Methods to support the generation of talent lists in corporate recruitment activities
The system scores candidate data to generate a talent list with higher accuracy, addressing the mismatch issue in existing recruitment methods by identifying high-potential candidates for companies.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- HRBRAIN CO LTD
- Filing Date
- 2024-08-30
- Publication Date
- 2026-07-22
AI Technical Summary
Existing methods for generating talent pools lack accuracy in matching candidates with companies, resulting in suboptimal recruitment outcomes.
A system that utilizes a server terminal to score candidate data based on match with company attributes, generating a talent list with associated scores to identify high-potential candidates.
Enhances the accuracy of talent list generation, enabling companies to approach candidates with higher precision and improve recruitment success.
Smart Images

Figure 0007892923000001 
Figure 0007892923000002 
Figure 0007892923000003
Abstract
Description
Technical Field
[0001] The present invention relates to a method for assisting in generating a talent list in a company's recruitment activities.
Background Art
[0002] In recruitment activities, among the candidates who did not get hired due to circumstances on the company side or the candidate side, there may be promising talents in the future.
[0003] For example, in Patent Document 1, a technique for generating a talent pool for registering excellent talents who can be future recruitment candidates, that is, talents, is disclosed.
Prior Art Documents
Patent Documents
[0004]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0005] However, in the technique disclosed in Patent Document 1, the information referred to for generating the talent pool only remains general information about job seekers, and there is still room for improving the accuracy in the matching degree between the company and the candidate.
[0006] Therefore, an object of the present invention is to generate a talent list with higher accuracy for a company to approach candidates.
Means for Solving the Problems
[0007] A method for supporting the generation of a talent list in a company's recruitment activities, according to one aspect of the present invention, wherein the control unit of a server terminal refers to data relating to a candidate stored in the storage unit of the server terminal, scores the degree of match with the company based on the candidate's selection data, and stores the candidate's information, along with the score result of the match with the company, as a talent list in the storage unit. [Effects of the Invention]
[0008] According to the present invention, it is possible to generate a more accurate talent list for companies to approach candidates. [Brief explanation of the drawing]
[0009] [Figure 1] This is a block diagram showing a talent list generation support system according to the first embodiment of the present invention. [Figure 2] Figure 1 is a functional block diagram showing the server terminal 100. [Figure 3] Figure 1 is a functional block diagram showing the candidate terminal 200. [Figure 4] This figure shows an example of candidate data stored in server 100. [Figure 5] This figure shows an example of corporate data stored on server 100. [Figure 6] This flowchart shows an example of the processing for a talent list generation support method according to the first embodiment of the present invention. [Figure 7] This flowchart shows an example of candidate scoring processing in talent list generation support according to the first embodiment of the present invention. [Modes for carrying out the invention]
[0010] Embodiments of the present invention will be described below with reference to the drawings. The embodiments described below are not intended to unduly limit the scope of the present invention as described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present invention.
[0011] <Structure> Figure 1 is a block diagram showing a system that supports the generation of a talent list in a company's recruitment activities, according to a first embodiment of the present invention. This system 1 includes, for example, a server terminal 100 that sends and receives predetermined information to multiple candidate terminals 200A and 200B of job candidates in the recruitment activities of a recruiting company, candidate terminals 200A and 200B of job candidates, and company terminals 300A and 300B of the company conducting the recruitment activities. Here, each of the company terminals 300A and 300B can implement a program and execute the above-mentioned recruitment support method that is executed on the server terminal 100, or the server terminal 100 and the company terminals can cooperate via an API (Application Programming Interface) and execute a part of the above-mentioned recruitment support method on the server terminal 100 or the company terminal. For the sake of explanation, each terminal is described as a single or a specific number, but there is no limit to the number of each.
[0012] The server terminal 100, the candidate terminals 200A and 200B, and the corporate terminals 300A and 300B are each connected via the network NW1. The network NW consists of the Internet, intranet, wireless LAN (Local Area Network), WAN (Wide Area Network), etc. Furthermore, the server terminal 100 is characterized by being connected via the network to a large-scale language model (a natural language processing model trained using vectorized text data including question and answer sentences, converted into a specified format; hereinafter referred to as "LLM").
[0013] The server terminal 100 and the enterprise terminals 300A and 300B may be general-purpose computers such as workstations or personal computers, or may be logically implemented by cloud computing.
[0014] The candidate terminals 200A and 200B are information processing devices such as personal computers or tablet terminals, for example, but may also be configured by smartphones, mobile phones, PDAs, etc.
[0015] In this embodiment, the system 1 includes the server terminal 100, the candidate terminals 200A and 200B, and the enterprise terminals 300A and 300B. It will be described as a configuration in which the users of each terminal use their respective terminals to operate on the server terminal 100. However, the server terminal 100 may be configured as a stand-alone device, and the server terminal itself may be provided with a function for each user to directly perform operations. Hereinafter, as necessary, the candidate terminals 200A and 200B will be collectively referred to as the candidate terminal 200, and the enterprise terminals 300A and 300B will be collectively referred to as the enterprise terminal 300.
[0016] FIG. 2 is a functional block configuration diagram of the server terminal 100 in FIG. 1. The server terminal 100 includes a communication unit 110, a storage unit 120, and a control unit 130.
[0017] The communication unit 110 is a communication interface for communicating with the candidate terminal 200 and the enterprise terminal 300 via the network NW1. Communication is performed according to a communication protocol such as TCP / IP (Transmission Control Protocol / Internet Protocol), for example.
[0018] The storage unit 120 stores programs for executing various control processes and each function within the control unit 130, input data, etc., and is composed of a RAM (Random Access Memory), a ROM (Read Only Memory), etc. Further, the storage unit 120 has a candidate data storage unit 121 that stores various data related to the employment candidate, and a company data storage unit 122 that stores various data related to the job-seeking companies that conduct employment activities. Note that a database (not shown) storing various data may be constructed outside the storage unit 120 or the server terminal 100.
[0019] The control unit 130 controls the overall operation of the server terminal 100 by executing the programs stored in the storage unit 120, and is composed of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc. As functions of the control unit 130, it has an information reception unit 131 that receives information from various terminals, and an information processing unit 132 that refers to and processes various data related to the employment candidate and various data related to the job-seeking companies that conduct employment activities. The information reception unit 131 and the information processing unit 132 are activated by the programs stored in the storage unit 120 and executed by the server terminal 100, which is a computer (electronic computing device).
[0020] The information reception unit 131 receives information from the employment candidate terminal 200 and the company terminal 300 via the communication unit 110.
[0021] The information processing unit 132 refers to various data related to the employment candidate received from the employment candidate terminal 200 (for example, candidate data 1000 described later, etc.) and various data related to the job-seeking company received from the company terminal 200 (for example, company data 2000 described later), and performs predetermined processing.
[0022] Furthermore, the control unit 130 may also have a screen generation unit (not shown) that generates screen information to be displayed via the user interfaces of the candidate terminal 200 and the company terminal 300 as needed. For example, using image and text data (not shown) stored in the storage unit 120 as material, the user interface is generated by arranging various images and text in predetermined areas of the user interface according to predetermined layout rules. Processing related to the image generation unit can also be performed by a GPU (Graphics Processing Unit).
[0023] Figure 3 is a functional block diagram showing the candidate terminal 200 of Figure 1. The candidate terminal 200 comprises a communication unit 210, a display and operation unit 220, a storage unit 230, and a control unit 240.
[0024] The communication unit 210 is a communication interface for communicating with the server terminal 100 via the network NW, and communication is performed using a communication protocol such as TCP / IP.
[0025] The display operation unit 220 is a user interface used by job candidates to input instructions and display text, images, etc., in accordance with the input data from the control unit 240. If the job candidate terminal 200 is a personal computer, it consists of a display and a keyboard or mouse, and if the job candidate terminal 200 is a smartphone or tablet, it consists of a touch panel, etc. This display operation unit 220 is activated by a control program stored in the storage unit 230 and executed by the job candidate terminal 200, which is a computer (electronic calculator).
[0026] The memory unit 230 stores programs for executing various control processes and functions within the control unit 240, input data, etc., and is composed of RAM, ROM, etc. The memory unit 230 also temporarily stores the contents of communications with the server terminal 100.
[0027] The control unit 240 controls the overall operation of the candidate terminal 200 by executing a program stored in the memory unit 230, and is composed of a CPU, GPU, and the like.
[0028] Figure 4 shows an example of candidate data stored in the server terminal 100.
[0029] The candidate data 1000 shown in Figure 4 stores various data related to the candidate for employment. In Figure 4, for the sake of explanation, an example of one candidate (a user identified by candidate ID "10001") is shown, but information on multiple candidates can be stored. Various data related to the candidate can include, for example, basic information about the candidate (e.g., name, address, contact information, etc.). In addition, as selection data related to the selection of candidates, it can include academic information about the candidate's educational background, work history information about the candidate's work history, skills information about the candidate's skills and qualifications, annual income information about the candidate's annual income (including desired annual income), and information from the candidate's responses through the response items included in the step letter and offer letter (response items asking whether they wish to be selected or are interested, response items asking about their willingness to change jobs, response items asking about what they are interested in regarding the recruiting company, response items asking about the status of other applications, response items asking about their impression of the recruiting company, response items asking about their desired economic conditions, response items asking about the criteria the candidate uses to choose a job, and job postings. This includes, but is not limited to, the following: response items asking about the likelihood of joining the company when an offer is made, response items asking about topics to be discussed in subsequent interviews, response information regarding acceptance of the offer, items regarding whether the candidate has expressed their intention to resign to their current company, etc.; interview information regarding the candidate's interviews with the recruiting company during the hiring process (status, pass / fail status, interviewer / person involved, etc.); and letter information regarding step letters and offer letters addressed to the candidate (for example, the content of the letter (the above response items in the step letter or offer letter, etc.)). Here, a step letter is a letter from the company to a candidate at each stage of the selection process informing the candidate of the company's desire for them to move on to the next step. Its purpose is to provide positive feedback to the candidate in a minimal yet rich manner, foster the candidate's desire to change jobs to the recruiting company, and includes response items that allow the company to collect information necessary for attracting the candidate and designing the offer.An offer letter is a letter in which a recruiting company presents the terms of the offer, including financial conditions, when it decides to hire a candidate, and the offer is finalized when the candidate accepts it. In this embodiment, the offer letter is designed around the following points: 1) understanding the candidate (reasons for joining the current company, reasons for changing jobs, past job change motivations and decision-making criteria), 2) understanding the candidate's needs (confirmation of prerequisites (what aspects of our company interest them), future career plans and career vision and the reasons for them), 3) extracting attractive points (decision-making criteria for changing jobs, desired job type / position, etc.), 4) competition (existence and status of competitors, priority and advantages compared to competitors), 5) financial conditions (current annual salary, desired annual salary, lower limit of financial conditions), and 6) timing of job change (decision-making date, possible start date). This information is basically collected from the candidate through the aforementioned step letters. Furthermore, candidate data can include information about content (articles, images, videos, etc. provided via web pages and / or email newsletters) distributed by the recruiting company to candidates during the recruitment process and to maintain contact with candidates afterward, as well as action data regarding candidates' behavior towards such content (views, likes, comments, etc.). In addition, candidate data can also include talent list information (a so-called talent pool) that stores information about candidates with a high degree of match with the company, associated with a score that measures the degree of match.
[0030] Figure 5 shows an example of corporate data stored on the server terminal 100.
[0031] Company Data 2000 primarily stores various data related to companies that conduct recruitment activities. Figure 5 shows an example of a single company (identified by company ID "20001") for illustrative purposes, but it can store information related to multiple companies. Various data related to a company include, for example, basic company information (company name, industry, number of employees, location (address), contact information, mission, evaluation system, welfare system, technical information, information on company recruitment (open positions, organization name, organizational information, start date, financial conditions, etc.)), interview information in the company's recruitment process (candidate name, status, interview content (start date, reason for joining, timing of job change, reason for changing jobs, etc.), pass / fail status, interviewer / person in charge, etc.), letter information regarding step letters and offer letters addressed to candidates (letter content (items in the step letter or offer letter to confirm the candidate's willingness to change jobs, items to confirm their intention to proceed to the next selection step, items to confirm the recruiting company's interests, items to avoid mismatches between the recruiting company and the candidate, etc.)), and candidate response information through response items included in step letters and offer letters (response items asking about their desire or interest in selection, response items asking about their willingness to change jobs, content of interest to the recruiting company). The information may include, but is not limited to, the following: response items to be asked, response items to be asked about the status of other applications, response items to be asked about the impression of the recruiting company, response items to be asked about desired economic conditions, response items to be asked about the criteria the candidate uses to choose a job, response items to be asked about the likelihood of joining the company if the recruiting company makes an offer, and response items to be asked about what the candidate would like to hear in subsequent interviews, response information regarding acceptance of the offer, and items regarding whether the candidate has expressed their intention to resign to their current employer, etc.; analytical information (response information by acceptance / rejection, analysis based on the above candidate response information (for example, comparison of response results for each step letter of a specific candidate, rejection rate based on the response results of multiple candidates, reasons for rejection, reasons for delay, comparison of each item with other companies, comparison of response content by acceptance / rejection, offer letter generation logic based on response results, etc.), sample comment information for generating various letters and interview handover notes, and sample content information for generating the above content distributed by the recruiting company to the candidate.
[0032] Figure 6 is a flowchart showing an example of the processing of a talent list generation support method according to the first embodiment of the present invention.
[0033] First, as part of step S101, the information processing unit 132 of the control unit 130 of the server terminal 100 refers to the candidate data in the candidate data storage unit 121 of the storage unit 120.
[0034] Next, as part of step S102, the information processing unit 132 of the control unit 130 of the server terminal 100 performs a matching score with the recruiting company for each candidate, who is stored as candidate data 1000 in the candidate data storage unit 121.
[0035] Here, the method for scoring the degree of match described above will be explained with reference to Figure 7. As a preliminary step, the information processing unit 132 of the control unit 130 of the server terminal 100 refers to one or a combination of the following: the candidate's selection data, such as interview data related to interview records of the interview between the candidate and the company, data on the candidate's career and mission to the company obtained as answer information to questions included in the step letter sent by the company to the candidate, and work history data related to the candidate's resume. By referring to these elements, it generates a profile of the candidate and stores it as candidate data in the candidate data storage unit 121. Then, as the processing of step S201, the information processing unit 133 of the control unit 130 of the server terminal 100 scores the degree of match between the candidate and the hiring company based on the above selection data. As an example of a scoring method, the information processing unit 132 extracts information from the above selection data, such as answer data to questions included in step data and / or offer letters (e.g., "intention to change jobs," "decision-making criteria for changing jobs," "what you find attractive about our company," "what you are concerned about our company," etc.), that matches the candidate to the attribute information of the hiring company (e.g., the company's industry, company image, etc.), and / or information regarding the candidate's career direction, and can assign a higher score depending on the degree to which the candidate matches the company. Here, the information processing unit 132 can prompt the LLM, which is connected to the server terminal 100 via a network, to refer to the candidate's selection data, extract sentences that match the company's attributes, and perform scoring according to the amount of matching sentences, and obtain a score from the LLM.
[0036] Next, as part of step S202, the information processing unit 133 of the control unit 130 of the server terminal 100 scores the candidate's intention to change jobs based on action data related to the content distributed by the recruiting company to the candidate through the recruitment activities and to continue contacting the candidate after the recruitment activities. Here, as a preliminary step, the information processing unit 132 stores the candidate's behavioral history regarding the above content, for example, whether or not they opened and / or viewed the distributed email newsletter and the number of times they did so, as action data in the candidate data 1000 of the storage unit 120. In addition, the candidate's participation in events via content distributed by the recruiting company and the number of casual interviews can also be stored as action data. Based on such action data, the information processing unit 132 can score the candidate's intention to change jobs by adding a score corresponding to each action.
[0037] Here, the degree of match that forms the basis for scoring can be measured and scored based on static data of the candidate, such as the candidate's attributes (experienced job roles, skills, work experience, etc.), company attributes (industry, business model, phase, size, etc.), information obtained during the recruitment process (interview evaluations, responses to step-by-step letter questionnaires, content of offer letters, etc.), and dynamic data, such as the candidate's website behavior data (visits to the recruiting company's website, opening of email newsletters, viewing of websites and / or email newsletters, viewing time and content, etc.), participation data in recruiting company recruitment events, and data posted by the candidate on social media, etc. (article postings, social media).
[0038] Returning to the process in step S102, the information processing unit 132 stores the scores of the candidates scored as described above (score related to the degree of match with the company, score related to the degree of intention to change jobs, and the sum of these scores) as a talent list in the candidate data 1000 of the candidate data storage unit 121, associating them with information that identifies each candidate. In this way, by storing each of the multiple candidates stored as candidate data as a company-specific dataset, associating them with a score based on the degree of match with the recruiting company, etc., the recruiting company can easily identify the personnel it should approach for recruitment. Furthermore, the company-specific dataset can also store data referenced for scoring the candidates (for example, information obtained from step letters, information obtained through interviews, action data on content, etc.).
[0039] As described above, the system generates a talent list as a unique dataset, and the information processing unit 132 can utilize this talent list to generate and recommend a list of individuals that should be approached by recruiting companies, and update and distribute content to job candidates.
[0040] First, as part of step S103, the information processing unit 132, based on the talent list generated above, shortlists candidates with high scoring scores (high match with the company, high intention to change jobs, and / or a high total score for these), and generates a list of candidates that the recruiting company should approach.
[0041] Next, as part of step S104, the information processing unit 132 sends the generated list of candidates to be approached to the target company's corporate terminal 300, thereby recommending candidates that the company should approach.
[0042] Furthermore, as part of the processing in step S104, the information processing unit 132 refers to the action data for the candidate's content included in the talent list generated above and updates the content information to be distributed to the candidate. For example, the information processing unit 132 can add articles similar to those with a high number of views among the articles distributed to the candidate, or articles that the candidate viewed when agreeing to proceed with the interview, as content information.
[0043] Next, as part of step S105, the information processing unit 132 distributes the generated content to the candidate terminal 200 of the target company. Here, the information processing unit 132 also sends step emails to the candidate after each interview, and the hiring company can design a scenario and execute a phased content distribution based on the generated scenario for the candidate.
[0044] This allows recruiting companies to generate a talent list based on candidate data, selecting candidates from a pool of applicants based on their match with the company, and creating their own dataset. This list includes information to identify candidates and scoring information. By utilizing this talent list, companies can identify the right people to approach and update their recruitment content, thereby conducting more precise recruitment activities.
[0045] Although embodiments of the invention have been described above, these can be implemented in various other forms, and can be carried out by various omissions, substitutions, and modifications. These embodiments and variations, as well as those with omissions, substitutions, and modifications, are included within the technical scope of the claims and their equivalents. [Explanation of Symbols]
[0046] 1 System: 100 Server terminals, 110 Communication unit, 120 Storage unit, 130 Control unit, 200 Candidate terminals, 300 Enterprise terminals, NW1 Network
Claims
1. A method to support the generation of talent lists in a company's recruitment activities, The control unit of the server terminal is: Referencing selection data stored in the storage unit of the server terminal, which includes information obtained during the recruitment process of job candidates interviewed by the company, the selection data includes at least one of the following: interview records relating to the job interview of the job candidate, information on the job candidate's answers to questions included in the step letter and offer letter to the job candidate, and information on the job candidate's resume. The method involves scoring the degree of match with the attribute information of the company based on the selection data of the aforementioned job candidates, wherein the scoring is characterized by referring to the attribute information of the company stored in the storage unit, extracting information that matches the attribute information contained in the selection data, and basing the scoring on the amount of the extracted information. A method for storing, as a result of scoring the degree of match with the aforementioned company, the referenced selection data along with the score of the degree of match with the aforementioned company, as a talent list in the storage unit.
2. The method according to claim 1, The control unit, The data on the actions of the job candidates in response to the content distributed by the company to the job candidates is stored in the storage unit. Based on the aforementioned action data, the likelihood of the job candidate changing jobs is scored. A method for storing information about the job candidates, along with the scoring results of the job candidates' intention to change jobs, as a talent list in the storage unit.
3. The method according to claim 1, The control unit generates a further list of candidates in the talent list who have a high match score with the company, as candidates to be approached.
4. The method according to claim 2, The control unit generates a further list of candidates who should be approached, based on the talent list, in which candidates with a high score in the job change intention score are identified.
5. The method according to claim 2, A method for updating the content based on the action data of the control unit.