JP7353696B1 - Information processing device, method, program, and system - Google Patents

Abstract

[Problem] To make it possible to obtain information useful for hiring job seekers while at least reducing the burden on the job seekers. [Solution] A program according to one aspect of the present disclosure includes means for acquiring job applicant information regarding a job applicant, and inputting first model input information based on the job applicant information into a natural language model. It functions as a means for acquiring resume information of job seekers generated by the model and as a means for outputting resume information. [Selection diagram] Figure 4

Description

Application of Article 30, Paragraph 2 of the Patent Act Posted on the website (https://prtimes.jp/main/html/rd/p/000000048.000045379.html) on March 6, 2023

Application of Article 30, Paragraph 2 of the Patent Act Posted on the website (https://findy-code.io/openai-career-summarize/lp) on March 6, 2023

Application of Article 30, Paragraph 2 of the Patent Act Posted on the website (https://findy-code.io/ai-interview/lp) on March 6, 2023

Application of Article 30, Paragraph 2 of the Patent Act Posted on the website (https://prtimes.jp/main/html/rd/p/000000051.000045379.html) on April 5, 2023

Article 30, Paragraph 2 of the Patent Law, Ideal, March 7, 2023, website (https://tHeBRIDGE.jp / 2023/03 / Internet -Services -TO -CHANGE -CHADICALLY -WITGPT -THE -THE -THE -SECOND -P ART ) Posted on

Application of Article 30, Paragraph 2 of the Patent Act April 6, 2023, website (https://thebridge.jp/2023/04/findy-releases-automatic-job-history-with-chatgpt?fbclid=IwAR3uB _WOnjXDflz90mQZVgzela8po_Gv2nTODmUdQ7o8vUbVDleluLNoZg) Publication of

Application of Article 30, Paragraph 2 of the Patent Act April 26, 2023, website (https://thebridge.jp/2023/04/how-does-startup-think-about-a-new-chat-gpt-era -interview-w-findy-yamada-san-and-sato-san)

The present disclosure relates to an information processing device, method, program, and system.

When looking for a job, job seekers need to create a resume (also called a work history) that describes how they can use their experience and skills to contribute to the company they are applying to. Although job seekers may be able to reuse resumes they have created in the past, they are required to create a resume for each company they apply to, which can feel cumbersome. On the other hand, a hiring manager at a recruiting company may try to search for job seekers who are potential candidates for employment (for example, to whom scouting documents should be sent) based on the profile information that job seekers have registered on a human resource matching platform. At this time, since the profile information contains a mixture of elements that the company considers important and elements that it does not, the burden of checking the profile information is not small.

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.

Japanese Patent Application Publication No. 2001-142939

According to the technical idea of Patent Document 1, the quality of the generated summary largely depends on the summary items registered by the company. Therefore, if a person in charge at a company sets inappropriate summary items, there is a risk that information that is highly relevant to the company's recruitment may be omitted from the summary, or that less relevant information may remain in the summary. .

An object of the present disclosure is to provide a technology that makes it possible to obtain information useful for hiring job seekers while at least reducing the burden on job seekers.

A program according to one aspect of the present disclosure includes means for acquiring job applicant information regarding a job applicant, and inputting first model input information based on the job applicant information into a natural language model, thereby generating information generated by the natural language model. It functions as a means for acquiring resume information of job seekers and a means for outputting resume information.

FIG. 1 is a block diagram showing the configuration of an information processing system according to the present embodiment. FIG. 2 is a block diagram showing the configuration of a client device according to the present embodiment. FIG. 2 is a block diagram showing the configuration of a server according to the present embodiment. FIG. 2 is an explanatory diagram of one aspect of the present embodiment. It is a flowchart of information processing of this embodiment. FIG. 7 is an explanatory diagram of one aspect of Modification Example 1; 12 is a flowchart of information processing in Modification 1. 12 is a detailed flowchart of obtaining job applicant information in Modification 1. FIG.

Hereinafter, one embodiment of the present invention will be described in detail based on the drawings. In addition, in the drawings for explaining the embodiments, the same components are generally designated by the same reference numerals, and repeated explanations thereof will be omitted.

(1) Configuration of information processing system The configuration of the information processing system will be explained. FIG. 1 is a block diagram showing the configuration of an information processing system according to this embodiment.

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.

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 transmitted from the client device 10. Server 30 is, for example, a server computer. The server 30 can manage a talent matching service (which can also be referred to as a "talent matching platform") in which job seekers and recruiting companies (which can include scouts) participate. Human resources matching services are equivalent to places that connect job seekers with hiring companies. In this specification, a job seeker includes a person who intends to seek a job, and at least registers job seeker information on the human resources matching service or prepares for registration (e.g., uploads a resume file or work history file, or (including those who enter job applicant information). Similarly, a recruiting company includes a legal entity or an individual with an intention to recruit, and at least uses a talent matching service to carry out recruitment activities directly or indirectly (via scouts) (e.g. sending scout documents, posting job information, etc.) (registration or preparation for registration).

The client device 10 is an example of an information processing device that sends 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 recruiting company (for example, a hiring manager at a recruiting company), or a person who introduces job seekers who are considered suitable for the recruiting company (a so-called job change agent). Here, the person in charge of recruitment at the recruiting company is not limited to the person in charge of the human resources department, but may be, for example, the person in charge of the department that is trying to hire people through job offers. Job seekers are those who are looking for a job change or (re)job hunting, or those who are interested in these activities.

Here, an example of the behavior of the server 30 regarding 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 searchably) by, for example, a hiring manager at a recruiting company. Recruiters can create and send scouting documents to job seekers who are deemed suitable for their company. Alternatively, the server 30 publishes job information provided by recruiting companies in a state where job seekers can view it, for example. Job seekers can create a resume and apply for a job at a recruiting company that they think is suitable for them. In this way, recruiting companies and job seekers can be linked.

(1-1) Configuration of client device The configuration of the client device will be explained. FIG. 2 is a block diagram showing the configuration of the client device of this embodiment.

As shown in FIG. 2, the client device 10 includes a storage device 11, a processor 12, an input/output interface 13, and a communication interface 14. Client device 10 is connected to display 21 .

The storage device 11 is configured to store programs and data. The storage device 11 is, for example, a combination of ROM (Read Only Memory), RAM (Random Access Memory), and storage (for example, flash memory or hard disk).

The programs include, for example, the following programs.
・OS (Operating System) program ・Application program that executes information processing (e.g. web browser or dedicated application)

The data includes, for example, the following data.
・Databases referenced in information processing ・Data obtained by executing information processing (that is, execution results of information processing)

The processor 12 is a computer that implements the functions of the client device 10 by activating 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)

The input/output interface 13 is configured to acquire information (for example, user instructions) from an input device connected to the client device 10 and output information (for example, an image) to an output device connected to the client device 10. be done.
The input device is, for example, a keyboard, pointing device, touch panel, or a combination thereof.
The output device is, for example, a display 21, a speaker, or a combination thereof.

Communication interface 14 is configured to control communication between client device 10 and an external device (eg, server 30).

The display 21 is configured to display images (still images or moving images). The display 21 is, for example, a liquid crystal display or an organic EL display.

(1-2) Server configuration The server configuration will be explained. FIG. 3 is a block diagram showing the configuration of the server of this embodiment.

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 34.

The storage device 31 is configured to store programs and data. The storage device 31 is, for example, a combination of ROM, RAM, and storage (eg, flash memory or hard disk).

The programs include, for example, the following programs.
・OS program ・Application program that executes information processing

The data includes, for example, the following data.
・Databases referenced in information processing ・Execution results of information processing

The processor 32 is a computer that implements the functions of the server 30 by activating a program stored in the storage device 31. The processor 32 is, for example, at least one of the following.
・CPU
・GPU
・ASIC
・FPGA

The input/output interface 33 is configured to obtain information (e.g., user instructions) from an input device connected to the server 30 and output information (e.g., an image) to an output device connected to the server 30. .
The input device is, for example, a keyboard, pointing device, touch panel, or a combination thereof.
The output device is, for example, a display.

Communication interface 34 is configured to control communications between server 30 and an external device (eg, client device 10).

(2) One aspect of the embodiment One aspect of the present embodiment will be described. FIG. 4 is an explanatory diagram of one aspect of this embodiment.

As shown in FIG. 4, a user US1, who is a hiring manager at a recruiting company, operates the client device 10 to select specific job information (an example of "target job information") from the job information of the company to which he belongs. Enter or specify. The target job information is job information used to create resume information for job seekers. The client device 10 transmits the target job offer information or information that can identify the target job offer information (eg, URL, identification information, etc.) to the server 30.

Similarly, the user US1 operates the client device 10 and inputs or specifies job applicant information regarding a specific job applicant (an example of "target job applicant information"). The target job applicant information is job applicant information of the job applicant, which is used to create resume information of the job applicant. The client device 10 transmits target job applicant information or information that can identify the target job applicant information (for example, a URL (Uniform Resource Locator), identification information, etc.) to the server 30.

The server 30 acquires target job offer information and target job applicant information based on information received from the client device 10. The server 30 inputs model input information based on target job offer information and target job applicant information into the natural language model ML5, thereby acquiring resume information of the specific job applicant generated by the natural language model ML5.

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 text may include at least one of target job offer information or target job applicant information. The natural language model ML5 may be an interactive model (which can also be called a chat type or conversation type) that alternately accepts instructions and generates responses. The natural language model ML5 may be a large-scale language model trained using a large amount of text data, or a model obtained by transfer learning of the large-scale language model. Further, the natural language model ML5 may be constructed in a system external to the information processing system 1.

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.

Thereby, the server 30 can provide resume information of a specific job applicant (job applicant corresponding to the target job offer information) to the user US1 without having the job applicant create a resume. In other words, the user US1, who is in charge of recruitment at the recruiting company, can obtain resume information of the job seeker while at least reducing the burden of creating a resume on the job seeker. In addition, since the user US1 can view the resume information generated in consideration of the target job offer information, the user US1 can decide whether or not to select the specific job applicant as a hiring candidate compared to the case where the user US1 views the target job applicant information. You can efficiently check information that can be used as a basis for making decisions. For example, if user US1 is in charge of hiring infrastructure engineers, and the job applicant has a work history as both an infrastructure engineer and a back-end engineer, for example, if the user US1 is in charge of hiring infrastructure engineers, the job seeker may refrain from mentioning the background as a back-end engineer, but not as an infrastructure engineer. By providing resume information with a thicker description of the job applicant's career history, it is possible to reduce the burden of confirmation on the user US1 while preserving the information necessary for determining whether or not to select the job applicant as a candidate for employment.

(3) Information processing Information processing of this embodiment will be explained. FIG. 5 is a flowchart of information processing according to this embodiment.

The process in FIG. 5 may be started, for example, by the client device 10 accessing a human resource matching service and receiving an instruction from a user (for example, a hiring manager at a recruiting company) to start creating resume information for a job applicant. .

As shown in FIG. 5, the server 30 acquires job offer information (S130).
Specifically, the server 30 receives target job offer information or information that can identify the target job offer information from the client device 10. The server 30 acquires target job offer information based on the received information.
As a first example, the user sends job information from the company to which he or she belongs to an object that accepts job information placed on the UI (User Interface) screen of the human resources matching service displayed on the display 21 of the client device 10. Enter the one you are interested in. The client device 10 transmits the input contents to this object to the server 30 as target job offer information.
As a second example, the user specifies job information of interest from a list of job information provided by the company to which the user belongs on the UI screen of the human resource matching service displayed on the display 21 of the client device 10. The client device 10 sends information identifying the specified job information (for example, a job ID that identifies a job corresponding to the specified job information, or a URL where the specified job information can be viewed) to the target job information. The information is sent to the server 30 as identifiable information.

The target job offer information may be any of the following, for example.
・Job information that has been recommended by a job seeker ・Job information for which a job seeker has applied Here, the job seeker's recommendation for the job information may be performed by the information processing system 1 (particularly the server 30), for example, on a rule basis or using a learned model. It may also be performed by humans (scouts).

The target job offer information can include at least one of the following.
・Information regarding the type of job for which recruitment is being offered ・Information regarding the character requirements sought by the hiring company (e.g., essential skills, welcome skills, or techniques used) ・Information regarding the treatment planned after employment ・Information regarding the recruiting company (e.g., company name, company information, etc.)

After step S130, the server 30 acquires job applicant information (S131).
Specifically, the server 30 receives from the client device 10 target job applicant information regarding a specific job applicant or information that allows the target job applicant information to be specified. The server 30 acquires target job applicant information based on the received information.
As a first example, the user enters job applicant information of an interested job applicant into an object that accepts job applicant information placed on the UI screen of the human resource matching service displayed on the display 21 of the client device 10, for example. Input by copying and pasting. The client device 10 transmits the input contents to this object to the server 30 as target job applicant information.
As a second example, the user specifies job applicant information viewed on the UI screen of the human resource matching service displayed on the display 21 of the client device 10. For example, in human resource matching services, job seekers can register their own job applicant information for viewing, and users (representatives at recruiting companies) can specify which of the viewed job applicant information they are interested in. can. The client device 10 sends information that identifies the specified job applicant information (for example, a user ID that identifies the job applicant corresponding to the specified job applicant information, or a URL where the specified job applicant information can be viewed). The target job applicant information is transmitted to the server 30 as identifiable information.

The job applicant corresponding to the target job applicant information may be any of the following, for example.
・Job seekers who are recommended as candidates for employment based on the job information provided by the company to which the user belongs (for example, the target job information obtained in step S130) ・Job seekers who are recommended as employment candidates based on the job information provided by the company to which the user belongs (for example, the target job information obtained in step S130) Job seekers that users have selected or reacted to (for example, liked, commented, or tagged) based on the job seeker information that can be viewed on the job seeker/talent matching service that they applied to.

The job applicant information may include information regarding at least one of the job applicant's name, attributes, background, characteristics, or intentions.
The job applicant's attributes can include, for example, at least one of gender, age, and place of residence.
The job applicant's history can include, for example, at least one of job type, title, place of work, work history (which can include, for example, length of employment or a summary of projects experienced), or educational background.
Job applicant characteristics may include, for example, at least one of skills, English proficiency, techniques used, preferences, strengths, or weaknesses.
The intention of the job seeker is, for example, at least one of what they want to work on in the future (specifically, what they want in their next job, such as desired job type, desired work, or desired career), what they do not want to work on in the future, or desired income. can include.

Further, the target job applicant information may correspond to a resume created by the job applicant. In this case, the resume information created by the server 30 may correspond to the result of revising (for example, summarizing) the resume created by the job seeker for the target job information.

The server 30 can acquire job offer information (S130) and job applicant information (S131) in the manner illustrated below.
As a first example, the server 30 searches for job applicant information that matches any of the job information provided by the company (recruiting company) to which the user belongs, and recommends to the user the job applicant corresponding to the discovered job applicant information. Good too. Then, the server 30 acquires the job information that is the target of the recommendation (for example, job information determined to match the job applicant information of the recommended job applicant), and acquires the job applicant information of the recommended job applicant. It's okay.
As a second example, the server 30 may receive from a job seeker an application or a reaction corresponding to any job information provided by the company (recruiting company) to which the user belongs. Then, the server 30 may obtain job information for which an application or reaction is made, and may obtain job applicant information of a job applicant who has applied or reacted.

After step S131, the server 30 acquires resume information (S132).
Specifically, the server 30 generates model input information based on the target job offer information acquired in step S130 and the target job applicant information acquired in step S131. As an example, the server 30 generates text based on target job offer information and target job applicant information as model input information. The text may correspond to instructions for the natural language model. The server 30 inputs the model input information into the natural language model, thereby acquiring resume information (text) of the job applicant corresponding to the target job applicant information generated by the natural language model.

The model input information can include information corresponding to constraints regarding the aspect (eg, output format) of the resume information (that is, the response sentence generated by the natural language model).
For example, the constraint may be at least one of the following.
・Restrictions on things you want to follow when generating resume information ・Restrictions on things you don't want to follow when generating resume information

For example, the constraint conditions regarding matters to be followed when generating resume information may include at least one of the following.
・Estimated number of characters, upper limit, or lower limit for resume information ・Estimated number, upper limit, or lower limit for the number of times the job applicant's name appears in resume information ・Resume information components and their estimated number of characters, upper limit, or lower limit ・Resume information・Use respectful style in resume information. ・Use expressions that are expected to give a specific impression to the reader of resume information. ・Use resume information to express the job seeker's technical level in an abstract manner. thing

Constraint conditions regarding items that should not be followed (desired to be prohibited) when generating resume information can include, for example, at least one of the following.
- Making the job seeker's name appear multiple times in the resume information - Including a greeting in the resume information - Specifying the skill level of the job seeker in the resume information - Conditions that are not predetermined as constraints (e.g. , conditions embedded in the text contained in the Qualified Job Applicant Information or Qualified Job Information).

In short, the instructions instruct the natural language model ML5 to create resume information for job seekers based on the acquired information (that is, job information and job seeker information) and in a manner that satisfies the constraints. It can be text. Further, the storage device 31 of the server 30 may store information (template) that is the source of the instruction text, and the server 30 can apply the acquired information (that is, job information and job applicant information) to the template. Instructions may also be generated. The constraint conditions may be embedded in the template in advance.

After step S132, the server 30 outputs resume information (S133).
Specifically, the server 30 outputs the resume information acquired in step S133. As an example, the server 30 presents resume information to the user via the client device 10. That is, the server 30 transmits resume information to the client device 10. The client device 10 displays the received resume information on the display 21.

The presentation of resume information may be performed on an app screen or a website screen, or by using email or other messages (e.g., SNS (Social Networking Service) message, SMS (Short Message Service) message, etc.). may be performed. Furthermore, the presentation of the resume information may include, for example, an announcement by posting a message on an electronic bulletin board, a chat tool, or an SNS in a format that can be viewed by the user (and an authorized person such as the user's boss).

(4) Summary As explained above, the server 30 of this embodiment obtains job applicant information about a job applicant, inputs model input information based on the job applicant information into a natural language model, and uses the corresponding natural language model. Acquires the job applicant's resume information generated by the model and outputs the resume information. Thereby, resume information of the job seeker can be provided to the user without having the job seeker create a resume of the job seeker. In other words, while at least reducing the burden on the job seeker to create a resume, the person in charge of recruitment at the recruiting company can obtain resume information of the job seeker.

The job applicant information may include information regarding at least one of the job applicant's attributes, background, characteristics, or intentions. This makes it possible to provide resume information that is generated taking into consideration at least one of the job seeker's attributes, career, characteristics, or intentions.

The job applicant information may include information regarding what the job applicant is looking for in his or her next job. This makes it possible to provide resume information that is generated taking into account the job seeker's requirements for the next job.

The model input information may be further based on specific job information (ie, target job information). This makes it possible to provide resume information that has been generated in consideration of specific job information.

The server 30 identifies specific job information from the job information of the company to which the user belongs, and inputs model input information based on the job applicant information and the specific job information into the natural language model. The job seeker's resume information generated by the above may be obtained and the resume information may be presented to the user. As a result, users can view resume information that has been generated by taking into consideration the job information of the company they belong to, so they can select the corresponding job applicant as a candidate for employment, compared to viewing the job applicant information itself. You can efficiently check information that will serve as a basis for deciding whether or not to do so.

The job applicant may be a person recommended for specific job information. Thereby, it is possible to provide the user with resume information of a person recommended for the job information of the company to which the user belongs.

The job seeker may be a person who has applied for specific job information. Thereby, it is possible to provide the user with resume information of a person who has applied for job information of the company to which the user belongs.

The specific job offer information may include at least one of information regarding the type of job to be recruited, and information regarding requirements for a person's image sought by the recruiting company. This makes it possible to provide resume information that has been generated in consideration of at least one of information regarding the type of job to be recruited or information regarding the requirements for the persona sought by the recruiting company.

The model input information may be further based on information that constrains aspects of the resume information. This makes it possible to stably acquire resume information in an appropriate format.

(5) Modification Example A modification example of this embodiment will be explained.

(5-1) Modification example 1
Modification 1 will be explained. Modification 1 is an example in which job seeker information is collected through question and answer sessions with job seekers, and resume information of the job seekers can be provided.

(5-1-1) One aspect of Modification 1 One aspect of Modification 1 will be described. FIG. 6 is an explanatory diagram of one aspect of Modified Example 1.

As shown in FIG. 6, the user US2, who corresponds to a job seeker, operates the client device 10 and starts creating his own resume information. The server 30 outputs questions to the user US2 regarding each of one or more items related to resume information, and receives answers to the questions (question and answer). Then, the server 30 acquires the job applicant information of the user US2 based on the answer from the user US2. However, the server 30 does not need to acquire job applicant information based only on the answer from the user US2, but rather information from other information sources (for example, job applicant information such as profile information voluntarily entered by the user). The job applicant information may be further acquired based on.

The server 30 inputs model input information based on the job applicant information of the user US2 into the natural language model ML5, thereby acquiring resume information of the user US2 generated by the natural language model ML5. The server 30 optionally inputs model input information into the natural language model ML5 for specific job information (for example, job information that the user US2 is interested in) in addition to the job applicant information of the user US2, so that the natural language The user US2's resume information generated by the model ML5 may be acquired.

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.

Thereby, the server 30 can provide the user US2 with his/her resume information without having the user US2 create the resume text itself. In other words, the user US2 can obtain his or her own resume information while at least reducing the burden of creating a resume on the user US2.

(5-1-2) Information Processing Information processing of Modified Example 1 will be explained. FIG. 7 is a flowchart of information processing according to modification 1. FIG. 8 is a detailed flowchart of acquiring job applicant information in Modification 1.

The process in FIG. 7 may be started, for example, by the client device 10 accessing a human resource matching service and receiving an instruction from a user (for example, the job applicant himself/herself) to start creating resume information of the job applicant.

As shown in FIG. 7, the server 30 acquires job offer information (S230).
Specifically, the server 30 receives target job offer information or information that can identify the target job offer information from the client device 10. The server 30 acquires target job offer information based on the received information. Note that the acquisition of job offer information (S230) can be omitted, and in this case, the server 30 uses model input information that is not based on the target job offer information in the acquisition of resume information (S132).
As a first example, the user inputs job information from a company in which he/she is interested into an object that accepts job information placed on the UI screen of the human resource matching service displayed on the display 21 of the client device 10. . The client device 10 transmits the input contents to this object to the server 30 as target job offer 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 human resource matching service displayed on the display 21 of the client device 10. The client device 10 sends information identifying the specified job information (for example, a job ID that identifies a job corresponding to the specified job information, or a URL where the specified job information can be viewed) to the target job information. The information is sent to the server 30 as identifiable information.

The target job offer information may be any of the following, for example.
・Job information for which the user has been recommended as a candidate for employment ・Job information for which the job seeker has applied or plans to apply ・The user selects or reacts to the job information that can be viewed on the human resources matching service (for example, job postings you liked, commented on, or tagged, etc.)

After step S230, the server 30 acquires job applicant information (S231).
Specifically, the server 30 receives from the client device 10 target job applicant information regarding a specific job applicant or information that allows the target job applicant information to be specified. The server 30 acquires target job applicant information based on the received information. As an example, the server 30 executes the process shown in FIG.

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 one or more questions associated with the item being processed. As an example, server 30 may randomly select any of the questions associated with the item being processed.

After step S2310, the server 30 outputs the question (S2311).
Specifically, the server 30 transmits the question (question text) selected in step S2310 to the client device 10. Note that when outputting a question (S2311) after step S2315, which will be described later, the server 30 transmits a question with a changed expression to the client device 10.
The client device 10 displays the received question on the display 21. The client device 10 receives answers to questions from the user and sends the answers to the server 30.

After step S2311, the server 30 executes response acquisition (S2312).
Specifically, the server 30 receives the answer to the question output in step S2311 from the client device 10.

After step S2312, the server 30 determines the appropriateness of the answer (S2313).
Specifically, the server 30 determines whether the answer obtained in step S2312 is appropriate for the item being processed. As an example, the server 30 generates an instruction sentence that requests the natural language model to determine whether the answer obtained in step S2312 is appropriate for the item being processed, and inputs it to the natural language model. . The server 30 determines the appropriateness of the answer obtained in step S2312 based on the response sentence generated by the natural language model.

If the answer is not determined to be appropriate in step S2313, the server 30 changes the question expression (S2315).
Specifically, the server 30 changes the expression of the question selected in step S2310 regarding the item being processed in order to ask the user again about the question. As an example, the server 30 obtains a reworded question by inputting model input information based on the question into a natural language model. For example, the server 30 may change the question "Please tell me about the outline of your most recent project" to the question "I'm sorry, but I couldn't get an appropriate answer, so please tell me again about the outline of your most recent project." After step S231, the server 30 re-executes the output of the question (S2311). This allows the user to be presented with a question worded differently regarding the item being processed.

If the answer is determined to be appropriate in step S2313, and the question and answer session for all items has not been completed, the server 30 selects the next item (S2314).
Specifically, the server 30 acquires the answer determined to be appropriate as job applicant information regarding the item being processed. Then, the server 30 selects any of the items for which the Q&A has not been completed as the next processing item. After step S2314, the server 30 re-executes question selection (S2310). This makes it possible to present questions to the user regarding items for which question-and-answer questions have not yet been completed.

If it is determined in step S2313 that the answer is appropriate and the question-and-answer session for all items has been completed, the server 30 ends the process of FIG. 8.

Furthermore, the server 30 may use job applicant information obtained by a method different from the process of FIG. 8 as part of the target job applicant information.
As a first example, a user inputs his or her own job applicant information into an object that accepts job applicant information and is displayed on the display 21 of the client device 10 and is placed on the UI screen of the human resources matching service. The client device 10 transmits the input contents to this object to the server 30 as part of the target job applicant information.
As a second example, the user specifies his or her registered job applicant information on the UI screen of the human resource matching service displayed on the display 21 of the client device 10. The client device 10 can identify part of the target job applicant information by using information that identifies the specified job applicant information (for example, a user ID that identifies the user or a URL that allows viewing the specified job applicant information). The information is sent to the server 30 as information.

After step S231, the server 30 executes acquisition of resume information (S132) to output of resume information (S133), similarly to the present embodiment.

(5-1-3) Summary As explained above, the server 30 of Modification Example 1 outputs questions to job seekers regarding each of one or more items, receives answers to the questions, and responds to the answers. Job applicant information may be acquired based on the information. Thereby, the server 30 can provide the job seeker with his or her own resume information without having the job seeker create the resume text itself. In other words, the job seeker can obtain his or her own resume information while at least reducing the burden of creating a resume on the job seeker.

At least one question may be associated with each of the one or more items. The server 30 causes the natural language model to determine whether the answer to the question is appropriate, and if it is determined that the answer to the question regarding any item is inappropriate, changes the expression of the question associated with the item. It may also be output to job seekers. As a result, even if the job seeker misunderstands the purpose of the question and gives an inappropriate answer, the question can be re-presented in a different way, increasing the possibility of obtaining an appropriate answer.

When a plurality of questions are associated with a first item included in one or more items, the server 30 randomly selects one of the plurality of questions associated with the first item and asks the job applicant. You can also output it. This disperses the questions presented to job seekers regarding each item. In other words, even if some questions are not worded appropriately, such as misleading the user, the frequency with which the question is presented will not be extremely high, so the question will be presented frequently. can alleviate the negative effects of

The server 30 causes the natural language model to determine whether or not the answer to the question is appropriate, and if the answer to the question output regarding any item is determined to be appropriate, the server 30 uses the answer to apply for a job application regarding the item. It may also be acquired as personal information. Thereby, the quality of job applicant information can be improved, and as a result, the quality of resume information can be improved.

The target job information may be job information specified by the job seeker. This makes it possible to provide resume information that takes into account job information that is of interest to job seekers.

Note that the information processing of Modification 1 can be combined with the information processing of this embodiment as appropriate. For example, similar to the information processing in Modification 1, using target job offer information obtained through interaction between a job seeker and a natural language model, similar to the information processing in this embodiment, the information processing information is sent to the recruiting company's hiring manager. Resume information suitable for a specific job offer from a recruiting company may be obtained and provided.

(6) Other Modifications The storage device 11 may be connected to the client device 10 via the network NW. Display 21 may be built into client device 10 . The storage device 31 may be connected to the server 30 via the network NW.

Each step of the above information processing can be executed by either the client device 10 or the server 30. Further, in the above description, an example was shown in which each step is executed in a specific order in information processing, but the execution order of each step is not limited to the example described as long as there is no dependency relationship.

In the above explanation, an example was shown in which resume information of a job applicant is acquired using a natural language model. This natural language model or another natural language model may be used to obtain a job applicant's catchphrase. Catchphrases contain less text than resume information and express the characteristics of a job seeker in concise terms. The server 30 may output a catchphrase (provide it to the user) instead of the resume information, or may output the catchphrase together with the resume information. By providing a catchphrase created in this way, a recruiting company's hiring manager can streamline the process of screening job applicant information, and job seekers can use it as a self-promotion material.
Specifically, the server 30 inputs model input information based on the resume information acquired in step S132 into the natural language model, thereby acquiring the job applicant's catchphrase (text) generated by the natural language model. Good too. As an example, the server 30 generates text based on resume information as model input information. The text may correspond to instructions for the natural language model. Furthermore, the model input information can include information corresponding to constraints regarding the aspect (for example, output format) of the catchphrase (that is, the response sentence generated by the natural language model).
For example, the constraint may be at least one of the following.
・Number of catchphrases to be generated ・Constrictions regarding matters to be followed when generating a catchphrase ・Constrictions regarding matters not to be followed when generating a catchphrase Constraints regarding matters to be followed when generating a catchphrase include, for example, at least one of the following: can be included.
・Approximate, upper or lower limit for the number of characters in a catchphrase ・Using formal expressions in a catchphrase ・Using expressions that are expected to give a specific impression to the reader of the catchphrase Items that should not be followed (to be prohibited) when generating a catchphrase For example, the constraint conditions may include at least one of the following.
・Use a catchphrase as a sentence ・Use a respectful attitude in a catchphrase ・Use expressions that are offensive to humans in a catchphrase ・Include in a catchphrase an explanation of why the catchphrase was chosen

The job applicant information may include information accumulated in the external system when the job applicant uses the external system. In this case, the server 30 may acquire job applicant information from an external system in acquiring job applicant information (S131) or acquiring job applicant information (S231). As a result, it is possible to augment the job seeker information that can be obtained without placing an input burden on the job seeker, and to provide higher quality resume information.
Specifically, the server 30 uses the job applicant's account information (for example, account name, login information, or a combination thereof) in a service provided by an external system (hereinafter referred to as "external service") to Job applicant information may be obtained from the system. The server 30 may acquire job applicant information using an API (Application Programming Interface) of an external service, or may acquire job applicant information by crawling a web page of an external service. The server 30 may obtain information regarding content posted by the job seeker, log information representing the job seeker's activities in the issue management service, or information regarding the profile registered by the job seeker with an external service. External services may include, but are not limited to, for example, Qiita(R), Zenn(R), LinkedIn(R), note(R), Slide Share, or Speaker Deck.

The server 30 may search for job information recommended to job seekers based on the acquired catchphrase or resume information, and output the searched job information. This can increase the matching rate between job seekers and hiring companies.
Specifically, the server 30 performs matching processing between catchphrases or resume information and job information, and outputs a predetermined number of job information selected in descending order of score or job information whose score exceeds a threshold (job seekers ) can be done.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited to the above embodiments. Moreover, various improvements and changes can be made to the embodiments described above without departing from the spirit of the present invention. Furthermore, the above embodiments and modifications can be combined.

(7) Additional Notes The matters explained in the embodiment and the modified example are added below.

(Additional note 1)
computer (30),
means for acquiring job applicant information regarding job seekers (S131, S231);
means for acquiring job applicant resume information generated by the natural language model by inputting first model input information based on job applicant information into the natural language model (S132);
means for outputting resume information (S133);
A program that functions as

(Additional note 2)
The job applicant information includes information regarding at least one of the job applicant's attributes, background, characteristics, or intentions;
The program described in Appendix 1.

(Additional note 3)
Job applicant information includes information regarding what job seekers are looking for in their next job.
The program described in Appendix 1.

(Additional note 4)
The first model input information is further based on the specific job information.
The program described in Appendix 1.

(Appendix 5)
further causing the computer 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 job seekers is to input first model input information based on job seeker information and specific job information into a natural language model, and to obtain resume information of job seekers generated by the natural language model. get information,
The output means presents resume information to the user.
The program described in Appendix 4.

(Appendix 6)
A job applicant is a person who has been recommended for a specific job posting;
The program described in Appendix 4.

(Appendix 7)
A job applicant is a person who has applied for specific job information.
The program described in Appendix 4.

(Appendix 8)
The specific job information includes at least one of information regarding the type of job to be recruited or information regarding the requirements for the personality sought by the recruiting company.
The program described in Appendix 4.

(Appendix 9)
The specific job information is the job information specified by the job seeker;
The program described in Appendix 4.

(Appendix 10)
The means for acquiring job applicant information (S231) outputs questions to the job applicant regarding each of one or more items, receives answers to the questions, and acquires job applicant information based on the answers.
The program described in Appendix 1.

(Appendix 11)
at least one question is associated with each of the one or more items;
The means for acquiring job applicant information uses a natural language model to determine whether or not an answer to a question is appropriate, and if the answer to a question regarding any item is determined to be inappropriate, it is associated with that item. Change the wording of the question and output it to job seekers.
The program described in Appendix 10.

(Appendix 12)
When a plurality of questions are associated with a first item included in one or more items, the means for acquiring job applicant information randomly selects one of the plurality of questions associated with the first item. output to job seekers,
The program described in Appendix 11.

(Appendix 13)
The means for acquiring job applicant information is to have a natural language model determine whether the answer to the question is appropriate or not, and if the answer to the question output regarding any item is determined to be appropriate, the corresponding answer obtain as job applicant information regarding the item,
The program described in Appendix 10.

(Appendix 14)
The first model input information is further based on information that constrains the form of resume information.
The program described in Appendix 1.

(Appendix 15)
Job applicant information includes information accumulated in external systems when job seekers use the external systems.
The program described in Appendix 1.

(Appendix 16)
computer,
means for inputting second model input information based on resume information into a natural language model to obtain a job applicant's catchphrase generated by the natural language model;
A means of outputting a catchphrase,
function as
A catchphrase has less text than resume information.
The program described in Appendix 1.

(Appendix 17)
A natural language model is an interactive large-scale language model,
The first model input information is an instruction sentence including the job applicant information,
The program described in Appendix 1.

(Appendix 18)
The computer (30)
a step of acquiring job applicant information regarding the job applicant (S131, S231);
inputting first model input information based on the job applicant information into the natural language model to obtain resume information of the job applicant generated by the natural language model (S132);
A method of performing the steps of outputting resume information (S133).

(Appendix 19)
Means for acquiring job applicant information regarding a job applicant (S131, S231);
means for acquiring job applicant resume information generated by the natural language model by inputting first model input information based on job applicant information into the natural language model (S132);
An information processing device comprising: means (S133) for outputting resume information.

(Additional note 20)
A system (1) comprising a first information processing device (30) and a second information processing device (10),
The first information processing device is
Means for acquiring job applicant information regarding a job applicant (S131, S231);
means for acquiring job applicant resume information generated by the natural language model by inputting first model input information based on job applicant information into the natural language model (S132);
means (S133) for outputting resume information to a second information processing device;
system.

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 (19)

computer,
means for obtaining job applicant information regarding the job applicant and including information regarding the work history of the job applicant ;
means for obtaining job information regarding job openings by companies;
By inputting the first model input information based on the job applicant information and the job offer information into a natural language model, a description of at least the job applicant's work history that is generated by the natural language model and that is related to the job applicant's work history. means for acquiring resume information of the job applicant including descriptions regarding the work history of the job applicant, the amount of description for each career being adjusted based on the first model input information;
means for outputting the resume information;
A program that functions as The job applicant information includes information regarding at least one of the job applicant's attributes, background, characteristics, or intentions;
The program according to claim 1. The job applicant information includes information regarding what the job applicant is looking for in the next job.
The program according to claim 1. further causing the computer to function as a means for identifying specific job information from job information of a company to which the user belongs,
The means for acquiring the job applicant's resume information is configured to input the first model input information based on the job applicant information and the specific job offer information into the natural language model, thereby obtaining resume information generated by the natural language model. the job seeker's resume information,
The outputting means presents the resume information to the user,
The program according to claim 1 . the job applicant is a person recommended for the job information;
The program according to claim 1 . The job seeker is a person who applied for the job information;
The program according to claim 1 . The job information includes at least one of information regarding the type of job to be recruited, and information regarding the requirements for the personality sought by the recruiting company.
The program according to claim 1 . The job information is job information specified by the job seeker;
The program according to claim 1 . The means for acquiring job applicant information outputs questions to the job applicant regarding each of one or more items, receives answers to the questions, and acquires the job applicant information based on the answers.
The program according to claim 1. at least one question is associated with each of the one or more items,
The means for acquiring job applicant information causes the natural language model to determine whether or not the answer to the question is appropriate, and if the answer to the question regarding any item is determined to be inappropriate, the means for acquiring the job applicant information changing the wording of the question regarding and outputting it to the job applicant;
The program according to claim 9 . computer,
means for obtaining job applicant information regarding a job applicant;
means for acquiring resume information of the job applicant generated by the natural language model by inputting first model input information based on the job applicant information into the natural language model;
means for outputting the resume information;
function as
The means for acquiring job applicant information outputs questions to the job applicant regarding each of one or more items, receives answers to the questions, and acquires the job applicant information based on the answers,
at least one question is associated with each of the one or more items,
The means for acquiring job applicant information causes the natural language model to determine whether or not the answer to the question is appropriate, and if the answer to the question regarding any item is determined to be inappropriate, the means for acquiring the job applicant information change the wording of the question and output it to the job seeker,
When a plurality of questions are associated with a first item included in the one or more items, the means for acquiring job applicant information randomly selects one of the plurality of questions associated with the first item. Select and output to the job seeker,
program. The means for acquiring job applicant information causes the natural language model to determine whether or not the answer to the question is appropriate, and when it is determined that the answer to the question output regarding any item is appropriate; , obtaining the answer as the job applicant information regarding the item;
The program according to claim 9 . The first model input information is further based on information that constrains the form of the resume information.
The program according to claim 1. The job applicant information includes information accumulated in the external system by the job applicant using the external system.
The program according to claim 1. computer,
means for obtaining job applicant information regarding a job applicant;
means for acquiring resume information of the job applicant generated by the natural language model by inputting first model input information based on the job applicant information into the natural language model;
means for outputting the resume information;
means for acquiring a catchphrase of the job applicant generated by the natural language model by inputting second model input information based on the resume information into the natural language model;
means for outputting the catchphrase;
function as
The catchphrase has a smaller amount of text than the resume information,
program. The natural language model is an interactive large-scale language model,
The first model input information is an instruction sentence including the job applicant information,
The program according to claim 1. The computer is
obtaining job applicant information regarding the job applicant and including information regarding the work history of the job applicant ;
obtaining job information regarding job openings by the company;
By inputting the first model input information based on the job applicant information and the job offer information into a natural language model, a description of at least the job applicant's work history that is generated by the natural language model and that is related to the job applicant's work history. acquiring resume information of the job applicant including descriptions regarding the job applicant's work history, the amount of description for each history being adjusted based on the first model input information;
A method comprising: outputting the resume information. means for acquiring job applicant information regarding the job applicant and including information regarding the work history of the job applicant ;
a means for obtaining job information regarding job openings by a company;
By inputting the first model input information based on the job applicant information and the job offer information into a natural language model, a description of at least the job applicant's work history that is generated by the natural language model and that is related to the job applicant's work history. means for acquiring resume information of the job applicant including descriptions regarding the work history of the job applicant, the amount of description for each career being adjusted based on the first model input information;
An information processing device comprising: means for outputting the resume information. A system comprising a first information processing device and a second information processing device,
The first information processing device includes:
means for acquiring job applicant information regarding the job applicant and including information regarding the work history of the job applicant ;
a means for obtaining job information regarding job openings by a company;
By inputting the first model input information based on the job applicant information and the job offer information into a natural language model, a description of at least the job applicant's work history that is generated by the natural language model and that is related to the job applicant's work history. means for acquiring resume information of the job applicant including descriptions regarding the work history of the job applicant, the amount of description for each career being adjusted based on the first model input information;
and means for outputting the resume information to the second information processing device.
system.