Case Personnel Matching System, Information Processing Method, and Program

Abstract

Efficiently match a large number of cases with a large number of talents. 【Solution means】The control unit acquires a plurality of case information regarding cases, the case information includes a description and conditions of the case, acquires a plurality of talent information regarding talents, the talent information includes a description, attributes and wishes of the talent, generates a prompt based on the plurality of case information and the plurality of talent information, the prompt includes an instruction to match the case with the talent, and outputs a result regarding the matching of the case with the talent based on the data output from the learned model according to the prompt.

Description

Technical Field

[0001] The present invention relates to a project talent matching system, an information processing method, and a program.

Background Art

[0002] Patent Document 1 discloses a technique that enables a user to confirm target information in a more convenient manner.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the technique of Patent Document 1, there is room for improvement in the technique of efficiently matching a large number of projects and a large number of talents.

Means for Solving the Problems

[0005] According to one aspect of the present invention, a project talent matching system is provided. The project talent matching system has at least one or more control units. The control unit acquires a plurality of project information regarding projects, the project information includes a description and conditions of the project, acquires a plurality of talent information regarding talents, the talent information includes a description, attributes, and wishes of the talent, generates a prompt based on the plurality of project information and the plurality of talent information, the prompt includes an instruction to match the project and the talent, and outputs a result regarding the matching of the project and the talent based on the data output from the learned model in response to the prompt.

Brief Description of the Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0007] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various features shown in the following embodiments (including modified examples; the same applies hereinafter) can be combined with each other.

[0008] <Embodiment 1> 1. System Configuration of the Case-Personnel Matching System FIG. 1 is a diagram showing an example of the system configuration of the project personnel matching system 1000. As shown in FIG. 1, the project personnel matching system 1000 includes, as a system configuration, a server device 100, a client device 110, a client device 120, and a client device 130. The server device 100 is an example of a computer. The server device 100, the client device 110, the client device 120, and the client device 130 are communicably connected via a network 150. The network 150 is any one of a WAN (Wide Area Network), a LAN (Local Area Network), and the Internet, or any combination thereof. The network 150 is configured to enable communication between devices connected to the network 150 via wired and / or wireless means. The project personnel matching system 1000 is a system that provides a so-called SaaS (Software as a Service) function.

[0009] The server device 100 executes a process of matching projects and personnel. Note that the number of server devices included in the project personnel matching system 1000 may be one or a plurality. When there are a plurality of server devices included in the project personnel matching system 1000, the functions of the server device 100 are provided as a so-called distributed system.

[0010] The client device 110 is a device operated by a person in charge of an SES business operator who uses the functions of the server device 100. The SES business operator is a business operator who dispatches personnel such as engineers introduced by a personnel placement company or the like to each project of a client destination introduced by a project introduction company or the like, and obtains a consideration by providing the labor force and / or technical force of the engineers.

[0011] The client device 120 is a device operated by a person in charge at a staffing agency, and introduces human resources such as engineers to SES operators. The client device 120 sends introduction emails for each of a plurality of human resources to a predetermined email address of a person in charge such as an SES operator of the client device 110 at a predetermined timing, such as once a day. The client device 120 sends, for example, introduction emails for about 10,000 human resources (hereinafter also referred to as human resource introduction emails) to a predetermined email address of a person in charge such as an SES operator of the client device 110 at one time. In practice, instead of the client device 120, a predetermined server device or system of the staffing agency may send the human resource introduction emails.

[0012] The client device 130 is a device operated by a person in charge at a project referral company, and introduces projects that are recruiting human resources such as engineers to SES operators. The client device 130 sends introduction emails for each of a plurality of projects to a predetermined email address of a person in charge such as an SES operator of the client device 110 at a predetermined timing, such as once a day. The client device 130 sends, for example, introduction emails for about 10,000 projects (hereinafter also referred to as project introduction emails) to a predetermined email address of a person in charge such as an SES operator of the client device 110 at one time. In practice, instead of the client device 130, a predetermined server device or system of the project referral company may send the project introduction emails.

[0013] The server device 100 receives the human resource introduction emails and project introduction emails sent to a predetermined email address of a person in charge such as an SES operator using technologies such as SMTP (Simple Mail Transfer Protocol), stores them in a predetermined storage area, and executes matching processes and the like as described later.

[0014] Here, the case personnel matching system described in the claims may be composed of a plurality of devices or may be composed of a single device. When the case personnel matching system described in the claims is composed of a single device, an example of such a device is, for example, the server device 100. When the case personnel matching system described in the claims is composed of a plurality of devices, examples of the plurality of devices are, for example, a distributed system that provides the functions of the server device 100, or a server device that provides the functions of the server device 100 and the large language model described later, or the server device 100 and the client device 110.

[0015] 2. Hardware Configuration Diagram (1) Hardware Configuration of Server Device 100 FIG. 2 is a diagram showing an example of the hardware configuration of the server device 100. As shown in FIG. 2, the server device 100 includes, as its hardware configuration, a control unit 210, a storage unit 220, and a communication unit 230.

[0016] The control unit 210 is a CPU (Central Processing Unit) or the like, which controls the entire server device 100 and executes processing according to the input information and the like.

[0017] The storage unit 220 is any one of an HDD (Hard Disk Drive), a ROM (Read Only Memory), a RAM (Random Access Memory), an SSD (Solid Sate Drive), or any combination thereof, and stores programs and data (for example, a plurality of personnel introduction emails, a plurality of case introduction emails, etc.) used when the control unit 210 executes processing based on the programs.

[0018] The storage unit 220 is an example of a storage medium. In the specification, it is described that the data used when the control unit 210 executes processing based on a program is stored in the storage unit 220, but it may also be stored in the storage unit of another device that can communicate with the server device 100. That is, the data may be stored in the storage unit of any device as long as the control unit 210 can refer to and / or acquire it. By the control unit 210 executing processing based on the program stored in the storage unit 220, the function of matching cases and human resources of the server device 100 and the processing of the server device 100 in the sequence diagrams shown in FIGS. 4, 6, and 8 described later are realized.

[0019] The communication unit 230 connects the server device 100 to a network and controls communication with other devices (for example, other server devices and / or client devices 110, etc.).

[0020] The server device 100 may include a plurality of each hardware configuration shown in FIG. 1. For example, the server device 100 may have a plurality of control units. The same applies to the client device 110, client device 120, and client device 130 shown below.

[0021] (2) Hardware Configuration of Client Device 110 FIG. 3 is a diagram showing an example of the hardware configuration of the client device 110. As shown in FIG. 3, the client device 110 includes, as a hardware configuration, a control unit 310, a storage unit 320, an input unit 330, an output unit 340, and a communication unit 350.

[0022] The control unit 310 is a CPU or the like, controls the entire client device 110, and executes processing according to the input information and the like.

[0023] The storage unit 320 is any one of an HDD, ROM, RAM, SSD, etc., or any combination thereof, and stores programs, data, etc. that the control unit 310 uses when executing processing based on the programs. The storage unit 320 is an example of a storage medium.

[0024] In the specification, it is described that the data used by the control unit 310 when executing processing based on the program is stored in the storage unit 320, but it may be stored in the storage unit of another device that can communicate with the client device 110. The data may be stored in the storage unit of any device as long as the control unit 310 can refer to and / or acquire it. By executing processing based on the program stored in the storage unit 320, the control unit 310 realizes the functions of the client device 110.

[0025] The input unit 330 is a device that inputs information into the client device 110 according to the operation of the operator. The input unit 330 receives the operation input made by the user. The operation input is transferred as a command signal to the control unit 310 via the internal bus 390. The control unit 310 can execute predetermined control and / or calculation based on the transferred command signal as necessary. The input unit 330 may be included in the housing of the client device 110 or may be externally attached. For example, the input unit 330 may be integrated with the output unit 340 and implemented as a touch panel. When the input unit 330 is implemented as a touch panel, the user can input a tap operation, a swipe operation, etc. to the input unit 330. Instead of the touch panel, the input unit 330 may be a switch button, a mouse, a track pad, a keyboard, etc.

[0026] The output unit 340 is, for example, a display unit typified by a display, and is a device that outputs (displays) information as a screen of a graphical user interface (GUI) operable by an operator. The output unit 340 may be included in the housing of the client device 110 or may be externally attached. More specifically, the output unit 340 can be implemented as a display device such as a liquid crystal display, an organic EL (Electron-Luminescence) display, or a plasma display. These display devices are preferably selectively implemented according to the type of the client device 110.

[0027] The communication unit 350 connects the client device 110 to the network 150 and controls communication with other devices.

[0028] The hardware configurations of the client device 120 and the client device 130 are also the same as the hardware configuration of the client device 110.

[0029] 3. Information Processing (1) Outline of Processing The control unit 210 acquires a plurality of case information regarding cases from a plurality of case introduction emails stored in the storage unit 220 and the like. The case information includes a description and conditions of the case. The control unit 210 acquires a plurality of human resource information regarding human resources from the storage unit 220 and the like. The human resource information includes a description, attributes, and wishes of the human resources. Based on the plurality of case information and the plurality of human resource information, the control unit 210 generates a prompt. The prompt includes an instruction to match the case with the human resource. Based on the data output from the learned model according to the prompt, the control unit 210 outputs a result regarding the matching of the case with the human resource.

[0030] By performing such processing, a large number of cases and a large number of human resources can be efficiently matched.

[0031] (2) Details of Processing (2-1) Matching of a Plurality of Case Information and a Plurality of Human Resource Information FIG. 4 is a sequence diagram (part 1) showing an example of information processing of the project talent matching system 1000. In sequence SQ401, the control unit 210 receives a request from the client device 110 to output a result screen of matching between a plurality of project information and a plurality of talent information. For example, when an operator of the client device 110 accesses a specific URL (Uniform Resource Locator) by a predetermined operation or clicks a predetermined button, the control unit 210 receives a request (HTTP request) to output a result screen of matching.

[0032] Here, a plurality of talent introduction emails and a plurality of project introduction emails are stored in a predetermined storage area such as the storage unit 220. The control unit 210 extracts a plurality of talent information from each of the plurality of talent introduction emails and stores them in a predetermined storage area such as the storage unit 220. The talent information includes a description of the talent, the attributes of the talent, and the wishes of the talent (also referred to as desired conditions).

[0033] The description of the talent is information expressed in a narrative or semi-structured text format about the talent's skills, experience, achievements, strengths, career path, self-promotion, etc. The description of the talent is information that plays a role in conveying aspects that cannot be fully captured by numbers or categories, such as the depth of an individual.

[0034] The attributes of the talent are quantitative or categorical factual information about the talent. It can also be said that it is information in a form that can be answered with options or numbers for pre-defined items. Examples of the attributes of the talent include, regarding technical skills, programming language: C++ (number of years of experience: 5 years, proficiency: advanced), regarding experience, number of years of development experience: 5 years, and held qualifications: basic information technology engineer, etc.

[0035] Hope is information that shows subjective and future-oriented aspects, such as the conditions that talents value when choosing a project, the preferred working style, the content of the project, etc. It is not just about skill matching, but also information that affects the satisfaction and long-term performance of talents. Examples of hopes include, regarding unit price / remuneration, the desired unit price: 700,000 yen or more per month (mandatory); regarding work location / working style, the desired work location: fully remote (mandatory) or within the 23 wards of Tokyo (desired); regarding the project content, the desired industry / domain: FinTech or healthcare-related (desired); regarding the contract period, the desired contract period: a long-term project of one year or more (desired); regarding the corporate / organizational culture, a venture company with a sense of speed (desired), etc.

[0036] Here, the control unit 210 performs a name-matching process on a plurality of talent information stored in a predetermined storage area such as the storage unit 220. As the name-matching process, the control unit 210 performs operations such as unifying the format, unifying the notation, removing unnecessary data such as spaces and symbols, grouping the data with a specific key (blocking key), calculating the similarity for each attribute for each record pair within the blocked group, and determining whether two records are talent information of the same person based on the calculated similarity for each attribute and the defined rules. When there is duplicate (or identical) talent information, the control unit 210 updates it with the talent information obtained later based on the date and time information. The date and time information is, for example, the information on the transmission date and time of the talent introduction email containing the talent information. In the following, it will be described assuming that the plurality of talent information is the information after the name-matching process is executed.

[0037] Similarly, the control unit 210 extracts a plurality of case information from each of the plurality of case introduction emails and stores it in a predetermined storage area such as the storage unit 220. The case information includes the description and conditions of the case.

[0038] The description of a case is information expressed in a free-form or semi-structured text format, covering the background, purpose, business content, project overview, details of the tasks to be undertaken, team structure, technology stack used, development environment, project phases, and the appeal, etc. of the case. The description of the case serves to convey the overall picture and charm of the case and to arouse the interest of talents.

[0039] The conditions of a case are specific and quantitative information such as the essential skills and experience required by the case side for talents, or the remuneration and employment system provided, etc. These are items that are directly compared with the "attributes" and "hopes" of the talent side and serve as the requirement definitions for matching. Examples of the conditions of a case include, for the essential conditions, experience in the requirements definition or basic design phase, and for the acceptable conditions, examples such as experience in system development in the financial industry. The recruitment conditions include contract type: outsourcing contract, estimated monthly unit price: 700,000 yen to 900,000 yen, work location: Chiyoda-ku, Tokyo [project destination] (remote work: possible up to 1 day per week), working hours: 9:30 to 18:30 (1-hour break), contract period: immediate to the end of [year and month] (renewal possible thereafter), etc.

[0040] Here, the control unit 210 performs a clustering process on a plurality of case information stored in a predetermined storage area such as the storage unit 220. As the clustering process, the control unit 210 performs operations such as unifying the format, unifying the notation, removing unnecessary data such as spaces and symbols, grouping the data with a specific key (blocking key), calculating the similarity for each attribute for each record pair within the blocked group, and determining whether two records are case information of the same case based on the calculated similarity for each attribute and the defined rules. When there is duplicate case information, the control unit 210 updates it with the case information obtained later based on the date and time. The date and time information is, for example, the information on the transmission date and time of the case introduction email containing the case information. In the following, the description will be made assuming that the plurality of case information is the information after the clustering process has been executed.

[0041] By executing the collation process as described above, it is possible to maintain and improve the accuracy and consistency of the case information within the system. Also, by eliminating duplicate data, storage capacity can be saved, and by reducing the amount of data to be processed such as in the matching process, the overall performance can be improved. Further, it becomes possible to perform matching always based on the latest case information, and the relevance and reliability of the matching results can be enhanced.

[0042] In sequence SQ402, the control unit 210 acquires a plurality of case information from a predetermined storage area such as the storage unit 220.

[0043] In sequence SQ403, the control unit 210 acquires a plurality of human resource information from a predetermined storage area such as the storage unit 220.

[0044] In sequence SQ404, the control unit 210 generates a prompt based on a plurality of case information and a plurality of human resource information. A prompt is an input for giving some instructions and / or questions to a learned model to prompt a response and / or generation. The prompt includes instructions for a task, provision of context, specification of format, data to be processed, and the like. The control unit 210 includes in the prompt, as an instruction for the task, an instruction to match a case with a human resource. Further, the control unit 210 includes in the prompt, as an instruction for the task, an instruction to include "the degree of matching (degree of agreement) between the case information of the case and the human resource information of the human resource" in the result regarding the matching. The degree of matching is also referred to as the match degree. By including the match degree (quantitative index) in the matching result, it becomes possible to objectively compare and rank a plurality of matching candidates. Also, by structuring the result in the form of a match degree, when receiving instructions for subsequent processing (filtering, sorting, display, etc.), the control unit 210 can perform the subsequent processing more efficiently. Also, it helps to judge the reliability and basis of the matching and can enhance the utility value of the system output. Further, the control unit 210 includes in the specification of the format an instruction to include "the reason for the matching between the case information of the case and the human resource information of the human resource" in the result regarding the matching. By including the reason for the matching in the matching result, the interpretability and transparency of the matching result can be improved. Also, by showing the reason why the system made that matching, it becomes easier for the user to trust the result. Also, by checking the reason, the user can quickly judge the validity of the matching, and the efficiency of system utilization is improved. Further, the control unit 210 includes in the prompt, as data to be processed, a plurality of case information and a plurality of human resource information.

[0045] In addition, the control unit 210 may also include an instruction in the prompt to output, as an instruction for the task, information on whether the human resources meet the essential skills and experience required by the project side. By adopting such a configuration, when, for example, displaying a matching result screen described later, the control unit 210 can display on the matching result screen information on whether the human resources meet the essential skills and experience required by the project side (for example, an image of a circle if they meet the requirements, an image of a cross if they do not meet the requirements, etc.).

[0046] A learned model is an AI (Artificial Intelligence) model whose internal parameters (weights and / or biases) etc. have been adjusted through a machine learning process (also referred to as learning or training) so that it can execute a task. So-called large language models (LLMs) and multimodal models are also examples of learned models. A large language model is a type of artificial intelligence model for natural language processing that is trained using a vast amount of text data. A multimodal model is an artificial intelligence (AI) model that integrates and processes multiple different types of data (modalities). Examples of multiple different types of data include text, images, audio, video, numerical data, etc. The learned model may be implemented on another server device that can communicate with the server device 100, or may be implemented on the server device 100. For the sake of simplicity of explanation in the specification, the explanation will be given by taking a large language model as an example of a learned model.

[0047] In sequence SQ404, the control unit 210 inputs the generated prompt into the large language model. In sequence SQ405, the control unit 210 receives, as output data from the large language model, a matching result between a plurality of project information and a plurality of human resource information.

[0048] In sequence SQ405, the control unit 210 generates a matching result screen including a result related to the matching based on the matching result received from the large language model. In sequence SQ407, the control unit 210 transmits the generated matching result screen to the client device 110. In sequence SQ408, the control unit 310 displays the received matching result screen on the output unit 340. As another example, the control unit 210 may transmit the data necessary for generating the matching result screen to the client device 110. The control unit 310 of the client device 110 may generate a matching result screen based on the received data and display it on the output unit 340. However, for the sake of simplicity of explanation, in this specification, it is described that the control unit 210 generates the matching result screen and transmits it to the client device. The same applies to other screens.

[0049] FIG. 5 is a diagram showing an example of the matching result screen 500. The matching result screen 500 is an example of the screen of the matching result displayed by the process shown in FIG. 4. The matching result screen 500 includes a project block and a talent item. In the example of FIG. 5, the project blocks are project block 510 and project block 520. The project block is a section showing the matching result of each project. The project block includes the project name, a brief description of the project, and a list of talents matched to the project. The talent item is an item for displaying the information of each matched talent. An item is a part or element displayed on the screen. In the example of FIG. 5, as the talents matched to the project corresponding to project block 510, talent items 511, 512, and 513 are included. Also, as the talents matched to the project corresponding to project block 520, talent items 521 and 522 are included. Each talent item includes the talent name, a simple attribute of the talent, the matching degree, and the reason for the match.

[0050] As an example, the control unit 210 may generate a matching result screen including matching results with a matching degree equal to or higher than a threshold value (for example, 70%) based on the matching degree included in the matching result received from the large language model and the threshold value of the matching degree. This process is an example of a process in which the control unit 210 outputs a result regarding the matching between a case and a human resource based on data output from a large language model, where the degree of match is equal to or higher than a set value. By executing such a process, it is possible to reduce noise in the output information by excluding unnecessary or low-degree-of-match results, thereby improving the usability of the system. In addition, it is possible to reduce the amount of data to be reviewed by humans subsequently or processed by other systems, and improve the overall processing efficiency. Further, it leads to savings in system resources (communication bandwidth, display load, storage, etc.). When the threshold value of the degree of match is 70% or more, in the example of FIG. 5, the case block 510 includes the human resource item 511 and the human resource item 512. Further, the case block 520 includes the human resource item 511 and the human resource item 512.

[0051] As another example, the control unit 210 may generate a matching result screen such that the number of included matching results is equal to or less than a threshold value based on the number of matching results received from the large language model and the threshold value of the number of matching results. In the example of FIG. 5, since three human resource matching results are included for the "website development project" and two human resource matching results are included for the "new service planning / launch", it can be said that a total of five matching results are included. The control unit 210 generates a matching result screen such that the number of such matching results is equal to or less than a threshold value (for example, N pieces). For example, the control unit 210 generates a screen including all the matching results received from the large language model, and sorts the matching results from the one with the highest degree of match based on the degree of match included in each matching result. The control unit 210 selects the top N pieces from the sorted list of matching results, and transmits a matching result screen including the selected top N pieces of matching results to the client device 110. This process is an example of a process in which the control unit 210 outputs the results related to matching so that the number of results related to matching is equal to or less than a threshold value. By executing such a process, it is possible to improve the visibility and usability of the display screen and prevent the user from being overwhelmed by a large amount of information. In addition, it is possible to suppress the consumption of system resources (communication bandwidth, memory, display processing, etc.) and reduce the load on the entire system. Further, by focusing on and presenting a small number of optimal results that the user is most likely to be interested in, it is possible to improve the efficiency of information search.

[0052] (2-2) Matching between the human resource information of the human resources selected on the human resource selection screen and a plurality of project information FIG. 6 is a sequence diagram (part 2) showing an example of information processing of the project-human resource matching system 1000. In sequence SQ601, the control unit 210 receives a request to output a human resource selection screen for selecting a human resource from the client device 110. For example, when an operator of the client device 110 accesses a specific URL (Uniform Resource Locator) by a predetermined operation or clicks a predetermined button, the control unit 210 receives a request to output a human resource selection screen (HTTP request).

[0053] In sequence SQ602, the control unit 210 acquires a plurality of human resource information from a predetermined storage area such as the storage unit 220.

[0054] In sequence SQ603, the control unit 210 generates a human resource selection screen for selecting one human resource from a plurality of human resources based on the plurality of human resource information. In sequence SQ604, the control unit 210 transmits the generated human resource selection screen to the client device 110. The process of sequence SQ603, or the processes of sequence SQ603 and sequence SQ604, is an example of a process of displaying a human resource selection screen for selecting a human resource.

[0055] In sequence SQ605, the control unit 310 displays the received human resource selection screen on the output unit 340. When a single human resource is selected via the human resource selection screen, in sequence SQ606, the control unit 310 transmits the human resource information of the selected human resource to the server device 100. The control unit 210 receives the human resource information of the human resource selected from the client device 110.

[0056] In sequence SQ607, the control unit 210 acquires a plurality of project information from a predetermined storage area such as the storage unit 220.

[0057] In sequence SQ608, the control unit 210 generates a prompt based on the human resource information of the selected single human resource and the plurality of project information. As described above, the prompt includes instructions for tasks, provision of context, specification of format, data to be processed, etc. The control unit 210 includes in the prompt, as an instruction for the task, an instruction to match the project and the human resource. Further, the control unit 210 includes in the prompt, as an instruction for the task, an instruction to include "the degree of matching (degree of agreement) between the project information of the project and the human resource information of the human resource" in the result regarding the matching. Further, the control unit 210 includes in the specification of the format an instruction to include "the reason for the matching between the project information of the project and the human resource information of the human resource" in the result regarding the matching. Further, the control unit 210 includes in the prompt, as the data to be processed, the plurality of project information and the selected single human resource information. The process of sequence SQ608 is an example of a process of generating a prompt based on the project information of a plurality of projects and the human resource information of the human resource selected via the human resource selection screen among the plurality of human resource information.

[0058] In sequence SQ609, the control unit 210 inputs the generated prompt into the large language model. In sequence SQ610, the control unit 210 receives, as output data from the large language model, the matching result between the plurality of project information and the human resource information of the selected human resource.

[0059] In sequence SQ611, the control unit 210 generates a matching result screen including a result regarding matching based on the matching result received from the large language model. In sequence SQ612, the control unit 210 transmits the generated matching result screen to the client device 110. The process of sequence SQ611, or the processes of sequence SQ611 and sequence SQ612, is an example of a process that outputs a result regarding the matching between the human resources selected via the human resources selection screen and a plurality of cases based on the data output from the large language model in response to a prompt. In sequence SQ613, the control unit 310 displays the received matching result screen on the output unit 340.

[0060] By executing the process as shown in FIG. 6, it is possible to provide a workflow for interactively and efficiently performing matching narrowed down to a specific target of interest (human resources). The matching process for a specific combination can be executed in real time or on demand according to the user's operation, and the responsiveness of the system can be improved. Also, compared with batch processing or the like that performs matching for all combinations, it is possible to concentrate and efficiently utilize the processing resources for specific search needs.

[0061] FIG. 7 is a diagram showing an example of a matching result screen 700. The matching result screen 700 is an example of a screen of the matching result displayed by the process shown in FIG. 6. On the matching result screen 700, a list of cases with a matching degree equal to or higher than a threshold value for a specific human resource when the specific human resource is selected is displayed. The matching result screen 700 includes an information area of the selected human resource and a list area of the matched cases. The information area of the selected human resource includes detailed information of the human resource serving as the basis for matching, such as the name, skills, experience, desired conditions, self-promotion, etc. of the human resource. In the list area of the matched cases, the cases matched to the selected human resource are displayed in a list format. As each item (case item) of the list, in the example of FIG. 7, case item 710, case item 720, and case item 730 are included. Each case item includes a case name, an outline or description of the case, a matching degree, a reason for matching, etc.

[0062] (2-3) Matching of case information of the case selected on the case selection screen and a plurality of human resource information FIG. 8 is a sequence diagram (part 3) showing an example of information processing of the case-human resource matching system 1000. In sequence SQ801, the control unit 210 receives a request for output of a case selection screen for selecting a case from the client device 110. For example, when an operator of the client device 110 accesses a specific URL by a predetermined operation or clicks a predetermined button, the control unit 210 receives a request for output of the case selection screen (HTTP request).

[0063] In sequence SQ802, the control unit 210 acquires a plurality of case information from a predetermined storage area such as the storage unit 220.

[0064] In sequence SQ803, the control unit 210 generates a case selection screen for selecting one human resource from a plurality of cases based on the plurality of case information. In sequence SQ804, the control unit 210 transmits the generated case selection screen to the client device 110. The processing of sequence SQ803, or the processing of sequence SQ803 and sequence SQ804, is an example of the processing for displaying a case selection screen for selecting a case.

[0065] In sequence SQ805, the control unit 310 displays the received case selection screen on the output unit 340. When a case is selected via the case selection screen, in sequence SQ806, the control unit 310 transmits the case information of the selected case to the server device 100. The control unit 210 receives the case information of the case selected from the client device 110.

[0066] In sequence SQ807, the control unit 210 acquires a plurality of human resource information from a predetermined storage area such as the storage unit 220.

[0067] In sequence SQ808, the control unit 210 generates a prompt based on the case information of the selected one case and the plurality of human resource information. As described above, the prompt includes instructions for tasks, provision of context, specification of format, data to be processed, etc. The control unit 210 includes, in the prompt, an instruction to match the case and the human resources as an instruction for the task. In addition, the control unit 210 includes, in the prompt, as an instruction for the task, an instruction to include "the degree of matching (degree of agreement) between the case information of the case and the human resource information of the human resources" in the result regarding the matching. In addition, the control unit 210 includes, as a specification of the format, an instruction to include "the reason for the matching between the case information of the case and the human resource information of the human resources" in the result regarding the matching. In addition, the control unit 210 includes, as data to be processed in the prompt, the plurality of human resource information and the case information of the selected one case. The processing of sequence SQ808 is an example of the processing for generating a prompt based on the case information of the case selected via the case selection screen among the plurality of human resource information and the plurality of case information.

[0068] In sequence SQ809, the control unit 210 inputs the generated prompt into the large language model. In sequence SQ810, the control unit 210 receives, as output data from the large language model, the matching results between a plurality of human resource information and the case information of the selected case.

[0069] In sequence SQ811, the control unit 210 generates a matching result screen including the results related to the matching based on the matching results received from the large language model. In sequence SQ812, the control unit 210 transmits the generated matching result screen to the client device 110. The process of sequence SQ811, or the processes of sequence SQ811 and sequence SQ812, is an example of a process that outputs the results related to the matching between the case selected via the case selection screen and a plurality of human resources based on the data output from the large language model in response to a prompt. In sequence SQ813, the control unit 310 displays the received matching result screen on the output unit 340.

[0070] By executing the process as shown in FIG. 8, it is possible to provide a workflow for interactively and efficiently performing matching narrowed down to a specific object of interest (case). The matching process for a specific combination can be executed in real time or on demand according to the user's operation, improving the responsiveness of the system. Also, compared with batch processing that performs matching for all combinations, it is possible to concentrate and efficiently utilize the processing resources for specific search needs.

[0071] FIG. 9 is a diagram showing an example of a matching result screen 900. The matching result screen 900 is an example of a screen of the matching result displayed by the process shown in FIG. 8. On the matching result screen 900, a list of human resources with a matching degree equal to or higher than a threshold value for a specific case when the specific case is selected is displayed. The matching result screen 900 includes an information area of the selected case and a list area of the matched human resources. The information area of the selected case includes an explanation of the case, conditions of the case, and the like. In the list area of the matched human resources, the human resources matched to the selected case are displayed in a list format. As each item (human resource item) in the list, in the example of FIG. 9, a human resource item 910, a human resource item 920, and a human resource item 930 are included. Each human resource item includes a human resource name, an attribute, a hope, a matching degree, a reason for matching, and the like.

[0072] According to the process of the embodiment, a large number of cases and a large number of human resources can be efficiently matched. More specifically, compared with the conventional rule-based or simple keyword matching, it is possible to highly interpret complex explanations (natural languages) of cases and human resources and a wide variety of conditions, attributes, and hopes, and to realize a more accurate matching. In addition, according to the process of the embodiment, it is possible to improve the processing ability to search for and identify an optimal combination efficiently and comprehensively from a large amount of case information and human resource information. In addition, according to the process of the embodiment, it is possible to automate the matching work that is time-consuming and costly by manual work by humans or a simple system, and to increase the processing speed and efficiency of the entire system.

[0073] (Modification Example 1) Hereinafter, Modification Example 1 of Embodiment 1 will be described. Modification Example 1 is included in Embodiment 1 and is not a different embodiment from Embodiment 1. The configurations and processes not described in Modification Example 1 are the same as those in Embodiment 1. The same applies to the other modification examples shown below.

[0074] FIG. 10 is a diagram showing an example of a matching result screen 1010. The matching result screen in FIG. 10 is another example of the matching result screen in FIG. 5. In the matching result screen 1010 of FIG. 10, an introduction text generation button is added to a predetermined area of the human resource item. That is, the control unit 210 of the first modification outputs a screen (matching result screen 1010) including the result regarding the matching. And the matching result screen includes an introduction text generation button which is a predetermined graphical user interface component (GUI component).

[0075] When the introduction text generation button is selected, the control unit 210 generates an introduction text of the case based on the case information of the case matched with the human resource for the human resource, and generates an introduction text of the human resource based on the human resource information of the human resource matched with the case for the case. The introduction text of the case is generated in a mode that can be transmitted by, for example, e-mail, and includes the addressee name, greeting, background of the introduction, outline of the case (conditions such as case name, business content, required skills / experience, salary, contract form, period, etc.), charm / recommended points of the case, matching points with the human resource, future process, etc. Further, the introduction text of the human resource is generated in a mode that can be transmitted by, for example, e-mail, and includes the addressee name (company name, department name, person in charge name, etc.), greeting, background of the introduction, outline of the human resource to be introduced (name, current situation, job type experience years, personality and strengths), matching points with the case, specific skills / experience / achievements, continuation information (outline of desired conditions, desired interview date and available time), attached documents such as resume and work history, etc.

[0076] According to the first modification, just by selecting a button, introduction texts for each of the matched human resource and the company related to the case can be generated, so that the burden on the person in charge of the SES operator can be reduced. Also, by combining structured and unstructured data such as matching results and individual case / human resource information, a natural text (introduction text) for human reading can be automatically generated. In addition, the manual work of creating the introduction text can be automated, and the efficiency of related operations can be significantly improved.

[0077] <Supplementary Note> This embodiment includes the following disclosure.

[0078] (Appendix 1) A case-personnel matching system for matching a case with personnel, having at least one or more control units, wherein the control unit acquires a plurality of case information regarding the case, the case information includes a description and conditions of the case, acquires a plurality of personnel information regarding the personnel, the personnel information includes a description, attributes, and wishes of the personnel, generates a prompt based on the plurality of case information and the plurality of personnel information, the prompt includes an instruction to match the case with the personnel, outputs a result regarding the matching of the case with the personnel based on the data output from the learned model according to the prompt. Case-personnel matching system. (Appendix 2) The case-personnel matching system according to Appendix 1, the result regarding the matching includes a matching degree indicating the degree of coincidence between the case information of the case and the personnel information of the personnel. Case-personnel matching system. (Appendix 3) The case-personnel matching system according to Appendix 2, wherein the control unit outputs a result regarding the matching of the case with the personnel where the matching degree is equal to or greater than a set value based on the data output from the learned model. Case-personnel matching system. (Appendix 4) The case-personnel matching system according to any one of Appendices 1 to 3, the result regarding the matching includes the reason for the matching between the case information of the case and the personnel information of the personnel. Case-personnel matching system. (Appendix 5) A project-personnel matching system according to any one of Appendices 1 to 4, wherein the control unit outputs the results related to the matching such that the number of the results related to the matching is equal to or less than a threshold value. Project-personnel matching system. (Appendix 6) A project-personnel matching system according to any one of Appendices 1 to 5, wherein the control unit displays a personnel selection screen for selecting personnel, generates a prompt based on the personnel information of the personnel selected via the personnel selection screen among the plurality of the project information and the plurality of the personnel information, and outputs the results related to the matching between the personnel selected via the personnel selection screen and the plurality of the projects based on the data output from the learned model according to the prompt. Project-personnel matching system. (Appendix 7) A project-personnel matching system according to any one of Appendices 1 to 6, wherein the control unit displays a project selection screen for selecting a project, generates a prompt based on the project information of the project selected via the project selection screen among the plurality of the personnel information and the plurality of the project information, and outputs the results related to the matching between the project selected via the project selection screen and the plurality of the personnel based on the data output from the learned model according to the prompt. Project-personnel matching system. (Appendix 8) A project-personnel matching system according to any one of Appendices 1 to 7, wherein the control unit outputs a screen including the results related to the matching, and the screen includes predetermined graphical user interface components. When the predetermined graphical user interface component is selected, for human resources, a description text of a case is generated based on the case information of the case matched with the human resources, and for the case, a description text of the human resources is generated based on the human resources information of the human resources matched with the case. Case-Human Resources Matching System. (Appendix 9) A case-human resources matching system according to any one of Appendices 1 to 8, The control unit, Performs a clustering process on a plurality of the case information, When there is duplicate case information, updates it with the case information obtained later based on the date and time. Case-Human Resources Matching System. (Appendix 10) A case-human resources matching system according to any one of Appendices 1 to 9, The control unit, Performs a clustering process on a plurality of the human resources information, When there is duplicate human resources information, updates it with the human resources information obtained later based on the date and time. Case-Human Resources Matching System. (Appendix 11) An information processing method executed by a case-human resources matching system that matches cases and human resources, Obtains a plurality of case information regarding the case, The case information includes a description and conditions of the case, Obtains a plurality of human resources information regarding the human resources, The human resources information includes a description, attributes, and wishes of the human resources, Generates a prompt based on a plurality of the case information and a plurality of the human resources information, The prompt includes an instruction to match the case and the human resources, Outputs a result regarding the matching of the case and the human resources based on the data output from the learned model in response to the prompt. Information Processing Method. (Appendix 12) A program, A computer, A program for causing the computer to function as the applicant talent matching system according to any one of Appendices 1 to 11.

[0079] Although the embodiments have been described above, these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. The embodiments are included in the scope and gist of the invention and are included in the invention described in the claims and its equivalent scope.

Explanation of Reference Numerals

[0080] 100: Server device 110: Client device 150: Network 210: Control unit 220: Storage unit 230: Communication unit 1000: Applicant talent matching system

Claims

1. A case-personnel matching system that matches cases with personnel, At least one control unit is included, The control unit is Acquire a plurality of pieces of case information relating to the case; The case information includes a description and terms of the case; acquiring a plurality of pieces of human resource information relating to the human resource; The human resources information includes a description, attributes, and wishes of the human resources; Display the talent selection screen to select talent, generating a prompt based on the plurality of pieces of case information and the personnel information of a personnel selected from the plurality of pieces of personnel information via the personnel selection screen; the prompt includes instructions to match the opportunity with the talent; outputting a result regarding matching between the human resource selected via the human resource selection screen and the plurality of jobs based on the data output from the trained model in response to the prompt; Project personnel matching system.

2. A case-personnel matching system that matches cases with personnel, At least one control unit is included, The control unit is Acquire a plurality of pieces of case information relating to the case; The case information includes a description and terms of the case; acquiring a plurality of pieces of human resource information relating to the human resource; The human resources information includes a description, attributes, and wishes of the human resources; Display the project selection screen to select a project, generating a prompt based on the case information of a case selected via the case selection screen from the plurality of case information and the plurality of personnel information; the prompt includes instructions to match the opportunity with the talent; outputting a result regarding matching between the job selected via the job selection screen and the plurality of human resources based on the data output from the trained model in response to the prompt; Project personnel matching system.

3. A case-personnel matching system that matches cases with personnel, At least one control unit is included, The control unit is Acquire a plurality of pieces of case information relating to the case; The case information includes a description and terms of the case; acquiring a plurality of pieces of human resource information relating to the human resource; The human resources information includes a description, attributes, and wishes of the human resources; generating a prompt based on the plurality of case information and the plurality of human resource information; the prompt includes instructions to match the opportunity with the talent; outputting a screen including results regarding matching between jobs and personnel based on data output from the trained model in response to the prompt; the screen includes a predetermined graphical user interface component; When the predetermined graphical user interface part is selected, for the human resource, a job introduction is generated based on job information of the job matched with the human resource, and for the job, a human resource introduction is generated based on human resource information of the human resource matched with the job. Project personnel matching system.

4. A job-related personnel matching system according to any one of claims 1 to 3, The result of the matching includes a match degree indicating a degree of matching between the job information of the job and the human resource information of the human resource. Project personnel matching system.

5. The job-personnel matching system according to claim 4, The control unit is outputting a result regarding matching between a job and a human resource with a matching degree equal to or greater than a set value based on the data output from the trained model; Project personnel matching system.

6. A job-related personnel matching system according to any one of claims 1 to 3, The result of the matching includes a reason for matching the case information of the case with the talent information of the talent. Project personnel matching system.

7. A job-related personnel matching system according to any one of claims 1 to 3, The control unit is outputting the results related to the matching such that the number of the results related to the matching is equal to or less than a threshold; Project personnel matching system.

8. A job-related personnel matching system according to any one of claims 1 to 3, The control unit is A name matching process is performed on the plurality of pieces of case information; If there is duplicated information, update it to the most recently acquired information based on the date and time. Project personnel matching system.

9. A job-related personnel matching system according to any one of claims 1 to 3, The control unit is A name matching process is performed on the plurality of pieces of human resource information; If duplicate personnel information exists, update it to the personnel information acquired later based on the date and time. Project personnel matching system.

10. An information processing method executed by a job-personnel matching system that matches jobs with personnel, comprising: Acquire a plurality of pieces of case information relating to the case; The case information includes a description and terms of the case; acquiring a plurality of pieces of human resource information relating to the human resource; The human resources information includes a description, attributes, and wishes of the human resources; Display the talent selection screen to select talent, generating a prompt based on the plurality of pieces of case information and the personnel information of a personnel selected from the plurality of pieces of personnel information via the personnel selection screen; the prompt includes instructions to match the opportunity with the talent; outputting a result regarding matching between the human resource selected via the human resource selection screen and the plurality of jobs based on the data output from the trained model in response to the prompt; Information processing methods.

11. An information processing method executed by a job-personnel matching system that matches jobs with personnel, comprising: At least one control unit is included, The control unit is Acquire a plurality of pieces of case information relating to the case; The case information includes a description and terms of the case; acquiring a plurality of pieces of human resource information relating to the human resource; The human resources information includes a description, attributes, and wishes of the human resources; Display the project selection screen to select a project, generating a prompt based on the case information of a case selected via the case selection screen from the plurality of case information and the plurality of personnel information; the prompt includes instructions to match the opportunity with the talent; outputting a result regarding matching between the job selected via the job selection screen and the plurality of human resources based on the data output from the trained model in response to the prompt; Information processing methods.

12. An information processing method executed by a job-personnel matching system that matches jobs with personnel, comprising: Acquire a plurality of pieces of case information relating to the case; The case information includes a description and terms of the case; acquiring a plurality of pieces of human resource information relating to the human resource; The human resources information includes a description, attributes, and wishes of the human resources; generating a prompt based on the plurality of case information and the plurality of human resource information; the prompt includes instructions to match the opportunity with the talent; outputting a screen including results regarding matching between jobs and personnel based on data output from the trained model in response to the prompt; the screen includes a predetermined graphical user interface component; When the predetermined graphical user interface part is selected, for the human resource, a job introduction is generated based on job information of the job matched with the human resource, and for the job, a human resource introduction is generated based on human resource information of the human resource matched with the job. Information processing methods.

13. A program, Computer, A program for causing the job-personnel matching system according to any one of claims 1 to 3 to function.

Images