Information processing system

Abstract

We will collect work experience information in a way that ensures all necessary details are included and that there is no duplication. [Solution] The work history information collection device (400) comprises an acquisition unit (4011) that acquires format information containing the necessary information to be included in a work history document, a collection unit (4012) that collects work history information relating to the user's work history, and a storage unit that stores a natural language processing algorithm (430). The collection unit (4012) collects work history information corresponding to the necessary information to be included by interacting with the user using the natural language processing algorithm stored in the storage unit (403).

Description

Technical Field

[0001] The present disclosure relates to a work history information collecting apparatus and a method for collecting work history information.

Background Art

[0002] A resume for work experience plays a very important role as one of the judgment materials for recruiting companies to determine whether a job seeker meets the recruitment requirements. For this reason, it is necessary that the information required by job seekers is completely described in the work experience resume without omission.

[0003] Patent Document 1 (Japanese Unexamined Patent Publication No. 2016-212533) describes a document analysis apparatus that acquires determination criterion data regarding the presence or absence of required entry items corresponding to the type of a document to be analyzed such as a resume, and uses the analyzed data and the determination criterion data to determine whether request data related to the required entry items exists in the document to be analyzed.

Prior Art Literature

Patent Literature

[0004]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0005] In the document analysis apparatus described in Patent Document 1, when there is duplicate information related to required entry items, it is impossible to check the presence of the duplicate information.

[0006] The present disclosure has been made to solve the problems as described above, and an object thereof is to collect work history information such that items related to required entry items are not omitted and do not overlap.

Means for Solving the Problem

[0007] The employment history information collection device relating to the first aspect of this disclosure comprises an acquisition unit that acquires format information containing the required information for an employment history document, a collection unit that collects employment history information relating to the user's employment history, and a storage unit that stores a natural language processing algorithm. The collection unit collects employment history information corresponding to the required information by interacting with the user using the natural language processing algorithm stored in the storage unit.

[0008] The method relating to the second aspect of this disclosure is a method for collecting work history information, the method causing a computer to perform the steps of obtaining format information containing required information for a work history and collecting work history information relating to a user's work history, the collection step including the step of collecting work history information corresponding to the required information by interacting with the user using a natural language processing algorithm. [Effects of the Invention]

[0009] According to this disclosure, work history information can be collected in a way that ensures all necessary information is included and does not duplicate any information. [Brief explanation of the drawing]

[0010] [Figure 1] This is a block diagram outlining the matching system. [Figure 2] This block diagram shows the configuration of the sharing server, recruiter equipment, and applicant equipment. [Figure 3] This is a block diagram showing the configuration of the generation server. [Figure 4] This figure shows an example of a corporate database. [Figure 5] This is a diagram showing an example of a member database. [Figure 6] This figure shows an example of a community database. [Figure 7] This figure shows an example of a job posting database. [Figure 8] This figure shows an example of a user database. [Figure 9] It is a diagram showing an example of a dialogue performed between a generation server and a user. [Figure 10] It is a diagram showing an example of a dialogue performed between a generation server and a user. [Figure 11] It is a diagram showing an example of a dialogue performed between a generation server and a user (with dictionary registration). [Figure 12] It is a diagram showing an example of a dialogue performed between a generation server and a user (with dictionary registration). [Figure 13] It is a diagram for explaining the functions of a generation server from the perspectives of a divergence phase and a convergence phase. [Figure 14] It is a diagram showing the functional configuration of a generation server. [Figure 15] It is a flowchart showing the processing procedure of a data import unit. [Figure 16] It is a flowchart showing the processing procedure of an information acquisition unit. [Figure 17] It is a flowchart showing the processing procedure of a dictionary information registration unit. [Figure 18] It is a flowchart showing the processing procedure of a dictionary information display unit. [Figure 19] It is a flowchart showing the processing procedure of an information organizing unit. [Figure 20] It is a flowchart showing the processing procedure of a resume registration unit. [Figure 21] It is a timing chart showing respective processing procedures of a sharing server, a recruiter apparatus, an applicant apparatus, and a generation server, which relate to a resume. [Figure 22] It is a diagram showing the functional configuration of a generation server according to a modification. [Figure 23] It is a diagram showing another example of a dialogue performed between a generation server and a user. [Figure 24] It is a diagram showing another example of a dialogue performed between a generation server and a user. [Figure 25] It is a diagram showing the functional configuration of a generation server including an IPC classification unit. [Figure 26]This flowchart shows the processing procedure of the IPC classification unit. [Figure 27] This figure shows an example of a resume including an IPC (Information Processing Classification). [Figure 28] This figure shows an example of a resume including an IPC (Information Processing Classification). [Figure 29] This figure shows an example of a resume including an IPC (Information Processing Classification). [Figure 30] This figure shows an example of a resume including an IPC (Information Processing Classification). [Figure 31] This figure shows an example of utilizing RAG technology in the functional configuration of a generation server. [Modes for carrying out the invention]

[0011] Embodiments of this disclosure will be described in detail below with reference to the drawings. The same or corresponding parts in the drawings are denoted by the same reference numerals, and their descriptions will not be repeated.

[0012] [Overall structure] Figure 1 is a block diagram illustrating the overview of Matching System 1. Matching System 1 can be used, for example, for crowdsourcing between companies. Crowdsourcing is generally the process of soliciting contributions from a large number of people to obtain the services, ideas, or content that are needed.

[0013] Many companies are promoting side jobs to make effective use of their human resources. By using crowdsourcing between companies, they can leverage the skills of their employees.

[0014] Referring to Figure 1, the general configuration of the matching system 1 will be explained. The matching system 1 comprises a sharing server 100, recruiter devices 200A, 200B, 200C..., applicant devices 300A, 300B, 300C..., and a generation server 400.

[0015] The sharing server 100 provides a matching service to numerous companies, facilitating the matching of business orders and acceptances between companies. Figure 1 shows companies A, B, C, etc., as examples of companies that use the matching service. Companies A, B, C, etc. are registered as corporate members of Matching System 1. Employees of Companies A, B, C, etc., who use Matching System 1 are also individually registered as members of Matching System 1.

[0016] The work offered through Matching System 1 is, for example, temporary work that is expected to be completed within a predetermined period. Therefore, those who accept work offered through Matching System 1 will engage in their primary work in their specific department within the company, and the work offered through Matching System 1 as a secondary job. In Matching System 1, for example, an applicant from Company A can also accept work from Company A. Therefore, in Matching System 1, it is permissible for an applicant belonging to a different department Y of Company A to accept work from department X of Company A.

[0017] Hereinafter, in Matching System 1, the work for which contractors are being sought may be referred to as "recruitment work" or "recruitment project," the person providing the recruitment project may be referred to as "recruiter," and the person applying to receive the recruitment project may be referred to as "applicant." Applying to recruitment work may be referred to as "applying to recruitment work" or "applying to recruitment project."

[0018] An applicant who wins a project is considered a "contractor," and the person who commissions the project to the contractor is considered a "client." However, in the following, "applicants" may be included in the term "contractor," and "clients" may be included in the term "commissioner."

[0019] The sharing server 100 has a database 120 built on it that is necessary for the matching service. Database 120 includes various databases in which information necessary for providing the matching service is registered. For example, database 120 contains information on members and recruitment activities. The sharing server 100 is managed and operated by a company separate from the companies that use the matching service. Any company that uses the matching service may manage and operate the sharing server 100.

[0020] Recruiter device 200A is operated by the administrator of company A. Recruiter device 200B is operated by the administrator of company B. Recruiter device 200C is operated by the administrator of company C. Hereinafter, recruiter devices 200A, 200B, 200C, etc. may be collectively referred to as "recruiter device 200".

[0021] Applicant device 300A is operated by an applicant from company A. Applicant device 300B is operated by an applicant from company B. Applicant device 300C is operated by an applicant from company C. Hereinafter, applicant devices 300A, 300B, 300C, etc. may be collectively referred to as "applicant device 300". Figure 1 shows two applicants for each company, but the number of applicants is not limited to this. There may be many more applicants for each company, or a company may have only one applicant. Sharing server 100 may accept applicants who are not affiliated with a company, such as freelancers.

[0022] In this embodiment, the managers of companies A, B, C, etc., will assume the role of recruiters. Therefore, in the following, the managers of each company may be referred to as "recruiters." Recruiters can also act as applicants for jobs advertised by other recruiters. In that case, recruiter device 200 will function as applicant device 300. In this embodiment, when a company manager acts as a recruiter, the device that the manager uses to utilize the matching service will be referred to as recruiter device 200.

[0023] Company A may have one administrator or multiple administrators. When assigning administrators to Company A, each administrator may be given a recruiter device 200, or a single recruiter device 200 may be shared by multiple people. The same applies to Companies B, C, etc.

[0024] The sharing server 100 and the recruiter device 200 are configured to communicate via the Internet 50, which is an example of a communication network. The sharing server 100 and the recruiter device 300 are configured to communicate via the Internet 50.

[0025] The sharing server 100 requires sign-in, including the input of a member ID and password, when accepting access from the recruiter device 200. Similarly, the sharing server 100 requires sign-in, including the input of a member ID and password, when accepting access from the applicant device 300. The sharing server 100 identifies each recruiter and applicant by the member ID provided during sign-in.

[0026] The recruiter device 200 accepts various operations from the recruiter. For example, the recruiter device 200 accepts operations such as inputting job postings (requested tasks), inputting evaluations of contractors who have completed the tasks, and searching for members of the matching service.

[0027] The recruiter device 200 communicates with the sharing server 100 in response to each operation performed on the recruiter device 200. The sharing server 100 registers the recruitment request (requested work) in the database 120 in response to an operation to input the recruitment request (requested work), registers the evaluation of the target applicant (contractor) in the database 120 in response to an operation to input an evaluation, and provides member information to the recruiter device 200 in response to an operation to search for members.

[0028] The applicant device 300 accepts various operations from the applicant. For example, the applicant device 300 accepts operations such as searching for job postings, applying for job postings, entering work performance, and entering evaluations of the recruiter (client).

[0029] The applicant device 300 communicates with the sharing server 100 in response to each operation performed on the applicant device 300. The sharing server 100 provides the applicant device 300 with appropriate job postings in response to an operation to search for job postings, issues a notification of acceptance or rejection to the applicant device 300 in response to an operation to apply for a job posting, registers the work performance in the database 120 in response to an operation to input work performance, and registers the evaluation of the target recruiter (client) in the database 120 in response to an operation to input an evaluation.

[0030] A recruiter belonging to a certain department of Company A can use Matching System 1 to hire an applicant belonging to another department of Company A as a contractor for a recruitment project. A recruiter belonging to Company A can use Matching System 1 to hire an applicant belonging to Company B as a contractor for a recruitment project.

[0031] Members using Matching System 1 access Sharing Server 100 as either recruiters or applicants. Hereafter, members of Matching System 1 may be referred to as "users." Also below, the recruiter devices 200 and applicant devices 300 operated by members may be collectively referred to as "user devices 500."

[0032] The sharing server 100 is connected to the generation server 400 in a communicative manner. The generation server 400 provides users with an interface to assist in creating resumes. The generation server 400 has a database 420 built on it that is necessary to provide such an interface to users. The generation server 400 may be managed by the company that manages the sharing server 100, or it may be managed by a company other than the company that manages the sharing server 100. The functionality of the generation server 400 may be included in the sharing server 100.

[0033] The generation server 400 is connected to the user device 500 via the Internet 50 for communication. The user device 500 includes the recruiter device 200 and the applicant device 300. Users access the generation server 400 using the user device 500.

[0034] The generation server 400, like the sharing server 100, requires sign-in, which involves entering a member ID and password, when accepting access from the user device 500. The generation server 400 identifies the user by the member ID provided during sign-in.

[0035] The generation server 400 provides the user with an interface to assist in creating a resume. As a result, the resume creation tool is displayed on the screen 550 of the user device 500. The generation server 400 is an example of a work history information collection device.

[0036] The generation server 400 has the function of collecting all necessary work history information from the user while interacting with the user by displaying a question box 551 and an answer box 552 on the screen 550. Based on the collected work history information, the generation server 400 creates a work history in a standardized format. The generation server 400 displays the created work history on the screen 550, giving the user the opportunity to check the work history. The generation server 400 saves the work history that the user has checked. When a user applies for a job posting, the generation server 400 cooperates with the sharing server 100 and sends the work history to the recruiter device 200.

[0037] The reason for introducing the generation server 400 into matching system 1 lies in the "complexity of creating a resume" and the "difficulty of standardizing resumes." Each of these points will be explained in detail below.

[0038] [The complexity of creating a resume / CV] To efficiently utilize internal talent, it is effective to clearly define each individual's skills and work experience. To do this, it is necessary to collect as much personal information as possible without omission and compile it into a standardized document format.

[0039] However, for job seekers, recalling their skills and work experience and then compiling them into a standardized document format is an extremely cumbersome process.

[0040] Of course, those who wish to formally change jobs may be able to maintain a certain level of motivation for the aforementioned cumbersome procedures, as they will be preparing for rigorous document screening and interviews. In contrast, employees applying for internal projects or those seeking side jobs outside the company will likely find it difficult to maintain motivation for these cumbersome procedures. This is because, in addition to not involving a formal job change, they are not required to undergo the rigorous document screening and multifaceted interviews.

[0041] Thus, in so-called "insider" cases, applicants tend to have little motivation to engage in the cumbersome procedures described above. In such cases, there is a challenge in that job seekers are unable to comprehensively collect all of an individual's skills and work experience, and to compile the collected information into a standardized document format.

[0042] Creating a high-quality resume requires more information about an individual's skills and experience. However, in internal cases, even if a lot of information is available, many job seekers lack the motivation to write a resume and find it tedious (or cumbersome) to write down their skills and experience. In such cases, the amount of information included in the resume tends to be small. Therefore, even if a lot of information is available to the job seeker, there is a challenge in that they cannot compile that information into a standardized document format.

[0043] [The difficulty of standardizing resumes] If resumes were standardized, evaluators could more easily assess each individual's work history. Furthermore, standardized resumes would allow companies to effectively manage talent by grouping employee resumes. However, since resumes are generally written in a free format, the style varies depending on the writer. Even if writers are required to use a uniform format, differences in individual document creation abilities make it difficult to standardize resumes. There is also the risk of duplicate information creeping into resumes due to writer's carelessness. Therefore, evaluators need time to assess each individual's work history based on their resumes. Additionally, it is difficult for companies to group individual work histories based on resumes.

[0044] Based on the background described above, a generation server 400 is installed in matching system 1. According to the generation server 400, work history information is collected from the user in an interactive format without any omissions, and a standardized work history document is created. The created work history document contains all necessary work history information without any omissions or duplication.

[0045] According to this embodiment, it is possible to assist users in creating a resume that includes all necessary information without any omissions or duplication. In addition, according to this embodiment, it is possible to assist users in creating a resume that appropriately reflects their work experience, regardless of their document creation ability. According to this embodiment, it is possible to collect work experience information in a way that includes all necessary information without any omissions or duplication.

[0046] Figure 2 is a block diagram showing the configuration of the sharing server 100, the recruiter device 200, and the applicant device 300.

[0047] [Configuration of Sharing Server 100] The sharing server 100 includes a processor 101, memory 102, storage 103, and a communication interface 104.

[0048] Memory 102 includes RAM (Random Access Memory), ROM (Read Only Memory), flash memory, or any other suitable memory system. Memory 102 stores programs necessary for the arithmetic processing of processor 101, as well as temporary data calculated during the arithmetic processing.

[0049] Storage 103 consists of hard disk drives and solid-state drives, etc. Storage 103 stores database 120. Database 120 contains multiple types of databases. These multiple types of databases include a corporate database (corporate DB) 121, a member database (member DB) 122, a community database (community DB) 123, and a job posting database (job posting DB) 124.

[0050] Some of these multiple types of databases may be stored in storage separate from the sharing server 100. For example, some of the multiple types of databases shown in Figure 2 may be stored on a cloud service separate from the sharing server 100. In this case, the sharing server 100 can access the necessary databases by communicating with the cloud via the internet 50.

[0051] The processor 101 connects to the Internet 50 via the communication interface 104, following a program stored in the memory 102. The processor 101 communicates with the recruiter device 200 and the applicant device 300 after connecting to the Internet 50. The processor 101 accesses the database 120 and performs processes such as extracting necessary data, registering new data in the database 120, and updating data registered in the database 120.

[0052] [Configuration of recruiter device 200] The recruiter device 200 comprises a processor 201, memory 202, communication interface 203, input / output interface 204, display 205, and operation unit 206. The operation unit 206 consists of a mouse and keyboard, etc.

[0053] Memory 202 includes RAM (Random Access Memory), ROM (Read Only Memory), flash memory, or any other suitable memory system. Memory 202 stores programs necessary for the arithmetic operations of processor 201, as well as temporary data calculated during those operations.

[0054] The processor 201 connects to the internet 50 via the communication interface 203 according to the program stored in memory 202. The processor 201 connects to the internet 50 and communicates with the sharing server 100. The processor 201 communicates with the sharing server 100 and performs processes such as sending job postings, displaying information of applicant members on the display 205, ordering work from selected contractors from among the applicants, and sending the evaluations of contractors entered by the recruiter to the sharing server 100.

[0055] Information entered through the operation of the control unit 206 is notified to the processor 201 via the input / output interface 204.

[0056] [Configuration of applicant device 300] The applicant device 300 comprises a processor 301, memory 302, communication interface 303, input / output interface 304, display 305, and operation unit 306. The operation unit 306 consists of a mouse and keyboard, etc.

[0057] Memory 302 includes RAM (Random Access Memory), ROM (Read Only Memory), flash memory, or any other suitable memory system. Memory 302 stores programs necessary for the arithmetic processing of the processor 301, as well as temporary data calculated during the arithmetic processing.

[0058] The processor 301 connects to the Internet 50 via the communication interface 303 according to the program stored in the memory 302. The processor 301 connects to the Internet 50 and communicates with the sharing server 100. The processor 301 communicates with the sharing server 100 and performs processes such as applying for job postings, displaying acceptance or rejection notifications for applied jobs on the display 305, sending the results of the received work to the sharing server 100, and sending the evaluation of the recruiter entered by the applicant to the sharing server 100.

[0059] Information entered through the operation of the control unit 306 is notified to the processor 301 via the input / output interface 304.

[0060] [Database 120] The following describes database 120. Company database 121 contains information on companies participating in matching system 1. Member database 122 contains information on members who use matching system 1. Many members are employees of companies participating in matching system 1.

[0061] Members registered in the member database 122 can use the matching system 1 to work as recruiters (clients) or applicants (contractors). Members may include employees of companies registered in the company database 121, as well as individuals (freelancers) who are not affiliated with any company.

[0062] The community database 123 stores information for identifying companies belonging to a community. Communities are formed by agreement between companies. Therefore, multiple communities can be formed depending on how the companies reach an agreement. The number of companies belonging to a single community can also be set in various ways. Companies that have community relationships form a relationship of trust to the extent determined by how the agreement was reached when the community was formed. The community database 123 registers information for identifying companies belonging to each community.

[0063] The job posting database 124 contains registered projects (job postings) for which contractors are being sought. Employees of each company can, while performing their primary duties in their respective departments within the company, become members of Matching System 1 and accept projects from other departments within their own company or from other companies that are registered in the job posting database 124. In this case, members accept projects from other departments within their own company or from other companies as a side job.

[0064] [Configuration of generation server 400] Figure 3 is a block diagram showing the configuration of the generation server 400. The generation server 400 comprises a processor 401, memory 402, storage 403, and a communication interface 404.

[0065] Memory 402 includes RAM (Random Access Memory), ROM (Read Only Memory), flash memory, or any other suitable memory system. Memory 402 stores programs necessary for the arithmetic operations of processor 401, as well as temporary data calculated during the arithmetic operations.

[0066] Storage 403 consists of hard disk drives and solid-state drives, etc. Storage 403 stores the database 420 and the Large Language Model (LLM) 430. The Large Language Model 430 is an example of a natural language processing algorithm. Storage 403 is an example of a memory unit where natural language processing algorithms are stored.

[0067] The large-scale language model 430 is a language model (pre-trained language model) that has been pre-trained using machine learning. A massive amount of text data is used to train the large-scale language model 430. The large-scale language model 430 is formed as an autoregressive model using a transformer such as GPT (Generative Pre-trained Transformer). The large-scale language model 430 in this embodiment may include Bard and others in addition to GPT (GPT-2, GPT-3, GPT-4).

[0068] Database 420 contains multiple types of databases. These multiple types of databases include a user database (user DB) 421, an interaction information database (interaction information DB) 422, and a dictionary database (dictionary DB) 423.

[0069] The memory 402 stores the program (algorithm) 410. The processor 401 executes the program (algorithm) 410, utilizing the large-scale language model 430 to create a resume.

[0070] Program 410 includes an interaction program 411, a verification program 412, and a creation program 413. Processor 401 interacts with the user by executing the interaction program 411, utilizing the large-scale language model 430. Through this, Processor 401 obtains a large amount of work history information from the user. Processor 401 verifies, by executing the verification program 412, that all the work history information necessary for creating a resume has been obtained, utilizing the large-scale language model 430. Processor 401 creates a resume by executing the creation program 413, utilizing the large-scale language model 430 to conform to a predetermined format.

[0071] [Database 420] The database 420 is described below. User database 421 registers "work history information" and "work history documents" for each user's member ID. In this disclosure, "work history information" means the information used to create the "work history document". The generation server 400 can, for example, receive work history information in file format from the user via the user device 500 before interacting with the user. When the generation server 400 receives work history information from the user, it registers the work history information in user database 421 for each user's member ID.

[0072] If the work history information registered in the user database 421 includes all the information necessary to create a work history document, the generation server 400 will create the work history document without interacting with the user.

[0073] The generation server 400 interacts with the user to obtain work history information from the user. The "work history information" obtained through the interaction is registered in the interaction information database 422 for each member ID. The generation server 400 uses the "work history information" registered in the interaction information database 422 to create a "work history document". If "work history information" is registered in the user database 421, the generation server 400 uses the "work history information" registered in the user database 421 and the "work history information" registered in the interaction information database 422 to create a "work history document". The generation server 400 registers the created "work history document" in the user database 421. The configuration of the user database 421 will be explained in detail later using Figure 8.

[0074] The dictionary database 423 contains terms and their meanings extracted during the interaction between the generation server 400 and the user. The generation server 400 associates the terms registered in the dictionary from the resume with the dictionary database 423. The generation server 400 (or sharing server 100) displays the resume on the user device 500. When the user clicks on a term registered in the dictionary from the resume with the mouse, the generation server 400 (or sharing server 100) displays the meaning of the term on the user device 500.

[0075] The large-scale language model 430 or a portion of the multiple types of databases may be stored in storage separate from the generation server 400. For example, the generation server 400 may connect to a different cloud service and store a portion of the multiple types of databases shown in Figure 3, or the large-scale language model 430, on that cloud. In this case, the generation server 400 can access the necessary databases or large-scale language model 430 by communicating with the cloud via the internet 50.

[0076] The processor 401 connects to the Internet 50 via the communication interface 404, following a program stored in memory 402. The processor 401 connects to the Internet 50 and communicates with the user device 500 (see Figure 1). The processor 401 accesses the database 420 and performs processes such as extracting necessary data, registering new data in the database 420, and updating data registered in the database 420.

[0077] The processor 401 communicates with the sharing server 100. For example, in response to a request from the sharing server 100, the processor 401 sends the member's (user's) resume, which is registered in the user database 421, to the sharing server 100.

[0078] [Company Database 121] Figure 4 shows an example of the company database 121. The company database 121 registers company IDs, company names, and company addresses for each company to identify them. In this embodiment, members are permitted to apply for and win jobs offered by various companies and departments.

[0079] [Member Database 122] Figure 5 shows an example of the member database 122. The member database 122 contains various information about members. This information includes a member ID to identify the member, the ID of the company to which the member belongs, the member's name, the member's authority, and the department to which the member belongs.

[0080] Member privileges include administrator and applicant. Members with administrator privileges are authorized to use Matching System 1 as both recruiters and applicants. Members with applicant privileges are authorized to use Matching System 1 as applicants, but not as recruiters. Department heads within a company are granted administrator privileges to manage the side-job status of their subordinates. Administrators with administrator privileges are authorized to approve applications from their subordinates who are applicants. Therefore, administrators function as approvers.

[0081] [Community Database 123] Figure 6 shows an example of the community database 123. The community database 123 registers information about communities formed between companies. The community information includes a community ID to identify the community, a community name, and a list of IDs of companies belonging to the community. Each company can form various communities by agreeing with other companies. Companies belonging to a community can change the companies that belong to that community by agreement with other companies.

[0082] [Job Posting Database 124] Figure 7 shows an example of the recruitment database 124. The recruitment database 124 contains information on recruitment opportunities. The recruitment information includes a project ID to identify the recruitment opportunity, the ID of the company to which the recruiter who registered the recruitment opportunity belongs, a list of non-disclosable company IDs, the disclosure level, the project title, estimated man-hours, estimated duration, and project details.

[0083] The list of non-disclosing company IDs registers the IDs of companies that are prohibited from disclosing their job postings. There are three levels of disclosure: "Our Company," "Within the Community," and "All." If the disclosure level is set to "All," applicants from outside the community will also be included in the disclosure.

[0084] On the right side of the recruitment database 124 in Figure 7, the IDs of companies that can view the recruitment postings are shown. For example, for the recruitment posting corresponding to posting ID=001, the disclosure level is set to "Our Company". In this case, only members belonging to the company that registered the recruitment posting (company ID=00A) can view the recruitment posting corresponding to posting ID=001.

[0085] Hereafter, using the project ID, the recruitment projects corresponding to each project ID may be referred to as project 001, project 002, project 003, etc. Similarly, using the community ID, the communities corresponding to each community ID may be referred to as community 01, community 02, community 03, etc., and using the member ID, the members corresponding to each member ID may be referred to as member P1, member P2, member P3, etc. Furthermore, using a part of the company ID, the companies corresponding to each company ID may be referred to as company A, company B, company C, etc.

[0086] In case 002, the disclosure level is set to "within the community." According to the community database 123 shown in Figure 6, the companies that have a community relationship with company A, which registered case 002, are company B and company C. Therefore, as shown in Figure 7, only members belonging to company A, company B, or company C can view case 002.

[0087] Case 003 has the same registered companies and disclosure level as Case 002. However, in Case 003, "00B" is registered in the list of non-disclosing company IDs. Therefore, as shown in Figure 7, only members belonging to either Company A or Company C can view Case 003, and members belonging to Company B are not authorized to view Case 003.

[0088] For job postings where the disclosure level is set to "all," all members can view the job posting. Job posting 005, shown in Figure 7, falls into this category. If one or more company IDs are registered in the non-disclosure company ID list for job posting 005, members belonging to those companies will not be granted permission to view job posting 005.

[0089] The estimated workload and estimated time are used by applicants and the matching system 1 to estimate the time required to process the job posting.

[0090] Furthermore, the company database 121, the member database 122, and the community database 123 may each be shared between the sharing server 100 and the generation server 400. The recruitment database 124 may register the member IDs of recruiters corresponding to the recruitment requests.

[0091] [User Database] Figure 8 shows an example of the user database 421. As shown in Figure 8, the user database 421 registers the "work history information" and "work history document" of each member (user) for each member ID. As mentioned above, "work history information" refers to the information used to create the "work history document". The "work history document" is created based on the "work history information". In this embodiment, there are cases in which the "work history information" is acquired in advance before the interaction between the generation server 400 and the user, and cases in which it is acquired through the interaction between the generation server 400 and the user.

[0092] The format of the resume is predetermined by the designer. This format includes the types of required information and the order in which that information should be presented.

[0093] A resume includes both "formal items" and "substantive items." Formal items include, for example, "name," "age," "gender," "work history summary," "work history (duration and content)," "qualifications and skills," and "self-introduction." As shown in Figure 8, these formal items are arranged in the resume in the order of "name," "age," "gender," "work history summary," "work history (duration and content)," "qualifications and skills," and "self-introduction." The resume created by the generation server 400 will include the "formal items" shown in Figure 8 in the order shown in Figure 8. Note that the types and order of "formal items" shown in Figure 8 are merely examples.

[0094] A resume contains content corresponding to each of the "formal items." The content that should be included in a resume includes predetermined "substantive items." As an example of "substantive items," this embodiment introduces an item called "STAR."

[0095] Generally, "STAR" is known as one of the methods used by interviewers to effectively interview job seekers. "STAR" is a coined word created by combining the first letters of "S (Situation)", "T (Task)", "A (Action)", and "R (Result)". The generation server 400 retrieves work history information from the user so that it includes the user's work history details for each of the four items intended by "STAR", and uses the retrieved work history information to create a resume.

[0096] The user database 421 contains not only the resumes (including content) created for each user, but also format information for resumes. This format information includes the necessary information to be included in a resume (formal and substantive information). The generation server 400 performs processing related to assisting in the creation of resumes while referring to the format registered in the user database 421.

[0097] The work history information registered in the user database 421 is the basis for creating a resume, similar to the work history information obtained through interaction between the generation server 400 and the user. If no work history information is registered in the user database 421, the generation server 400 creates a resume based on the "work history information" obtained through interaction with the user. Therefore, in this disclosure, it is not essential that work history information is registered in the user database 421. The user database 421 is an example of a work history database in which work history information collected before interaction by the collection unit is registered.

[0098] "Work history information" includes, for example, information about the name of the company the user previously worked for, the department, job duties, work experience, and period of employment, and includes the "STAR" information mentioned above. Alternatively, "Work history information" may refer to information about the qualifications the user holds.

[0099] "Work experience information" includes fragmented information about the user's work experience. Fragmented information is, for example, information about one of several required items included in a resume. One of several required items is, for example, information about the qualifications the user holds. Alternatively, fragmented information is information that constitutes part of the required items. For example, if the user holds three qualifications, the fragmented information is information about one of those three qualifications.

[0100] The user database 421, together with the dialogue information database 422 and the dictionary database 423, constitutes database 420. Here, the user database 421 of database 420 is described in detail using diagrams. The dialogue information database 422 and the dictionary database 423 have already been explained in order to understand their respective configurations, so their explanations will not be repeated here.

[0101] [Example of dialogue] Figures 9 and 10 illustrate an example of interaction between the generation server 400 and the user. The user accesses the generation server 400 using the user device 500. The generation server 400 interacts with the user using the large-scale language model 430 in the following manner. In particular, the generation server 400 diverges the interaction with the user to ensure that all of the user's work history is obtained without omission from the perspective of STAR (Situation, Task, Action, Result) related to the required information. As a result, the generation server 400 obtains all of the user's work history information necessary for creating the resume.

[0102] This section describes an example in which the generation server 400 interacts with the user using the screen of the user device 500. Specifically, the generation server 400 asks the user about their work history by displaying request text and question text on the screen of the user device 500. The user answers the inquiry by typing text using the keyboard or other means on the user device 500. The generation server 400 may also interact with the user via voice.

[0103] First, the generation server 400 displays a request on the screen that says, "Please enter your work history." (Step S1). The user responds to the request in Step S1 with, "I worked as a lead designer at XX Company." (Step S2).

[0104] Based on the response in step S2, the generation server 400 displays the question "What was the work environment like?" on the screen (step S3). The user responds to the question in step S3 with, "The team was understaffed and had a large backlog of unprocessed cases. The account manager set unrealistic deadlines, which caused stress and low morale within the team" (step S4).

[0105] Based on the response in step S4, the generation server 400 displays the following message on the screen: "Please describe the responsibilities and roles you played in the situation and challenges at that time" (step S5). The user responds to the question in step S5 with: "My role as a team leader was not only to ensure the team could complete the work on time, but also to communicate the processing capacity to other departments and maintain the team's motivation" (step S6).

[0106] In the same manner, the generation server 400 interacts with the user in a chat format to obtain all the necessary work history information from the user for creating the work history document. The generation server 400 then creates the work history document based on the work history information. The generation server 400 displays a request message on the screen saying, "Your work history document has been created. Please review it." (Step S7). Furthermore, the generation server 400 presents the created work history document to the user (Step S8). The user checks the work history document on the screen of the user device 500.

[0107] In particular, the generation server 400 diverges the interaction between the generation server 400 and the user so that all of the user's work history is acquired without omission from the perspective of STAR (Situation, Task, Action, Result).

[0108] Step S3 is an example of a query to obtain work history information corresponding to "Situation" from the user. Similarly, Step S5 is an example of a query to obtain work history information corresponding to "Task" from the user. Although not illustrated in Figures 9 and 10, "Action" refers to the method the user used to overcome "Situation" or "Task". "Result" refers to the outcome obtained by the user's "Action".

[0109] The dialogue program 411 includes parameters to ensure that the dialogue diverges in terms of STAR (Situation, Task, Action, Result). Such parameters are designed, for example, by the system administrator of the generation server 400.

[0110] In addition, the generation server 400 may allow users to send CSV (Comma Separated Value) files or the like containing work history information from the user device 500 to the generation server 400, in addition to or instead of chat-style dialogue.

[0111] To give some examples of "diverging," see below. For example, when information obtained from a user is expanded into text, the number of characters in that text may not meet the character limit specified in the required information. More specifically, when asked "What kind of work environment is it?", the answer may not reach the required character limit (for example, 100 characters or more). In such cases, the generation server 400 will ask the user additional questions such as "What was your relationship with your immediate supervisor like?" or "What was your relationship with your colleagues like?".

[0112] Alternatively, if the user's response lacks sufficient detail, the generation server 400 will ask the user additional questions. For example, if the reason is unclear from the user's response, the generation server 400 will ask the user additional questions. For instance, if the user responds with "The team is understaffed...", but the response does not include any keywords indicating the reason for the understaffing, the generation server 400 will ask the user additional questions such as "Why was the team understaffed?"

[0113] If the information regarding the "reason" in the response received from the user is insufficient, the generation server 400 may use the large-scale language model 430 to organize the information and then present the user with options for the reason. For example, suppose the response received from the user was: "The team was understaffed and had a large backlog of unprocessed cases. The account manager set an unreasonable deadline, which caused stress on the team and lowered morale."

[0114] In this case, the generation server 400 determines that, for example, (a) the reason for the shortage of personnel and (b) the reason why the user has a large number of unprocessed cases are insufficient, and presents the user with options in order to obtain each of the reasons.

[0115] To obtain "(a) Reasons for the personnel shortage," the generation server 400 may, for example, ask, "You mentioned that you were short on personnel. Are any of the following reasons? (Multiple selections allowed)," and present the user with the following options: "A: We couldn't find enough people even after hiring," "B: Orders suddenly increased," "C: Many people quit," and "D: Other (free description)."

[0116] To obtain "(b) the reason why the user ended up with a large number of unprocessed cases," the generation server 400 may, for example, ask, "You mentioned that you had a large number of unprocessed cases. Are any of the reasons among the following? (Multiple selections allowed)," and may also present the user with the following options: "A: Insufficient information sharing between sales and development, resulting in an excessive number of cases being accepted relative to the number of development personnel," "B: Insufficient management ability on the account manager's part," "C: Insufficient skills among development personnel," and "D: Other (free description)."

[0117] A user may select three options, A, B, and C, as their response to (a) above, and two options, A and B, as their response to (b) above.

[0118] As a result, the generation server 400 can extract more detailed information from the user regarding the reasons for (a) and (b) above. For example, the information obtained from the user before asking additional questions was: "The team was understaffed and had a large backlog of pending cases. The account manager set unrealistic deadlines, which caused stress and lowered morale within the team."

[0119] In response, by asking additional questions regarding (a) and (b) above, the generating server 400 can extract information from the user such as, "There was insufficient information sharing between sales and development, the number of projects received was excessive and too rapid compared to the number of development personnel, and the account managers lacked the management skills to handle all the projects. Due to the large number of projects and the tendency for working hours to exceed the limit, many people quit, further exacerbating the personnel shortage. In addition, we were recruiting experienced mid-career employees who could hit the ground running, but we were unable to find enough people."

[0120] [Example of dialogue (when dictionary registration occurs)] Figures 11 and 12 show an example of a dialogue between the generation server 400 and the user (with dictionary registration). Here, we will explain the operation of the generation server 400 when it detects a term that should be registered in the dictionary database 423 in the dialogue shown in Figures 9 and 10, which have already been explained.

[0121] As shown in Figure 11, the generation server 400 detects "lead designer" in the input of step S2 as a term that is easily misunderstood. In this case, the generation server 400 displays the inquiry sentence "Does 'lead designer' mean ○○○○○○?" on the screen (step S2a).

[0122] The user responds to the inquiry in step S2a with "No, it means xxxxxx" (step S2b). Based on the response in step S2b, the generation server 400 displays the message "Understood" on the screen (step S2c). Furthermore, in step S2c, the generation server 400 registers the term "lead designer" and its meaning as a set in the dictionary database 423.

[0123] Subsequently, the generation server 400 continues the interaction with the user and obtains all the necessary work experience information from the user to create the resume. The generation server 400 then creates the resume based on the work experience information. The generation server 400 displays a request message on the screen saying, "Your work experience has been created. Please review it." (Step S7). Furthermore, the generation server 400 presents the created resume to the user (Step S8).

[0124] As shown in Figure 12, the term "Lead Designer" in the resume is underlined. The user understands that the underlined term is linked to a dictionary. When the user clicks on a term displayed on the screen with a mouse or other device, the meaning of the term registered in the dictionary database 423 is displayed on the screen. The user checks the resume, including the dictionary link, on the user device 500 screen. The generation server 400 registers the resume approved by the user in the user database 421, linked to the user's member ID.

[0125] Resumes registered in the user database 421 are sent to the recruiter device 200 upon the user's request. The recruiter device 200 displays the resume, including links to a dictionary. When a recruiter clicks on a term displayed on the screen with a mouse or other means, the meaning of that term, registered in the dictionary database 423, is displayed on the screen. This allows recruiters to accurately understand the terms used in the resume.

[0126] [Generation Server Functions] Figure 13 is a diagram illustrating the processing performed by the generation server 400 from the perspective of the divergence phase and the convergence phase.

[0127] The generation server 400 includes a large-scale language model 430 and a program 410 (dialogue program 411, confirmation program 412, and creation program) that performs processing to support the creation of a resume using the large-scale language model 430. The processing to support the creation of a resume is divided into a divergence phase and a convergence phase, as shown in Figure 13.

[0128] The combination of the dialogue program 411 and the large-scale language model 430 constitutes the "Dialogue AI (Artificial Intelligence) 4110". The Dialogue AI 4110 obtains a large amount of work history information necessary for creating a resume from the user. Furthermore, the Dialogue AI 4110 asks the user whether the created resume aligns with the user's intentions.

[0129] The combination of the verification program 412 and the large-scale language model 430 constitutes the "Verification AI 4120". The Verification AI 4120 verifies that all work experience information corresponding to the necessary entries required for creating a resume has been acquired without any omissions.

[0130] The combination of the creation program 413 and the large-scale language model 430 constitutes the "creation (summarization) AI 4130". The creation (summarization) AI 4130 creates a resume in accordance with a predetermined resume format.

[0131] In the divergence phase, the conversational AI 4110 engages in a chat-like conversation with the user, obtaining work experience information related to the required information for the resume from the user. At this time, the conversational AI 4110 controls the conversation so that it diverges in terms of "STAR (Situation, Task, Action, Result)" according to parameters designed by the system administrator.

[0132] In the divergence phase, the verification AI 4120 reads the resume format. The resume format contains the necessary information required to create a resume. The verification AI 4120 verifies that all work experience information corresponding to the necessary information required to create a resume has been obtained without any omissions. If work experience information is missing, the verification AI 4120 instructs the dialogue AI 4110 to continue the conversation regarding the missing work experience information.

[0133] The conversational AI 4110 stores the conversation history. Therefore, if instructed by the conversational AI 4120 to continue the conversation, the conversational AI 4110 can continue the conversation from where it left off without having to restart a conversation that has already been completed.

[0134] In the divergent phase, the conversational AI 4110 engages in divergent dialogues, and the confirmation AI 4120 repeatedly verifies the information until all necessary work history information corresponding to the required items for creating a resume is obtained without any omissions.

[0135] After completing the divergence phase, the generation server 400 moves to the convergence phase. In the convergence phase, the creation AI (summarization AI) 4130 has the function of organizing the acquired information into a predetermined format. More specifically, the creation AI 4130 creates a resume according to a predetermined resume format. The conversational AI 4110 presents the created resume to the user. The user checks the resume. If the user determines that the resume does not meet their expectations, they instruct the conversational AI 4110 to make corrections. In this case, the creation AI 4130 corrects the resume based on the user's correction instructions. The conversational AI 4110 presents the corrected resume to the user. The user checks the resume.

[0136] In the convergence phase, the creation (and modification) of the resume by the creation AI 4130 and the dialogue between the conversational AI 4110 and the user are repeated until a resume that meets the user's expectations is created.

[0137] Figure 14 shows the functional configuration of the generation server 400. As shown in Figure 14, the generation server 400 includes a control unit 4010. The control unit 4010 is implemented by the processor 401 shown in Figure 3, memory 402, and communication interface 404.

[0138] The control unit 4010 can function as the dialogue AI 4110, confirmation AI 4120, and creation AI 4130 shown in Figure 13 by utilizing the large-scale language model 430. The control unit 4010 performs processing related to assisting in the creation of a resume by accessing the database 420.

[0139] The control unit 4010 includes a data import unit 4011, an information acquisition unit 4012, a dictionary information registration unit 4013, a dictionary information display unit 4014, an information organization unit 4015, and a resume registration unit 4016.

[0140] The data import unit 4011 imports the user's existing work history information into the conversational AI 4110. For example, the data import unit 4011 can receive work history information from the user via the user device 500 in a predetermined file format. The control unit 4010 uses the imported work history information to create a work history document. In this way, by utilizing the user's existing work history information, the conversational cost of the conversational AI 4110 can be reduced.

[0141] The information acquisition unit 4012 uses the conversational AI 4110 to acquire work history information from the user. The information acquisition unit 4012 uses the verification AI 4120 to confirm that all work history information corresponding to the necessary entries for creating a work history document has been acquired without any omissions.

[0142] The dictionary information registration unit 4013 registers unique terms obtained during the interaction between the user and the dialogue AI 4110 in the dictionary database 423. Here, unique terms may be information specific to an organization, such as a company.

[0143] The dictionary information display unit 4014 displays terms registered in the dictionary database 423 as links if they appear in the resume. The information organization unit 4015 uses the creation AI 4130 to create the resume in a predetermined format.

[0144] The resume registration unit 4016 stores the created resume in the user database 421. In particular, if a term registered in the dictionary database 423 is included in the resume, the resume registration unit 4016 generates a link that associates the term in the resume with the meaning of the term registered in the dictionary database 423, and then stores the resume information in the user database 421.

[0145] [Processing procedure of control unit 4010] Next, with reference to Figures 15 to 20, an example of the processing procedure of the control unit 4010 included in the generation server 400 will be described. Here, the processing procedures of the control unit 4010 will be described for each of the following: the data import unit 4011, the information acquisition unit 4012, the dictionary information registration unit 4013, the dictionary information display unit 4014, the information organization unit 4015, and the resume registration unit 4016.

[0146] Figure 15 is a flowchart showing the processing procedure of the data import unit 4011. First, the data import unit 4011 obtains the format information of the resume and the work history information registered before the interaction between the dialogue AI 4110 and the user from the user database 421 (step S11). Step S11 is an example of a collection unit that collects work history information related to the user's work history. Furthermore, step S11 is an example of an acquisition unit that obtains format information containing the necessary information to be included in the resume.

[0147] "Work history information registered before the interaction between the conversational AI 4110 and the user" refers to the "work history information" shown in Figure 8. The data import unit 4011 may also read the user's work history information from a predetermined local file in step S11. The work history document format information includes the required information for the work history document, as well as the order in which these required information should be placed.

[0148] Next, the data import unit 4011 inputs the work history information obtained in step S11 as preliminary information into the conversational AI 4110 (step S12). Next, the data import unit 4011 determines whether the work history information obtained in step S11 contains all the information necessary to create a work history document (step S13). The data import unit 4011 calls the confirmation AI 4120 and makes the determination in step S13 by referring to the work history document format information.

[0149] If the work history information obtained in step S11 contains all the information necessary to create a resume, no interaction between the conversational AI 4110 and the user is required. Therefore, if the work history information obtained in step S11 contains all the information necessary to create a resume, the data import unit 4011 passes the processing to the information organization unit 4015. The information organization unit 4015 then creates the resume.

[0150] If the work history information obtained in step S11 does not contain all the information necessary to create a work history document, the data import unit 4011 passes the processing to the information acquisition unit 4012.

[0151] Figure 16 is a flowchart showing the processing procedure of the information acquisition unit 4012. First, the information acquisition unit 4012 uses the large-scale language model 430 to call the dialogue AI 4110 and the confirmation AI 4120 (step S21).

[0152] Next, the information acquisition unit 4012 interacts with the user using the conversational AI 4110 (step S22). Through this, the information acquisition unit 4012 acquires conversational information (including work history information) from the user. Step S22 is an example of a collection unit that collects work history information related to the user's work history. Furthermore, step S22 is an example of a conversation unit that collects work history information by interacting with the user. Next, the information acquisition unit 4012 stores the conversational information in the conversational information database 422 (step S23). The conversational information is information that shows the history of conversations with the user.

[0153] Next, the information acquisition unit 4012 determines, based on the dialogue information, whether all the necessary work history information corresponding to the required entries for creating the work history document has been acquired without omission (step S24). At this time, the information acquisition unit 4012 refers to the format information acquired in step S11 and makes the determination in step S24. The information acquisition unit 4012 may also acquire the format information from the user database 421 in a step other than step S11. If the information acquisition unit 4012 has not acquired all the necessary work history information corresponding to the required entries without omission, it returns to step S22.

[0154] If the information acquisition unit 4012 has acquired all the necessary work history information corresponding to the required fields, it asks the user whether there is any other work history information (step S25). If there is other work history information, the information acquisition unit 4012 returns to step S22. If there is no other work history information, the information acquisition unit 4012 passes the process to the information organization unit 4015. The information organization unit 4015 then creates the work history document.

[0155] Figure 17 is a flowchart showing the processing procedure of the dictionary information registration unit 4013. First, the dictionary information registration unit 4013 detects words to be registered in the dictionary during the dialogue between the dialogue AI 4110 and the user (step S31). Words to be registered in the dictionary include proper nouns and polysemous word information. Words to be registered in the dictionary may also be information specific to an organization, such as a company. Next, the dictionary information registration unit 4013 confirms the meaning of the word with the user (step S32).

[0156] Next, the dictionary information registration unit 4013 obtains the user's response (step S33). Then, the dictionary information registration unit 4013 registers the word detected in step S31 and its meaning based on the user's response as dictionary information in the dictionary database 423 (step S34), and terminates the process according to this flowchart. Step S34 is an example of a registration unit that registers the meaning of terms included in the work history information in the dictionary database.

[0157] Figure 18 is a flowchart showing the processing procedure of the dictionary information display unit 4014. First, the dictionary information display unit 4014 retrieves the user's work history from the user database 421 (step S41). Next, the dictionary information display unit 4014 retrieves terms present in the work history from the dictionary database 423 (step S42). Then, the dictionary information display unit 4014 displays the work history with links on the screen of the user device 500 (step S43).

[0158] Next, the dictionary information display unit 4014 displays the dictionary information corresponding to the link on the screen of the user device 500 in response to the user's operation (step S44), and terminates the process based on this flowchart. The dictionary information display unit 4014 is an example of a display unit that displays a resume on a display device. The user device 500 is an example of a display device. In addition, the dictionary information display unit 4014 may display the resume on a display device equipped on the generation server 400 instead of the user device 500, or in addition to the user device 500.

[0159] Figure 19 is a flowchart showing the processing procedure of the information organization unit 4015. First, the information organization unit 4015 calls the created AI 4130 using the large-scale language model 430 (step S51).

[0160] Next, the information organization unit 4015 reads the dialogue information from the dialogue information database 422 (step S52). Also, if pre-registered work history information exists in the user database 421, the information organization unit 4015 reads the work history information from the user database 421 in step S52.

[0161] Next, the information organization unit 4015 creates a resume from the dialogue information (step S53). Furthermore, if the information organization unit 4015 has read work history information from the user database 421, in step S53 it creates a resume from the work history information and the dialogue information. Step S53 is an example of a resume creation unit.

[0162] The information organization unit 4015 refers to the format information obtained in step S11 and creates a resume in the format that conforms to the format information. The information acquisition unit 4012 may acquire the format information from the user database 421 in a step other than step S11. Next, the information organization unit 4015 displays the resume on the screen of the user device 500 (step S54).

[0163] Next, the information processing unit 4015 determines whether or not it has received the user's approval operation (step S55). If the information processing unit 4015 has received the user's approval operation, it terminates the process based on this flowchart.

[0164] If the information organization unit 4015 has not received an approval operation from the user, it determines whether or not it has received a rejection operation from the user (step S56). If the information organization unit 4015 has not received a rejection operation from the user, it returns to step S55. If the information organization unit 4015 has received a rejection operation from the user, it passes the process to the information acquisition unit 4012. The information acquisition unit 4012 calls the dialogue AI 4110 again and interacts with the user to acquire new dialogue information from the user.

[0165] Furthermore, the information processing unit 4015 may not only acquire new dialogue information from the user, but may also engage in dialogue with the user again without changing the conditions prior to the dialogue. This is because, generally, large-scale language models may generate multiple answers (sentences) with different nuances for the same question and conditions.

[0166] Figure 20 is a flowchart showing the processing procedure of the resume registration unit 4016. First, the resume registration unit 4016 retrieves the user's resume from the user database 421 (step S61). Next, the resume registration unit 4016 refers to the dictionary database 423 to generate links between the resume and dictionary information (step S62). Next, the resume registration unit 4016 stores the linked resume in the user database 421 (step S63).

[0167] Next, the resume registration unit 4016 receives a request from the user to output the resume (step S64). Then, the resume registration unit 4016 outputs the resume to the user device 500 (step S65), and the process based on this flowchart ends. The user device 500 may display the resume on its screen. Alternatively, the user device 500 may store the resume data in memory until instructed by the user.

[0168] [Sequence of processes executed by matching system 1] Figure 21 is a timing chart showing the processing procedures for the sharing server 100, recruiter device 200, applicant device 300, and generation server 400 regarding resumes. The processing flow of the matching system 1 regarding resumes will be explained using the timing chart shown in Figure 21.

[0169] First, the applicant accesses the generation server using the applicant device 300 and creates a resume (step S101). The generation server 400 registers the created resume in the user database 421 (step S102). The detailed processing procedures for steps S101 and S102 have already been explained using Figures 15 to 20, so that explanation will not be repeated here.

[0170] Next, the applicant accesses the sharing server 100 using the applicant device 300, searches for job postings, and then decides where to apply (step S103). Next, the applicant operates the applicant device 300 to send a command from the applicant device 300 to the sharing server 100 requesting the applicant's resume (step S104). Upon receiving the command, the sharing server 100 identifies the applicant (step S105). More specifically, the sharing server 100 identifies the applicant's member ID.

[0171] Next, the sharing server 100 sends a command to the generation server 400 requesting the submission of the resume (step S106). This command includes the applicant's member ID. Based on the member ID included in the command, the generation server 400 searches the user database 421 for the applicant's resume (step S107).

[0172] Next, the generation server 400 sends the resumes detected as a result of the search to the sharing server 100 (step S108). The sharing server 100 then obtains the applicant's resume (step S109). Next, the sharing server 100 sends the obtained resume to the applicant device 300 (step S110).

[0173] The applicant device 300 displays the received resume on its screen (step S111). If the resume contains terms registered in the dictionary database 423, the resume, including a link to the dictionary, is displayed on the screen.

[0174] Applicants confirm that there are no problems with the resume displayed on the screen. For example, applicants confirm that there is no information that needs to be updated in the resume. If there are no problems with the resume, applicants approve it using the keyboard or other means. If there are problems with the resume, applicants reject it using the keyboard or other means.

[0175] The applicant device 300 determines whether or not it has detected an approval operation (step S112). If the applicant device 300 detects a disapproval operation instead of an approval operation, it returns to step S101. In this case, the process of creating the resume is executed again. However, it is desirable that the generation server 400 does not execute the process of creating the resume from the beginning, but rather interacts with the applicant regarding matters that need to be corrected and corrects the contents of the resume.

[0176] If the applicant device 300 detects an approval operation, it sends a command to the sharing server 100 instructing it to send the resume (step S113). The sharing server 100 identifies the recruiter to whom the resume should be sent (step S114). For example, the sharing server 100 identifies the recruiter to whom the resume should be sent based on the application destination determined in step S103.

[0177] Next, the sharing server 100 sends the resume to the recruiter device 200 (step S115). The recruiter device 200 displays the received resume on its screen (step S116). If the resume contains terms registered in the dictionary database 423, the resume, including a link to the dictionary, is displayed on the screen. The recruiter uses the resume to understand the applicant's work history. When the applicant clicks on a term registered in the dictionary within the resume using the mouse, the meaning of the term is displayed on the recruiter device 200. Therefore, if the resume contains terms that the applicant does not understand, such as internal company jargon, the recruiter can understand the meaning of those terms.

[0178] In Figure 21, the sharing server 100 and the generation server 400 may be configured as a single server. That is, the functions of the generation server 400 may be provided to the sharing server 100, or the functions of the sharing server 100 may be provided to the generation server 400. Steps S110 and S115 are examples of output units configured to output the resumes created by the creation unit to the user device.

[0179] As described above, this embodiment can assist users in creating a resume that includes all necessary information and avoids any duplicate entries. In addition, this embodiment can assist users in creating a resume that appropriately reflects their work experience, regardless of their document creation abilities. Furthermore, this embodiment provides the following advantages.

[0180] a. Regardless of the user's document creation ability, we can provide the user with a resume that appropriately expresses their skills and experience.

[0181] b. It can collect a wide variety of user work history information without any omissions. c. By providing users with an interactive interface, the burden on users to appropriately extract work history information can be reduced.

[0182] d. It can reduce the burden on users in creating their resumes. e. Because resumes are created in a standardized format, efficiency can be increased when managing and searching through a large number of resumes.

[0183] f. For users who find it difficult to maintain motivation for the cumbersome process of creating a resume, such as employees applying for internal projects or those seeking side jobs outside the company, this provides an interface for creating high-quality resumes.

[0184] g. If a term registered in dictionary database 423 is included in a resume, the resume will be displayed on the screen with a link to the dictionary, so that recruiters can understand the meaning of any unfamiliar terms in the resume.

[0185] Furthermore, some components of the generation server 400 may be configured on separate devices. For example, at least one of the multiple databases included in database 420 and the large-scale language model 430 may be located on a cloud separate from the generation server 400. In this case, it is sufficient that the generation server 400 and the cloud are connected via a network to enable communication.

[0186] [Differentiation] In this embodiment, an example is shown in which the generation server 400 is located in the matching system 1. However, a generation server that creates resumes may be constructed independently of the matching system 1. An example of a generation server that creates resumes independently of the matching system 1 will be described.

[0187] Figure 22 shows the functional configuration of the generation server 400A in a modified example. The generation server 400A, like the generation server 400, has a processor, memory, communication interface, and storage, and includes a control unit 4010A realized by these configurations.

[0188] The generation server 400A is connected to the user device 500A, which is used by the user, via the internet or other means, enabling communication between the two devices.

[0189] The generation server 400A includes a requirements database (requirements DB) 426, a source information storage database (source information storage DB) 427, a generation format database (generation format DB) 428, and large language models 430A and 430B. These databases and large language models are configured in the storage of the generation server 400A.

[0190] Large-scale language models 430A and 430B, like large-scale language model 430, are natural language processing models trained using large amounts of text data. In this disclosure, Google's BERT® (LaMBDA) or OpenAI's GPT-4 may be used as the large-scale language model. In this disclosure, the large-scale language model is an example of a natural language processing algorithm. Other language models other than the large-scale language model may be used as the natural language processing algorithm. Models generated by machine learning, such as pattern matching, may be used as the natural language processing algorithm. Furthermore, instead of using the two large-scale language models 430A and 430B, one large-scale language model may be used. For example, large-scale language model 430 may be used.

[0191] As shown in Figure 22, the control unit 4010A includes an input unit 4021, a content satisfaction determination unit 4022, an input request unit 4023, a source information storage unit 4024, a generation unit 4025, a confirmation request unit 4026, and an output unit 4027.

[0192] The input unit 4021 receives information entered by the user using the user device 500. The information entered by the user includes work history information. The input unit 4021 may, for example, accept work history information in chat format. The input unit 4021 may also accept work history information in audio file format and other file formats. When using a large-scale language model such as GPT-3 and a chat-format UI such as ChatGPT, files may be attached to the chat. In this case, the generation server 400 may be provided with a function to convert files into chat-format documents.

[0193] The output unit 4027 outputs various information to the user device 500. The output unit 4027 may output not only chat-formatted information but also other files such as audio to the user device 500. When the control unit 4010A interacts with the user in chat format, the input of information to the input unit 4021 and the output of information from the output unit 4027 are repeatedly performed.

[0194] The fulfillment requirements database 426 contains information regarding the requirements (fulfillment requirements) that the large-scale language model 430A uses to determine whether all work experience information corresponding to the necessary entries for creating a resume has been acquired without any omissions.

[0195] Information regarding multiple types of satisfaction requirements may be registered in the satisfaction requirement database 426. In this case, the control unit 4010A may transmit multiple types of satisfaction requirements to the user device 500A and allow the user to select their preferred satisfaction requirements. Alternatively, the control unit 4010A may receive the satisfaction requirements set by the user via the user device 500A.

[0196] Furthermore, the control unit 4010A may use the contents of numerous satisfaction requirements as training data to generate a trained model that functions as an AI. In that case, the generated trained model may be used instead of the large-scale language model. Alternatively, the satisfaction requirements may be used in the Prompt of the already existing large-scale language model 430A. The satisfaction requirements may include specific information, such as the number of companies that the user wants to include in their resume.

[0197] The content satisfaction determination unit 4022 uses the large-scale language model 430 to determine whether the information obtained from the input unit 4021 satisfies the satisfaction requirements. If the content satisfaction determination unit 4022 determines that the information obtained from the input unit 4021 does not satisfy the satisfaction requirements, it instructs the input request unit 4023 to obtain additional information. If the content satisfaction determination unit 4022 determines that the information obtained from the input unit 4021 satisfies the satisfaction requirements, it outputs the information obtained from the input unit 4021 to the original information storage unit 4024.

[0198] The input request unit 4023 instructs the large-scale language model 430A to continue interacting with the user so that additional information (missing information) can be obtained from the user, based on the instructions of the content satisfaction determination unit 4022. If multiple pieces of additional information are required, the large-scale language model 430A may interact with the user so that multiple pieces of additional information are obtained all at once, or it may interact with the user so that each piece of additional information is obtained sequentially. For example, if information A, B, and C are missing, the large-scale language model 430A may first query the user for information A.

[0199] Furthermore, the large-scale language model 430A may automatically generate dialogue rules to prompt the user for additional information, or it may select dialogue rules from pre-configured options.

[0200] The source information storage unit 4024 temporarily stores the work history information that will be used as the basis for generating the work history document. The source information storage unit 4024 outputs the temporarily stored work history information to the source information storage database 427. The source information storage database 427 registers the work history information. The generation unit 4025 creates the work history document using the work history information registered in the source information storage database 427. The generation unit 4025 may also have a function to create the work history document without waiting for a determination from the content satisfaction determination unit 4022.

[0201] For example, if a user already has a draft of their resume, they may only want to finalize or format the resume. In this case, the input unit 4021 may receive the draft resume data from the user via the user device 500. Furthermore, the input unit 4021 may register the received data in the source information storage database 427. The generation unit 4025 may create the resume based on the draft data registered in the source information storage database 427.

[0202] The generation format database 428 contains the formats necessary for the large-scale language model 430B to generate work history data.

[0203] Multiple formats may be registered in the generation format database 428. In this case, the control unit 4010A may send multiple formats to the user device 500A and allow the user to select their preferred format. Alternatively, the control unit 4010A may accept a format set by the user via the user device 500A.

[0204] Furthermore, the control unit 4010A may use a number of formats as training data to generate a trained model that functions as an AI. In that case, the generated trained model may be used instead of the large-scale language model. Alternatively, the format may be used in the Prompt of the already existing large-scale language model 430A.

[0205] The generation unit 4025 generates a resume using the large-scale language model 430B. The formats registered in the generation format database 428 are input into the large-scale language model 430B. The generation unit 4025 refers to the source information storage database 427 and creates a resume that reflects the work experience information in a predetermined format. Alternatively, the large-scale language model 430B may create the resume instead of the generation unit 4025. The resume generated by the generation unit 4025 is output to the confirmation request unit 4026.

[0206] The confirmation request unit 4026 requests the user to confirm the work history document. The confirmation request unit 4026 transmits the work history document to the user device 500 via the output unit 4027. The user confirms the contents of the work history document displayed on the user device 500. The confirmation request unit 4026 may also divide the contents of the work history document into multiple items and have the user confirm the contents of the work history document for each item.

[0207] For example, if the resume contains information about both Company A and Company B, the confirmation request unit 4026 may have the user confirm the information about Company A, and then have the user confirm the information about Company B. Of course, the confirmation request unit 4026 may also have the user confirm all the contents of the resume at once. The large-scale language model 430B may automatically generate dialogue rules for when the user is asked to review the resume, or it may select dialogue rules from pre-configured options.

[0208] Furthermore, some components of the generation server 400A may be configured separately from the generation server 400A. For example, at least one of the sufficiency requirements database 426, the source information storage database 427, the generation format database 428, the large-scale language model 430A, and the large-scale language model 430B may be configured separately from the generation server 400A. In this case, it is sufficient that the device configured separately from the generation server 400A and the generation server 400A are connected to each other via a network so that they can communicate with each other.

[0209] [Variations related to the use of IPC classification] Generally, a technical professional's resume details the skills they possess. However, with the rapid development of IT-related technologies, new and previously little-known fields of technology are constantly emerging, leading to rapid diversification of technologies. On the other hand, the level of detail of skills possessed by users varies from field to field. As a result, consistency in the description of skills in resumes is being lost. This is hindering recruiters when analyzing applicants' resumes.

[0210] Such problems also exist within companies. It is important for those in a position to evaluate employees to understand and systematically organize the skills they possess. This is thought to enable the maximum utilization of the company's technical resources. However, given the circumstances described above, even if each employee is required to submit a resume, it is difficult to manage each employee's skills uniformly according to a consistent standard based on the submitted resumes.

[0211] Therefore, an index is needed that can classify various technical skills using a uniform standard. One possible solution is to use the IPC (International Patent Classification). The IPC is an internationally standardized technical classification system for classifying patented inventions. By using the IPC, it is possible to classify technologies in detail by dividing them into hierarchical levels such as "sections," "subsections," "classes," "subclasses," "main groups," and "subgroups."

[0212] IPC is originally an index used to classify patent documents. However, by utilizing IPC as an index to classify engineers' skills, it is possible to classify the skills of various engineers, including those working with the latest technologies, using a uniform standard. However, because IPC is a highly specialized classification index used in the patent industry, it is difficult for users unfamiliar with IPC to accurately select the IPC that corresponds to their skills from among the many IPC options.

[0213] Therefore, this document proposes a system that enables users to select an appropriate IPC (Instructional Programming Code) corresponding to their skills through interaction between the generation server 400 and the user. Here, IPC is assumed as an example of required information or format information for a resume, and user career information necessary to obtain an IPC corresponding to the user's skills is assumed as an example of career information. The generation server 400 collects the user's career information necessary to obtain an IPC by interacting with the user using a natural language processing algorithm.

[0214] Figures 23 and 24 illustrate other examples of interactions between the generation server 400 and the user. Figures 23 and 24 show examples in which the generation server 400 obtains appropriate IPCs corresponding to the user's skills through interaction with the user.

[0215] First, the generation server 400 displays a request message on the screen that reads, "Please enter your work history." (Step S201). The user responds to the request in Step S1 with their work history (Step S202). In Step S202, for example, work history related to the development of lithium-ion secondary batteries is provided.

[0216] Based on the response in step S2, the generation server 400 uses the large-scale language model 430 to organize the information and presents the user with IPCs that may correspond to the user's skills (step S203). In step S203, the user is presented with one or more "IPCs" corresponding to each of the pieces of information obtained through the dialogue, such as "Research and development of lithium-ion secondary batteries," "Development of new cathode materials," "Development of lithium cobalt nickel manganese oxide," "Development of silicon anodes," "Development of electrolytes that suppress degradation," and "Development and practical application of lithium-ion secondary batteries using lithium titanate as the anode."

[0217] Next, the generation server 400 presents the user with several IPCs as selection candidates from among the IPCs presented in step S203 (step S204). At this time, the generation server 400 may present the selection candidates along with checkboxes, as shown in Figure 24. The user considers whether there is an IPC among the options that seems appropriate. If there is an IPC among the options that seems appropriate, the user checks the checkbox corresponding to that IPC to respond. In this case, a button 601 as shown in Figure 24 may be displayed on the screen of the user device 500. After checking the checkbox, the user clicks the button 601. When the generation server 400 detects the click operation of the button 601, it determines the IPC to be included in the user's resume based on the user's response.

[0218] In this way, the generation server 400 suggests to the user relevant IPCs from among a large number of IPCs based on the work history obtained through the correspondence. Therefore, even if the user does not have specialized knowledge of IPCs, they can select IPCs that are relevant to their skills. Here, an example of using "subgroups" is shown, but higher-level symbols such as "subclasses" or "groups" may be used depending on the level of granularity desired for classification. In addition, explanations such as "subclass," "group," or "main group" may be added to the description text of "subgroups" and displayed, or buttons such as a question mark may be added to allow users to check the content of higher levels as needed.

[0219] While this example shows the user selecting an IPC related to their technical field, the IPC presented to the user may be a "section," "subsection," "class," "subclass," "main group," or "subgroup." For example, a subclass, such as "H01: Electrical Components," may be presented to the user. Furthermore, along with the classification code, the name of the technical field to which that classification code belongs may also be presented to the user.

[0220] If no suitable IPC exists among the options proposed in step S205, the user can request the generation server 400 to present other candidates again or to restart the work history entry process from the beginning. In this case, buttons 602 and 603, as shown in Figure 24, may be displayed on the screen of the user device 500.

[0221] When the generation server 400 detects a click operation of button 602, it selects an IPC from the IPCs presented in step S203 that is different from the options presented in step S204, and presents the selected IPC to the user. When the generation server 400 detects a click operation of button 603, it returns to step S204 and prompts the user to enter their work history.

[0222] Furthermore, the generation of IPC candidates may be performed automatically multiple times. The generation server 400 may generate different answers for the same text (or the same question). Therefore, by automatically generating IPCs multiple times from step S202 before proposing IPC candidates in step S204, the range of IPC candidates can be broadened. This increases the likelihood that the user can select an IPC that is suitable for them.

[0223] As described above, the generation server 400 assists the user's actions in identifying IPCs corresponding to the user's skills through interaction between the generation server 400 and the user. Note that the processing in step S203 is not essential in this embodiment. That is, after detecting multiple IPCs that are thought to correspond to the user's skills through interaction, the generation server 400 may present some of the detected IPCs to the user in step S204 without performing the processing in step S203.

[0224] Furthermore, the generation server 400 may autonomously present other candidates to the user, not only when requested by the user to present other candidates again. For example, the generation server 400 may execute the process of creating candidate options multiple times and present multiple candidates to the user. In general, the answers obtained from a large-scale language model to a query may differ even if the content of the first query and the second query are the same. Therefore, by having the generation server 400 execute the process of creating candidate options multiple times, it is possible that the generation server 400 will derive multiple candidates from different perspectives. If the user's selection for each of these multiple candidates can be obtained, the generation server 400 can obtain a broader range of answers regarding IPC from the user.

[0225] Figure 25 shows the functional configuration of the generation server 400, including the IPC classification unit 4017. In this modified example, the IPC classification unit 4017 is added to the control unit 4010 of the generation server 400 shown in Figure 14. The IPC classification unit 4017 determines the user's IPC to be included in the resume. Using the user's work history information obtained through dialogue, the IPC classification unit 4017 can present the user with IPCs that are considered to correspond to the user's skills. Furthermore, the IPC classification unit 4017 can also present the user with IPCs that are considered to correspond to the user's skills using work history information imported by the data import unit 4011. After presenting the user with multiple IPCs, the IPC classification unit 4017 determines the IPC that is appropriate for the user's skills through dialogue. The determined IPC is taken into the information organization unit 4015. The information organization unit 4015 uses the creation AI 4130 to create a resume including the IPC in a predetermined format. The resume registration unit 4016 stores the created resumes in the user database 421.

[0226] Figure 26 is a flowchart showing the processing procedure of the IPC classification unit 4017. First, the IPC classification unit 4017 calls the conversational AI 4110 using the large-scale language model 430 (step S71).

[0227] Next, the IPC classification unit 4017 interacts with the user using the conversational AI 4110 (step S72). Through this, the IPC classification unit 4017 obtains conversational information (including work history information) from the user. Step S72 is an example of a collection unit that collects work history information related to the user's work history. Furthermore, step S72 is an example of a dialogue unit that collects work history information by interacting with the user. Note that information regarding IPCs may be stored in the dictionary database 423. In this case, the IPC classification unit 4017 may refer to the dictionary database 423 to determine which IPCs to present to the user.

[0228] Next, the IPC classification unit 4017 presents the user with several IPCs that are considered to correspond to the user's skills (step S73). Then, the IPC classification unit 4017 determines whether or not the user has performed the operation of selecting an IPC from among the presented IPCs (step S74).

[0229] The IPC classification unit 4017 determines the user's request if the user has not performed an operation to select an IPC (step S76). More specifically, if the user requests the recreation of an IPC, the IPC classification unit 4017 returns to step S73, changes the IPCs it presents, and then presents several IPCs to the user again. This process is performed, for example, when a click operation of button 602 shown in Figure 24 is detected. If the user requests to restart the interaction, the IPC classification unit 4017 returns to step S72 and interacts with the user again. This process is performed, for example, when a click operation of button 603 shown in Figure 24 is detected.

[0230] The IPC classification unit 4017 determines, for example, that the user is performing an operation to select an IPC when it detects a click operation of the button 601 shown in Figure 24. In this case, the IPC classification unit 4017 determines the IPC to be recorded in the resume based on the user's operation (step S75), and completes the processing according to this flowchart. The generation server 400 registers the IPC determined in step S75 as part of the work history information in the user database 421. Therefore, the work history information includes the IPC. In this flowchart, steps S72 to S75 are an example of a collection unit that collects patent classification information related to the user's work based on information obtained from the user through dialogue. As shown in steps S72 to S75, the collection unit presents the user with multiple IPCs related to the user's work based on information obtained from the user through dialogue, and then determines the IPC corresponding to the user's selection as the user's work history information.

[0231] Next, we will describe some examples of resumes with reference to Figures 27 to 30. Figures 27 to 30 show examples of resumes that include IPC classifications. The resumes shown in Figures 27 to 30 include basic information, job duties, and IPCs related to the job duties. In particular, Figure 27 shows a resume format in which the IPC section is listed separately from the job duties section. In contrast, Figure 28 shows a resume format in which the corresponding IPCs are incorporated into the job duties description.

[0232] A format may be adopted in which an IPC (Instructional Programming Certificate) section is listed separately from the job description section, while the corresponding IPC is incorporated into the job description. Figure 29 shows an example of a resume created using such a format.

[0233] If a patent application exists in which the user is credited as an inventor, a patent section may be included in the resume, as shown in Figure 30. The patent section may include the corresponding IPC (Instructional Program) information along with the patent information. By including the user's patent information along with the IPC in the resume in this way, the user can more strongly showcase their expertise.

[0234] In this way, IPCs corresponding to the user's skills can be included in the resume in various formats. The generation server 400 stores information on job content, job experience, and employment period linked with the IPC as work history information in the user database 421. As shown in Figure 30, if the generation server 400 obtains information on the user's patents, it stores the patent information linked with the IPC as work history information in the user database 421. Furthermore, the generation server 400 stores the resumes exemplified in Figures 27 to 30 in the user database 421. The generation server 400 may also allow the user to select the format of the resume through dialogue. Dialogue is a concept that includes expressions of intent (questions and answers, etc.) exchanged between the generation server 400 and the user.

[0235] Here, we have explained patent classification as an example of format information that includes the necessary information to be included in a resume. Patent classification is not limited to IPC; F-terms, FI-terms, and CPC (Cooperative Patent Classification) may also be used.

[0236] [Other variations] Figure 31 shows an example of utilizing Retrieval-Augmented Generation (RAG) technology in the functional configuration of the generation server 400. RAG is a technology that configures a large-scale language model to access a knowledge source containing the latest and most accurate information, and then has the large-scale language model generate answers based on that knowledge source. As is well known, large-scale language models can sometimes output inaccurate or misleading information, which is called hallucination. RAG can complement such imperfections in large-scale language models and improve the quality of the answers they generate.

[0237] To improve the accuracy of selecting IPCs, an IPC database 429 containing IPCs and patent information may be provided on the generation server 400, as shown in Figure 31. The large-scale language model 430 retrieves IPCs from the IPC database 429 and identifies candidate IPCs that are considered to correspond to the user's skills based on the retrieved IPCs.

[0238] This prevents the large-scale language model 430 from outputting responses that constitute hallucination. As a result, the accuracy and reliability of the large-scale language model 430 can be improved. In addition, system administrators can easily access the information sources from which the large-scale language model 430 derived its responses. This allows system administrators to easily determine the accuracy of the responses obtained from the large-scale language model 430.

[0239] In general, by adopting RAG technology, it is possible to create conversational AI that specializes in the desired function and can provide more precise answers. For example, by including company confidential information, it is possible to create conversational AI intended for use exclusively within the company. It is also possible to input a large amount of information tailored to the purpose into the large-scale language model 430. Furthermore, there is the advantage of being able to easily switch between different types of large-scale language models 430.

[0240] Generally, to obtain appropriate answers from generative AI, it is considered important to improve the quality of the prompts that users input when interacting with the AI. Prompt engineering is a technique known for improving the quality of such prompts. Prompt engineering is a technique for developing and optimizing prompts given to large-scale language models in order to use them efficiently. Prompt engineering is a method for optimizing the output for a specific task, based on the premise of leveraging existing models.

[0241] In contrast, there is the concept of fine-tuning. Fine-tuning is a technique that improves the performance of an existing model for a specific task by further training it. In fine-tuning, at least a portion of a pre-trained model, which was generated based on one dataset, is further trained on another dataset. This fine-tunes the parameters of the machine learning model for a specific task. Fine-tuning is sometimes interpreted as a type of transfer learning in a broad sense. However, the two differ in that fine-tuning is a technique that fine-tunes the weights of all layers of a pre-trained model, while transfer learning is a technique that fixes the weights of a pre-trained model and trains only using the added layers.

[0242] Fine-tuning has the problem of requiring enormous computational resources because it necessitates further training of large language models with numerous parameters. Prompt tuning solves this problem through a different approach than fine-tuning. In prompt tuning, the prompts themselves are the target of training. In other words, in prompt tuning, the parameters corresponding to the prompts are the target of optimization.

[0243] RLHF (Reinforcement Learning from Human Feedback) is a model learning method that combines "supervised learning," "reinforcement learning," and "inverse reinforcement learning." According to RLHF, it is possible to train AI on complex tasks such as natural language processing while minimizing elements that require human involvement, such as supervised learning. Therefore, it is possible that the large-scale language model 430 may be trained using such RLHF.

[0244] In this embodiment, a large-scale language model was given as an example of a natural language processing algorithm. However, algorithms that can be adopted as natural language processing algorithms are not limited to large-scale language models. For example, instead of a large-scale language model, an algorithm generated by a rule-based method such as pattern matching may be adopted.

[0245] The user device 500 (recruiter device 200 and applicant device 300) does not necessarily have to be equipped with a processor, memory, communication interface, and input / output interface as shown in Figure 2, but may also be a thin client system using VDI (Virtual Desktop Infrastructure). A thin client system using VDI is a system that transfers and uses a desktop environment located on a server to a terminal in a remote location. The user device 500 (recruiter device 200 and applicant device 300), sharing server 100, and generation server 400 do not necessarily have to be independent devices. When using such a thin client system, the functions of the user device 500, sharing server 100, and generation server 400 can be provided on the same aggregation server.

[0246] Databases 120 and 420 are not limited to relational databases; object-oriented databases, NoSQL databases, and other types of databases may also be used.

[0247] Each of the sharing server 100 and the generation server 400 is an example of a compute device. A compute device may be configured using servers (on-premise servers, cloud servers, etc.) or serverless systems. Here, an on-premise server is a server installed and managed within facilities managed by the company itself. A cloud server is a server provided by another company via a network (a leased server). A serverless system is a system that allows the use of compute and memory functions only when needed, without being aware of the existence of a server. A compute device includes servers and serverless systems. Servers include on-premise servers and cloud servers.

[0248] [Aspect] The following are the aspects of this disclosure.

[0249] (Article 1) The work history information collection device (generation server 400, 400A) described in Article 1 comprises an acquisition unit (step S11) that acquires format information containing the required information for a work history document, a collection unit (step S11, step S22) that collects work history information relating to the user's work history, and a storage unit (storage 403) that stores a natural language processing algorithm. The collection unit collects work history information corresponding to the required information by interacting with the user using the natural language processing algorithm stored in the storage unit (step S22).

[0250] (Paragraph 2) The work history information collection device described in Paragraph 2 further comprises, in addition to the work history information collection device described in Paragraph 1, a creation unit (step S53) that creates a work history document using the work history information collected by the collection unit, and when the collection unit has completed collecting work history information relating to the required information, the creation unit uses a natural language processing algorithm stored in the storage unit to create a work history document according to the format information (step S53).

[0251] (Paragraph 3) The work history information collection device described in Paragraph 3 further includes, in addition to the work history information collection device described in Paragraph 2, a work history database (user database 421) in which work history information collected before interaction by the collection unit is registered. If the work history information registered in the work history database contains information corresponding to the required entries, the creation unit creates a work history document based on the work history information registered in the work history database (step S13).

[0252] (Paragraph 4) The work history information collection device described in Paragraph 4 further comprises, in addition to the work history information collection device described in Paragraph 2 or 3, an output unit configured to output the work history created by the creation unit to a user device (step S110, step S115: the generation server 400 may also have the function of a sharing server 100), and the user device is a recruiter device (200) operated by a recruiter, or an applicant device (300) operated by an applicant, in a matching system that matches recruiters who are looking for contractors for work with applicants.

[0253] (Paragraph 5) The work history information collection device described in Paragraph 5 further comprises, in addition to the work history information collection device described in any one of Paragraphs 1 to 4, a dictionary database (dictionary database 423), a registration unit (step S34) that registers the meanings of terms included in the work history information in the dictionary database, and a display unit (step S43) that displays the work history document on a display device (user device 500), wherein the display unit displays the meaning of the term on the display device (step S44) if the term registered in the dictionary database is included in the work history document.

[0254] (Clause 6) In addition to the work history information collection device described in paragraph 5, the collection unit of the work history information collection device described in paragraph 6 will inquire with the user about the meaning of terms while interacting with the user (step S32).

[0255] (Clause 7) The employment history information collection device described in paragraph 7 includes, in addition to the employment history information collection device described in any one of paragraphs 1 to 6, a natural language processing algorithm which includes a large-scale language model (large-scale language models 430, 430A, 430B).

[0256] (Clause 8) In addition to the employment history information collection device described in any one of paragraphs 1 to 7, the collection unit of the employment history information collection device described in paragraph 8 collects patent classification information related to the user's job based on information obtained from the user through dialogue (step S75), and the employment history information includes the said patent classification information.

[0257] (Paragraph 9) In addition to the employment history information collection device described in Paragraph 8, the collection unit of the employment history information collection device described in Paragraph 9 presents the user with multiple patent classification information related to the user's job based on the information obtained from the user through dialogue, and then confirms the patent classification information according to the user's selection as employment history information (Steps S72 to S75).

[0258] (Paragraph 10) The method described in Paragraph 10 is a method for creating a resume information collection, the method comprising causing a computer to perform the steps of obtaining format information containing the required information for a resume and collecting resume information relating to a user's work history, the collecting step of collecting resume information corresponding to the required information by interacting with the user using a natural language processing algorithm.

[0259] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims rather than by the description of the embodiments above, and all modifications within the meaning and scope equivalent to the claims are intended to be included. [Explanation of Symbols]

[0260] 1 Matching system, 50 Internet, 100 Sharing server, 101 Processor, 102 Memory, 103 Storage, 104 Communication interface, 120 Database (DB), 121 Corporate database (Corporate DB), 122 Member database (Member DB), 123 Community database (Community DB), 124 Recruitment database (Recruitment DB), 200, 200A, 200B, 200C Recruiter device, 201 Processor, 202 Memory, 203 Communication interface, 204 Input / Output interface, 205 Display, 206 Operation unit, 300, 300A, 300B, 300C Applicant device, 301 Processor, 302 Memory, 303 Communication interface, 304 Input / Output interface, 305 Display, 306 Operation unit, 400, 400A Generation server, 401 Processor, 402 Memory, 403 Storage, 404 Communication Interface, 410 Program, 411 Dialogue Program, 412 Confirmation Program, 413 Creation Program, 420 Database (DB), 421 User Database (User DB), 422 Dialogue Information Database (Dialogue Information DB), 423 Dictionary Database (Dictionary DB), 426 Fulfillment Requirements Database (Fulfillment Requirements DB), 427 Original Information Storage Database (Original Information Storage DB), 428 Generation Format Database (Generation Format DB), 429 IPC Database, 430, 430A, 430B Large-scale Language Model, 500, 500A User Device, 550 Screen, 551 Question Frame, 552 Answer Frame, 601~603 Buttons, 4010, 4010A Control Unit, 4011 Data Import Unit, 4012 Information Acquisition Unit, 4013 Dictionary Information Registration Unit, 4014 Dictionary information display unit, 4015 Information organization unit, 4016 Resume registration unit, 4017 IPC classification unit, 4021 Input unit, 4022 Content satisfaction determination unit, 4023 Input request unit, 4024 Original information storage unit, 4025 Generation unit, 4026 Confirmation request unit, 4027 Output unit, 4110 Dialogue AI, 4120 Confirmation AI, 4130 Creation AI.

Claims

1. A device for collecting employment history information, An acquisition unit that obtains format information containing the necessary information to be included in a resume, A collection unit that collects work history information about the user's work history, It comprises a memory unit that stores natural language processing algorithms, The aforementioned collection unit is a work history information collection device that collects work history information corresponding to the required information by interacting with the user using a natural language processing algorithm stored in the memory unit.

2. The system further comprises a creation unit that creates a resume using the work history information collected by the aforementioned collection unit, The work history information collection device according to claim 1, wherein the creation unit creates a work history document in accordance with the format information using a natural language processing algorithm stored in the storage unit when the collection unit has completed collecting work history information relating to the required information.

3. The system further includes a career history database in which career history information collected prior to the dialogue by the aforementioned collection unit is registered. The creation unit creates a resume based on the work history information registered in the work history database if the work history information registered in the work history database includes information corresponding to the required items to be included, as described in claim 2.

4. The system further includes an output unit configured to output the resume created by the creation unit to a user device, The job history information collection device according to claim 2 or 3, wherein the user device is a recruiter device operated by a recruiter, or an applicant device operated by an applicant, in a matching system that matches recruiters who are seeking contractors for work with applicants.

5. Dictionary database and, A registration unit that registers the meanings of terms included in the aforementioned work history information into a dictionary database, The system further comprises a display unit that displays the aforementioned work history on a display device, The employment history information collection device according to any one of claims 1 to 4, wherein the display unit displays the meaning of a term on the display device if the term registered in the dictionary database is included in the employment history document.

6. The employment history information collection device according to claim 5, wherein the collection unit inquires from the user about the meaning of the terms while interacting with the user.

7. The employment history information collection device according to any one of claims 1 to 6, wherein the natural language processing algorithm includes a large-scale language model.

8. The collection unit collects patent classification information related to the user's job based on the information obtained from the user through the dialogue. The employment history information collection device according to any one of claims 1 to 7, wherein the employment history information includes the patent classification information.

9. The employment history information collection device according to claim 8, wherein the collection unit presents the user with a plurality of patent classification information related to the user's job based on the information obtained from the user through the dialogue, and then determines the patent classification information according to the user's selection as the employment history information.

10. A method for collecting work history information, The above method involves a computer, Steps include obtaining format information that includes the necessary information for a resume, The system performs the steps of collecting work history information about the user's work history, The method includes a step of collecting work history information corresponding to the required information by interacting with the user using a natural language processing algorithm.

Images