: Emotion data

[0481] Step 7:

[0482] The terminal sends the answered questionnaire data to the server by pressing the send button.

[0483] Input: Survey data

[0484] Output: Request to send survey data to the server

[0485] Step 8:

[0486] The server stores the received survey data in the database using an INSERT query.

[0487] Input: Survey data

[0488] Output: Update database (save survey data)

[0489] Step 9:

[0490] The server uses an emotion analysis engine to analyze the facial expressions and tone of voice sent from the device and generate emotion data, which is then stored in a database.

[0491] Input: facial expression data, voice data

[0492] Output: Saved emotion data

[0493] Step 10:

[0494] The server performs preprocessing of the received questionnaire data and emotion data, such as cleaning text data and normalizing numerical data.

[0495] Input: Survey data, emotion data

[0496] Output: Preprocessed data

[0497] Step 11:

[0498] The server inputs the preprocessed data into a generative AI model to generate business proposals. The AI ​​model used is a generative AI model such as GPT-3.

[0499] Input: Preprocessed data

[0500] Output: Business proposal data

[0501] Step 12:

[0502] The server evaluates the suitability of the generated business proposals using emotional data analysis and selects the most appropriate proposal.

[0503] Input: Business proposal data, emotion data

[0504] Output: Evaluated business proposal

[0505] Step 13:

[0506] The server converts the selected business proposal into JSON format and sends it to the terminal via REST API.

[0507] Input: Evaluated Business Proposal

[0508] Output: Business proposal data in JSON format

[0509] Step 14:

[0510] The device parses the JSON data received from the server and displays the suggestions in the user interface.

[0511] Input: Business proposal data in JSON format

[0512] Output: Displayed business proposal

[0513] Step 15:

[0514] The user checks the displayed business proposals and selects the business he or she desires.

[0515] Input: Business proposal list

[0516] Output: Selected tasks

[0517] Step 16:

[0518] The terminal transmits the business information selected by the user to the server.

[0519] Input: Selected business

[0520] Output: Request to send selection information to the server

[0521] Step 17:

[0522] The server saves the user's selections in a database and updates the career plan.

[0523] Input: Selected business information

[0524] Output: Updated career plan

[0525] The goal is that by going through all the steps of this system, users will be able to receive the best job offers based on their preferences and aptitudes.

[0526] (Application example 2)

[0527] 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."

[0528] In companies, mismatched work assignments between new graduates and existing employees can lead to reduced efficiency and motivation. In particular, employees can be assigned to work that does not match their skills or career path, which can lead to a decline in performance. In addition, while appropriate personnel assignment is crucial for operating online or virtual stores, traditional methods make it difficult to propose optimal work assignments that take into account individual characteristics and emotions.

[0529] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting questionnaire response data, means for transmitting the collected data to the server, means for preprocessing the data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate business proposals, means for evaluating the proposals and selecting an appropriate proposal, means for presenting the selected business proposals to the user, means for saving the user's selections on the server, means for analyzing emotion data from input text, and means for adjusting the business proposals based on the emotion data. This makes it possible to achieve optimal job assignments that take into account the characteristics and emotions of employees and improve the efficiency of corporate human resource utilization.

[0530] "Survey response data" refers to response data that contains information about the work desired by new graduates and existing employees.

[0531] A "server" is a computer system that receives, stores, and processes questionnaire response data and emotion data.

[0532] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis.

[0533] A "generative AI model" is an artificial intelligence model that generates business proposals based on preprocessed data.

[0534] "Job proposals" refer to the optimal jobs that the generative AI model proposes to new graduates and existing employees.

[0535] "Evaluation" is the process of determining the appropriateness of the generated business proposals.

[0536] "Users" refers to new graduates and existing employees who use this system.

[0537] "Emotion data" refers to data related to emotions analyzed from the user's input text, facial expressions, and tone of voice.

[0538] "Adjustment" refers to modifying or optimizing business proposals based on analyzed emotional data.

[0539] An "internship test" refers to a trial work experience in the department to which an existing employee wishes to be transferred.

[0540] "Feedback data" refers to data that records evaluations and impressions collected during the internship period.

[0541] The "final transfer proposal" refers to the final proposed transfer job based on the results of analyzing the feedback data.

[0542] This invention provides a system for assigning new graduates and existing employees to the most suitable jobs and reducing job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis using an emotion engine, and a user interface.

[0543] The specific operation of the system is explained below.

[0544] Hardware and software used

[0545] Hardware: Smartphone (Android or iOS)

[0546] Software: Python, EmotionEngine, JobMatchGPT, JSON, REST API

[0547] Data flow and processing overview

[0548] 1. Collection of survey response data: Users (new graduates and existing employees) access a designated survey page using their smartphones and answer questions about their work experience and desired work. The survey data is then sent from the device to the server.

[0549] 2. Emotion data collection: While the user is answering the questionnaire, EmotionEngine analyzes the emotional data from the text input, facial expressions, and tone of voice in real time. This emotional data is also sent to the server.

[0550] 3. Data preprocessing and analysis: The server preprocesses the received survey response data and sentiment data, converting them into a format suitable for analysis. Preprocessing includes data normalization and tokenization. Next, this data is input into a generative AI model (JobMatchGPT) to generate job suggestions.

[0551] 4. Evaluation and adjustment of business proposals: The server evaluates the generated business proposals based on the emotional data and selects the most appropriate proposal. The evaluation takes into account the results of emotional analysis using the Emotion Engine.

[0552] 5. Presentation of business proposals: The selected business proposals are converted into JSON format and sent to the user's device via the REST API. The user can then review the business proposals on their device and select the desired business.

[0553] 6. Transfer preference and internship exam: For existing employees, internship exams are proposed based on their transfer preference. Feedback data during the internship period is also collected along with emotion data and analyzed on the server.

[0554] 7. Generation of final transfer proposal: Based on the analysis results of the feedback data, the server generates a final transfer proposal and presents it to the user through the user interface.

[0555] Examples of specific examples and prompts

[0556] Example: Mr. Tanaka (a new graduate) is interested in running a virtual store and answers the questionnaire saying he is interested in "virtual store management." The system will propose the most suitable job, including emotional data, and the job Mr. Tanaka selects will be reflected in his career plan.

[0557] Example prompt sentence:

[0558] "I'm interested in working in a virtual store. I have experience in customer service and would like to gain more technical knowledge. Which role would be right for me?"

[0559] In this way, this system aims to reduce work mismatches and improve employee performance by analyzing users' characteristics and wishes in detail and making work suggestions.

[0560] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0561] Step 1:

[0562] Users access the questionnaire page using their smartphones and answer questions about their work experience and desired work. The data entered includes work experience, areas of interest, skills, career path, etc. This data is sent from the device to the server.

[0563] Step 2:

[0564] The server receives the survey response data sent from the terminal and stores it in a database. The input is the survey response data, and the output is the data stored in the database.

[0565] Step 3:

[0566] While the user is answering the questionnaire, EmotionEngine collects emotional data from text input, facial expressions, and tone of voice. This emotional data is sent from the device to the server. The input is text, facial expressions, and voice data, and the output is emotional data analyzed in real time.

[0567] Step 4:

[0568] The server preprocesses the received survey response data and emotion data. Preprocessing includes normalizing and tokenizing the data to convert it into a format suitable for analysis. The input is the raw survey response data and emotion data, and the output is the preprocessed data.

[0569] Step 5:

[0570] Based on the preprocessed data, the server uses a generative AI model (JobMatchGPT) to generate job suggestions. The input is the preprocessed data, and the output is job suggestions. This generation process takes into account skills, experience, and emotional data.

[0571] Step 6:

[0572] The server evaluates the generated business proposals based on emotional data and selects the most suitable proposal. The evaluation also takes into account the results of emotional analysis using EmotionEngine. The input is the business proposal and emotional data, and the output is a selected business proposal that reflects the evaluation results.

[0573] Step 7:

[0574] The selected business proposal is converted into JSON format and sent to the user's device via REST API. The user reviews the provided proposals and selects the desired business. The input is the selected business proposal, and the output is the business selected by the user.

[0575] Step 8:

[0576] For existing employees, an internship exam is proposed based on their transfer preference. The user decides whether to take the internship exam. The input is the transfer preference data and the proposal content, and the output is the user's choice of whether to accept or reject the internship exam.

[0577] Step 9:

[0578] During the internship period, the server collects feedback data from users and emotion data updated in real time. The input is the feedback data and emotion data, and the output is a final transfer proposal including the analysis results.

[0579] Step 10:

[0580] Based on the analysis results of the feedback data and emotion data, the server generates a final transfer proposal and presents it to the user through the user interface. The user reviews the final proposal and decides whether to accept the transfer. The input is the analyzed data, and the output is the final transfer proposal and its selection result.

[0581] The above are the specific processing steps for providing an optimal task allocation that takes into consideration the characteristics and emotions of the user.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] [Second embodiment]

[0586] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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).

[0592] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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."

[0598] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, and a user interface.

[0599] System operation and program processing

[0600] 1. Survey collection

[0601] User: A new graduate or existing employee logs into the system and accesses the designated survey page.

[0602] Terminal: The user answers the questions in the survey and presses the send button to send the answer data to the server. Examples of questions include "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[0603] Example: Mr. Tanaka says he is interested in sales and marketing positions and notes that he has prior sales experience.

[0604] 2. Data reception and preparation for analysis

[0605] Server: Receives the survey response data and stores it in a database.

[0606] Server: Cleanses and normalizes the received data, and converts text data into a format suitable for analysis by tokenizing it, for example. For example, it converts the contents of a survey into specific keywords so that the model can easily understand them.

[0607] 3. Data analysis and business proposal generation

[0608] Server: The preprocessed data is input into a generative AI model (such as GPT-3) to generate optimal job suggestions. The model outputs multiple job suggestions based on the user's preferences and aptitude.

[0609] Server: Evaluates the generated job proposals and selects the most appropriate one. For example, "sales position" and "marketing position" are selected from the generated proposals.

[0610] 4. Presentation of business proposal

[0611] Server: Generates the selected business proposals in JSON format and sends them to the user's device.

[0612] Terminal: Parses the JSON data sent and displays it in the user interface. The user can then review and select the business proposals presented.

[0613] Example: Tanaka's screen shows the suggestions "Sales" and "Marketing", and she chooses Sales.

[0614] 5. Propose an internship test and collect feedback

[0615] Server: For existing employees, the server analyzes the questionnaire responses based on their transfer preferences and generates and presents internship proposals. It also includes a function to collect feedback data during the internship period.

[0616] Example: Mr. Sato wants to transfer to the marketing department and will take an internship exam. After the internship period ends, Mr. Sato will submit his opinion through the feedback form.

[0617] 6. Generate and present the final transfer proposal

[0618] Server: After the internship ends, the collected feedback data is analyzed and a final transfer proposal is generated. The generated proposal is sent to the user's device and displayed on the user interface.

[0619] Example: After analyzing Sato's feedback, it is determined that a formal transfer to the Marketing department is appropriate, and a final proposal is made.

[0620] Example of a system

[0621] Example 1: Tanaka-san (new graduate):

[0622] In the survey, he indicated that he wanted to work in "sales" and "marketing" and that he had previous experience in sales work.

[0623] The server analyzes the data and generates suggestions for "sales jobs" and "marketing jobs."

[0624] Tanaka chooses "sales" and this is reflected in his career plan.

[0625] Example 2: Sato-san (existing employee):

[0626] In the survey, I expressed a desire to be transferred to the marketing department.

[0627] I accepted the internship offer and experienced working in the marketing department for one month.

[0628] After completing the course, he provided feedback and was eventually offered a permanent transfer to the Marketing department, which he accepted.

[0629] This system allows new graduates and existing employees to be assigned to tasks that best suit them, reducing job mismatches and supporting long-term career development within the company.

[0630] The processing flow will be explained below.

[0631] Step 1:

[0632] User: New graduates or existing employees log in to the system and access the survey page. To log in, they must enter their user ID and password.

[0633] Terminal: Sends the login information entered by the user to the server.

[0634] Step 2:

[0635] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[0636] On the device: After successful authentication, the survey page is displayed to the user.

[0637] Step 3:

[0638] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[0639] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[0640] Step 4:

[0641] Server: Receives the survey response data and stores it in the database using an INSERT query.

[0642] Server: Preprocesses the received data and converts it into a format suitable for analysis by performing text normalization, tokenization, etc.

[0643] Step 5:

[0644] Server: Inputs the preprocessed data into the generative AI model, which receives the data via an API.

[0645] Server: The generative AI model generates business proposals and returns the results to the server.

[0646] Step 6:

[0647] Server: Evaluates the generated business proposals and selects the most appropriate one. The proposals are scored and the one with the highest score is selected.

[0648] Server: Generates the selected business proposals in JSON format.

[0649] Step 7:

[0650] Server: The generated JSON data is sent to the user's device as a REST API response.

[0651] Step 8:

[0652] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[0653] User: Review the proposed work and select the work they wish to do.

[0654] Step 9:

[0655] Terminal: Sends the user's selection to the server.

[0656] Server: Receives the selections and stores them in the database, updating the user's career plan.

[0657] Step 10:

[0658] Server: For existing employees, a means is provided to collect questionnaire response data based on transfer preferences and generate internship trial proposals. Proposals for internship trials are generated and displayed on the user interface as well.

[0659] User: Confirms and accepts the internship attempt and also completes and submits feedback during the internship period.

[0660] Step 11:

[0661] Server: After the internship ends, analyze the collected feedback data and generate a final transfer proposal.

[0662] Server: Sends the final proposal to the user and displays it in the user interface.

[0663] Step 12:

[0664] User: Review the final proposal and choose whether to accept it.

[0665] The above is the specific processing flow of the "JoB Match GPT" system.

[0666] Example 1

[0667] 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."

[0668] Modern companies require both new graduates and existing employees to be assigned to the most appropriate jobs based on their preferences and aptitudes. However, traditional manual job assignment methods are prone to mismatches and are labor-intensive and time-consuming, so a system that efficiently and effectively proposes jobs is needed. Furthermore, there is a lack of effective methods for proposing internships based on employee transfer requests and for collecting and analyzing subsequent feedback. This makes it difficult to optimize transfers and career plans, and to support long-term career development within the company.

[0669] 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.

[0670] In this invention, the server includes means for cleansing and normalizing survey data, means for tokenizing the data and converting it into a format suitable for analysis, means for sending the generated job proposals to the user's device in JSON format and displaying them on a user interface, means for preprocessing the survey response data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate job proposals, means for evaluating the generated job proposals and selecting an appropriate proposal, means for presenting the selected job proposal to the user, and means for saving the user's selections on the server. This makes it possible to efficiently collect and analyze data on the jobs desired by new graduates and existing employees, and to generate and present optimal job proposals and transfer proposals. This reduces job mismatches and supports long-term career development within the company.

[0671] "Survey response data" refers to data that includes information provided by new graduates and existing employees regarding the work they would like to do.

[0672] A "server" is a computer system that receives, stores, analyzes, and generates proposals from survey response data.

[0673] "Preprocessing" refers to the process of cleansing, normalizing, and converting collected survey response data into a format suitable for analysis.

[0674] A "generative AI model" is an artificial intelligence model used to analyze survey response data and generate business proposals.

[0675] "Business proposals" are optimal business operations proposed by the generative AI model based on the user's wishes and aptitude.

[0676] An "internship exam" refers to a trial period during which existing employees gain experience in the work they wish to transfer to.

[0677] "Feedback data" refers to data that includes the opinions and impressions of existing employees, collected during the internship test period.

[0678] "User interface" refers to the screen and operating environment through which users operate the system and confirm business proposals and internship exam proposals.

[0679] "Cleansing" is the process of removing duplicates and errors from survey response data and organizing the data.

[0680] "Normalization" is the process of standardizing the format of survey response data and converting it into a form suitable for analysis.

[0681] "Tokenization" is the process of breaking down text data into words and phrases, making it easier to analyze.

[0682] "JSON format" is a data format used to structure data and send it to a user's device.

[0683] A "user terminal" is a device such as a computer or smartphone that a user uses to access the system and respond to business proposals and questionnaires.

[0684] MODE FOR CARRYING OUT THE INVENTION

[0685] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, and a user interface.

[0686] Survey collection

[0687] Users log in to the system as new graduates or existing employees. A dedicated ID and password are used to log in. After logging in, they are redirected to a survey page where they answer specified questions. For example, questions include "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?" After the user has finished answering, they press the send button to send the survey response data to the server.

[0688] Data reception and preparation for analysis

[0689] The server receives the survey response data sent by users and stores it in a database. Next, the data is cleansed (removing duplicates and errors) and normalized (standardizing the format). Furthermore, the text data is tokenized and converted into a format that can be analyzed by a generative AI model (e.g., GPT-3).

[0690] Data analysis and business proposal generation

[0691] The server inputs the preprocessed data into the generative AI model to generate the optimal job proposal. For example, the prompt statement could be "Please generate the optimal job proposal for Tanaka. Tanaka has experience in sales and marketing." Based on this prompt, the generative AI model outputs job proposals such as "sales position" and "marketing position." The multiple job proposals generated are evaluated, and the most appropriate proposal is selected.

[0692] Presenting business proposals

[0693] The server generates the selected business proposals in JSON format and sends them to the user's device. The device parses the received JSON data and displays it on the user interface, allowing the user to check and select from the presented business proposals.

[0694] Internship test proposal and feedback collection

[0695] The system analyzes questionnaire responses from existing employees based on their transfer preferences and generates internship exam proposals. The server stores and analyzes feedback data collected during the internship period. For example, if Mr. Sato requests a transfer to the marketing department, he takes the internship exam and submits his feedback after completing it.

[0696] Generate and present the final transfer proposal

[0697] The server analyzes the collected feedback data after the internship period and generates a final transfer proposal, which is sent to the user's device and displayed on the user interface.

[0698] Specific examples

[0699] Example 1: Mr. Tanaka, a new graduate

[0700] In the questionnaire, Tanaka indicated that he would like to work in "sales" and "marketing" and that he has experience in sales work.

[0701] The server analyzes this and generates job proposals for "sales positions" and "marketing positions."

[0702] Tanaka chose a sales position, which is reflected in his career plan.

[0703] Example 2: Existing employee Sato

[0704] In the survey, Sato expressed a desire to be transferred to the marketing department.

[0705] He accepted the internship offer and gained experience working in the marketing department for one month.

[0706] After completing the internship, the employee submits feedback, which is then analyzed by the server, who then makes a formal proposal for transfer to the marketing department.

[0707] This system allows new graduates and existing employees to be assigned to jobs that best suit them, reducing job mismatches and supporting long-term career development within the company.

[0708] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0709] Program processing flow

[0710] Step 1: Survey collection

[0711] 1. A user logs into the system

[0712] Input: User ID and password

[0713] Output: The user is redirected to the survey page after successful login.

[0714] Specific operation: The user enters their ID and password and clicks the login button. For example, Mr. Tanaka logs in by entering his ID "tanaka123" and password.

[0715] 2. Visit the survey page and answer the questions

[0716] Input: User's survey response

[0717] Output: User survey response data

[0718] Specific operation: The user answers the survey questions and presses the submit button. For example, Mr. Tanaka answers that he is interested in "sales and marketing positions" and has experience in sales work.

[0719] 3. Send the survey response data to the server

[0720] Input: User survey response data

[0721] Output: Survey data sent to the server

[0722] Specific operation: The user clicks the send button and the survey data is sent to the server. For example, Tanaka's survey data is recorded in the server's database.

[0723] Step 2: Receive data and prepare for analysis

[0724] 1. Receive survey response data

[0725] Input: Survey data sent to the server

[0726] Output: Survey data stored in a database

[0727] Specific operation: The server receives the survey data and stores it in a database. For example, Tanaka's survey response data is recorded in the database.

[0728] 2. Cleanse and normalize the data

[0729] Input: Survey data in the database

[0730] Output: Cleansed and normalized data

[0731] What it does: The server removes duplicates and errors from data and standardizes formats. For example, it automatically corrects data inconsistencies like "Tanaka" and "Tanaka."

[0732] 3. Tokenize the data

[0733] Input: Cleansed and normalized data

[0734] Output: Tokenized data

[0735] Specific operation: Text data is divided into words and phrases and converted into a format that can be understood by the generative AI model. For example, keywords such as "sales job" and "sales work" are tokenized.

[0736] Step 3: Data analysis and business proposal generation

[0737] 1. Feed preprocessed data into a generative AI model

[0738] Input: Tokenized data

[0739] Output: Multiple business proposals

[0740] Specific operation: The cleansed and normalized data is input into a generative AI model (e.g., GPT-3). The prompt sentence is "Please generate the optimal business proposal for Mr. Tanaka. Mr. Tanaka has experience in sales and marketing."

[0741] 2. Generate optimal business proposals

[0742] Input: Output data from a generative AI model

[0743] Output: Multiple business proposals

[0744] Specific operation: The server receives the job proposals generated by the generative AI model. For example, job proposals for "sales positions" and "marketing positions" are output.

[0745] 3. Evaluate and select the generated business proposals

[0746] Input: Generated business proposal

[0747] Output: Selected business proposals

[0748] Specific operation: The server evaluates job proposals based on multiple evaluation criteria and selects the most appropriate proposal. For example, "sales position" and "marketing position" are evaluated and selected as the most suitable.

[0749] Step 4: Present the business proposal

[0750] 1. Generate a business proposal in JSON format

[0751] Input: Selected business proposal

[0752] Output: JSON format data

[0753] Specific operation: The selected job proposals are generated in JSON format and sent to the user's device. For example, proposals for "sales positions" and "marketing positions" are generated as JSON format data.

[0754] 2. Parse and display the proposal data on the device

[0755] Input: JSON format data

[0756] Output: Data displayed in the user interface

[0757] Specific operation: The device parses the received JSON data and displays it in the user interface. For example, Tanaka's screen will display suggestions for "sales" and "marketing."

[0758] 3. The user selects a business proposal

[0759] Input: Business proposal displayed on the user interface

[0760] Output: User's selection

[0761] Specific operation: The user checks the presented job proposals and selects one. For example, Mr. Tanaka selects "Sales position."

[0762] Step 5: Propose an internship test and gather feedback

[0763] 1. Generate internship exam proposals

[0764] Input: Survey data based on transfer preferences

[0765] Output: Internship Exam Proposal

[0766] Specific operation: The server analyzes the transfer request data of existing employees and generates an internship exam proposal. For example, it generates an internship exam proposal for Mr. Sato in the marketing department.

[0767] 2. Gather feedback during the internship

[0768] Input: Feedback data during internship period

[0769] Output: Collected feedback data

[0770] Specific operation: The server stores the feedback data collected during the internship. For example, Mr. Sato sends feedback about the work of the marketing department.

[0771] Step 6: Generate and present the final transfer proposal

[0772] 1. Analyze feedback data

[0773] Input: Collected feedback data

[0774] Output: Analysis results

[0775] Specific operation: The server analyzes the feedback data and generates the optimal transfer proposal. For example, Sato-san's feedback is analyzed.

[0776] 2. Generate the final transfer proposal

[0777] Input: Analysis results

[0778] Output: Final transfer proposal

[0779] Specific operation: The server generates a final transfer proposal based on the analysis results. For example, a "formal transfer proposal to the marketing department" is generated for Sato-san.

[0780] 3. Send the final proposal to the device and present it

[0781] Input: Final Transfer Proposal

[0782] Output: The final proposal displayed in the user interface

[0783] Specific operation: The server sends the final proposal to the user's device and displays it on the user interface. For example, "Formal transfer proposal to the marketing department" is displayed on Mr. Sato's screen.

[0784] (Application example 1)

[0785] 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."

[0786] With conventional personnel allocation systems, it is difficult to assign the right people to new graduates and existing employees, leading to job mismatches. Furthermore, automated equipment in factories is rarely allocated to the most appropriate departments, making it difficult to improve productivity. Furthermore, there is a lack of effective means for providing work proposals and managing feedback. This creates challenges that make it difficult to efficiently manage employees and automated equipment and optimally assign them to work.

[0787] 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.

[0788] In this invention, the server includes means for collecting survey response data regarding the work desired by new graduates and existing employees, means for transmitting the survey response data to the server, means for preprocessing the collected survey response data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate work proposals, means for evaluating the generated work proposals and selecting an appropriate proposal, means for presenting the selected work proposals to the user, means for saving the user's selections on the server, means for collecting data from the automated device and analyzing the work assigned to the device, means for presenting optimal work proposals to the automated device based on the generative AI model, means for collecting feedback on the presented work proposals, and means for analyzing the feedback data to improve work efficiency. This enables optimal work assignments for new graduates and existing employees as well as efficient department allocation of automated devices, thereby improving overall work efficiency.

[0789] "New graduates" refer to people who have recently graduated from an educational institution and are entering the workforce for the first time.

[0790] "Existing employees" refers to employees who are already employed by a company or organization and are currently working.

[0791] "Survey response data" refers to information obtained from new graduates and existing employees answering questions about their work.

[0792] "Server" refers to a computer system that collects, stores, analyzes, transmits, etc. data.

[0793] A "generative AI model" refers to a machine learning model that performs natural language processing and generates appropriate business proposals from input data.

[0794] "Work proposals" refer to proposals for work that the generative AI model determines to be most suitable for new graduates and existing employees.

[0795] "Feedback data" refers to information that indicates the results and opinions of users or automated devices when they perform a proposed task.

[0796] "Automated equipment" refers to machines and robots used to automate tasks in factories and other operating environments.

[0797] "Analysis" refers to the process of using collected data to extract information and identify patterns and trends.

[0798] "User" refers to new graduates, existing employees, or anyone authorized to review and decide on business proposals from these individuals.

[0799] "Work efficiency" refers to the ratio between the effectiveness of the work provided and the time it takes, and is a concept that aims to achieve high results in a short amount of time.

[0800] A "department" or "placement" refers to a position within a company or organization that is responsible for a specific task.

[0801] An "internship test" refers to an exam given to those seeking transfer to experience new work and confirm their suitability.

[0802] "Efficiency" refers to high productivity in carrying out designated tasks.

[0803] This invention relates to a system for assigning new graduates and existing employees to optimal work, and a system for efficiently allocating automated equipment within a factory to different departments. This system uses the following hardware and software to process data and perform calculations.

[0804] Hardware and Software

[0805] Server: A computer system for collecting, storing, analyzing, and transmitting data.

[0806] User device: A device (PC, smartphone, tablet, etc.) used to display survey responses and business proposals.

[0807] Generative AI model: A machine learning model (e.g., GPT-3) used to perform natural language processing and generate relevant business suggestions from input data.

[0808] API: Application Program Interface for sending, receiving, and processing data.

[0809] Overall system flow

[0810] 1. Collection of survey response data

[0811] New graduates and existing employees use user terminals to answer a questionnaire about the work they would like to do, which includes specific questions based on prompts.

[0812] For example, answer questions such as, "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[0813] 2. Data transmission to the server and pre-processing

[0814] The user terminal transmits the survey response data to the server, which cleanses and normalizes the received data and converts it into a format suitable for analysis.

[0815] 3. Generate business proposals

[0816] The server inputs the preprocessed data into a generative AI model to generate job suggestions. The generative AI model (e.g., GPT-3) generates optimal job suggestions, such as "sales positions" or "marketing positions," based on the input data.

[0817] 4. Presentation and selection of business proposals

[0818] The server sends the generated business proposals in JSON format to the user's device, which parses them and displays them on the user interface. The user then checks the presented business proposals and selects one.

[0819] 5. Feedback Data Collection

[0820] After the proposed work is performed, feedback data is collected, which is analyzed by the server and used to generate more efficient work suggestions.

[0821] Specific examples

[0822] Example 1: New graduates

[0823] New graduates say they are interested in sales jobs.

[0824] The server analyzes the response data and generates a business proposal for a sales position.

[0825] "Sales position" is displayed on the user terminal, and the new graduate selects it.

[0826] The sales staff will work according to the suggestions made by the sales staff and send their feedback to the server at a later date.

[0827] Example 2: Existing employees

[0828] An existing employee expressed a desire to transfer to the marketing department and responded to a survey.

[0829] The server analyzes the transfer request data and generates an internship proposal.

[0830] Existing employees agree to the internship proposal and gain experience working in the marketing department for a certain period of time.

[0831] After the internship ends, feedback is collected and a final transfer proposal is generated.

[0832] Prompt Sentence Examples

[0833] "Here is the robot's data. Please provide the optimal business proposal.

[0834] {'current_task': 'welding', 'skills': ['welding', 'cutting'], 'experience': {'welding': 200, 'cutting': 100}}"

[0835] This system will enable optimal job assignments for new graduates and existing employees, as well as efficient allocation of automated equipment within the factory, thereby improving overall operational efficiency.

[0836] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0837] Program processing flow

[0838] Step 1:

[0839] Collection of survey response data

[0840] Input: Users (new graduates and existing employees) answer a job-related survey. The survey includes questions such as "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[0841] Operation: The user terminal sends the entered answer data to the server.

[0842] Output: Survey response data is stored on the server.

[0843] Step 2:

[0844] Transmission of data to the server and pre-processing

[0845] Input: Survey response data sent from the user's device.

[0846] Operation:

[0847] The server cleanses the received data (removes unnecessary data and fills in missing values) and normalizes it (standardizes the data format).

[0848] After cleansing and normalization, the data is tokenized and converted into a format that is easy for the GPT-3 model to parse.

[0849] Output: Preprocessed data.

[0850] Step 3:

[0851] Generate business proposals

[0852] Input: Preprocessed data.

[0853] Operation:

[0854] The server inputs the preprocessed data into a generative AI model (such as GPT-3) to generate business proposals.

[0855] For example, the following prompt could be input to a generative AI model: "Here is the robot's data. Please suggest the best task for it: {'current_task': 'welding', 'skills': ['welding', 'cutting'], 'experience': {'welding': 200, 'cutting': 100}}"

[0856] Output: The generated business proposal.

[0857] Step 4:

[0858] Presentation and selection of business proposals

[0859] Input: The generated business proposal.

[0860] Operation:

[0861] The server converts the generated business proposal into JSON format and sends it to the user's terminal.

[0862] The user terminal parses the JSON data and displays it on the user interface.

[0863] The user checks the presented business proposals and makes a selection.

[0864] Output: The business proposal selected by the user.

[0865] Step 5:

[0866] Feedback data collection

[0867] Input: Feedback on the job selected by the user.

[0868] Operation:

[0869] After carrying out the proposed work, the user enters feedback.

[0870] Feedback includes the difficulty of the task, the degree of accomplishment, and suggestions for improvement.

[0871] The server collects feedback data from the user terminals and stores it in a database.

[0872] Output: Collected feedback data.

[0873] Step 6:

[0874] Analyzing feedback data and generating improvement suggestions

[0875] Input: Collected feedback data.

[0876] Operation:

[0877] The server analyzes the feedback data and re-inputs it into the generative AI model to generate even more efficient business proposals.

[0878] Through this loop, the accuracy of business proposals is improved.

[0879] Output: A new and improved business proposal.

[0880] The above steps will enable new graduates and existing employees to be assigned to the right jobs, as well as enable the efficient allocation of automated equipment within the factory, thereby improving overall work efficiency.

[0881] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0882] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis using an emotion engine, and a user interface.

[0883] System operation and program processing

[0884] 1. Survey collection

[0885] User: New graduates or existing employees log in to the system and access the designated survey page. To log in, they must enter their user ID and password.

[0886] Terminal: Sends the login information entered by the user to the server.

[0887] 2. Data reception and preparation for analysis

[0888] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[0889] On the device: After successful authentication, the survey page is displayed to the user.

[0890] 3. Survey responses

[0891] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[0892] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[0893] 4. Collecting survey and sentiment data

[0894] Server: Receives the survey response data and stores it in the database using an INSERT query.

[0895] On the device: While the user is answering the survey, the emotion engine analyzes the user's facial expressions, tone of voice, and the emotion of the text in real time to generate emotion data.

[0896] Server: Receives emotion data and stores it together with the survey response data.

[0897] 5. Data Preprocessing and Analysis

[0898] Server: Preprocesses the received survey response data and sentiment data, converting them into a format suitable for analysis, including data normalization and text tokenization.

[0899] Server: Inputs the preprocessed data into the generative AI model.

[0900] 6. Business proposal generation and emotional feedback

[0901] Server: The generative AI model generates business proposals and returns the results to the server.

[0902] Server: Analyzes real-time user sentiment data regarding the proposal content and evaluates the suitability of the business proposal.

[0903] Server: Selects the appropriate proposal and generates it in JSON format.

[0904] 7. Presentation of business proposal

[0905] Server: The generated JSON data is sent to the user's device as a REST API response.

[0906] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[0907] User: Review the proposed work and select the work they wish to do.

[0908] 8. Transfer Requests and Internship Exams

[0909] Server: For existing employees, the server also collects questionnaire responses based on transfer preferences and generates internship exam proposals. It also has a means of acquiring emotional data and analyzing it in real time.

[0910] Terminal: The proposal is displayed in the user interface and the user is asked to confirm whether or not to accept the internship attempt.

[0911] 9. Gathering feedback and final proposal

[0912] Server: Analyzes the feedback and sentiment data collected during the internship and generates the final transfer proposal.

[0913] Server: Presents the final proposal to the user and displays it in the user interface.

[0914] User: Review the final proposal and choose whether to accept it.

[0915] Example of a system

[0916] Example 1: Tanaka-san (new graduate):

[0917] In the survey, participants indicated that they wanted to work in sales and marketing and had previous experience in sales. Real-time emotional data was also collected.

[0918] The server analyzes the data and generates suggestions for "sales jobs" and "marketing jobs," taking into account sentiment data regarding the suggestions.

[0919] Tanaka chooses "sales" and this is reflected in his career plan.

[0920] Example 2: Sato-san (existing employee):

[0921] They will then be asked to fill out a questionnaire to request a transfer to the marketing department and take an internship exam. Feedback, including sentiment data, will be collected during the internship.

[0922] After completing the training, the feedback is analyzed and a formal transfer to the marketing department is proposed.

[0923] This allows the system to assign new graduates and existing employees to tasks that are best suited to them, reducing job mismatches, and also provides more accurate suggestions by taking into account users' emotional data.

[0924] The processing flow will be explained below.

[0925] Step 1:

[0926] User: New graduates or existing employees log in to the system and access the survey page. To log in, they must enter their user ID and password.

[0927] Terminal: Sends the login information entered by the user to the server.

[0928] Step 2:

[0929] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[0930] On the device: After successful authentication, the survey page is displayed to the user.

[0931] Step 3:

[0932] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[0933] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[0934] Step 4:

[0935] On the device: While the user is answering the survey, the emotion engine analyzes the user's facial expressions, tone of voice, and the sentiment of the text in real time.

[0936] Terminal: The emotion engine analyzes emotion data in real time and sends it to the server.

[0937] Step 5:

[0938] Server: Receives the survey response data and sentiment data and stores them in the database using an INSERT query.

[0939] Step 6:

[0940] Server: Preprocesses the received survey response data and sentiment data, cleansing and normalizing the data, and tokenizing the text data.

[0941] Step 7:

[0942] Server: Inputs the preprocessed data into the generative AI model to generate optimal business proposals.

[0943] Server: The generative AI model generates business proposals and returns the results to the server.

[0944] Step 8:

[0945] Server: Evaluates the collected emotional data for the proposed work content and selects work proposals with positive user emotional data.

[0946] Server: Generates the selected business proposals in JSON format.

[0947] Step 9:

[0948] Server: The generated JSON data is sent to the user's device as a REST API response.

[0949] Step 10:

[0950] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[0951] User: Review the proposed work and select the work they wish to do.

[0952] Step 11:

[0953] Terminal: Sends the task selected by the user to the server.

[0954] Server: Saves the user's selection in the database and updates the user's career plan.

[0955] Step 12:

[0956] Users: Existing employees answer a questionnaire based on their transfer preferences, including questions about their preferred department, past work experience, and skill set.

[0957] Terminal: Sends the survey response data and emotion data to the server.

[0958] Step 13:

[0959] Server: Receives the survey response data and sentiment data and performs preprocessing, such as data cleansing, normalization, and tokenization of text data.

[0960] Step 14:

[0961] Server: The preprocessed data is fed into a generative AI model to generate internship exam suggestions, taking into account emotional data.

[0962] Server: Generates the proposed content in JSON format and sends it to the user's device.

[0963] Step 15:

[0964] Terminal: The submitted proposal is displayed on the user interface and the user is asked whether or not to carry out the internship trial.

[0965] User: Choose whether to conduct an internship trial.

[0966] Step 16:

[0967] Server: Collects user feedback and sentiment data during the internship period. The collected data is stored in a database.

[0968] Step 17:

[0969] Server: After the internship period ends, the feedback data and sentiment data are analyzed to generate a final transfer proposal.

[0970] Server: Generates the final proposal in JSON format and sends it to the user's device.

[0971] Step 18:

[0972] Terminal: The final proposal is displayed in the user interface.

[0973] User: Review the final proposal and choose whether to accept it.

[0974] Example 2

[0975] 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."

[0976] It is important to accurately understand the preferences and aptitudes of new graduates and existing employees to reduce job mismatches, but conventional methods have the problem of low accuracy in proposals because they do not take into account user emotional data. Furthermore, when it comes to transfers for existing employees, feedback data from internships has not been effectively utilized, resulting in a lack of appropriateness in transfer proposals. There is a need to solve these issues.

[0977] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0978] In this invention, the server includes means for collecting and analyzing emotional data of the user while answering the questionnaire, means for evaluating the suitability of a job proposal using the emotional data, and means for analyzing the feedback data and emotional data during the internship period and generating a final transfer proposal, thereby enabling highly accurate job proposals and transfer proposals that take the user's emotional data into consideration.

[0979] "Questionnaire response data" refers to response information to questions entered by users into the system.

[0980] A "server" is a computer system connected to a network that processes and stores data and manages communications with other terminals.

[0981] A "generative AI model" refers to an artificial intelligence model that uses deep learning technology to analyze data and make predictions.

[0982] "Emotional data" refers to data that represents the user's emotional state analyzed from facial expressions, tone of voice, text content, etc.

[0983] "Preprocessing" refers to a series of operations that normalize and organize data prior to analysis, converting it into a format suitable for analysis.

[0984] "Business proposal" refers to the industry, job content, career plan, etc. proposed to the user.

[0985] An "internship test" refers to an experiment in which an existing employee undergoes work experience for a certain period of time in the department to which they wish to be transferred, and the results are evaluated.

[0986] "Feedback Data" refers to data regarding user opinions, evaluations, and performance collected during the internship period.

[0987] "User interface" refers to the screens and operating means provided for the user and the system to exchange information.

[0988] This invention relates to a system for allocating new graduates and existing employees to the most suitable jobs and reducing job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis, and a user interface.

[0989] Hardware and software used

[0990] Server: A device that processes and stores data and manages communications with other terminals, and is equipped with multiple high-performance processors and large-capacity memory.

[0991] Database: Uses an RDBMS such as MySQL or PostgreSQL.

[0992] Generative AI model: Uses OpenAI's GPT-3 or similar deep learning models.

[0993] Sentiment analysis engine: Use facial recognition APIs such as Amazon Rekognition and speech analysis APIs such as Google Cloud Speech-to-Text.

[0994] Terminal: A device used by users to answer questionnaires or take internship exams, and is typically a personal computer or tablet equipped with a camera and microphone.

[0995] Browser: Use a web browser such as Chrome or Firefox.

[0996] System operation and concrete examples

[0997] Survey collection

[0998] Users log in to the system and access the questionnaire page. A user ID and password are required to log in. Users answer questions such as "jobs they are interested in," "past experience," "strengths and weaknesses," and "desired career path."

[0999] The terminal sends the user's login information to the server, and if authentication is successful, a questionnaire page is displayed.

[1000] Data storage and sentiment analysis

[1001] The server stores the received survey data in a database. Using facial expression recognition APIs and voice analysis APIs, it analyzes emotional data from the user's facial expressions and tone of voice in real time and stores the data in the database.

[1002] Data preprocessing and analysis using generative AI models

[1003] The server normalizes the survey data and sentiment data, tokenizes the text data, and inputs this into a generative AI model to generate business proposals. For example, OpenAI's GPT-3 model is used.

[1004] The generated business proposals are evaluated for suitability using emotional data, and appropriate proposals are selected.

[1005] Presentation of business proposals and user selection

[1006] The server converts the selected business proposal into JSON format and sends it to the terminal via REST API.

[1007] The device parses the JSON data and displays the proposed tasks on the user interface. The user can then review the proposed tasks and select the desired task.

[1008] Specific examples

[1009] Example 1: A new graduate logs into the system and submits a questionnaire indicating their preference for "sales" and "marketing." The server uses a generative AI model and sentiment analysis to create proposals for both "sales" and "marketing." After evaluating the suitability, it is determined that sales is the most suitable. Based on this proposal, the new graduate selects a sales position.

[1010] Example 2: An existing employee requests a transfer to the marketing department and conducts an internship test. During the internship, sentiment data and feedback data are collected, and a transfer proposal to the marketing department is finally generated.

[1011] Prompt Sentence Examples

[1012] 1. "A new graduate indicated that he / she would like to work in sales and marketing and has experience in sales. Please explain what kind of business proposals will be generated, including emotional data."

[1013] 2. "When an existing employee requests a transfer to the marketing department, explain how feedback data is collected through an intern exam and a final proposal is generated."

[1014] As a result, this system makes job and transfer proposals that take into maximum consideration the wishes and aptitudes of new graduates and existing employees, thereby reducing job mismatches.

[1015] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1016] Step 1:

[1017] The user logs in to the system. The user enters their user ID and password on the login screen and clicks the "Login" button.

[1018] Input: User ID, Password

[1019] Output: Login request

[1020] Step 2:

[1021] The device sends the user's login information to the server. The login request is sent using the HTTPS protocol.

[1022] Input: Login request

[1023] Output: Authentication request to the server

[1024] Step 3:

[1025] The server authenticates the received login information by checking it against its database, and if authentication is successful, starts a user session.

[1026] Input: Authentication request (user ID, password)

[1027] Output: Authentication result (success or failure)

[1028] Step 4:

[1029] After successful authentication, the device displays the survey page to the user. The survey form is rendered using HTML and CSS.

[1030] Input: Authentication result (success)

[1031] Output: Survey page

[1032] Step 5:

[1033] Users access the survey page and answer questions, entering information such as "interesting work," "past experience," "strengths and weaknesses," and "desired career path."

[1034] Input: Survey response

[1035] Output: Survey data

[1036] Step 6:

[1037] The device uses a camera and microphone to capture facial expressions and tone of voice in real time while the user answers the survey.

[1038] Input: Real-time facial expressions and voice of the user

[1039] Output: Emotion data

[1040] Step 7:

[1041] The terminal sends the answered questionnaire data to the server by pressing the send button.

[1042] Input: Survey data

[1043] Output: Request to send survey data to the server

[1044] Step 8:

[1045] The server stores the received survey data in the database using an INSERT query.

[1046] Input: Survey data

[1047] Output: Update database (save survey data)

[1048] Step 9:

[1049] The server uses an emotion analysis engine to analyze the facial expressions and tone of voice sent from the device and generate emotion data, which is then stored in a database.

[1050] Input: facial expression data, voice data

[1051] Output: Saved emotion data

[1052] Step 10:

[1053] The server performs preprocessing of the received questionnaire data and emotion data, such as cleaning text data and normalizing numerical data.

[1054] Input: Survey data, emotion data

[1055] Output: Preprocessed data

[1056] Step 11:

[1057] The server inputs the preprocessed data into a generative AI model to generate business proposals. The AI ​​model used is a generative AI model such as GPT-3.

[1058] Input: Preprocessed data

[1059] Output: Business proposal data

[1060] Step 12:

[1061] The server evaluates the suitability of the generated business proposals using emotional data analysis and selects the most appropriate proposal.

[1062] Input: Business proposal data, emotion data

[1063] Output: Evaluated business proposal

[1064] Step 13:

[1065] The server converts the selected business proposal into JSON format and sends it to the terminal via REST API.

[1066] Input: Evaluated Business Proposal

[1067] Output: Business proposal data in JSON format

[1068] Step 14:

[1069] The device parses the JSON data received from the server and displays the suggestions in the user interface.

[1070] Input: Business proposal data in JSON format

[1071] Output: Displayed business proposal

[1072] Step 15:

[1073] The user checks the displayed business proposals and selects the business he or she desires.

[1074] Input: Business proposal list

[1075] Output: Selected tasks

[1076] Step 16:

[1077] The terminal transmits the business information selected by the user to the server.

[1078] Input: Selected business

[1079] Output: Request to send selection information to the server

[1080] Step 17:

[1081] The server saves the user's selections in a database and updates the career plan.

[1082] Input: Selected business information

[1083] Output: Updated career plan

[1084] The goal is that by going through all the steps of this system, users will be able to receive the best job offers based on their preferences and aptitudes.

[1085] (Application example 2)

[1086] 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."

[1087] In companies, mismatched work assignments between new graduates and existing employees can lead to reduced efficiency and motivation. In particular, employees can be assigned to work that does not match their skills or career path, which can lead to a decline in performance. In addition, while appropriate personnel assignment is crucial for operating online or virtual stores, traditional methods make it difficult to propose optimal work assignments that take into account individual characteristics and emotions.

[1088] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting questionnaire response data, means for transmitting the collected data to the server, means for preprocessing the data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate business proposals, means for evaluating the proposals and selecting an appropriate proposal, means for presenting the selected business proposals to the user, means for saving the user's selections on the server, means for analyzing emotion data from input text, and means for adjusting the business proposals based on the emotion data. This makes it possible to achieve optimal job assignments that take into account the characteristics and emotions of employees and improve the efficiency of corporate human resource utilization.

[1089] "Survey response data" refers to response data that contains information about the work desired by new graduates and existing employees.

[1090] A "server" is a computer system that receives, stores, and processes questionnaire response data and emotion data.

[1091] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis.

[1092] A "generative AI model" is an artificial intelligence model that generates business proposals based on preprocessed data.

[1093] "Job proposals" refer to the optimal jobs that the generative AI model proposes to new graduates and existing employees.

[1094] "Evaluation" is the process of determining the appropriateness of the generated business proposals.

[1095] "Users" refers to new graduates and existing employees who use this system.

[1096] "Emotion data" refers to data related to emotions analyzed from the user's input text, facial expressions, and tone of voice.

[1097] "Adjustment" refers to modifying or optimizing business proposals based on analyzed emotional data.

[1098] An "internship test" refers to a trial work experience in the department to which an existing employee wishes to be transferred.

[1099] "Feedback data" refers to data that records evaluations and impressions collected during the internship period.

[1100] The "final transfer proposal" refers to the final proposed transfer job based on the results of analyzing the feedback data.

[1101] This invention provides a system for assigning new graduates and existing employees to the most suitable jobs and reducing job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis using an emotion engine, and a user interface.

[1102] The specific operation of the system is explained below.

[1103] Hardware and software used

[1104] Hardware: Smartphone (Android or iOS)

[1105] Software: Python, EmotionEngine, JobMatchGPT, JSON, REST API

[1106] Data flow and processing overview

[1107] 1. Collection of survey response data: Users (new graduates and existing employees) access a designated survey page using their smartphones and answer questions about their work experience and desired work. The survey data is then sent from the device to the server.

[1108] 2. Emotion data collection: While the user is answering the questionnaire, EmotionEngine analyzes the emotional data from the text input, facial expressions, and tone of voice in real time. This emotional data is also sent to the server.

[1109] 3. Data preprocessing and analysis: The server preprocesses the received survey response data and sentiment data, converting them into a format suitable for analysis. Preprocessing includes data normalization and tokenization. Next, this data is input into a generative AI model (JobMatchGPT) to generate job suggestions.

[1110] 4. Evaluation and adjustment of business proposals: The server evaluates the generated business proposals based on the emotional data and selects the most appropriate proposal. The evaluation takes into account the results of emotional analysis using the Emotion Engine.

[1111] 5. Presentation of business proposals: The selected business proposals are converted into JSON format and sent to the user's device via the REST API. The user can then review the business proposals on their device and select the desired business.

[1112] 6. Transfer preference and internship exam: For existing employees, internship exams are proposed based on their transfer preference. Feedback data during the internship period is also collected along with emotion data and analyzed on the server.

[1113] 7. Generation of final transfer proposal: Based on the analysis results of the feedback data, the server generates a final transfer proposal and presents it to the user through the user interface.

[1114] Examples of specific examples and prompts

[1115] Example: Mr. Tanaka (a new graduate) is interested in running a virtual store and answers the questionnaire saying he is interested in "virtual store management." The system will propose the most suitable job, including emotional data, and the job Mr. Tanaka selects will be reflected in his career plan.

[1116] Example prompt sentence:

[1117] "I'm interested in working in a virtual store. I have experience in customer service and would like to gain more technical knowledge. Which role would be right for me?"

[1118] In this way, this system aims to reduce work mismatches and improve employee performance by analyzing users' characteristics and wishes in detail and making work suggestions.

[1119] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1120] Step 1:

[1121] Users access the questionnaire page using their smartphones and answer questions about their work experience and desired work. The data entered includes work experience, areas of interest, skills, career path, etc. This data is sent from the device to the server.

[1122] Step 2:

[1123] The server receives the survey response data sent from the terminal and stores it in a database. The input is the survey response data, and the output is the data stored in the database.

[1124] Step 3:

[1125] While the user is answering the questionnaire, EmotionEngine collects emotional data from text input, facial expressions, and tone of voice. This emotional data is sent from the device to the server. The input is text, facial expressions, and voice data, and the output is emotional data analyzed in real time.

[1126] Step 4:

[1127] The server preprocesses the received survey response data and emotion data. Preprocessing includes normalizing and tokenizing the data to convert it into a format suitable for analysis. The input is the raw survey response data and emotion data, and the output is the preprocessed data.

[1128] Step 5:

[1129] Based on the preprocessed data, the server uses a generative AI model (JobMatchGPT) to generate job suggestions. The input is the preprocessed data, and the output is job suggestions. This generation process takes into account skills, experience, and emotional data.

[1130] Step 6:

[1131] The server evaluates the generated business proposals based on emotional data and selects the most suitable proposal. The evaluation also takes into account the results of emotional analysis using EmotionEngine. The input is the business proposal and emotional data, and the output is a selected business proposal that reflects the evaluation results.

[1132] Step 7:

[1133] The selected business proposal is converted into JSON format and sent to the user's device via REST API. The user reviews the provided proposals and selects the desired business. The input is the selected business proposal, and the output is the business selected by the user.

[1134] Step 8:

[1135] For existing employees, an internship exam is proposed based on their transfer preference. The user decides whether to take the internship exam. The input is the transfer preference data and the proposal content, and the output is the user's choice of whether to accept or reject the internship exam.

[1136] Step 9:

[1137] During the internship period, the server collects feedback data from users and emotion data updated in real time. The input is the feedback data and emotion data, and the output is a final transfer proposal including the analysis results.

[1138] Step 10:

[1139] Based on the analysis results of the feedback data and emotion data, the server generates a final transfer proposal and presents it to the user through the user interface. The user reviews the final proposal and decides whether to accept the transfer. The input is the analyzed data, and the output is the final transfer proposal and its selection result.

[1140] The above are the specific processing steps for providing an optimal task allocation that takes into consideration the characteristics and emotions of the user.

[1141] 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.

[1142] 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.

[1143] 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.

[1144] [Third embodiment]

[1145] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1146] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1147] 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).

[1148] 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.

[1149] 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.

[1150] 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).

[1151] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1152] 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.

[1153] 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.

[1154] 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.

[1155] 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.

[1156] 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."

[1157] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, and a user interface.

[1158] System operation and program processing

[1159] 1. Survey collection

[1160] User: A new graduate or existing employee logs into the system and accesses the designated survey page.

[1161] Terminal: The user answers the questions in the survey and presses the send button to send the answer data to the server. Examples of questions include "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[1162] Example: Mr. Tanaka says he is interested in sales and marketing positions and notes that he has prior sales experience.

[1163] 2. Data reception and preparation for analysis

[1164] Server: Receives the survey response data and stores it in a database.

[1165] Server: Cleanses and normalizes the received data, and converts text data into a format suitable for analysis by tokenizing it, for example. For example, it converts the contents of a survey into specific keywords so that the model can easily understand them.

[1166] 3. Data analysis and business proposal generation

[1167] Server: The preprocessed data is input into a generative AI model (such as GPT-3) to generate optimal job suggestions. The model outputs multiple job suggestions based on the user's preferences and aptitude.

[1168] Server: Evaluates the generated job proposals and selects the most appropriate one. For example, "sales position" and "marketing position" are selected from the generated proposals.

[1169] 4. Presentation of business proposal

[1170] Server: Generates the selected business proposals in JSON format and sends them to the user's device.

[1171] Terminal: Parses the JSON data sent and displays it in the user interface. The user can then review and select the business proposals presented.

[1172] Example: Tanaka's screen shows the suggestions "Sales" and "Marketing", and she chooses Sales.

[1173] 5. Propose an internship test and collect feedback

[1174] Server: For existing employees, the server analyzes the questionnaire responses based on their transfer preferences and generates and presents internship proposals. It also includes a function to collect feedback data during the internship period.

[1175] Example: Mr. Sato wants to transfer to the marketing department and will take an internship exam. After the internship period ends, Mr. Sato will submit his opinion through the feedback form.

[1176] 6. Generate and present the final transfer proposal

[1177] Server: After the internship ends, the collected feedback data is analyzed and a final transfer proposal is generated. The generated proposal is sent to the user's device and displayed on the user interface.

[1178] Example: After analyzing Sato's feedback, it is determined that a formal transfer to the Marketing department is appropriate, and a final proposal is made.

[1179] Example of a system

[1180] Example 1: Tanaka-san (new graduate):

[1181] In the survey, he indicated that he wanted to work in "sales" and "marketing" and that he had previous experience in sales work.

[1182] The server analyzes the data and generates suggestions for "sales jobs" and "marketing jobs."

[1183] Tanaka chooses "sales" and this is reflected in his career plan.

[1184] Example 2: Sato-san (existing employee):

[1185] In the survey, I expressed a desire to be transferred to the marketing department.

[1186] I accepted the internship offer and experienced working in the marketing department for one month.

[1187] After completing the course, he provided feedback and was eventually offered a permanent transfer to the Marketing department, which he accepted.

[1188] This system allows new graduates and existing employees to be assigned to tasks that best suit them, reducing job mismatches and supporting long-term career development within the company.

[1189] The processing flow will be explained below.

[1190] Step 1:

[1191] User: New graduates or existing employees log in to the system and access the survey page. To log in, they must enter their user ID and password.

[1192] Terminal: Sends the login information entered by the user to the server.

[1193] Step 2:

[1194] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[1195] On the device: After successful authentication, the survey page is displayed to the user.

[1196] Step 3:

[1197] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[1198] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[1199] Step 4:

[1200] Server: Receives the survey response data and stores it in the database using an INSERT query.

[1201] Server: Preprocesses the received data and converts it into a format suitable for analysis by performing text normalization, tokenization, etc.

[1202] Step 5:

[1203] Server: Inputs the preprocessed data into the generative AI model, which receives the data via an API.

[1204] Server: The generative AI model generates business proposals and returns the results to the server.

[1205] Step 6:

[1206] Server: Evaluates the generated business proposals and selects the most appropriate one. The proposals are scored and the one with the highest score is selected.

[1207] Server: Generates the selected business proposals in JSON format.

[1208] Step 7:

[1209] Server: The generated JSON data is sent to the user's device as a REST API response.

[1210] Step 8:

[1211] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[1212] User: Review the proposed work and select the work they wish to do.

[1213] Step 9:

[1214] Terminal: Sends the user's selection to the server.

[1215] Server: Receives the selections and stores them in the database, updating the user's career plan.

[1216] Step 10:

[1217] Server: For existing employees, a means is provided to collect questionnaire response data based on transfer preferences and generate internship trial proposals. Proposals for internship trials are generated and displayed on the user interface as well.

[1218] User: Confirms and accepts the internship attempt and also completes and submits feedback during the internship period.

[1219] Step 11:

[1220] Server: After the internship ends, analyze the collected feedback data and generate a final transfer proposal.

[1221] Server: Sends the final proposal to the user and displays it in the user interface.

[1222] Step 12:

[1223] User: Review the final proposal and choose whether to accept it.

[1224] The above is the specific processing flow of the "JoB Match GPT" system.

[1225] Example 1

[1226] 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."

[1227] Modern companies require both new graduates and existing employees to be assigned to the most appropriate jobs based on their preferences and aptitudes. However, traditional manual job assignment methods are prone to mismatches and are labor-intensive and time-consuming, so a system that efficiently and effectively proposes jobs is needed. Furthermore, there is a lack of effective methods for proposing internships based on employee transfer requests and for collecting and analyzing subsequent feedback. This makes it difficult to optimize transfers and career plans, and to support long-term career development within the company.

[1228] 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.

[1229] In this invention, the server includes means for cleansing and normalizing survey data, means for tokenizing the data and converting it into a format suitable for analysis, means for sending the generated job proposals to the user's device in JSON format and displaying them on a user interface, means for preprocessing the survey response data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate job proposals, means for evaluating the generated job proposals and selecting an appropriate proposal, means for presenting the selected job proposal to the user, and means for saving the user's selections on the server. This makes it possible to efficiently collect and analyze data on the jobs desired by new graduates and existing employees, and to generate and present optimal job proposals and transfer proposals. This reduces job mismatches and supports long-term career development within the company.

[1230] "Survey response data" refers to data that includes information provided by new graduates and existing employees regarding the work they would like to do.

[1231] A "server" is a computer system that receives, stores, analyzes, and generates proposals from survey response data.

[1232] "Preprocessing" refers to the process of cleansing, normalizing, and converting collected survey response data into a format suitable for analysis.

[1233] A "generative AI model" is an artificial intelligence model used to analyze survey response data and generate business proposals.

[1234] "Business proposals" are optimal business operations proposed by the generative AI model based on the user's wishes and aptitude.

[1235] An "internship exam" refers to a trial period during which existing employees gain experience in the work they wish to transfer to.

[1236] "Feedback data" refers to data that includes the opinions and impressions of existing employees, collected during the internship test period.

[1237] "User interface" refers to the screen and operating environment through which users operate the system and confirm business proposals and internship exam proposals.

[1238] "Cleansing" is the process of removing duplicates and errors from survey response data and organizing the data.

[1239] "Normalization" is the process of standardizing the format of survey response data and converting it into a form suitable for analysis.

[1240] "Tokenization" is the process of breaking down text data into words and phrases, making it easier to analyze.

[1241] "JSON format" is a data format used to structure data and send it to a user's device.

[1242] A "user terminal" is a device such as a computer or smartphone that a user uses to access the system and respond to business proposals and questionnaires.

[1243] MODE FOR CARRYING OUT THE INVENTION

[1244] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, and a user interface.

[1245] Survey collection

[1246] Users log in to the system as new graduates or existing employees. A dedicated ID and password are used to log in. After logging in, they are redirected to a survey page where they answer specified questions. For example, questions include "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?" After the user has finished answering, they press the send button to send the survey response data to the server.

[1247] Data reception and preparation for analysis

[1248] The server receives the survey response data sent by users and stores it in a database. Next, the data is cleansed (removing duplicates and errors) and normalized (standardizing the format). Furthermore, the text data is tokenized and converted into a format that can be analyzed by a generative AI model (e.g., GPT-3).

[1249] Data analysis and business proposal generation

[1250] The server inputs the preprocessed data into the generative AI model to generate the optimal job proposal. For example, the prompt statement could be "Please generate the optimal job proposal for Tanaka. Tanaka has experience in sales and marketing." Based on this prompt, the generative AI model outputs job proposals such as "sales position" and "marketing position." The multiple job proposals generated are evaluated, and the most appropriate proposal is selected.

[1251] Presenting business proposals

[1252] The server generates the selected business proposals in JSON format and sends them to the user's device. The device parses the received JSON data and displays it on the user interface, allowing the user to check and select from the presented business proposals.

[1253] Internship test proposal and feedback collection

[1254] The system analyzes questionnaire responses from existing employees based on their transfer preferences and generates internship exam proposals. The server stores and analyzes feedback data collected during the internship period. For example, if Mr. Sato requests a transfer to the marketing department, he takes the internship exam and submits his feedback after completing it.

[1255] Generate and present the final transfer proposal

[1256] The server analyzes the collected feedback data after the internship period and generates a final transfer proposal, which is sent to the user's device and displayed on the user interface.

[1257] Specific examples

[1258] Example 1: Mr. Tanaka, a new graduate

[1259] In the questionnaire, Tanaka indicated that he would like to work in "sales" and "marketing" and that he has experience in sales work.

[1260] The server analyzes this and generates job proposals for "sales positions" and "marketing positions."

[1261] Tanaka chose a sales position, which is reflected in his career plan.

[1262] Example 2: Existing employee Sato

[1263] In the survey, Sato expressed a desire to be transferred to the marketing department.

[1264] He accepted the internship offer and gained experience working in the marketing department for one month.

[1265] After completing the internship, the employee submits feedback, which is then analyzed by the server, who then makes a formal proposal for transfer to the marketing department.

[1266] This system allows new graduates and existing employees to be assigned to jobs that best suit them, reducing job mismatches and supporting long-term career development within the company.

[1267] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1268] Program processing flow

[1269] Step 1: Survey collection

[1270] 1. A user logs into the system

[1271] Input: User ID and password

[1272] Output: The user is redirected to the survey page after successful login.

[1273] Specific operation: The user enters their ID and password and clicks the login button. For example, Mr. Tanaka logs in by entering his ID "tanaka123" and password.

[1274] 2. Visit the survey page and answer the questions

[1275] Input: User's survey response

[1276] Output: User survey response data

[1277] Specific operation: The user answers the survey questions and presses the submit button. For example, Mr. Tanaka answers that he is interested in "sales and marketing positions" and has experience in sales work.

[1278] 3. Send the survey response data to the server

[1279] Input: User survey response data

[1280] Output: Survey data sent to the server

[1281] Specific operation: The user clicks the send button and the survey data is sent to the server. For example, Tanaka's survey data is recorded in the server's database.

[1282] Step 2: Receive data and prepare for analysis

[1283] 1. Receive survey response data

[1284] Input: Survey data sent to the server

[1285] Output: Survey data stored in a database

[1286] Specific operation: The server receives the survey data and stores it in a database. For example, Tanaka's survey response data is recorded in the database.

[1287] 2. Cleanse and normalize the data

[1288] Input: Survey data in the database

[1289] Output: Cleansed and normalized data

[1290] What it does: The server removes duplicates and errors from data and standardizes formats. For example, it automatically corrects data inconsistencies like "Tanaka" and "Tanaka."

[1291] 3. Tokenize the data

[1292] Input: Cleansed and normalized data

[1293] Output: Tokenized data

[1294] Specific operation: Text data is divided into words and phrases and converted into a format that can be understood by the generative AI model. For example, keywords such as "sales job" and "sales work" are tokenized.

[1295] Step 3: Data analysis and business proposal generation

[1296] 1. Feed preprocessed data into a generative AI model

[1297] Input: Tokenized data

[1298] Output: Multiple business proposals

[1299] Specific operation: The cleansed and normalized data is input into a generative AI model (e.g., GPT-3). The prompt sentence is "Please generate the optimal business proposal for Mr. Tanaka. Mr. Tanaka has experience in sales and marketing."

[1300] 2. Generate optimal business proposals

[1301] Input: Output data from a generative AI model

[1302] Output: Multiple business proposals

[1303] Specific operation: The server receives the job proposals generated by the generative AI model. For example, job proposals for "sales positions" and "marketing positions" are output.

[1304] 3. Evaluate and select the generated business proposals

[1305] Input: Generated business proposal

[1306] Output: Selected business proposals

[1307] Specific operation: The server evaluates job proposals based on multiple evaluation criteria and selects the most appropriate proposal. For example, "sales position" and "marketing position" are evaluated and selected as the most suitable.

[1308] Step 4: Present the business proposal

[1309] 1. Generate a business proposal in JSON format

[1310] Input: Selected business proposal

[1311] Output: JSON format data

[1312] Specific operation: The selected job proposals are generated in JSON format and sent to the user's device. For example, proposals for "sales positions" and "marketing positions" are generated as JSON format data.

[1313] 2. Parse and display the proposal data on the device

[1314] Input: JSON format data

[1315] Output: Data displayed in the user interface

[1316] Specific operation: The device parses the received JSON data and displays it in the user interface. For example, Tanaka's screen will display suggestions for "sales" and "marketing."

[1317] 3. The user selects a business proposal

[1318] Input: Business proposal displayed on the user interface

[1319] Output: User's selection

[1320] Specific operation: The user checks the presented job proposals and selects one. For example, Mr. Tanaka selects "Sales position."

[1321] Step 5: Propose an internship test and gather feedback

[1322] 1. Generate internship exam proposals

[1323] Input: Survey data based on transfer preferences

[1324] Output: Internship Exam Proposal

[1325] Specific operation: The server analyzes the transfer request data of existing employees and generates an internship exam proposal. For example, it generates an internship exam proposal for Mr. Sato in the marketing department.

[1326] 2. Gather feedback during the internship

[1327] Input: Feedback data during internship period

[1328] Output: Collected feedback data

[1329] Specific operation: The server stores the feedback data collected during the internship. For example, Mr. Sato sends feedback about the work of the marketing department.

[1330] Step 6: Generate and present the final transfer proposal

[1331] 1. Analyze feedback data

[1332] Input: Collected feedback data

[1333] Output: Analysis results

[1334] Specific operation: The server analyzes the feedback data and generates the optimal transfer proposal. For example, Sato-san's feedback is analyzed.

[1335] 2. Generate the final transfer proposal

[1336] Input: Analysis results

[1337] Output: Final transfer proposal

[1338] Specific operation: The server generates a final transfer proposal based on the analysis results. For example, a "formal transfer proposal to the marketing department" is generated for Sato-san.

[1339] 3. Send the final proposal to the device and present it

[1340] Input: Final Transfer Proposal

[1341] Output: The final proposal displayed in the user interface

[1342] Specific operation: The server sends the final proposal to the user's device and displays it on the user interface. For example, "Formal transfer proposal to the marketing department" is displayed on Mr. Sato's screen.

[1343] (Application example 1)

[1344] 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."

[1345] With conventional personnel allocation systems, it is difficult to assign the right people to new graduates and existing employees, leading to job mismatches. Furthermore, automated equipment in factories is rarely allocated to the most appropriate departments, making it difficult to improve productivity. Furthermore, there is a lack of effective means for providing work proposals and managing feedback. This creates challenges that make it difficult to efficiently manage employees and automated equipment and optimally assign them to work.

[1346] 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.

[1347] In this invention, the server includes means for collecting survey response data regarding the work desired by new graduates and existing employees, means for transmitting the survey response data to the server, means for preprocessing the collected survey response data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate work proposals, means for evaluating the generated work proposals and selecting an appropriate proposal, means for presenting the selected work proposals to the user, means for saving the user's selections on the server, means for collecting data from the automated device and analyzing the work assigned to the device, means for presenting optimal work proposals to the automated device based on the generative AI model, means for collecting feedback on the presented work proposals, and means for analyzing the feedback data to improve work efficiency. This enables optimal work assignments for new graduates and existing employees as well as efficient department allocation of automated devices, thereby improving overall work efficiency.

[1348] "New graduates" refer to people who have recently graduated from an educational institution and are entering the workforce for the first time.

[1349] "Existing employees" refers to employees who are already employed by a company or organization and are currently working.

[1350] "Survey response data" refers to information obtained from new graduates and existing employees answering questions about their work.

[1351] "Server" refers to a computer system that collects, stores, analyzes, transmits, etc. data.

[1352] A "generative AI model" refers to a machine learning model that performs natural language processing and generates appropriate business proposals from input data.

[1353] "Work proposals" refer to proposals for work that the generative AI model determines to be most suitable for new graduates and existing employees.

[1354] "Feedback data" refers to information that indicates the results and opinions of users or automated devices when they perform a proposed task.

[1355] "Automated equipment" refers to machines and robots used to automate tasks in factories and other operating environments.

[1356] "Analysis" refers to the process of using collected data to extract information and identify patterns and trends.

[1357] "User" refers to new graduates, existing employees, or anyone authorized to review and decide on business proposals from these individuals.

[1358] "Work efficiency" refers to the ratio between the effectiveness of the work provided and the time it takes, and is a concept that aims to achieve high results in a short amount of time.

[1359] A "department" or "placement" refers to a position within a company or organization that is responsible for a specific task.

[1360] An "internship test" refers to an exam given to those seeking transfer to experience new work and confirm their suitability.

[1361] "Efficiency" refers to high productivity in carrying out designated tasks.

[1362] This invention relates to a system for assigning new graduates and existing employees to optimal work, and a system for efficiently allocating automated equipment within a factory to different departments. This system uses the following hardware and software to process data and perform calculations.

[1363] Hardware and Software

[1364] Server: A computer system for collecting, storing, analyzing, and transmitting data.

[1365] User device: A device (PC, smartphone, tablet, etc.) used to display survey responses and business proposals.

[1366] Generative AI model: A machine learning model (e.g., GPT-3) used to perform natural language processing and generate relevant business suggestions from input data.

[1367] API: Application Program Interface for sending, receiving, and processing data.

[1368] Overall system flow

[1369] 1. Collection of survey response data

[1370] New graduates and existing employees use user terminals to answer a questionnaire about the work they would like to do, which includes specific questions based on prompts.

[1371] For example, answer questions such as, "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[1372] 2. Data transmission to the server and pre-processing

[1373] The user terminal transmits the survey response data to the server, which cleanses and normalizes the received data and converts it into a format suitable for analysis.

[1374] 3. Generate business proposals

[1375] The server inputs the preprocessed data into a generative AI model to generate job suggestions. The generative AI model (e.g., GPT-3) generates optimal job suggestions, such as "sales positions" or "marketing positions," based on the input data.

[1376] 4. Presentation and selection of business proposals

[1377] The server sends the generated business proposals in JSON format to the user's device, which parses them and displays them on the user interface. The user then checks the presented business proposals and selects one.

[1378] 5. Feedback Data Collection

[1379] After the proposed work is performed, feedback data is collected, which is analyzed by the server and used to generate more efficient work suggestions.

[1380] Specific examples

[1381] Example 1: New graduates

[1382] New graduates say they are interested in sales jobs.

[1383] The server analyzes the response data and generates a business proposal for a sales position.

[1384] "Sales position" is displayed on the user terminal, and the new graduate selects it.

[1385] The sales staff will work according to the suggestions made by the sales staff and send their feedback to the server at a later date.

[1386] Example 2: Existing employees

[1387] An existing employee expressed a desire to transfer to the marketing department and responded to a survey.

[1388] The server analyzes the transfer request data and generates an internship proposal.

[1389] Existing employees agree to the internship proposal and gain experience working in the marketing department for a certain period of time.

[1390] After the internship ends, feedback is collected and a final transfer proposal is generated.

[1391] Prompt Sentence Examples

[1392] "Here is the robot's data. Please provide the optimal business proposal.

[1393] {'current_task': 'welding', 'skills': ['welding', 'cutting'], 'experience': {'welding': 200, 'cutting': 100}}"

[1394] This system will enable optimal job assignments for new graduates and existing employees, as well as efficient allocation of automated equipment within the factory, thereby improving overall operational efficiency.

[1395] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1396] Program processing flow

[1397] Step 1:

[1398] Collection of survey response data

[1399] Input: Users (new graduates and existing employees) answer a job-related survey. The survey includes questions such as "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[1400] Operation: The user terminal sends the entered answer data to the server.

[1401] Output: Survey response data is stored on the server.

[1402] Step 2:

[1403] Transmission of data to the server and pre-processing

[1404] Input: Survey response data sent from the user's device.

[1405] Operation:

[1406] The server cleanses the received data (removes unnecessary data and fills in missing values) and normalizes it (standardizes the data format).

[1407] After cleansing and normalization, the data is tokenized and converted into a format that is easy for the GPT-3 model to parse.

[1408] Output: Preprocessed data.

[1409] Step 3:

[1410] Generate business proposals

[1411] Input: Preprocessed data.

[1412] Operation:

[1413] The server inputs the preprocessed data into a generative AI model (such as GPT-3) to generate business proposals.

[1414] For example, the following prompt could be input to a generative AI model: "Here is the robot's data. Please suggest the best task for it: {'current_task': 'welding', 'skills': ['welding', 'cutting'], 'experience': {'welding': 200, 'cutting': 100}}"

[1415] Output: The generated business proposal.

[1416] Step 4:

[1417] Presentation and selection of business proposals

[1418] Input: The generated business proposal.

[1419] Operation:

[1420] The server converts the generated business proposal into JSON format and sends it to the user's terminal.

[1421] The user terminal parses the JSON data and displays it on the user interface.

[1422] The user checks the presented business proposals and makes a selection.

[1423] Output: The business proposal selected by the user.

[1424] Step 5:

[1425] Feedback data collection

[1426] Input: Feedback on the job selected by the user.

[1427] Operation:

[1428] After carrying out the proposed work, the user enters feedback.

[1429] Feedback includes the difficulty of the task, the degree of accomplishment, and suggestions for improvement.

[1430] The server collects feedback data from the user terminals and stores it in a database.

[1431] Output: Collected feedback data.

[1432] Step 6:

[1433] Analyzing feedback data and generating improvement suggestions

[1434] Input: Collected feedback data.

[1435] Operation:

[1436] The server analyzes the feedback data and re-inputs it into the generative AI model to generate even more efficient business proposals.

[1437] Through this loop, the accuracy of business proposals is improved.

[1438] Output: A new and improved business proposal.

[1439] The above steps will enable new graduates and existing employees to be assigned to the right jobs, as well as enable the efficient allocation of automated equipment within the factory, thereby improving overall work efficiency.

[1440] 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.

[1441] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis using an emotion engine, and a user interface.

[1442] System operation and program processing

[1443] 1. Survey collection

[1444] User: New graduates or existing employees log in to the system and access the designated survey page. To log in, they must enter their user ID and password.

[1445] Terminal: Sends the login information entered by the user to the server.

[1446] 2. Data reception and preparation for analysis

[1447] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[1448] On the device: After successful authentication, the survey page is displayed to the user.

[1449] 3. Survey responses

[1450] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[1451] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[1452] 4. Collecting survey and sentiment data

[1453] Server: Receives the survey response data and stores it in the database using an INSERT query.

[1454] On the device: While the user is answering the survey, the emotion engine analyzes the user's facial expressions, tone of voice, and the emotion of the text in real time to generate emotion data.

[1455] Server: Receives emotion data and stores it together with the survey response data.

[1456] 5. Data Preprocessing and Analysis

[1457] Server: Preprocesses the received survey response data and sentiment data, converting them into a format suitable for analysis, including data normalization and text tokenization.

[1458] Server: Inputs the preprocessed data into the generative AI model.

[1459] 6. Business proposal generation and emotional feedback

[1460] Server: The generative AI model generates business proposals and returns the results to the server.

[1461] Server: Analyzes real-time user sentiment data regarding the proposal content and evaluates the suitability of the business proposal.

[1462] Server: Selects the appropriate proposal and generates it in JSON format.

[1463] 7. Presentation of business proposal

[1464] Server: The generated JSON data is sent to the user's device as a REST API response.

[1465] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[1466] User: Review the proposed work and select the work they wish to do.

[1467] 8. Transfer Requests and Internship Exams

[1468] Server: For existing employees, the server also collects questionnaire responses based on transfer preferences and generates internship exam proposals. It also has a means of acquiring emotional data and analyzing it in real time.

[1469] Terminal: The proposal is displayed in the user interface and the user is asked to confirm whether or not to accept the internship attempt.

[1470] 9. Gathering feedback and final proposal

[1471] Server: Analyzes the feedback and sentiment data collected during the internship and generates the final transfer proposal.

[1472] Server: Presents the final proposal to the user and displays it in the user interface.

[1473] User: Review the final proposal and choose whether to accept it.

[1474] Example of a system

[1475] Example 1: Tanaka-san (new graduate):

[1476] In the survey, participants indicated that they wanted to work in sales and marketing and had previous experience in sales. Real-time emotional data was also collected.

[1477] The server analyzes the data and generates suggestions for "sales jobs" and "marketing jobs," taking into account sentiment data regarding the suggestions.

[1478] Tanaka chooses "sales" and this is reflected in his career plan.

[1479] Example 2: Sato-san (existing employee):

[1480] They will then be asked to fill out a questionnaire to request a transfer to the marketing department and take an internship exam. Feedback, including sentiment data, will be collected during the internship.

[1481] After completing the training, the feedback is analyzed and a formal transfer to the marketing department is proposed.

[1482] This allows the system to assign new graduates and existing employees to tasks that are best suited to them, reducing job mismatches, and also provides more accurate suggestions by taking into account users' emotional data.

[1483] The processing flow will be explained below.

[1484] Step 1:

[1485] User: New graduates or existing employees log in to the system and access the survey page. To log in, they must enter their user ID and password.

[1486] Terminal: Sends the login information entered by the user to the server.

[1487] Step 2:

[1488] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[1489] On the device: After successful authentication, the survey page is displayed to the user.

[1490] Step 3:

[1491] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[1492] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[1493] Step 4:

[1494] On the device: While the user is answering the survey, the emotion engine analyzes the user's facial expressions, tone of voice, and the sentiment of the text in real time.

[1495] Terminal: The emotion engine analyzes emotion data in real time and sends it to the server.

[1496] Step 5:

[1497] Server: Receives the survey response data and sentiment data and stores them in the database using an INSERT query.

[1498] Step 6:

[1499] Server: Preprocesses the received survey response data and sentiment data, cleansing and normalizing the data, and tokenizing the text data.

[1500] Step 7:

[1501] Server: Inputs the preprocessed data into the generative AI model to generate optimal business proposals.

[1502] Server: The generative AI model generates business proposals and returns the results to the server.

[1503] Step 8:

[1504] Server: Evaluates the collected emotional data for the proposed work content and selects work proposals with positive user emotional data.

[1505] Server: Generates the selected business proposals in JSON format.

[1506] Step 9:

[1507] Server: The generated JSON data is sent to the user's device as a REST API response.

[1508] Step 10:

[1509] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[1510] User: Review the proposed work and select the work they wish to do.

[1511] Step 11:

[1512] Terminal: Sends the task selected by the user to the server.

[1513] Server: Saves the user's selection in the database and updates the user's career plan.

[1514] Step 12:

[1515] Users: Existing employees answer a questionnaire based on their transfer preferences, including questions about their preferred department, past work experience, and skill set.

[1516] Terminal: Sends the survey response data and emotion data to the server.

[1517] Step 13:

[1518] Server: Receives the survey response data and sentiment data and performs preprocessing, such as data cleansing, normalization, and tokenization of text data.

[1519] Step 14:

[1520] Server: The preprocessed data is fed into a generative AI model to generate internship exam suggestions, taking into account emotional data.

[1521] Server: Generates the proposed content in JSON format and sends it to the user's device.

[1522] Step 15:

[1523] Terminal: The submitted proposal is displayed on the user interface and the user is asked whether or not to carry out the internship trial.

[1524] User: Choose whether to conduct an internship trial.

[1525] Step 16:

[1526] Server: Collects user feedback and sentiment data during the internship period. The collected data is stored in a database.

[1527] Step 17:

[1528] Server: After the internship period ends, the feedback data and sentiment data are analyzed to generate a final transfer proposal.

[1529] Server: Generates the final proposal in JSON format and sends it to the user's device.

[1530] Step 18:

[1531] Terminal: The final proposal is displayed in the user interface.

[1532] User: Review the final proposal and choose whether to accept it.

[1533] Example 2

[1534] 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."

[1535] It is important to accurately understand the preferences and aptitudes of new graduates and existing employees to reduce job mismatches, but conventional methods have the problem of low accuracy in proposals because they do not take into account user emotional data. Furthermore, when it comes to transfers for existing employees, feedback data from internships has not been effectively utilized, resulting in a lack of appropriateness in transfer proposals. There is a need to solve these issues.

[1536] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1537] In this invention, the server includes means for collecting and analyzing emotional data of the user while answering the questionnaire, means for evaluating the suitability of a job proposal using the emotional data, and means for analyzing the feedback data and emotional data during the internship period and generating a final transfer proposal, thereby enabling highly accurate job proposals and transfer proposals that take the user's emotional data into consideration.

[1538] "Questionnaire response data" refers to response information to questions entered by users into the system.

[1539] A "server" is a computer system connected to a network that processes and stores data and manages communications with other terminals.

[1540] A "generative AI model" refers to an artificial intelligence model that uses deep learning technology to analyze data and make predictions.

[1541] "Emotional data" refers to data that represents the user's emotional state analyzed from facial expressions, tone of voice, text content, etc.

[1542] "Preprocessing" refers to a series of operations that normalize and organize data prior to analysis, converting it into a format suitable for analysis.

[1543] "Business proposal" refers to the industry, job content, career plan, etc. proposed to the user.

[1544] An "internship test" refers to an experiment in which an existing employee undergoes work experience for a certain period of time in the department to which they wish to be transferred, and the results are evaluated.

[1545] "Feedback Data" refers to data regarding user opinions, evaluations, and performance collected during the internship period.

[1546] "User interface" refers to the screens and operating means provided for the user and the system to exchange information.

[1547] This invention relates to a system for allocating new graduates and existing employees to the most suitable jobs and reducing job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis, and a user interface.

[1548] Hardware and software used

[1549] Server: A device that processes and stores data and manages communications with other terminals, and is equipped with multiple high-performance processors and large-capacity memory.

[1550] Database: Uses an RDBMS such as MySQL or PostgreSQL.

[1551] Generative AI model: Uses OpenAI's GPT-3 or similar deep learning models.

[1552] Sentiment analysis engine: Use facial recognition APIs such as Amazon Rekognition and speech analysis APIs such as Google Cloud Speech-to-Text.

[1553] Terminal: A device used by users to answer questionnaires or take internship exams, and is typically a personal computer or tablet equipped with a camera and microphone.

[1554] Browser: Use a web browser such as Chrome or Firefox.

[1555] System operation and concrete examples

[1556] Survey collection

[1557] Users log in to the system and access the questionnaire page. A user ID and password are required to log in. Users answer questions such as "jobs they are interested in," "past experience," "strengths and weaknesses," and "desired career path."

[1558] The terminal sends the user's login information to the server, and if authentication is successful, a questionnaire page is displayed.

[1559] Data storage and sentiment analysis

[1560] The server stores the received survey data in a database. Using facial expression recognition APIs and voice analysis APIs, it analyzes emotional data from the user's facial expressions and tone of voice in real time and stores the data in the database.

[1561] Data preprocessing and analysis using generative AI models

[1562] The server normalizes the survey data and sentiment data, tokenizes the text data, and inputs this into a generative AI model to generate business proposals. For example, OpenAI's GPT-3 model is used.

[1563] The generated business proposals are evaluated for suitability using emotional data, and appropriate proposals are selected.

[1564] Presentation of business proposals and user selection

[1565] The server converts the selected business proposal into JSON format and sends it to the terminal via REST API.

[1566] The device parses the JSON data and displays the proposed tasks on the user interface. The user can then review the proposed tasks and select the desired task.

[1567] Specific examples

[1568] Example 1: A new graduate logs into the system and submits a questionnaire indicating their preference for "sales" and "marketing." The server uses a generative AI model and sentiment analysis to create proposals for both "sales" and "marketing." After evaluating the suitability, it is determined that sales is the most suitable. Based on this proposal, the new graduate selects a sales position.

[1569] Example 2: An existing employee requests a transfer to the marketing department and conducts an internship test. During the internship, sentiment data and feedback data are collected, and a transfer proposal to the marketing department is finally generated.

[1570] Prompt Sentence Examples

[1571] 1. "A new graduate indicated that he / she would like to work in sales and marketing and has experience in sales. Please explain what kind of business proposals will be generated, including emotional data."

[1572] 2. "When an existing employee requests a transfer to the marketing department, explain how feedback data is collected through an intern exam and a final proposal is generated."

[1573] As a result, this system makes job and transfer proposals that take into maximum consideration the wishes and aptitudes of new graduates and existing employees, thereby reducing job mismatches.

[1574] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1575] Step 1:

[1576] The user logs in to the system. The user enters their user ID and password on the login screen and clicks the "Login" button.

[1577] Input: User ID, Password

[1578] Output: Login request

[1579] Step 2:

[1580] The device sends the user's login information to the server. The login request is sent using the HTTPS protocol.

[1581] Input: Login request

[1582] Output: Authentication request to the server

[1583] Step 3:

[1584] The server authenticates the received login information by checking it against its database, and if authentication is successful, starts a user session.

[1585] Input: Authentication request (user ID, password)

[1586] Output: Authentication result (success or failure)

[1587] Step 4:

[1588] After successful authentication, the device displays the survey page to the user. The survey form is rendered using HTML and CSS.

[1589] Input: Authentication result (success)

[1590] Output: Survey page

[1591] Step 5:

[1592] Users access the survey page and answer questions, entering information such as "interesting work," "past experience," "strengths and weaknesses," and "desired career path."

[1593] Input: Survey response

[1594] Output: Survey data

[1595] Step 6:

[1596] The device uses a camera and microphone to capture facial expressions and tone of voice in real time while the user answers the survey.

[1597] Input: Real-time facial expressions and voice of the user

[1598] Output: Emotion data

[1599] Step 7:

[1600] The terminal sends the answered questionnaire data to the server by pressing the send button.

[1601] Input: Survey data

[1602] Output: Request to send survey data to the server

[1603] Step 8:

[1604] The server stores the received survey data in the database using an INSERT query.

[1605] Input: Survey data

[1606] Output: Update database (save survey data)

[1607] Step 9:

[1608] The server uses an emotion analysis engine to analyze the facial expressions and tone of voice sent from the device and generate emotion data, which is then stored in a database.

[1609] Input: facial expression data, voice data

[1610] Output: Saved emotion data

[1611] Step 10:

[1612] The server performs preprocessing of the received questionnaire data and emotion data, such as cleaning text data and normalizing numerical data.

[1613] Input: Survey data, emotion data

[1614] Output: Preprocessed data

[1615] Step 11:

[1616] The server inputs the preprocessed data into a generative AI model to generate business proposals. The AI ​​model used is a generative AI model such as GPT-3.

[1617] Input: Preprocessed data

[1618] Output: Business proposal data

[1619] Step 12:

[1620] The server evaluates the suitability of the generated business proposals using emotional data analysis and selects the most appropriate proposal.

[1621] Input: Business proposal data, emotion data

[1622] Output: Evaluated business proposal

[1623] Step 13:

[1624] The server converts the selected business proposal into JSON format and sends it to the terminal via REST API.

[1625] Input: Evaluated Business Proposal

[1626] Output: Business proposal data in JSON format

[1627] Step 14:

[1628] The device parses the JSON data received from the server and displays the suggestions in the user interface.

[1629] Input: Business proposal data in JSON format

[1630] Output: Displayed business proposal

[1631] Step 15:

[1632] The user checks the displayed business proposals and selects the business he or she desires.

[1633] Input: Business proposal list

[1634] Output: Selected tasks

[1635] Step 16:

[1636] The terminal transmits the business information selected by the user to the server.

[1637] Input: Selected business

[1638] Output: Request to send selection information to the server

[1639] Step 17:

[1640] The server saves the user's selections in a database and updates the career plan.

[1641] Input: Selected business information

[1642] Output: Updated career plan

[1643] The goal is that by going through all the steps of this system, users will be able to receive the best job offers based on their preferences and aptitudes.

[1644] (Application example 2)

[1645] 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."

[1646] In companies, mismatched work assignments between new graduates and existing employees can lead to reduced efficiency and motivation. In particular, employees can be assigned to work that does not match their skills or career path, which can lead to a decline in performance. In addition, while appropriate personnel assignment is crucial for operating online or virtual stores, traditional methods make it difficult to propose optimal work assignments that take into account individual characteristics and emotions.

[1647] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting questionnaire response data, means for transmitting the collected data to the server, means for preprocessing the data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate business proposals, means for evaluating the proposals and selecting an appropriate proposal, means for presenting the selected business proposals to the user, means for saving the user's selections on the server, means for analyzing emotion data from input text, and means for adjusting the business proposals based on the emotion data. This makes it possible to achieve optimal job assignments that take into account the characteristics and emotions of employees and improve the efficiency of corporate human resource utilization.

[1648] "Survey response data" refers to response data that contains information about the work desired by new graduates and existing employees.

[1649] A "server" is a computer system that receives, stores, and processes questionnaire response data and emotion data.

[1650] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis.

[1651] A "generative AI model" is an artificial intelligence model that generates business proposals based on preprocessed data.

[1652] "Job proposals" refer to the optimal jobs that the generative AI model proposes to new graduates and existing employees.

[1653] "Evaluation" is the process of determining the appropriateness of the generated business proposals.

[1654] "Users" refers to new graduates and existing employees who use this system.

[1655] "Emotion data" refers to data related to emotions analyzed from the user's input text, facial expressions, and tone of voice.

[1656] "Adjustment" refers to modifying or optimizing business proposals based on analyzed emotional data.

[1657] An "internship test" refers to a trial work experience in the department to which an existing employee wishes to be transferred.

[1658] "Feedback data" refers to data that records evaluations and impressions collected during the internship period.

[1659] The "final transfer proposal" refers to the final proposed transfer job based on the results of analyzing the feedback data.

[1660] This invention provides a system for assigning new graduates and existing employees to the most suitable jobs and reducing job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis using an emotion engine, and a user interface.

[1661] The specific operation of the system is explained below.

[1662] Hardware and software used

[1663] Hardware: Smartphone (Android or iOS)

[1664] Software: Python, EmotionEngine, JobMatchGPT, JSON, REST API

[1665] Data flow and processing overview

[1666] 1. Collection of survey response data: Users (new graduates and existing employees) access a designated survey page using their smartphones and answer questions about their work experience and desired work. The survey data is then sent from the device to the server.

[1667] 2. Emotion data collection: While the user is answering the questionnaire, EmotionEngine analyzes the emotional data from the text input, facial expressions, and tone of voice in real time. This emotional data is also sent to the server.

[1668] 3. Data preprocessing and analysis: The server preprocesses the received survey response data and sentiment data, converting them into a format suitable for analysis. Preprocessing includes data normalization and tokenization. Next, this data is input into a generative AI model (JobMatchGPT) to generate job suggestions.

[1669] 4. Evaluation and adjustment of business proposals: The server evaluates the generated business proposals based on the emotional data and selects the most appropriate proposal. The evaluation takes into account the results of emotional analysis using the Emotion Engine.

[1670] 5. Presentation of business proposals: The selected business proposals are converted into JSON format and sent to the user's device via the REST API. The user can then review the business proposals on their device and select the desired business.

[1671] 6. Transfer preference and internship exam: For existing employees, internship exams are proposed based on their transfer preference. Feedback data during the internship period is also collected along with emotion data and analyzed on the server.

[1672] 7. Generation of final transfer proposal: Based on the analysis results of the feedback data, the server generates a final transfer proposal and presents it to the user through the user interface.

[1673] Examples of specific examples and prompts

[1674] Example: Mr. Tanaka (a new graduate) is interested in running a virtual store and answers the questionnaire saying he is interested in "virtual store management." The system will propose the most suitable job, including emotional data, and the job Mr. Tanaka selects will be reflected in his career plan.

[1675] Example prompt sentence:

[1676] "I'm interested in working in a virtual store. I have experience in customer service and would like to gain more technical knowledge. Which role would be right for me?"

[1677] In this way, this system aims to reduce work mismatches and improve employee performance by analyzing users' characteristics and wishes in detail and making work suggestions.

[1678] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1679] Step 1:

[1680] Users access the questionnaire page using their smartphones and answer questions about their work experience and desired work. The data entered includes work experience, areas of interest, skills, career path, etc. This data is sent from the device to the server.

[1681] Step 2:

[1682] The server receives the survey response data sent from the terminal and stores it in a database. The input is the survey response data, and the output is the data stored in the database.

[1683] Step 3:

[1684] While the user is answering the questionnaire, EmotionEngine collects emotional data from text input, facial expressions, and tone of voice. This emotional data is sent from the device to the server. The input is text, facial expressions, and voice data, and the output is emotional data analyzed in real time.

[1685] Step 4:

[1686] The server preprocesses the received survey response data and emotion data. Preprocessing includes normalizing and tokenizing the data to convert it into a format suitable for analysis. The input is the raw survey response data and emotion data, and the output is the preprocessed data.

[1687] Step 5:

[1688] Based on the preprocessed data, the server uses a generative AI model (JobMatchGPT) to generate job suggestions. The input is the preprocessed data, and the output is job suggestions. This generation process takes into account skills, experience, and emotional data.

[1689] Step 6:

[1690] The server evaluates the generated business proposals based on emotional data and selects the most suitable proposal. The evaluation also takes into account the results of emotional analysis using EmotionEngine. The input is the business proposal and emotional data, and the output is a selected business proposal that reflects the evaluation results.

[1691] Step 7:

[1692] The selected business proposal is converted into JSON format and sent to the user's device via REST API. The user reviews the provided proposals and selects the desired business. The input is the selected business proposal, and the output is the business selected by the user.

[1693] Step 8:

[1694] For existing employees, an internship exam is proposed based on their transfer preference. The user decides whether to take the internship exam. The input is the transfer preference data and the proposal content, and the output is the user's choice of whether to accept or reject the internship exam.

[1695] Step 9:

[1696] During the internship period, the server collects feedback data from users and emotion data updated in real time. The input is the feedback data and emotion data, and the output is a final transfer proposal including the analysis results.

[1697] Step 10:

[1698] Based on the analysis results of the feedback data and emotion data, the server generates a final transfer proposal and presents it to the user through the user interface. The user reviews the final proposal and decides whether to accept the transfer. The input is the analyzed data, and the output is the final transfer proposal and its selection result.

[1699] The above are the specific processing steps for providing an optimal task allocation that takes into consideration the characteristics and emotions of the user.

[1700] 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.

[1701] 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.

[1702] 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.

[1703] [Fourth embodiment]

[1704] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1705] 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.

[1706] 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).

[1707] 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.

[1708] 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.

[1709] 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).

[1710] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1711] 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.

[1712] 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.

[1713] 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.

[1714] 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.

[1715] 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.

[1716] 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."

[1717] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, and a user interface.

[1718] System operation and program processing

[1719] 1. Survey collection

[1720] User: A new graduate or existing employee logs into the system and accesses the designated survey page.

[1721] Terminal: The user answers the questions in the survey and presses the send button to send the answer data to the server. Examples of questions include "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[1722] Example: Mr. Tanaka says he is interested in sales and marketing positions and notes that he has prior sales experience.

[1723] 2. Data reception and preparation for analysis

[1724] Server: Receives the survey response data and stores it in a database.

[1725] Server: Cleanses and normalizes the received data, and converts text data into a format suitable for analysis by tokenizing it, for example. For example, it converts the contents of a survey into specific keywords so that the model can easily understand them.

[1726] 3. Data analysis and business proposal generation

[1727] Server: The preprocessed data is input into a generative AI model (such as GPT-3) to generate optimal job suggestions. The model outputs multiple job suggestions based on the user's preferences and aptitude.

[1728] Server: Evaluates the generated job proposals and selects the most appropriate one. For example, "sales position" and "marketing position" are selected from the generated proposals.

[1729] 4. Presentation of business proposal

[1730] Server: Generates the selected business proposals in JSON format and sends them to the user's device.

[1731] Terminal: Parses the JSON data sent and displays it in the user interface. The user can then review and select the business proposals presented.

[1732] Example: Tanaka's screen shows the suggestions "Sales" and "Marketing", and she chooses Sales.

[1733] 5. Propose an internship test and collect feedback

[1734] Server: For existing employees, the server analyzes the questionnaire responses based on their transfer preferences and generates and presents internship proposals. It also includes a function to collect feedback data during the internship period.

[1735] Example: Mr. Sato wants to transfer to the marketing department and will take an internship exam. After the internship period ends, Mr. Sato will submit his opinion through the feedback form.

[1736] 6. Generate and present the final transfer proposal

[1737] Server: After the internship ends, the collected feedback data is analyzed and a final transfer proposal is generated. The generated proposal is sent to the user's device and displayed on the user interface.

[1738] Example: After analyzing Sato's feedback, it is determined that a formal transfer to the Marketing department is appropriate, and a final proposal is made.

[1739] Example of a system

[1740] Example 1: Tanaka-san (new graduate):

[1741] In the survey, he indicated that he wanted to work in "sales" and "marketing" and that he had previous experience in sales work.

[1742] The server analyzes the data and generates suggestions for "sales jobs" and "marketing jobs."

[1743] Tanaka chooses "sales" and this is reflected in his career plan.

[1744] Example 2: Sato-san (existing employee):

[1745] In the survey, I expressed a desire to be transferred to the marketing department.

[1746] I accepted the internship offer and experienced working in the marketing department for one month.

[1747] After completing the course, he provided feedback and was eventually offered a permanent transfer to the Marketing department, which he accepted.

[1748] This system allows new graduates and existing employees to be assigned to tasks that best suit them, reducing job mismatches and supporting long-term career development within the company.

[1749] The processing flow will be explained below.

[1750] Step 1:

[1751] User: New graduates or existing employees log in to the system and access the survey page. To log in, they must enter their user ID and password.

[1752] Terminal: Sends the login information entered by the user to the server.

[1753] Step 2:

[1754] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[1755] On the device: After successful authentication, the survey page is displayed to the user.

[1756] Step 3:

[1757] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[1758] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[1759] Step 4:

[1760] Server: Receives the survey response data and stores it in the database using an INSERT query.

[1761] Server: Preprocesses the received data and converts it into a format suitable for analysis by performing text normalization, tokenization, etc.

[1762] Step 5:

[1763] Server: Inputs the preprocessed data into the generative AI model, which receives the data via an API.

[1764] Server: The generative AI model generates business proposals and returns the results to the server.

[1765] Step 6:

[1766] Server: Evaluates the generated business proposals and selects the most appropriate one. The proposals are scored and the one with the highest score is selected.

[1767] Server: Generates the selected business proposals in JSON format.

[1768] Step 7:

[1769] Server: The generated JSON data is sent to the user's device as a REST API response.

[1770] Step 8:

[1771] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[1772] User: Review the proposed work and select the work they wish to do.

[1773] Step 9:

[1774] Terminal: Sends the user's selection to the server.

[1775] Server: Receives the selections and stores them in the database, updating the user's career plan.

[1776] Step 10:

[1777] Server: For existing employees, a means is provided to collect questionnaire response data based on transfer preferences and generate internship trial proposals. Proposals for internship trials are generated and displayed on the user interface as well.

[1778] User: Confirms and accepts the internship attempt and also completes and submits feedback during the internship period.

[1779] Step 11:

[1780] Server: After the internship ends, analyze the collected feedback data and generate a final transfer proposal.

[1781] Server: Sends the final proposal to the user and displays it in the user interface.

[1782] Step 12:

[1783] User: Review the final proposal and choose whether to accept it.

[1784] The above is the specific processing flow of the "JoB Match GPT" system.

[1785] Example 1

[1786] 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."

[1787] Modern companies require both new graduates and existing employees to be assigned to the most appropriate jobs based on their preferences and aptitudes. However, traditional manual job assignment methods are prone to mismatches and are labor-intensive and time-consuming, so a system that efficiently and effectively proposes jobs is needed. Furthermore, there is a lack of effective methods for proposing internships based on employee transfer requests and for collecting and analyzing subsequent feedback. This makes it difficult to optimize transfers and career plans, and to support long-term career development within the company.

[1788] 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.

[1789] In this invention, the server includes means for cleansing and normalizing survey data, means for tokenizing the data and converting it into a format suitable for analysis, means for sending the generated job proposals to the user's device in JSON format and displaying them on a user interface, means for preprocessing the survey response data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate job proposals, means for evaluating the generated job proposals and selecting an appropriate proposal, means for presenting the selected job proposal to the user, and means for saving the user's selections on the server. This makes it possible to efficiently collect and analyze data on the jobs desired by new graduates and existing employees, and to generate and present optimal job proposals and transfer proposals. This reduces job mismatches and supports long-term career development within the company.

[1790] "Survey response data" refers to data that includes information provided by new graduates and existing employees regarding the work they would like to do.

[1791] A "server" is a computer system that receives, stores, analyzes, and generates proposals from survey response data.

[1792] "Preprocessing" refers to the process of cleansing, normalizing, and converting collected survey response data into a format suitable for analysis.

[1793] A "generative AI model" is an artificial intelligence model used to analyze survey response data and generate business proposals.

[1794] "Business proposals" are optimal business operations proposed by the generative AI model based on the user's wishes and aptitude.

[1795] An "internship exam" refers to a trial period during which existing employees gain experience in the work they wish to transfer to.

[1796] "Feedback data" refers to data that includes the opinions and impressions of existing employees, collected during the internship test period.

[1797] "User interface" refers to the screen and operating environment through which users operate the system and confirm business proposals and internship exam proposals.

[1798] "Cleansing" is the process of removing duplicates and errors from survey response data and organizing the data.

[1799] "Normalization" is the process of standardizing the format of survey response data and converting it into a form suitable for analysis.

[1800] "Tokenization" is the process of breaking down text data into words and phrases, making it easier to analyze.

[1801] "JSON format" is a data format used to structure data and send it to a user's device.

[1802] A "user terminal" is a device such as a computer or smartphone that a user uses to access the system and respond to business proposals and questionnaires.

[1803] MODE FOR CARRYING OUT THE INVENTION

[1804] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, and a user interface.

[1805] Survey collection

[1806] Users log in to the system as new graduates or existing employees. A dedicated ID and password are used to log in. After logging in, they are redirected to a survey page where they answer specified questions. For example, questions include "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?" After the user has finished answering, they press the send button to send the survey response data to the server.

[1807] Data reception and preparation for analysis

[1808] The server receives the survey response data sent by users and stores it in a database. Next, the data is cleansed (removing duplicates and errors) and normalized (standardizing the format). Furthermore, the text data is tokenized and converted into a format that can be analyzed by a generative AI model (e.g., GPT-3).

[1809] Data analysis and business proposal generation

[1810] The server inputs the preprocessed data into the generative AI model to generate the optimal job proposal. For example, the prompt statement could be "Please generate the optimal job proposal for Tanaka. Tanaka has experience in sales and marketing." Based on this prompt, the generative AI model outputs job proposals such as "sales position" and "marketing position." The multiple job proposals generated are evaluated, and the most appropriate proposal is selected.

[1811] Presenting business proposals

[1812] The server generates the selected business proposals in JSON format and sends them to the user's device. The device parses the received JSON data and displays it on the user interface, allowing the user to check and select from the presented business proposals.

[1813] Internship test proposal and feedback collection

[1814] The system analyzes questionnaire responses from existing employees based on their transfer preferences and generates internship exam proposals. The server stores and analyzes feedback data collected during the internship period. For example, if Mr. Sato requests a transfer to the marketing department, he takes the internship exam and submits his feedback after completing it.

[1815] Generate and present the final transfer proposal

[1816] The server analyzes the collected feedback data after the internship period and generates a final transfer proposal, which is sent to the user's device and displayed on the user interface.

[1817] Specific examples

[1818] Example 1: Mr. Tanaka, a new graduate

[1819] In the questionnaire, Tanaka indicated that he would like to work in "sales" and "marketing" and that he has experience in sales work.

[1820] The server analyzes this and generates job proposals for "sales positions" and "marketing positions."

[1821] Tanaka chose a sales position, which is reflected in his career plan.

[1822] Example 2: Existing employee Sato

[1823] In the survey, Sato expressed a desire to be transferred to the marketing department.

[1824] He accepted the internship offer and gained experience working in the marketing department for one month.

[1825] After completing the internship, the employee submits feedback, which is then analyzed by the server, who then makes a formal proposal for transfer to the marketing department.

[1826] This system allows new graduates and existing employees to be assigned to jobs that best suit them, reducing job mismatches and supporting long-term career development within the company.

[1827] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1828] Program processing flow

[1829] Step 1: Survey collection

[1830] 1. A user logs into the system

[1831] Input: User ID and password

[1832] Output: The user is redirected to the survey page after successful login.

[1833] Specific operation: The user enters their ID and password and clicks the login button. For example, Mr. Tanaka logs in by entering his ID "tanaka123" and password.

[1834] 2. Visit the survey page and answer the questions

[1835] Input: User's survey response

[1836] Output: User survey response data

[1837] Specific operation: The user answers the survey questions and presses the submit button. For example, Mr. Tanaka answers that he is interested in "sales and marketing positions" and has experience in sales work.

[1838] 3. Send the survey response data to the server

[1839] Input: User survey response data

[1840] Output: Survey data sent to the server

[1841] Specific operation: The user clicks the send button and the survey data is sent to the server. For example, Tanaka's survey data is recorded in the server's database.

[1842] Step 2: Receive data and prepare for analysis

[1843] 1. Receive survey response data

[1844] Input: Survey data sent to the server

[1845] Output: Survey data stored in a database

[1846] Specific operation: The server receives the survey data and stores it in a database. For example, Tanaka's survey response data is recorded in the database.

[1847] 2. Cleanse and normalize the data

[1848] Input: Survey data in the database

[1849] Output: Cleansed and normalized data

[1850] What it does: The server removes duplicates and errors from data and standardizes formats. For example, it automatically corrects data inconsistencies like "Tanaka" and "Tanaka."

[1851] 3. Tokenize the data

[1852] Input: Cleansed and normalized data

[1853] Output: Tokenized data

[1854] Specific operation: Text data is divided into words and phrases and converted into a format that can be understood by the generative AI model. For example, keywords such as "sales job" and "sales work" are tokenized.

[1855] Step 3: Data analysis and business proposal generation

[1856] 1. Feed preprocessed data into a generative AI model

[1857] Input: Tokenized data

[1858] Output: Multiple business proposals

[1859] Specific operation: The cleansed and normalized data is input into a generative AI model (e.g., GPT-3). The prompt sentence is "Please generate the optimal business proposal for Mr. Tanaka. Mr. Tanaka has experience in sales and marketing."

[1860] 2. Generate optimal business proposals

[1861] Input: Output data from a generative AI model

[1862] Output: Multiple business proposals

[1863] Specific operation: The server receives the job proposals generated by the generative AI model. For example, job proposals for "sales positions" and "marketing positions" are output.

[1864] 3. Evaluate and select the generated business proposals

[1865] Input: Generated business proposal

[1866] Output: Selected business proposals

[1867] Specific operation: The server evaluates job proposals based on multiple evaluation criteria and selects the most appropriate proposal. For example, "sales position" and "marketing position" are evaluated and selected as the most suitable.

[1868] Step 4: Present the business proposal

[1869] 1. Generate a business proposal in JSON format

[1870] Input: Selected business proposal

[1871] Output: JSON format data

[1872] Specific operation: The selected job proposals are generated in JSON format and sent to the user's device. For example, proposals for "sales positions" and "marketing positions" are generated as JSON format data.

[1873] 2. Parse and display the proposal data on the device

[1874] Input: JSON format data

[1875] Output: Data displayed in the user interface

[1876] Specific operation: The device parses the received JSON data and displays it in the user interface. For example, Tanaka's screen will display suggestions for "sales" and "marketing."

[1877] 3. The user selects a business proposal

[1878] Input: Business proposal displayed on the user interface

[1879] Output: User's selection

[1880] Specific operation: The user checks the presented job proposals and selects one. For example, Mr. Tanaka selects "Sales position."

[1881] Step 5: Propose an internship test and gather feedback

[1882] 1. Generate internship exam proposals

[1883] Input: Survey data based on transfer preferences

[1884] Output: Internship Exam Proposal

[1885] Specific operation: The server analyzes the transfer request data of existing employees and generates an internship exam proposal. For example, it generates an internship exam proposal for Mr. Sato in the marketing department.

[1886] 2. Gather feedback during the internship

[1887] Input: Feedback data during internship period

[1888] Output: Collected feedback data

[1889] Specific operation: The server stores the feedback data collected during the internship. For example, Mr. Sato sends feedback about the work of the marketing department.

[1890] Step 6: Generate and present the final transfer proposal

[1891] 1. Analyze feedback data

[1892] Input: Collected feedback data

[1893] Output: Analysis results

[1894] Specific operation: The server analyzes the feedback data and generates the optimal transfer proposal. For example, Sato-san's feedback is analyzed.

[1895] 2. Generate the final transfer proposal

[1896] Input: Analysis results

[1897] Output: Final transfer proposal

[1898] Specific operation: The server generates a final transfer proposal based on the analysis results. For example, a "formal transfer proposal to the marketing department" is generated for Sato-san.

[1899] 3. Send the final proposal to the device and present it

[1900] Input: Final Transfer Proposal

[1901] Output: The final proposal displayed in the user interface

[1902] Specific operation: The server sends the final proposal to the user's device and displays it on the user interface. For example, "Formal transfer proposal to the marketing department" is displayed on Mr. Sato's screen.

[1903] (Application example 1)

[1904] 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."

[1905] With conventional personnel allocation systems, it is difficult to assign the right people to new graduates and existing employees, leading to job mismatches. Furthermore, automated equipment in factories is rarely allocated to the most appropriate departments, making it difficult to improve productivity. Furthermore, there is a lack of effective means for providing work proposals and managing feedback. This creates challenges that make it difficult to efficiently manage employees and automated equipment and optimally assign them to work.

[1906] 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.

[1907] In this invention, the server includes means for collecting survey response data regarding the work desired by new graduates and existing employees, means for transmitting the survey response data to the server, means for preprocessing the collected survey response data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate work proposals, means for evaluating the generated work proposals and selecting an appropriate proposal, means for presenting the selected work proposals to the user, means for saving the user's selections on the server, means for collecting data from the automated device and analyzing the work assigned to the device, means for presenting optimal work proposals to the automated device based on the generative AI model, means for collecting feedback on the presented work proposals, and means for analyzing the feedback data to improve work efficiency. This enables optimal work assignments for new graduates and existing employees as well as efficient department allocation of automated devices, thereby improving overall work efficiency.

[1908] "New graduates" refer to people who have recently graduated from an educational institution and are entering the workforce for the first time.

[1909] "Existing employees" refers to employees who are already employed by a company or organization and are currently working.

[1910] "Survey response data" refers to information obtained from new graduates and existing employees answering questions about their work.

[1911] "Server" refers to a computer system that collects, stores, analyzes, transmits, etc. data.

[1912] A "generative AI model" refers to a machine learning model that performs natural language processing and generates appropriate business proposals from input data.

[1913] "Work proposals" refer to proposals for work that the generative AI model determines to be most suitable for new graduates and existing employees.

[1914] "Feedback data" refers to information that indicates the results and opinions of users or automated devices when they perform a proposed task.

[1915] "Automated equipment" refers to machines and robots used to automate tasks in factories and other operating environments.

[1916] "Analysis" refers to the process of using collected data to extract information and identify patterns and trends.

[1917] "User" refers to new graduates, existing employees, or anyone authorized to review and decide on business proposals from these individuals.

[1918] "Work efficiency" refers to the ratio between the effectiveness of the work provided and the time it takes, and is a concept that aims to achieve high results in a short amount of time.

[1919] A "department" or "placement" refers to a position within a company or organization that is responsible for a specific task.

[1920] An "internship test" refers to an exam given to those seeking transfer to experience new work and confirm their suitability.

[1921] "Efficiency" refers to high productivity in carrying out designated tasks.

[1922] This invention relates to a system for assigning new graduates and existing employees to optimal work, and a system for efficiently allocating automated equipment within a factory to different departments. This system uses the following hardware and software to process data and perform calculations.

[1923] Hardware and Software

[1924] Server: A computer system for collecting, storing, analyzing, and transmitting data.

[1925] User device: A device (PC, smartphone, tablet, etc.) used to display survey responses and business proposals.

[1926] Generative AI model: A machine learning model (e.g., GPT-3) used to perform natural language processing and generate relevant business suggestions from input data.

[1927] API: Application Program Interface for sending, receiving, and processing data.

[1928] Overall system flow

[1929] 1. Collection of survey response data

[1930] New graduates and existing employees use user terminals to answer a questionnaire about the work they would like to do, which includes specific questions based on prompts.

[1931] For example, answer questions such as, "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[1932] 2. Data transmission to the server and pre-processing

[1933] The user terminal transmits the survey response data to the server, which cleanses and normalizes the received data and converts it into a format suitable for analysis.

[1934] 3. Generate business proposals

[1935] The server inputs the preprocessed data into a generative AI model to generate job suggestions. The generative AI model (e.g., GPT-3) generates optimal job suggestions, such as "sales positions" or "marketing positions," based on the input data.

[1936] 4. Presentation and selection of business proposals

[1937] The server sends the generated business proposals in JSON format to the user's device, which parses them and displays them on the user interface. The user then checks the presented business proposals and selects one.

[1938] 5. Feedback Data Collection

[1939] After the proposed work is performed, feedback data is collected, which is analyzed by the server and used to generate more efficient work suggestions.

[1940] Specific examples

[1941] Example 1: New graduates

[1942] New graduates say they are interested in sales jobs.

[1943] The server analyzes the response data and generates a business proposal for a sales position.

[1944] "Sales position" is displayed on the user terminal, and the new graduate selects it.

[1945] The sales staff will work according to the suggestions made by the sales staff and send their feedback to the server at a later date.

[1946] Example 2: Existing employees

[1947] An existing employee expressed a desire to transfer to the marketing department and responded to a survey.

[1948] The server analyzes the transfer request data and generates an internship proposal.

[1949] Existing employees agree to the internship proposal and gain experience working in the marketing department for a certain period of time.

[1950] After the internship ends, feedback is collected and a final transfer proposal is generated.

[1951] Prompt Sentence Examples

[1952] "Here is the robot's data. Please provide the optimal business proposal.

[1953] {'current_task': 'welding', 'skills': ['welding', 'cutting'], 'experience': {'welding': 200, 'cutting': 100}}"

[1954] This system will enable optimal job assignments for new graduates and existing employees, as well as efficient allocation of automated equipment within the factory, thereby improving overall operational efficiency.

[1955] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1956] Program processing flow

[1957] Step 1:

[1958] Collection of survey response data

[1959] Input: Users (new graduates and existing employees) answer a job-related survey. The survey includes questions such as "What kind of work are you interested in?", "What is your past work experience?", and "What are your strengths and weaknesses?"

[1960] Operation: The user terminal sends the entered answer data to the server.

[1961] Output: Survey response data is stored on the server.

[1962] Step 2:

[1963] Transmission of data to the server and pre-processing

[1964] Input: Survey response data sent from the user's device.

[1965] Operation:

[1966] The server cleanses the received data (removes unnecessary data and fills in missing values) and normalizes it (standardizes the data format).

[1967] After cleansing and normalization, the data is tokenized and converted into a format that is easy for the GPT-3 model to parse.

[1968] Output: Preprocessed data.

[1969] Step 3:

[1970] Generate business proposals

[1971] Input: Preprocessed data.

[1972] Operation:

[1973] The server inputs the preprocessed data into a generative AI model (such as GPT-3) to generate business proposals.

[1974] For example, the following prompt could be input to a generative AI model: "Here is the robot's data. Please suggest the best task for it: {'current_task': 'welding', 'skills': ['welding', 'cutting'], 'experience': {'welding': 200, 'cutting': 100}}"

[1975] Output: The generated business proposal.

[1976] Step 4:

[1977] Presentation and selection of business proposals

[1978] Input: The generated business proposal.

[1979] Operation:

[1980] The server converts the generated business proposal into JSON format and sends it to the user's terminal.

[1981] The user terminal parses the JSON data and displays it on the user interface.

[1982] The user checks the presented business proposals and makes a selection.

[1983] Output: The business proposal selected by the user.

[1984] Step 5:

[1985] Feedback data collection

[1986] Input: Feedback on the job selected by the user.

[1987] Operation:

[1988] After carrying out the proposed work, the user enters feedback.

[1989] Feedback includes the difficulty of the task, the degree of accomplishment, and suggestions for improvement.

[1990] The server collects feedback data from the user terminals and stores it in a database.

[1991] Output: Collected feedback data.

[1992] Step 6:

[1993] Analyzing feedback data and generating improvement suggestions

[1994] Input: Collected feedback data.

[1995] Operation:

[1996] The server analyzes the feedback data and re-inputs it into the generative AI model to generate even more efficient business proposals.

[1997] Through this loop, the accuracy of business proposals is improved.

[1998] Output: A new and improved business proposal.

[1999] The above steps will enable new graduates and existing employees to be assigned to the right jobs, as well as enable the efficient allocation of automated equipment within the factory, thereby improving overall work efficiency.

[2000] 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.

[2001] This invention relates to the "JoB Match GPT" system, which aims to assign new graduates and existing employees to the most suitable jobs and reduce job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis using an emotion engine, and a user interface.

[2002] System operation and program processing

[2003] 1. Survey collection

[2004] User: New graduates or existing employees log in to the system and access the designated survey page. To log in, they must enter their user ID and password.

[2005] Terminal: Sends the login information entered by the user to the server.

[2006] 2. Data reception and preparation for analysis

[2007] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[2008] On the device: After successful authentication, the survey page is displayed to the user.

[2009] 3. Survey responses

[2010] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[2011] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[2012] 4. Collecting survey and sentiment data

[2013] Server: Receives the survey response data and stores it in the database using an INSERT query.

[2014] On the device: While the user is answering the survey, the emotion engine analyzes the user's facial expressions, tone of voice, and the emotion of the text in real time to generate emotion data.

[2015] Server: Receives emotion data and stores it together with the survey response data.

[2016] 5. Data Preprocessing and Analysis

[2017] Server: Preprocesses the received survey response data and sentiment data, converting them into a format suitable for analysis, including data normalization and text tokenization.

[2018] Server: Inputs the preprocessed data into the generative AI model.

[2019] 6. Business proposal generation and emotional feedback

[2020] Server: The generative AI model generates business proposals and returns the results to the server.

[2021] Server: Analyzes real-time user sentiment data regarding the proposal content and evaluates the suitability of the business proposal.

[2022] Server: Selects the appropriate proposal and generates it in JSON format.

[2023] 7. Presentation of business proposal

[2024] Server: The generated JSON data is sent to the user's device as a REST API response.

[2025] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[2026] User: Review the proposed work and select the work they wish to do.

[2027] 8. Transfer Requests and Internship Exams

[2028] Server: For existing employees, the server also collects questionnaire responses based on transfer preferences and generates internship exam proposals. It also has a means of acquiring emotional data and analyzing it in real time.

[2029] Terminal: The proposal is displayed in the user interface and the user is asked to confirm whether or not to accept the internship attempt.

[2030] 9. Gathering feedback and final proposal

[2031] Server: Analyzes the feedback and sentiment data collected during the internship and generates the final transfer proposal.

[2032] Server: Presents the final proposal to the user and displays it in the user interface.

[2033] User: Review the final proposal and choose whether to accept it.

[2034] Example of a system

[2035] Example 1: Tanaka-san (new graduate):

[2036] In the survey, participants indicated that they wanted to work in sales and marketing and had previous experience in sales. Real-time emotional data was also collected.

[2037] The server analyzes the data and generates suggestions for "sales jobs" and "marketing jobs," taking into account sentiment data regarding the suggestions.

[2038] Tanaka chooses "sales" and this is reflected in his career plan.

[2039] Example 2: Sato-san (existing employee):

[2040] They will then be asked to fill out a questionnaire to request a transfer to the marketing department and take an internship exam. Feedback, including sentiment data, will be collected during the internship.

[2041] After completing the training, the feedback is analyzed and a formal transfer to the marketing department is proposed.

[2042] This allows the system to assign new graduates and existing employees to tasks that are best suited to them, reducing job mismatches, and also provides more accurate suggestions by taking into account users' emotional data.

[2043] The processing flow will be explained below.

[2044] Step 1:

[2045] User: New graduates or existing employees log in to the system and access the survey page. To log in, they must enter their user ID and password.

[2046] Terminal: Sends the login information entered by the user to the server.

[2047] Step 2:

[2048] Server: Receives the login information and verifies the credentials against a database. If authentication is successful, the user's session begins.

[2049] On the device: After successful authentication, the survey page is displayed to the user.

[2050] Step 3:

[2051] User: Answers a survey, including questions about their interests, past experience, strengths and weaknesses, and desired career path.

[2052] Terminal: The survey response data entered by the user is sent to the server by pressing the send button.

[2053] Step 4:

[2054] On the device: While the user is answering the survey, the emotion engine analyzes the user's facial expressions, tone of voice, and the sentiment of the text in real time.

[2055] Terminal: The emotion engine analyzes emotion data in real time and sends it to the server.

[2056] Step 5:

[2057] Server: Receives the survey response data and sentiment data and stores them in the database using an INSERT query.

[2058] Step 6:

[2059] Server: Preprocesses the received survey response data and sentiment data, cleansing and normalizing the data, and tokenizing the text data.

[2060] Step 7:

[2061] Server: Inputs the preprocessed data into the generative AI model to generate optimal business proposals.

[2062] Server: The generative AI model generates business proposals and returns the results to the server.

[2063] Step 8:

[2064] Server: Evaluates the collected emotional data for the proposed work content and selects work proposals with positive user emotional data.

[2065] Server: Generates the selected business proposals in JSON format.

[2066] Step 9:

[2067] Server: The generated JSON data is sent to the user's device as a REST API response.

[2068] Step 10:

[2069] Terminal: Receives and parses the JSON data sent from the server. Based on the parsed data, the business proposal content is displayed on the user interface.

[2070] User: Review the proposed work and select the work they wish to do.

[2071] Step 11:

[2072] Terminal: Sends the task selected by the user to the server.

[2073] Server: Saves the user's selection in the database and updates the user's career plan.

[2074] Step 12:

[2075] Users: Existing employees answer a questionnaire based on their transfer preferences, including questions about their preferred department, past work experience, and skill set.

[2076] Terminal: Sends the survey response data and emotion data to the server.

[2077] Step 13:

[2078] Server: Receives the survey response data and sentiment data and performs preprocessing, such as data cleansing, normalization, and tokenization of text data.

[2079] Step 14:

[2080] Server: The preprocessed data is fed into a generative AI model to generate internship exam suggestions, taking into account emotional data.

[2081] Server: Generates the proposed content in JSON format and sends it to the user's device.

[2082] Step 15:

[2083] Terminal: The submitted proposal is displayed on the user interface and the user is asked whether or not to carry out the internship trial.

[2084] User: Choose whether to conduct an internship trial.

[2085] Step 16:

[2086] Server: Collects user feedback and sentiment data during the internship period. The collected data is stored in a database.

[2087] Step 17:

[2088] Server: After the internship period ends, the feedback data and sentiment data are analyzed to generate a final transfer proposal.

[2089] Server: Generates the final proposal in JSON format and sends it to the user's device.

[2090] Step 18:

[2091] Terminal: The final proposal is displayed in the user interface.

[2092] User: Review the final proposal and choose whether to accept it.

[2093] Example 2

[2094] 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."

[2095] It is important to accurately understand the preferences and aptitudes of new graduates and existing employees to reduce job mismatches, but conventional methods have the problem of low accuracy in proposals because they do not take into account user emotional data. Furthermore, when it comes to transfers for existing employees, feedback data from internships has not been effectively utilized, resulting in a lack of appropriateness in transfer proposals. There is a need to solve these issues.

[2096] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2097] In this invention, the server includes means for collecting and analyzing emotional data of the user while answering the questionnaire, means for evaluating the suitability of a job proposal using the emotional data, and means for analyzing the feedback data and emotional data during the internship period and generating a final transfer proposal, thereby enabling highly accurate job proposals and transfer proposals that take the user's emotional data into consideration.

[2098] "Questionnaire response data" refers to response information to questions entered by users into the system.

[2099] A "server" is a computer system connected to a network that processes and stores data and manages communications with other terminals.

[2100] A "generative AI model" refers to an artificial intelligence model that uses deep learning technology to analyze data and make predictions.

[2101] "Emotional data" refers to data that represents the user's emotional state analyzed from facial expressions, tone of voice, text content, etc.

[2102] "Preprocessing" refers to a series of operations that normalize and organize data prior to analysis, converting it into a format suitable for analysis.

[2103] "Business proposal" refers to the industry, job content, career plan, etc. proposed to the user.

[2104] An "internship test" refers to an experiment in which an existing employee undergoes work experience for a certain period of time in the department to which they wish to be transferred, and the results are evaluated.

[2105] "Feedback Data" refers to data regarding user opinions, evaluations, and performance collected during the internship period.

[2106] "User interface" refers to the screens and operating means provided for the user and the system to exchange information.

[2107] This invention relates to a system for allocating new graduates and existing employees to the most suitable jobs and reducing job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis, and a user interface.

[2108] Hardware and software used

[2109] Server: A device that processes and stores data and manages communications with other terminals, and is equipped with multiple high-performance processors and large-capacity memory.

[2110] Database: Uses an RDBMS such as MySQL or PostgreSQL.

[2111] Generative AI model: Uses OpenAI's GPT-3 or similar deep learning models.

[2112] Sentiment analysis engine: Use facial recognition APIs such as Amazon Rekognition and speech analysis APIs such as Google Cloud Speech-to-Text.

[2113] Terminal: A device used by users to answer questionnaires or take internship exams, and is typically a personal computer or tablet equipped with a camera and microphone.

[2114] Browser: Use a web browser such as Chrome or Firefox.

[2115] System operation and concrete examples

[2116] Survey collection

[2117] Users log in to the system and access the questionnaire page. A user ID and password are required to log in. Users answer questions such as "jobs they are interested in," "past experience," "strengths and weaknesses," and "desired career path."

[2118] The terminal sends the user's login information to the server, and if authentication is successful, a questionnaire page is displayed.

[2119] Data storage and sentiment analysis

[2120] The server stores the received survey data in a database. Using facial expression recognition APIs and voice analysis APIs, it analyzes emotional data from the user's facial expressions and tone of voice in real time and stores the data in the database.

[2121] Data preprocessing and analysis using generative AI models

[2122] The server normalizes the survey data and sentiment data, tokenizes the text data, and inputs this into a generative AI model to generate business proposals. For example, OpenAI's GPT-3 model is used.

[2123] The generated business proposals are evaluated for suitability using emotional data, and appropriate proposals are selected.

[2124] Presentation of business proposals and user selection

[2125] The server converts the selected business proposal into JSON format and sends it to the terminal via REST API.

[2126] The device parses the JSON data and displays the proposed tasks on the user interface. The user can then review the proposed tasks and select the desired task.

[2127] Specific examples

[2128] Example 1: A new graduate logs into the system and submits a questionnaire indicating their preference for "sales" and "marketing." The server uses a generative AI model and sentiment analysis to create proposals for both "sales" and "marketing." After evaluating the suitability, it is determined that sales is the most suitable. Based on this proposal, the new graduate selects a sales position.

[2129] Example 2: An existing employee requests a transfer to the marketing department and conducts an internship test. During the internship, sentiment data and feedback data are collected, and a transfer proposal to the marketing department is finally generated.

[2130] Prompt Sentence Examples

[2131] 1. "A new graduate indicated that he / she would like to work in sales and marketing and has experience in sales. Please explain what kind of business proposals will be generated, including emotional data."

[2132] 2. "When an existing employee requests a transfer to the marketing department, explain how feedback data is collected through an intern exam and a final proposal is generated."

[2133] As a result, this system makes job and transfer proposals that take into maximum consideration the wishes and aptitudes of new graduates and existing employees, thereby reducing job mismatches.

[2134] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2135] Step 1:

[2136] The user logs in to the system. The user enters their user ID and password on the login screen and clicks the "Login" button.

[2137] Input: User ID, Password

[2138] Output: Login request

[2139] Step 2:

[2140] The device sends the user's login information to the server. The login request is sent using the HTTPS protocol.

[2141] Input: Login request

[2142] Output: Authentication request to the server

[2143] Step 3:

[2144] The server authenticates the received login information by checking it against its database, and if authentication is successful, starts a user session.

[2145] Input: Authentication request (user ID, password)

[2146] Output: Authentication result (success or failure)

[2147] Step 4:

[2148] After successful authentication, the device displays the survey page to the user. The survey form is rendered using HTML and CSS.

[2149] Input: Authentication result (success)

[2150] Output: Survey page

[2151] Step 5:

[2152] Users access the survey page and answer questions, entering information such as "interesting work," "past experience," "strengths and weaknesses," and "desired career path."

[2153] Input: Survey response

[2154] Output: Survey data

[2155] Step 6:

[2156] The device uses a camera and microphone to capture facial expressions and tone of voice in real time while the user answers the survey.

[2157] Input: Real-time facial expressions and voice of the user

[2158] Output: Emotion data

[2159] Step 7:

[2160] The terminal sends the answered questionnaire data to the server by pressing the send button.

[2161] Input: Survey data

[2162] Output: Request to send survey data to the server

[2163] Step 8:

[2164] The server stores the received survey data in the database using an INSERT query.

[2165] Input: Survey data

[2166] Output: Update database (save survey data)

[2167] Step 9:

[2168] The server uses an emotion analysis engine to analyze the facial expressions and tone of voice sent from the device and generate emotion data, which is then stored in a database.

[2169] Input: facial expression data, voice data

[2170] Output: Saved emotion data

[2171] Step 10:

[2172] The server performs preprocessing of the received questionnaire data and emotion data, such as cleaning text data and normalizing numerical data.

[2173] Input: Survey data, emotion data

[2174] Output: Preprocessed data

[2175] Step 11:

[2176] The server inputs the preprocessed data into a generative AI model to generate business proposals. The AI ​​model used is a generative AI model such as GPT-3.

[2177] Input: Preprocessed data

[2178] Output: Business proposal data

[2179] Step 12:

[2180] The server evaluates the suitability of the generated business proposals using emotional data analysis and selects the most appropriate proposal.

[2181] Input: Business proposal data, emotion data

[2182] Output: Evaluated business proposal

[2183] Step 13:

[2184] The server converts the selected business proposal into JSON format and sends it to the terminal via REST API.

[2185] Input: Evaluated Business Proposal

[2186] Output: Business proposal data in JSON format

[2187] Step 14:

[2188] The device parses the JSON data received from the server and displays the suggestions in the user interface.

[2189] Input: Business proposal data in JSON format

[2190] Output: Displayed business proposal

[2191] Step 15:

[2192] The user checks the displayed business proposals and selects the business he or she desires.

[2193] Input: Business proposal list

[2194] Output: Selected tasks

[2195] Step 16:

[2196] The terminal transmits the business information selected by the user to the server.

[2197] Input: Selected business

[2198] Output: Request to send selection information to the server

[2199] Step 17:

[2200] The server saves the user's selections in a database and updates the career plan.

[2201] Input: Selected business information

[2202] Output: Updated career plan

[2203] The goal is that by going through all the steps of this system, users will be able to receive the best job offers based on their preferences and aptitudes.

[2204] (Application example 2)

[2205] 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."

[2206] In companies, mismatched work assignments between new graduates and existing employees can lead to reduced efficiency and motivation. In particular, employees can be assigned to work that does not match their skills or career path, which can lead to a decline in performance. In addition, while appropriate personnel assignment is crucial for operating online or virtual stores, traditional methods make it difficult to propose optimal work assignments that take into account individual characteristics and emotions.

[2207] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting questionnaire response data, means for transmitting the collected data to the server, means for preprocessing the data and converting it into a format suitable for analysis, means for inputting the preprocessed data into a generative AI model to generate business proposals, means for evaluating the proposals and selecting an appropriate proposal, means for presenting the selected business proposals to the user, means for saving the user's selections on the server, means for analyzing emotion data from input text, and means for adjusting the business proposals based on the emotion data. This makes it possible to achieve optimal job assignments that take into account the characteristics and emotions of employees and improve the efficiency of corporate human resource utilization.

[2208] "Survey response data" refers to response data that contains information about the work desired by new graduates and existing employees.

[2209] A "server" is a computer system that receives, stores, and processes questionnaire response data and emotion data.

[2210] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis.

[2211] A "generative AI model" is an artificial intelligence model that generates business proposals based on preprocessed data.

[2212] "Job proposals" refer to the optimal jobs that the generative AI model proposes to new graduates and existing employees.

[2213] "Evaluation" is the process of determining the appropriateness of the generated business proposals.

[2214] "Users" refers to new graduates and existing employees who use this system.

[2215] "Emotion data" refers to data related to emotions analyzed from the user's input text, facial expressions, and tone of voice.

[2216] "Adjustment" refers to modifying or optimizing business proposals based on analyzed emotional data.

[2217] An "internship test" refers to a trial work experience in the department to which an existing employee wishes to be transferred.

[2218] "Feedback data" refers to data that records evaluations and impressions collected during the internship period.

[2219] The "final transfer proposal" refers to the final proposed transfer job based on the results of analyzing the feedback data.

[2220] This invention provides a system for assigning new graduates and existing employees to the most suitable jobs and reducing job mismatches. This system presents appropriate job proposals and transfer destinations through questionnaire collection, data analysis, job proposal generation, internship exam proposals, feedback collection, emotion data analysis using an emotion engine, and a user interface.

[2221] The specific operation of the system is explained below.

[2222] Hardware and software used

[2223] Hardware: Smartphone (Android or iOS)

[2224] Software: Python, EmotionEngine, JobMatchGPT, JSON, REST API

[2225] Data flow and processing overview

[2226] 1. Collection of survey response data: Users (new graduates and existing employees) access a designated survey page using their smartphones and answer questions about their work experience and desired work. The survey data is then sent from the device to the server.

[2227] 2. Emotion data collection: While the user is answering the questionnaire, EmotionEngine analyzes the emotional data from the text input, facial expressions, and tone of voice in real time. This emotional data is also sent to the server.

[2228] 3. Data preprocessing and analysis: The server preprocesses the received survey response data and sentiment data, converting them into a format suitable for analysis. Preprocessing includes data normalization and tokenization. Next, this data is input into a generative AI model (JobMatchGPT) to generate job suggestions.

[2229] 4. Evaluation and adjustment of business proposals: The server evaluates the generated business proposals based on the emotional data and selects the most appropriate proposal. The evaluation takes into account the results of emotional analysis using the Emotion Engine.

[2230] 5. Presentation of business proposals: The selected business proposals are converted into JSON format and sent to the user's device via the REST API. The user can then review the business proposals on their device and select the desired business.

[2231] 6. Transfer preference and internship exam: For existing employees, internship exams are proposed based on their transfer preference. Feedback data during the internship period is also collected along with emotion data and analyzed on the server.

[2232] 7. Generation of final transfer proposal: Based on the analysis results of the feedback data, the server generates a final transfer proposal and presents it to the user through the user interface.

[2233] Examples of specific examples and prompts

[2234] Example: Mr. Tanaka (a new graduate) is interested in running a virtual store and answers the questionnaire saying he is interested in "virtual store management." The system will propose the most suitable job, including emotional data, and the job Mr. Tanaka selects will be reflected in his career plan.

[2235] Example prompt sentence:

[2236] "I'm interested in working in a virtual store. I have experience in customer service and would like to gain more technical knowledge. Which role would be right for me?"

[2237] In this way, this system aims to reduce work mismatches and improve employee performance by analyzing users' characteristics and wishes in detail and making work suggestions.

[2238] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2239] Step 1:

[2240] Users access the questionnaire page using their smartphones and answer questions about their work experience and desired work. The data entered includes work experience, areas of interest, skills, career path, etc. This data is sent from the device to the server.

[2241] Step 2:

[2242] The server receives the survey response data sent from the terminal and stores it in a database. The input is the survey response data, and the output is the data stored in the database.

[2243] Step 3:

[2244] While the user is answering the questionnaire, EmotionEngine collects emotional data from text input, facial expressions, and tone of voice. This emotional data is sent from the device to the server. The input is text, facial expressions, and voice data, and the output is emotional data analyzed in real time.

[2245] Step 4:

[2246] The server preprocesses the received survey response data and emotion data. Preprocessing includes normalizing and tokenizing the data to convert it into a format suitable for analysis. The input is the raw survey response data and emotion data, and the output is the preprocessed data.

[2247] Step 5:

[2248] Based on the preprocessed data, the server uses a generative AI model (JobMatchGPT) to generate job suggestions. The input is the preprocessed data, and the output is job suggestions. This generation process takes into account skills, experience, and emotional data.

[2249] Step 6:

[2250] The server evaluates the generated business proposals based on emotional data and selects the most suitable proposal. The evaluation also takes into account the results of emotional analysis using EmotionEngine. The input is the business proposal and emotional data, and the output is a selected business proposal that reflects the evaluation results.

[2251] Step 7:

[2252] The selected business proposal is converted into JSON format and sent to the user's device via REST API. The user reviews the provided proposals and selects the desired business. The input is the selected business proposal, and the output is the business selected by the user.

[2253] Step 8:

[2254] For existing employees, an internship exam is proposed based on their transfer preference. The user decides whether to take the internship exam. The input is the transfer preference data and the proposal content, and the output is the user's choice of whether to accept or reject the internship exam.

[2255] Step 9:

[2256] During the internship period, the server collects feedback data from users and emotion data updated in real time. The input is the feedback data and emotion data, and the output is a final transfer proposal including the analysis results.

[2257] Step 10:

[2258] Based on the analysis results of the feedback data and emotion data, the server generates a final transfer proposal and presents it to the user through the user interface. The user reviews the final proposal and decides whether to accept the transfer. The input is the analyzed data, and the output is the final transfer proposal and its selection result.

[2259] The above are the specific processing steps for providing an optimal task allocation that takes into consideration the characteristics and emotions of the user.

[2260] 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.

[2261] 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.

[2262] 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.

[2263] 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.

[2264] 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.

[2265] 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.

[2266] 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).

[2267] 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.

[2268] 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."

[2269] 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.

[2270] 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,...

Claims

1. A means of collecting survey response data on the work desired by new graduates and existing employees, and means for transmitting the questionnaire response data to a server; A means of preprocessing the collected survey response data and converting it into a format suitable for analysis; A means for inputting the preprocessed data into a generative AI model to generate business proposals; A means for evaluating the generated business proposals and selecting an appropriate proposal; a means for presenting the selected business proposal to a user; means for storing the user's selections on a server; A system including:

2. A means for collecting survey response data based on existing employees' transfer wishes; means for generating and presenting to a user internship exam proposals; A means of collecting feedback data during the internship period; a means for analyzing the collected feedback data and generating a final transfer proposal; The system of claim 1 , comprising:

3. means for displaying the generated business proposals and transfer proposals on a user interface; A means for updating a career plan to reflect the job or transfer destination selected by the user; The system of claim 1 , comprising:

Images