Information processing device, method, program, and system
The information processing system improves job matching by predicting income benchmarks from text features, addressing inaccuracies in existing methods and enhancing the efficiency of job searches and recruitment.
Patent Information
- Application Number
- JP2023032072
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2023-03-02
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2043-03-02
AI Technical Summary
Job seekers and companies face challenges in estimating reasonable incomes, leading to mismatched job searches and recruitment difficulties due to inaccurate predictions based on the degree of match between work history and required skills.
An information processing system that includes a server predicting income benchmarks by extracting features from text information about job applicants or desired profiles using trained models, and outputting these predictions to job seekers and recruiters.
Enhances the accuracy of income predictions, allowing job seekers to adjust their expectations and recruiters to optimize their hiring strategies, thereby improving the efficiency of job matching processes.
Smart Images

Figure 0007595327000001 
Figure 0007595327000002 
Figure 0007595327000003
Abstract
Description
[Technical field]
[0001] The present disclosure relates to an information processing device, a method, a program, and a system. [Background technology]
[0002] When job seekers choose a new job or a new job, income is one of the main factors they consider. However, it is not easy for them to estimate a reasonable income if they are hired. If a job seeker is looking for an income that is far beyond their appropriate income, they may not match the persona that the company is looking for, making their job search difficult.
[0003] On the other hand, it is not easy for companies looking to hire to get a sense of the average salary of the person they are looking for. If a company offers a salary that is far below the average salary of someone who fits the profile they are looking for, they may not receive applications from people who fit the criteria, and may have difficulty in securing the personnel they desire.
[0004] Patent Document 1 describes a technical idea that aims to present job information according to a user's work history. This technical idea corrects the base salary according to the degree of agreement between the user's work history and the skills required for the recruited personnel, and sets a salary unique to the user. [Prior art documents] [Patent documents]
[0005] [Patent Document 1] JP 2022-043587 A Summary of the Invention [Problem to be solved by the invention]
[0006] The technical idea of Patent Document 1 is to refer to the degree of match between the user's work history and the skills required of the recruited personnel in order to set the user's salary appropriately. However, in cases where a job seeker wants to know his or her own appropriate income, or wants to know whether the income that is planned to be offered to a job seeker who is deemed to match the profile of the person the company is looking for is appropriate, the analysis based on the degree of match does not provide sufficient prediction accuracy and may not provide useful information.
[0007] The purpose of this disclosure is to provide information useful in job search or recruiting activities. [Means for solving the problem]
[0008] A program of one embodiment of the present disclosure causes a computer to function as a means for obtaining text information described about a target talent, who is either a job seeker or the type of person a recruiting company is looking for, a means for extracting a first feature from the text information, a means for predicting an income benchmark for the target talent by applying an income prediction model to the first feature, and a means for outputting the predicted income benchmark for the target talent. [Brief description of the drawings]
[0009] [Figure 1] 1 is a block diagram showing a configuration of an information processing system according to an embodiment of the present invention; [Diagram 2] 2 is a block diagram showing a configuration of a job seeker terminal according to the present embodiment. FIG. [Diagram 3] FIG. 2 is a block diagram showing a configuration of a server according to the present embodiment. [Figure 4] FIG. 2 is a block diagram showing the configuration of a recruiting party terminal according to the present embodiment. [Diagram 5] FIG. 2 is an explanatory diagram of basic functions of the information processing system according to the present embodiment. [Figure 6] FIG. 1 is an explanatory diagram of one aspect of the present embodiment. [Figure 7] FIG. 13 is an explanatory diagram of another aspect of the present embodiment. [Figure 8] 13 is a flowchart of a job seeker prediction process according to the present embodiment. [Figure 9] 13A and 13B are diagrams illustrating an example of a screen displayed in the job seeker prediction process of the present embodiment. [Figure 10] 13 is a flowchart of a prediction process by a recruiting party according to the present embodiment. [Figure 11] FIG. 13 is a diagram showing an example of a screen displayed in the recruiting party prediction process of the present embodiment. [Figure 12] FIG. 13 is a block diagram showing a configuration of an information processing system according to a first modified example. [Figure 13] FIG. 13 is a diagram showing a data structure of a repository database in the first modified example. [Figure 14] FIG. 13 is a diagram showing a data structure of a development activity database according to the first modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0010] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. In the drawings for explaining the embodiment, the same components are generally designated by the same reference numerals, and the repeated description will be omitted.
[0011] (1) Information Processing System Configuration The configuration of the information processing system will be described below. Fig. 1 is a block diagram showing the configuration of the information processing system according to the present embodiment.
[0012] As shown in FIG. 1, the information processing system 1 includes a job seeker terminal 10, a server 30, and a recruiter terminal 50. The job seeker terminal 10 and the server 30 are connected via a network (eg, the Internet or an intranet) NW. The recruiting side terminal 50 and the server 30 are connected via a network NW.
[0013] The job seeker terminal 10 is an example of an information processing device that transmits a request to the server 30. The job seeker terminal 10 is, for example, a smartphone, a tablet terminal, or a personal computer. A user of the job seeker terminal 10 is a person who is job-changing or (re)job-hunting, or a person who is interested in these activities.
[0014] The server 30 is an example of an information processing device that provides a client device (the job seeker terminal 10 or the employer's terminal 50 in the example of FIG. 1) with a response in response to a request sent from the client device. The server 30 is, for example, a server computer. The server 30 manages a talent matching platform in which users of the job seeker terminal 10 and users of the employer's terminal 50 participate. The talent matching platform corresponds to a place that connects job seekers with recruiting companies. In this specification, a job seeker includes a person who intends to seek a job, and at least a person who registers job seeker information on the talent platform or prepares to register (for example, uploads a resume file or a curriculum vitae file, or inputs job seeker information). Similarly, a recruiting company includes a corporation or individual who intends to recruit, and at least a person who registers job seeker information on the talent platform or prepares to register.
[0015] The recruiting side terminal 50 is an example of an information processing device that transmits a request to the server 30. The recruiting side terminal 50 is, for example, a smartphone, a tablet terminal, or a personal computer. The user of the recruiting side terminal 50 is a person who belongs to the recruiting company (for example, a company recruiter).
[0016] (1-1) Configuration of the job seeker's device The configuration of the job seeker's terminal will now be described with reference to Fig. 2, which is a block diagram showing the configuration of the job seeker's terminal of this embodiment.
[0017] 2, the job seeking terminal 10 includes a storage device 11, a processor 12, an input / output interface 13, and a communication interface 14. The job seeking terminal 10 is connected to a display 21.
[0018] The storage device 11 is configured to store programs and data. The storage device 11 is, for example, a combination of a Read Only Memory (ROM), a Random Access Memory (RAM), and a storage (for example, a flash memory or a hard disk).
[0019] The programs include, for example, the following programs: ·OS (Operating System) programs · Programs for applications that process information (e.g. web browsers)
[0020] The data includes, for example, the following data: Databases referenced in information processing Data obtained by performing information processing (i.e., the results of performing information processing)
[0021] The processor 12 is a computer that realizes the functions of the job seeking terminal 10 by starting a program stored in the storage device 11. The processor 12 is, for example, at least one of the following: ·CPU(Central Processing Unit) ·GPU(Graphic Processing Unit) ·ASIC(Application Specific Integrated Circuit) ·FPGA(Field Programmable Array)
[0022] The input / output interface 13 is configured to obtain information (eg, user instructions) from an input device connected to the job seeking terminal 10, and to output information (eg, images) to an output device connected to the job seeking terminal 10. The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof. The output device is, for example, a display 21, a speaker, or a combination thereof.
[0023] The communication interface 14 is configured to control communication between the job seeking terminal 10 and an external device (eg, the server 30).
[0024] The display 21 is configured to display an image (a still image or a moving image). The display 21 is, for example, a liquid crystal display or an organic EL display.
[0025] (1-2) Server configuration The configuration of the server will now be described with reference to Fig. 3, which is a block diagram showing the configuration of the server according to this embodiment.
[0026] As shown in FIG. 3, the server 30 includes a storage device 31, a processor 32, an input / output interface 33, and a communication interface .
[0027] The storage device 31 is configured to store programs and data, and is, for example, a combination of a ROM, a RAM, and a storage (for example, a flash memory or a hard disk).
[0028] The programs include, for example, the following programs: -OS programs Application programs that perform information processing
[0029] The data includes, for example, the following data: Databases referenced in information processing Results of information processing
[0030] The processor 32 is a computer that realizes the functions of the server 30 by starting a program stored in the storage device 31. The processor 32 is, for example, at least one of the following. ·CPU GPU ·ASIC FPGA
[0031] The input / output interface 33 is configured to obtain information (eg, a user's instruction) from an input device connected to the server 30, and to output information (eg, an image) to an output device connected to the server 30. The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof. The output device is, for example, a display.
[0032] The communication interface 34 is configured to control communication between the server 30 and an external device (the job seeker terminal 10 or the recruiter terminal 50).
[0033] (1-3) Configuration of the recruiter's terminal The configuration of the recruiting party terminal will now be described with reference to Fig. 4, which is a block diagram showing the configuration of the recruiting party terminal of this embodiment.
[0034] 4, the recruiting side terminal 50 includes a storage device 51, a processor 52, an input / output interface 53, and a communication interface 54. The recruiting side terminal 50 is connected to a display 61.
[0035] The storage device 51 is configured to store programs and data, and is, for example, a combination of a ROM, a RAM, and a storage (for example, a flash memory or a hard disk).
[0036] The programs include, for example, the following programs: -OS programs · Programs for applications that process information (e.g. web browsers)
[0037] The data includes, for example, the following data: Databases referenced in information processing Results of information processing
[0038] The processor 52 is a computer that realizes the functions of the recruiting party terminal 50 by starting the programs stored in the storage device 51. The processor 52 is, for example, at least one of the following: ·CPU GPU ·ASIC FPGA
[0039] The input / output interface 53 is configured to acquire information (e.g., user instructions) from an input device connected to the recruiting party terminal 50, and to output information (e.g., images) to an output device connected to the recruiting party terminal 50. The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof. The output device is, for example, a display 61, a speaker, or a combination thereof.
[0040] The communication interface 54 is configured to control communication between the recruiting party terminal 50 and an external device (eg, the server 30).
[0041] The display 61 is configured to display an image (still image or moving image). The display 61 is, for example, a liquid crystal display or an organic EL display.
[0042] (2) One aspect of the embodiment An embodiment of the present invention will be described. Fig. 5 is an explanatory diagram of basic functions of the information processing system of the present invention. Fig. 6 is an explanatory diagram of one embodiment of the present invention. Fig. 7 is an explanatory diagram of another embodiment of the present invention.
[0043] 5, a user US1 transmits job seeker information to a server 30 via a job seeker terminal 10. On the other hand, a user US2 transmits job information to the server 30 via a job offeror terminal 50.
[0044] The server 30 acquires job seeker information and job offer information, and handles this information according to the specifications of the human resources matching platform. As an example, the server 30 performs a matching process between the job seeker information and the job offer information. Assume that the job seeker information acquired from the user US1 matches with the job offer information acquired from the user US2. In this case, the server 30 transmits the job seeker information acquired from the user US1 to the employer's terminal 50, and transmits the job offer information acquired from the user US2 to the job seeker's terminal 10. This makes it possible to link the user US1, who is a job seeker, with the user US2, who is a member of the company offering a job.
[0045] Depending on the specifications of the talent matching platform, the server 30 may behave differently. For example, the server 30 may not perform the matching process and may simply make at least one of the job information and job seeker information publicly available, for example, in an anonymous and searchable state. Alternatively, the server 30 may transmit the job information or job seeker information to a terminal of a talent intermediary, who may then perform the matching process.
[0046] As shown in FIG. 6, the server 30 of the present embodiment may predict the income benchmark of the user US1 based on the job seeker information acquired from the user US1. That is, the job seeker information corresponds to text information written about the user US1, and the server 30 extracts features from the text information. The text information may be, for example, a free-form text, multiple-choice text, or a combination of these. The server 30 predicts the income benchmark of the user US1 by applying an income prediction model to the extracted features, and transmits the prediction result to the job seeker terminal 10. This allows the user US1 to know the appropriate income if he or she is employed, and if the desired income is not met, the user US1 can brush up the content of the job seeker information or use the income benchmark as a criterion for selecting a job application destination.
[0047] As shown in FIG. 7, the server 30 of this embodiment may predict the income benchmark of the profile of the person expected to be employed by the recruiting company to which the user US2 belongs, based on the recruitment information acquired from the user US2. That is, the recruitment information corresponds to text information described about the profile of the person expected to be employed by the recruitment information, and the server 30 extracts features from the text information. The server 30 predicts the income benchmark of the profile of the person expected to be employed by applying an income prediction model to the extracted features, and transmits the prediction result to the recruiting side terminal 50. This allows the recruiting company to grasp the market rate of income of a person who matches the profile of the person expected to be employed by the recruiting company, so that if there is a discrepancy between the income planned to be presented to the job seeker to be employed and the income benchmark, the content of the recruitment information created can be reviewed, or the income benchmark can be used as a decision-making material when planning a recruitment plan.
[0048] As used herein, revenue benchmark is used in at least one of the following senses. - The appropriate income (market income) of the job seeker, predicted based on the job seeker's job information The salary that should be offered to the job seeker if hired -Appropriate income (average income) for a person who matches the profile of the person the company is looking for The salary that a company should offer to a job seeker when hiring
[0049] Note that the server 30 may perform both the income benchmark prediction described with reference to FIG. 6 and the income benchmark prediction described with reference to FIG. 7, or may perform only one of them.
[0050] (3) Information processing The information processing of this embodiment will be described.
[0051] (3-1) Job Seeker Prediction Processing The job seeker prediction process of this embodiment will be described below. Fig. 8 is a flowchart of the job seeker prediction process of this embodiment. Fig. 9 is a diagram showing an example of a screen displayed in the job seeker prediction process of this embodiment.
[0052] The process in FIG. 8 may be started, for example, by the job seeker terminal 10 accessing the talent matching platform and receiving an instruction from a user to start registering job seeker information.
[0053] As shown in FIG. 8, the job seeker terminal 10 executes information acquisition (S110). Specifically, the job seeker terminal 10 acquires job seeker information from a user who is a job seeker (an example of a "target talent"). The job seeker information includes text information describing the job seeker. As a first example of information acquisition (S110), the job seeker terminal 10 receives an instruction from a user to upload a resume file or a curriculum vitae file that has already been created. These resume files and curriculum vitae files are examples of job seeker information. As a second example of information acquisition (S110), the job seeker terminal 10 acquires text information on the job seeker information of the user (job seeker) entered on a form provided by the human resources matching platform as job seeker information. The job seeker information may include the job seeker's profile (e.g., work history, work experience, skills, or qualifications), the treatment desired by the job seeker (e.g., job type, treatment (which may include income), or working conditions), or a combination thereof.
[0054] The job seeker information may include at least one of the following: Information about teams the job seeker has previously belonged to Information about the job applicant's previous work experience Information about the job seeker's technical skills Information about the candidate's management experience
[0055] Information about the team may include, for example, information about the size of the team, or the job seeker's role or tenure on the team.
[0056] In this specification, a team means a group consisting of multiple members. In this specification, a team may also refer to an engineer team, which is a group consisting of multiple engineers. A team (particularly, an engineer team) may be in charge of developing a specific product. The product is typically software, and may be, for example, a website for providing a web service such as SaaS (Software as a Service), or an application installed on a computer. In a team, each engineer advances development by dividing up roles for each function, output, etc. One or more teams may belong to an organization such as a company. In addition, engineers in a team are not limited to only company employees employed by a specific company (organization), but may be company employees of any company in a development project in which multiple companies jointly advance development. Furthermore, engineers in a team may include dispatched employees and sole proprietors (so-called freelancers).
[0057] The information relating to past work may include, for example, details of projects that the job seeker has worked on in the past, or information relating to the job seeker's work in those projects, the period of time in which he or she worked, or the performance of that work.
[0058] Information regarding technical skills may include, for example, information regarding programming languages or markup languages used by the job seeker.
[0059] Information regarding management experience may include, for example, information regarding job title, length of experience, or number of people managed.
[0060] After step S110, the job seeking terminal 10 executes reception of a user instruction (S111). Specifically, the job seeker terminal 10 receives an instruction from a user requesting a prediction of the user's income benchmark. The job seeker terminal 10 generates a prediction request in response to the instruction and transmits it to the server 30. The prediction request includes information that can identify the information acquired in step S110. The job seeker terminal 10 may extract text included in the job seeker information or perform anonymization processing (e.g., masking personal information or excluding it from transmission) as necessary.
[0061] As an example, the job seeker terminal 10 displays the screen of Fig. 9 on the display 21. The screen of Fig. 9 includes objects J21 to J24. Object J21 displays the details of the job applicant information acquired in step S110. The UI that accepts the job seeker information in step S110 may have an input field (form) for each information element that constitutes the job seeker information (the element marked with a # symbol in FIG. 9). For example, the UI may include a job type information field, a management experience field, and a project in charge field. Furthermore, the project field may include a team information field (of people who have worked together on the project), a role information field, and a performance information field. This makes it possible to prevent information elements to be included in the job seeker information from being overlooked, to increase the accuracy of extractable features, and to increase the validity of predicted income benchmarks, compared to the case where completely free-form input fields are used.
[0062] The object J22 accepts a user instruction to start editing the job seeker information. When the object J22 is selected, the job seeker terminal 10 may display on the display 21 a UI (User Interface) for editing the contents entered in the job seeker information form, or may display on the display 21 a UI for selecting a resume file or curriculum vitae file to be uploaded.
[0063] The object J23 receives an instruction to request a prediction of the user's income benchmark. When the object J23 is selected, the job seeker terminal 10 generates a prediction request and transmits it to the server 30.
[0064] The object J24 receives a user instruction to submit the job seeker information acquired in step S110. The job seeker terminal 10 transmits the job seeker information to the server 30 when the object J24 is selected.
[0065] After step S111, the server 30 executes information acquisition (S130). Specifically, the server 30 receives the prediction request transmitted in step S111. The server 30 acquires job seeker information based on the received prediction request.
[0066] After step S130, the server 30 executes extraction of features (S131). Specifically, the server 30 extracts features (hereinafter referred to as "job applicant features") from the job applicant information acquired in step S130.
[0067] As a first example of feature extraction (S131), the server 30 obtains job applicant features by providing job applicant information or text information corresponding to at least a part of it as an input to a trained model of a natural language system. As such a trained model, for example, a deep learning model (natural language processing model) such as BERT (Bidirectional Encoder Representations from Transformers) can be used.
[0068] As a second example of feature extraction (S131), the server 30 generates job seeker features by rule-based analysis of the job seeker information or text information corresponding to at least a part of the job seeker information. For example, the server 30 may increase features related to management experience when the job seeker information contains phrases such as "leading a team" or "mentoring junior colleagues." Alternatively, the server 30 may increase features related to the latest technical skills when the job seeker information contains keywords such as "k8s" or "Rust."
[0069] As a third example of the extraction of feature amounts (S131), the server 30 may combine the above first and second examples.
[0070] After step S131, the server 30 executes a revenue benchmark prediction (S132). Specifically, the server 30 predicts the job seeker's income benchmark by applying an income prediction model (hereinafter referred to as the "first model") to the job seeker features extracted in step S131. As an example, the server 30 predicts the job seeker's income benchmark in the form of x yen ± y yen, where x is the center of the predicted value and y is the prediction range (e.g., standard deviation).
[0071] The first model can be constructed by supervised learning. The learning data used in supervised learning is collected from a large amount of job seeker information created in the past by the same or different job seekers and the job search results using the job seeker information. The learning data includes job seeker features for learning and corresponding correct answer data. The correct answer data is the value of annual salary (or monthly salary, or may be unit price of remuneration) previously offered to a job seeker by an employer, and the job seeker features for learning can be extracted in the same manner as in step S131 from the job seeker information used by the job seeker in his or her job search.
[0072] After step S132, the server 30 executes output of the prediction result (S133). Specifically, the server 30 transmits the predicted result of the job seeker's income benchmark obtained in step S132 to the job seeker's terminal 10. This allows the user (job seeker) to be notified of the predicted result. The notification may be made on an app screen or a website screen, or may be made by using an email or other message (for example, a Social Networking Service (SNS) message, a Short Message Service (SMS) message, a chat tool message, etc.).
[0073] After step S133, the job seeking terminal 10 executes screen display (S112). Specifically, the job seeking terminal 10 receives the prediction result transmitted in step S133. The job seeking terminal 10 displays on the display 21 a screen for informing the user of the received prediction result.
[0074] (3-2) Recruiter prediction processing The recruiting side prediction process of this embodiment will be described. Fig. 10 is a flowchart of the recruiting side prediction process of this embodiment. Fig. 11 is a diagram showing an example of a screen displayed in the recruiting side prediction process of this embodiment.
[0075] The process in FIG. 10 may be started, for example, by the recruiting party terminal 50 accessing the talent matching platform and receiving an instruction from a user to start registering recruitment information.
[0076] As shown in FIG. 10, the recruiting side terminal 50 executes information acquisition (S250). Specifically, the recruiting party terminal 50 acquires recruitment information from the user. The recruitment information includes text information describing the type of person (an example of a "target talent") that the recruiting company is looking for. As a first example of information acquisition (S250), the recruiting side terminal 50 accepts an instruction from a user to upload a created recruitment information file. The recruitment information file is an example of recruitment information. As a second example of information acquisition (S250), the recruiting party terminal 50 acquires recruitment information entered on a form provided by the talent matching platform.
[0077] The job information may include at least one of the following: Information about the benefits that will be offered to the job seeker if hired Information about the profile requirements of the employer
[0078] Information regarding the benefits that are expected to be provided to the job seeker if hired may include, for example, information regarding the type of job, benefits (which may include salary), or working conditions that are expected to be provided to the job seeker if hired.
[0079] The information on the requirements of the profile that the recruiting company is looking for may include information on the must-have or preferred requirements of the profile. The requirements may include at least one of the following: Information about the teams the person has played for in their past careers Information about the person's past roles Information about the profile's technical skills Information about the profile's management experience
[0080] Information about the team may include, for example, information about the size of the team, or the role or tenure of a figure on the team.
[0081] The information about the work that the person profile has been in charge of in the past may include, for example, details of projects that the person profile has been in charge of in the past, or information about the work that the person profile was in charge of in the project, the period of time in charge, or the performance of the project.
[0082] Information regarding technical skills may include, for example, information regarding programming languages or markup languages used by the portrait.
[0083] Information regarding management experience may include, for example, information regarding job title, length of experience, or number of people managed.
[0084] After step S250, the recruiting side terminal 50 executes reception of a user instruction (S251). Specifically, the recruiting party terminal 50 receives an instruction from a user requesting a prediction of an income benchmark for the type of person desired by a recruiting company. The recruiting party terminal 50 generates a prediction request in response to the instruction and transmits it to the server 30. The prediction request includes information capable of identifying the recruitment information acquired in step S250. If necessary, the recruiting party terminal 50 may extract text included in the recruitment information or perform anonymization processing (for example, masking information capable of identifying the recruiting company corresponding to the recruitment information or excluding it from being transmitted).
[0085] As an example, the recruiting party terminal 50 displays the screen of Fig. 11 on the display 61. The screen of Fig. 11 includes objects J31 to J34. Object J31 displays the content of the job information acquired in step S250.
[0086] The object J32 accepts a user instruction to start editing the job information. When the object J32 is selected, the recruiting party terminal 50 may display on the display 61 a UI for editing the contents entered in the job information form, or may display on the display 61 a UI for selecting a job information file to be uploaded.
[0087] Object J33 accepts an instruction to request a prediction of the income benchmark of the type of person desired by the recruiting company. When object J33 is selected, the recruiting party terminal 50 generates a prediction request and transmits it to the server 30.
[0088] The object J34 receives a user instruction to post the job information acquired in step S250 on the talent matching platform. When the object J34 is selected, the recruiting party terminal 50 transmits the job information to the server 30.
[0089] After step S251, the server 30 executes information acquisition (S230). Specifically, the server 30 receives the prediction request transmitted in step S251. The server 30 acquires job information based on the received prediction request.
[0090] After step S230, the server 30 executes extraction of features (S231). Specifically, the server 30 extracts features (hereinafter, referred to as "job features") from the job information acquired in step S230.
[0091] As a first example of feature extraction (S231), the server 30 obtains job feature amounts by providing the job information or text information corresponding to at least a part of it as an input to a natural language trained model. As such a trained model, for example, a deep learning model such as BERT can be used.
[0092] As a second example of the extraction of features (S231), the server 30 generates job feature quantities by analyzing the job information or text information corresponding to at least a part of the job information in a rule-based manner.
[0093] As a third example of the extraction of feature amounts (S231), the server 30 may combine the above first and second examples.
[0094] After step S231, the server 30 executes a revenue benchmark prediction (S232). Specifically, the server 30 predicts the income benchmark of the type of person desired by the hiring company by applying an income prediction model (hereinafter referred to as the "second model") to the job offer feature quantity extracted in step S231. As an example, the server 30 predicts the income benchmark of the type of person desired by the hiring company in the format of x yen ± y yen.
[0095] The second model can be constructed by supervised learning. The learning data used in supervised learning is collected from a large number of job postings issued in the past by the same or different recruiting companies, and the results of recruiting activities using the job postings. The learning data includes job posting features for learning and corresponding correct answer data. The correct answer data is the value of the annual salary (or monthly salary, or may be the unit price of remuneration) that the recruiting company has offered in the past to the personnel it is looking to hire, and the job posting features for learning can be extracted in the same manner as in step S231 from the job postings used by the recruiting company in its recruiting activities.
[0096] After step S232, the server 30 executes output of the prediction result (S233). Specifically, the server 30 transmits the predicted income benchmark result of the type of person desired by the recruiting company, obtained in step S232, to the recruiting side terminal 50. This allows the user (the recruiting person at the recruiting company corresponding to the job information) to be notified of the predicted result. The notification may be made on the app screen or website screen, or may be made by using email or other messages (for example, SNS messages, SMS messages, etc.).
[0097] Optionally, the server 30 may identify the income to be offered to the job seeker to be hired in the job information acquired in step S230, and compare the income with the prediction result in step S232. Then, when the income to be offered to the job seeker to be hired deviates from the prediction result, the server 30 may generate at least one of the following information and output it together with the prediction result: Comparison results (e.g., information showing differences) Recommendations for changes to the benefits (e.g., improved benefits or lower salary offers) that would be offered to the job seeker if hired Information recommending changes to the job seeker's requirements (e.g., relaxing or tightening the requirements)
[0098] After step S233, the recruiting party terminal 50 executes screen display (S252). Specifically, the recruiting party terminal 50 receives the prediction result transmitted in step S233. The recruiting party terminal 50 displays on the display 61 a screen that notifies the user of the received prediction result.
[0099] (4) Summary As described above, the server 30 acquires text information described on a target talent who is either a job seeker or a person profile desired by a recruiting company, and extracts job seeker features or job offer features from the text information. The server 30 predicts the income benchmark of the target talent by applying an income prediction model (first model or second model) to the job seeker features or job offer features, and outputs the prediction result. This allows the job seeker to know the appropriate income if he or she is hired, and can brush up the content of the job seeker information created, or use the income benchmark as a criterion for selecting a place to apply. The recruiting company can know the market rate of income for the person profile desired by the recruiting company, and can review the content of the job offer information created, or use the income benchmark as a criterion for deciding when planning a recruitment plan.
[0100] The server 30 may acquire at least one of the resume file or curriculum vitae file of the job seeker, or the job seeker information input on the talent matching platform, thereby extracting the job seeker feature amount and predicting the job seeker's income benchmark.
[0101] The income benchmark of the target talent may be the average income of a person who matches the profile of the person the recruiting company is looking for, or the income that the recruiting company should offer to the job seeker when hiring, and the server 30 may acquire recruitment information related to the profile of the person the recruiting company is looking for that is input on the talent matching platform. This makes it possible to extract recruitment features and predict the income benchmark of the profile of the person the recruiting company is looking for.
[0102] The text information may include information on benefits that are to be provided to the job seeker if the job seeker is hired from among the job information. This makes it possible to predict a reasonable income benchmark based on the job feature that reflects the information on benefits that are to be provided to the job seeker if the job seeker is hired.
[0103] The text information may include information on at least one of the essential requirements or preferred requirements of the profile of the person the recruiting company is looking for in the job information. This makes it possible to predict a reasonable income benchmark based on the job feature that reflects the information on the essential requirements or preferred requirements of the profile of the person the recruiting company is looking for.
[0104] The server 30 may identify the income to be offered to the job seeker to be hired in the job information, and if the income deviates from the income benchmark for the target human resources, recommend changing at least one of the treatment to be offered if the job seeker is hired or the requirements for the personality profile desired by the hiring company. This encourages the optimization of the treatment to be offered if the job seeker is hired by the hiring company or the requirements for the personality profile desired by the hiring company, thereby improving the efficiency of hiring activities.
[0105] The text information may include information about a team to which the target talent belonged in the past career. This makes it possible to predict a reasonable income benchmark based on the job seeker feature or job offer feature reflecting the information about the team to which the target talent belonged in the past career.
[0106] The text information may include information about the work that the target talent has previously performed. This makes it possible to predict a reasonable income benchmark based on the job seeker feature or job offer feature that reflects the information about the work that the target talent has previously performed.
[0107] The text information may include information about the technical skills of the target talent, which allows a reasonable income benchmark to be predicted based on the job seeker features or job offer features that reflect the information about the technical skills of the target talent.
[0108] The text information may include information about the management experience of the target talent, which allows a reasonable income benchmark to be predicted based on the job seeker feature or job offer feature reflecting the information about the management experience of the target talent.
[0109] (5) Variations A modification of this embodiment will now be described.
[0110] (5-1) Variation 1 A description will be given of Modification 1. Modification 1 is an example in which an income benchmark of a job seeker is predicted further based on information about a repository in which the job seeker has been involved in the issue management service.
[0111] (5-1-1) Information Processing System Configuration The configuration of the information processing system will be described below with reference to Fig. 12, which is a block diagram showing the configuration of the information processing system according to the first modification.
[0112] As shown in FIG. 12, the server 30 is connected to an external system 70 via a network NW. The external system 70 provides information on development activities by engineers as job seekers in response to a request from the server 30. The external system 70 is typically a software development platform such as GitHub (registered trademark). GitHub manages source code, which is the product of development by engineers, and manages reviews of the source code.
[0113] The external system 70 is not limited to GitHub, and may be other software development platforms such as GitLab (registered trademark) or Bitbucket (registered trademark). Alternatively, the external system 70 may be an issue management tool (e.g., Jira (registered trademark)) or a task management tool (e.g., Trello (registered trademark) or backlog (registered trademark)) in software development. These software development platforms, issue management tools, or task management tools may be collectively referred to as an issue management service. In the following explanation, it is assumed that GitHub is used as the external system 70.
[0114] GitHub is a source code hosting service. It has repositories (a means of management) for version control of source code, which is the result of development. GitHub manages a list of source code at a given point in time. GitHub has various functions such as issue (creation), push, commit, pull request, and merging.
[0115] Issue is a function for managing issues in projects and source code. Push is a function for uploading source code that has been created or modified in an engineer's local environment (local repository) to a remote environment (remote repository). Commit is a function for registering changes to source code. Pull request is a function for notifying that a push has been made and requesting a review. Merge is a function for finalizing the review results and integrating the history. Here, source code is a concept that includes code (character strings) written in a programming language such as Python or a markup language such as HTML or CSS, as well as scripts (character strings) written in a scripting language, which is a type of programming language such as JavaScript (registered trademark).
[0116] A programming language is a language used in software development, and specific examples include JavaScript (registered trademark), Java (registered trademark), Scala, PHP, Ruby, Python, Go, C#, etc. A software framework is a software platform used in software development, and specific examples include jQuery, React, Vue.js, Angular, Nuxt.js, Next.js, ReactNative, Spring Framework, Play Framework, Laravel, CakePHP, RubyonRails, Django, Flask, TensorFlow, gin, Unity, Express, etc.
[0117] Various engineers carry out various development activities using the external system 70. The external system 70 stores information related to logs of such development activities (hereinafter referred to as "development activity information"). The server 30 acquires the development activity information from the external system 70. The server 30 may collect the development activity information periodically, or may collect such development activity information in response to some trigger (for example, reception of a prediction request from the job seeker terminal 10).
[0118] (5-1-2) Database A description will be given of the database of the modification 1. The following database is stored in the storage device 31.
[0119] (5-1-2-1) Repository Database A description will now be given of the repository database of Modification 1. Fig. 13 is a diagram showing the data structure of the repository database of Modification 1.
[0120] The repository database stores repository information, which is information relating to a repository created in the external system 70.
[0121] 13, the repository database includes a "Repository ID" field, a "Team ID" field, and an "Address" field. Each field is associated with the other fields.
[0122] The “repository ID” field stores a repository ID. The repository ID is information for identifying a repository. The server 30 can obtain the repository ID from the external system 70.
[0123] The "Team ID" field stores a team ID. The team ID is information that identifies the team that created the repository identified by the corresponding repository ID. The server 30 can obtain the team ID from the external system 70. The team ID is useful when collecting development activity information by engineers belonging to the same team in a lump sum, but in a configuration where collection of such information is not necessary, the team ID does not need to be stored in the repository database.
[0124] The team ID may be associated with an organization ID in a database (not shown). The organization ID associated with the team ID identifies the organization to which the team corresponding to the team ID belongs. The team ID may also be associated with an engineer ID in a database (not shown). The engineer ID associated with the team ID identifies a member belonging to the team corresponding to the team ID.
[0125] The "Address" field stores address information, which is information for accessing a repository identified by a corresponding repository ID (for example, a URL (Uniform Resource Locator)).
[0126] (5-1-2-2) Development Activity Database An explanation will be given of the development activity database of the modified example 1. Fig. 14 is a diagram showing the data structure of the development activity database of the modified example 1.
[0127] The development activity database stores development activity information, which is information about activities performed by engineers regarding source code stored in a repository created in the external system 70.
[0128] For example, when a user (i.e., an engineer) pushes source code from a local repository, the external system 70 records, as log information, information that can identify the user who made the push and the date and time when the push was made. Similarly, the external system records log information for at least one of the following activities: The activity of recording added or modified files in the local repository of the issue management service (equivalent to a commit in GitHub, for example; hereinafter, similar activities will be referred to as "commits") · Activities to create issues regarding source code ·Activities to close issues The activity of requesting a review of a file that has been added or changed in a local repository (e.g., equivalent to a pull request on GitHub; hereinafter, similar activities are referred to as "pull requests") - Reviewing files in response to the above requests The activity of approving the integration of the requested files into the project body (equivalent to merging in GitHub, hereinafter, similar activities will be referred to as "merging"). · Comment creation activity · Creating responses to comments
[0129] The server 30 updates the development activity database based on the development activity information acquired from the external system 70. The server 30 may acquire the development activity information periodically, or may acquire the development activity information in response to some trigger (for example, reception of a prediction request from the job seeker terminal 10).
[0130] As shown in FIG. 14, the development activity database includes an "activity ID" field, a "repository ID" field, an "action ID" field, an "engineer ID" field, a "date and time" field, and a "source code" field.
[0131] The “activity ID” field stores an activity ID. The activity ID is information for identifying an activity performed by an engineer regarding source code stored in a repository created in the external system 70.
[0132] The "Repository ID" field stores a repository ID. The repository ID is information for identifying a repository in which a source code in which an activity identified by a corresponding activity ID has been performed is stored.
[0133] The "action" field stores action information. The action information is information about the type of activity specified by the corresponding activity ID.
[0134] The "engineer ID" field stores an engineer ID. The engineer ID is information for identifying the engineer (i.e., the user of the external system 70) who performed the activity identified by the corresponding activity ID.
[0135] The "Date and Time" field stores date and time information. The date and time information is information about the date and time when the activity identified by the corresponding activity ID was performed.
[0136] The "source code" field stores source code information. The source code information is information about the source code in which the activity identified by the corresponding activity ID was performed (for example, file name information, information about the changed file).
[0137] (5-1-3) Information processing The job seeker prediction process of the first modification will be described.
[0138] As shown in FIG. 8, the job seeker terminal 10 executes information acquisition (S110). Specifically, the job seeker terminal 10 acquires information capable of identifying the job seeker's engineer ID in addition to the job seeker information described in this embodiment. After step S110, the job seeking terminal 10 executes reception of a user instruction (S111).
[0139] After step S111, the server 30 executes information acquisition (S130). Specifically, the server 30 receives the prediction request transmitted in step S111. The server 30 acquires job seeker information and the job seeker's engineer ID based on the received prediction request. The server 30 refers to, for example, the development activity database (FIG. 14) based on the job seeker's engineer ID, and extracts information about repositories in which the job seeker has been involved in the issue management service.
[0140] After step S130, the server 30 executes extraction of features (S131). Specifically, in addition to the job seeker characteristics described in this embodiment, the server 30 extracts characteristics (hereinafter referred to as "development activity characteristics") from the information related to the repository acquired in step S130. As an example, the server 30 may extract characteristics related to at least one of the following: Number of repositories that job seekers have engaged with Number of stars (favorites) for repositories that job seekers have been involved in Number of commits made Number of issues created regarding source code Number of created issues that have been closed Number of pull requests made Number of files reviewed in response to pull requests ·Number of reviews of pull requests by other engineers Number of merged pull requests Number of comments created Number of replies to comments created · Number of coding sessions (active days) Average time to first review a pull request by another engineer [h] Average time from creation of a pull request to being merged or closed [h] Average time from first commit to pull request creation [h] Average time from creation to review of pull request [h] ·Average time from first review to close [h] ·Average time from first review to final approval [h] Average time from last approval to merge [h] Average time from creation to merging a pull request into the main branch [h] Average time from the first commit associated with a pull request that was merged into the main branch to the merge [h] Percentage of pull requests merged without review [%] Change failure rate -Average number of comments per pull request -Average number of lines changed per pull request Number of files changed per pull request
[0141] After step S131, the server 30 executes a revenue benchmark prediction (S132). Specifically, the server 30 predicts the income benchmark of the job seeker by applying an income prediction model (hereinafter referred to as the "third model") to the job seeker features and development activity features extracted in step S131. As an example, the server 30 predicts the income benchmark of the job seeker in the format of x yen ± y yen.
[0142] The third model can be constructed by supervised learning. The learning data used in supervised learning is collected from a large number of job seeker information created in the past by the same or different job seekers, information on repositories in which the job seeker was involved in the issue management service, and the job search results based on the job seeker information. The learning data includes job seeker features and development activity features for learning, and corresponding correct answer data. The correct answer data is the value of the annual salary (or monthly salary, or remuneration unit price) previously presented to the job seeker by the employer, and the job seeker features and development activity features for learning can be extracted in the same manner as in step S131 from the job seeker information used by the job seeker in the job search and information on repositories in which the job seeker was involved in the issue management service (however, information that can be obtained at the time of the job search).
[0143] After step S132, the server 30 executes output of the prediction result (S133). After step S133, the job seeking terminal 10 executes screen display (S112). (5-1-4) As described above, the server 30 of the first modification acquires information about repositories in which the job seeker has been involved in the issue management service, and predicts the job seeker's income benchmark by applying the income prediction model (third model) to the development activity features and job seeker features based on the information about the repositories. This makes it possible to predict a reasonable benchmark that further takes into account the information about the job seeker's development activities.
[0144] (5-2) Variation 2 We will now explain Modification 2. Modification 2 is an example in which an income benchmark for the type of person the company seeking a job seeker is expected to hire is predicted based on information about a group of users who match the job information in the human resources matching platform.
[0145] The recruitment side prediction process of the modified example 2 will be described. As shown in FIG. 10, the recruiting side terminal 50 executes the processes from obtaining information (S250) to receiving user instructions (S251).
[0146] After step S251, the server 30 executes information acquisition (S230). Specifically, the server 30 receives the prediction request transmitted in step S251. The server 30 acquires job information based on the received prediction request.
[0147] Furthermore, the server 30 acquires information on a group of users (job seekers or potential job seekers) who match the acquired job information in the human resources platform (hereinafter referred to as "matching group information").
[0148] The relevance population information may include, for example, at least one of the following: The number of users who match the job information (hereinafter referred to as "match number") Statistics on job-seeking (job change or (re)employment) intentions of users who match job information The number of users who match job information and have a job-seeking intent above a threshold -Statistics of salaries (current salary or desired salary) of users who match job information
[0149] As a first example, the server 30 may compare the job seeker information (e.g., desired treatment or profile) of all users registered on the human resources platform with the target job information (e.g., planned treatment for the job seeker to be hired, or the profile of the person (particularly the essential requirements) desired by the hiring company) to identify users who actually match the job information. The number of matches can be derived by counting the number of identified users. In addition, based on the job seeker information of the identified users, it is possible to derive statistics on job-seeking intentions, the number of users whose degree of job-seeking intention is above a threshold, salary statistics, etc. As a second example, the server 30 may compare the job seeker information of a randomly selected predetermined number of users with the target job information to calculate a match rate, and multiply the number of employer users of the human resources matching platform by the match rate to predict the number of users who match the job information. Also, based on the job seeker information of users among the predetermined number of users who match the job information, it is possible to estimate statistics on job-seeking intentions, the number of users whose degree of job-seeking intention is equal to or greater than a threshold, statistics on salaries, etc.
[0150] After step S230, the server 30 executes extraction of features (S231). Specifically, in addition to the job offer feature described in this embodiment, the server 30 extracts a feature (hereinafter, referred to as a "compatible group feature") from the compatible group information acquired in step S230. As an example, the server 30 may calculate the compatible group feature by substituting the compatible group information into a predetermined conversion formula. Alternatively, the server 30 may treat the compatible group information as the compatible group feature as it is.
[0151] After step S231, the server 30 executes a revenue benchmark prediction (S232). Specifically, the server 30 predicts the income benchmark of the type of person desired by the recruiting company by applying an income prediction model (hereinafter referred to as the "fourth model") to the job offer features and the matching group features extracted in step S231. As an example, the server 30 predicts the income benchmark of the type of person desired by the recruiting company in the form of x yen ± y yen.
[0152] The fourth model can be constructed by supervised learning. The learning data used in supervised learning is collected from a large number of job offers issued by the same or different recruiting companies in the past, matching group information obtained based on the job offers, and the results of recruiting activities based on the job offers. The learning data includes job offer features and matching group features for learning, and corresponding correct answer data. The correct answer data is the value of the annual salary (or monthly salary, or may be the unit price of remuneration) that the recruiting company has offered to the human resources to be recruited in the past, and the job offer features and matching group features for learning can be extracted in the same manner as in step S231 from the job offers used by the recruiting company in its recruiting activities and the matching group information obtained based on the job offers (however, the matching group information at the time of the recruiting activities).
[0153] After step S232, the server 30 executes output of the prediction result (S233). After step S233, the recruiting party terminal 50 executes screen display (S252).
[0154] As described above, the server 30 of the second modification obtains information on a group of users who match the job information in the human resources matching platform, and predicts the income benchmark of the person profile desired by the recruiting company by applying the income prediction model (fourth model) to the matching group feature amount and the job feature amount based on the information. This makes it possible to predict a reasonable benchmark that further considers the number of candidates with the desired profile.
[0155] (6) Other modifications The storage device 11 may be connected to the job seeking side terminal 10 via the network NW. The display 21 may be integrated with the job seeking side terminal 10. The storage device 31 may be connected to the server 30 via the network NW. The storage device 51 may be connected to the recruiting side terminal 50 via the network NW. The display 61 may be integrated with the recruiting side terminal 50.
[0156] Each step of the above information processing can be executed by any of the job seeker terminal 10, the server 30, and the employer terminal 50. In addition, in the above explanation, an example was given in which each step in the information processing is executed in a specific order, but the execution order of each step is not limited to the example explained above as long as there is no dependency between the steps.
[0157] (7) Additional Notes The matters described in the embodiment and the modified examples are supplemented below.
[0158] (Appendix 1) A computer (30), A means for acquiring text information describing a target talent, which is either a job seeker or a personality profile desired by a recruiting company (S130, S230); A means for extracting a first feature from text information (S131, S231); A means for predicting an income benchmark of the target talent by applying an income prediction model to the first feature (S132, S232); A means for outputting a predicted result of the income benchmark of the target human resources (S133, S233); A program that functions as a
[0159] (Appendix 2) The means for acquiring text information acquires at least one of the resume file or job history file of the target talent, or the job seeker information of the target talent entered on the talent matching platform; 2. The program described in Appendix 1.
[0160] (Appendix 3) The computer is caused to function as a means for acquiring information on repositories in which the target human resource has been involved in the issue management service (S130); The means for predicting the income benchmark of the target talent predicts the income benchmark of the target talent by applying an income prediction model to the second feature amount and the first feature amount based on the information about the repository; 2. The program described in Appendix 2.
[0161] (Appendix 4) The income benchmark for the target personnel is the average income of a person who matches the profile of the person the recruiting company is looking for, or the income that the recruiting company should offer to the job seeker if they were to hire. The means of acquiring text information is to acquire job information related to the type of person required by the company that is recruiting, which is entered on the human resources matching platform. 2. The program described in Appendix 1.
[0162] (Appendix 5) The text information includes information on the employment information regarding benefits that will be offered to the job seeker if he or she is hired. 6. The program described in Appendix 4.
[0163] (Appendix 6) The text information includes information on at least one of the required or preferred characteristics of the person the company is looking for in the job information, 6. The program described in Appendix 4.
[0164] (Appendix 7) Computer, A means for identifying in the job posting the salary offered to a job seeker; a measure to recommend changes to at least one of the benefits to be offered to the job seeker if hired or the profile requirements of the employer, if the salary offered to the job seeker deviates from the salary benchmark for the target talent; 5. The program according to claim 4,
[0165] (Appendix 8) The computer is caused to function as a means (S230) for acquiring information on a group of users who match the job information in the human resources matching platform; The means for predicting the income benchmark of the target talent includes predicting the income benchmark of the target talent by applying an income prediction model to the third feature based on information about a group of users matching the job information and the first feature; 6. The program described in Appendix 4.
[0166] (Appendix 9) The text information includes information about the teams the target person has belonged to in their past careers. 2. A program according to claim 2 or 3.
[0167] (Appendix 10) The text information includes information about the work the target personnel has previously performed, 2. A program according to claim 2 or 3.
[0168] (Appendix 11) The text information includes information about the technical skills of the target personnel, 2. A program according to claim 2 or 3.
[0169] (Appendix 12) The text information includes information about the management experience of the target personnel, 2. A program according to claim 2 or 3.
[0170] (Appendix 13) A computer (30) A step of acquiring text information describing a target talent, which is either a job seeker or a person profile desired by a recruiting company (S130, S230); A step of extracting a first feature from text information (S131, S231); A step of predicting an income benchmark of the target talent by applying an income prediction model to the first feature (S132, S232); A step of outputting the predicted results of the income benchmark of the target human resources (S133, S233); How to do it.
[0171] (Appendix 14) A means for acquiring text information describing a target talent, which is either a job seeker or a personality profile desired by a recruiting company (S130, S230); A means for extracting a first feature from text information (S131, S231); A means for predicting an income benchmark of a target talent by applying an income prediction model to the first feature (S132, S232); A means for outputting the predicted results of the income benchmark of the target human resources (S133, S233); An information processing device (30) comprising:
[0172] (Appendix 15) A system (1) including a first information processing device (30) and a second information processing device (10, 50), The first information processing device is A means for acquiring text information from a second information processing device, the text information being described regarding a target talent that is either a job seeker or a personality profile desired by a recruiting company; A means for extracting a first feature from text information (S131, S231); A means for predicting an income benchmark of a target talent by applying an income prediction model to the first feature (S132, S232); A means for outputting the predicted results of the income benchmark of the target human resource to the second information processing device (S13#, S233); Equipped with system.
[0173] Although the embodiment of the present invention has been described in detail above, the scope of the present invention is not limited to the above embodiment. Furthermore, the above embodiment can be improved or modified in various ways without departing from the spirit of the present invention. Furthermore, the above embodiment and the modified examples can be combined. [Explanation of symbols]
[0174] 1: Information processing system 10: Job seeker's terminal 11:Storage device 12: Processor 13: Input / Output Interface 14: Communication interface 21: Display 30: Server 31: Storage device 32 : Processor 33: Input / Output Interface 34: Communication interface 50: Recruiter's terminal 51:Storage device 52: Processor 53: Input / Output Interface 54: Communication interface 61: Display 70: External system
Claims
1. Computer, A means for acquiring text information describing a target human resource that includes either a job seeker or a person profile desired by a recruiting company but does not include the other; means for extracting a first feature from the text information; A means for predicting an income benchmark of the target talent by applying an income prediction model to the first feature amount; A means for outputting a predicted result of the income benchmark of the target talent; Functioning as a The income prediction model is a trained model. program.
2. The means for acquiring text information acquires at least one of a resume file or a curriculum vitae file of the target talent, or job seeker information of the target talent input on a talent matching platform; The program according to claim 1.
3. The computer is caused to function as a means for acquiring information regarding repositories in which the target personnel has been involved in an issue management service; The means for predicting the income benchmark of the target talent predicts the income benchmark of the target talent by applying the income prediction model to the second feature amount based on the information about the repository and the first feature amount. The program according to claim 2.
4. The income benchmark for the target personnel is the average income of a person who matches the profile of the person the recruiting company is looking for, or the income that the recruiting company should present to a job seeker who is to be hired when recruiting, The means for acquiring text information acquires job information related to the profile of the person the recruiting company is looking for, which is inputted on a human resources matching platform. The program according to claim 1.
5. The text information includes information on benefits to be provided to the job seeker if he or she is hired from among the job information. The program according to claim 4.
6. The text information includes information regarding at least one of the essential requirements or desirable requirements of the person sought by the recruiting company in the job information, The program according to claim 4.
7. The computer, means for identifying a salary offered to a job seeker for employment in said job posting; A means for recommending a change to at least one of the treatment to be provided to the job seeker if the job seeker is hired or the requirements for the personality profile sought by the recruiting company when the income to be offered to the job seeker deviates from the income benchmark for the target human resources; The program according to claim 4,
8. The computer is caused to function as a means for acquiring information on a group of users who match the job information in the human resources matching platform; The means for predicting the income benchmark of the target talent predicts the income benchmark of the target talent by applying the income prediction model to the third feature amount based on information about a group of users matching the job information and the first feature amount. The program according to claim 4.
9. The text information includes information about the teams to which the target personnel belonged in their past careers. The program according to claim 2 or 3.
10. The text information includes information regarding the work that the target human resource has previously been in charge of, The program according to claim 2 or 3.
11. The text information includes information regarding the technical skills of the target personnel; The program according to claim 2 or 3.
12. The text information includes information regarding the management experience of the target human resource. The program according to claim 2 or 3.
13. The income prediction model is constructed by supervised learning using training data, the learning data includes a first feature amount for learning and correct answer data corresponding to the first feature amount for learning, the first feature value for learning is extracted from job seeker information used in a past job search by a job seeker who is the same as or different from the job seeker, and the correct answer data corresponding to the first feature value for learning is an income value presented by a recruiting party in the past job search; The program according to claim 1.
14. The computer A step of obtaining text information describing a target talent that includes either a job seeker or a personality profile desired by a recruiting company but does not include the other; Extracting a first feature from the text information; predicting an income benchmark for the target talent by applying an income prediction model to the first feature; outputting a predicted result of the income benchmark of the target talent; Run The income prediction model is a trained model. method.
15. A means for acquiring text information describing a target human resource that includes either a job seeker or a person profile desired by a recruiting company but does not include the other; means for extracting a first feature from the text information; A means for predicting an income benchmark of the target talent by applying an income prediction model to the first feature amount; A means for outputting a predicted result of the income benchmark of the target talent; Equipped with The income prediction model is a trained model. Information processing device.
16. A system including a first information processing device and a second information processing device, The first information processing device, A means for acquiring text information from the second information processing device, the text information being described regarding a target personnel that includes either a job seeker or a person profile desired by a recruiting company but does not include the other; means for extracting a first feature from the text information; A means for predicting an income benchmark of the target talent by applying an income prediction model to the first feature amount; A means for outputting a predicted result of the income benchmark of the target human resource to the second information processing device; Equipped with The income prediction model is a trained model. system.
Citation Information
Patent Citations
Human resources distribution support method, and human resources distribution support device
JP2003108805A
Reward amount trial calculation system
JP2019207478A
Server device, control method of server device, and control program of server device
JP2022043587A
JPP7228940B
Information processing device, information processing method, and program
WO2020008663A1
