Search support system, search support method and program

Abstract

To provide a search support system or the like capable of reducing costs required for searching.SOLUTION: There is provided a search support system. The search support system includes at least one processor. The processor is configured to execute the following steps by reading a program: a search step of searching for search object information, where the search object information is job seeker information or job offer information registered in a database; a setting step of setting specific points to be extracted from the search object information on the basis of input from a searcher before, during, or after the execution of the search; an information creation step of creating specific information corresponding to the specific points for every piece of search object information by using keywords or sentences contained in the search object information extracted by the search on the basis of information creation reference information, where the information creation reference information includes a correlation among the search object information, the specific points, and the specific information; and a result display control step of displaying search results including the specific information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a search support system, a search support method, and a program. [Background technology]

[0002] As disclosed in Patent Document 1, a technique is known in which a recruiter searches for job seekers who meet the recruiter's requirements. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-269220 Summary of the Invention [Problem to be solved by the invention]

[0004] In the above-mentioned conventional technology, the cost of checking whether the searched job seekers match the job requirements can be high.

[0005] In view of the above circumstances, the present invention provides a search support system and the like that can reduce the cost required for searching. [Means for solving the problem]

[0006] According to one aspect of the present invention, a search support system is provided. The search support system includes at least one processor. The processor is configured to execute the following steps by reading a program. In the search step, a search is performed on search target information. The search target information is job seeker information or recruitment information registered in a database. In the setting step, specific points to be extracted from the search target information are set based on input from the searcher before, during, or after the search is performed. In the information creation step, specific information corresponding to the specific points is created for each piece of search target information based on reference information for information creation, using keywords or sentences contained in the search target information extracted by the search. The reference information for information creation includes correlations between the search target information, the specific points, and the specific information. In the result display control step, search results including the specific information are displayed.

[0007] According to this aspect, since the search results include specific information corresponding to the set specific points, the search target information can be screened efficiently, thereby reducing the cost required for searches by the searcher. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram showing a search support system 1. FIG. [Figure 2] 2 is a block diagram showing the hardware configuration of the server device 10. FIG. [Figure 3] FIG. 2 is a block diagram showing the hardware configuration of a recruiting party terminal 20 and a job seeker terminal 30. [Figure 4] 1 is a block diagram showing functions realized by a server device 10 (control unit 11), a recruiting party terminal 20 (control unit 21), and a job seeker terminal 30 (control unit 31). [Figure 5] 10 is a diagram showing an example of a job seeker information search result display screen RD displayed on the recruiter terminal 20. FIG. [Figure 6] FIG. 10 is a diagram illustrating an example of a UI for setting the filtering conditions of age and current annual income. [Figure 7] 1 is an activity diagram showing an example (first pattern) of the flow of information processing (job seeker search processing) executed by search support system 1. FIG. [Figure 8] 10 is an activity diagram showing another example (second pattern) of the flow of information processing (job seeker search processing) executed by search support system 1. FIG. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the accompanying drawings. Various features shown in the following embodiments can be combined with each other.

[0010] Incidentally, the program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable 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 realized on a client terminal (so-called cloud computing).

[0011] Furthermore, various information processing according to an embodiment may realize input and output corresponding to the input. Here, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited as long as an output is obtained as a result of the input. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression formula constructed using a statistical method), a trained model that has previously trained the correlation between input and output, or a large-scale language model that can output a desired result by inputting a prompt.

[0012] In one embodiment, a "unit" may 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 one embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit set consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations can be performed on a circuit in the broad sense.

[0013] Furthermore, a circuit in the broad sense is a circuit realized by at least an appropriate combination of a circuit, circuitry, processor, memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0014] 1. Hardware Configuration This section explains the hardware configuration.

[0015] <Search Support System 1> Fig. 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.

[0016] The search support system 1 constitutes at least a part of a recruitment and job search system used by, for example, multiple recruiters (a first recruiter U1 and a second recruiter U2) and multiple job seekers (a first job seeker U3 and a second job seeker U4). The search support system 1 mainly performs searches for job seekers by recruiters and searches for job openings by job seekers. In one embodiment, the search support system 1 is made up of one or more devices or components. These components will be described below.

[0017] <Server device 10> 2 is a block diagram showing the hardware configuration of server device 10. Server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. Control unit 11, storage unit 12, and communication unit 13 are electrically connected within server device 10 via communication bus 14.

[0018] <Control unit 11> The control unit 11 processes and controls the overall operations 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 predetermined programs stored in the storage unit 12. In other words, information processing by 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. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and multiple control units 11 may be provided for each function. A combination of these may also be used.

[0019] <Storage section 12> The memory unit 12 stores various pieces of information defined above. 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 operations. The memory unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

[0020] <Communications Department 13> The communication unit 13 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), or wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, or BLUETOOTH (registered trademark) communication as needed. That is, it is more preferable to implement it as a collection of multiple communication means. That is, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0021] The server device 10 may be an on-premise server or a cloud server. The cloud server device 10 may provide the above-described functions and processes in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0022] <Recruiter Terminal 20> Fig. 3 is a block diagram showing the hardware configuration of the recruiting party terminal 20 and the job seeker terminal 30. As shown in Fig. 3A, the recruiting party 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 within the recruiting party terminal 20 via the communication bus 26. The recruiting party terminal 20 is an information processing terminal used in the course of business by each recruiter who is a user belonging to an organization that receives services provided by the server device 10. The description of the control unit 21, the memory unit 22, and the communication unit 23 is omitted here, as they are the same as the description of each unit in the server device 10.

[0023] <Input section 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 can 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, etc. to the input unit 24. Instead of a touch panel, a switch button, a mouse, a trackpad, a QWERTY keyboard, etc. can be used as the input unit 24.

[0024] <Output section 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 selectively using them depending on the type of recruiter terminal 20.

[0025] <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 within the job seeker terminal 30 via the communication bus 36. The job seeker terminal 30 is an information processing terminal used by each job seeker who is a user receiving services provided by the server device 10. The description of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 is omitted here as they are the same as the description of each unit in the recruiter terminal 20.

[0026] 2. Functional configuration This section describes the functional configuration of this embodiment. Information processing by 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 (at least one processor included in the search support system 1).

[0027] FIG. 4 is a block diagram showing functions realized by the server device 10 (controller 11), the recruiter terminal 20 (controller 21), and the job seeker terminal 30 (controller 31).

[0028] As shown in Fig. 4A, server device 10 (control unit 11) includes a basic display control unit 111, a setting unit 112, a search unit 113, an information creation unit 114, a result display control unit 115, an individual information control unit 116, a scout document creation unit 117, and an artificial intelligence unit 120. As shown in Fig. 4B, recruiter terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212. As shown in Fig. 4C, job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation acquisition unit 312.

[0029] First Embodiment In the following, as a first embodiment, a description will be given of a form in which a recruiter who uses the search support system 1 searches for job seeker information as a searcher. Therefore, in the following description, the "searcher" refers to the recruiter, and the "information to be searched" refers to job seeker information.

[0030] Recruiters include organizations such as for-profit corporations (such as companies), non-profit corporations (such as cooperatives and foundations), and public corporations (such as local governments). Recruiters 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.

[0031] Job seeker information is information (registration information) about job seekers registered in a job seeker database. The job seeker database is stored, for example, in the storage unit 12. The job seeker's registration information also includes the job seeker's resume, curriculum vitae, and other profile information. Note that a "resume" is a document that mainly describes the job seeker's profile, current situation, educational background, work history, desired working conditions, etc., while a "curriculum vitae," also known as a résumé, is a document in which a job seeker conveys to a recruiter his or her work history, experience, skills, qualifications, etc., related to his or her past work. The job seeker's registration information may also include the job seeker's desired industry and occupation.

[0032] <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 job advertisement and scouting document created by the recruiter, registration information created by the job seeker, etc. on the display unit 211 of the recruiter terminal 20 or the display unit 311 of the job seeker terminal 30.

[0033] <Setting section 112> The setting unit 112 is configured to set specific points to be extracted from the search target information based on an input from the searcher before, during, or after a search is performed by the search unit 113. The search target information is job seeker information or job information registered in the database. In the first embodiment, as described above, the search target information is job seeker information.

[0034] The setting unit 112 may accept input of the specific point itself from the searcher, or may accept input of reference information for setting the specific point from the searcher. When accepting input of the specific point itself, the setting unit 112 accepts input of text including at least one keyword or sentence, and sets the input text as the specific point. Furthermore, the setting unit 112 may present the searcher with options for the specific point prepared in advance, and set one selected by the searcher from the options as the specific point.

[0035] When receiving input of reference information for setting specific points, setting unit 112 determines the specific points based on the input reference information. The reference information is information that includes items that can determine the specific points, and typically, when the search target information is job seeker information, the reference information is job information, and when the search target information is job information, the reference information is job seeker information.

[0036] In the first embodiment, the criteria information is job information for which a searcher searches for candidates. This allows the searcher (employer) to set specific points by selecting a job for which they want to search for job seekers. Note that the job information may include, in addition to the job posting, accompanying information such as the behavioral history of the employer or job seeker regarding the job.

[0037] Specifically, the setting unit 112 determines specific points related to the requirements of the job offer or the career or aspirations of the job seeker based on the reference information for setting and the criteria information specified by the searcher. This allows the searcher to set specific points using pre-registered criteria information without directly creating specific points. In the first embodiment, the setting unit 112 determines specific points based on the job offer information and the reference information for setting. If the job offer information includes an item indicating the requirements of the job offer, the setting unit 112 may extract the content of the item as the specific point.

[0038] In the first embodiment, the setting unit 112, for example, displays a list of job information registered by a searcher on the recruiter terminal 20 and accepts a selection input of job information for which specific points are to be set (i.e., for searching for job seekers (candidates)) from the recruiter terminal 20. The setting unit 112 may also accept an upload of job posting data from the recruiter terminal 20 and set specific points based on the job posting. That is, the setting unit 112 may accept designation of job information (standard information) by uploading a job posting. Furthermore, the setting unit 112 may accept input of access information indicating the location of the job information on a network (e.g., a URL or IP address of a recruitment site, recruitment management system, etc.) and set specific points based on the job information downloaded from the location on the network. That is, the setting unit 112 may accept designation of job information (standard information) by input of access information.

[0039] The setting reference information includes a correlation between the reference information and the specific point. The setting reference information is stored, for example, in the memory unit 12. The setting reference information is an estimator constructed so that it can input the reference information and output the specific point. The setting reference information may include, for example, a table, a function, a simple algorithm, etc., that indicates the correlation between the feature (vector data) extracted from the reference information and the specific point. The correlation included in the setting reference information can be constructed, for example, by statistically analyzing data that records the relationship between the actual reference information (a job posting in the first embodiment) and the specific point.

[0040] The setting reference information may include a specific point setting model that has been trained to receive reference information and output specific points. In this case, the setting unit 112 inputs the reference information into the specific point setting model of the artificial intelligence unit 120 to obtain specific points output by the specific point setting model. This makes it possible to set specific points based on setting examples of specific points in a large number of reference information or natural language processing.

[0041] The specific point setting model in the first embodiment is a learning model that is trained using a combination of reference information for learning (e.g., job information) and specific points related to the reference information (e.g., job requirements extracted from the job information, or specific points related to the career or aspirations of a job seeker) as training data. In the specific point setting model, parameters calculated, tuned, etc. by learning constitute correlations of the setting reference information.

[0042] The specific point setting model may be a generative AI including a large-scale language model. In this case, the setting unit 112 inputs criteria information (e.g., job information) and inputs a prompt including an instruction to output specific points related to the criteria information (e.g., job requirements in the job information, or specific points related to the job seeker's background or aspirations) to the specific point setting model, causing the specific point setting model to output the specific points. The setting unit 112 may generate a prompt that instructs the specific point setting model to set specific points based on the criteria information and input the prompt to the specific point setting model. Furthermore, the setting unit 112 may input a prompt that inserts, as input and output samples, one or more samples of criteria information and one or more corresponding samples of specific points to the specific point setting model in addition to the setting and output instructions for the specific points and the criteria information. The specific point setting model extracts specific points based on the criteria information in accordance with the input prompt.

[0043] The specific points related to the requirements of the job posting include, for example, keywords related to at least one of experience, skills, and qualifications. Specific examples of such specific points include "basic knowledge of information security," "experience in developing and designing IT systems," and "information security assessment of systems." Typically, the setting unit 112 sets the skills or experience required in the job posting as the specific points. In this case, the setting reference information includes correlations for setting the required skills or experiences as specific points.

[0044] The specific points related to the job seeker's career include, for example, keywords related to at least one of educational background, work history, and organizations to which the job seeker has belonged or currently belongs. The specific points related to the job seeker's aspirations include, for example, keywords related to at least one of desired job type, desired industry, desired position, desired annual salary, and desired work location.

[0045] The specific point setting model may extract the contents of specific items included in the reference information as specific points. When the specific point setting model is a generation AI, the setting unit 112 inserts an instruction to output the contents of the specific items of the reference information as specific points into the prompt. The specific items are predetermined items, such as "essential requirements" and "welcome (preferable) requirements" in a job posting.

[0046] The specific point setting model may select and output a specific point corresponding to the input reference information from a pre-prepared list containing candidate keywords for the specific point. The specific point setting model may output the candidate keyword listed in the list as the specific point itself, or may output a combination of multiple candidate keywords listed in the list as the specific point. When the specific point setting model is a generation AI, the setting unit 112 inserts into the prompt the contents of the list containing the candidate keywords or a reference to the list, and an instruction to select and output a specific point suitable for the reference information from the candidate keywords included in the list.

[0047] The setting unit 112 may accept from the searcher modifications to the specific points determined based on the reference information. Specifically, the setting unit 112 may present the specific points to a user terminal (the recruiter terminal 20 in the first embodiment) and accept editing such as modification, deletion, or addition of keywords included in the specific points.

[0048] The setting unit 112 may also set multiple specific points. That is, the setting unit 112 may accept input of multiple specific points from the searcher, or may set multiple specific points based on one specified reference information. Furthermore, the setting unit 112 may set a specific point from text input by the searcher, and may also set another specific point based on the reference information. When the setting unit 112 sets multiple specific points, the information creation unit 114 creates specific information for each of the multiple specific points.

[0049] The setting unit 112 may receive an input from the searcher to set a specific point before the search unit 113 searches for the search target information. This allows the searcher to execute a search for the search target information after inputting the specific point or after specifying the criteria information, thereby smoothing the flow of the search by the searcher. In particular, in the first embodiment, by receiving the specification of job information before executing the search, it is possible to search for job seekers after determining the job for which candidates are to be searched. Note that "before executing a search" means before the search unit 113 receives input of search conditions, before the search unit 113 starts the search process (when search conditions are not input), or after the search conditions are input and before the search unit 113 starts the search process. Therefore, it is also possible to receive an input for setting a specific point simultaneously with the input of search conditions by the search unit 113.

[0050] In addition, the setting unit 112 may accept input for setting a specific point while the search unit 113 is performing a search (after the search process has started and before the search results are displayed), or may accept input for setting a specific point after the search has been performed (after the search results are displayed).

[0051] The specific point may be set before, during, or after the search is performed by the search unit 113, as long as it is set before the information creation unit 114 starts creating the specific information. However, it is preferable that the setting unit 112 set the specific point before the search is performed by the search unit 113. This makes it possible to perform a search using the specific point, as will be described later.

[0052] The setting unit 112 may also set a pre-created point that has been prepared in advance as the specific point. The pre-created point is created in advance for each piece of reference information before the searcher specifies the reference information, and is stored in the storage unit 12 or the like. In this case, the setting reference information referenced by the setting unit 112 includes a correlation for setting the pre-created point of the reference information as the specific point. The setting unit 112 references the setting reference information to obtain the pre-created point of the specified reference information, and determines the pre-created point as the specific point to be used by the information creation unit 114.

[0053] A pre-created point is, for example, a specific point that was set in reference information by the setting unit 112 when the reference information was specified by a searcher in the past. That is, for reference information that has a setting history of a specific point, the setting unit 112 reuses a past specific point (a pre-created point). In this case, the pre-created point may be a specific point determined by the setting unit 112 based on the reference information, or may be a specific point created by the searcher.

[0054] The pre-created points may be created when the reference information is registered or edited. For example, in the first embodiment, when a job posting is registered or the contents of the job posting are modified, the specific points of the job posting may be automatically set by the specific point setting model, and the specific points may be linked to the job posting and stored as pre-created points.

[0055] The setting unit 112 may present a plurality of pre-created points to the searcher and accept selection of a pre-created point to be set as a specific point from the searcher.

[0056] <Search section 113> The search unit 113 is configured to execute a search for search target information. In the first embodiment, the search unit 113 executes a search for job seeker information that satisfies the search criteria input from the employer terminal 20 and / or the search criteria set by the search unit 113 in the job seeker database.

[0057] Specifically, the search unit 113 receives a search query including at least one search keyword from a searcher, and performs a keyword search of search target information based on the received search query. That is, the search unit 113 extracts search target information including keywords that are the same as or similar to the search keywords included in the received search query. In the keyword search, keyword similarity is determined by, for example, comparison using feature quantities such as vector data, reference to a database in which synonyms, similar words, and spelling variations are registered, determination using a learning model (large-scale language model), etc.

[0058] When the searcher specifies criteria information for setting specific points, the search unit 113 may perform a search by comparing the vector data of the criteria information specified by the searcher with the vector data of the search target information. This makes it possible to extract search target information having attributes similar to those included in the criteria information. In particular, in the first embodiment, a vector data search using such criteria information makes it possible to search for job seekers who match the requirements, etc., included in a job posting.

[0059] The search unit 113 may perform both a keyword search and a vector data search using reference information, and may obtain the union or intersection of the search results. Alternatively, the search unit 113 may perform only a vector data search using reference information. In this case, a searcher can perform a search by simply specifying the reference information, without inputting a search query.

[0060] If a specific point is set by the setting unit 112 before a search is performed, the search unit 113 may perform a search by comparing vector data of the specific point with vector data of the search target information. This makes it possible to extract search target information having attributes similar to the specific point, regardless of whether or not reference information is specified, and without the need to input a search query. In particular, in the first embodiment, a vector data search using such a specific point can also be used to search for job seekers who match the requirements, etc., included in a job posting.

[0061] The search unit 113 may perform both a keyword search and a vector data search using a specific point, and may obtain the union or intersection of the search results. Alternatively, the search unit 113 may perform only a vector data search using a specific point. In this case, a searcher can perform a search without entering a search query by simply inputting a specific point or specifying reference information for setting a specific point.

[0062] <Information Creation Department 114> The information creation unit 114 is configured to create, based on the information creation reference information, specific information corresponding to the specific point for each piece of search target information, using keywords or sentences contained in the search target information extracted by the search by the search unit 113. In the first embodiment, the information creation unit 114 creates specific information for each piece of extracted job seeker information.

[0063] The specific information includes at least related keywords related to keywords included in the specific points in the search target information. The information creation unit 114 may use related keywords extracted from each piece of search target information or related sentences including related keywords as the specific information. Alternatively, the information creation unit 114 may create the specific information by combining multiple related keywords or related sentences, abstracting or normalizing related keywords, extracting keywords from related sentences, deleting unnecessary keywords from related sentences, or the like.

[0064] "Related keywords" include keywords that match or are similar to keywords included in a specific point, keywords that are a superordinate (abstract) or subordinate (concrete) version of keywords included in a specific point, etc. Similarity determination for related keywords is performed, for example, by comparing features such as vector data, referencing a database in which synonyms, similar words, and spelling variations are registered, or by judgment using a learning model (including a large-scale language model). Furthermore, determination of superordinate or subordinate concepts for related keywords is performed by referencing a table (database) that defines the relationship between superordinate and subordinate concepts for each keyword, or by judgment using a learning model (including a large-scale language model).

[0065] In the first embodiment, for example, if the specific point includes a skill keyword representing a specific skill, the information creation unit 114 extracts keywords corresponding to the skill (keywords that match or are similar to the skill keyword, or keywords that are a sub-concept of the skill keyword) as related keywords from career-related items (items related to work history, qualifications, skills, etc.) included in the job seeker information, and creates specific information based on the related keywords. For example, if the specific point includes the skill keyword "information security," the information creation unit 114 extracts, as related keywords, not only the keyword "information security" itself but also keywords that are a sub-concept of "information security," such as "encryption technology" and "authentication algorithm" (i.e., keywords that correspond to specific examples, detailed classifications, etc. of "information security"). The information creation unit 114 creates specific information that includes the related keywords extracted in this way.

[0066] The identification information may include, in addition to the related keywords, supplemental information indicating attributes of the related keywords. For example, in the first embodiment, if the related keywords are skill keywords representing skills, the information creation unit 114 may further extract keywords or numerical values ​​(e.g., the name of the organization, department, job title, occupational title, period, etc. to which the job seeker belonged when using the skill (currently or in the past)) indicating experience related to the skill (e.g., experience in acquiring or using the skill) from the job seeker information and add the extracted keywords to the identification information as supplemental information. Furthermore, the information creation unit 114 may add supplemental explanations of the related keywords (e.g., the commercial materials, environment, business scale, etc. to which the skill was applied) to the identification information as supplemental information.

[0067] If the specific point is a skill or experience that is a job requirement, the information creation unit 114 may create specific information that includes a career history related to the specific skill or experience included in the job seeker information. This allows the skills or experience that are required for the job offer and the basis for that experience to be confirmed in the search results. For example, if the specific point is related to a specific experience, the information creation unit 114 may extract each job seeker's career history corresponding to that experience from the job seeker information and add this to the specific information as supplemental information. For example, the information creation unit 114 may extract from the job seeker information the name of the organization, department name, job title, job type, period, etc., in which the job seeker had the experience corresponding to the experience, and add this to the specific information.

[0068] The information creation reference information includes correlations between the search target information, the specific points, and the specific information. The information creation reference information is stored, for example, in the storage unit 12. The information creation reference information is an estimator configured to be able to output specific information by inputting the search target information and the specific points. The information creation reference information may include, for example, a table, function, simple algorithm, etc. that indicates a first correlation between keywords included in the specific points and related keywords extracted from the search target information, and a table, function, simple algorithm, etc. that indicates a second correlation between related keywords extracted from the search target information and the specific information. The correlations included in the information creation reference information can be constructed, for example, by statistically analyzing data that records the relationships between actual search target information (job seeker information in the first embodiment), the specific points, and the specific information.

[0069] The reference information for information creation may include a specific information creation model that has been trained to be able to input search target information and specific points and output specific information. In this case, the information creation unit 114 inputs the search target information and specific points into the specific information creation model of the artificial intelligence unit 120 and causes the specific information creation model to output specific information. This makes it possible to create specific information based on examples of specific information creation from a large number of pairs of search target information and specific points, or on natural language processing.

[0070] The specific information creation model in the first embodiment is a learning model that is trained using a combination of job seeker information for learning, specific points for learning, and specific information created from the job seeker information and the specific points as training data. In the specific information creation model, parameters calculated, tuned, etc. through learning form correlations of the information creation reference information.

[0071] The specific information creation model may be a generative AI including a large-scale language model. In this case, the information creation unit 114 receives job seeker information and specific points as input, inputs a prompt including an instruction to output specific information corresponding to the specific points from the job seeker information, and causes the specific information creation model to output the specific information. The information creation unit 114 may generate a prompt that instructs the specific information creation model to create specific information based on the job seeker information and specific points, and input the prompt to the specific information creation model. Furthermore, the information creation unit 114 may input, in addition to the instruction to create and output the specific information, the job seeker information, and the specific points, a prompt that inserts, as input and output samples, for example, one or more samples of pairs of job seeker information and specific points and one or more samples of specific information corresponding to the pairs. The specific information creation model creates the specific information according to the input prompt.

[0072] Furthermore, the specific information creation model may take as input job seeker information and specific points related to specific skills or experience, and output specific information extracted from the job seeker information, including keywords or numerical values ​​(e.g., the name of the organization, department name, job title, job type, period, etc. to which the job seeker belonged when using the skill (currently or in the past)) that represent the job seeker's career related to the skills or experience (e.g., experience in acquiring or using the skill, past experience corresponding to or similar to the experience, etc.). When the specific information creation model is a generative AI, the information creation unit 114 takes as input job seeker information and specific points, and inputs to the specific information creation model a prompt including an instruction to output, from the job seeker information, specific information including the job seeker's career corresponding to the specific points (e.g., the name of the organization, department name, job title, job type, period, etc. to which the job seeker currently belongs or in the past).

[0073] The information creation unit 114 associates the created specific information with the corresponding search target information and stores it in, for example, the storage unit 12 so that it can be referenced by the result display control unit 115. Furthermore, if the information creation unit 114 cannot create specific information (for example, if related keywords cannot be extracted from the search target information), it associates information (code) indicating that the specific information could not be created with the search target information and stores it.

[0074] The information creating unit 114 may create multiple pieces of specific information for one specific point. That is, the information creating unit 114 may extract multiple related keywords related to the keyword included in one specific point from one piece of search target information.

[0075] The information creation unit 114 may assign a matching index to each piece of specific information, which indicates the degree of matching with the specific point. This allows the display of search results by the search unit 113 to be adjusted based on the matching index. The matching index is a numerical value that indicates a greater match as the number increases, and may be selected from among discrete numerical values ​​(labels) or may be a continuous numerical value. For example, the matching index may be assigned as a label such as "definite match" or "probably match."

[0076] The matching index is set, for example, based on the degree of match between the related keywords extracted from the search target information when the specific information is created and the keywords included in the specific point. For example, the information creation unit 114 assigns the highest evaluation index (an index indicating a definite match (e.g., a "definite match" label)) to specific information whose related keywords match the keywords included in the specific point, and assigns the next highest evaluation index (an index indicating a likely match (e.g., a "probably match" label)) to other specific information (specific information whose related keywords are similar to the keywords included in the specific point or are in a superordinate or subordinate conceptual relationship). Note that the information creation unit 114 may assign the highest evaluation index not only to specific information whose related keywords match the keywords included in the specific point, but also to specific information whose related keywords are similar to the keywords included in the specific point.

[0077] Furthermore, the matching index may be calculated as, for example, the similarity (for example, cosine similarity) between the vector data of the specific information and the vector data of the specific point.

[0078] The information creation unit 114 may cause the specific information creation model to output a matching index together with the specific information. For example, when the specific information creation is performed by a generation AI, the information creation unit 114 may input to the specific information creation model, in addition to an instruction to create and output the specific information, a prompt that includes an instruction to assign a matching index (or a label representing the matching index) to the specific information, or an instruction to output the specific information for each matching index (degree of matching).

[0079] Furthermore, the information creation unit 114 may input the specific points and specific information to a matching index calculation model of the artificial intelligence unit 120 and cause the matching index calculation model to output a matching index. The matching index calculation model is a learning model that receives the specific points and specific information as input and is trained to output a matching index. In other words, the matching index calculation model is a learning model that is trained using combinations of the specific points and specific information and the matching indexes corresponding to them as training data.

[0080] <Result display control unit 115> The result display control unit 115 is configured to display search results including the specific information. In the first embodiment, the result display control unit 115 causes the job seeker information searched for by the search unit 113 to be displayed on the recruiting party terminal 20.

[0081] Specifically, the result display control unit 115 displays a plurality of pieces of search target information extracted by the search unit 113 in a list format including the respective specific information, thereby enabling the searcher to screen the search results by referring to the specific information.

[0082] In addition, if a specific point has not been set when the search unit 113 completes the search, the result display control unit 115 may first display the search results that do not include the specific information, and after setting the specific point, create the specific information using the above method and then update the search results, thereby re-displaying the search results with the specific information added.

[0083] Fig. 5 is a diagram showing an example of a search result display screen RD for job seeker information displayed on the employer terminal 20. The search result display screen RD in the lower part of Fig. 5 is a portion that continues from the right side of the search result display screen RD in the upper part, with a portion of the right side further omitted.

[0084] The search result display screen RD displays a list of one item per line of job seeker information searched (extracted) by the search unit 113. The search result display screen RD displays, for each job seeker information, extracted information EI extracted from the job seeker information and specific information SI created by the information creation unit 114.

[0085] The extracted information EI includes information about the job seeker's profile and / or career history, and may include, for example, the job seeker's current organization, current position, university or graduate school from which they graduated, age, place of residence, work experience, number of years of work experience, current annual salary, etc.

[0086] The specific information SI includes specific information for each specific point. If multiple specific points are set, a display column (list column) of specific information is provided for each specific point. In the example of Figure 5, the item name of the specific information is "Specific Point 1," etc., but the content of the specific point (keywords, etc.) may also be displayed as the item name. In the example of Figure 5, "Specific Point 1" may be displayed as "Basic knowledge of information security," and "Specific Point 2" may be displayed as "Development and design experience of IT systems, etc."

[0087] Additionally, if multiple pieces of specific information have been created for one specific point, the multiple pieces of specific information will be displayed in association with that single point. For example, if multiple experiences corresponding to specific point 2, "experience in developing and designing IT systems, etc.", are extracted from the job seeker's information and specific information based on each experience is created, these pieces of specific information will be displayed in the results list.

[0088] 5, only a portion of the text of the specific information is displayed in the result list, but the entire text of the specific information can be displayed by the searcher selecting the display field for the specific information. That is, if the number of characters of the specific information is equal to or greater than a predetermined number, the result display control unit 115 may display only a portion (the beginning) of the text representing the specific information in the search results, and may also display the entire text of the specific information when the searcher selects the specific information in the search results. This allows the content of the specific information to be confirmed and understood by selecting each individual piece of information without impairing the visibility of the result list, even if the number of characters of the specific information is large.

[0089] Selection of specific information in the result list includes operations by the searcher, such as hovering the mouse cursor (mouseover), tapping, long-tapping, clicking, and double-clicking. Furthermore, the entire specific information can be displayed in a format such as a tooltip or pop-up hint, where an area displaying the specific information is overlaid on the result list with an element containing the entire specific information. In this case, like a tooltip, detailed information about the specific information is not displayed when the result list is normally displayed, but is dynamically displayed when a specific operation, such as a mouseover, is performed on the result list. This allows the entire content of the specific information to be confirmed and understood without impairing the visibility of the result list, even if the entire text of the specific information is long. Note that the specific information displayed in a format such as a tooltip may disappear (or be deactivated) after a predetermined time has elapsed.

[0090] When multiple pieces of specific information created for one specific point are displayed, the result display control unit 115 displays the full text of the selected specific information in the form of a tooltip or the like in response to a selection operation, such as a mouseover, on each piece of specific information. For example, if two pieces of specific information (specific information 1 and specific information 2) are created for specific point 1, when specific information 1 is selected in the result list, the full text of specific information 1 is displayed, and when specific information 2 is selected in the result list, the full text of specific information 2 is displayed. In this way, when multiple pieces of specific information are created for one specific point, the result display control unit 115 may display the multiple pieces of specific information corresponding to one specific point and may also display the entire text of only the specific information selected in the search results. This allows the user to check and understand the entire text content of each piece of specific information without impairing the visibility of the result list, even if the entire text of each piece of specific information created is long.

[0091] If there is a specific point in the search target information included in the search results for which no specific information has been created, the result display control unit 115 may display a notation indicating that no specific information exists (for example, "Null") in the display column for that specific point instead of the specific information.

[0092] When criterion information is selected, the result display control unit 115 may display auxiliary information indicating the selected criterion information on the same screen as the search results. The auxiliary information is displayed, for example, above the search results. When the criterion information is job information, the auxiliary information includes, for example, a job summary, required requirements, preferred requirements, etc.

[0093] The result display control unit 115 may determine the specific information to be displayed in the search results based on the matching index assigned to the specific information. This allows only specific information that has a high degree of matching with the specific point to be displayed in the search results, thereby improving the efficiency of screening by the searcher.

[0094] Specifically, the result display control unit 115 may display, in the search results, only search target information for which specific information with a matching index equal to or greater than a predetermined value has been created. This makes it possible to exclude from the search results search target information that does not have specific information with a high degree of matching, and search target information for which specific information has not been created (for which the specific information does not match the specific point). As a result, the search efficiency of the searcher is improved. Note that the result display control unit 115 may display only search target information for which specific information has been created, regardless of the magnitude of the matching index (whether or not a matching index has been assigned). In other words, if a matching index has not been assigned to the specific information by the information creation unit 114, the result display control unit 115 may not display, as a search result, search target information for which specific information has not been created.

[0095] When displaying multiple pieces of specific information created for one specific point, the result display control unit 115 may determine the display order of the pieces of specific information based on the matching index. For example, the result display control unit 115 may display the specific information from the top in descending order of the matching index, or may display multiple pieces of specific information so that specific information labeled "definitely a match" is on top and specific information labeled "probably a match" is on the bottom.

[0096] The result display control unit 115 may display a matching index for each specific information as a search result. The result display control unit 115 may also accept a searcher's selection of specific information and display a matching index for the specific information. For example, the result display control unit 115 may receive a searcher's selection of specific information in the result list of FIG. 5 (by hovering the mouse cursor over it, tapping, etc.) and display a matching index (a label representing the matching index) superimposed on the result list using an element such as a tooltip.

[0097] The result display control unit 115 may display the specific information in the result list in a manner that allows each matching indicator to be recognized. For example, the result display control unit 115 may display the specific information with an icon or the like indicating a label such as "definite match" or "probable match," or may display the specific information in a visually distinguishable manner, such as by color coding, depending on the size of the matching indicator.

[0098] The result display control unit 115 may accept input of refinement conditions (filtering conditions) for the search results from the searcher. For example, in the first embodiment, the refinement conditions include the current organization, current position, graduated university or graduate school, age, place of residence, work experience, number of years of work experience, and current annual income. The result display control unit 115 displays, as search results, only search target information that satisfies the input refinement conditions from among the searched search target information. Of the refinement conditions, those expressed as numerical values ​​may be input using a visual UI.

[0099] FIG. 6 shows an example of a UI for setting the filtering conditions of age and current annual income. The first slide bar SB1 is a UI for selecting an age range, and the second slide bar SB2 is a UI for selecting a current annual income range. The first slide bar SB1 and the second slide bar SB2 each accept inputs by sliding objects (circles) indicating upper and lower limits to the left and right. The first slide bar SB1 and the second slide bar SB2 are displayed, for example, on the same screen as the result list on the search result display screen RD of FIG. 5, and are positioned above the result list. This allows a searcher to easily set the upper and / or lower limits of the filtering conditions while viewing the result list. When the upper and / or lower limits of a specified condition are set using the first slide bar SB1, the second slide bar SB2, etc., the search target information displayed in the result list is narrowed down according to the set conditions, and the result list is updated.

[0100] The result display control unit 115 may use the presence or absence of specific information corresponding to a specific point as a condition for narrowing down the search results. For example, the result display control unit 115 may exclude from the search results search target information that does not have specific information corresponding to a specific point specified by the searcher. The result display control unit 115 may also use a matching index of a specific point as a condition for narrowing down the search results. For example, the result display control unit 115 may display as search results only search target information that satisfies the matching index condition specified by the searcher in the specific information corresponding to the specific point specified by the searcher (for example, the matching index is a predetermined value (a predetermined label is attached as the matching index), the matching index is equal to or greater than a threshold, etc.). This makes it possible, for example, to display only search target information that is labeled "definitely a match."

[0101] <Individual information control unit 116> The individual information control unit 116 is configured to individually display details of search target information selected by the searcher from among the search target information included in the search results. In the first embodiment, the individual information control unit 116 displays job seeker information (profile information, resume, etc.) selected by the searcher from the search results on the recruiter terminal 20. For example, the individual information control unit 116 receives an input operation for any item in the result list of FIG. 5 (for example, any of the extracted information EI) and displays the individual job seeker information.

[0102] When displaying details of the selected search target information, the individual information control unit 116 may highlight the basis portion of the specific information (for example, keywords corresponding to specific points) by coloring, changing font, decorating, etc. Furthermore, when multiple specific points are set (multiple pieces of specific information are created for one piece of search target information), the individual information control unit 116 may display the basis portion of the specific information for each specific point in a visually distinguishable manner by color coding, etc. Furthermore, the individual information control unit 116 may adjust the initial display position of the search target information so that the basis portion is initially displayed on the display screen of the search target information transitioned from the search result screen.

[0103] Furthermore, when displaying details of the selected search target information, the individual information control unit 116 may add and display specific information at the beginning of the search target information. In this case, if multiple pieces of specific information have been created, the individual information control unit 116 may add a sentence summarizing these pieces of specific information, keywords extracted from these pieces of specific information, etc., to the beginning of the search target information. Furthermore, the individual information control unit 116 may accept a selection of the specific information added to the beginning or a description related to the specific information, and change (jump) the display position of the search target information so that the basis part of the selected specific information is displayed on the display screen.

[0104] <Scout Document Creation Department 117> The scouting document creation unit 117 is configured to create and send scouting documents for job seekers selected by the recruiter. The scouting documents are sent to job seekers who are registered in the search support system 1 and are candidates for the job.

[0105] Specifically, the scout document creation unit 117 creates a scout document for a job seeker whose job seeker information is selected by the searcher (employer) from among the job seeker information included in the search results. The scout document may include a job posting included in the reference information as well as specific information corresponding to the job seeker to whom it is addressed. This saves the recruiter the trouble of attaching a job posting to the scout document (selecting a job posting to attach to the scout document). Therefore, by selecting job information (job posting) when setting specific points, the recruiter can efficiently perform the process from searching for job seekers to sending the scout document. Furthermore, including specific information in the scout document can inform the job seeker of the recruiter's focus, thereby facilitating the matching of job offers and job seekers. Note that the scout document may also be called a scout email.

[0106] When multiple job seeker information items are selected as the destination of the scout document, the scout document creation unit 117 collectively creates multiple scout documents to which the same job posting is attached and in which specific information corresponding to each job seeker information item is inserted.

[0107] The scout document creation unit 117 may create a scout document by accepting input of characters, etc. from the recruiter terminal 20, or may input a job posting included in the reference information (i.e., selected by the recruiter at the time of search) into the scout document creation model of the artificial intelligence unit 120 and have the scout document creation model output a scout document. The scout document creation unit 117 may prepare a scout text template or scout document creation model for each job type or industry.

[0108] The scout document creation model is a learning model that is trained to use job postings as input and scout documents as output. In other words, the scout document creation model is a learning model that is trained using a combination of a training job posting and the scout document data corresponding to that job posting as training data.

[0109] The scout document creation model may be a generative AI including a large-scale language model. In this case, the scout document creation unit 117 inputs a job posting, inputs a prompt including an instruction to output a scout document to the scout document creation model, and causes the scout document creation model to output the scout document. The scout document creation unit 117 may generate a prompt that instructs the scout document creation model to create a scout document from the job posting, and input the prompt to the scout document creation model. Furthermore, the scout document creation unit 117 may input a prompt that inserts, for example, one or more sample job postings and one or more corresponding scout document samples to the scout document creation model in addition to the scout document creation and output instruction and the job posting. The scout document creation model creates a scout document from the job posting according to the input prompt.

[0110] <Attachment of job posting> The scout document creation unit 117 may attach the job posting included in the standard information to a scout document created manually by the recruiter or to an existing scout document, or may attach the job posting included in the standard information to a scout document output (i.e., automatically generated) by the scout document creation model described above.

[0111] When a job posting is to be attached to a scouting document created manually by a recruiter, the scouting document creation unit 117 acquires the scouting document created by the recruiter inputting text using the input unit 24 of the recruiter terminal 20, and attaches the job posting acquired by the setting unit 112 to the acquired scouting document. When a job posting is to be attached to an existing scouting document, the scouting document creation unit 117 acquires the existing scouting document by means of uploading a file from the recruiter terminal 20, or the like, and attaches the job posting acquired by the setting unit 112 to the acquired existing scouting document.

[0112] The scout document creation model may also be a learning model that has been trained to be able to output a scout document to which a job posting included in the reference information is attached. That is, the scout document creation unit 117 may input a job posting to the scout document creation model and cause the scout document creation model to output a scout document to which the job posting is attached. Alternatively, the scout document creation unit 117 may input an existing scout document and a job posting to the scout document creation model and cause the scout document creation model to output a scout document to which the job posting is attached. Furthermore, if the scout document creation model is a generative AI, the scout document creation unit 117 may input a job posting and input a prompt to the scout document creation model that includes an instruction to output a scout document to which the job posting is attached, and cause the scout document creation model to output a scout document to which the job posting is attached.

[0113] <insert specific information> The scout document creation unit 117 inserts into the scout document a sentence in which multiple specific information items are listed, such as, for example, "I am interested in the following points about you: (1) <Specific Information 1> (2) <Specific Information 2> (3) <Specific Information 3>" (where <Specific Information n> reflects the text of the specific information corresponding to the job seeker set as the recipient of the scout document). The scout document creation unit 117 may also insert into the scout document only specific information that has been assigned a matching index (for example, an index indicating a definite match) of a predetermined level or higher.

[0114] The scout document creation unit 117 inserts the specific information created by the information creation unit 114 into a scout document created manually by the recruiter, an existing scout document, a scout document output by a scout document creation model, etc. The scout document creation unit 117 may also create a scout document template into which specific information has been inserted in advance, and accept text input from the recruiter into that template.

[0115] The scout document creation model may be a learning model that receives a job posting and specific information as input and is trained to output a scout document with the specific information inserted. In other words, the scout document creation model may be a learning model that is trained using a combination of a training job posting and specific information and data on the job posting and scout document corresponding to the specific information as training data. Furthermore, if the scout document creation model is a generative AI, the scout document creation unit 117 may receive a job posting and specific information as input, input a prompt to the scout document creation model that includes an instruction to output a scout document with the specific information inserted, and cause the scout document creation model to output the scout document with the specific information inserted.

[0116] Furthermore, the scout document creation unit 117 may input a job posting and specific information into a scout document creation model, and cause the scout document creation model to output a scout document with the job posting attached and the specific information inserted.

[0117] <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.

[0118] The artificial intelligence unit 120 is an AI (Artificial Intelligence) equipped with learning models such as Transformers including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, and GPT-4), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), etc., and language models such as Recurrent Neural Networks (RNNs), and may include generative AI.

[0119] 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.

[0120] 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 pairs of input data for learning and output data (correct answer data). Furthermore, the language model may not only be trained for a specific task, but also be a general-purpose model that can be used for a wide range of tasks.

[0121] The artificial intelligence unit 120 may be a general-purpose natural language processing learning model, such as a large-scale language model (LLM), trained on a huge amount of data. LLMs are learning models that have previously trained on a large amount of data, such as text data (e.g., (i) web content on the Internet, or (ii) data stored in a specified database). They can execute various language processing tasks when given tasks, and can perform a wide range of natural language processing tasks, such as grasping sentence patterns and contexts, answering questions, and generating sentences, according to given prompts. Such general-purpose learning models include language models that can handle various tasks without fine-tuning, such as through one-shot learning or few-shot learning. Furthermore, general-purpose learning models may also be configured to handle various tasks through zero-shot learning. 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.

[0122] The learning models included in the artificial intelligence unit 120 (learning models used in each functional unit, such as the specific point setting model and the specific information creation model) can undergo additional learning as transfer learning or fine tuning. For example, each time new job seeker registration information, job posting registration, etc. is generated, the artificial intelligence unit 120 may perform additional learning and fine tuning using this as new training data. This improves the accuracy of the information output from the learning model.

[0123] The learning model included in the artificial intelligence unit 120 may be a learning model (distilled model) obtained by knowledge distillation using an original learning model. In knowledge distillation, a trained model such as a large-scale language model is used as a teacher model, and the parameters of the student model (distilled model) are adjusted to reduce the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model, thereby learning the student model, which becomes the distilled model. Alternatively, the student model may be learned to reduce the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (combination of input data and output data of the learning model). Compared to the original learning model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while maintaining performance similar to the learning model. Therefore, using a distilled model can reduce the cost of the search support system 1.

[0124] For example, the specific point setting model, the specific information creation model, etc. may be distilled models trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the search support system 1 is introduced, a large-scale language model may be used as the specific point setting model, the specific information creation model, etc., and once training data from the large-scale language model has been accumulated, a distilled model obtained by knowledge distillation using the training data may be used as the specific point setting model, the specific information creation model, etc.

[0125] <Display> The display unit 211 of the recruiting party 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.

[0126] <Operation acquisition part> The operation acquisition unit 212 of the recruiting party terminal 20 accepts operations by a user (recruiter) who uses the recruiting party terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 accepts operations by a user (job seeker) who uses the job seeker terminal 30.

[0127] Second Embodiment The following describes, as the second embodiment, an embodiment in which a job seeker using the search support system 1 searches for job information as a searcher. In the second embodiment, "job seeker information" as the "search target information" in the first embodiment is replaced with "job information," and "job information" as the "reference information" in the first embodiment is replaced with "job seeker information." The functions (processing contents) of the basic display control unit 111, setting unit 112, search unit 113, information creation unit 114, result display control unit 115, and individual information control unit 116 are the same as those in the first embodiment.

[0128] Specifically, in the second embodiment, the setting unit 112 determines specific points related to the job seeker's requirements based on the job seeker information specified by the job seeker performing a job search (i.e., job seeker information registered by the job seeker himself / herself) and the setting reference information. In the second embodiment, the setting unit 112 determines specific points related to the job seeker's career history or aspirations.

[0129] The setting reference information (specific point setting model) is constructed using data on job seeker information (registration information on job seekers) instead of the job information (job posting) in the first embodiment. For example, the specific point setting model in the second embodiment is a learning model that learns using as training data a combination of job seeker information for learning and specific points related to the job seeker's career or aspirations extracted from the job seeker information. Furthermore, when the specific point setting model is a generation AI, the setting unit 112 inputs the job seeker information, inputs a prompt including an instruction to output specific points related to the job seeker's career or aspirations in the job seeker information, to the specific point setting model, and causes the specific point setting model to output the specific points.

[0130] In addition, in the second embodiment, when a job seeker's registration information is registered or when the content of the registration information is modified, a specific point for the registration information is set using a specific point setting model, and the specific point may be linked to the registration information and stored as a pre-created point.

[0131] In the second embodiment, the search unit 113 searches the job database for job information that satisfies the search criteria input from the job seeker terminal 30 and / or the search criteria set by the search unit 113. Furthermore, the search unit 113 performs a search using vector data of job seeker information or vector data of specific points, thereby making it possible to search for job offers that match the career or aspirations of the job seeker.

[0132] In the second embodiment, the information creating unit 114 creates specific information for each job information item extracted by the search unit 113 based on the information creation reference information.

[0133] The information creation reference information (specific information creation model) is constructed using data on job information (job postings) instead of the job seeker information (job seeker registration information) of the first embodiment. For example, the specific information creation model in the second embodiment is a learning model that learns using as training data a combination of job information for learning, specific points for learning, and specific information created from the job information and the specific points. When the specific information creation model is a generation AI, the information creation unit 114 inputs the job information and the specific points, inputs a prompt to the specific information creation model that includes an instruction to output specific information corresponding to the specific points from the job information, and causes the specific information creation model to output the specific information.

[0134] In the second embodiment, the result display control unit 115 causes the job seeker terminal 30 to display the job information searched for by the search unit 113. In addition, the individual information control unit 116 causes the job seeker terminal 30 to display the job information (job posting, etc.) selected by the searcher (job seeker) from the search results.

[0135] 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.

[0136] This information processing includes a search step, a setting step, an information creation step, a result display control step, and a scout document creation step. In the search step, a search is performed on the search target information. In the setting step, specific points to be extracted from the search target information are set based on input from the searcher before, during, or after the search is performed. In the information creation step, specific information corresponding to the specific points is created for each piece of search target information using keywords or sentences contained in the search target information extracted by the search, based on reference information for information creation. In the result display control step, search results containing the specific information are displayed. In the scout document creation step, a scout document is created for job seekers whose job seeker information is selected by the searcher from among the job seeker information contained in the search results.

[0137] Here, two example patterns of information processing of the search support system 1 are presented in accordance with the first embodiment (a form in which the searcher is a job seeker). Figure 7 is an activity diagram showing an example (first pattern) of the flow of information processing (job seeker search processing) executed by the search support system 1. Below, the information processing will be explained in accordance with each activity in this activity diagram.

[0138] The job seeker search process begins with the user (recruiter) selecting job information. The recruiter specifies the job information on the recruiter terminal 20 (activity A101). The server device 10 acquires the specified job information from the recruiter terminal 20 (activity A102). Next, the server device 10 sets specific points based on the acquired job information (activity A103).

[0139] After setting the specific points, the server device 10 executes a job seeker search based on the specified job information (activity A104). Note that the specific points may be set during or after the job seeker search. Next, the server device 10 creates specific information for each piece of searched job seeker information based on the specific points (activity A105). After creating the specific information, the server device 10 outputs the search results including the specific information to the recruiting party terminal 20 (activity A106). As a result, the job seeker search results are displayed on the recruiting party terminal 20 (activity A107).

[0140] The recruiter selects a job seeker to whom a scout document is to be sent from the search results on the recruiter terminal 20, and instructs the creation of the scout document (activity A108). The server device 10 creates a scout document to which the job advertisement specified by the recruiter is attached and in which specific information about the recipient job seeker is inserted (activity A109). Next, the server device 10 outputs the created scout document to the recruiter terminal 20 (activity A110). As a result, the created scout document is displayed on the recruiter terminal 20 (activity A111).

[0141] 8 is an activity diagram showing another example (second pattern) of the flow of information processing (job seeker search processing) executed by search support system 1. Below, the information processing will be explained along with each activity in this activity diagram.

[0142] The job seeker search process begins with the input of a search query by the user, the recruiter. The recruiter inputs the search query into the recruiter terminal 20 (activity A201). The server device 10 executes a job seeker search based on the input search query (activity A202). Next, the server device 10 primarily outputs the search results to the recruiter terminal 20 (activity A203). As a result, the job seeker search results are primarily displayed on the recruiter terminal 20 (activity A204). Note that the search results here do not include any specific information.

[0143] After the search results are primarily displayed, the recruiter specifies job information on the recruiter terminal 20 (activity A205). The server device 10 acquires the specified job information from the recruiter terminal 20 (activity A206). Next, the server device 10 sets specific points based on the acquired job information (activity A207). After setting the specific points, the server device 10 creates specific information for each piece of searched job seeker information based on the specific points (activity A208). After creating the specific information, the server device 10 secondarily outputs the search results including the specific information to the recruiter terminal 20 (activity A209). As a result, the search results for job seekers are secondarily displayed on the recruiter terminal 20 (activity A210).

[0144] 4. Effect The operation of this embodiment can be summarized as follows: Since the search results include specific information corresponding to the set specific points, the search target information can be screened efficiently, thereby reducing the cost required for searches by the searcher.

[0145] Although the embodiment of the present invention has been described above, the present invention is not limited to this and can be modified as appropriate within the scope of the technical idea of ​​the invention.

[0146] 5.Other In the above embodiment, the server device 10 performs various storage and control functions. However, 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 blockchain technology or the like. In particular, the artificial intelligence unit 120 may be an external component of the server device 10. In this case, the external artificial intelligence unit 120 may be provided, for example, by an artificial intelligence service server and configured to receive inputs from each functional unit of the server device 10, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to the server device 10. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that executes language processing tasks using a language model. The artificial intelligence service server may be constructed using LLM. The artificial intelligence service server receives inputs of prompts such as text, images, and voice, and generates and responds to the prompts.

[0147] Furthermore, the search support system 1 does not necessarily have to include the scout document creation unit 117. Furthermore, the search support system 1 may be used only for job seeker searches by employers, or only for job seekers to search for jobs, or may be used for both job seeker searches and job search.

[0148] The aspect of this embodiment is not limited to the search support system 1, but may be an information processing method or a program. The search support method includes steps executed by the search support system 1. The program causes a computer to execute the steps of the search support system 1.

[0149] It may be provided in the following manner.

[0150] (1) A search support system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program: a search step, executing a search on search target information, wherein the search target information is job seeker information or employment information registered in a database; a setting step, setting specific points to be extracted from the search target information based on input from a searcher before, during, or after the search is performed; an information creation step, based on reference information for information creation, using keywords or sentences contained in the search target information extracted by the search, to create specific information corresponding to the specific points for each piece of search target information, wherein the reference information for information creation includes correlations between the search target information, the specific points, and the specific information; and a result display control step, displaying search results including the specific information.

[0151] (2) In the search support system described in (1) above, in the result display control step, the search target information extracted by the search is displayed in a list format including the specific information for each of the search target information.

[0152] (3) In the search support system described in (1) or (2) above, the reference information for information creation includes a specific information creation model that has been trained to be able to input the search target information and the specific point and output the specific information, and in the information creation step, the search target information and the specific point are input into the specific information creation model, and the specific information is output from the specific information creation model.

[0153] (4) In the search support system described in any one of (1) to (3) above, in the setting step, the specific points related to the requirements of the job offer or the career or aspirations of the job seeker are determined based on the criteria information specified by the searcher and the setting reference information, wherein when the search target information is job seeker information, the criteria information is job offer information, and when the search target information is job offer information, the criteria information is job seeker information, and the setting reference information includes a correlation between the criteria information and the specific points.

[0154] (5) In the search support system described in (4) above, the setting reference information includes a specific point setting model that has been trained to use the standard information as input and to be able to output the specific point, and in the setting step, the standard information is input into the specific point setting model to obtain the specific point that has been output by the specific point setting model.

[0155] (6) In the search support system described in (4) or (5) above, the search target information is job seeker information, and the criteria information is job information for which the searcher searches for candidates.

[0156] (7) In the search support system described in (6) above, in the setting step, the skills or experience required in the job information are set as the specific points, and in the information creation step, the specific information is created, including the career history related to the skills or experience that are the specific points included in the job seeker information.

[0157] (8) In the search support system described in (6) or (7) above, the processor is configured to further execute the following steps: in a scout document creation step, a scout document is created for a job seeker whose job seeker information is selected by the searcher from among the job seeker information included in the search results, wherein the scout document is attached with a job posting included in the standard information and includes the specific information corresponding to the job seeker to whom it is addressed.

[0158] (9) In the search support system described in any one of (1) to (8) above, in the setting step, input for setting the specific point is received from the searcher before the search is performed.

[0159] (10) In the search support system described in (9) above, in the search step, the search is performed by comparing vector data of the reference information specified by the searcher with vector data of the search target information, wherein if the search target information is job seeker information, the reference information is job information, and if the search target information is job information, the reference information is job seeker information.

[0160] (11) In the search support system described in (9) or (10) above, in the setting step, the specific point is set before the search is performed, and in the search step, the search is performed by comparing vector data of the specific point with vector data of the search target information.

[0161] (12) In the search support system described in any one of (1) to (11) above, in the information creation step, a matching index indicating the degree of matching with the specific point is assigned to each of the specific information, and in the result display control step, the specific information to be displayed in the search results is determined based on the matching index.

[0162] (13) In the search support system described in (12) above, in the result display control step, only the search target information for which the specific information with a matching index equal to or greater than a predetermined value is created is displayed in the search results.

[0163] (14) In the search support system described in any one of (1) to (13) above, in the result display control step, a portion of the text representing the specific information is displayed in the search results, and the entire text is displayed in response to selection of the specific information in the search results.

[0164] (15) In the search support system described in (14) above, in the result display control step, when multiple pieces of specific information are created for one of the specific points, the multiple pieces of specific information corresponding to one of the specific points are displayed, and the entire text is displayed only for the specific information selected in the search results.

[0165] (16) A search support method comprising the steps executed by the search support system according to any one of (1) to (15) above.

[0166] (17) A program for causing a computer to execute each step of the search support system described in any one of (1) to (15) above. Of course, this is not the case.

[0167] Finally, while various embodiments of the present disclosure have been described, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. Such embodiments and modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0168] 1: Search support system 2: Communication line 10: Server device 11: Control section 12: Storage section 13: Communications Department 14: Communication bus 20: Recruiter terminal 21: Control unit 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 30: Job seeker terminal 31: Control unit 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communication bus 111: Basic display control section 112: Setting section 113: Search section 114: Information Creation Department 115: Result display control section 116: Individual information control unit 117: Scout Document Creation Department 120: Artificial Intelligence Department 211: Display section 212: Operation acquisition section 311: Display section 312: Operation acquisition section

Claims

1. A search support system, at least one processor; The processor is configured to execute the following steps by reading the program: In the search step, a search is performed on search target information, and the search target information is job seeker information or job information registered in a database; In the setting step, a specific point to be extracted from the search target information is set based on an input from a searcher before, during, or after the execution of the search; In the information creation step, specific information corresponding to the specific point is created for each piece of search target information based on reference information for information creation, using keywords or sentences included in the search target information extracted by the search, wherein the reference information for information creation includes correlations between the search target information, the specific point, and the specific information; In the result display control step, the search support system displays search results including the specific information.

2. 2. The search support system according to claim 1, In the result display control step, the search support system displays the plurality of pieces of search target information extracted by the search in a list format including the respective pieces of specific information.

3. 2. The search support system according to claim 1, the information creation reference information includes a specific information creation model that has been trained to be able to input the search target information and the specific point and output the specific information, In the information creation step, the search target information and the specific point are input to the specific information creation model, and the specific information is output from the specific information creation model.

4. 2. The search support system according to claim 1, A search support system in which, in the setting step, the specific points related to the requirements of a job offer or the career or aspirations of a job seeker are determined based on standard information specified by the searcher and setting reference information, wherein when the search target information is job seeker information, the standard information is job information, and when the search target information is job information, the standard information is job seeker information, and the setting reference information includes a correlation between the standard information and the specific points.

5. 5. The search support system according to claim 4, the setting reference information includes a specific point setting model that is trained to use the reference information as an input and to be able to output the specific point; In the setting step, the reference information is input to the specific point setting model to acquire the specific point output by the specific point setting model.

6. 5. The search support system according to claim 4, the search target information is job seeker information, The search support system, wherein the criteria information is job postings for which the searcher searches for candidates.

7. 7. The search support system according to claim 6, In the setting step, skills or experiences required in the job information are set as the specific points; In the information creation step, the search support system creates the specific information including a career history related to the specific point, which is a skill or experience, included in the job seeker information.

8. 7. The search support system according to claim 6, The processor is further configured to perform the following steps: In the scout document creation step, a scout document is created for a job seeker whose job seeker information is selected by the searcher from among the job seeker information included in the search results, and the scout document is accompanied by a job posting included in the standard information and includes the specific information corresponding to the job seeker to whom it is addressed.

9. 2. The search support system according to claim 1, In the setting step, an input for setting the specific point is received from the searcher before the search is executed.

10. 10. The search support system according to claim 9, A search support system in which, in the search step, the search is performed by comparing vector data of reference information specified by the searcher with vector data of the search target information, wherein if the search target information is job seeker information, the reference information is job information, and if the search target information is job information, the reference information is job seeker information.

11. 10. The search support system according to claim 9, In the setting step, the specific point is set before the search is performed; A search support system, wherein the search step executes the search by comparing vector data of the specific point with vector data of the search target information.

12. 2. The search support system according to claim 1, In the information creation step, a matching index indicating a degree of matching with the specific point is assigned to each of the specific information; In the result display control step, the specific information to be displayed in the search results is determined based on the matching index.

13. 13. The search support system according to claim 12, In the result display control step, only the search target information for which the specific information having a matching index equal to or greater than a predetermined value is created is displayed in the search results.

14. 2. The search support system according to claim 1, In the result display control step, a portion of the text representing the specific information is displayed in the search results, and the entire text is displayed in response to selection of the specific information in the search results.

15. 15. The search support system according to claim 14, In the result display control step, when multiple pieces of specific information are created for one specific point, the search support system displays the multiple pieces of specific information corresponding to one specific point, and displays the entire text for only the specific information selected in the search results.

16. A search support method, comprising: A search support method comprising the steps executed by the search support system according to any one of claims 1 to 15.

17. A program, A program for causing a computer to execute each step of the search support system according to any one of claims 1 to 15.

Images