JP7482335B1 - Search support system, search support method and program - Google Patents

Abstract

[Problem] To provide a search support system etc. that can efficiently search for information on job seekers or job offers. [Solution] According to one aspect of the present invention, a search support system is provided. The search support system includes a processor. The processor is configured to execute the following steps: In the reception step, an input of at least one search word is received. In the setting step, related information including the relevance between the search word and each of a plurality of search fields is set for the search word based on reference information. The reference information includes the relationship between the search word and the related information, and the search field is the search target range in the registered information of job seekers or employers. In the search step, registered information including the search word is searched for for each of a plurality of search fields, and the display priority of the searched registered information is determined based on the relevance for each search field included in the related information. [Selected Figure] Figure 1

Description

The present invention relates to a search support system, a search support method, and a program.

As disclosed in Patent Document 1, a technology is known that searches for job seekers by inputting search words and search conditions.

Patent No. 7281024

When searching for job seekers or jobs, search accuracy can be improved by setting a search field for each search word that specifies the search range for job seeker or job posting information (for example, entering search words in an input box provided for each search field). However, this procedure makes entering search words cumbersome.

In consideration of the above circumstances, the present invention aims to provide a search support system that can efficiently search for information on job seekers or job openings.

According to one aspect of the present invention, a search support system is provided. The search support system includes a processor. The processor is configured to execute the following steps: In the reception step, an input of at least one search word is received. In the setting step, related information including the relevance between the search word and each of a plurality of search fields is set for the search word based on the reference information. The reference information includes the relationship between the search word and the related information, and the search field is the search target range in the registered information of the job seeker or employer. In the search step, registered information including the search word is searched for for each of the plurality of search fields, and a display priority of the searched registered information is determined based on the relevance for each search field included in the related information.

According to this embodiment, the relevance of the entered search word to the search field is set, and the display order of the registered information in the search results is adjusted based on this relevance. This allows employers or job seekers to efficiently search for registered information.

FIG. 1 is a configuration diagram showing a search support system 1. FIG. 2 is a block diagram showing the hardware configuration of the server device 10. FIG. 2 is a block diagram showing the hardware configuration of a recruiter terminal 20 and a job seeker terminal 30. 2 is a block diagram showing functions realized by the server device 10 (control unit 11), the recruiter terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31). FIG. FIG. 13 is a diagram showing an example of a search word input screen ID when a recruiter searches for a job seeker. FIG. 13 is a diagram showing an example of a related information table TB in which the degrees of relatedness are described. FIG. 2 is an activity diagram showing the flow of information processing (search processing for job seeker registration information by a recruiter) executed by the search support system 1.

The following describes embodiments of the present invention with reference to the drawings. The various features shown in the following embodiments can be combined with each other.

The program for implementing the software used in this embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so that it can be downloaded from an external server, or may be provided so that the program is started on an external computer and its functions are implemented on a client terminal (so-called cloud computing).

In this embodiment, a "unit" may also include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In addition, this embodiment handles various types of information, which may be represented, for example, by physical values of signal values representing voltage and current, high and low signal values as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations may be performed on a circuit in the broad sense.

In the broad sense, a circuit is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, and memory. In other words, it includes application specific integrated circuits (ASICs), programmable logic devices (e.g., simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)), etc.

1. Hardware Configuration This section describes the hardware configuration.

<Search Support System 1>
1 is a configuration diagram showing a search support system 1. The search support system 1 comprises a communication line 2, a server device 10, a plurality of recruiter terminals 20, and a plurality of job seeker terminals 30. The server device 10, the recruiter terminals 20, and the job seeker terminals 30 are configured to be able to communicate with each other via the communication line 2. The connection between the server device 10, the recruiter terminals 20, and the job seeker terminals 30 may be wired or wireless.

The search support system 1 constitutes part of a recruitment and job search system used by multiple recruiters (first recruiter U1 and second recruiter U2) and multiple job seekers (first job seeker U3 and third job seeker U4). The search support system 1 mainly searches for job seekers or job postings. In one embodiment, the search support system 1 is made up of one or more devices or components. These components are described below.

<Server device 10>
2 is a block diagram showing a hardware configuration of the server device 10. The server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected to each other inside the server device 10 via the communication bus 14.

<Control unit 11>
The control unit 11 processes and controls the overall operation related to the server device 10. The control unit 11 is, for example, a central processing unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading out a predetermined program stored in the storage unit 12. That is, information processing by software stored in the storage unit 12 can be specifically realized by the control unit 11, which is an example of hardware, and executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and may be implemented to have multiple control units 11 for each function. Also, a combination of these may be used.

<Storage unit 12>
The storage unit 12 stores various information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program calculations. The storage unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11. The storage unit 12 may also be an external storage device connected to the server device 10.

<Communication unit 13>
The communication unit 13 is preferably a wired communication means such as USB, IEEE 1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 3G/LTE/5G, BLUETOOTH (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

The server device 10 may be in an on-premise form or in a cloud form. As a cloud-based server device 10, for example, the above-mentioned functions and processes may be provided in the form of SaaS (Software as a Service) or cloud computing. In addition, the server device 10 may be a multi-computer including multiple computers, or may be a virtual machine virtually constructed by software.

<Employer terminal 20>
Fig. 3 is a block diagram showing the hardware configuration of the recruiter terminal 20 and the job seeker terminal 30. As shown in Fig. 3A, the recruiter terminal 20 comprises a control unit 21, a memory unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the memory unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected inside the recruiter terminal 20 via the communication bus 26. The explanation of the control unit 21, the memory unit 22, and the communication unit 23 is omitted here because it is the same as the explanation of each unit in the server device 10. Note that the recruiter terminal 20 may be a terminal operated by a human resources agency that communicates with job seekers on behalf of the recruiter.

<Input unit 24>
The input unit 24 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 may execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 24 may be included in the housing of the recruiter terminal 20, or may be attached externally. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input tap operations, swipe operations, and the like to the input unit 24. As the input unit 24, a switch button, a mouse, a track pad, a QWERTY keyboard, and the like can be adopted instead of a touch panel.

<Output unit 25>
The output unit 25 displays a screen of a graphical user interface (GUI) that can be operated by the user. The output unit 25 may be included in the housing of the recruiter terminal 20, or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are implemented by using different devices depending on the type of recruiter terminal 20.

<Job Seeker Terminal 30>
3B , the job seeker terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected inside the job seeker terminal 30 via the communication bus 36. Descriptions of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 will be omitted as they are similar to the descriptions of the respective units in the recruiter terminal 20.

2. Functional Configuration In this section, the functional configuration of the present embodiment will be described. Information processing by the software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (a processor included in the search support system 1).

Figure 4 is a block diagram showing the functions realized by the server device 10 (control unit 11), the employer terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

As shown in FIG. 4A, the server device 10 (control unit 11) includes a basic display control unit 111, a reception unit 112, a setting unit 113, a search unit 114, a reference information registration unit 115, an extraction unit 116, a reevaluation unit 117, and an artificial intelligence unit 120. As shown in FIG. 4B, the recruiter terminal 20 (control unit 21) includes a display unit 211 and an operation reception unit 212. As shown in FIG. 4C, the job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation reception unit 312.

<Basic display control unit 111>
The basic display control unit 111 is configured to display various information on the recruiter terminal 20 and the job seeker terminal 30. For example, the basic display control unit 111 displays a resume and curriculum vitae prepared by the job seeker, a job advertisement and scouting document prepared by the recruiter, etc. on the display unit 211 of the recruiter terminal 20 or the display unit 311 of the job seeker terminal 30.

Employers include organizations such as profit-making corporations (e.g., companies), non-profit organizations (e.g., cooperatives, foundations), and public organizations (e.g., local governments). Employers also include recruitment agencies that act as agents of organizations to mediate between job seekers and organizations. Recruitment agencies are also called headhunters or agents.

<Reception Unit 112>
The reception unit 112 is configured to receive input of at least one search word for searching for job seekers or job information from the recruiter terminal 20 or the job seeker terminal 30. Fig. 5 is a diagram showing an example of a search word input screen ID when a recruiter searches for a job seeker. The search word input screen ID includes a search word input field WF and an execute button B1.

The employer inputs any job seeker search word into the search word input field WF on the employer terminal 20. When the execute button B1 is input (pressed) with at least one job seeker search word input, the input job seeker search word is accepted by the reception unit 112. Also, as shown in FIG. 5, when multiple search words are input into the search word input field WF, the reception unit 112 accepts the input of multiple search words.

Similarly, when a job seeker searches for job information (e.g., a job posting), the job seeker inputs at least one job search term into the job seeker terminal 30, and the input job search term is accepted by the acceptance unit 112.

<Setting Unit 113>
The setting unit 113 is configured to set related information including the degree of relevance between the search word and each of the multiple search fields for the search word received by the receiving unit 112 based on the reference information. The reference information is information including the relationship between the search word and the related information. The search field is the search target range in the registered information of the job seeker or the employer.

The registration information of the job seeker to be searched (hereinafter, "job seeker registration information") is registered, for example, in a job seeker database stored in the memory unit 12 of the server device 10. The job seeker registration information includes the job seeker's resume, work history, and other profile information. A "resume" is a document that mainly describes the job seeker's profile, current situation, educational background, employment history, desired working conditions, etc., while a "work history" is also called a résumé, and is a document in which a job seeker conveys to an employer the job seeker's work history, experience, skills, qualifications, etc. related to his or her past work. The job seeker information may also include conditions such as the industry and job type desired by the job seeker.

The registration information of the employer to be searched (hereinafter referred to as "employer registration information") is registered, for example, in an employer database stored in the memory unit 12 of the server device 10. The employer registration information includes a job posting, organizational information, etc. The "job posting" includes information such as the type of job for which personnel are desired to be hired, the industry, the position, the job content, working conditions (annual salary, work location, etc.), application qualifications, and the employer's selling points.

The search field is one of the search conditions, and is an item for specifying the search target range (search category). The search target range of each search field is set in advance before executing a search. Examples of search fields for job seeker registration information or employer registration information include "address", "industry type", "job title", "department", "job content", "educational background", "language ability", "skill", "qualification", "award", and "company name". For example, in a search for the search field (search target range) for "address", only information categorized as "address" (with a label corresponding to the search field "address") among the information contained in the job seeker registration information and employer registration information is searched, and other information is not searched. Information (items) contained in the job seeker registration information and employer registration information are linked to search fields in advance. In addition, information contained in the job seeker registration information and employer registration information may be linked to multiple search fields. For example, "information regarding language ability" in the job seeker registration information is linked to multiple search fields such as "job content", "language ability", "skill", "qualification", and "award".

The relevance is a numerical representation of the degree of relevance between a search word and a search field. The relevance is set for each search word and for each of the multiple search fields. For example, it is set as a numerical value between 0 and 1. A combination of a search word and a search field with the maximum relevance (e.g., "1.0") means that the two are most relevant. A combination of a search word and a search field with the minimum relevance (e.g., "0") means that the two are less relevant or not relevant. For example, the search word "sales" is highly relevant to the search field "job type", so the relevance between "sales" and "job type" is set to "1.0". Furthermore, the search word "sales" is less relevant to the search field "company name", so the relevance between "sales" and "company name" is set to "0". Furthermore, the search word "sales" is relevant to a certain degree to the search field "job content", so the relevance between "sales" and "job content" is set to "0.5".

The relevance of each search word to multiple search fields is stored as reference information, for example, in the storage unit 12 of the server device 10. The reference information may be any information that defines the relationship between each individual search word and the relevance to multiple search fields, and typically, a table (database) that describes the relevance of each search word to each of multiple search fields can be used.

Figure 6 is a diagram showing an example of a related information table TB in which relevance is described. As shown in Figure 6, in the related information table TB, for each search word, the relevance to multiple search fields set in the job seeker registration information or employer registration information is described. The setting unit 113 searches the related information table TB for the search word received by the reception unit 112, and sets the related information defined in the related information table TB (relevance for each search field) for the search word. Note that the reference information (related information table TB) may be prepared separately for searching job seeker registration information and for searching employer registration information, or may be shared by both.

When referring to (searching for) a search word (hereinafter, "registered word") included in the reference information, the setting unit 113 may detect registered words that are similar to the search word (e.g., registered words that are synonyms, similar words, spelling variations, etc.) in addition to registered words that exactly match the search word received by the receiving unit 112, and set related information of the detected registered words as related information of the search word. For example, the setting unit 113 may set related information of the registered word "English", which is a synonym, for the search word "English".

The setting unit 113 may set related information for a search word, for example, by a related information setting model of the artificial intelligence unit 120. The related information setting model is, for example, a generative AI including a large-scale language model. The setting unit 113 inputs a search word, inputs a prompt including an instruction to set related information for the search word based on reference information (information defining related information for each search word) to the related information setting model, and causes the related information to be output from the related information setting model. Furthermore, the setting unit 113 may directly insert reference information (a combination of one or more search words and one or more pieces of related information corresponding to the search words) as a sample of input and output, in addition to the instruction to output related information and the search word, into the prompt input to the related information setting model.

For a search word not included in the reference information, the setting unit 113 sets related information in which the relevance levels for each of a plurality of search fields are all set to the same value. That is, if a registered word that matches or is similar to the search word received by the receiving unit 112 is not registered in the reference information (e.g., is not detected in the related information table TB), all relevance levels for the search word are set to a predetermined initial value. This makes it possible to display normal search results for a search word for which related information is not defined without causing an error. The initial value of the relevance level for a search word not registered in the reference information can be, for example, "1.0". In this case, the setting unit 113 sets the relevance level for all search fields to "1.0" as related information for the search word.

When the reception unit 112 receives multiple search words, the setting unit 113 sets related information for each of the multiple search words based on the reference information. For example, when "ABC Co., Ltd." and "sales" are input as search words, the setting unit 113 sets corresponding related information (relevance to the search field) for each of these search words.

<Search unit 114>
The search unit 114 is configured to search for job seeker registration information or employer registration information based on the search word received by the reception unit 112. Specifically, the search unit 114 searches for job seeker registration information or employer registration information that includes the search word for each of a plurality of search fields, and determines the display priority of the searched job seeker registration information or employer registration information based on the relevance of each search field included in the related information. That is, the search unit 114 displays job seeker registration information or employer registration information that is found by a search in a search field with a high relevance using a certain search word with priority over job seeker registration information or employer registration information that is found by a search in a search field with a low relevance using the same search word. Here, "prioritized display" includes displaying at the top of the list of search results (upper part of the list), highlighting other results, omitting other results, and the like.

Specifically, the search unit 114 assigns a score to the searched job seeker registration information or employer registration information according to the relevance of the search word to the search field containing the search word, and preferentially displays job seeker registration information or employer registration information with a high score. This makes it easier for job seeker registration information or employer registration information found in a highly relevant search field to be preferentially displayed, improving the search quality and speed of job seeker registration information or employer registration information.

The "score" may be, for example, the relevance itself or a numerical value proportional to the relevance. For example, if a job seeker is searched for using the search word "sales" as shown in FIG. 6, and job seeker registration information is detected in both the "job type" search field and the "job title" search field, a score of "1.0" is assigned to the job seeker registration information detected in "job type," and a score of "0.5" is assigned to the job seeker registration information detected in "job title." As a result, the job seeker registration information detected in "job title" is displayed with priority over the job seeker registration information detected in "job type."

The search unit 114 may also assign a higher score to the searched registration information the more search fields that contain the search word. "The number of search fields that contain the search word" refers to the number of search fields in which the corresponding job seeker registration information or employer registration information was found in a search using the search word. This makes it possible to preferentially display job seeker registration information or employer registration information that has a larger number of search fields that are hit.

For example, the search unit 114 may determine the priority of displaying job seeker registration information or employer registration information using a first score, which is the sum of the relevance of each hit search field, and a second score that is assigned according to the number of hit search fields. For example, for a certain search word, job seeker registration information or employer registration information that is hit in two search fields, a search field with a relevance of "0.5" and a search field with a relevance of "1.0", is assigned a first score of "1.5" and a second score of "2". For example, the search unit 114 may first determine the priority of job seeker registration information or employer registration information in descending order of second score, and if the second scores are the same, determine the priority by comparing the first scores.

The search unit 114 may not display, as a search result, job seeker registration information or employer registration information for which the search word hits only in search fields with a relevance level below a certain value (e.g., "0"). In addition, the search unit 114 may not perform a search using the search word in search fields with a relevance level below a certain value.

When the reception unit 112 receives multiple search words, the search unit 114 searches for job seeker registration information or employer registration information that includes the search words in each of the multiple search fields for each of the multiple search words, and determines the display priority of the searched job seeker registration information or employer registration information based on the relevance for each search field included in the related information for each of the multiple search words. This allows the display order of the registration information in the search results to be adjusted even when a search is performed using multiple search words, allowing employers or job seekers to efficiently search for registration information.

When a search is performed using multiple search words, the first score of the searched job seeker registration information or employer registration information is, for example, the sum of the first scores for each search word. Specifically, for example, when a search is performed using two search words, the first score of the job seeker registration information or employer registration information with a first score of "1.5" for the first search word and a first score of "0.5" for the second search word will be "2.0". Similarly, the second score is, for example, the sum of the second scores for each search word.

<Reference Information Registration Unit 115>
The reference information registration unit 115 is configured to generate related information for a search word not included in the reference information, and to register the search word and the related information in the reference information in association with each other. This makes it possible to perform a search with related information added to a newly used search word.

When a registered word that matches or is similar to the search word received by the reception unit 112 is not registered in the reference information (e.g., is not detected in the related information table TB), the reference information registration unit 115 adds related information to the search word. The search word to which related information has been added becomes a registered word in the reference information.

For example, when the receiving unit 112 receives a search word (hereinafter, "unregistered word") that is not included in the reference information (in other words, when the setting unit 113 sets the relevance of the search word to a predetermined initial value), the reference information registration unit 115 adds the unregistered word to the unregistered list. The reference information registration unit 115 periodically (for example, daily) adds related information to the unregistered word included in the unregistered list and registers it in the reference information as a registered word. The unregistered word registered in the reference information is deleted from the unregistered list.

The reference information registration unit 115 may also register the unregistered word in the reference information in real time at the time the unregistered word is acquired, without adding the unregistered word to the unregistered list. In this case, the setting unit 113 sets the related information registered by the reference information registration unit 115 to the search word that was an unregistered word when it was received by the receiving unit 112 (i.e., when it was input by the user). This prevents the setting unit 113 from setting the relevance of the unregistered word to a predetermined initial value.

Related information for unregistered words is generated, for example, by the related information generation model of the artificial intelligence unit 120. The reference information registration unit 115 inputs the search word (unregistered word) into the related information generation model, which is a learning model, and causes the related information generation model to output related information corresponding to the search word. This makes it possible to provide unregistered words with objective related information backed up by learning data.

The related information generation model is a learning model that is trained to receive a search word as input and output related information corresponding to the search word. In other words, the related information generation model is a learning model that is trained using the search word and the data of the related information corresponding to the search word as training data. The related information generation model may also be a generative AI including a large-scale language model. In this case, the reference information registration unit 115 receives the search word as input, inputs a prompt including an instruction to generate related information based on the search word to the related information generation model, and causes the related information generation model to output the related information. The reference information registration unit 115 may also input a prompt into the related information generation model that includes, for example, one or more search word samples and one or more corresponding related information samples as input and output samples in addition to the instruction to generate and output the related information and the search word.

<Extraction Unit 116>
The extraction unit 116 is configured to extract registered words for which related information needs to be adjusted from the reference information. Specifically, the storage unit 12 stores at least one of the search results of job seeker registration information or employer registration information by search words, and event occurrence results for job seekers or employers included in the search results. The extraction unit 116 extracts reevaluation target words for which at least one of the associated search results and event occurrence results does not satisfy a predetermined standard from the search words (registered words) included in the reference information. This makes it possible to grasp registered words for which related information needs to be adjusted to improve search efficiency, based on the search results and the event results for the searched job seekers or employers.

"Words to be reevaluated whose search results do not meet the predetermined criteria" are, for example, search words for which the number of hits for job seeker registration information or employer registration information is below a predetermined threshold. "Words to be reevaluated whose event occurrence results do not meet the predetermined criteria" are, for example, search words for which the number of events related to the searched job seeker or employer is below a predetermined threshold. "Events related to job seekers" include, for example, viewing job seeker registration information, sending a scout email to a job seeker, replying to a scout email, etc. "Events related to employers" include, for example, viewing employer registration information, applying for a job posting, etc. The memory unit 12 of the server device 10 stores a search log in which the search words, search results (searched job seeker registration information or employer registration information), and the occurrence status of events related to job seekers or employers are linked to each other.

The extraction unit 116 periodically (e.g., daily) extracts words to be re-evaluated from all registered words included in the reference information and adds them to the re-evaluation list. The words to be re-evaluated included in the re-evaluation list are periodically re-evaluated by the system administrator or the re-evaluation unit 117 described below. Words to be re-evaluated that have been re-evaluated are deleted from the re-evaluation list. When the system administrator re-evaluates, the relevant information for the words to be re-evaluated included in the reference information is rewritten by inputting it from a management terminal, etc.

<Reevaluation Unit 117>
The reevaluation unit 117 is configured to reevaluate the words to be reevaluated extracted by the extraction unit 116. Specifically, the reevaluation unit 117 inputs the words to be reevaluated into a reevaluation model, which is a learning model, causes the reevaluation model to output new related information associated with the words to be reevaluated, and registers the words to be reevaluated and the related information in the reference information in association with each other. In other words, the reevaluation unit 117 overwrites and rewrites the related information registered in the reference information with the new related information. This makes it possible to update the related information of registered words that require reevaluation. This improves the efficiency of searching registered information by employers or job seekers.

The reevaluation model is a learning model that is trained to input the reevaluation target word and output new related information corresponding to the reevaluation target word. In other words, the reevaluation model is a learning model that is trained using the reevaluation target word and the data of the related information corresponding to it as teacher data. The reevaluation model may also be a generation AI including a large-scale language model. In this case, the reevaluation unit 117 inputs the reevaluation target word, inputs a prompt including an instruction to generate related information based on the reevaluation target word to the reevaluation model, and causes the reevaluation model to output the related information. In addition, the reevaluation unit 117 may input, as input and output samples, a prompt into which, for example, one or more samples of the reevaluation target word and one or more samples of related information corresponding thereto are inserted, in addition to the instruction to generate and output the related information and the reevaluation target word. The new related information after reevaluation to be inserted as a sample may be generated by the reevaluation model, or may be reevaluated and input by a user such as an administrator of the search support system 1. In addition, a search result or an event occurrence result associated with the reevaluation target word may be inserted into the prompt to be input to the reevaluation model.

The related information generated and output by the re-evaluation model is different from the related information generated by, for example, a related information setting model and stored as reference information. The re-evaluation unit 117 may insert, into the prompt input to the re-evaluation model, an instruction to output related information (degree of relevance) different from the related information contained in the current reference information.

In addition, the learning data for the reevaluation model may be a combination of related information reevaluated by a user such as an administrator or by the learning model, and related information before reevaluation.

The re-evaluation model may be an associated information generation model that has been updated by additional learning (fine-tuning). That is, the re-evaluation unit 117 may update the associated information of the word to be re-evaluated by inputting the word to be re-evaluated into the latest associated information generation model.

<Artificial Intelligence Department 120>
The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

The artificial intelligence unit 120 may be an AI (Artificial Intelligence) equipped with a transformer including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, and GPT-3), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), etc., or a language model such as a recurrent neural network (RNN), and may include a generative AI.

The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data consists of a pair of input data for learning and output data (correct answer data). In addition, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used for a wide range of tasks.

The artificial intelligence unit 120 may be a general-purpose natural language processing learning model such as a large-scale language model (LLM) that has learned a huge amount of data as artificial intelligence. Such a general-purpose learning model includes a language model that can handle various tasks without fine tuning by one-shot learning, few-shot learning, etc. In addition, the general-purpose learning model may be configured to be capable of handling various tasks by zero-shot learning as well. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or a common general-purpose learning model.

The learning models included in the artificial intelligence unit 120 (learning models used in each functional unit, such as the related information generation model) are capable of additional learning. For example, each time a new search word is input, a search field is set, search results are obtained, etc., the artificial intelligence unit 120 may perform additional learning and fine-tune using these as new training data. This improves the accuracy of the degree of relevance included in the related information output from the learning model.

<Display section>
The display unit 211 of the recruiter terminal 20 and the display unit 311 of the job seeker terminal 30 each display a screen indicated by the screen data transmitted from the server device 10 .

<Operation reception section>
The operation acceptance unit 212 of the recruiting party terminal 20 accepts operations by a user (recruiter) who uses the recruiting party terminal 20. The operation acceptance unit 312 of the job seeker terminal 30 accepts operations by a user (job seeker) who uses the job seeker terminal 30.

3. Information Processing Method This section describes an information processing method of the server device 10. This information processing method is executed by a computer, with each unit of the server device 10 acting as each step.

This information processing method includes a receiving step of receiving input of at least one search word, a setting step of setting related information for the search word, including the relevance between the search word and each of a plurality of search fields, based on reference information, and a search step of searching for registered information including the search word for each of the plurality of search fields, and determining the display priority of the searched registered information based on the relevance for each search field included in the related information. The reference information includes the relationship between the search word and the related information, and the search field is the search target range in the registered information of job seekers or employers.

Figure 7 is an activity diagram showing the flow of information processing (search processing for job seeker registration information by an employer) executed by search support system 1. Below, the information processing is explained along with each activity in this activity diagram. Note that below, the search processing for job seeker registration information using the employer terminal 20 is explained, but the flow of the search processing for job seeker registration information using the job seeker terminal 30 is also similar.

The process of searching registered job seeker information by an employer begins with the employer inputting a search word. The employer inputs at least one search word into the employer terminal 20 (activity A101). The server device 10 accepts the input of the search word from the employer terminal 20 (activity A102). The server device 10 sets related information for the accepted search word based on the reference information (activity A103). Next, the server device 10 uses the search word to search registered job seeker information for each search field (activity A104). This provides search results for each search field (job seeker registration information hits).

After obtaining the search results, the server device 10 determines the display priority of the searched job seeker registration information based on the relevance of each search field included in the related information (activity A105). The server device 10 outputs the search results (hit job seeker registration information) together with the determined display priority information to the employer terminal 20 (activity A106). As a result, the job seeker registration information included in the search results is displayed in the order of display priority on the employer terminal 20 (activity A107).

4. Operation The operation of this embodiment can be summarized as follows. That is, the relevance of the input search word to the search field is set, and the display order of registered information in the search results is adjusted based on this relevance. Therefore, employers or job seekers do not need to input search words or set search conditions for each search field, and can efficiently search registered information.

The above describes an embodiment of the present invention, but the present invention is not limited to this and can be modified as appropriate without departing from the technical concept of the invention.

5. Others In the above embodiment, the server device 10 performs various storage and control, but multiple external devices may be used instead of the server device 10. That is, various information and programs may be distributed and stored in multiple external devices using block chain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the artificial intelligence unit 120, which is an external configuration, is configured to receive input from each functional unit of the server device 10 and return the instructed output to the server device 10.

The aspect of this embodiment is not limited to the search support system 1, and may be an information processing method or a program. The recruitment support method includes each step executed by the search support system 1. The program causes a computer to execute each step of the search support system 1.

The control unit 11 of the search support system 1 does not necessarily have to include the extraction unit 116 and the re-evaluation unit 117. In other words, the control unit 11 does not necessarily have to have a function for updating related information for search words. In addition, the control unit 11 does not necessarily have to include the reference information registration unit 115. For example, related information for unregistered words may be created and registered by input operations by a system administrator.

It may be provided in the following ways:

(1) A search support system comprising a processor, the processor being configured to execute the following steps: in a reception step, an input of at least one search word is received; in a setting step, related information including the relevance between the search word and each of a plurality of search fields is set for the search word based on reference information, the reference information including the relationship between the search word and the related information, the search fields being the search target range in the registered information of job seekers or employers; in a search step, the registered information including the search word is searched for for each of the plurality of search fields, and a display priority of the searched registered information is determined based on the relevance for each of the search fields included in the related information.

(2) In the search support system described in (1) above, the relevance is a numerical representation of the degree of relevance between the search word and the search field, and in the search step, the searched registered information is assigned a score according to the magnitude of the relevance of the search word to the search field in which the search word is included, and registered information with a high score is preferentially displayed.

(3) A search support system according to (2) above, in which, in the search step, the greater the number of search fields that contain the search word, the higher the score assigned to the searched registered information.

(4) In the search support system described in (2) or (3) above, in the setting step, the related information is set for the search words not included in the reference information, with the relevance levels for each of the multiple search fields all being set to the same value.

(5) In the search support system described in any one of (1) to (4) above, the processor is further configured to execute the following steps, and in the reference information registration step, the related information is generated for the search word not included in the reference information, and the search word and the related information are associated with each other and registered in the reference information.

(6) In the search support system described in (5) above, in the reference information registration step, the search word is input into a related information generation model, which is a learning model, and the related information is output from the related information generation model.

(7) In the search support system described in (6) above, in the reference information registration step, an instruction to generate the related information based on the search word is input to the related information generation model.

(8) In the search support system described in any one of (1) to (7) above, the processor is further configured to execute the following steps: in the storage step, the search results of the registered information by the search word and at least one of the event occurrence results for the job seeker or the employer included in the search result are stored; and in the extraction step, from among the search words included in the reference information, words to be reevaluated for which at least one of the associated search results and the associated event occurrence results do not satisfy a predetermined criterion are extracted.

(9) In the search support system described in (8) above, the processor is further configured to execute the following steps: in the reevaluation step, the word to be reevaluated is input into a reevaluation model, which is a learning model, and the reevaluation model is caused to output new related information associated with the word to be reevaluated, and the word to be reevaluated and the related information are associated with each other and registered in the reference information. A search support system.

(10) In the search support system described in (9) above, in the reevaluation step, an instruction to generate the related information based on the word to be reevaluated is input to the reevaluation model.

(11) A search support system according to any one of (1) to (10) above, wherein the receiving step receives input of a plurality of the search words, the setting step sets the related information for each of the plurality of the search words based on the reference information, and the searching step searches for the registered information containing the search word for each of the plurality of search fields for each of the plurality of the search words, and determines the display priority of the searched registered information based on the relevance for each of the search fields included in the related information for each of the plurality of the search words.

(12) A search support method comprising steps executed by a search support system described in any one of (1) to (11) above.

(13) A program that causes a computer to execute each step of the search support system described in any one of (1) to (11) above.
Of course, this is not the case.

Finally, various embodiments of the present disclosure have been described, but these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and modifications thereof are within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents as set forth in the claims.

1 : Search support system 2 : Communication line 10 : Server device 11 : Control unit 12 : Memory unit 13 : Communication unit 14 : Communication bus 20 : Recruiter terminal 21 : Control unit 22 : Memory unit 23 : Communication unit 24 : Input unit 25 : Output unit 26 : Communication bus 30 : Job seeker terminal 31 : Control unit 32 : Memory unit 33 : Communication unit 34 : Input unit 35 : Output unit 36 : Communication bus 111 : Basic display control unit 112 : Reception unit 113 : Setting unit 114 : Search unit 115 : Reference information registration unit 116 : Extraction unit 117 : Reevaluation unit 120 : Artificial intelligence unit 211 : Display unit 212 : Operation reception unit 311 : Display unit 312 : Operation reception unit

Claims (13)

A search support system, comprising:
The device includes a reception unit, a setting unit, and a search unit,
The receiving unit receives an input of at least one search word,
the setting unit sets, for the search word, related information including a degree of relevance between the search word and each of a plurality of search fields based on the reference information, wherein the reference information includes a relationship between the search word and the related information, and the search field is a search target range in the registered information of job seekers or employers;
A search support system in which the search unit searches for registered information containing the search word for each of the multiple search fields, and the higher the relevance for each search field contained in the related information, the higher the display priority of the searched registered information. 2. The search support system according to claim 1,
The relevance level is a numerical representation of the degree of relevance between the search word and the search field,
A search support system in which the search unit assigns a higher score to the searched registered information the greater the relevance of the search word to the search field in which the search word is contained, and displays registered information with a higher score preferentially. 3. The search support system according to claim 2,
A search support system in which the search unit assigns a higher score to the searched registered information the greater the number of search fields in which the search word is included. 3. The search support system according to claim 2,
The setting unit sets the related information for the search words not included in the reference information, the related information having the same relevance value for each of the multiple search fields. A search support system, comprising:
The apparatus includes a reception unit, a setting unit, a search unit, and a reference information registration unit,
The receiving unit receives an input of at least one search word,
the setting unit sets, for the search word, related information including a degree of relevance between the search word and each of a plurality of search fields based on the reference information, wherein the reference information includes a relationship between the search word and the related information, and the search field is a search target range in the registered information of job seekers or employers;
the search unit searches for the registered information including the search word for each of the plurality of search fields, and determines a display priority of the searched registered information based on the relevance for each of the search fields included in the related information;
The reference information registration unit , for the search word that is not included in the reference information , inputs the search word into a related information generation model, which is a learning model, and generates the related information by having the related information generation model output the related information, and registers the search word and the related information in the reference information by corresponding each other. 6. The search support system according to claim 5 ,
The reference information registration unit inputs an instruction to generate the related information based on the search word to the related information generation model. A search support system, comprising:
The device includes a reception unit, a setting unit, and a search unit,
The receiving unit receives an input of at least one search word,
the setting unit sets, for the search word, related information including a degree of relevance between the search word and each of a plurality of search fields based on the reference information, wherein the reference information includes a relationship between the search word and the related information, and the search field is a search target range in the registered information of job seekers or employers;
the search unit searches for the registered information including the search word for each of the plurality of search fields, and determines a display priority of the searched registered information based on the relevance for each of the search fields included in the related information;
A search support system in which, in the reference information, the search word and the related information that is obtained by inputting the search word into a related information generation model, which is a learning model, and outputting the related information generation model are registered in correspondence with each other. A search support system, comprising:
The apparatus includes a reception unit, a setting unit, a search unit, a storage unit, and an extraction unit,
The receiving unit receives an input of at least one search word,
the setting unit sets, for the search word, related information including a degree of relevance between the search word and each of a plurality of search fields based on the reference information, wherein the reference information includes a relationship between the search word and the related information, and the search field is a search target range in the registered information of job seekers or employers;
the search unit searches for the registered information including the search word for each of the plurality of search fields, and determines a display priority of the searched registered information based on the relevance for each of the search fields included in the related information;
The storage unit stores at least one of a search result of the registered information by the search word and an event occurrence result of the job seeker or the recruiter included in the search result,
A search support system in which the extraction unit extracts, from the search words included in the reference information, words to be reevaluated where at least one of the associated search results and the event occurrence results does not satisfy a predetermined criterion. 9. The search support system according to claim 8,
A re-evaluation unit is further provided,
The re-evaluation unit inputs the word to be re-evaluated into a re-evaluation model, which is a learning model, causes the re-evaluation model to output new related information associated with the word to be re-evaluated, and associates the word to be re-evaluated and the related information with each other and registers them in the reference information. 10. The search support system according to claim 9,
The re-evaluation unit inputs an instruction to the re-evaluation model to generate the related information based on the re-evaluated word. 2. The search support system according to claim 1,
The receiving unit receives input of a plurality of the search words,
The setting unit sets the related information for each of the plurality of search words based on the reference information;
The search unit searches for registered information containing a plurality of search words in each of a plurality of search fields for each of the plurality of search words, and determines the display priority of the searched registered information based on the relevance for each of the search fields included in the related information for each of the plurality of search words. A search support method, comprising:
A search support method comprising the step of executing processing of each unit of the search support system according to any one of claims 1 to 11. A program,
A program for causing a computer to execute the processing of each unit of the search support system according to any one of claims 1 to 11.