Information processing system, information processing method, and program

Abstract

To provide an information processing system or the like capable of efficiently creating a sentence explaining an organization or the like.SOLUTION: According to an aspect of the present invention, there is provided an information processing system including at least one processor, the processor being configured to execute the following steps by reading a program: In the base information acquisition step, base information including information on a position in an organization is acquired, in the explanation information acquisition step, explanation information necessary for explaining the organization in accordance with the position is acquired or created from organization registration information registered in an organization database or public information on a network, and in the explanation sentence creation step, an explanation sentence for explaining the organization in accordance with the position is created based on the explanation information, in the description information acquisition step, when the organization registration information does not include an essential item necessary for creating a description sentence, supplementary information for supplementing the organization registration information is acquired by searching the public information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent Document 1 describes an information processing system that creates a job posting. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7329159 Summary of the Invention [Problem to be solved by the invention]

[0004] When creating a job posting, it may be necessary to write about the organization, business, department, etc.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that can efficiently create text that explains an organization and the like. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program: a base information acquisition step for acquiring base information including information regarding positions within an organization; an explanatory information acquisition step for acquiring or creating explanatory information necessary to explain the organization according to positions from organization registration information registered in an organization database or public information on a network; an explanatory text creation step for creating explanatory text that explains the organization according to positions based on the explanatory information; and an explanatory information acquisition step for acquiring supplementary information that supplements the organization registration information by searching public information if the organization registration information does not include required items necessary for creating the explanatory text.

[0007] According to this aspect, the organization registration information is referenced from the organization database as explanatory information, and if the amount of information in the organization registration information is insufficient, the explanatory information is supplemented with public information on the network, and an explanatory text for the organization is created based on this explanatory information. Therefore, an explanatory text for the organization according to the position can be created efficiently. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. FIG. [Figure 2] 2 is a block diagram showing the hardware configuration of the server device 10. FIG. [Figure 3] FIG. 2 is a block diagram showing the hardware configuration of a recruiting party terminal 20 and a job seeker terminal 30. [Figure 4] 1 is a block diagram showing functions realized by a server device 10 (control unit 11), a recruiting party terminal 20 (control unit 21), and a job seeker terminal 30 (control unit 31). [Figure 5] FIG. 10 is a diagram showing an example of a job posting JP. [Figure 6] 10 is a flowchart showing an example of explanation information acquisition processing executed by the explanation information acquisition unit 113. FIG. [Figure 7] 1 is an activity diagram showing an example (first pattern) of the flow of information processing (job advertisement creation processing) executed by information processing system 1. FIG. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

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

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

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

[0015] <Information Processing System 1> Fig. 1 is a configuration diagram showing an information processing system 1. The information processing system 1 comprises a communication line 2, a server device 10, a plurality of recruiter terminals 20, and a plurality of job seeker terminals 30. The server device 10, the recruiter terminals 20, and the job seeker terminals 30 are configured to be able to communicate with each other via the communication line 2. The connection between the server device 10, the recruiter terminals 20, and the job seeker terminals 30 may be wired or wireless.

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

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

[0018] <Control unit 11> The control unit 11 processes and controls the overall operations related to the server device 10. The control unit 11 is, for example, a central processing unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading out predetermined programs stored in the storage unit 12. In other words, information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and the server device 10 may have multiple control units 11 for each function. Alternatively, a combination of these may be used.

[0019] <Storage section 12> The memory unit 12 stores various pieces of information defined above. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program operations. The memory unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

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

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

[0022] <Recruiter Terminal 20> Fig. 3 is a block diagram showing the hardware configuration of the recruiting party terminal 20 and the job seeker terminal 30. As shown in Fig. 3A, the recruiting party terminal 20 comprises a control unit 21, a memory unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the memory unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected within the recruiting party terminal 20 via the communication bus 26. The recruiting party terminal 20 is an information processing terminal used in the course of business by each recruiter who is a user belonging to an organization that receives services provided by the server device 10. The description of the control unit 21, the memory unit 22, and the communication unit 23 is omitted here, as they are the same as the description of each unit in the server device 10.

[0023] <Input section 24> The input unit 24 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 can execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 24 may be included in the housing of the recruiter terminal 20 or may be attached externally. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input tap operations, swipe operations, etc. to the input unit 24. Instead of a touch panel, a switch button, a mouse, a trackpad, a QWERTY keyboard, etc. can be used as the input unit 24.

[0024] <Output section 25> The output unit 25 displays a screen of a graphical user interface (GUI) that can be operated by the user. The output unit 25 may be included in the housing of the recruiter terminal 20, or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are implemented by selectively using them according to the type of recruiter terminal 20.

[0025] <Job Seeker Terminal 30> 3B, the job seeker terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected within the job seeker terminal 30 via the communication bus 36. The job seeker terminal 30 is an information processing terminal used by each job seeker who is a user receiving services provided by the server device 10. The description of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 is omitted here as they are the same as the description of each unit in the recruiter terminal 20.

[0026] 2. Functional configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (at least one processor included in the information processing system 1).

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

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

[0029] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the recruiter terminal 20 and the job seeker terminal 30. For example, the basic display control unit 111 displays a job advertisement and scouting document created by the recruiter, registration information created by the job seeker, etc. on the display unit 211 of the recruiter terminal 20 or the display unit 311 of the job seeker terminal 30.

[0030] Recruiters include organizations such as for-profit corporations (such as companies), non-profit corporations (such as cooperatives and foundations), and public corporations (such as local governments). Recruiters also include recruitment agencies that act as agents of organizations to mediate between job seekers and organizations. Recruitment agencies are also called headhunters or agents.

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

[0032] <Base information acquisition unit 112> The base information acquisition unit 112 is configured to acquire base information including information about positions within an organization. A "position within an organization" is a position within the organization for which a recruiter is recruiting (a position for which the explanatory text creation unit 114, described below, creates an explanatory text). Furthermore, "information about a position (base information)" is information including keywords or text that represent the position name, organization name, business division, department, job title, job content (job requirements), or a combination thereof.

[0033] The base information acquisition unit 112 may accept input of information related to a position from the recruiting party terminal 20, and acquire the information entered at the recruiting party terminal 20 as base information. The base information acquisition unit 112 may also accept selection of a document (typically a job posting) from the recruiting party terminal 20 that includes a description of the position, and extract information related to the position from the document selected at the recruiting party terminal 20 (for example, in the case of a job posting, a description of the position written in the recruitment conditions), and acquire this as base information. Furthermore, the base information acquisition unit 112 may acquire at least a part of the base information (for example, the name of the organization, the name of the business division, etc.) from the registration information of the recruiter who is using the recruiting party terminal 20. In other words, the base information acquisition unit 112 may acquire, as base information, the information entered at the recruiting party terminal 20 plus additional information.

[0034] Furthermore, the base information acquisition unit 112 may generate job content included in the base information based on the position name input at the recruiter terminal 20. For example, the base information acquisition unit 112 may input the position name into a job content generation model of the artificial intelligence unit 120 and cause the job content generation model to output job content. The job content generation model is a learning model that receives a position name as input and is trained so as to be able to output job content.

[0035] <Explanatory information acquisition unit 113> The explanation information acquisition unit 113 is configured to acquire or create explanation information necessary to explain the organization according to the position from the organization registration information registered in the organization database or public information on the network.

[0036] "Organization registration information" includes information about the organization, such as information indicating the business content, information indicating the industry, information indicating the size of the organization, information indicating performance, information indicating the merchandise (products or services) handled, information indicating the financial situation, and information indicating the management plan. Furthermore, organization registration information may include information about the entire organization (e.g., the business content, industry, performance, etc. of the entire organization), or information about a part of the organization (e.g., a business division, a department, etc.) (e.g., the business content, industry, performance, etc. of one business division). Furthermore, organization registration information may include information (text) that can be used as is as an explanatory text for the organization in a job posting.

[0037] The organization database is an internal database of the information processing system 1 (i.e., a database that is not publicly available), and is stored, for example, in the storage unit 12. The explanatory information acquisition unit 113 searches for organization registration information corresponding to the base information, using keywords such as a position name, organization name, business division name, department name, job title, and job description included in the base information. The explanatory information acquisition unit 113 may always use the organization name (as a search condition) as part of the base information used to search for organization registration information, so that organization registration information of an organization different from the organization targeted by the base information is not extracted in the search. Furthermore, the explanatory information acquisition unit 113 may search for organization registration information corresponding to the base information, using tags indicating a business division, a department, etc., that are assigned to the organization registration information.

[0038] When the organization registration information does not include required items necessary for creating an explanatory text, the explanatory information acquisition unit 113 searches public information to acquire supplementary information that supplements the organization registration information. Examples of "required items" include the business details, mission, performance, development status, domain, personnel, organizational structure, and the like related to the products or services handled by the position (the position for which the explanatory text is being created) for which the base information has been acquired. The "products or services handled by the position" are inferred by the explanatory information acquisition unit 113, for example, from the business division name, job description, and the like included in the base information. The required items may be specified in advance, or may be dynamically set by the explanatory information acquisition unit 113 according to the base information (the content of the position). The number of required items designated may be one or more. When multiple required items are designated, the explanatory information acquisition unit 113 may acquire supplementary information when it determines that all required items are not included in the organization registration information (AND condition), or may acquire supplementary information when it determines that at least one of the multiple required items is not included in the organization registration information (OR condition).

[0039] The explanation information acquisition unit 113, for example, inputs organization registration information into a required item determination model of the artificial intelligence unit 120 and causes the required item determination model to output whether the required items of the organization registration information are satisfied. The required item determination model is a learning model that receives organization registration information as input and is trained so as to be able to output whether the required items are satisfied.

[0040] The required item determination model is trained using training data that is a combination of organization registration information for learning and information indicating whether required items in the organization registration information are satisfied. The required item determination model may be a generative AI including a large-scale language model. In this case, the explanation information acquisition unit 113 receives the organization registration information and required items as input, inputs a prompt including an instruction to output whether the required items in the organization registration information are satisfied to the required item determination model, and causes the required item determination model to output whether the required items are satisfied. The explanation information acquisition unit 113 may generate a prompt that instructs the required item determination model to determine whether the required items in the organization registration information are satisfied, and input the prompt to the required item determination model. Furthermore, the explanation information acquisition unit 113 may input, to the required item determination model, a prompt that includes, as input and output samples, one or more samples of organization registration information and required items and one or more corresponding samples of whether the required items are satisfied, in addition to the instruction to determine whether the required items are satisfied and output the organization registration information and required items. The required item determination model determines whether required items are met according to the input prompt.

[0041] If the explanation information acquisition unit 113 determines that the organization registration information includes the required fields, it does not search for public information or acquire supplemental information. On the other hand, if the explanation information acquisition unit 113 determines that the organization registration information does not include the required fields, it searches for public information and acquires supplemental information. "Public information" is, for example, information that is publicly available on a website accessible via the Internet.

[0042] The types of websites from which the explanatory information acquisition unit 113 acquires supplemental information (i.e., searches for) are not limited as long as they contain at least information about the organization, and include official websites, unofficial websites, and other sites. Official websites are websites established by the organization itself for which the explanatory text is being created (i.e., recruiting for positions), and examples include corporate websites, investor relations websites, commercial sites (product sites or service sites), brand sites, promotion sites, owned media sites, campaign sites, e-commerce sites, member sites, recruitment sites, and landing pages. Unofficial websites are websites established by organizations (external institutions) different from the organization for which the explanatory text is being created (i.e., recruiting for positions), and examples include industry information introduction sites, news sites, economic information sites, and commercial database sites. Unofficial websites include both free and paid viewing pages.

[0043] The explanatory information acquisition unit 113 may create a search query for public information based on the first reference information and the base information, and search for supplemental information using the search query. This allows a wide range of supplemental information to be searched for from public information on the Internet. The search query includes at least one search keyword. The search query may also include search conditions (such as numerical parameters).

[0044] The explanatory information acquisition unit 113 may acquire supplemental information by performing an information search using a search query on a search engine on a network, or by performing an information search using a search query in a commercial database in which information about organizations is registered. This allows for the collection of extensive supplemental information or highly reliable supplemental information, thereby improving the quality of the explanatory information collected for creating explanatory text. Note that the explanatory information acquisition unit 113 may perform both an information search using a search engine and an information search in a commercial database, or may perform only one of them.

[0045] When searching for information using a search engine, all websites targeted by the search engine are searched. The explanatory information acquisition unit 113 inserts the created search query into the search condition input field of the search engine and executes the search. In addition, when searching for information in a commercial database, the explanatory information acquisition unit 113 inputs the created search query into a search tool provided in the commercial database and executes the search.

[0046] The first reference information includes a correlation between the base information and the search query. The first reference information may also include a correlation between the base information, required items (or missing information that is missing in the organization registration information), and the search query. The first reference information is stored, for example, in the storage unit 12. The first reference information is, for example, information for creating keywords that can search for required items (i.e., missing information) that were not included in the organization registration information. The explanation information acquisition unit 113 references the first reference information to create a search query that includes, for example, a combination of keywords that represent the company or business name corresponding to the position and keywords that represent or are related to the required items.

[0047] The first reference information may include a query generation model trained to receive base information and output a search query. In this case, the explanatory information acquisition unit 113 inputs the base information into the query generation model of the artificial intelligence unit 120 and causes the query generation model to output a search query. This enables generation of a search query based on search examples of supplemental information for a large amount of base information or natural language processing. The query generation model may receive a combination of base information and required items or missing information (hereinafter referred to as "composite information") and be trained to output a search query. In this case, the explanatory information acquisition unit 113 inputs the composite information into the query generation model and causes the query generation model to output a search query. In the query generation model, parameters calculated, tuned, etc. by learning configure the correlation of the first reference information.

[0048] The query generation model is trained using a combination of base information or compound information for training and a search query corresponding to the base information or compound information as training data. The query generation model may be a generative AI including a large-scale language model. In this case, the explanatory information acquisition unit 113 receives the base information or compound information as input, inputs a prompt including an instruction to output a search query corresponding to the base information or compound information to the query generation model, and causes the query generation model to output the search query. The explanatory information acquisition unit 113 may generate a prompt that instructs the query generation model to create a search query corresponding to the base information or compound information, and input the prompt to the query generation model. Furthermore, the explanatory information acquisition unit 113 may input a prompt to the query generation model that includes, in addition to the search query creation / output instruction and the base information or compound information, one or more samples of base information or compound information and one or more corresponding search query samples as input and output samples. The query generation model generates a search query according to the input prompt.

[0049] The query creation model may be trained using training data that combines search target information and search queries capable of searching the search target information, and may generate search queries to search for differential information based on differential information between first information about an organization included in a job posting and an explanatory sentence created by a description sentence creation model (described below) based on second information other than the first information among information included in the same job posting as the first information, and may be trained to minimize loss between the search information searched by the search query and the differential information. This improves the search accuracy for supplemental information for creating explanatory sentences for organizations in job postings.

[0050] The job postings used to train the query generation model are, for example, numerous job postings for which job postings have actually been made or are being made (e.g., job postings registered in a job posting database managed by the information processing system 1 and made available to job seekers). The first information includes a description of the organization corresponding to the position for which the job posting is made, such as the organization name, business division, department, job title, and job description of the position. The second information is information not directly related to the description of the organization, such as the position name and application requirements (required qualifications, skills, experience, etc.). FIG. 5 is a diagram showing an example of a job posting JP. In the example of FIG. 5, of the information included in the job posting JP, the description of the organization included in the second item I2 (job description and working conditions) is extracted as the first information. The information included in the second item I2 that is not related to the description of the organization, as well as the first item I1 (position name), the third item I3 (application qualifications), and the fourth item I4 (desired profile) are extracted as the second information. All of the second information in one job posting may be used for learning, or only part of the second information (for example, only the application requirements) may be used for learning.

[0051] The first information and the second information are classified using, for example, a knowledge graph. The first information and the second information may be divided from the original job posting and stored separately. That is, the training data used to train the query generation model may be composed of a set of first information and a set of second information. In addition, in the training data, the first information and the second information may be further divided by item (e.g., qualifications, skills, experience, etc.) and stored separately.

[0052] Specifically, the query generation model includes a neural network constructed by machine learning (first learning) using, as training data, a combination of search target information (typically, missing information in organization registration information) and a search query capable of searching for the search target information from public information. In the first learning, the weighting (weight coefficient) of the neural network is set so that a search query is output to the output layer when the search target information is input to the input layer. Thereafter, in the first learning, the weighting (weight coefficient) of the neural network is adjusted so as to reduce the first loss. The first loss is the loss between the search target information and supplementary information searched from public information by the search query output to the output layer when the search target information of the training data is input to the input layer of the neural network (for example, the amount of deviation between the two or a value evaluated by a loss function).

[0053] The query generation model (neural network) undergoes second learning (readjustment of weighting parameters) using the first information and the second information as learning data. Specifically, the parameter output model is trained to reduce the second loss. The second loss is calculated using the following procedure: First, the second information from the learning data is input to the explanatory sentence generation model, and the explanatory sentence generation model is caused to output explanatory sentences. Next, difference information between the explanatory sentences and the first information included in the learning data (information that is included in the first information but not in the explanatory sentences) is extracted. Furthermore, the difference information is input to the query generation model, and the query generation model is caused to output a search query. Finally, a search is performed on public information using the search query, and the loss between the retrieved search information and the difference information (for example, the amount of deviation between the two or a value evaluated by a loss function) is determined to be the second loss.

[0054] The second learning is performed, for example, after the weighting of the neural network has been adjusted to a certain extent by the first learning. The first learning and the second learning may be performed alternately. Furthermore, the query generation model is successively updated by the first learning and / or the second learning using new learning data, for example, when a new job posting is registered in the job posting database.

[0055] Furthermore, the query generation model learned in the second learning does not necessarily have to be the model constructed in the first learning described above. That is, the second learning may be performed on a query generation model constructed by a means other than the first learning. In other words, only the second learning may be performed without the first learning being performed.

[0056] The explanatory information acquisition unit 113 may obtain organization search information that includes information already included in the organization registration information by searching public information, and obtain supplementary information by removing overlapping portions with the organization registration information from the organization search information.

[0057] If the explanatory information acquisition unit 113 is unable to find supplemental information that supplements the organization registration information by searching the public information (that is, if the supplemental information could not be acquired), it may cause the recruiter terminal 20 to display an alert indicating that the supplemental information could not be acquired. Furthermore, when displaying the alert, the explanatory information acquisition unit 113 may cause the recruiter terminal 20 to display an input form for accepting input of supplemental information, and acquire the supplemental information input from the recruiter terminal 20.

[0058] The explanatory information acquisition unit 113 may create explanatory information structured according to the required items from the organization registration information and / or supplemental information based on the second reference information. This allows the structured explanatory information to be input into the explanatory sentence creation model, thereby improving the accuracy of explanatory sentence creation by the explanatory sentence creation model. Note that when the explanatory information acquisition unit 113 searches for supplemental information, the organization registration information and supplemental information that have been structured or otherwise obtained are acquired as explanatory information, and when the search for supplemental information is not performed (when there is no missing information in the organization registration information), the organization registration information that has been structured or otherwise obtained is acquired as explanatory information. Furthermore, when the organization registration information does not include information that can be used as explanatory information, explanatory information in which only the supplemental information has been structured or otherwise obtained may be acquired.

[0059] "Structuring according to required fields" includes, for example, categorizing information (keywords or sentences) included in the organization registration information and / or supplemental information by required field (for example, hierarchizing using a knowledge graph, assigning tags according to categories, etc.). Information that does not fall into any required field is not categorized or is classified into the "uncategorized" category.

[0060] The second reference information includes a correlation between the organization registration information and / or the supplemental information and the structured explanatory information. The second reference information is stored, for example, in the storage unit 12. The second reference information includes, for example, information such as a category name for structuring the information included in the organization registration information and / or the supplemental information. The explanatory information acquisition unit 113 refers to the second reference information to categorize the information included in the organization registration information and / or the supplemental information.

[0061] The second reference information may include an information conversion model that has been trained to receive organization registration information and / or supplemental information and output explanatory information structured according to required fields. In this case, the explanatory information acquisition unit 113 inputs the organization registration information and / or supplemental information into the information conversion model of the artificial intelligence unit 120 and causes the information conversion model to output explanatory information. This enables structuring of explanatory information based on numerous structuring examples of organization registration information and / or supplemental information, or natural language processing. In the information conversion model, parameters calculated, tuned, etc. through learning configure the correlations of the second reference information.

[0062] The information conversion model is trained using a combination of organization registration information and / or supplemental information for learning and structured explanatory information corresponding to the organization registration information and / or supplemental information as training data. The information conversion model may be a generative AI including a large-scale language model. In this case, the explanatory information acquisition unit 113 receives the organization registration information and / or supplemental information as input, inputs a prompt including an instruction to output structured explanatory information based on the organization registration information and / or supplemental information to the information conversion model, and causes the information conversion model to output the explanatory information. The explanatory information acquisition unit 113 may generate a prompt that instructs the information conversion model to create explanatory information based on the organization registration information and / or supplemental information, and input the prompt to the information conversion model. Furthermore, the explanatory information acquisition unit 113 may input a prompt to the information conversion model that includes, as input and output samples, one or more samples of organization registration information and / or supplemental information and one or more corresponding samples of explanatory information, in addition to the instruction to create and output the explanatory information and the organization registration information and / or supplemental information. The information transformation model creates structured explanatory information according to the input prompts.

[0063] At least two of the required item determination model, the query generation model, and the information conversion model may be integrated into a single learning model. Typically, the explanation information acquisition unit 113 may input base information and organization registration information to an integrated model in which the required item determination model, the query generation model, and the information conversion model are integrated, and cause the integrated model to output explanation information. The explanation information is created based on the organization registration information and / or supplemental information.

[0064] FIG. 6 is a flow diagram showing an example of explanation information acquisition processing executed by the explanation information acquisition unit 113. First, the explanation information acquisition unit 113 acquires organization registration information from the organization database based on the base information (step S110). Next, the explanation information acquisition unit 113 determines whether the acquired organization registration information contains missing information (whether required fields are included) (step S120). If there is missing information (step S120: YES), the explanation information acquisition unit 113 creates a search query for public information (step S130). After creating the search query, the explanation information acquisition unit 113 searches for supplemental information using the search query (step S140). Thereafter, the explanation information acquisition unit 113 creates explanation information based on the organization registration information and supplemental information (step S150).

[0065] In step S120, if there is no missing information in the acquired organization registration information (step S120: NO), the explanatory information acquisition unit 113 does not create a search query or search for supplementary information, and in step S150, creates explanatory information based only on the organization registration information.

[0066] <Explanatory Text Creation Unit 114> The explanatory text creation unit 114 is configured to create explanatory text that explains the organization according to the position for which the base information has been acquired by the base information acquisition unit 112, based on the explanatory information acquired by the explanatory information acquisition unit 113. The "explanatory text" is text that describes information about the organization (for example, business content, industry, size, performance, products handled, financial situation, management plan, etc.) related to the organization to which the position belongs, the business division or department, the job title corresponding to the position, the job content required for the position, etc.

[0067] The explanatory text creation unit 114 may use the explanatory information itself as is, or may adjust the format, etc., to create explanatory text. Alternatively, the explanatory text creation unit 114 may input the explanatory information into an explanatory text creation model of the artificial intelligence unit 120 and cause the explanatory text creation model to output explanatory text. The explanatory text creation model is a learning model that is trained so that it can input explanatory information and output explanatory text. This makes it possible to create explanatory text based on a large number of explanatory text creation examples or natural language processing.

[0068] The explanatory text creation model is trained using a combination of explanatory information for learning and explanatory text corresponding to the explanatory information as training data. The explanatory text creation model may be a generative AI including a large-scale language model. In this case, the explanatory information acquisition unit 113 receives explanatory information as input, inputs a prompt including an instruction to output explanatory text corresponding to the explanatory information to the explanatory text creation model, and causes the explanatory text creation model to output the explanatory text. The explanatory information acquisition unit 113 may generate a prompt that instructs the explanatory text creation model to create explanatory text corresponding to the explanatory information, and input the prompt to the explanatory text creation model. Furthermore, the explanatory information acquisition unit 113 may input a prompt to the explanatory text creation model that includes, for example, one or more explanatory information samples and one or more corresponding explanatory text samples as input and output samples, in addition to the explanatory text creation / output instruction and the explanatory information. The explanatory text creation model creates explanatory text according to the input prompt.

[0069] The explanatory text creation model may be trained using training data that combines first information about an organization included in a job posting with second information other than the first information included in the same job posting, and may be trained to minimize the loss of similarity between the explanatory text created by the explanatory text creation model based on the second information and the first information, thereby improving the accuracy of creating explanatory text for an organization suitable for insertion into a job posting.

[0070] Specifically, the explanatory text creation model includes a neural network constructed by machine learning using first information and second information as training data. In this learning, the weighting (weight coefficients) of the neural network are set so that explanatory text is output to the output layer when the second information is input to the input layer. Then, in this learning, the weighting of the neural network is adjusted so that the loss (e.g., the amount of deviation between the two, the value evaluated by the loss function, etc.) between the explanatory text output to the output layer when the second information of the training data is input to the input layer of the neural network is reduced. The explanatory text creation model is successively updated by learning using new training data, for example, when a new job posting is registered in the job posting database.

[0071] In addition, when the explanatory sentence creation model is updated, the query creation model, which learns using the output of the explanatory sentence creation model (explanatory sentences created by the explanatory sentence creation model), is also updated. In other words, the learning of the explanatory sentence creation model and the learning of the query creation model are linked and run in parallel.

[0072] The explanatory text created by the explanatory text creation unit 114 is linked to the position (base information) and stored, for example, in the memory unit 12 so that it can be referenced by the organization information registration unit 115, job posting creation unit 116, etc., which will be described later.

[0073] <Organization Information Registration Unit 115> The organization information registration unit 115 is configured to register the explanatory text created by the explanatory text creation unit 114 as organization registration information in the organization database in association with information included in the base information. This makes it possible to add organization registration information that can be used as explanatory text (i.e., has little missing information), thereby improving the accuracy of newly created explanatory text. Examples of information associated with explanatory text registered as organization registration information include information that can be used to search for organization registration information, such as position name, organization name, business division name, department name, job title, and job description.

[0074] The organization information registration unit 115 may accept edits to the explanatory text from the user (employer) and register the edited explanatory text in the organization database as organization registration information. This allows explanatory text with content desired by employers to be registered as organization registration information, thereby improving the accuracy of newly created explanatory texts.

[0075] Specifically, the organization information registration unit 115 displays the explanatory text created by the explanatory text creation unit 114 on the recruiter terminal 20, and accepts editing of the explanatory text (for example, adding, deleting, or changing keywords, correcting the text, etc.) from the recruiter terminal 20.

[0076] The organization information registration unit 115 may accept user evaluations of the explanatory text (for example, comments indicating the direction of correction, scoring, etc.). The user evaluations acquired by the organization information registration unit 115 are used, for example, as feedback (relearning) to the explanatory text creation model.

[0077] <Job Posting Department 116> The job posting creation unit 116 is configured to create a job posting corresponding to the position being recruited. The job posting created by the job posting creation unit 116 is registered in a job posting database. The job posting creation unit 116 may create a job posting by accepting input of characters, etc. from the recruiter terminal 20, or may input initial conditions into a job posting creation model in the artificial intelligence unit 120 and have the job posting creation model output a job posting.

[0078] The job posting creation model is a learning model that has been trained to be able to input the initial conditions required to create a job posting and output a job posting. The initial conditions are, for example, information included in the base information (position name, organization name, business division, department, job title, job description, etc.). Furthermore, the job posting creation unit 116 may accept input of the initial conditions from the recruiter terminal 20 separately from the base information.

[0079] The job posting creation model is a learning model that learns using a combination of initial conditions and job posting data corresponding to the initial conditions as training data. The job posting creation model may be a generative AI that includes a large-scale language model. In this case, the job posting creation unit 116 inputs the initial conditions, inputs a prompt including an instruction to output a job posting to the job posting creation model, and causes the job posting creation model to output the job posting. The job posting creation unit 116 may generate a prompt that instructs the job posting creation model to create a job posting from the initial conditions and input the prompt to the job posting creation model. Furthermore, the job posting creation unit 116 may input a prompt to the job posting creation model that includes, for example, one or more sample initial conditions and one or more corresponding job posting samples in addition to the job posting creation / output instruction and the initial conditions. The job posting creation model creates a job posting from the initial conditions according to the input prompt.

[0080] The job posting creation unit 116 may create a job posting into which the explanatory text created by the explanatory text creation unit 114 is inserted. This reduces the amount of work required for the employer to create an explanatory text about the organization related to the position being recruited in the job posting. Note that when the organization information registration unit 115 accepts editing of the explanatory text by the user, the edited explanatory text is inserted into the job posting.

[0081] The job posting creation unit 116 may insert explanatory text into a job posting manually created by a recruiter or into an existing job posting, or may insert explanatory text into a job posting output (i.e., automatically generated) by the above-described job posting creation model. For example, the job posting creation unit 116 may input at least a portion of the base information into the job posting creation model, cause the job posting creation model to output a job posting without explanatory text inserted, and insert explanatory text into the job posting. In this case, the job posting creation model is a learning model that is trained to input at least a portion of the base information and output a job posting without explanatory text inserted. This makes it possible to use a general-purpose job posting creation model to generate a job posting with explanatory text describing the organization inserted according to the position, based on the base information input or specified by the user (the recruiter).

[0082] When inserting explanatory text into a job posting created manually by a recruiter, job posting creation unit 116 acquires a job posting created by the recruiter inputting text using input unit 24 of recruiter terminal 20, and inserts the explanatory text created by explanatory text creation unit 114 into the acquired job posting. When inserting explanatory text into an existing job posting, job posting creation unit 116 acquires the existing job posting by means of file uploading from recruiter terminal 20, or the like, and inserts the explanatory text created by explanatory text creation unit 114 into the acquired existing job posting.

[0083] The job posting creation model may also be a learning model that has been trained to receive at least a portion of the base information and explanatory text as input and output a job posting with the explanatory text inserted. That is, the job posting creation unit 116 may input at least a portion of the base information and explanatory text to the job posting creation model and cause the job posting creation model to output a job posting with the explanatory text inserted. This allows a job posting with explanatory text describing the organization according to the position to be generated based on the base information input or specified by the user (employer). The job posting creation model may also further adjust the explanatory text to suit the job posting. When the job posting creation model is a generation AI, the job posting creation unit 116 may receive at least a portion of the base information and explanatory text, input a prompt to the job posting creation model including an instruction to output a job posting with the explanatory text attached, and cause the job posting creation model to output a job posting with the explanatory text inserted.

[0084] Furthermore, the job posting creation unit 116 may input an existing job posting and explanatory text into the job posting creation model, and cause the job posting creation model to output a job posting with the explanatory text inserted. In this case, the job posting creation model is a learning model that has been trained so that it can input a job posting and explanatory text and output a job posting with the explanatory text inserted. If the job posting creation model is a generative AI, the job posting creation unit 116 may input an existing job posting and explanatory text, input a prompt to the job posting creation model that includes an instruction to output a job posting with the explanatory text attached, and cause the job posting creation model to output the job posting with the explanatory text inserted.

[0085] The job posting creation unit 116 may accept edits from the user to the job posting output by the job posting creation model. Specifically, the job posting creation unit 116 displays the job posting output by the job posting creation model on the recruiter terminal 20, and accepts edits to the job posting from the recruiter terminal 20. The job posting creation unit 116 also registers the edited job posting in the job posting database.

[0086] <Artificial Intelligence Department 120> The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

[0087] The artificial intelligence unit 120 is an AI (Artificial Intelligence) equipped with learning models such as Transformers including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, GPT-3, and GPT-4), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), etc., and language models such as Recurrent Neural Networks (RNNs), and may include generative AI.

[0088] The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

[0089] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data consists of pairs of input data for learning and output data (correct answer data). Furthermore, the language model may not only be trained for a specific task, but also be a general-purpose model that can be used for a wide range of tasks.

[0090] The artificial intelligence unit 120 may be a general-purpose natural language processing learning model, such as a large-scale language model (LLM), trained on a huge amount of data. LLMs are learning models that have previously trained on a large amount of data, such as text data (e.g., (i) web content on the Internet, or (ii) data stored in a specified database). They can execute various language processing tasks when given tasks, and can perform a wide range of natural language processing tasks, such as grasping sentence patterns and contexts, answering questions, and generating sentences, according to given prompts. Such general-purpose learning models include language models that can handle various tasks without fine-tuning, such as through one-shot learning or few-shot learning. Furthermore, general-purpose learning models may also be configured to handle various tasks through zero-shot learning. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or a common general-purpose learning model.

[0091] The learning models included in the artificial intelligence unit 120 (learning models used in each functional unit, such as a required item determination model, a query creation model, an information conversion model, and an explanatory text creation model) can undergo additional learning as transfer learning or fine tuning. For example, each time new job seeker registration information, job posting registration, etc., is generated, the artificial intelligence unit 120 may perform additional learning and fine tuning using this as new training data. This improves the accuracy of the information output from the learning models.

[0092] The learning model included in the artificial intelligence unit 120 may be a learning model (distilled model) obtained by knowledge distillation using an original learning model. In knowledge distillation, a trained model such as a large-scale language model is used as a teacher model, and the parameters of the student model are adjusted to reduce the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model, thereby learning the student model, which becomes the distilled model. Alternatively, the student model may be learned to reduce the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (combination of input data and output data of the learning model). Compared to the original learning model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while maintaining performance similar to the learning model. Therefore, using a distilled model can reduce the cost of the information processing system 1.

[0093] For example, the required item determination model, query generation model, information conversion model, explanatory text creation model, etc. may be distilled models trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the information processing system 1 is introduced, a large-scale language model may be used as the required item determination model, query generation model, information conversion model, explanatory text creation model, etc., and once training data from the large-scale language model has been accumulated, distilled models obtained by knowledge distillation using the training data may be used as the required item determination model, query generation model, information conversion model, explanatory text creation model, etc.

[0094] <Display section> The display unit 211 of the recruiting party terminal 20 and the display unit 311 of the job seeker terminal 30 each display a screen indicated by the screen data transmitted from the server device 10.

[0095] <Operation acquisition part> The operation acquisition unit 212 of the recruiting party terminal 20 accepts operations by a user (recruiter) who uses the recruiting party terminal 20. The operation acquisition unit 312 of the job seeker terminal 30 accepts operations by a user (job seeker) who uses the job seeker terminal 30.

[0096] 3. Information Processing Method This section describes an information processing method of the server device 10. This information processing method is executed by a computer, with each unit of the server device 10 acting as each step.

[0097] This information processing comprises a base information acquisition step, an explanatory information acquisition step, an explanatory text creation step, an organization information registration step, and a job posting creation step. In the base information acquisition step, base information including information about positions within the organization is acquired. In the explanatory information acquisition step, explanatory information necessary to explain the organization according to the position is acquired or created from organization registration information registered in the organization database or public information on the network. In the explanatory text creation step, explanatory text is created to explain the organization according to the position based on the explanatory information. In the organization information registration step, the explanatory text is registered in the organization database as organization registration information in association with the information included in the base information. In the job posting creation step, a job posting with the explanatory text inserted is created.

[0098] 7 is an activity diagram showing an example (first pattern) of the flow of information processing (job advertisement creation processing) executed by information processing system 1. Below, the information processing will be explained along with each activity in this activity diagram.

[0099] The job posting creation process begins with the user (employer) inputting information about the position (base information). The employer inputs at least part of the base information into the employer terminal 20 (activity A101). The server device 10 acquires the base information entered into the employer terminal 20 (activity A102). Note that the server device 10 may add additional information to the information about the position entered into the employer terminal 20 to create base information. Next, the server device 10 acquires organization registration information based on the acquired base information, and further acquires supplemental information by searching public information as necessary (activity A103).

[0100] After acquiring the organization registration information, etc., the server device 10 creates explanatory information based on the acquired organization registration information, etc. (activity A104). Next, the server device 10 creates explanatory text based on the created explanatory information (activity A105). After creating the explanatory text, the server device 10 outputs the created explanatory text to the recruiting party terminal 20 (activity A106). As a result, the explanatory text is displayed on the recruiting party terminal 20 (activity A107).

[0101] The recruiter edits the description text on the recruiter terminal 20 (activity A108). Server device 10 accepts the edits to the description text made by the recruiter terminal 20 and registers the edited description text in the organization database as organization registration information (activity A109). Next, server device 10 creates a job posting with the edited description text inserted (activity A110). After creating the job posting, server device 10 outputs the created job posting to the recruiter terminal 20 (activity A111). As a result, the created job posting is displayed on the recruiter terminal 20 (activity A112).

[0102] 4. Effect The operation of this embodiment can be summarized as follows: Namely, organization registration information is referenced from the organization database as explanatory information, and if the amount of information in the organization registration information is insufficient, the explanatory information is supplemented with public information on the network, and an explanatory text for the organization is created based on this explanatory information. Therefore, an explanatory text for the organization according to the position can be created efficiently.

[0103] Although the embodiment of the present invention has been described above, the present invention is not limited to this and can be modified as appropriate within the scope of the technical idea of ​​the invention.

[0104] 5.Other In the above embodiment, the server device 10 performs various storage and control functions. However, multiple external devices may be used instead of the server device 10. That is, various information and programs may be distributed and stored in multiple external devices using blockchain technology or the like. In particular, the artificial intelligence unit 120 may be an external component of the server device 10. In this case, the external artificial intelligence unit 120 may be provided, for example, by an artificial intelligence service server and configured to receive inputs from each functional unit of the server device 10, receive requests to execute artificial intelligence services, and return the instructed output as a processing result to the server device 10. The artificial intelligence service server may be a server that provides services using a language model as a learning model, or a server that executes language processing tasks using a language model. The artificial intelligence service server may be constructed using LLM. The artificial intelligence service server receives inputs of prompts such as text, images, and voice, and generates and responds to the prompts.

[0105] Furthermore, the information processing system 1 does not necessarily have to include the job advertisement creation unit 116. In other words, the explanatory text created by the information processing system 1 may be used for purposes other than job advertisements.

[0106] The aspect of this embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes steps executed by the information processing system 1. The program causes a computer to execute the steps of the information processing system 1.

[0107] It may be provided in the following manner.

[0108] (1) An information processing system comprising at least one processor, the processor being configured to execute each of the following steps by reading a program: a base information acquisition step acquires base information including information about positions within an organization; an explanatory information acquisition step acquires or creates explanatory information necessary to explain the organization according to the position from organization registration information registered in an organization database or public information on a network; an explanatory text creation step creates explanatory text to explain the organization according to the position based on the explanatory information; and, in the explanatory information acquisition step, if the organization registration information does not include required items necessary for creating the explanatory text, acquires supplemental information to supplement the organization registration information by searching the public information.

[0109] (2) In the information processing system described in (1) above, in the explanatory information acquisition step, a search query for the public information is created based on first reference information and the base information, and the supplementary information is searched for using the search query, wherein the first reference information includes a correlation between the base information and the search query.

[0110] (3) In the information processing system described in (2) above, the first reference information includes a query creation model that has been trained to use the base information as input and to be able to output the search query, and in the explanatory information acquisition step, the base information is input into the query creation model and the query creation model is caused to output the search query.

[0111] (4) In the information processing system described in (2) or (3) above, in the explanatory information acquisition step, the supplementary information is acquired by searching for information using the search query using a search engine on a network, or by searching for information using the search query in a commercial database in which information about organizations is registered.

[0112] (5) In an information processing system described in any one of (1) to (4) above, in the explanatory information acquisition step, the explanatory information structured according to the required items is created from the organization registration information and / or the supplementary information based on second reference information, wherein the second reference information includes a correlation between the organization registration information and / or the supplementary information and the structured explanatory information.

[0113] (6) In the information processing system described in (5) above, the second reference information includes an information conversion model that has been trained to input the organization registration information and / or the supplementary information and output the explanatory information structured according to the required items, and in the explanatory information acquisition step, the organization registration information and / or the supplementary information are input into the information conversion model and the information conversion model is caused to output the explanatory information.

[0114] (7) In the information processing system described in any one of (1) to (6) above, in the explanatory text creation step, the explanatory information is input into an explanatory text creation model, and the explanatory text creation model is made to output the explanatory text, and here, the explanatory text creation model is a learning model that has been trained to be able to input the explanatory information and output the explanatory text.

[0115] (8) In the information processing system described in (7) above, the explanatory text creation model is trained using training data that combines first information about an organization included in a job posting and second information other than the first information included in the same job posting, and is trained so that the loss between the explanatory text created by the explanatory text creation model based on the second information and the first information is minimized.

[0116] (9) In the information processing system described in (7) or (8) above, in the explanatory information acquisition step, the base information is input into a query creation model, the query creation model is caused to output a search query, and the supplementary information is searched for using the search query, and the query creation model generates a search query to search for the difference information based on difference information between first information about an organization included in a job posting and the explanatory text created by the explanatory text creation model based on second information other than the first information among information included in the same job posting as the first information, and the information processing system is trained to minimize loss between the search information searched for by the search query and the difference information.

[0117] (10) In the information processing system described in any one of (1) to (9) above, the processor is configured to further execute the following steps: in the organization information registration step, the explanatory text is registered in the organization database as the organization registration information in association with information contained in the base information.

[0118] (11) In the information processing system described in (10) above, in the organization information registration step, edits to the explanatory text from the user are accepted, and the edited explanatory text is registered in the organization database as the organization registration information.

[0119] (12) In the information processing system described in any one of (1) to (11) above, the processor is configured to further execute the following steps: in the job posting creation step, a job posting is created with the explanatory text inserted.

[0120] (13) In the information processing system described in (12) above, in the job posting creation step, at least a portion of the base information and the explanatory text are input into a job posting creation model, and the job posting creation model is made to output a job posting with the explanatory text inserted, wherein the job posting creation model is a learning model that has been trained to be able to input at least a portion of the base information and the explanatory text and output a job posting with the explanatory text inserted.

[0121] (14) In the information processing system described in (12) above, in the job posting creation step, at least a portion of the base information is input into a job posting creation model, and the job posting creation model is caused to output a job posting without the explanatory text inserted, and the explanatory text is inserted into the job posting, wherein the job posting creation model is a learning model that has been trained to be able to input at least a portion of the base information and output a job posting without the explanatory text inserted.

[0122] (15) An information processing method, comprising steps executed by the information processing system according to any one of (1) to (14) above.

[0123] (16) A program for causing a computer to execute each step of the information processing system described in any one of (1) to (14) above. Of course, this is not the case.

[0124] Finally, while various embodiments of the present disclosure have been described, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. Such embodiments and modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0125] 1: Information processing system 2: Communication line 10: Server device 11: Control section 12: Storage section 13: Communications Department 14: Communication bus 20: Recruiter terminal 21: Control unit 22: Storage section 23: Communications Department 24: Input section 25: Output section 26: Communication bus 30: Job seeker terminal 31: Control unit 32: Storage section 33: Communications Department 34: Input section 35: Output section 36: Communication bus 111: Basic display control section 112: Base information acquisition unit 113: Explanation information acquisition unit 114: Explanatory Text Creation Department 115: Organization Information Registration Department 116: Job posting department 120: Artificial Intelligence Department 211: Display section 212: Operation acquisition section 311: Display section 312: Operation acquisition section I1: 1st item I2: 2nd item I3: Item 3 I4: Item 4 JP: Requesting votes U1: The first person to ask for help U2: The second person seeking help U3: The first job seeker U4: The second job seeker

Claims

1. An information processing system, at least one processor; The processor is configured to execute the following steps by reading the program: In the base information acquisition step, base information including information about positions within the organization is acquired; In the explanation information acquisition step, explanation information necessary to explain the organization according to the position is acquired or created from organization registration information registered in an organization database or public information on a network; In the explanatory text creation step, an explanatory text for explaining the organization is created according to the position based on the explanatory information; In the explanatory information acquisition step, if the organization registration information does not include the required items necessary for creating the explanatory text, the information processing system acquires supplementary information that supplements the organization registration information by searching the public information.

2. 2. The information processing system according to claim 1, An information processing system, wherein in the explanatory information acquisition step, a search query for the public information is created based on first reference information and the base information, and the supplementary information is searched for using the search query, wherein the first reference information includes a correlation between the base information and the search query.

3. 3. The information processing system according to claim 2, the first reference information includes a query generation model that is trained to use the base information as input and to be able to output the search query; In the explanation information acquisition step, the base information is input to the query generation model, and the query generation model is caused to output the search query.

4. 3. The information processing system according to claim 2, In the explanatory information acquisition step, the supplementary information is acquired by searching for information using the search query using a search engine on a network, or by searching for information using the search query in a commercial database in which information about organizations is registered.

5. 2. The information processing system according to claim 1, An information processing system in which, in the explanatory information acquisition step, the explanatory information is created from the organization registration information and / or the supplementary information based on second reference information, the explanatory information being structured according to the required items, and wherein the second reference information includes a correlation between the organization registration information and / or the supplementary information and the structured explanatory information.

6. 6. The information processing system according to claim 5, the second reference information includes an information conversion model that has been trained to receive the organization registration information and / or the supplementary information as input and to output the explanatory information structured according to the required items; In the explanation information acquisition step, the organization registration information and / or the supplementary information is input to the information conversion model, and the information conversion model is caused to output the explanation information.

7. 2. The information processing system according to claim 1, In the explanatory text creation step, the explanatory information is input into an explanatory text creation model, and the explanatory text creation model is caused to output the explanatory text, wherein the explanatory text creation model is a learning model that has been trained to be able to input the explanatory information and output the explanatory text, an information processing system.

8. 8. The information processing system according to claim 7, The explanatory sentence creation model is The training data is a combination of first information about an organization included in a job posting and second information other than the first information included in the same job posting, and An information processing system in which the explanatory sentence creation model is trained to reduce loss between the explanatory sentence created based on the second information and the first information.

9. 8. The information processing system according to claim 7, In the explanation information acquisition step, the base information is input to a query generation model, a search query is output from the query generation model, and the supplemental information is searched for using the search query; The query creation model generates a search query for searching for differential information based on differential information between first information about an organization included in a job posting and the explanatory text created by the explanatory text creation model based on second information other than the first information, among information included in the same job posting as the first information, and is trained to minimize loss between the search information searched for by the search query and the differential information.

10. 2. The information processing system according to claim 1, The processor is further configured to perform the steps of: In the organization information registration step, the explanatory text is registered as the organization registration information in the organization database in association with information included in the base information.

11. 11. The information processing system according to claim 10, In the organization information registration step, the information processing system accepts edits to the explanatory text from a user, and registers the edited explanatory text in the organization database as the organization registration information.

12. 2. The information processing system according to claim 1, The processor is further configured to perform the steps of: In the job posting creation step, the information processing system creates a job posting into which the explanatory text is inserted.

13. 13. The information processing system according to claim 12, In the job posting creation step, at least a portion of the base information and the explanatory text are input into a job posting creation model, and the job posting creation model is caused to output a job posting with the explanatory text inserted, wherein the job posting creation model is a learning model that has been trained to be able to input at least a portion of the base information and the explanatory text and output a job posting with the explanatory text inserted, an information processing system.

14. 13. The information processing system according to claim 12, In the job posting creation step, at least a portion of the base information is input into a job posting creation model, and the job posting creation model is caused to output a job posting without the explanatory text inserted, and the explanatory text is inserted into the job posting, wherein the job posting creation model is a learning model that has been trained to be able to input at least a portion of the base information and output a job posting without the explanatory text inserted, an information processing system.

15. An information processing method, comprising: An information processing method comprising the steps executed by the information processing system according to any one of claims 1 to 14.

16. A program, A program for causing a computer to execute each step of the information processing system according to any one of claims 1 to 14.

Images