Matching system, method, and program

Abstract

To provide a matching system, a matching method, and a matching program for facilitating comprehensive matching between a user and a user who requests it.SOLUTION: A matching system 10 includes a user skill information storage part 32, a skill information storage part 33, an extraction part 51, and an output part 52. The user skill information storage unit 32 stores user skill information in which a plurality of users and scores indicating skill levels of the plurality of users are associated with each other. The skill information storage unit 33 stores a plurality of skills in a tree structure. The extracting unit 51 extracts, from the skill information storage unit 33, a skill that is related to at least a part of the acquired text and that is stored in the lowest level of the tree structure. The output unit 52 specifies an arbitrary number of users in descending order of the scores of the skills extracted in the user skill information storage unit 32 and displays the specified users as a search result.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] When organizations such as companies and public institutions are looking for highly skilled personnel to perform a certain task, they widely use technology that searches for the desired personnel from among multiple personnel and matches the desired personnel with a searcher. Patent Document 1 describes a personnel search device that includes a work history database, a search processing unit, and an output processing unit. The work history database stores, for each of multiple personnel, the work history related to the tasks performed by that personnel. The search processing unit searches for experienced personnel based on the work history registered in the work history database and calculates the knowledge level for each experienced personnel. The output processing unit outputs the experienced personnel and their knowledge level obtained by the search processing unit as search results. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-77024 Summary of the Invention [Problem to be solved by the invention]

[0004] A user of the staff search device described in Patent Document 1 can search for an experienced staff member if the work history data registered in the work history database matches the keywords included in the search conditions, but the work history data of each staff member often does not match the above keywords, and if there is no match, no search results are output.

[0005] Therefore, an object of the present invention is to provide a matching system, a matching method, and a matching program that facilitate comprehensive matching between users and users who are looking for them. [Means for solving the problem]

[0006] The matching system of the present invention includes a user skill information storage unit, a skill information storage unit, an extraction unit, and an output unit. The user skill information storage unit stores user skill information that associates multiple users with scores indicating the level of each of the multiple users' skills. The skill information storage unit stores the multiple skills in a tree structure. The extraction unit extracts skills associated with at least a portion of the acquired text from the skill information storage unit. The output unit identifies any number of users in the user skill information storage unit in descending order of the scores of the skills extracted by the extraction unit, and displays the identified users as search results.

[0007] The matching system preferably further includes a score calculation unit that calculates a score based on the user's skill-related questionnaire responses or work history, and stores the calculated score in the user skill information storage unit.

[0008] The score calculation unit preferably calculates the score based on the level of a skill related to at least a portion of the acquired text.

[0009] Preferably, the matching system further includes a notification unit that notifies the user identified by the output unit that the user has been identified.

[0010] The matching method of the present invention includes a user skill information storage step, a skill information storage step, an extraction step, and an output step. The user skill information storage step stores user skill information that associates multiple users with scores indicating the level of each of the multiple users' skills. The skill information storage step stores the multiple skills in a tree structure. The extraction step extracts skills associated with at least a portion of the acquired text from the skill information storage unit. The output step identifies any number of users in the user skill information storage unit in descending order of the scores of the skills extracted by the extraction step, and displays the identified users as search results.

[0011] The matching program of the present invention causes a computer to execute the above steps. [Effects of the Invention]

[0012] According to the present invention, comprehensive matching between users and users who want them is facilitated. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is an explanatory diagram of a matching system according to an embodiment of the present invention; [Figure 2] 1 is an explanatory diagram showing an overview of a matching system according to an embodiment of the present invention; [Figure 3] FIG. 2 is an explanatory diagram of user skill information stored in a user skill information storage unit. [Figure 4] FIG. 2 is an explanatory diagram illustrating an example of a skill information storage unit. [Figure 5] FIG. 10 is a schematic diagram showing an example of a registered image of a questionnaire response regarding skills. [Figure 6] FIG. 10 is a schematic diagram illustrating an example of a question posting image. [Figure 7] FIG. 10 is a schematic diagram showing an example of an answer confirmation image for a question post. [Figure 8] FIG. 10 is a schematic diagram illustrating an example of a know-how submission image. [Figure 9]FIG. 10 is a schematic diagram illustrating an example of a business history registration image. [Figure 10] FIG. 4 is a schematic diagram illustrating an example of an output image displayed by an output unit. [Figure 11] 10 is a schematic diagram illustrating an example of a notification image notified by a notification unit. FIG. DETAILED DESCRIPTION OF THE INVENTION

[0014] An embodiment of the present invention will be described below with reference to the drawings. An embodiment of the present invention will be described with reference to FIG. 1. A matching system 10 shown in FIG. 1 is for matching users who have skills in a certain business with users who are looking for such skills. The matching system 10 may be used by administrators as well as users, and in this example, it is configured to be usable by both users and administrators. The administrator manages users and user skill information. The administrator may also use the matching device 12 as a user.

[0015] The matching system 10 includes a matching device 12, an administration terminal 14 used by an administrator, user terminals 16A, 16B, 16C, etc. used by users, and a server 18, all of which are connected via a communication network CN. The matching device 12 cooperates with the server 18 to extract skills, which will be described later. In the following description, when there is no need to distinguish between the user terminals 16A, 16B, 16C, etc., they will be referred to as user terminals 16. Servers (not shown) other than the server 18 may also be connected to the communication network CN.

[0016] The management terminal 14 is a terminal device used by the administrator, and functions as a management terminal for various management operations such as user management and management of user skill information (described later). The matching system 10 can increase or decrease the number of users, and user management includes, for example, registering and deleting users.

[0017] The management terminal 14 is a personal computer. However, the management terminal 14 is not limited to a personal computer, and well-known devices such as a tablet terminal or a smartphone can be used. The number of management terminals 14 needs to be at least one, but may be multiple. For example, if there are multiple administrators, there may be multiple management terminals 14, and the number of management terminals 14 is arbitrary.

[0018] The user terminal 16 is a terminal device used by a user. The user terminal 16 is used, for example, to input various evaluations that constitute user skill information and to search for users. The user terminal 16 also displays matched users and notifies matched users, for example.

[0019] The user terminal 16 is a personal computer. However, the user terminal 16 is not limited to a personal computer, and well-known devices such as tablet terminals and smartphones can be used. The number of user terminals 16 needs to be at least one, but may be multiple. For example, if there are multiple users, there may be multiple user terminals 16, and the number of user terminals 16 is arbitrary.

[0020] The server 18 sends a program that runs on the browser to the management terminal 14 and the user terminal 16, which causes the management terminal 14 and the user terminal 16 to run on the browser. Therefore, the management terminal 14 performs the above-mentioned user management, and the user terminal 16 performs the above-mentioned user search, both on the browser. The server 18 is configured as a computer, and performs various processes in response to input operations on the management terminal 14 and the user terminal 16.

[0021] 2 is composed of a matching device 12, a management terminal 14, a user terminal 16, and a server 18. In this example, the matching system 10 includes a user memory unit 31, a user skill information memory unit 32, a skill information memory unit 33, an extraction unit 51, an output unit 52, etc. The matching device 12 may further include a score calculation unit 53, a notification unit 54, etc. The user memory unit 31, the user skill information memory unit 32, the skill information memory unit 33, etc. configure a database DB.

[0022] 2, the user storage unit 31 stores user information generated by the generation unit 30 in response to an input operation by the administrator from the management terminal 14. The user skill information storage unit 32 stores user skill information generated by the generation unit 30 in response to an input operation by the administrator from the management terminal 14 or an input operation by the user from the user terminal 16. The skill information storage unit 33 stores, in a tree structure, a plurality of skills generated by the generation unit 30 in response to an input operation by the administrator from the management terminal 14. The plurality of skills are stored as text data in the skill information storage unit 33. Details of the generation unit 30 will be described later.

[0023] The extraction unit 51 cooperates with the server 18, which is an external device, to extract skills associated with at least a portion of text acquired from the user terminal 16 from the skill information storage unit 33. The server 18 is equipped with a large-scale language model. The extraction unit 51 acquires text from the input unit 21 of the user terminal 16, reads all skill information from the skill information storage unit 33, and sends the acquired text and all skill information to the server 18 as part of a prompt. The server 18 calculates the degree of association between the acquired text and the skill information and extracts skills associated with at least a portion of the acquired text. The server 18 sends the extracted skills to the extraction unit 51.

[0024] The output unit 52 identifies any number of users in the user skill information storage unit 32 in descending order of the scores of the skills extracted by the extraction unit 51, and causes the identified users to be displayed on the user terminal 16 as search results.

[0025] The score calculation unit 53 calculates a score based on the questionnaire responses (or work history) regarding the user's skills input from the user terminal 16, and stores the calculated score in the user skill information storage unit 32. The score calculation unit 53 also calculates a score based on the level of skills related to at least a part of the acquired text.

[0026] The notification unit 54 notifies the user identified by the output unit 52 that the user has been identified, and causes the user terminal 16 to display this.

[0027] The management terminal 14 comprises an input unit 21, a display unit 22, and a processing control unit 23. The input unit 21 is, for example, a keyboard, a mouse, or a touch panel display. The display unit 22 displays display images for managing users, managing user skill information, etc. A touch panel display may be used as the input unit 21 and the display unit 22. The processing control unit 23 performs various processes in response to acquisition of various information from the input unit 21 and the server 18. The processes include display control processing for displaying display images on the display unit 22. The same applies to the user terminal 16.

[0028] The matching program performs predetermined processing by causing the matching device 12 to execute the matching program. The steps executed by the matching program are a user skill information storage step, a skill information storage step, an extraction step, and an output step.

[0029] The user skill information storage step stores user skill information that associates a plurality of users with scores that indicate the level of skill possessed by each of the plurality of users.

[0030] The skill information storage step stores a plurality of skills in a branched tree structure. The extraction step extracts skills related to at least a part of the acquired text from the skill information storage unit 33.

[0031] The output step identifies any number of users in the user skill information storage unit 32 in descending order of the scores of the skills extracted in the extraction step, and displays the identified users as search results.

[0032] The operation of the above configuration will now be described. User management and the like is performed in the management terminal 14. In this case, when an input operation is performed in the management terminal 14 to input the name of a user to be registered and a registration request requesting user registration, the processing control unit 23 of the management terminal 14 transmits the input content indicating the user name and registration request to the generation unit 30 of the matching device 12. In response to receiving the input content, the generation unit 30 assigns user identification information (user ID) unique to each user, generates user information that associates the user name with the user ID, and stores the generated user information in the user storage unit 31.

[0033] When an input operation is performed on the management terminal 14 and / or the user terminal 16 to input user information to be registered, a score indicating the user's skill level, and a registration request requesting registration of the user information and the score indicating the user's skill level, the processing control unit 23 of the management terminal 14 and / or the user terminal 16 transmits the input content indicating the user information, the score indicating the user's skill level, and the registration request to the generation unit 30 of the matching device 12. Upon receiving the input content from the input unit 21 of the user terminal 16, the generation unit 30 generates user skill information for each user, associating the user name with a skill ID (described below) and other information, and stores the generated user skill information in the user skill information storage unit 32. In this manner, the user skill information storage unit 32 stores multiple pieces of user skill information. With reference to FIG. 3 , two users assigned user IDs “1001” and “1002” will be described as an example. The input content regarding the skills possessed by each of these two users is sent from the processing control unit 23 of the user terminal 16 to the generation unit 30 of the matching device 12 by an input operation on the input unit 21 of the user terminal 16. The generation unit 30 stores the user skill information generated by the generation unit 30 in the user skill information storage unit 32. The score calculation unit 53 reads the user skill information from the user skill information storage unit 32, calculates a score indicating the level of each skill, and stores the user skill information associating the user with the calculated score in the user skill information storage unit 32 of the matching device 12. In this example, the score calculation unit 53 calculates the score based on multiple elements such as the degree of interest in skills and the level of experience and knowledge. The score calculation unit 53 evaluates each element and then calculates the score based on the evaluation. In this example, the elements used for score calculation are "element 1," "element 2," "element 3," "element 4," and "element 5." Each element and the method for evaluating each element and calculating the score by the score calculation unit 53 will be described later.

[0034] The skill information storage unit 33 stores multiple skills in a tree structure, as shown in FIG. 4, for example. When a registration request for registering a skill name and hierarchical information to be registered is input in the management terminal 14, the processing control unit 23 of the management terminal 14 transmits the input content indicating the skill name, hierarchical information, and registration request to the generation unit 30 of the matching device 12. Upon receiving the input content, the generation unit 30 assigns skill identification information (skill ID) specific to each skill in response to the reception, generates skill information in which the skill name and skill ID are associated, and stores the generated skill information in the skill information storage unit 33. As described above, the generation unit 30 functions as a user information generation unit that generates user information, a user skill information generation unit that generates user skill information, and a skill information generation unit that generates skill information. The generation unit 30 may be replaced with multiple generation units, each of which includes a user information generation unit, a user skill information generation unit, and a skill information generation unit.

[0035] FIG. 4 shows an example in which "programming language knowledge" and "relational database knowledge" are input through an input operation on the input unit 21 of the management terminal 14. These skill names are all at the highest level 1. The skill names below "programming language knowledge" are "Java" (registered trademark), "JavaScript," etc., and the skill names below "relational database knowledge" are "PostgreSQL," "MtSQL / MariaDB," etc. In this example, the skill information stored in the branched tree structure described above is stored in the skill information storage unit 33. The skill information storage unit 33 can store an explanation of each skill. Here, the explanation of each skill refers to a detailed explanation of the skill, for example, when the skill name is not a general name but a name used only within a certain organization, and is the subject of skill extraction, as described below. In this example, skill ID "0100" is "programming language knowledge", skill ID "0101" is "Java" (registered trademark), skill ID "0102" is "JavaScript" (registered trademark), skill ID "0103" is "TypeScript", skill ID "0104" is "C", skill ID "0200" is "relational database knowledge", skill ID "0201" is "PostgreSQL", skill ID "0202" is "MtSQL / MariaDB" (registered trademark), and skill ID "0203" is "Oracle Database" (registered trademark).

[0036] Here, among the elements used for score calculation, "Element 1" is evaluated by the score calculation unit 53 based on the results of the user's responses to a questionnaire regarding the user's skills, which are periodically collected, in which the user has answered that they are "good at," and the user skill information storage unit 32 stores the evaluation result. "Element 2" is evaluated by the score calculation unit 53 based on the results of the user's responses to the questionnaire in which the user has answered that they are "interested," and the user skill information storage unit 32 stores the evaluation result. When the user inputs their questionnaire responses to the input unit 21 of the user terminal 16, questionnaire response information is generated. When a registration request for the questionnaire response information is made from the input unit 21 of the user terminal 16, the processing control unit 23 of the user terminal 16 sends the questionnaire response information to the user skill information storage unit 32 of the matching device 12, and the evaluations for "Element 1" and "Element 2" are stored in the user skill information storage unit 32. In this example, each element is rated on a scale of 0 to 10, with 0 being the lowest rating and 10 being the highest rating. In this example, all elements are rated on a scale of 10, but the scale is not limited to 10 and may be any number.

[0037] FIG. 5 shows an example of a registration image G1 of a skill-related questionnaire response displayed on the display unit 22 of the user terminal 16. The registration image G1 includes, for example, a skill name display image portion G1a, a response registration image portion G1b, and an update button B1a for submitting the response. In this example, the questionnaire prompts users to answer "Specialties" with a number of stars (1 to 5) and to indicate their "Interest" in a two-level response. In this example, users can enter responses regarding "Programming Language Knowledge," "Java" (registered trademark), "JavaScript" (registered trademark), "TypeScript," "C," "Relational Database Knowledge," "PostgreSQL," and so on. For example, if a user with user ID "1002" selects three stars for one of the skills and operates the update button B1a for submitting the response on the input unit 21 of the user terminal 16, the response is sent from the processing control unit 23 of the user terminal 16 to the user skill information storage unit 32 of the matching device 12. The score calculation unit 53 reads the answer from the user skill information storage unit 32 and multiplies the number of stars (3) by 2 to calculate a score of "6" based on the 10-point rating. The score calculation unit 53 stores this rating result in the user skill information storage unit 32 as a rating for "element 1." For answers with two stars, the score calculation unit 53 similarly multiplies the score by 2 to obtain a rating of "4," which is then stored in the user skill information storage unit 32. For answers with a binary value of on or off, such as "interest," on is rated as "10" and off is rated as "0." The survey is conducted periodically, and each time it is conducted, the answers to each user's "strengths" are stored as ratings for "element 1," and the answers to each user's "interests" are stored as ratings for "element 2." In this example, the higher the number of stars or rating numbers, the higher the rating, but this may be reversed. Symbols other than stars may also be used.

[0038] The evaluation of "element 3" will be described with reference to FIG. 6. "Element 3" is evaluated based on the question posted by the user and the answer posted. The question and answer are stored in a question posting storage unit (not shown) of the matching device 12. The question posting image G2 has a title input image section G2a for inputting the title of the question, a question content input image section G2b for inputting the question content, and a post button B2a for registering the question. When the user performs an input operation in the title input image section G2a and the question content input image section G2b from the input unit 21 of the user terminal 16 and selects the post button B2a, the input content is sent from the process control unit 23 of the user terminal 16 to the question posting storage unit, and the question is posted. When the question posting storage unit receives the input content, it generates a chat screen (not shown) in response to the reception through API (Application Programming Interface) integration (LINE WORKS (registered trademark), Teams (registered trademark), etc.), and the generated screen is sent from the processing control unit 23 of the user terminal 16 to the display unit 22 of the user terminal 16, allowing other users to post answers via the chat tool. FIG. 7 shows an example of an answer confirmation image G3 that is displayed on the display unit 22 of the user terminal 16 and allows the user to check the question for which an answer has been registered and the content of the answer. The answer confirmation image G3 includes a title display image portion G3a that displays the title of the question, a question content display image portion G3b that displays the content of the question, an answer content display image portion G3c that displays the content of the answer, a solved button B3a that is displayed when the question is solved, and a best answer selection button B3b that selects the most useful answer. When the asker (user) performs an input operation on the Solved button B2b on the input unit 21 of the user terminal 16, the input content is sent from the process control unit 23 of the user terminal 16 to the question posting storage unit. Upon receiving the input content, the question posting storage unit stores the posted question as solved in the question posting storage unit in response to this reception. The user can also view solved questions.

[0039] For example, if a user asks, "When I install Eclipse version X.XX on my Mac, it freezes on the last screen. What should I do?" and the answerer (user) replies, "It seems that the latest Mac version is currently experiencing an error. Please try installing version Y.YY," the extraction unit 51 cooperates with the server 18 to extract from the skill information storage unit 33 the skills "programming language knowledge" and "Java," which are related (or may match) to at least a portion of the text of the acquired question and answer. In this example, the extraction is performed using a large-scale language model. This large-scale language model extracts related skills by calculating the degree of association (similarity) between at least a portion of the acquired text and multiple skills stored in the skill information storage unit 33. The extraction unit 51 (see FIG. 2) causes the server 18 (see FIG. 2), which is an external device of the matching device 12 (see FIG. 2), to extract related skills using the large-scale language model. The large-scale language model prompts the user with the following text: "If there are any skills that seem to be related to the following text, please select them from the skill information storage unit 33 below and return the skill IDs, separated by commas. [Questioner] When installing Eclipse version X.XX on my Mac, it freezes on the last screen. [Answerer] The latest Mac version seems to be experiencing an error. Please try installing version Y.YY." The skill IDs are extracted by entering the following text and the skill information (in text format) as a prompt. As described above, in this example, the skill ID "0100" for "Programming Language Knowledge" and the skill ID "0101" for "Java," which are skills related to "Eclipse," are extracted. The server 18 then sends the extracted skill IDs to the extraction unit 51. The skill ID is sent from the extraction unit 51 to the user skill information storage unit 32 (see Figure 2), and the previously assigned rating of "5" for the respondent's (user ID "1001") skill ID "0100" is stored in the user skill information storage unit 32 as a rating of "element 3," and the previously assigned rating of "5" for the skill ID "0101" is stored in the user skill information storage unit 32 as a rating of "element 3."The extraction using this large-scale language model performed by the server 18 (see Figure 2) can be performed at any time or in a night batch. However, in this example, it is performed in a night batch because performing it in a night batch reduces the load on the server 18.

[0040] The skill evaluation of "element 4" will be described with reference to FIG. 8. "Element 4" is evaluated by the score calculation unit 53 based on the know-how posted by the user. This know-how posting is stored in a know-how posting storage unit (not shown) of the matching device 12. The know-how posting image G4 has a title input image section G4a for inputting the title of the know-how, a know-how content posting image section G4b for posting the content of the know-how, and a button B4a for posting the know-how. When a user posts know-how using the input unit 21 of the user terminal 16, the know-how posting is sent from the processing control unit 23 of the user terminal 16 to the know-how posting storage unit, and when the posted content is received, it is stored in the know-how posting storage unit in response to this reception. Other users can view the posted know-how.

[0041] For example, if the stored know-how is "Summary of the procedure for running Tomcat on Eclipse. First, download Eclipse from the following website...," the skill "Java," which is related (or may match) at least a portion of the acquired text, is extracted from the skill information storage unit 33. Here, in this example, as with "element 3," the extraction is performed using a large-scale language model. The large-scale language model calculates the degree of association (similarity) between at least a portion of the acquired text and multiple skills stored in the skill information storage unit 33, and extracts the related skills. The extraction unit 51 causes the server 18, which is an external device to the matching device 12, to extract the related skills using the large-scale language model. The large-scale language model inputs the text "If there are any skills that are thought to be related to the following text, please select them from the skill information storage unit 33 below and return the skill IDs separated by commas. 'Summary of the procedure for running Tomcat on Eclipse. First, download Eclipse from the following website...'" and skill information (in text format) as a prompt, and extracts the skill IDs. In this example, the skill ID "0100" of "programming language knowledge," which is a skill related to "Eclipse," and the skill ID "0101" of "Java" are extracted. The server 18 sends the extracted skill IDs to the extraction unit 51. The skill IDs are sent from the extraction unit 51 to the user skill information storage unit 32, and the evaluation "10" previously given to the know-how poster (user ID "1001") for the skill ID "0100" is stored as an evaluation of "element 4," and the evaluation "10" previously given to the skill ID "0101" is stored as an evaluation of "element 4" in the user skill information storage unit 32 (see FIG. 3). This extraction using a large-scale language model performed by the server 18 (see FIG. 2) may be performed at any time or in an overnight batch. However, in this example, the extraction is performed in an overnight batch because performing the extraction in an overnight batch reduces the load on the server 18.

[0042] The skill evaluation of "Element 5" will be explained using FIG. 9. "Element 5" is evaluated based on the user's own work history registered by the user. This work history is stored in a work history storage unit (not shown) of the matching device 12. The work history registration image G5 has a user name display image section G5a, a work history input image section G5b, a button B5a for updating the work history, and the like.

[0043] For example, if "C" is registered in the work history, a skill "C" related to (or possibly matching) this skill is extracted from the skill information storage unit 33. Here, in this example, extraction is performed using a large-scale language model, as with "element 3" and "element 4." The large-scale language model processes the relevance (similarity) between at least a portion of the acquired text and multiple skills stored in the skill information storage unit 33 to extract related skills. The extraction unit 51 causes the server 18, which is an external device to the matching device 12, to extract related skills using the large-scale language model. The text "If there are any skills that are thought to be related to the following text, please select them from the skill information storage unit 33 below and return the skill IDs separated by commas: 'Eclipse...'" and skill information (in text format) are input as prompts to the large-scale language model, and the skill IDs are extracted. In this example, the skill ID "0100" of "programming language knowledge" and the skill ID "0101" of "Java," which are skills related to "Eclipse," are extracted. The server 18 sends the extracted skill ID to the extraction unit 51. The skill ID is sent from the extraction unit 51 to the user skill information storage unit 32, and the evaluation of "10" previously given to the know-how poster (user ID "1001") for skill ID "0100" is stored as an evaluation of "element 4" and the evaluation of "10" for skill ID "0101" is stored as an evaluation of "element 5" in the user skill information storage unit 32. This extraction using a large-scale language model performed by the server 18 (see FIG. 2) may be performed whenever know-how is registered or may be performed in a nighttime batch, but in this example it is performed whenever it is performed.

[0044] Here, the term "large-scale language model" includes any large-scale language model (LLM), such as GPT (Generative Pretrained Transformer)-1, GPT-2, GPT-3, GPT-3.5, GPT-4, GPT-4o (registered trademark), T5 (Text-to-Text Transfer Transformer), ELMo (Embeddings from Language Models), BERT (Bidirectional Encoder Representations from Transformers), LaMDA (Large language Model Meta AI), PaLM (Pathways Language Model) (registered trademark), PaLM2, NEMO LLM, Claude (registered trademark), Alpaca 7B, Vicuna 13B, OpenFlamingo, Transformer, or large-scale language models that have been modified, improved, transferred, or additionally trained.

[0045] The user skill information storage unit 32 stores an evaluation of each element for each user and skill, with a maximum value of 10 and a minimum value of 0. Each element is weighted so that the total sum is 100%, and the score calculation unit 53 calculates a score indicating the level of skill. In this example, the score calculation unit 53 calculates the score by assigning 40% to "element 1," 30% to "element 2," and 10% to each of "element 3" to "element 5," rounding off any decimal point. This weighting is not limited to this, and any weighting may be used. For the skill ID "0100" of user ID "1001," the evaluations are "2" for "element 1," "10" for "element 2," "5" for "element 3," "10" for "element 4," and "10" for "element 5," resulting in a calculated score of "6." For skill ID "0101," the evaluations are "4" for "Element 1," "10" for "Element 2," "5" for "Element 3," "10" for "Element 4," and "10" for "Element 5," resulting in a calculated score of "7." The score calculation unit 53 then sends this score to the user skill information storage unit 32, which stores this score. In this example, the number of elements is five, but the number of elements can be any number. In this way, by calculating scores based on evaluations of skill-related questionnaire responses or work history, etc., and performing matching, more objective and accurate matching can be achieved.

[0046] The extraction unit 51 cooperates with the server 18 to extract, from the skill information storage unit 33, skills related to at least a portion of text acquired from the processing control unit 23 of the user terminal 16 in response to an input operation performed on the input unit 21 of the user terminal 16. The "text" here does not refer to the answer to "element 3," the post to "element 4," or the text in the business history of "element 5," but rather to text related to skills to be searched for in matching. However, it may also refer to the answer to "element 3," the post to "element 4," or the text in the business history of "element 5." The server 18 includes a large-scale language model. This large-scale language model is the same as the large-scale language model used to extract the skills of "element 3," "element 4," and "element 5." The large-scale language model calculates the degree of association (similarity) between at least a portion of the acquired text and multiple skills stored in the skill information storage unit 33, and extracts related skills. The extraction unit 51 causes the server 18, which is an external device of the matching device 12, to extract related skills using the large-scale language model. If the text obtained from the user terminal 16 is "Eclipse," the large-scale language model receives the text "If there are any skills that are thought to be related to the following text, please select them from the skill information storage unit 33 below and return the skill IDs separated by commas: 'Eclipse'" and the skill information (in text format) as a prompt to extract the skill ID. The skill IDs "0100" and "0101" are extracted as related skills. The server 18 sends the extracted skill IDs to the extraction unit 51. Note that by using the large-scale language model only for skill extraction, less prompt text needs to be input into the large-scale language model, enabling faster processing.

[0047] The extraction unit 51 may extract only the skills stored in the lowest layer from the skill information storage unit 33. Matching using the skills stored in the lowest layer can improve matching accuracy. When calculating the score, the skills in the lowest layer may be given higher priority and evaluated higher.

[0048] Text entered on the input unit 21 of the user terminal 16 is sent from the processing control unit 23 of the user terminal 16 to the extraction unit 51 of the matching device 12, and the extraction unit 51 extracts skills desired by the user from the skill information storage unit 33 of the matching device 12. Then, any number of users with the highest scores for the skills extracted by the extraction unit 51 of the matching device 12 are identified in the user skill information storage unit 32, and the identified users are sent to the output unit 52 as search results. This facilitates comprehensive matching between users and users seeking them.

[0049] FIG. 10 illustrates an example of an output image G6 displayed on the display unit 22 of the user terminal 16 by the output unit 52. The output image G6 identifies, for example, any number of users in the user skill information storage unit 32 in descending order of the skill scores extracted by the extraction unit 51. The output image G6 includes a keyword input search section G6a for inputting the skill to be searched for, a search button B6a for executing the search, a refinement input section G6b for inputting search refinement conditions, and a matching list image section G6c for displaying the identified users as search results. In this example, six users are identified in descending order of their scores. When the output unit 52 receives the search results from the extraction unit 51 of the matching device 12, the search results are sent from the processing control unit 23 of the user terminal 16 to the display unit 22 of the user terminal 16 in response to the reception of the search results, and the output image G6 is displayed on the display unit 22 of the user terminal 16. The matching list image section G6c displays the user's name, organization, skill score, and the like, and includes a button B6b for displaying detailed skill information. When button B6b is selected from the input unit 21 of the user terminal 16, the selection is sent from the process control unit 23 of the user terminal 16 to the output unit 52 of the matching device 12. When this output unit 52 receives the input operation from the input unit 21 of the user terminal 16, it responds by sending detailed information to the process control unit 23 of the user terminal 16, and the detailed information is displayed on the display unit 22 of the user terminal 16. Furthermore, the user terminal 16 also has a call button B6c and a chat button B6d. When a user selects one of these buttons on the input unit 21 of the user terminal 16, the selection is sent from the process control unit 23 of the user terminal 16 to the output unit 52 of the matching device 12 via API (Application Programming Interface) integration (LINE WORKS (registered trademark), Teams (registered trademark), etc.). When this output unit 52 receives the selection, it responds by starting a call or chat with the selected user. There are n buttons B6b, B6c, and B6d, each of which is a button B6b, a call button B6c, and a chat button B6d.

[0050] 11, when the notification unit 54 receives the search results from the output unit 52 of the matching device 12, in response to this reception, it generates notification content notifying the user of the identification, and sends the notification content from the processing control unit 23 of the user terminal 16 to the display unit 22 of the user terminal 16, where a notification image G7 is displayed on the display unit 22. The notification image G7 can display details such as the matched user's name, organization, required skills, etc. By notifying the matched user, subsequent interactions with the matched user can be made smoother. [Explanation of symbols]

[0051] 10 Matching System 12 Matching device 14 Management terminal 16A, 16B, 16C,... User terminal 18 Servers 31 User memory section 32 User skill information storage unit 33 Skill information storage unit 51 Extraction part 52 Output section 53 Score calculation section 54 Notification Department

Claims

1. a user skill information storage unit that stores user skill information that associates a plurality of users with a score that indicates the level of skill of each of the plurality of users; a skill information storage unit that stores the plurality of skills in a tree structure; an extraction unit that extracts the skill associated with at least a portion of the acquired text from the skill information storage unit; an output unit that identifies an arbitrary number of users in the user skill information storage unit in descending order of the scores of the skills extracted by the extraction unit, and displays the identified users as search results; A matching system comprising:

2. The matching system according to claim 1 , further comprising a score calculation unit that calculates the score based on questionnaire responses or work history regarding the user's skills and stores the calculated score in the user skill information storage unit.

3. The matching system according to claim 2 , wherein the score calculation unit calculates the score based on the level of the skill related to at least a portion of the acquired text.

4. The matching system according to claim 1 , further comprising a notification unit that notifies the user identified by the output unit that the user has been identified.

5. a user skill information storage step of storing user skill information in which a plurality of users are associated with a score indicating a level of skill possessed by each of the plurality of users; a skill information storage step of storing the plurality of skills in a tree structure; an extraction step of extracting the skills associated with at least a portion of the acquired text from the skill information storage unit; an output step of identifying an arbitrary number of users in the user skill information storage unit in descending order of the skill scores extracted by the extraction step, and displaying the identified users as search results; A matching method having the following structure:

6. a user skill information storage step of storing user skill information in which a plurality of users are associated with a score indicating a level of skill possessed by each of the plurality of users; a skill information storage step of storing the plurality of skills in a tree structure; an extraction step of extracting the skills associated with at least a portion of the acquired text from the skill information storage unit; an output step of identifying an arbitrary number of users in the user skill information storage unit in descending order of the skill scores extracted by the extraction step, and displaying the identified users as search results; A matching program that causes a computer to execute the above.

Images