Information processing device, method, program and system
The system uses a natural language model to generate tailored resume information from job applicant and job offer data, addressing the need for multiple resume creation and improving recruitment efficiency.
Patent Information
- Application Number
- JP2023077019
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-09
- Publication Date
- 2024-11-21
- Estimated Expiration
- 2043-05-09
AI Technical Summary
Existing job seeking processes require job seekers to create multiple resumes tailored for different companies, and hiring managers face a burden in sifting through mixed profile information to find relevant candidates.
A system utilizing a natural language model to generate resume information based on job applicant and job offer data, reducing the need for job seekers to create multiple resumes and enabling hiring managers to efficiently assess candidates.
Reduces the burden on job seekers by automating resume creation and allows hiring managers to make informed decisions with tailored resume information, enhancing the recruitment process.
Smart Images

Figure 2024161943000001_ABST
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-hunting, job seekers need to create a resume (also called a curriculum vitae) that describes how they can contribute to the company they are applying to by utilizing their experience and skills. Although job seekers may be able to reuse resumes they have created in the past, they are required to create a new resume for each company they are applying to, which can feel cumbersome. On the other hand, recruiters at companies who are hiring may try to search for job seekers who are potential candidates (for example, to whom they can send scouting letters) based on the profile information that job seekers have registered on a talent matching platform. In this case, the burden of checking the profile information is not small, as the profile information contains a mixture of elements that the company considers important and elements that it does not.
[0003] Patent Document 1 discloses a technical idea of generating a summary according to summary items registered by a company based on resume data registered by a user. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2001-142939 A Summary of the Invention [Problem to be solved by the invention]
[0005] According to the technical idea of Patent Document 1, the quality of the generated summary depends heavily on the summary items registered by the company. Therefore, if the person in charge at the company sets inappropriate summary items, there is a risk that information highly relevant to the company's recruitment will be omitted from the summary, or less relevant information will remain in the summary.
[0006] An object of the present disclosure is to provide a technology that enables a job seeker to obtain information that is useful for recruitment while at least reducing the burden on the job seeker. [Means for solving the problem]
[0007] A program according to one embodiment of the present disclosure causes a computer to function as a means for acquiring job seeker information relating to a job seeker, a means for acquiring resume information for the job seeker generated by a natural language model by inputting first model input information based on the job seeker information into a natural language model, and a means for outputting the resume information. [Brief description of the drawings]
[0008] [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] FIG. 2 is a block diagram showing a configuration of a client device according to the present embodiment. [Diagram 3] FIG. 2 is a block diagram showing a configuration of a server according to the present embodiment. [Figure 4] FIG. 1 is an explanatory diagram of one aspect of the present embodiment. [Diagram 5] 4 is a flowchart of information processing according to the present embodiment. [Figure 6] FIG. 13 is an explanatory diagram of one aspect of Modification 1. [Figure 7] 13 is a flowchart of information processing in the first modified example. [Figure 8] 13 is a detailed flowchart of obtaining job seeker information in the first modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] 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.
[0010] (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.
[0011] As shown in FIG. 1, the information processing system 1 includes a client device 10 and a server 30. The client device 10 and the server 30 are connected via a network (eg, the Internet or an intranet) NW.
[0012] The server 30 is an example of an information processing device that provides the client device 10 with a response in response to a request sent from the client device 10. The server 30 is, for example, a server computer. The server 30 can manage a talent matching service (which can also be called a "talent matching platform") in which job seekers and recruiting companies (which may include scouts) participate. The talent matching service corresponds to a place that connects job seekers and 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 matching service or prepares to register (e.g., 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 hire, and at least a person who uses the talent matching service to carry out recruitment activities (e.g., sends scout documents, registers job information, or prepares to register) directly or indirectly (through a scout).
[0013] The client device 10 is an example of an information processing device that transmits a request to the server 30. The client device 10 is, for example, a smartphone, a tablet terminal, or a personal computer. The user of the client device 10 is a job seeker, a person belonging to a company offering a job (for example, a recruiter at the company offering a job), or a person who introduces job seekers who are deemed suitable for the company offering a job (a so-called job-seeking agent). Here, the recruiter at the company offering a job is not limited to a person in the human resources department, but may be, for example, a person in a department that is looking to hire people through job offers. A job seeker is a person who is changing jobs or (re)hunting jobs, or a person who is interested in these activities.
[0014] Here, an example of the behavior of the server 30 with regard to the management of the human resources matching service will be described. Specifically, the server 30 makes the profile information provided by the job seeker viewable (for example, published anonymously and searchable) by, for example, the recruiting staff of the hiring company. The recruiting staff can create and send scouting documents to job seekers who are deemed suitable for their company. Alternatively, the server 30 publishes the job information provided by the hiring company in, for example, a state that can be viewed by job seekers. The job seeker can create a resume and apply for a job at a hiring company that he or she deems suitable for him or her. In this way, hiring companies and job seekers can be linked together.
[0015] (1-1) Client device configuration The configuration of the client device will now be described with reference to Fig. 2, which is a block diagram showing the configuration of the client device of this embodiment.
[0016] 2, the client device 10 includes a storage device 11, a processor 12, an input / output interface 13, and a communication interface 14. The client device 10 is connected to a display 21.
[0017] 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).
[0018] The programs include, for example, the following programs: ·OS (Operating System) programs · Programs for applications that process information (e.g. web browsers or dedicated applications)
[0019] 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)
[0020] The processor 12 is a computer that realizes the functions of the client device 10 by running 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)
[0021] The input / output interface 13 is configured to obtain information (eg, a user's instruction) from an input device connected to the client device 10, and to output information (eg, an image) to an output device connected to the client device 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.
[0022] The communication interface 14 is configured to control communications between the client device 10 and an external device (eg, a server 30).
[0023] 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.
[0024] (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.
[0025] 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 .
[0026] 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).
[0027] The programs include, for example, the following programs: -OS programs Application programs that perform information processing
[0028] The data includes, for example, the following data: Databases referenced in information processing Results of information processing
[0029] 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
[0030] 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.
[0031] The communication interface 34 is configured to control communications between the server 30 and external devices (eg, the client device 10).
[0032] (2) One aspect of the embodiment An embodiment of the present invention will now be described with reference to Fig. 4, which is an explanatory diagram of an embodiment of the present invention.
[0033] As shown in FIG. 4, a user US1, who corresponds to a recruiter at a company offering a job, operates a client device 10 to input or specify a specific job information item (an example of a "target job information item") among the job information items at the company to which the user belongs. The target job information item is job information that is used to create resume information for a job seeker. The client device 10 transmits the target job information item or information that can identify the target job information item (e.g., a URL, identification information, etc.) to the server 30.
[0034] Similarly, user US1 operates client device 10 to input or specify job seeker information about a specific job seeker (an example of "target job seeker information"). The target job seeker information is information about the job seeker that is used to create resume information for the job seeker. Client device 10 transmits the target job seeker information or information that can identify the target job seeker information (e.g., a Uniform Resource Locator (URL), identification information, etc.) to server 30.
[0035] The server 30 acquires the target job vacancy information and the target job seeker information based on the information received from the client device 10. The server 30 acquires the resume information of the specific job seeker generated by the natural language model ML5 by inputting model input information based on the target job vacancy information and the target job seeker information into the natural language model ML5.
[0036] Here, the natural language model ML5 is a trained model that performs natural language processing according to, for example, an instruction sentence and generates a response sentence. The instruction sentence may include at least one of target job information or target job seeker information. The natural language model ML5 may be an interactive (also called chat or conversation) model that alternates between receiving an instruction sentence and generating a response sentence. The natural language model ML5 may be a large-scale language model trained with a large amount of text data, or a model that is obtained by transfer learning the large-scale language model. The natural language model ML5 may also be constructed in a system external to the information processing system 1.
[0037] The server 30 transmits the acquired resume information to the client device 10. The client device 10 presents the resume information received from the server 30 to the user US1.
[0038] As a result, the server 30 can provide the user US1 with resume information of a specific job seeker (a job seeker corresponding to the target job information) without making the job seeker create a resume for that job seeker. In other words, the user US1, who is a recruiter at a company offering a job, can obtain the resume information of the job seeker while at least reducing the burden on the job seeker of creating a resume. In addition, since the user US1 can view resume information created in consideration of the target job information, the user US1 can efficiently confirm information that is a basis for deciding whether or not to make the specific job seeker a candidate for employment, compared to the case of viewing the target job seeker information. For example, if the user US1 is in charge of recruiting infrastructure engineers and the job seeker has work experience as both an infrastructure engineer and a back-end engineer, the user US1 can provide resume information that is less detailed about the back-end engineer's experience and more detailed about the infrastructure engineer's experience, thereby reducing the burden on the user US1 to confirm while retaining the information necessary for deciding whether or not to make the job seeker a candidate for employment.
[0039] (3) Information processing The information processing of this embodiment will be described with reference to a flowchart of FIG 5.
[0040] The process of FIG. 5 may be started, for example, when the client device 10 accesses a talent matching service and receives an instruction from a user (for example, a recruiter at a company offering a job) to start creating resume information for a job seeker.
[0041] As shown in FIG. 5, the server 30 acquires job information (S130). Specifically, the server 30 receives the target job information or information capable of identifying the target job information from the client device 10. The server 30 acquires the target job information based on the received information. As a first example, the user inputs job information of the company to which the user belongs that the user is interested in to an object that accepts job information arranged on a UI (User Interface) screen of the human resources matching service that is displayed on the display 21 of the client device 10. The client device 10 transmits the content input to this object to the server 30 as the target job information. As a second example, the user specifies job information of interest from a list of job information from the company to which the user belongs on the UI screen of the human resources matching service displayed on the display 21 of the client device 10. The client device 10 transmits information identifying the specified job information (for example, a job ID identifying a job corresponding to the specified job information, or a URL at which the specified job information can be viewed) to the server 30 as information capable of identifying the target job information.
[0042] The target job information may be, for example, any of the following: Job listings recommended by job seekers · Job information that has been applied for by job seekers Job information selected or reacted to (for example, liked, commented, or tagged) by a user from among the company's job information available on the personnel matching service Here, the recommendation of job seekers to job information may be performed by the information processing system 1 (particularly the server 30) on a rule-based basis or using a trained model, for example, or may be performed by a human (scout).
[0043] The target job information may include at least one of the following: Information about the job you are looking for Information about the employer's profile requirements (e.g. required skills, preferred skills, or available technologies) Information about planned benefits after employment Information about the company you are hiring (e.g. company name or company details)
[0044] After step S130, the server 30 acquires job seeker information (S131). Specifically, the server 30 receives target job seeker information relating to a specific job seeker, or information capable of identifying the target job seeker information, from the client device 10. The server 30 acquires the target job seeker information based on the received information. As a first example, a user inputs, for example, by copying and pasting, job seeker information of a job seeker of interest to an object for accepting job seeker information arranged on the UI screen of the human resources matching service displayed on the display 21 of the client device 10. The client device 10 transmits the content input to this object to the server 30 as target job seeker information. As a second example, the user specifies the job seeker information viewed on the UI screen of the talent matching service displayed on the display 21 of the client device 10. For example, in the talent matching service, job seekers register their own job seeker information so that it can be viewed, and the user (a person in charge at a company offering a job) can specify the viewed job seeker information of interest. The client device 10 transmits information identifying the specified job seeker information (for example, a user ID identifying a job seeker corresponding to the specified job seeker information, or a URL at which the specified job seeker information can be viewed) to the server 30 as information for identifying the target job seeker information.
[0045] The job seeker corresponding to the target job seeker information may be, for example, any of the following: A job seeker who is recommended as a candidate for employment in response to job information provided by the company to which the user belongs (for example, the target job information obtained in step S130) A job seeker who applied for a job posting by a company to which the user belongs (for example, the target job posting acquired in step S130) Job seekers selected or reacted to (for example, liked, commented, or tagged) by users based on job seeker information viewable on the human resources matching service
[0046] The job seeker information may include information regarding at least one of the job seeker's name, attributes, background, characteristics, or intentions. The job seeker attributes may include, for example, at least one of gender, age, or place of residence. The job seeker's work history may include, for example, at least one of a job type, a job title, a place of employment, a work history (which may include, for example, a period of employment or an overview of projects undertaken), or an educational history. The job seeker characteristics may include, for example, at least one of skills, English language proficiency, techniques used, preferences, strengths, or weaknesses. The job seeker's intentions may include, for example, at least one of what the job seeker wants to do in the future (specifically, what the job seeker wants in his or her next job, such as a desired job type, desired duties, or desired career), what the job seeker does not want to do in the future, or a desired income.
[0047] The target job seeker information may also correspond to a resume prepared by the job seeker. In this case, the resume information prepared by the server 30 may correspond to a result of revising (e.g. summarizing) the resume prepared by the job seeker for the target job information.
[0048] The server 30 can acquire job information (S130) and job seeker information (S131) in the following exemplary manner. As a first example, the server 30 may search for job seeker information that matches any of the job seeker information by the company (job-seeking company) to which the user belongs, and recommend to the user a job seeker corresponding to the job seeker information found. The server 30 may then obtain the job seeker information that is the target of the recommendation (e.g., the job seeker information that is determined to match the job seeker information of the recommended job seeker), and obtain the job seeker information of the recommended job seeker. As a second example, the server 30 may receive from a job seeker an application or a reaction to any of the job information by the company (employing company) to which the user belongs. The server 30 may then acquire the job information that is the subject of the application or reaction, and acquire job seeker information of the job seeker who applied or reacted.
[0049] After step S131, the server 30 executes acquisition of resume information (S132). Specifically, the server 30 generates model input information based on the target job vacancy information acquired in step S130 and the target job seeker information acquired in step S131. As an example, the server 30 generates text based on the target job vacancy information and the target job seeker information as the model input information. The text may correspond to an instruction sentence for the natural language model. The server 30 inputs the model input information into the natural language model to acquire resume information (text) of a job seeker corresponding to the target job seeker information, which is generated by the natural language model.
[0050] The model input information may include information corresponding to constraints on aspects (eg, output format) of resume information (ie, response sentences generated by the natural language model). For example, the constraints may be at least one of the following: ·Constraints on what you want to follow when generating resume information · Restrictions on what not to follow when generating resume information
[0051] Constraints regarding matters to be followed when generating resume information may include, for example, at least one of the following: -Guideline, upper or lower limit for the number of characters in resume information - The approximate number of times a job seeker's name appears in a resume, or the upper or lower limit - Components of resume information and their approximate, upper or lower limits for length · Use appropriate line breaks in resume information · Use polite language in resume information · Use expressions that are expected to give the reader of the resume a certain impression - Abstractly expressing the skill level of a job seeker in resume information
[0052] Constraints regarding matters that should not be followed (prohibited) when generating resume information may include, for example, at least one of the following. · Having a job seeker's name appear multiple times in resume information · Include a greeting in your resume -Specifically express the job seeker's skill level in the resume information Complying with conditions that are not predefined as constraints (for example, conditions embedded in the text included in the target job applicant information or target job information)
[0053] In short, the instruction sentence may be a sentence instructing the natural language model ML5 to create resume information for a job seeker based on the acquired information (i.e., the job information and job seeker information) and so as to satisfy the constraint conditions. Also, information (template) that is the source of the instruction sentence may be stored in the storage device 31 of the server 30, and the server 30 may generate the instruction sentence by applying the acquired information (i.e., the job information and job seeker information) to the template. The constraint conditions may be embedded in the template in advance.
[0054] After step S132, the server 30 executes output of resume information (S133). Specifically, the server 30 outputs the resume information acquired in step S133. As an example, the server 30 presents the resume information to the user via the client device 10. That is, the server 30 transmits the resume information to the client device 10. The client device 10 displays the received resume information on the display 21.
[0055] The presentation of resume information may be made on an app screen or a website screen, or may be made by using email or other messages (e.g., SNS (Social Networking Service) messages, SMS (Short Message Service) messages, etc.). Presentation of resume information may also include announcement by posting a message on an electronic bulletin board, chat tool, or SNS in a format viewable by the user (and further by a legitimate person such as the user's supervisor).
[0056] (4) Summary As described above, the server 30 of this embodiment acquires job seeker information on a job seeker, inputs model input information based on the job seeker information into a natural language model, acquires resume information of the job seeker generated by the natural language model, and outputs the resume information. This makes it possible to provide the user with resume information of the job seeker without the job seeker having to create the resume for the job seeker. In other words, the hiring manager of the company offering a job can obtain the resume information of the job seeker while at least reducing the burden on the job seeker of creating a resume.
[0057] The job seeker information may include information regarding at least one of the attributes, history, characteristics, and intentions of the job seeker. This makes it possible to provide resume information that is generated in consideration of at least one of the attributes, history, characteristics, and intentions of the job seeker.
[0058] The job seeker information may include information regarding the job seeker's requirements for his / her next job, which makes it possible to provide resume information that is created taking into account the job seeker's requirements for his / her next job.
[0059] The model input information may be further based on a particular job listing (i.e., a target job listing), thereby enabling the provision of resume information that is generated with the particular job listing in mind.
[0060] The server 30 may identify a specific job offer from the job offer information of the company to which the user belongs, and input model input information based on the job seeker information and the specific job offer information into the natural language model to obtain resume information of the job seeker generated by the natural language model, and present the resume information to the user. This allows the user to view resume information generated in consideration of the job offer information of the company to which the user belongs, and therefore allows the user to efficiently check information that is used as a basis for deciding whether or not to consider the corresponding job seeker as a candidate for employment, compared to the case of viewing the job seeker information itself.
[0061] The job seeker may be a person recommended for a particular job posting, so that the user can be provided with resume information of people recommended for the job posting of the company to which the user belongs.
[0062] The job seeker may be a person who has applied for a specific job posting. This makes it possible to provide the user with resume information of people who have applied for the job posting of the company to which the user belongs.
[0063] The specific job information may include at least one of information on the type of job being recruited or information on the requirements for the personality profile desired by the recruiting company. This makes it possible to provide resume information that has been created taking into consideration at least one of information on the type of job being recruited or information on the requirements for the personality profile desired by the recruiting company.
[0064] The model input information may be further based on information that constrains the aspect of the resume information, thereby making it possible to stably obtain resume information in an appropriate aspect.
[0065] (5) Variations A modification of this embodiment will now be described.
[0066] (5-1) Variation 1 A description will now be given of Modification 1. Modification 1 is an example in which job seeker information is collected through a question and answer session with the job seeker, and resume information of the job seeker can be provided.
[0067] (5-1-1) One aspect of Modification 1 A description will be given of one aspect of Modification 1. Fig. 6 is an explanatory diagram of one aspect of Modification 1.
[0068] As shown in FIG. 6, a user US2, who corresponds to a job seeker, operates a client device 10 and starts creating his / her own resume information. The server 30 outputs questions to the user US2 for each of one or more items related to the resume information and receives answers to the questions (question and answer session). The server 30 then acquires job seeker information of the user US2 based on the answers from the user US2. However, the server 30 does not need to acquire the job seeker information based only on the answers from the user US2, and may acquire the job seeker information based further on information from other information sources (for example, job seeker information such as profile information voluntarily entered by the user).
[0069] The server 30 inputs model input information based on the job seeker information of the user US2 into the natural language model ML5, thereby obtaining resume information of the user US2 generated by the natural language model ML5. The server 30 may optionally input model input information for specific job listings (e.g., job listings of interest to the user US2) in addition to the job seeker information of the user US2 into the natural language model ML5, thereby obtaining resume information of the user US2 generated by the natural language model ML5.
[0070] The server 30 transmits the acquired resume information to the client device 10. The client device 10 presents the resume information received from the server 30 to the user US2.
[0071] This allows the server 30 to provide the user US2 with his / her resume information without the user US2 having to create the resume text itself. In other words, the user US2 can obtain his / her own resume information while at least reducing the burden on the user US2 of creating a resume.
[0072] (5-1-2) Information processing The following describes information processing in Modification 1. Fig. 7 is a flowchart of information processing in Modification 1. Fig. 8 is a flowchart showing details of obtaining job seeker information in Modification 1.
[0073] The process of FIG. 7 may be started, for example, by the client device 10 accessing a talent matching service and receiving an instruction from a user (for example, the job seeker) to start creating resume information for the job seeker.
[0074] As shown in FIG. 7, the server 30 acquires job information (S230). Specifically, the server 30 receives the target job information or information that can identify the target job information from the client device 10. The server 30 acquires the target job information based on the received information. Note that the acquisition of job information (S230) can be omitted, and in this case, the server 30 uses model input information that is not based on the target job information in acquiring resume information (S132). As a first example, a user inputs job information from a company that the user is interested in into an object for accepting job information arranged on a UI screen of a human resources matching service displayed on the display 21 of the client device 10. The client device 10 transmits the content input into this object to the server 30 as the target job information. As a second example, the user specifies job information of interest from a list of job information included in the UI screen of the talent matching service displayed on the display 21 of the client device 10. The client device 10 transmits information identifying the specified job information (e.g., a job ID identifying a job corresponding to the specified job information, or a URL at which the specified job information can be viewed) to the server 30 as information capable of identifying the target job information.
[0075] The target job information may be, for example, any of the following: Job listings that have been recommended to you as a potential employee Job information for which a job seeker has applied or plans to apply Job information that a user has selected or reacted to (for example, liked, commented on, or tagged) among the job information available on the personnel matching service
[0076] After step S230, the server 30 acquires job seeker information (S231). Specifically, the server 30 receives target job seeker information related to a specific job seeker or information that can identify the target job seeker information from the client device 10. The server 30 acquires the target job seeker information based on the received information. As an example, the server 30 executes the process of FIG.
[0077] As shown in FIG. 8, the server 30 executes question selection (S2310). Specifically, at least one question is associated with each of one or more items related to resume information. The server 30 selects one of the questions associated with the item being processed among the one or more items. As an example, the server 30 may randomly select one of the questions associated with the item being processed.
[0078] After step S2310, the server 30 executes output of a question (S2311). Specifically, the server 30 transmits the question (question sentence) selected in step S2310 to the client device 10. When outputting the question (S2311) after step S2315 described later, the server 30 transmits the question with the modified wording to the client device 10. The client device 10 displays the received question on the display 21. The client device 10 receives an answer to the question from the user and transmits the answer to the server 30.
[0079] After step S2311, the server 30 executes acquisition of a response (S2312). Specifically, the server 30 receives from the client device 10 the answer to the question output in step S2311.
[0080] After step S2312, the server 30 executes a determination of the appropriateness of the answer (S2313). Specifically, the server 30 judges whether the answer acquired in step S2312 is appropriate for the item being processed. As an example, the server 30 generates an instruction sentence for requesting the natural language model to judge whether the answer acquired in step S2312 is appropriate for the item being processed, and inputs the instruction sentence to the natural language model. The server 30 judges the appropriateness of the answer acquired in step S2312 based on the response sentence generated by the natural language model.
[0081] If the answer is not determined to be appropriate in step S2313, the server 30 changes the wording of the question (S2315). Specifically, the server 30 changes the wording of the question selected in step S2310 in order to ask the user again about the question regarding the item being processed. As an example, the server 30 inputs model input information based on the question into a natural language model to obtain a question with a changed wording. For example, the server 30 may change the question "Please tell me about the outline of your most recent project" to a question "I'm sorry, I couldn't get a proper answer, so please tell me about the outline of your most recent project again." After step S231, the server 30 re-executes the output of the question (S2311). This allows a differently worded question to be presented to the user regarding the item being processed.
[0082] If the answer is determined to be appropriate in step S2313 and questions and answers for all items have not been completed, the server 30 selects the next item (S2314). Specifically, the server 30 acquires the answers determined to be appropriate as job seeker information related to the item being processed. The server 30 then selects one of the items for which a question and answer session has not yet been completed as the next item to be processed. After step S2314, the server 30 re-executes the question selection (S2310). This makes it possible to present a question to the user for the item for which a question and answer session has not yet been completed.
[0083] If the answers are determined to be appropriate in step S2313 and questions and answers for all items have been completed, the server 30 ends the process of FIG.
[0084] Furthermore, the server 30 may use job seeker information acquired by a method other than the process of FIG. 8 as part of the target job seeker information. As a first example, a user inputs his / her own job seeker information into an object for accepting job seeker information arranged on a UI screen of a human resources matching service displayed on the display 21 of the client device 10. The client device 10 transmits the contents of the input to this object to the server 30 as part of the target job seeker information. As a second example, a user specifies his / her own registered job seeker information on the UI screen of the talent matching service displayed on the display 21 of the client device 10. The client device 10 transmits information identifying the specified job seeker information (e.g., a user ID identifying the user, or a URL at which the specified job seeker information can be viewed) to the server 30 as information capable of identifying a part of the target job seeker information.
[0085] After step S231, the server 30 executes the processes of obtaining resume information (S132) to outputting resume information (S133) in the same manner as in this embodiment.
[0086] (5-1-3) Summary As described above, the server 30 of the first modification may output questions to the job seeker for each of one or more items, receive answers to the questions, and acquire job seeker information based on the answers. This allows the server 30 to provide the job seeker with his / her resume information without requiring the job seeker to write the resume text itself. In other words, the job seeker can obtain his / her own resume information while at least reducing the burden on the job seeker of creating a resume.
[0087] At least one question may be associated with each of one or more items. The server 30 may use a natural language model to determine whether or not an answer to a question is appropriate, and if it is determined that an answer to a question regarding any item is inappropriate, the server 30 may change the wording of the question associated with that item and output it to the job seeker. In this way, even if the job seeker misunderstands the purpose of the question and gives an inappropriate answer, the question can be presented again in a different wording, thereby increasing the possibility of obtaining an appropriate answer.
[0088] When multiple questions are associated with a first item included in one or more items, the server 30 may randomly select one of the multiple questions associated with the first item and output it to the job seeker. This distributes the questions presented to the job seeker for each item. In other words, even if some questions are not appropriately expressed, such as causing misunderstandings to users, the frequency with which the questions are presented will not be extremely high, and the adverse effects of frequently presenting the questions can be mitigated.
[0089] The server 30 may use a natural language model to determine whether the answer to the question is appropriate, and if the answer to the question output for any item is determined to be appropriate, acquire the answer as job seeker information for that item. This can improve the quality of job seeker information, and as a result, the quality of resume information.
[0090] The target job information may be job information designated by the job seeker, which allows the job seeker to be provided with resume information that takes into account the job information that interests the job seeker.
[0091] The information processing of the first modification can be appropriately combined with the information processing of the present embodiment. For example, by using target job information acquired by a dialogue between a job seeker and a natural language model in the same way as the information processing of the first modification, resume information suitable for a specific job offer of a job-seeking company may be acquired and provided to a hiring manager of the job-seeking company in the same way as the information processing of the present embodiment.
[0092] (6) Other modifications The storage device 11 may be connected to the client device 10 via a network NW. The display 21 may be built into the client device 10. The storage device 31 may be connected to the server 30 via the network NW.
[0093] Each step of the above information processing can be executed by either the client device 10 or the server 30. In addition, in the above description, an example in which each step in the information processing is executed in a specific order has been shown, but the execution order of each step is not limited to the example described above as long as there is no dependency between the steps.
[0094] In the above explanation, an example was given in which a natural language model was used to acquire resume information of a job seeker. This natural language model or another natural language model may be used to acquire a catchphrase of the job seeker. A catchphrase is shorter in length than resume information and expresses the characteristics of the job seeker in concise words. The server 30 may output (provide to the user) the catchphrase instead of resume information, or may output the catchphrase together with the resume information. Providing a catchphrase created in this way can improve the efficiency of the recruiting staff of a company looking to hire and can be used by a job seeker as one of the materials for self-promotion. Specifically, the server 30 may input model input information based on the resume information acquired in step S132 into the natural language model, thereby acquiring the catchphrase (text) of the job seeker generated by the natural language model. As an example, the server 30 generates text based on the resume information as the model input information. The text may correspond to an instruction sentence for the natural language model. In addition, the model input information may include information corresponding to a constraint condition regarding the aspect (e.g., output format) of the catchphrase (i.e., the response sentence generated by the natural language model). For example, the constraints may be at least one of the following: Number of catchphrases to generate ·Constraints on what you want to be followed when generating catchphrases ·Constraints on what not to follow when generating catchphrases Constraints on what should be followed when generating catchphrases may include, for example, at least one of the following: -Guideline, upper or lower limit for the number of characters in the catchphrase · Use sentence endings in catchphrases Use expressions that are expected to give a certain impression to the reader of the catchphrase. Constraints regarding matters that should not be followed (prohibited) when generating a catchphrase can include, for example, at least one of the following. · Make the catchphrase a sentence · Use polite language in catchphrases - Using expressions in catchphrases that are unpleasant for humans -Include in your tagline an explanation of why you chose it
[0095] The job seeker information may include information stored in an external system as a result of the job seeker using the external system. In this case, the server 30 may acquire the job seeker information from the external system in acquiring the job seeker information (S131) or acquiring the job seeker information (S231). This makes it possible to supplement the job seeker information that can be acquired without imposing an input burden on the job seeker, and to provide higher quality resume information. Specifically, the server 30 may acquire job seeker information from an external system using account information (e.g., account name, login information, or a combination thereof) of the job seeker in a service provided by the external system (hereinafter referred to as an "external service"). The server 30 may acquire the job seeker information using an API (Application Programming Interface) of the external service, or may acquire the job seeker information by crawling a web page of the external service. The server 30 may acquire information on content posted by the job seeker, log information representing the activity of the job seeker in the issue management service, or information on the profile registered by the job seeker in the external service. The external service may include, but is not limited to, Qiita (registered trademark), Zenn (registered trademark), LinkedIn (registered trademark), note (registered trademark), Slide Share, or Speaker Deck, for example.
[0096] The server 30 may search for job information recommended to the job seeker based on the acquired catchphrase or resume information, and output the searched job information. This can increase the matching rate between the job seeker and the hiring company. Specifically, the server 30 may perform a matching process between the catchphrase or resume information and job information, and output (present to the job seeker) a predetermined number of job information selected in descending order of score, or job information whose score exceeds a threshold value.
[0097] 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.
[0098] (7) Additional Notes The matters described in the embodiment and the modified examples are supplemented below.
[0099] (Appendix 1) A computer (30), A means for acquiring job seeker information relating to a job seeker (S131, S231); a means for inputting first model input information based on job seeker information into a natural language model, thereby acquiring resume information of the job seeker generated by the natural language model (S132); A means for outputting resume information (S133); A program that functions as a
[0100] (Appendix 2) The job applicant information includes information regarding at least one of the job applicant's attributes, career history, characteristics, or intentions; 2. The program described in Appendix 1.
[0101] (Appendix 3) Job Seeker Information includes information about what a job seeker is looking for in their next job, 2. The program described in Appendix 1.
[0102] (Appendix 4) The first model input information is further based on the specific job posting, 2. The program described in Appendix 1.
[0103] (Appendix 5) The computer is further made to function as a means (S130, S230) for identifying specific job information from job information of the company to which the user belongs; The means for acquiring resume information of the job seeker includes inputting first model input information based on the job seeker information and the specific job offer information into a natural language model, thereby acquiring resume information of the job seeker generated by the natural language model; The output means presents the resume information to the user. 5. The program described in Appendix 4.
[0104] (Appendix 6) The job seeker is a recommended candidate for a particular job posting; 5. The program described in Appendix 4.
[0105] (Appendix 7) A job seeker is someone who has applied for a specific job posting; 5. The program described in Appendix 4.
[0106] (Appendix 8) A particular job posting contains at least one of the following: information about the type of job being advertised or the profile requirements of the employer; 5. The program described in Appendix 4.
[0107] (Appendix 9) A specific job posting is a job posting specified by a job seeker; 5. The program described in Appendix 4.
[0108] (Appendix 10) The means for acquiring job seeker information (S231) outputs questions to the job seeker for each of one or more items, accepts answers to the questions, and acquires job seeker information based on the answers. 2. The program described in Appendix 1.
[0109] (Appendix 11) One or more items each have at least one question associated with them, the means for acquiring job seeker information causes a natural language model to determine whether or not an answer to a question is appropriate, and when it is determined that an answer to a question regarding any item is inappropriate, changes the wording of the question associated with that item and outputs the changed answer to the job seeker; 11. The program according to claim 10.
[0110] (Appendix 12) the means for acquiring job seeker information, when a first item included in the one or more items has a plurality of questions associated with it, randomly selecting one of the plurality of questions associated with the first item and outputting the selected one to the job seeker; 12. The program according to claim 11.
[0111] (Appendix 13) the means for acquiring job seeker information includes having a natural language model determine whether or not an answer to a question is appropriate, and when it is determined that an answer outputted for any item to a question is appropriate, acquiring the answer as job seeker information relating to that item; 11. The program according to claim 10.
[0112] (Appendix 14) The first model input information is further based on information constraining an aspect of the resume information; 2. The program described in Appendix 1.
[0113] (Appendix 15) Job seeker information includes information stored in an external system by a job seeker using the external system, 2. The program described in Appendix 1.
[0114] (Appendix 16) Computer, a means for inputting second model input information based on resume information into a natural language model to obtain a catchphrase for the job seeker generated by the natural language model; A means for outputting a catchphrase; Function as a A catchphrase is shorter than resume information. 2. The program described in Appendix 1.
[0115] (Appendix 17) A natural language model is a large-scale interactive language model. the first model input information is an instruction statement including the job seeker information; 2. The program described in Appendix 1.
[0116] (Appendix 18) A computer (30) A step of acquiring job seeker information relating to a job seeker (S131, S231); inputting first model input information based on job seeker information into a natural language model to obtain resume information of the job seeker generated by the natural language model (S132); A step (S133) of outputting resume information; A method for performing.
[0117] (Appendix 19) A means for acquiring job seeker information relating to a job seeker (S131, S231); A means for inputting first model input information based on job seeker information into a natural language model to obtain resume information of the job seeker generated by the natural language model (S132); A means for outputting resume information (S133); An information processing device comprising:
[0118] (Appendix 20) A system (1) comprising a first information processing device (30) and a second information processing device (10), The first information processing device is A means for acquiring job seeker information relating to a job seeker (S131, S231); A means for inputting first model input information based on job seeker information into a natural language model to obtain resume information of the job seeker generated by the natural language model (S132); A means for outputting resume information to a second information processing device (S133); Equipped with system. [Explanation of symbols]
[0119] 1: Information processing system 10: Client device 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
Claims
1. Computer, a means of obtaining job seeker information about a job seeker; a means for inputting first model input information based on the job seeker information into a natural language model, thereby acquiring resume information of the job seeker generated by the natural language model; A means for outputting the resume information; A program that functions as a
2. The job seeker information includes information regarding at least one of the job seeker's attributes, career history, characteristics, or intentions. The program according to claim 1.
3. The job seeker information includes information regarding the job seeker's requirements for his or her next job, The program according to claim 1.
4. The first model input information is further based on a specific job posting. The program according to claim 1.
5. The computer is further caused to function as a means for identifying the specific job information from job information of the company to which the user belongs; the means for acquiring resume information of the job seeker inputs the first model input information based on the job seeker information and the specific job offer information into the natural language model to acquire resume information of the job seeker generated by the natural language model; The output means presents the resume information to the user. The program according to claim 4.
6. The job seeker is a person who has been recommended for the particular job posting; The program according to claim 4.
7. The job seeker is a person who applied for the specific job information. The program according to claim 4.
8. The specific job information includes at least one of information regarding the type of job being recruited or information regarding the requirements for the personality profile required by the recruiting company; The program according to claim 4.
9. The specific job information is job information specified by the job seeker. The program according to claim 4.
10. the means for acquiring job seeker information outputs questions to the job seeker for each of one or more items, accepts answers to the questions, and acquires the job seeker information based on the answers; The program according to claim 1.
11. at least one question is associated with each of the one or more items; the means for acquiring job seeker information causes the natural language model to determine whether or not the answers to the questions are appropriate, and when it is determined that the answer to the question regarding any item is inappropriate, changes the wording of the question regarding that item and outputs the changed answer to the job seeker. The program according to claim 10.
12. when a plurality of questions are associated with a first item included in the one or more items, the means for acquiring job seeker information randomly selects one of the plurality of questions associated with the first item and outputs the selected question to the job seeker; The program according to claim 11.
13. the means for acquiring job seeker information causes the natural language model to determine whether or not the answers to the questions are appropriate, and when it is determined that the answer outputted for any of the items is appropriate, acquires the answer as the job seeker information for that item; The program according to claim 10.
14. The first model input information is further based on information constraining an aspect of the resume information; The program according to claim 1.
15. The job seeker information includes information accumulated in an external system by the job seeker using the external system. The program according to claim 1.
16. The computer, a means for inputting second model input information based on the resume information into the natural language model to obtain a catchphrase for the job seeker generated by the natural language model; means for outputting the catchphrase; Functioning as a The catchphrase has a smaller amount of text than the resume information. The program according to claim 1.
17. the natural language model is an interactive large-scale language model; the first model input information is a command statement including the job seeker information; The program according to claim 1.
18. The computer obtaining job seeker information relating to a job seeker; inputting first model input information based on the job seeker information into a natural language model to obtain resume information of the job seeker generated by the natural language model; outputting the resume information; A method for performing.
19. a means for obtaining job seeker information relating to a job seeker; a means for inputting first model input information based on the job seeker information into a natural language model to obtain resume information of the job seeker generated by the natural language model; A means for outputting the resume information; An information processing device comprising:
20. A system including a first information processing device and a second information processing device, The first information processing device, a means for obtaining job seeker information relating to a job seeker; a means for inputting first model input information based on the job seeker information into a natural language model to obtain resume information of the job seeker generated by the natural language model; means for outputting the resume information to the second information processing device; Equipped with system.
Citation Information
Patent Citations
Job hunting / job offer information system and recording medium with recorded program for providing the same
JP2001142939A
Electronic personal history system
JP2004252586A
Matching device and method
JP2009301422A
Crowdworker support system, crowdworker support method, and crowdworker support program
JP7116443B1
Resume tool
US20170262811A1
Cited By
Information processing systems, programs, and information processing methods
JP2026113042A
Information processing system, program, and information processing method
JP7643773B1
Job Seeker Support System
JP7819995B1
Information processing system, information processing method, and information processing program
JP7855186B1
