Job Seeker Support System

Abstract

We provide a job seeker support system that helps you create a resume (work history) that matches the job information you are applying for. [Solution] The job seeker support system 10 comprises a resume input unit that acquires resumes created by job seekers, a resume analysis unit that uses learning model 1 to extract components contained in the resume and map the components item by item to generate a resume sheet, a resume output unit that compares the resume sheet with the resume model and extracts missing items that are missing from the resume, a resume update unit that updates the resume sheet based on information on missing items obtained by interviewing the job seeker, a job information input unit that acquires job application information, a job information analysis unit that uses learning model 2 to extract components contained in job application information and map the components item by item to generate a job sheet, and an update content output unit that generates an updated sample optimized according to the job application information based on the job sheet and resume sheet.

Description

[Technical Field]

[0001] The present invention relates to a job seeker support system that supports job seekers in creating resumes (work histories) that match job application information. [Background technology]

[0002] Various matching methods have been proposed for intermediary sites that support job seekers' job hunting and career change activities and recruiting activities of companies seeking to hire. For example, Patent Document 1 discloses a matching device that includes a selection criteria database that registers document screening criteria for each job offer, a selection result history storage means that records the history of document screening results for applicants who have previously applied for each job offer, and a determination means that determines the likelihood that a job seeker will pass the document screening, and mentions that the device can determine the likelihood that a job seeker will pass the document screening for each job offer and provide the job seeker with the likelihood of passing the document screening for each job offer in advance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2010-026817 Summary of the Invention [Problem to be solved by the invention]

[0004] When job seekers are looking for a job, they are required to create a resume (career history) that lists information about their work history and skills. However, it is not easy for job seekers to create a resume that matches the job information they are applying for, that is, a resume that is likely to clear the document screening criteria, and this takes a lot of time.

[0005] An object of the present invention is to provide a job seeker support system that supports job seekers in creating resumes (work histories) that match the information on job applications they are applying for. [Means for solving the problem]

[0006] In order to achieve the above object, the job seeker support system according to the first invention comprises: Resumes tailored to the job applicant's job application of A job seeker support system that supports the creation of a learning model storage unit that stores a learning model 1 constructed so as to be able to decompose and extract components included in the resume; a resume input unit that acquires the resume created by the job seeker; a resume analysis unit that uses the learning model 1 to decompose and extract components included in the resume acquired by the resume input unit, and maps the components for each item to generate a resume sheet; a resume output unit that uses a resume model that is predefined as items required for the resume, compares the items included in the resume sheet generated by the resume analysis unit with the items defined in the resume model, and checks for and extracts missing items that are missing from the resume; a resume update unit that updates the resume sheet based on information obtained by interviewing the job seeker about the missing items; Equipped with The learning model 1 is characterized in that it is constructed so that it can extract the components of a resume by item by learning to break down the components contained in multiple resumes of various formats.

[0007] According to the first invention, by using the learning model 1, it becomes possible to accurately and efficiently examine and extract the missing items that are missing from the resume created by the job seeker, thereby making it possible to provide the job seeker with appropriate advice. Furthermore, the job seeker can accurately fill in the missing items in the resume, and can create a resume that is more likely to meet the document screening criteria.

[0010] No. 2 The job seeker support system according to the invention is the first Clearly Leave, The learning model storage unit stores a learning model 2 constructed to be able to decompose and extract components contained in the job application information, and a job information input unit for acquiring job information that a job seeker has decided to apply for; A job information analysis unit that uses the learning model 2 to decompose and extract components contained in the job application information acquired by the job information input unit, and maps the components by item to generate a job sheet; By comparing the job offer sheet with the resume sheet, elements missing from the resume are extracted. Created in bullet point format an update content output unit that outputs a resume update proposal; Equipped with The learning model 2 is characterized in that it is constructed so that it can extract the components of multiple job information items in various formats by learning to decompose the components contained in the job information items.

[0011] No. 2 According to the invention, by utilizing the learning model 2, it is possible to accurately and efficiently extract elements that are missing from the resume created by the job seeker based on the job information that the job seeker has decided to apply for, and output a resume update proposal, thereby making it possible to provide the job seeker with appropriate advice.

[0012] No. 3 The job seeker support system according to the invention is 2 In the invention, The update content output unit The content and order of the resume are optimized based on the criteria including the must-have conditions and want-to-have conditions included in the job information that the job seeker has decided on. It is characterized by having a means for generating an updated sample (model resume).

[0013] No. 3According to the invention, by using the learning model 2, it is possible to generate an updated sample with the resume content optimized according to the job information selected by the job seeker, and the job seeker can use the updated sample as a reference to create a resume that is more likely to meet the document screening criteria. [Effects of the Invention]

[0014] According to the present invention, when a job seeker creates a resume (work history) that matches the job information for which he or she is applying, it becomes possible to create a resume that is efficient and has a high probability of meeting the document screening criteria. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a functional configuration diagram showing an example of a functional configuration of a job seeker support system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a flowchart illustrating an example of a processing procedure executed in the job seeker support system according to the embodiment of the present invention. [Figure 3] FIG. 2 is a flowchart illustrating an example of a processing procedure executed in the job seeker support system according to the embodiment of the present invention. [Figure 4A] 1 is a table showing an example of proposed items obtained by breaking down resume components in the job seeker support system according to an embodiment of the present invention. [Figure 4B] 1 is a table showing an example of proposed items obtained by breaking down resume components in the job seeker support system according to an embodiment of the present invention. [Figure 5] 10 is a table showing an example of proposed items obtained by breaking down job offer components in the job seeker support system according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0016] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings. However, the present invention is not limited to the following embodiments.

[0017] FIG. 1 is a functional configuration diagram showing an example of the functional configuration of a job seeker support system according to an embodiment of the present invention. As shown in FIG. 1, job seeker support system 10 includes resume input unit 11, resume analysis unit 12, resume output unit 13, resume update unit 14, job information input unit 15, job information analysis unit 16, update content output unit 17, and learning model storage unit 18. Learning model storage unit 18 stores learning model 1 and learning model 2, and is configured to support job seekers in creating resumes (work histories) tailored to the job information they are applying for. While learning model 1 and learning model 2 are depicted as separate components in FIG. 1, this is not limiting, and learning model 1 and learning model 2 may be combined into a single component.

[0018] Here, the job seeker support system 10 is a general computer device, and includes, for example, a processing unit (CPU), a main memory device (RAM), an auxiliary memory device such as a HDD, SSD, or flash memory, an input device such as a keyboard, mouse, or touch panel, an output device such as a display or speaker, a communication device for communicating with external devices, etc. Furthermore, a smartphone, a tablet terminal, a PC (Personal Computer), etc. can also be used as the computer device.

[0019] The resume input unit 11 acquires a resume (work history) in which a job seeker writes down information such as his or her work history and skills.

[0020] The resume analysis unit 12 uses the learning model 1 to decompose and extract the components contained in the resume acquired by the resume input unit 11, and generates a resume sheet by mapping the components for each item.

[0021] Here, learning model 1 is constructed so that it can extract the components of multiple resumes of various formats by training it to decompose the components contained in the resumes.

[0022] The resume output unit 13 uses a resume model predefined as items required for the resume to compare the items included in the resume sheet generated by the resume analysis unit 12 with the items defined in the resume model, and checks for and extracts any missing items that are missing from the resume. Here, the resume model is defined as, for example, a general-purpose ideal resume, and is updated as needed.

[0023] This makes it possible to use learning model 1 to accurately and efficiently examine and extract missing items from the resume created by the job seeker, thereby providing the job seeker with appropriate advice.

[0024] The resume update unit 14 updates the resume sheet based on information obtained by interviewing the job seeker, for example, for each of the missing items extracted by the resume output unit 13. In other words, a mechanism is provided for updating the resume sheet for missing items that are missing from the resume created by the job seeker.

[0025] This allows the job seeker to accurately and efficiently fill in the missing items in the resume, and enables the job seeker to create a resume that is highly likely to meet the document screening criteria.

[0026] The job information input unit 15 acquires the job information that the job seeker has decided to apply for.

[0027] The job information analysis unit 16 uses the learning model 2 to decompose and extract the components contained in the job information acquired by the job information input unit 15, and maps the components by item to generate a job sheet.

[0028] Here, learning model 2 is constructed so that it can extract the components of multiple job postings in various formats by learning to decompose the components contained in the job postings.

[0029] The update content output unit 17 has a means for comparing the job offer sheet with the resume sheet, extracting elements missing from the resume, and outputting a resume update proposal. Here, the resume update proposal is, for example, a list of items that should be updated in the resume. This provides a mechanism for presenting a resume update proposal according to the job information applied for by the job seeker.

[0030] This makes it possible to use learning model 2 to accurately and efficiently examine and extract elements that are missing from the resume prepared by the job seeker based on the job information that the job seeker has decided to apply for, thereby making it possible to provide the job seeker with appropriate advice.

[0031] Furthermore, the updated content output unit 17 generates an updated sample (model work history) in which the resume content is optimized according to the job application information based on the job offer sheet and the resume sheet. That is, by taking into consideration the must conditions and want conditions, etc. included in the job application information determined by the job seeker, the content and order to be written in the resume are optimized, thereby providing a mechanism for generating an updated sample resume with a high probability of passing the document screening.

[0032] This makes it possible to use learning model 2 to generate an updated sample that optimizes the content and order to be written in the resume based on the job information selected by the job seeker, and the job seeker can use this updated sample as a reference to create a resume that is more likely to meet the document screening criteria.

[0033] Next, the processes executed by this system will be described using the flowcharts shown in Figures 2 and 3. Figures 2 and 3 are flowcharts showing an example of the processing procedure executed in the job seeker support system according to the embodiment of the present invention.

[0034] <Step S11> Job seekers obtain a resume (work history) that lists information about their work history, skills, etc.

[0035] <Step S12> Using learning model 1, the components contained in the resume obtained in step S11 are decomposed and extracted, and the components are mapped for each item to generate a resume sheet.

[0036] Here, learning model 1 is constructed so that it can extract the components of multiple resumes of various formats by training it to decompose the components contained in the resumes.

[0037] Figures 4A and 4B show examples of proposed items broken down into resume components. These proposed items are predefined as a resume model, with the items required for the resume, and a resume sheet is generated based on these proposed items. If there are any missing items in the resume created by the job seeker, for example, the corresponding items are left blank on the resume sheet. Furthermore, these proposed items are designed to be updated as needed.

[0038] <Step S13> Using a resume model that has been predefined as the items required for the resume, the items included in the resume sheet generated in step S12 are compared with the items defined in the resume model to check and extract missing items that are missing from the resume created by the job seeker. Specifically, for example, items that are left blank on the resume sheet are extracted as missing items.

[0039] This makes it possible to use learning model 1 to accurately and efficiently examine and extract missing items from resumes created by job seekers, thereby enabling the provision of appropriate advice to job seekers.

[0040] <Step S14> For the missing items extracted in step S13, information obtained by interviewing the job seeker for each item is added to the resume sheet.

[0041] In other words, by providing a mechanism for updating the resume sheet to fill in any missing items that are missing from the resume created by the job seeker, the job seeker can accurately and efficiently fill in the missing items in the resume, and can create a resume that is more likely to meet the document screening criteria.

[0042] <Step S21> Next, in step S14, the resume sheet is updated, and then the job information for which the job seeker has decided to apply is acquired.

[0043] <Step S22> Using learning model 2, the components contained in the job application information acquired in step S21 are decomposed and extracted, and the components are mapped for each item to generate a job sheet.

[0044] Here, learning model 2 is constructed so that it can extract the components of multiple job postings in various formats by learning to decompose the components contained in the job postings.

[0045] Figure 5 shows an example of proposed items broken down into job components. These proposed items are predefined as general items for the job application information, and a job sheet is generated based on these proposed items. If there are any missing items in the job application information, the corresponding items are left blank in the job sheet, for example. Furthermore, these proposed items are designed to be updated as needed.

[0046] <Step S23> The job offer sheet generated in step S22 is compared with the resume sheet updated in step S14, and elements missing from the resume are extracted and a resume update proposal is output. Here, the resume update proposal is, for example, a list of the content to be updated in the resume, output in text format.

[0047] Specifically, if the resume created by a job seeker does not match the job information they are applying for, for example, if the experience and skills are not expressed appropriately or the points they should emphasize are not clear, the system will present specific suggestions for updating the resume to match the job requirements.

[0048] In other words, by using learning model 2 to accurately and efficiently examine and extract elements that are missing from the resume created by the job seeker based on the job information that the job seeker has decided to apply for, and output a resume update proposal, it becomes possible to provide a system that presents resume update proposals in accordance with the job information that the job seeker has decided to apply for, and it becomes possible to provide accurate advice to the job seeker.

[0049] Furthermore, in this step, an updated sample (model work history) is generated in which the resume content is optimized in accordance with the job application information, based on the job application sheet generated in step S22 and the resume sheet updated in step S14. Here, the updated sample is, for example, resume content optimized in accordance with the job application information, output in text format.

[0050] Specifically, for example, based on the resume update proposal, the system takes into consideration the must-have and want-to-have conditions included in the job information selected by the job seeker, optimizes the content and order to be written in the resume, and generates an updated sample resume with a high probability of passing the document screening.

[0051] In other words, by using learning model 2 to generate an updated sample that optimizes the content and order to be written in the resume based on the job information selected by the job seeker, the job seeker can use the updated sample as a reference to create a resume that is more likely to meet the document screening criteria.

[0052] The above-described processing procedures (steps S11 to S14 and steps S21 to S23) may be realized as a method executed by a computer, or may be realized as a program to be executed by a computer.

[0053] As described above, the job seeker support system of the present invention enables job seekers to create resumes (work history) tailored to the job information they are applying for efficiently and with a high probability of meeting the document screening criteria. [Explanation of symbols]

[0054] 11...Resume input section 12...Resume Analysis Section 13...Resume output section 14…Resume Update Section 15...Job information input section 16…Recruitment information analysis department 17...Update content output section 18...Learning model memory section 21...Learning Model 1 22...Learning Model 2

Claims

1. A job seeker support system that supports job seekers in creating resumes tailored to job information they are applying for, a learning model storage unit that stores a learning model 1 constructed so as to be able to decompose and extract components included in the resume; a resume input unit that acquires the resume created by the job seeker; a resume analysis unit that uses the learning model 1 to decompose and extract components included in the resume acquired by the resume input unit, and maps the components for each item to generate a resume sheet; a resume output unit that uses a resume model that is predefined as items required for the resume, compares the items included in the resume sheet generated by the resume analysis unit with the items defined in the resume model, and checks for and extracts missing items that are missing from the resume; a resume update unit that updates the resume sheet based on information obtained by interviewing the job seeker about the missing items; Equipped with The learning model 1 is constructed to be able to extract the components of a resume item by item by learning to break down the components contained in a plurality of resumes having various formats.

2. 2. The job seeker support system according to claim 1, The learning model storage unit stores a learning model 2 constructed to be able to decompose and extract components contained in the job application information, and a job information input unit for acquiring job information that a job seeker has decided to apply for; A job information analysis unit that uses the learning model 2 to decompose and extract components contained in the job application information acquired by the job information input unit, and maps the components by item to generate a job sheet; an update content output unit that compares the job offer sheet with the resume sheet, extracts elements missing from the resume, and outputs a resume update proposal created in a bulleted format; Equipped with The learning model 2 is constructed to be able to extract the components of a plurality of job information items in various formats by learning to decompose the components contained in the job information, thereby enabling extraction of the components of the job information item by item.

3. 3. The job seeker support system according to claim 2, The job seeker support system is characterized in that the update content output unit has a means for generating an updated sample of the resume in which the contents and order of the resume sheet are optimized based on criteria including must-have conditions and want-have conditions included in the job application information determined by the job seeker.

Images