Talent market place system using generative ai, and talent market place program using generative ai

Abstract

To support decision making of a recruiter with further comprehensive and multi-lateral evaluation of talents and recommendation based on various input data.SOLUTION: A TMP system 1 for supporting matching of a recruiter and an applicant includes: an atypical information shaping unit 20 which outputs, with generative AI 2, history and achievement data 22 of each talent from atypical talent data 21; an evaluation item setting unit 30 which extracts, with the generative AI 2, evaluation items of each talent, and outputs them as skill definition 32 on the basis of recruiting data 31; and a recommend processing unit 40 which selects, with the generative AI 2, recommend items from the evaluation items of the skill definition 32, evaluates, with the generative AI 2, each talent on the basis of the history and achievement data 22 for each selected recommend item according to each set evaluation criterion, generates a reason of recommendation with the generative AI 2 for a talent to be recommended, and outputs the same together with the evaluation results.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a technology that contributes to human capital management in enterprises, and particularly to a technology effective for application to a talent market place system and a talent market place program that realize a talent market place.

Background Art

[0002] In Japanese companies where the productive population is decreasing, it is essential to utilize human capital with maximum efficiency. That is, the management, while overlooking the entire company, links the talent strategy in which the personnel department procures and trains the human resources necessary for the implementation of the business strategy, and the business strategy in which each business department formulates a business strategy that makes the most of the strengths of human resources (management strategy). By doing so, it is important to maximize the value of "human assets" and lead to an improvement in the medium- to long-term corporate value.

[0003] However, in the modern VUCA (Volatility, Uncertainty, Complexity, Ambiguity) where future prediction is difficult, the business strategy changes, and the mobility and diversity of human resources are also increasing. It is extremely difficult to respond to both changes in the conventional centralized decision-making structure led by the management and the personnel department.

[0004] Therefore, there has been a consideration to form a mechanism of "internal talent market" (talent market place) that matches and links the operations necessary for the implementation of the business strategy and the abilities, achievements, and intentions of each individual human resource according to the market principle, and to dynamically link the talent strategy and the business strategy by this mechanism to improve on-site engagement and productivity.

[0005] As a technology related to determining an assignment destination by matching a recruiter (job requester) and an applicant (job seeker), for example, in Japanese Patent Application Laid-Open No. 2004-62270 (Patent Document 1), for each of a plurality of categories common to the job requester and the job seeker, the job requester side response information selected by the job requester from among a plurality of set options is compared with the job seeker side response information selected by the job seeker, and the evaluation points of the job seeker from the perspective of the job requester and the evaluation points of the job requester from the perspective of the job seeker are respectively calculated, and matching between the job requester and the job seeker is performed based on these points.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0007] According to the conventional technology as described in Patent Document 1, it is possible to perform matching between an applicant and a recruiter to create an assignment plan, but it is a simple matching method that assists the personnel department when creating a trial plan for the assignment destination, and there are limitations in terms of the appropriateness and effectiveness of the matching results.

[0008] In order to enable more appropriate and effective matching in the talent marketplace, it is required to support the decision-making of recruiters through more comprehensive and multi-faceted evaluation and recommendation of talents. To achieve this, it is required to diversify the data input into the talent marketplace and have a mechanism for performing standardized evaluation and recommendation after setting evaluation items from multiple perspectives.

[0009] Therefore, an object of the present invention is to provide a talent marketplace system and a talent marketplace program that support the decision-making of recruiters through more comprehensive and multi-faceted evaluation and recommendation of talents based on various input data.

[0010] The above and other objects and novel features of the present invention will become apparent from the description of this specification and the accompanying drawings.

Means for Solving the Problems

[0011] Among the inventions disclosed in the present application, the outline of representative ones will be briefly described as follows.

[0012] A talent marketplace system, which is a representative embodiment of the present invention, is a talent marketplace system that supports matching between recruiters and applicants. The system includes an unstructured information shaping unit that extracts information on the experience and achievements of each talent from the unstructured information related to each talent of the applicant and outputs it as resume and achievement data by a generative AI; an evaluation item setting unit that extracts information on skills that are evaluation items for each talent by a generative AI based on job information and outputs it as a skill definition; a recommendation process unit that selects, by a generative AI, recommendation items to be evaluated with emphasis in the cases related to the recruiter from the evaluation items of the skill definition, evaluates each of the selected recommendation items for each talent by a generative AI based on the resume and achievement data according to the evaluation criteria set for each, generates a reason for the recommendation for each talent by a generative AI, and outputs it together with the result of the evaluation.

[0013] Further, the present invention can also be applied to a program that operates a computer as the above-described talent marketplace system.

Effects of the Invention

[0014] Among the inventions disclosed in the present application, the effects obtained by representative ones will be briefly described as follows.

[0015] That is, according to a representative embodiment of the present invention, it is possible to support the decision-making by recruiters through more comprehensive and multi-faceted evaluation and recommendation of talents based on various input data.

Brief Description of Drawings

[0016]

Figure 1

Figure 2

Figure 3

Embodiments for Carrying Out the Invention

[0017] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In all the drawings for explaining the embodiments, the same reference numerals are generally given to the same parts, and the repeated explanations thereof are omitted. On the other hand, for the parts explained with reference numerals in a certain drawing, they are not shown again in the explanations of other drawings, but may be referred to with the same reference numerals.

[0018] <Overview> A talent marketplace (hereinafter sometimes referred to as "TMP") system which is an embodiment of the present invention is, for example, an information processing system that matches a plurality of internal recruitment within a company, etc. (the departments, groups, etc. (hereinafter sometimes collectively referred to as "recruiters") that are the recruiters) with applicants for these.

[0019] In this embodiment, during matching, in addition to stereotypical information such as the job title, qualifications, and possessed skills of the applicant, various unstructured information existing within the company that has not been utilized conventionally (text, images, audio, and other information; in this embodiment, it will be described as text information) is used as input data, enabling the utilization of diverse input data. Unstructured information includes, for example, various types of text information such as the applicant's work history, self-promotion text, information related to matching and human resources such as the recruitment requirements by the recruiter, as well as project plans, proposals, reports, and chats created by the applicant during work.

[0020] To handle the input of such unstructured information (text information), in this embodiment, by leveraging generative AI (Artificial Intelligence) such as GhatGPT (registered trademark) that has seen increasing utilization in recent years, promising candidates who match the recruitment requirements based on unstructured information are evaluated and picked out from multiple aspects. And together with quantitative evaluation, qualitative evaluation such as the reasons for recommendation is output as text, etc., to support the decision-making of the recruiter through more comprehensive and multi-faceted evaluation and recommendation of talents.

[0021] Figure 2 is a diagram showing an overview of an example of talent evaluation and recommendation in a talent marketplace (TMP) system according to an embodiment of the present invention. Here, for the recruitment requirements on the recruitment side related to a specific project, first, on the talent side of the applicant on the left side of the figure, for example, a candidate list of talents is mechanically filtered by stereotypical information such as job title, qualifications, and possessed skills, and narrowed down to a certain number of candidates.

[0022] Then, by using various types of fixed and non-fixed information such as the work experience, supervisor evaluations, and project plans and reports created in the course of work of these human resources, as well as the fixed and non-fixed information such as the recruitment requirements and job data of the recruiting side as input, evaluation items for comprehensively evaluating human resources are set. The setting of these evaluation items may be manually performed by users such as the person in charge or the human resources person on the recruiting side. However, in this embodiment, the generative AI 2 automatically sets them by using non-fixed information. It is also possible to improve practicality and effectiveness by manually revising the evaluation items proposed by the generative AI 2.

[0023] After that, for each of the set evaluation items, the generative AI 2 evaluates them, for example, on a five-point scale based on the content described in the fixed and non-fixed information, picks up promising human resources as candidates based on the evaluation, and for each of these human resources, outputs the reasons and basis for the evaluation as text in addition to the evaluation. For example, recommend promising human resources to the recruiting side in the form of "Evaluation and Recommendation Text" on the right side in the figure.

[0024] <System Configuration> FIG. 1 is a diagram showing an overview of a configuration example of a talent marketplace (TMP) system according to an embodiment of the present invention. The TMP system 1 may be implemented by an information processing terminal such as a PC (Personal Computer) or a tablet-type terminal, or may be implemented by a server device or a virtual server constructed on a cloud computing service. Although it is described as one logical information processing system in the figure, physically, the functions may be distributed and implemented on a plurality of information processing terminals, servers, etc.

[0025] The TMP system 1 realizes various functions related to TMP construction by executing, for example, an OS (Operating System), a DBMS (DataBase Management System), middleware such as a web server program, and software operating thereon, which are expanded onto the memory from a recording device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) by a CPU (Central Processing Unit) not shown in the figure.

[0026] This TMP system 1 has, for example, each part such as a filtering part 10, an unstructured information shaping part 20, an evaluation item setting part 30, and a recommendation processing part 40 implemented as software. These parts may be implemented as one application program as a whole, or may be implemented as independent programs and cooperate with each other.

[0027] The filtering part 10 has a function of inputting information of a candidate talent list 11 obtained from personnel information and application information with recruitment requirements related to a target case, filtering and narrowing down in advance based on structured information such as job positions and qualifications, and outputting a list of candidate talents 12.

[0028] The unstructured information shaping part 20 has a function of inputting unstructured talent data 21, which is various unstructured information (text) such as a project plan or a report related to candidate talents 12, automatically extracting experiences and achievements using a generation AI2, shaping them into a predetermined format, and outputting them as experience / achievement data 22. By automatically describing the content of the experience / achievement data 22 by the generation AI2, labor saving of applicants can be achieved, and by standardizing unstructured information to a certain extent, it can be easily utilized.

[0029] Also, by pre-defining the skill definition 32 described later and automatically extracting experiences, achievements, etc. according to this, it is possible to extract in a form that conforms to the information required by the recruiter. This can support addressing the issue of "not knowing what to write" when an applicant appeals with their experiences and achievements during application, and the issue of "not being able to judge what was not written" when a recruiter evaluates an applicant's experiences and achievements.

[0030] The evaluation item setting unit 30 has a function of dynamically creating and outputting a skill definition 32 that lists all the skills (evaluation items) required in each job offer data 31 with the job offer data 31 from a plurality of recruiters as input. The skills required in a large number of job offer data 31 can be said to be skills in high demand. The skill definition 32 may be automatically created by the generation AI2 in consideration of the purpose and content of the recruitment, etc., with the job offer data 31 as input, and the personnel department, etc. may manually adjust and customize the content for creation. Characteristics and positions such as "skills that can be acquired immediately" and "skills that take time to acquire" may be set, or weightings such as importance may be set. When creating the skill definition 32, an existing skill definition may be used as an initial value to reflect existing efforts, management policies, etc.

[0031] The recommendation processing unit 40 selects, with the generation AI2, an evaluation axis consisting of skills that focus on analyzing the recruitment requirements related to the target case from the skills (evaluation items) in the skill definition 32, with the skill definition 32, the experience / achievement data 22 related to each candidate talent 12, etc. as input, and evaluates each candidate talent 12 with the generation AI2 based on the selected evaluation axis, and has a function of outputting promising talents as recommended talents 43 based on the evaluation results. When outputting the recommended talents 43, for example, with the generation AI2, strengths / weaknesses of the target talent and support that should be provided by the department to which the target talent belongs may be generated, and output as a text such as the "evaluation and recommendation text" shown in Figure 2, for example, in a form understandable to the recruiter, so as to encourage the matching to be soft-landed.

[0032] When selecting evaluation axes, for example, with respect to the evaluation axes objectively selected by the generative AI 2, the recruiter may subjectively adjust and revise them according to the requirements of the business or project, etc. For each selected evaluation axis, the recruiter can set the evaluation criteria (how to read the data of the human resources) for evaluation according to the circumstances of the business or project, etc. For example, as a five-level evaluation, criteria such as "5: Deep knowledge and experience to become a leader, 4: Immediate combat power, 3: Have experience and can be practical with training, 2: Have knowledge, 1: No particular suitability" can be set.

[0033] When evaluating each candidate human resource 12, the generative AI 2 objectively reads and processes a large amount of regular and irregular information related to each individual human resource according to the evaluation axes and evaluation criteria. From the evaluation results for each candidate human resource 12, a skill map 42 can be obtained that shows how many human resources with what level for each skill (evaluation item) in the skill definition 32, and thus an inventory of human resources based on skills can be carried out.

[0034] When outputting the recommended human resources 43 based on the evaluation results of each candidate human resource 12, by adding not only quantitative numerical values but also the text of the reasons for the recommendation (that is, a summary of the resume of the candidate human resource 12 based on the evaluation axes), it is possible to support the qualitative understanding of the recruiter when evaluating and judging the recommended human resources 43 and the explanation to the surroundings (without having to go to obtain the raw data).

[0035] <Flow of processing> Figure 3 is a flowchart showing an overview of an example of the process flow related to personnel recommendation in an embodiment of the present invention. First, the filtering unit 10 filters and narrows down the information of the personnel list 11 of applicants based on the recruitment requirements related to the target case and based on fixed information such as job positions and qualifications, and outputs candidate personnel 12 (step S01). After that, the unstructured information shaping unit 20 inputs various unstructured personnel data 21 such as project plans and reports related to the candidate personnel 12, automatically extracts work experience and achievements, etc. using the generation AI2, shapes them into a predetermined format, and outputs them as work experience / achievement data 22 (S02).

[0036] After that, the evaluation item setting unit 30 inputs job applicant data 31 from a plurality of recruiters, and dynamically creates or updates a skill definition 32 that lists all the skills (evaluation items) required in each job applicant data 31 using the generation AI2 and manually, and outputs it (S03).

[0037] After that, the recommendation processing unit 40 inputs the skill definition 32, the work experience / achievement data 22 related to each candidate personnel 12, etc., and selects evaluation axes (recommendation items) that focus on analyzing the recruitment requirements related to the target case from the evaluation items in the skill definition 32 using the generation AI2 and manually (S04). Then, for each selected evaluation axis, evaluation criteria for scoring are set (S05), and each candidate personnel 12 is scored and evaluated using the generation AI2 based on each evaluation axis (recommendation item) (S06). Furthermore, for promising personnel, landing support (comprehensive review) is performed to generate reasons for recommendation, strengths / weaknesses of the target personnel, and support that should be provided by the department to which the target personnel belongs, etc. (S07), and these are output as recommended personnel 43 in a form such as the "evaluation / recommendation text" shown in the example of FIG. 2, and the process ends.

[0038] As described above, according to the TMP system 1 which is an embodiment of the present invention, by utilizing the generative AI 2, it is possible to comprehensively evaluate and pick up promising talents who match the recruitment requirements based on various unstructured information (text information) from multiple aspects. And together with quantitative evaluations such as scoring, it is possible to support the decision-making of recruiters through more comprehensive and multi-faceted evaluations and recommendations of talents, such as outputting qualitative evaluations such as the reasons for recommendations as text.

[0039] As described above, the invention made by the present inventor has been specifically described based on the embodiments. However, it goes without saying that the present invention is not limited to the above embodiments and can be variously modified without departing from the gist thereof. Also, the above embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described. Further, it is possible to add, delete, or replace a part of the configuration of the above embodiments with other configurations.

[0040] Note that each of the above configurations, functions, processing units, processing means, etc. may be realized in hardware, for example, by designing a part or all of them with an integrated circuit. Also, each of the above configurations, functions, etc. may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be placed in a recording device such as a memory, a hard disk, an SSD, or a recording medium such as an IC card, an SD card, or a DVD.

[0041] Also, in each of the above figures, control lines and information lines are shown as those considered necessary for explanation, and do not necessarily show all the control lines and information lines in implementation. In practice, it may be considered that almost all configurations are interconnected.

Industrial Applicability

[0042] The present invention can be used in a talent marketplace system and a talent marketplace program for realizing a talent marketplace.

Explanation of Signs

[0043] 1... Talent Marketplace (TMP) System, 2... Generative AI 10... Filtering Unit, 11... Talent List, 12... Candidate Talent 20... Unstructured Information Shaping Unit, 21... Unstructured Talent Data, 22... Experience and Achievement Data 30... Evaluation Item Setting Unit, 31... Recruitment Requirement Data, 32... Skill Definition 40... Recommendation Processing Unit, 42... Skill Map, 43... Recommended Talent

Claims

1. A talent marketplace system for assisting in the matching of recruiters and applicants, an unstructured information shaping unit that extracts information on the experience and achievements of each talent from the unstructured information related to each talent of the applicants and outputs it as resume and achievement data by a generative AI; an evaluation item setting unit that extracts information on skills that are evaluation items for each talent by a generative AI based on job information and outputs it as a skill definition; a recommendation processing unit that selects, by a generative AI, recommendation items to be evaluated with emphasis in the cases related to the recruiters from the evaluation items of the skill definition, evaluates each of the selected recommendation items for each talent by a generative AI according to the evaluation criteria set for each, generates a reason for the recommendation for each of the talents to be recommended by a generative AI, and outputs it together with the result of the evaluation. A talent marketplace system having these components.

2. In the talent marketplace system according to Claim 1, the evaluation item setting unit accepts input for revising the skill definition extracted by a generative AI. A talent marketplace system.

3. In the talent marketplace system according to Claim 1, the recommendation processing unit accepts input for revising the recommendation items selected by a generative AI. A talent marketplace system.

4. In the talent marketplace system according to Claim 1, the recommendation processing unit generates, by a generative AI, information including the strengths / weaknesses of the talent to be recommended and advice for the recruiter for each of the talents to be recommended, and outputs it together with the result of the evaluation. A talent marketplace system.

5. In the talent marketplace system according to Claim 1, further, it has a filtering unit that filters each talent of the applicants in advance based on the structured information of each talent. A talent marketplace system.

6. A talent marketplace program for operating a computer as a talent marketplace system for assisting in the matching of recruiters and applicants, wherein the computer From the unstructured information related to each talent of the applicant, extracting, by means of a generative AI, the information on the experience and achievements of each talent and outputting it as resume and achievement data; Based on the job information, extracting, by means of a generative AI, the information on the skills that are the evaluation items for each talent and outputting it as a skill definition; From the evaluation items of the skill definition, selecting, by means of a generative AI, the recommended items to be evaluated with emphasis in the case related to the recruiter; For each of the selected recommended items, evaluating, by means of a generative AI based on the resume and achievement data, each talent according to the evaluation criteria set for each; Generating, by means of a generative AI, the reason for the recommendation for the talent to be recommended and outputting it together with the result of the evaluation. A talent marketplace program that executes the above steps.

Images