Search support system, search support method, and program

Abstract

To provide a search support system and the like capable of reducing cost required for search.SOLUTION: There is provided a search support system. The search support system includes a processor. The processor is configured to execute the steps of: acquiring searcher information relating to searchers performing job seeker searches and records including at least one of a first interaction performed by recruiters with respect to job seeker information relating to job seekers and a second interaction performed by the job seekers with respect to recruiter information relating to the recruiters; extracting a group of job seekers to be recommended to the searchers based on the searcher information and the record; and presenting search conditions for the job seeker search, to the searchers based on the group.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 Art

[0002] As disclosed in Patent Document 1, there is known a technique for a job seeker to search for job applicants who meet the conditions based on the job applicant information registered by the job applicant.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above prior art, it is necessary to repeat the search while changing the search conditions until the searcher (job seeker) finds a job applicant who meets the requirements, and the cost required for the search is large.

[0005] In view of the above circumstances, the present invention aims to provide a search support system and the like that can reduce the cost required for the search.

Means for Solving the Problems

[0006] According to one aspect of the present invention, a search support system is provided. This search support system comprises a processor. The processor is configured to perform the following steps: In the acquisition step, it acquires searcher information relating to a searcher performing a job seeker search, and records including at least one of a first interaction made by an employer with respect to the job seeker information relating to the job seeker, and a second interaction made by the job seeker with respect to the employer information relating to the employer. In the extraction step, it extracts a group of job seekers to recommend to the searcher based on the searcher information and records. In the presentation step, it presents the search criteria for the job seeker search to the searcher based on the group.

[0007] In this configuration, searchers with similar criteria (e.g., job postings) can present their search criteria based on past related first interactions (e.g., sending a recruitment letter) or second interactions (e.g., replying to a recruitment letter). This reduces the cost required for the searcher to perform the search. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram illustrating the configuration of Search Support System 1. [Figure 2] This is a block diagram showing the hardware configuration of server device 10. [Figure 3] This block diagram shows the hardware configuration of the searcher terminal 20 and the job seeker terminal 30. [Figure 4] This is a block diagram showing the functions realized by the server device 10 (control unit 11), the searcher terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31). [Figure 5] This is a diagram showing an example of the display screen for scout documents on SD. [Figure 6] This is an example of an interaction table (IT) included in a record. [Figure 7] This is an example of the search criteria presentation screen PD displayed on the user's terminal 20. [Figure 8] This figure shows an example of the distribution of annual income among job seekers belonging to the recommended group. [Figure 9] This is an activity diagram showing the flow of information processing (search condition presentation processing) performed by the search support system 1. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described below with reference to the drawings. The various features shown in the embodiments below can be combined with each other.

[0010] Incidentally, the program for implementing the software appearing in this embodiment may be provided as a non-transitory computer-readable medium, or it may be provided so that it can be downloaded from an external server, or it may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0011] Furthermore, in this embodiment, "part" may include, for example, hardware resources implemented by circuits in a broad sense, and the information processing of software that can be specifically realized by these hardware resources. In addition, various types of information are handled in this embodiment, and these types of information can be represented, for example, by the physical values ​​of signal values ​​representing voltage and current, the high or low values ​​of signal values ​​as a set of binary bits composed of 0s or 1s, or by quantum superposition (so-called qubits), and communication and calculations can be performed on circuits in a broad sense.

[0012] Furthermore, a circuit in a broad sense is a circuit realized by combining at least a suitable combination of circuits, circuits, processors, and memory. In other words, it includes application-specific integrated circuits (ASICs), programmable logic devices (for example, simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)), etc.

[0013] 1. Hardware Configuration This section describes the hardware configuration.

[0014] <Search Support System 1> Figure 1 is a configuration diagram representing the search support system 1. The search support system 1 comprises a communication line 2, a server device 10, multiple searcher terminals 20, and multiple job seeker terminals 30. The server device 10, the searcher terminals 20, and the job seeker terminals 30 are configured to communicate with each other via the communication line 2. The connection between the server device 10, the searcher terminals 20, and the job seeker terminals 30 and the communication line 2 may be wired or wireless.

[0015] The search support system 1 constitutes part of a job posting and job search system used by multiple searchers (first searcher U1 and second searcher U2) and multiple job seekers (first job seeker U3 and second job seeker U4). The search support system 1 primarily handles the searching of job seekers by searchers, the sending of scouting documents (scouting emails or scouting messages) from searchers to job seekers, and the replies of scouting documents by job seekers. In one embodiment, the search support system 1 consists of one or more devices or components. These components will be described below.

[0016] <Server device 10> FIG. 2 is a block diagram showing the hardware configuration of the server device 10. The server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected inside the server device 10 via the communication bus 14.

[0017] <Control unit 11> The control unit 11 performs processing and control of the overall operation related to the server device 10. The control unit 11 is, for example, a Central Processing Unit (CPU). The control unit 11 reads a predetermined program stored in the storage unit 12 to realize various functions related to the server device 10. That is, the information processing by the software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and may be implemented to have a plurality of control units 11 for each function, or a combination thereof.

[0018] <Storage unit 12> The storage unit 12 stores various information defined by the foregoing description. This can be implemented 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 necessary information (arguments, arrays, etc.) related to the calculation of the program. The storage unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

[0019] <Communication unit 13> The communication unit 13 preferably uses wired communication methods such as USB, IEEE1394, Thunderbolt®, and wired LAN network communication, but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, and Bluetooth® communication as needed. In other words, it is more preferable to implement it as a collection of these multiple communication methods. That is, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

[0020] The server device 10 may be on-premises or in a cloud environment. In the case of a cloud-based server device 10, for example, it may provide the above-mentioned functions and processing in the form of SaaS (Software as a Service) or cloud computing.

[0021] <Searcher terminal 20> Figure 3 is a block diagram showing the hardware configuration of the searcher terminal 20 and the job seeker terminal 30. As shown in Figure 3A, the searcher terminal 20 comprises a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, storage unit 22, communication unit 23, input unit 24, and output unit 25 are electrically connected within the searcher terminal 20 via the communication bus 26. The explanation of the control unit 21, storage unit 22, and communication unit 23 is the same as the explanation of each part in the server device 10, so it is omitted. Note that the searcher terminal 20 may be a terminal operated by a recruitment agency that communicates with job seekers on behalf of employers.

[0022] <Input section 24> The input unit 24 receives operation inputs made by the user. The operation inputs are transmitted to the control unit 21 via the communication bus 26 as command signals. The control unit 21 can perform predetermined controls or calculations based on the transmitted command signals as needed. The input unit 24 may be included in the housing of the searcher terminal 20 or it may be external. 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, the input unit 24 can be a switch button, mouse, trackpad, QWERTY keyboard, etc.

[0023] <Output section 25> The output unit 25 displays a graphical user interface (GUI) screen that can be operated by the user. The output unit 25 may be included in the housing of the searcher terminal 20 or it may be an external device. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, liquid crystal display, organic EL display, or plasma display. It is preferable that these display devices be used depending on the type of searcher terminal 20.

[0024] <Job seeker terminal 30> As shown in Figure 3B, the job seeker terminal 30 comprises a control unit 31, a storage unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, storage unit 32, communication unit 33, input unit 34, and output unit 35 are electrically connected within the job seeker terminal 30 via the communication bus 36. The descriptions of the control unit 31, storage unit 32, communication unit 33, input unit 34, and output unit 35 are the same as the descriptions of each part in the searcher terminal 20 and are therefore omitted.

[0025] 2. Functional Configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the memory 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 (the processor provided by the search support system 1).

[0026] Figure 4 is a block diagram showing the functions realized by the server device 10 (control unit 11), the searcher terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

[0027] As shown in Figure 4A, the server device 10 (control unit 11) comprises a basic display control unit 111, a searcher registration unit 112, a job seeker registration unit 113, a record storage unit 114, an acquisition unit 115, an extraction unit 116, a presentation unit 117, a search unit 118, and an artificial intelligence unit 119. As shown in Figure 4B, the searcher terminal 20 (control unit 21) comprises a display unit 211 and an operation reception unit 212. As shown in Figure 4C, the job seeker terminal 30 (control unit 31) comprises a display unit 311 and an operation reception unit 312.

[0028] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the searcher terminal 20 or the job seeker terminal 30. For example, the basic display control unit 111 displays resumes and work histories created by job seekers, job postings and recruitment documents created by employers, search conditions presented by the presentation unit 117, and search results from the search unit 118 on the display unit 211 of the searcher terminal 20 or the display unit 311 of the job seeker terminal 30.

[0029] <Searcher Registration Section 112> The searcher registration unit 112 is configured to register searchers and employers to use the service. For example, the searcher registration unit 112 receives input from the operation reception unit 212 of the searcher terminal 20 and stores in the storage unit 12 employer information relating to the employer to which the searcher belongs or acts as an agent, and searcher information relating to the searcher who is performing the job seeker search.

[0030] Job seekers include organizations (employers) such as for-profit corporations (e.g., companies), non-profit organizations (e.g., cooperatives, foundations, etc.), and public corporations (e.g., local governments, etc.), as well as human resources personnel, recruitment personnel, recruiters, etc., of these organizations, and recruitment agencies and their representatives who act as intermediaries between job seekers and employers on behalf of these organizations. Recruitment agencies are also known as headhunters or agents.

[0031] Job seeker information includes information from the job posting (such as working conditions), information from the organization (such as name, address, representative, and business activities), and information from the recruitment agency (such as name). Job seeker information includes job seeker information from the employer to which the job seeker belongs, information from the job posting that the job seeker is searching for, and information about the attributes of the job seeker, such as the hiring manager conducting the search (such as areas of expertise and industry).

[0032] <Job Seeker Registration Section 113> The job seeker registration unit 113 is configured to register job seekers to use the service. For example, the job seeker registration unit 113 receives input from the operation reception unit 312 of the job seeker terminal 30 and stores job seeker information about the job seeker in the storage unit 12. The job seeker information includes the job seeker's resume, work history, and other profile information.

[0033] A "resume" is a document that primarily contains the job seeker's profile, current situation, educational background, work history, and desired working conditions, while a "work history document," also known as a resume, is a document in which the job seeker communicates their past work experience, skills, qualifications, etc., to the employer. Furthermore, the job seeker's information may also include the industry and job type the job seeker desires.

[0034] <Record storage unit 114> The record storage unit 114 is configured to store records that include at least one of a first interaction with job seeker information, either directly or through a recruitment agency, and a second interaction with job seeker information.

[0035] The first type of interaction includes sending recruitment letters to job seekers by employers or recruitment agencies, viewing job seeker information (resumes, work history, etc.), and flagging job seeker information (adding to favorites, bookmarking, adding to target list).

[0036] Second-tier interactions include job seekers responding to recruitment messages received from employers or recruitment agencies, viewing employer information (job postings, etc.), and flagging employer information (adding to favorites, bookmarking, or adding to target lists).

[0037] The record may include a history of sending recruitment documents to job seekers as the first interaction. This allows the presentation unit 117 to present search criteria based on trends in the attributes of job seekers to whom recruitment documents are sent by employers or recruitment agencies.

[0038] The record may include a history of responses from job seekers to recruitment documents as a second interaction. This allows the presentation unit 117 to present search criteria based on trends in the attributes of job seekers who respond to recruitment documents.

[0039] The record storage unit 114 stores the transmission history of recruitment documents sent by multiple employers or recruitment agencies, and the replies to recruitment documents sent by multiple job seekers. Specifically, for recruitment documents sent by employers or recruitment agencies to job seekers, the record storage unit 114 stores information such as the sender (employer or recruitment agency), the recipient job seeker, the job posting associated with the recruitment document, and the date and time of transmission as a transmission history. In addition, for reply documents sent by job seekers to employers or recruitment agencies, the record storage unit 114 stores information such as the sender (job seeker), the recipient employer or recruitment agency, the recruitment document associated with the reply document, and the date and time of transmission as a transmission history.

[0040] Recruitment letters can be created and sent by the employer (organization) themselves, or created and sent on behalf of the employer by a recruitment agency. The recruitment letters handled by Search Support System 1 include recruitment letters sent by employers to job seekers and recruitment letters sent by recruitment agencies on behalf of employers (recruitment letters sent indirectly from employers).

[0041] Figure 5 shows an example of the display screen SD for a scout document. The display screen SD shows the scout document DO along with a summary DS of the job information in the scout document (items extracted from the job posting). The header of the display screen SD contains a back button SB1, a reply button SB2, and a delete button SB3. The back button SB1 is used to return to the list of scout documents. The reply button SB2 is used to invoke the function to create a reply document. The delete button SB3 is used to delete the open scout document. Each button (including buttons on other screens described later) functions when pressed using an input device (e.g., mouse, trackpad, touch panel, etc.).

[0042] <Acquisition part 115> The acquisition unit 115 is configured to acquire searcher information registered by the searcher registration unit 112 and records stored in the record storage unit 114.

[0043] <Extraction part 116> The extraction unit 116 is configured to extract a group of job seekers to recommend to the searcher based on the searcher information and records acquired by the acquisition unit 115. Specifically, the extraction unit 116 first determines the attributes of the searcher who possesses the searcher information from the items included in the searcher information, and extracts the first instruction or second interaction in the records that the searcher with similar attributes (identical or similar attributes) has been involved in in the past. Next, the extraction unit 116 extracts job seekers related to the extracted first instruction or second interaction as recommended job seekers. The group consisting of the extracted multiple recommended job seekers is designated as the recommended group to recommend to the searcher.

[0044] To determine the attributes of a searcher, the following items from the searcher information are used: the organization or department to which the searcher belongs, information about the job posting the searcher is trying to find (e.g., job title or industry), and the searcher's own attributes. The searcher information may include information from multiple job postings.

[0045] For example, searchers belonging to the same organization or department are considered to have similar attributes. Similarly, searchers who search based on job postings for the same or similar occupation or industry are also considered to have similar attributes. Furthermore, searchers whose own attributes, such as areas of expertise or industry experience, are the same or similar are also considered to have similar attributes.

[0046] A job seeker involved in the first interaction includes, for example, a job seeker to whom a recruitment letter was sent, a job seeker whose information was viewed, flagged, or otherwise manipulated, a job seeker who was searched by an employer or recruitment agency, and so on.

[0047] Job seekers involved in the second interaction include, for example, job seekers who responded to a recruitment letter, or job seekers who performed actions such as viewing or flagging job postings from organizations to which the searcher belongs (or acts as an intermediary).

[0048] The record includes the interaction rate for each individual job seeker, broken down by the searcher's attributes, calculated from the history of first interactions between multiple searchers and second interactions between multiple job seekers. The interaction rate indicates the likelihood that a job seeker will react (e.g., reply to a recruitment message) if an action (e.g., sending a recruitment message) is taken with that job seeker.

[0049] Figure 6 shows an example of an interaction table IT included in a record. The interaction table IT in Figure 6A contains aggregated values ​​based on the interaction history of combinations of job seekers C1-C4 and searchers J1-J5. The numbers in the table are, for example, the total value of points (described later) from interactions that occurred. For example, "0" in the table indicates that no interaction occurred, and "1" indicates that an interaction occurred (for example, a reply to a scout document).

[0050] The numerical values ​​included in the record's interaction table IT may be values ​​relating only to the first interaction, or values ​​relating only to the second interaction. For example, the numerical values ​​included in the interaction table IT may be 1 or 0 indicating whether a job seeker or other searcher sent a scout to a job seeker, or 1 or 0 indicating whether a job seeker responded to a scout from a job seeker or other searcher. Furthermore, the record's interaction table IT may include aggregate values ​​of interactions between job seekers and job postings, or aggregate values ​​of interactions between job seekers and other job postings.

[0051] In the example of interaction table IT in Figure 6A, searcher J1 has received interactions from job seekers C1, C3, and C4 (e.g., replies to recruitment documents), suggesting that further interactions can be expected. However, no interaction has occurred with job seeker C2, indicating that further interactions cannot be expected.

[0052] The extraction unit 116 identifies potential job seekers (for example, job seekers likely to receive recruitment letters) based on the interaction table IT and the attributes of the new searcher. Specifically, the extraction unit 116 first calculates the similarity between the attributes of the new searcher and the attributes of the searchers included in the record. More specifically, the extraction unit 116 vectorizes the searcher attributes and uses cosine similarity or the like on the vector to calculate the similarity between the new searcher and multiple searchers included in the record.

[0053] After calculating the similarity, the extraction unit 116 weights the interaction-based numerical values ​​(interaction aggregate values) corresponding to multiple searchers included in the record according to their similarity to the new searcher. The extraction unit 116 identifies job seekers with a large sum of the weighted interaction aggregate values ​​(expected interaction value) as job seekers who are likely to interact with the new searcher. For example, the extraction unit 116 extracts the top 100 people with high expected interaction values ​​as a recommended group.

[0054] In the example shown in Figure 6A, when a new searcher J6 performs a search, the extraction unit 116 calculates the similarity between the new searcher J6 and the searchers J1 to J5 registered in the record by matching the searcher information. For example, if the similarities between searchers J1 to J5 and searcher J6 are 0.5, 0.3, 0.5, 0.8, and 0.2, respectively, as shown in Figure 6B, then the expected interaction values ​​for job seekers C1 to C4 will be 1.2, 1.6, 1.0, and 2.3, respectively. Therefore, among job seekers C1 to C4, job seeker C4 is the job seeker most likely to have an interaction.

[0055] The extraction unit 116 may use information from multiple job postings that the searcher intends to search for as the attributes of the new searcher. In this case, the extraction unit 116 may use a vector obtained by combining the vectors of each of the multiple job postings as the vector of the searcher's attributes.

[0056] Furthermore, the extraction unit 116 extracts groups based on points set according to the types of the first and second interactions. This allows for weighting of interactions on both the employer and job seeker sides, making it easier to extract job seekers suitable for recommendation.

[0057] For example, the extraction unit 116 assigns 3 points to job seekers who receive a scouting letter, 5 points to job seekers who reply to the scouting letter, and 1 point to job seekers who view the employer's information. Job seekers whose total points exceed a certain value, or whose ranking based on the total points exceeds a certain value, are then selected as a recommended group. In other words, the extraction unit 116 assigns points in the order of replying to a scouting letter, sending a scouting letter, and viewing information. The number of job seekers included in the recommended group is not particularly limited.

[0058] The extraction unit 116 may instruct the artificial intelligence to extract groups based on the searcher information and records, and have the artificial intelligence extract the groups. This makes it possible to appropriately extract recommended groups by using the aggregation of past first instructions or second interactions. Specifically, the extraction unit 116 instructs the artificial intelligence to extract job seekers from among the multiple job seekers to be searched, from the data contained in the records (instruction history) that are related to the data corresponding to the attributes of the searcher indicated by the searcher information, and inputs the searcher information and records into the artificial intelligence, causing the artificial intelligence to output recommended groups.

[0059] <Presentation part 117> The presentation unit 117 is configured to present search criteria for job seekers to the searcher based on the recommended group extracted by the extraction unit 116. Search criteria are search terms (search queries), parameters, etc., that are entered as conditions when searching for job seekers. Figure 7 is an example of the search criteria presentation screen PD displayed on the searcher terminal 20. On the presentation screen PD, the search terms and parameters presented by the presentation unit 117 are displayed, for example, in a list.

[0060] For example, when the acquisition unit 115 acquires information on job postings (issued by employers to which the searcher belongs or acts as an agent) corresponding to the searcher as searcher information, and the history of sending scouting documents to job seekers as records, the extraction unit 116 extracts job seekers who are likely to receive scouting documents for the job postings as recommended job seekers to the searcher, based on the job postings and the history of sending scouting documents. Based on this, the presentation unit 117 presents search conditions to the searcher based on the work history descriptions of the recommended group. This significantly reduces the cost required for the searcher when searching for job seekers who are eligible to receive scouting documents.

[0061] The display unit 117 compares the terms included in the job seeker information of job seekers included in the recommended group with the terms included in the job seeker information of job seekers outside the recommended group and presents the selected terms as search conditions. This makes it possible to present search conditions that make it easier for job seekers belonging to the recommended group to be included in the search results, and less likely for job seekers not belonging to the recommended group to be included in the search results.

[0062] Here, "job seekers outside the recommended group" refers, for example, to all job seekers who are included in the recommended group, excluding those who are included in the recommended group. Furthermore, "job seekers outside the recommended group" may also include job seekers who are not included in the recommended group but who have the same or similar occupational or industrial experience as those included in the recommended group.

[0063] The specific procedure for selecting the terms to be presented as search criteria is as follows: First, the presentation unit 117 extracts the first term from the job seeker information belonging to the recommended group using natural language processing. Similarly, the presentation unit 117 extracts the second term from the job seeker information not belonging to the recommended group using natural language processing. Next, the presentation unit 117 extracts the terms from the extracted first term that were not extracted as the second term and presents them as search criteria terms.

[0064] The presentation unit 117 assigns scores to the terms selected through the above comparison, based on their frequency of use in the job seeker information of job seekers included in the recommended group, and prioritizes presenting terms with higher scores as search conditions. This improves the search accuracy for job seekers belonging to the recommended group. Specifically, the presentation unit 117 presents terms with a score above a certain level, or terms that rank above a certain level when sorted in descending order of score, as search terms. Alternatively, the presentation unit 117 may present all selected terms in order of score.

[0065] The presentation unit 117 assigns a higher score to selected terms the more frequently they are used in the job seeker information of job seekers included in the recommended group. This makes it easier to search for job seekers belonging to the recommended group and job seekers with similar attributes to these job seekers.

[0066] Furthermore, the presentation unit 117 assigns a higher score to selected terms the less frequently they are used in the job seeker information of job seekers outside the recommended group. This makes it more difficult for job seekers who do not belong to the recommended group to be found.

[0067] Furthermore, the presentation unit 117 presents a range of parameters indicating the attributes of job seekers included in the recommended group as search conditions, based on the distribution of job seekers included in the recommended group. This makes it possible to set a volume zone with a large number of job seekers belonging to a specific range as a search condition, based on the distribution of job seekers belonging to the recommended group.

[0068] Examples of "parameters indicating the attributes of job seekers" include annual income. Figure 8 shows an example of the distribution of annual income of job seekers belonging to a recommended group. The annual income of job seekers is extracted from the current annual income of job seekers listed in the job seeker information (resume or work history). In the example in Figure 8A, the presentation unit 117 determines that the range of annual income from 6 million to 12 million yen is the volume zone (parameter indicating the attributes of job seekers) with a large number of corresponding job seekers, and presents this range as a search condition. Note that the number of job seekers or the percentage of the number of job seekers to the total may be set in advance as a threshold for determining the volume zone. Based on this threshold, the presentation unit 117 may determine the volume zone and present the determined volume zone as a search condition. In addition, the distribution of job seekers may be shown using two or more items as axes.

[0069] As shown in Figure 8B, the presentation unit 117 may use a heatmap HM showing the distribution of annual income and occupation of job seekers belonging to the recommended group to present occupations with a large number of job seekers within the annual income range set as a search condition. The heatmap HM in Figure 8B shows the distribution of job seekers belonging to the recommended group, with the annual income information included in the job seeker information as the axis. For example, the presentation unit 117 presents an annual income range of "6 million to 12 million yen" and "occupation A," "occupation C," and "occupation D," which have a large number of job seekers within this annual income range, as search conditions. Alternatively, instead of occupation, the presentation unit 117 may present an annual income range and industry as search conditions based on the distribution of annual income and industry. Furthermore, search conditions may be presented based on the distribution of job seekers for items included in the job seeker information other than annual income, occupation, and industry. Thus, the items used as the distribution of job seekers are not limited to items that can be expressed numerically.

[0070] The presentation unit 117 may instruct the artificial intelligence to create search conditions for job seekers based on the recommended group, and have the artificial intelligence create the search conditions. Specifically, the presentation unit 117 instructs the artificial intelligence to create appropriate words or parameters as search conditions from the job seeker information of job seekers included in the recommended group, and inputs the job seeker information of job seekers included in the recommended group into the artificial intelligence, thereby causing the artificial intelligence to output the search conditions.

[0071] The display unit 117 may also display statistical data of job seekers included in the recommended group on the searcher terminal 20 in a way that does not identify individuals. Examples of statistical data include annual income (average, highest, or lowest), the number of people from each industry or company, etc.

[0072] Furthermore, before presenting the created search conditions to the searcher, the presentation unit 117 may modify the search conditions using the search results obtained by searching for job seekers using those search conditions, and then present the modified search conditions to the searcher. This further improves the accuracy of searching for job seekers included in the recommended group and significantly reduces the cost required for the searcher to perform the search.

[0073] Specifically, the presentation unit 117 instructs the search unit 118 to perform a search using the search terms, parameters, etc., included in the search conditions created based on the recommended group. The presentation unit 117 then modifies, adds, or deletes the search terms and parameters included in the search conditions according to the proportion of job seekers belonging to the recommended group included in the search results obtained by the search unit 118.

[0074] More specifically, the presentation unit 117 modifies the search conditions based on the number of job seekers included in the recommended group among the job seekers in the search results, and presents the modified search conditions to the searcher. This ensures that a certain number of recommended job seekers belonging to the recommended group are detected. For example, the presentation unit 117 repeats the modification of the search results and the execution of the search until the search results include more than a predetermined threshold of recommended job seekers (or the ratio of recommended job seekers included in the search results to the total number of recommended job seekers is greater than or equal to the threshold). Alternatively, the presentation unit 117 may determine whether or not to modify the search conditions based on the number of recommended job seekers included in a certain range at the top of the display order of the search results. After the modification of the search conditions is complete, the presentation unit 117 presents the modified search conditions to the searcher terminal 20.

[0075] In the search criteria modification flow, the presentation unit 117 modifies the search criteria by referring to the recommended job seeker's job seeker information (resume and work history). For example, in selecting search terms based on a score according to the frequency of use in the job seeker information, the presentation unit 117 makes adjustments such as modifying (lowering) the criteria (threshold) for the score of the search terms to be adopted.

[0076] The presentation unit 117 may instruct the artificial intelligence to modify the search conditions and have the artificial intelligence modify the search conditions. Specifically, the presentation unit 117 instructs the artificial intelligence to modify the search conditions, inputs the search conditions, the search results based on those search conditions, and the job seeker information of the recommended job seekers into the artificial intelligence, and has the artificial intelligence output the modified search conditions.

[0077] <Search section 118> The search unit 118 performs a job seeker search based on the search criteria entered by the searcher who has been presented with the search criteria. Specifically, the search unit 118 searches for job seekers based on the search criteria entered from the searcher terminal 20, using the job seeker information registered by the job seeker registration unit 113 (that is, by referring to the job seeker database stored in the storage unit 12). The search unit 118 also displays the search results on the searcher terminal 20.

[0078] The searcher enters the search criteria while referring to the search criteria presented to the searcher terminal 20 by the presentation unit 117. The searcher can use the search criteria as they are, or they can copy or modify parts of the search criteria before entering them.

[0079] <Artificial Intelligence Department 119> The artificial intelligence unit 119 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by each functional unit of the server device 10 may be common to all units, or it may be prepared individually for each functional unit.

[0080] The artificial intelligence unit 119 is an AI (Artificial Intelligence) that includes transformers such as GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, and GPT-3), BERT (Bidirectional Encoder Representations from Transformers), and BART (Bidirectional and Auto-regressive Transformer), as well as language models such as recurrent neural networks (RNNs), and includes generative AI.

[0081] The language model is an example of a learning model using a machine learning algorithm. Specific machine learning algorithms include nearest neighbors, naive Bayes, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 119 can apply the above algorithms as appropriate.

[0082] The artificial intelligence unit 119 has a trained model as artificial intelligence, which is constructed using 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 consists of pairs of input data and output data (correct answer data) for training. Furthermore, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used universally for a wide range of tasks.

[0083] The artificial intelligence unit 119 includes a general-purpose natural language processing learning model, such as a Large Language Model (LLM), which has learned from a vast amount of data. Such a general-purpose learning model includes language models that can handle various tasks without fine-tuning, such as one-shot learning or few-shot learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or it may be a common general-purpose learning model.

[0084] For example, when using separate learning models, one learning model is trained to take searcher information and records as input and output recommended populations, while the other learning model is trained to take recommended populations as input and output search conditions. Alternatively, when using a general-purpose learning model, the system is prompted to take searcher information and records as input and output recommended populations, and also to take recommended populations as input and output search conditions.

[0085] The artificial intelligence included in the artificial intelligence unit 119 is capable of performing additional learning. For example, the artificial intelligence unit 119 learns whether the presented search conditions were actually used by the searcher in a search. In other words, as feedback to the search conditions created and presented by the artificial intelligence, the artificial intelligence unit 119 performs additional learning and fine-tunes using a training dataset that combines the presented search conditions with labeled actual search conditions. As a result, the search conditions output from the learning model are optimized and presented to the user.

[0086] <Display> The display unit 211 of the searcher terminal 20 and the display unit 311 of the job seeker terminal 30 each display the screen indicated by the screen data transmitted from the server device 10.

[0087] <Operation Reception Section> The operation reception unit 212 of the searcher terminal 20 receives operations from the user (searcher) using the searcher terminal 20. The operation reception unit 312 of the job seeker terminal 30 receives operations from the user (job seeker) using the job seeker terminal 30.

[0088] 3. Information Processing Methods This section describes the information processing method of the server device 10. In this information processing method, each part of the server device 10 is executed by a computer as a step.

[0089] Specifically, this information processing method comprises an acquisition step, an extraction step, a presentation step, and a search step. In the acquisition step, searcher information about the searcher performing the job seeker search and records including at least one of the first interaction that the employer had with the job seeker information and the second interaction that the job seeker had with the employer information are obtained. In the extraction step, a group of job seekers to recommend to the searcher is extracted based on the searcher information and records. In the presentation step, search criteria for the job seeker search are presented to the searcher based on the group. In the search step, the job seeker search is performed based on the search criteria entered by the searcher who has been presented with the search criteria.

[0090] Figure 9 is an activity diagram showing the flow of information processing (search condition presentation processing) performed by the search support system 1. The information processing will be explained below in accordance with each activity in this activity diagram.

[0091] The process of presenting search criteria begins after the searcher has registered their searcher information. The searcher inputs an instruction to start a search on the searcher terminal 20 (Activity A101). Upon receiving the instruction to start the search, the server device 10 retrieves the searcher information and records (Retrieval step, Activity A102).

[0092] Next, the server device 10 extracts recommended groups based on the acquired searcher information and records (extraction step, activity A103). Furthermore, the server device 10 creates and modifies search conditions based on the recommended groups (activity A104). Modification of search conditions is made through feedback from the results of actual searches performed using those search conditions. After the search conditions are finalized, the server device 10 presents the search conditions to the searcher terminal 20 (presentation step, activity A105). As a result, the search conditions are presented to the searcher terminal 20 (activity A106).

[0093] After the search criteria are displayed on the searcher terminal 20, the searcher, referring to the displayed search criteria, enters the search criteria to be used in the designated input field on the searcher terminal 20 and instructs the server device 10 to perform the search (Activity A107). The server device 10 receives the search criteria from the searcher terminal 20 and performs a search for job seekers based on those criteria (Activity A108). After the search is performed, the server device 10 outputs the search results to the searcher terminal 20 (Activity A109). As a result, the search results are displayed on the searcher terminal 20 (Activity A110).

[0094] 4. Effect The operation of this embodiment can be summarized as follows: Searchers with similar conditions to the searcher (e.g., job postings) can present search criteria based on past related first interactions (e.g., sending a recruitment letter) or second interactions (e.g., replying to a recruitment letter). Therefore, the cost required for the searcher to perform a search is reduced.

[0095] Although embodiments of the present invention have been described above, the present invention is not limited thereto and can be modified as appropriate without departing from the technical spirit of the invention.

[0096] 5. Others In the above embodiment, the server device 10 performed various storage and control functions, but instead of the server device 10, multiple external devices may be used. That is, various information and programs may be stored in a distributed manner across multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 119 may be an external component of the server device 10. In that case, the external artificial intelligence unit 119 is configured to receive input from each functional unit of the server device 10 and return the instructed output to the server device 10.

[0097] The embodiments of this model are not limited to the search support system 1, but may also be an information processing method or a program. The search support method comprises each step of the search support system 1. The program causes a computer to execute each step of the search support system 1.

[0098] The product may be provided in any of the following embodiments.

[0099] (1) A search support system comprising a processor, wherein the processor is configured to perform the following steps: in the acquisition step, it acquires searcher information relating to a searcher performing a job seeker search, and a record including at least one of a first interaction made by an employer with respect to the job seeker information relating to the job seeker and a second interaction made by the job seeker with respect to the employer information relating to the employer; in the extraction step, it extracts a group of job seekers to recommend to the searcher based on the searcher information and the record; and in the presentation step, it presents the search conditions for the job seeker search to the searcher based on the group.

[0100] (2) A search support system as described in (1) above, wherein in the extraction step, the system instructs the artificial intelligence to extract the group based on the searcher information and the record, and causes the artificial intelligence to extract the group.

[0101] (3) A search support system as described in (1) or (2) above, wherein in the presentation step, the system presents selected terms as search conditions by comparing terms included in the job seeker information of job seekers included in the group with terms included in the job seeker information of job seekers outside the group.

[0102] (4) A search support system as described in (3) above, wherein in the presentation step, the selected terms are scored according to their frequency of use in the job seeker information of the job seekers included in the group, and the terms with higher scores are presented preferentially as search conditions.

[0103] (5) A search support system as described in (4) above, wherein in the presentation step, the higher the frequency of use of the selected words in the job seeker information of the job seekers included in the group, the higher the score.

[0104] (6) A search support system as described in (4) or (5) above, wherein in the presentation step, the selected term is given a higher score the less frequently it is used in the job seeker information of job seekers outside the group.

[0105] (7) A search support system according to any one of (1) to (6) above, wherein in the presentation step, the system presents a range of parameters indicating the attributes of job seekers included in the group as the search conditions, based on the distribution of job seekers included in the group.

[0106] (8) A search support system according to any one of (1) to (7) above, wherein in the presentation step, the search support system modifies the search conditions using the search results obtained by searching for job seekers using the search conditions, and presents the modified search conditions to the searcher.

[0107] (9) A search support system as described in (8) above, wherein in the presentation step, the search conditions are modified based on the number of job seekers included in the group among the job seekers included in the search results, and the modified search conditions are presented to the searcher.

[0108] (10) A search support system according to any one of (1) to (9) above, wherein in the extraction step, the system extracts the group based on points set according to the type of the first interaction and the second interaction.

[0109] (11) A search support system described in any one of (1) to (10) above, wherein the searcher information is job posting information, information about the searcher's attributes, information about the organization, or information about the recruitment agency.

[0110] (12) A search support system according to any one of (1) to (11) above, wherein the record includes the history of sending a scouting document to the job seeker as the first interaction.

[0111] (13) A search support system according to any one of (1) to (12) above, wherein the record includes the history of replies from the job seeker to the scouting document as the second interaction.

[0112] (14) A search support system as described in (1) above, wherein in the acquisition step, information on job postings corresponding to the searcher as searcher information and the history of sending scout documents to the job seeker as records; in the extraction step, based on the job postings and the history of sending scout documents, job seekers who are likely to receive scout documents for the job postings are extracted as job seekers to be recommended to the searcher; and in the presentation step, the search conditions are presented to the searcher based on the text relating to the work history of the group.

[0113] (15) A search support method comprising each step of the search support system described in any one of (1) to (14) above.

[0114] (16) A program that causes a computer to perform each step of the search assistance system described in any one of (1) to (14) above. Of course, this is not always the case.

[0115] Finally, while various embodiments relating to this disclosure have been described, these are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of symbols]

[0116] 1: Search support system 2: Communication lines 10: Server device 11: Control Unit 12: Storage section 13: Communications Department 14: Communications bus 20: Searcher terminal 21: Control Unit 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communications bus 30: Job seeker terminal 31: Control Unit 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communications bus 111: Basic Display Control Unit 112: Searcher Registration Department 113: Job Seeker Registration Department 114: Record storage unit 115: Acquisition Department 116:Extraction part 117:Presentation part 118: Search Department 119: Artificial Intelligence Department 211:Display section 212: Operation Reception Section 311: Display section 312: Operation Reception Section

Claims

1. It is a search support system, Equipped with a processor, The aforementioned processor is configured to perform the following steps: In the acquisition step, we acquire searcher information that includes at least the information from the job posting. In the presentation step, the artificial intelligence is instructed to create search conditions for job seekers based on the searcher information, the artificial intelligence creates the search conditions, and the created search conditions are presented to the searcher, where the artificial intelligence is a large-scale language model or generative AI. A search support system that, in the search step, performs a job seeker search based on the presented search conditions, or search conditions in which part of the presented search conditions has been modified.

2. In the search support system described in Claim 1, In the aforementioned presentation step, the search support system determines the attributes of the searcher based on the searcher information, and further instructs the artificial intelligence to create the search conditions based on the determined attributes, causing the artificial intelligence to create the search conditions, where the attributes are the job title or industry of the job posting included in the searcher information.

3. In the search support system described in Claim 1, In the acquisition step described above, a record is further acquired that includes at least one of the first interaction the employer made with the job seeker's information about the job seeker and the second interaction the job seeker made with the employer's information about the employer. In the aforementioned presentation step, the search support system instructs the artificial intelligence to create the search conditions based on the searcher information and the records, and causes the artificial intelligence to create the search conditions.

4. In the search support system described in claim 3, In the aforementioned presentation step, the search support system presents, based on the searcher information, the terms extracted from the job seeker information of the job seeker included in the first interaction as the search conditions.

5. In the search support system described in claim 4, In the aforementioned presentation step, the search support system assigns a score to the terms according to their frequency of use in the job seeker information, and preferentially presents the terms with higher scores as search conditions.

6. In the search support system described in claim 1, In the presentation step, the search support system modifies the search criteria using the search results obtained by searching for job seekers using the search criteria, and presents the modified search criteria to the searcher.

7. In the search support system described in claim 1, A search support system in which the aforementioned searcher information further includes information about the searcher's attributes, organizational information, or information about a recruitment agency.

8. In the search support system described in claim 3, The record includes a search support system that includes the history of sending recruitment documents to job seekers as the first interaction.

9. In the search support system described in claim 3, The aforementioned record is a search support system that includes the history of replies from job seekers to recruitment documents as the second interaction.

10. In the search support system described in claim 8, In the presentation step, the search support system instructs the artificial intelligence to create the search conditions based on the job posting and the history of the scouting document transmission, has the artificial intelligence create the search conditions, and presents the created search conditions to the searcher.

11. A search support method, A search support method comprising an information processing device performing each step of the search support system described in any one of claims 1 to 10.

12. It is a program, A program that causes a computer to perform each step of the search support system described in any one of claims 1 to 10.

Images