Information processing system, information processing method, and program

Abstract

To provide an information processing system, an information processing method, and a program for creating a summary of information on an organization.SOLUTION: In an information processing system, a server device, a plurality of information user terminals, and a plurality of job-seeker terminals 30 may communicate with each other via a communication line. The server device includes: a receiving unit which receives, from an information user terminal 20, an input of first access information to access an organization information site; an acquisition unit which acquires, based on the first access information received by the receiving unit, information on an organization as summary creation information from the organization information site and at least one secondary access site associated with the organization information site; and an organization information summary creation unit 114 which inputs primary information and secondary information included in the summary creation information to a summary creation model at a time.SELECTED DRAWING: Figure 4

Description

[Technical Field]

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

[0002] As disclosed in Patent Document 1, a technique is known for automatically creating a job posting based on information input by an information user. [Prior art documents] [Patent documents]

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

[0004] Incidentally, job advertisements and the like may include information about the organization of the hiring company or the like.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that can relatively easily create a summary of organizational information. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system. The information processing system includes at least one processor. The processor is configured to execute the following steps by reading a program: In the receiving step, input of first access information for accessing an organization information site is received. Here, the organization information site is a website containing information about the organization. In the acquiring step, information about the organization is acquired as summary creation information from the organization information site and at least one secondary access site linked to the organization information site based on the first access information. Here, the secondary access site is a website accessible from second access information included in the organization information site. In the organization information summarizing step, the summary creation information acquired from the organization information site and the secondary access site is input to a summary creation model, and the summary creation model is caused to output an organization information summary. Here, the organization information summary is a document summarizing information about the organization, and the summary creation model is a learning model that is trained to be able to input the summary creation information and output an organization information summary.

[0007] According to this aspect, a user can input primary access information (e.g., the URL of an organization information site) to create an organization information summary based on public information. Furthermore, when creating the organization information summary, in addition to the organization information site, secondary access sites linked to the organization information site are also referenced, so that an organization information summary of a certain quality can be obtained. [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] 2 is a block diagram showing the hardware configuration of an information user terminal 20 and a job seeker terminal 30. FIG. [Figure 4]1 is a block diagram showing functions realized by a server device 10 (controller 11), an information user terminal 20 (controller 21), and a job seeker terminal 30 (controller 31). [Figure 5] 10 is a diagram showing an example of an organization information summary OS created by an organization information summary creating unit 114. FIG. [Figure 6] FIG. 10 is a diagram showing an example of a job posting JP created by a job posting creation unit 115. [Figure 7] 1 is an activity diagram showing the flow of information processing (processing for creating an organization information summary) executed by the 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> 1 is a configuration diagram showing an information processing system 1. The information processing system 1 includes a communication line 2, a server device 10, a plurality of information user terminals 20, and a plurality of job seeker terminals 30. The server device 10, the information user 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 information user terminals 20, and the job seeker terminals 30 may be wired or wireless.

[0016] The information processing system 1 constitutes, for example, a part of a human resources management system or a recruitment and job search system used by multiple information users (first information user U1 and second information user U2) and multiple job seekers (first job seeker U3 and second job seeker U4). The information processing system 1 mainly manages organizational information. 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 multiple control units 11 may be provided for each function. A combination of these may also be used.

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

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

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

[0022] <Information user terminal 20> Fig. 3 is a block diagram showing the hardware configuration of the information user terminal 20 and the job seeker terminal 30. As shown in Fig. 3A, the information user terminal 20 includes 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 via the communication bus 26 inside the information user terminal 20. The explanation of the control unit 21, the memory unit 22, and the communication unit 23 is omitted here as it is the same as the explanation 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 information user terminal 20 or may be externally attached. 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 information user 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 used appropriately depending on the type of the information user 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 via the communication bus 36 inside the job seeker terminal 30. The explanation of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 will be omitted as they are the same as the explanation of each unit in the information user 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 (a processor provided in the information processing system 1).

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

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

[0029] <Basic display control unit 111> The basic display control unit 111 is configured to display various information on the information user terminal 20 and the job seeker terminal 30. For example, the basic display control unit 111 displays organizational information as well as job postings, scout documents, etc. created by the information user on the display unit 211 of the information user terminal 20 or the display unit 311 of the job seeker terminal 30.

[0030] Information users include service providers who use organizational information obtained from the information processing system 1 for their own services, sales, etc., and recruiters who use the information processing system 1 to post job openings. Information users include organizations such as for-profit corporations (e.g., companies), non-profit corporations (e.g., cooperatives, incorporated foundations), and public corporations (e.g., local governments). Information users also include recruitment agencies that act as agents of organizations to mediate between job seekers and organizations. Recruitment agencies are also called headhunters, agents, etc.

[0031] <Reception Department 112> The reception unit 112 is configured to receive input from the information user terminal 20 and the job seeker terminal 30. Specifically, the reception unit 112 receives input of first access information for accessing the organization information site from the information user terminal 20.

[0032] An organization information site is a website that contains information about an organization. Examples of "information about an organization" include information about the business, the type of industry, the size of the organization, performance, the merchandise (products or services) handled, financial status, and business plans.

[0033] An organization information site is a website that contains at least information about the organization. Examples of organization information sites include the official website of the organization itself, which is the subject of the organization information summary. Examples of official websites that can be organization information sites include corporate websites, investor relations websites, commercial websites (product websites or service websites), brand websites, promotional websites, owned media websites, campaign websites, e-commerce websites, member websites, recruitment websites, and landing pages.

[0034] Organization information sites also include unofficial websites established by organizations (external institutions) different from the organization for which the organization information summary is being created. Examples of unofficial websites that could be organization information sites include industry information sites, news sites, and economic information sites. Unofficial websites include both free and paid viewing pages.

[0035] Additionally, the organizational information site may include private websites that are not publicly available to anyone outside the organization for which the organizational information summary is being created, and are only available to those within the organization (and cannot be accessed from outside the organization).

[0036] The first access information is information that indicates the location of the organization information site on the network, and is information that, for example, can be input into a web browser to display the organization information site in the web browser. The first access information includes, for example, the URL and IP address of the organization information site. Typically, the receiving unit 112 receives the URL of the organization information site input into the information user terminal 20 as the first access information.

[0037] <Acquisition part 113> The acquisition unit 113 is configured to acquire information about the organization as information for creating a summary from the organization information site and at least one secondary access site linked to the organization information site based on the first access information received by the reception unit 112.

[0038] A secondary access site is a website accessible from second access information included in the organization information site (primary access site). The second access information is information indicating the location of the secondary access site on the network, and includes, for example, the URL and IP address of the secondary access site. Typically, the second access information is a URL listed on the organization information site as a link to the secondary access site. The second access information is obtained, for example, by crawling or web scraping the organization information site.

[0039] The summary creation information is information used to create an organization information summary in the organization information summary creation unit 114, which will be described later. The organization information summary is a document that summarizes the information about the organization targeted by the organization information site accessed by the first access information.

[0040] The organizational information summary should be a document that summarizes organizational information by item. This makes it easier for information users to obtain the information they need from the organizational information summary. It also makes it easier to create other documents (job postings, scouting documents, etc.) using the organizational information summary. Examples of "organizational information items" include basic information (name, year of establishment, etc.), organizational overview, business content, merchandise handled (products or services provided), industry, organizational size, performance, financial status, business plan (management policy), organizational structure (management structure), corporate culture (mission, vision, etc.), and items that combine these (for example, "organization overview and business content").

[0041] The organizational information summary may also include organizational challenges. This improves the accuracy of the hiring position information generated by the position information creation unit 117, which will be described later. The organizational challenges are described in, for example, items such as performance, financial status, and business plan in the organizational information summary. The organizational information summary may include a sentence that directly describes the organizational challenges, or may include a sentence that allows the organizational challenges to be anticipated (for example, a business plan, goals, etc.).

[0042] The acquisition unit 113 selects reference access information to be referenced to acquire summary creation information from the second access information included in the organization information site, based on the URL of the secondary access site and the URL identification reference information included in the second access information. The URL identification reference information includes a correspondence between the character string included in the URL and the reference access information. This prevents the creation of an organization information summary based on information that is inappropriate as organization information or information with low reliability. This improves the effectiveness and accuracy of the obtained organization information summary.

[0043] The URL identification reference information includes, for example, conditions (whitelist) for URLs of secondary access sites to be selected as reference access information, conditions (blacklist) for URLs of secondary access sites to be excluded from reference access information, etc. Specifically, the URL identification reference information includes, for example, a first character string included in a URL (particularly the domain part) to be selected as reference access information, and / or a second character string included in a URL (particularly the domain part) to be excluded from reference access information.

[0044] Examples of the first character string include words related to organizational information (words that suggest the inclusion of "organizational information"), such as "company," "corporate," and "detail." The acquisition unit 113 may select, as reference access information, second access information whose URL includes a predetermined first character string. This allows collection of appropriate information as an information source for an organizational information summary (information for creating a summary).

[0045] The second character string may be, for example, a character string used in the URL of a website of a social networking service (SNS) (e.g., a character string representing the service name of the SNS, the name of the service provider of the SNS, or an abbreviation thereof). Alternatively, the second character string may be the URL of a specific SNS website itself. The acquiring unit 113 may not select, as reference access information, second access information whose URL includes a predetermined second character string. This prevents unreliable information or information whose reliability is difficult to verify from being used as an information source for an organization information summary (information for creating a summary). Furthermore, when creating an organization information summary, the amount of information input to a summary creation model (described later) can be reduced.

[0046] The acquiring unit 113 lists the second access information (URLs) acquired from, for example, the organization information site. Furthermore, the acquiring unit 113 performs cleansing (deletion of unnecessary data, etc.) on the list of second access information using the URL identification reference information, and acquires information from the secondary access site accessed from the reference access information (i.e., the second access information determined as reference access information).

[0047] The acquisition unit 113 stores primary information about the organization obtained by crawling or web scraping the organization information site (primary access site) and secondary information about the organization obtained by web scraping each of at least one secondary access site as summary creation information, for example, in the storage unit 12. The acquisition unit 113 may use text data extracted from the organization information site or the secondary access site, for example, excluding control symbols such as HTML tags, as summary creation information, or may use sentences about the organization extracted from the text data using a learning model as summary creation information.

[0048] The acquisition unit 113 may cause the information extraction model to acquire (extract) information about the organization (information for creating a summary) by crawling or web scraping the primary access site and the secondary access site. The information extraction model is a learning model that is trained so as to be able to input primary access information (e.g., the URL of the primary access site) and output information about the organization (primary information and secondary information). The information extraction model is trained using a combination of the primary access information for learning and the information about the organization acquired from the primary access information as training data.

[0049] The information extraction model may also be a generative AI including a large-scale language model. In this case, the acquisition unit 113 inputs a prompt to the information extraction model, the prompt including an instruction to extract primary information and secondary access information (e.g., URLs of secondary access sites) about the organization from primary access sites by processing such as crawling or web scraping, and an instruction to extract secondary information about the organization from secondary access sites based on the extracted second access information by further processing such as crawling or web scraping, and causes the information extraction model to output the primary information and secondary information. The acquisition unit 113 may also generate a prompt that instructs the information extraction model to extract information about the organization from primary access sites and secondary access sites, and input the prompt to the information extraction model.

[0050] <Organization Information Summary Creation Department 114> The organization information summary creation unit 114 is configured to input summary creation information acquired from the organization information site and the secondary access site into the summary creation model of the artificial intelligence unit 120 and cause the summary creation model to output an organization information summary. Specifically, the organization information summary creation unit 114 simultaneously inputs the primary information and secondary information included in the summary creation information into the summary creation model.

[0051] The summary creation model is a learning model that has been trained to be able to input summary creation information and output an organizational information summary. The summary creation model is a learning model that has been trained using a combination of information about the organization used for learning and an organizational information summary that summarizes that information as training data. Note that the information about the organization used for learning in the summary creation model does not necessarily have to be obtained from a website.

[0052] The summary creation model may be a generative AI including a large-scale language model. In this case, the organizational information summary creation unit 114 receives summary creation information as input, inputs a prompt including an instruction to output an organizational information summary to the summary creation model, and causes the summary creation model to output the organizational information summary. The organizational information summary creation unit 114 may generate a prompt that instructs the summary creation model to create an organizational information summary from the summary creation information, and input the prompt to the summary creation model. Furthermore, the organizational information summary creation unit 114 may input a prompt to the summary creation model that includes, as input and output samples, one or more samples of summary creation information and one or more corresponding organizational information summary samples, in addition to the instruction to create and output the organizational information summary and the summary creation information. The summary creation model creates an organizational information summary from the summary creation information in accordance with the input prompt.

[0053] Furthermore, the organizational information summary creation unit 114 may input the names of items included in the organizational information summary to the summary creation model along with an instruction to output the organizational information summary. This makes it possible to create an organizational information summary that is highly accurate in summarizing information and also has excellent visibility. Specifically, the organizational information summary creation unit 114 inserts, into the prompt input to the summary creation model, multiple item names and an instruction to create a summary by summarizing information about the organization (information for summary creation) for each of these items. Examples of item names included in the organizational information summary (item names input to the summary creation model) include "basic information," "organization overview," "business content," "products handled," "industry," "organization size," "performance," "financial status," "business plan," "organizational structure," "corporate culture," and item names that combine these (e.g., "organization overview and business content"), etc.

[0054] The organizational information summary creation unit 114 may further input, into the summary creation model, the names of the items included in the organizational information summary, along with an instruction not to output, as an organizational information summary, any items corresponding to the item names whose corresponding descriptions or contents are not included in the summary creation information. That is, if the organizational information summary creation unit 114 cannot extract information about an item instructed to be included in the organizational information summary from the summary creation information, the organizational information summary creation unit 114 may insert, as a supplementary instruction, an instruction not to output the item as an organizational information summary (to create an organizational information summary that does not include the item) into a prompt for the summary creation model. For example, the organizational information summary creation unit 114 may insert an instruction such as "If there is not enough information, please delete the item" into the prompt input to the summary creation model. This provides an instruction in the prompt to prevent information about the item from being output if, for example, the summary creation information does not contain a description corresponding to an item included in the organizational information summary. This suppresses hallucination, in which an item is created based on information not included in the summary creation information.

[0055] The organization information summary created by the organization information summary creation unit 114 is displayed on the information user terminal 20 by, for example, the basic display control unit 111. Fig. 5 is a diagram showing an example of the organization information summary OS created by the organization information summary creation unit 114. The organization information summary OS includes the above-mentioned items and their contents (keywords or sentences).

[0056] <Job Posting Department 115> The job posting creation unit 115 is configured to create a job posting for job posting (recruiting job seekers) based on instructions from an information user (recruiter).

[0057] The job posting creation unit 115 creates a job posting based on the initial conditions for creating the job posting, which are input, for example, from the information user terminal 20. The initial conditions include at least one of the profile of the person the employer is looking for, the recruitment background of the job, and the recruitment conditions.

[0058] The profile of the candidate includes, for example, information about the job (position) being recruited for and information defining the profile of the candidate the employer is seeking. The recruitment background is the reason for the recruitment of the personnel or position, and includes, for example, the organizational goals, challenges, business situation (e.g., the start of a new project), etc. Furthermore, the recruitment conditions include, for example, the type of job or position being recruited for, the required skills, the required experience (services, products, etc.), etc.

[0059] Specifically, the job posting creation unit 115 inputs the initial conditions into the job posting creation model of the artificial intelligence unit 120 and causes the job posting creation model to output a job posting. The job posting creation model is a learning model that takes the initial conditions as input and trains to output a job posting. In other words, the job posting creation model is a learning model that trains using combinations of initial conditions and job posting data corresponding to those initial conditions as training data.

[0060] The job posting creation model may also be a generative AI that includes a large-scale language model. In this case, the job posting creation unit 115 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 115 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. The job posting creation unit 115 may also 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.

[0061] The job posting creation unit 115 may accept a selection of a recruitment background from multiple recruitment background options and create a job posting based on the selected recruitment background. The recruitment background options include at least one option output from the recruitment background creation model of the artificial intelligence unit 120 by inputting the organizational information summary created by the organizational information summary creation unit 114 into the recruitment background creation model. This allows a job posting corresponding to the personnel needed by the organization to be automatically created by selecting a recruitment background generated based on the organizational information summary. Furthermore, by inputting the organizational information summary with reduced unnecessary information (noise) into the recruitment background creation model, a recruitment background that appropriately reflects the organization's challenges, etc., can be presented to the employer, compared to when organizational information from a website is directly input into the recruitment background creation model.

[0062] The recruitment background creation model is a learning model that is trained so that it can input an organizational information summary and output options for recruitment backgrounds. The recruitment background creation model is a learning model that is trained using a combination of a training organizational information summary and a recruitment background based on the training organizational information summary as training data. Note that the training organizational information summary for the recruitment background creation model does not have to be created by the organizational information summary creation unit 114, as long as it has the same format, structure, etc. as the organizational information summary created by the organizational information summary creation unit 114.

[0063] The recruitment background creation model may be a generative AI including a large-scale language model. In this case, the job posting creation unit 115 inputs the organizational information summary and inputs a prompt including an instruction to output at least one recruitment background option to the recruitment background creation model, causing the recruitment background creation model to output the recruitment background options. The job posting creation unit 115 may generate a prompt that instructs the recruitment background creation model to create recruitment background options from the organizational information summary and input the prompt to the recruitment background creation model. Furthermore, the job posting creation unit 115 may input a prompt to the recruitment background creation model that includes, as input and output samples, one or more organizational information summary samples and one or more corresponding recruitment background option samples, in addition to the instruction to create and output recruitment background options and the organizational information summary. The recruitment background creation model creates recruitment background options from the organizational information summary according to the input prompt.

[0064] The job posting creation unit 115 accepts at least one selection from the information user from the presented multiple recruitment background options. The recruitment background options presented to the employer by the job posting creation unit 115 may consist solely of options output by the recruitment background creation model, or may consist of options output by the recruitment background creation model and options set by another algorithm. Examples of other algorithms include an algorithm that extracts, from predefined recruitment backgrounds, recruitment backgrounds that are related (e.g., highly similar) to input information from the employer, such as initial conditions other than the recruitment background. For example, if the difference in feature values ​​(vector distance) between the input information and a certain recruitment background is less than a threshold (e.g., the cosine similarity of the vector data is greater than or equal to a threshold), the input information and a certain recruitment background are determined to be highly similar, and the recruitment background is set as the selection. Note that vector data is a vector value quantified from text data using known techniques such as natural language processing using morphological analysis or categorical variable encoding.

[0065] FIG. 6 is a diagram showing an example of a job posting JP created by the job posting creation unit 115. The job posting JP includes multiple items such as the name of the position being recruited, job content and working conditions, application qualifications, and appealing points. Note that the job posting JP may also include items other than these. The job posting creation model generates sentences for these items based on initial conditions. The job posting created by the job posting creation unit 115 is added to a database stored in the memory unit 12, for example.

[0066] The job posting creation unit 115 may create a job posting with an organizational information summary inserted. This allows a job posting including organizational information to be created without the need for the employer to collect and input organizational information. Specifically, the job posting creation unit 115 acquires the organizational information summary created by the organizational information summary creation unit 114. The job posting creation unit 115 may insert the acquired organizational information summary into the job posting in its entirety, or may extract some items from the organizational information summary (e.g., organization overview, business content, etc.) and insert them into the job posting. The organizational information summary is inserted, for example, in the "Job Content and Working Conditions" section of the job posting to introduce the organization (division or department) and the background to the hiring.

[0067] The job posting creation unit 115 may insert the organizational information summary into a job posting manually created by a recruiter or an existing job posting, or may insert the organizational information summary into a job posting output (i.e., automatically generated) by the job posting creation model described above. When inserting the organizational information summary into a job posting manually created by a recruiter or the like, the job posting creation unit 115 acquires a job posting created by the recruiter or the like inputting text using the input unit 24 of the information user terminal 20, and acquires the organizational information summary created by the organizational information summary creation unit 114. The job posting creation unit 115 then inserts the organizational information summary into the acquired job posting. When inserting the organizational information summary into an existing job posting, the job posting creation unit 115 acquires the existing job posting by means of file uploading from the information user terminal 20, or the like, and acquires the organizational information summary created by the organizational information summary creation unit 114. The job posting creation unit 115 then inserts the organizational information summary into the acquired existing job posting. The location in the job posting where the organization information summary is to be inserted may be selected arbitrarily by the employer, or a predetermined location such as the beginning of the job posting may be set as the insertion location in advance.

[0068] Furthermore, the job posting creation model may be a learning model that has been trained to be able to output a job posting with an organizational information summary inserted. That is, the job posting creation unit 115 may input initial conditions and an organizational information summary into the job posting creation model, and cause the job posting creation model to output a job posting with an organizational information summary inserted. Alternatively, the job posting creation unit 115 may input an existing job posting and an organizational information summary into the job posting creation model, and cause the job posting creation model to output a job posting with an organizational information summary inserted.

[0069] <Scout Document Creation Department 116> The scout document creation unit 116 is configured to create a scout document based on a job posting selected by an information user (such as a recruiter). The scout document is sent to job seekers registered in the information processing system 1 who are candidates for the job.

[0070] The scout document creation unit 116 may create a scout document by accepting text input from the information user terminal 20, or may input a job posting into the scout document creation model of the artificial intelligence unit 120 and have the scout document creation model output a scout document.

[0071] The scout document creation model is a learning model that is trained to use job postings as input and scout documents as output. In other words, the scout document creation model is a learning model that is trained using a combination of a training job posting and the scout document data corresponding to that job posting as training data.

[0072] The scout document creation model may also be a generative AI that includes a large-scale language model. In this case, the scout document creation unit 116 inputs a job posting, inputs a prompt including an instruction to output a scout document to the scout document creation model, and causes the scout document creation model to output the scout document. The scout document creation unit 116 may generate a prompt that instructs the scout document creation model to create a scout document from the job posting, and input the prompt to the scout document creation model. The scout document creation unit 116 may also input a prompt that inserts, for example, one or more sample job postings and one or more corresponding scout document samples to the scout document creation model in addition to the scout document creation and output instruction and the job posting. The scout document creation model creates a scout document from the job posting according to the input prompt.

[0073] The scout document creation unit 116 may create a scout document for a job seeker with the organizational information summary inserted. This allows the employer to create a scout document containing organizational information without collecting and inputting organizational information. The scout document creation unit 116 may insert the entire organizational information summary into the scout document, or may extract some items from the organizational information summary (e.g., organization overview, business content, etc.) and insert them into the scout document.

[0074] The scout document creation unit 116 may insert the organizational information summary into a scout document created manually by a recruiter or an existing scout document, or may insert the organizational information summary into a scout document output (i.e., automatically generated) by the scout document creation model described above. When inserting the organizational information summary into a scout document created manually by a recruiter or the like, the scout document creation unit 116 acquires a scout document created by the recruiter or the like inputting text using the input unit 24 of the information user terminal 20, and also acquires the organizational information summary created by the organizational information summary creation unit 114. The scout document creation unit 116 then inserts the organizational information summary into the acquired scout document. When inserting the organizational information summary into an existing scout document, the scout document creation unit 116 acquires the existing scout document by means of file upload from the information user terminal 20 or other means, and also acquires the organizational information summary created by the organizational information summary creation unit 114. The scout document creation unit 116 then inserts the organizational information summary into the existing scout document that has been acquired. The location in the scout document where the organizational information summary is to be inserted may be selected arbitrarily by the recruiter or the like, or a predetermined location, such as an item describing the organization in the scout document, may be set as the insertion location in advance.

[0075] The scout document creation model may also be a learning model that has been trained to be able to output a scout document with an organizational information summary inserted. That is, the scout document creation unit 116 may input a job posting and an organizational information summary into the scout document creation model, and cause the scout document creation model to output a scout document with an organizational information summary inserted. Alternatively, the scout document creation unit 116 may input an existing scout document and an organizational information summary into the scout document creation model, and cause the scout document creation model to output a scout document with an organizational information summary inserted.

[0076] <Position Information Creation Department 117> The position information creation unit 117 is configured to create hiring position information, which is information about positions estimated to be needed by the organization, based on the organizational information summary. Specifically, the position information creation unit 117 inputs the organizational information summary created by the organizational information summary creation unit 114 into a hiring position information creation model of the artificial intelligence unit 120 and causes the hiring position information creation model to output at least one hiring position information. This makes it possible to present potential hiring position information based on the organizational information summary to information users (such as human resources managers and recruiters within the organization). Furthermore, by inputting the organizational information summary with reduced unnecessary information (noise) into the hiring position information creation model, it is possible to present positions that are more suitable for solving organizational issues to information users than when organizational information on a website is directly input into the hiring position information creation model.

[0077] The hiring position information includes, in addition to the name of the position required to solve the problem, information such as the reason the position is needed, the department hiring for the position, required experience, skills, job content, job responsibilities, job title, etc. Each element included in the hiring position information may be composed of sentences (natural language), tagged keywords, or a combination of sentences and keywords.

[0078] The hiring position information creation model is a learning model that has been trained to be able to input an organizational information summary and output hiring position information. The hiring position information creation model is a learning model that has trained using a combination of a learning organizational information summary and hiring position information based on the organizational information summary as training data. Note that the learning organizational information summary for the hiring position information creation model does not have to be one created by the organizational information summary creation unit 114, as long as it has the same format, structure, etc. as the organizational information summary created by the organizational information summary creation unit 114.

[0079] The hiring position information creation model may be a generative AI including a large-scale language model. In this case, the position information creation unit 117 inputs the organizational information summary, inputs a prompt including an instruction to output hiring position information to the hiring position information creation model, and causes the hiring position information creation model to output the hiring position information. The position information creation unit 117 may generate a prompt that instructs the hiring position information creation model to create hiring position information from the organizational information summary, and input the prompt to the hiring position information creation model. Furthermore, in addition to the instruction to create and output hiring position information and the organizational information summary, the position information creation unit 117 may input a prompt to the hiring position information creation model that inserts, as input and output samples, for example, one or more samples of organizational information summary and one or more corresponding hiring position information samples. The hiring position information creation model creates hiring position information from the organizational information summary in accordance with the input prompt.

[0080] Furthermore, the position information creation unit 117 may input an instruction to the hiring position information creation model to output hiring position information by referring to the issues included in the organization information summary. This allows for accurate estimation of positions required to solve organizational issues.

[0081] The position information creation unit 117 may input an instruction to prioritize the hiring position information together with an instruction to output the hiring position information to the hiring position information creation model. For example, the position information creation unit 117 inserts an instruction to output multiple hiring position information in order of priority into a prompt input to the hiring position information creation model.

[0082] The position information creation unit 117 may add supplemental information not included in the organizational information summary to the hiring position information output by the hiring position creation model. The supplemental information may include, for example, the filling status of the relevant position within the organization (such as the name of the current employee and the number of employees). The hiring position creation model may also be a learning model that has been trained to be able to output hiring position information including the supplemental information. In other words, the position information creation unit 117 may input the organizational information summary and the source of the supplemental information into the hiring position creation model and cause the hiring position creation model to output hiring position information including the supplemental information.

[0083] The position information creation unit 117 may output multiple hiring positions from an organization information summary for one organization to the hiring position creation model, estimate recommended positions for recruitment in the organization based on the multiple hiring position information and the information on job openings for the organization registered in the job database, and present the estimated recommended positions. This makes it possible to present to information users positions that are necessary for solving organizational problems but are not currently hiring.

[0084] The "job database" is not limited to a database registered or referenced by the job recruitment and job search service configured by the information processing system 1, but may also be a database in which job recruitment is registered in a service external to the information processing system 1. In other words, the job recruitment information (typically, a job posting) referenced by the position information creation unit 117 when recommending a recommended position may be job recruitment information imported from a service external to the information processing system 1, or may be job recruitment information published on the Internet.

[0085] The position information creation unit 117 accesses the job reference website based on website access information (e.g., the URL of the job reference website) to the job reference website that is provided by the information user (employer) or included in the organization information site that the reception unit 112 receives. The job reference website is a site that includes job information access information for accessing job information. Note that the organization information site that the reception unit 112 receives (entered into the information user terminal 20) may be a job reference website (when recruitment information is posted on the organization information site).

[0086] Examples of job reference websites include an organization's recruitment site and a job posting list page prepared for each organization provided by the organization's applicant tracking system (ATS: Applicant Tracking System). A job posting list page is a website that lists job postings along with job posting links (job information access information) for each job posting. The job posting list page may be a website that can be viewed only by organizations associated with the posted job postings (with viewing restrictions).

[0087] The position information creation unit 117 uses the website access information to acquire multiple job posting links contained in the job posting reference website. Note that the job posting reference website may also include links other than job posting links (for example, links to a privacy policy display page or a help page). Therefore, the position information creation unit 117 extracts only the job posting links from among the links contained in the job posting reference website, for example, by URL pattern recognition. Furthermore, the position information creation unit 117 performs a crawling or web scraping process on the extracted job posting links to acquire job posting data from the web pages of each URL.

[0088] The reference job postings that the position information creation unit 117 refers to when recommending a recommended position are job postings for which job postings are available, job postings that are currently being recruited, and job postings for which the time since the job posting was concluded is within a predetermined value (for example, one month).

[0089] The position information creation unit 117 compares the positions included in the hiring position information with the available positions included in the reference job posting, and determines that any position included in the hiring position information that is not identical to or similar to the available position is a recommended position. In other words, the position information creation unit 117 may determine that the recommended position is the difference between the positions included in the hiring position information and the available positions currently being recruited. The similarity criterion for positions is a threshold value for the difference in feature amounts (vector distance) between two positions, and, for example, positions whose feature amount difference is less than the threshold value (for example, the cosine similarity of the vector data is equal to or greater than a threshold) are determined to be similar to each other. The similarity of positions may also be determined by referencing a table that defines similar position names in advance.

[0090] The position information creation unit 117 may extract recommended positions from the positions extracted from the comparison between the hiring position information and the reference job posting by further comparing the positions with the current organizational structure. The organizational structure includes the current organizational chart, the number of current employees in each position, etc. For example, the position information creation unit 117 determines that a position where the gap between the number of current employees and the required number of employees is equal to or greater than a predetermined value is a recommended position.

[0091] The position information creation unit 117 may present the number of candidates who meet the conditions of the hiring position information among the personnel within the organization or job seekers registered in the job seeker database, or the number of job openings registered in the job openings database from organizations other than the organization for which the hiring position information was created that have conditions similar to those of the hiring position information. This allows the information user to understand the hiring difficulty of the position included in the hiring position information. In other words, the more candidates there are, the lower the hiring difficulty, and the more similar job openings there are, the higher the hiring difficulty. Therefore, this information can be provided to the information user as the hiring difficulty.

[0092] Candidates who meet the conditions of the hiring position information are extracted, for example, by a matching index that indicates the degree of match between the hiring position information and the registered information of personnel within the organization or job seekers. For example, the position information creation unit 117 counts personnel within the organization or job seekers whose matching index is equal to or greater than a predetermined threshold as candidates.

[0093] The matching index is calculated as the similarity (for example, cosine similarity) between the vector data of the employment position information (particularly the recruitment conditions such as experience and skills) and the vector data of the job seeker's registration information, for example.

[0094] The position information creation unit 117 may input the hiring position information and the job seeker's registration information into the matching index calculation model of the artificial intelligence unit 120 and cause the matching index calculation model to output a matching index. The matching index calculation model is a learning model that receives the hiring position information and the registration information as input and is trained to output a matching index. In other words, the matching index calculation model is a learning model that is trained using combinations of the hiring position information, the registration information, and the corresponding matching indexes as training data.

[0095] The matching index calculation model may also be a generative AI including a large-scale language model. In this case, the position information creation unit 117 receives the hiring position information and the registered information as input, inputs a prompt including an instruction to calculate a matching index based on the hiring position information and the registered information to the matching index calculation model, and causes the matching index calculation model to output the matching index. The position information creation unit 117 may generate a prompt that instructs the matching index calculation model to calculate a matching index from the hiring position information and the registered information, and input the prompt to the matching index calculation model. The position information creation unit 117 may also input a prompt to the matching index calculation model that includes, as input and output samples, one or more samples of hiring position information and registered information and one or more corresponding matching index samples, in addition to the instruction to calculate and output the matching index, the hiring position information, and the registered information. The matching index calculation model calculates a matching index from the hiring position information and the registered information according to the input prompt.

[0096] Job offers with conditions similar to those of the hiring position information are extracted, for example, by a similarity index indicating the degree of similarity between the hiring position information and job postings of other organizations. The position information creation unit 117 counts, for example, job offers from other organizations with a similarity index equal to or greater than a predetermined threshold as job offers with conditions similar to those of the hiring position information.

[0097] The similarity index is calculated as the degree of similarity (for example, cosine similarity) between the vector data of the employment position information (particularly, recruitment conditions such as experience and skills) and the vector data of the job posting.

[0098] The position information creation unit 117 may input the hiring position information and the job advertisement into a similarity calculation model of the artificial intelligence unit 120 and cause the similarity calculation model to output a similarity. The similarity calculation model is a learning model that receives the hiring position information and the job advertisement as input and is trained to output a similarity. In other words, the similarity calculation model is a learning model that is trained using combinations of the hiring position information, the job advertisement, and the corresponding similarities as training data.

[0099] The similarity calculation model may also be a generative AI including a large-scale language model. In this case, the position information creation unit 117 receives the hiring position information and the job posting, inputs a prompt including an instruction to calculate the similarity based on the hiring position information and the job posting to the similarity calculation model, and outputs the similarity. The position information creation unit 117 may generate a prompt that instructs the similarity calculation model to calculate the similarity from the hiring position information and the job posting, and input the prompt to the similarity calculation model. The position information creation unit 117 may also input a prompt to the similarity calculation model that includes, in addition to the instruction to calculate and output the similarity, the hiring position information, and the job posting, one or more samples of the hiring position information and the job posting, and one or more corresponding similarity samples as input and output samples. The similarity calculation model calculates the similarity from the hiring position information and the job posting according to the input prompt.

[0100] The position information creation unit 117 may create a job posting for internal recruitment or for job seekers outside the organization based on the hiring position information. For example, the position information creation unit 117 inputs the hiring position information into a job posting creation model and causes the job posting creation model to output a job posting corresponding to the position targeted by the hiring position information. The job posting creation model here is a learning model that has been trained to take hiring position information as input and output a job posting. Furthermore, the position information creation unit 117 may input hiring position information and input a prompt including an instruction to output a job posting into the job posting creation model, which is a generative AI including a large-scale language model, and cause the job posting creation model to output the job posting.

[0101] <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.

[0102] 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, and GPT-3), BERT (Bidirectional Encoder Representations from Transformers), and BART (Bidirectional and Auto-regressive Transformer), and language models such as Recurrent Neural Networks (RNNs), and may include generative AI.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] The learning models included in the artificial intelligence unit 120 (learning models used in each functional unit, such as a summary creation model, a recruitment background creation model, and a hiring position information creation model) can undergo additional learning as transfer learning or fine tuning. For example, each time new job seeker registration information and new job postings are registered, the artificial intelligence unit 120 may perform additional learning and fine tuning using these as new training data. This improves the accuracy of the information output from the learning models.

[0107] 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.

[0108] For example, the summary creation model etc. may be a distilled model 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 summary creation model etc., and once training data from the large-scale language model has been accumulated, a distilled model obtained by knowledge distillation using the training data may be used as the summary creation model etc.

[0109] <Display section> The display unit 211 of the information user 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.

[0110] <Operation acquisition part> The operation acquisition unit 212 of the information user terminal 20 accepts operations by a user (information user) who uses the information user terminal 20. The operation acceptance unit 312 of the job seeker terminal 30 accepts operations by a user (job seeker) who uses the job seeker terminal 30.

[0111] 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.

[0112] This information processing includes a receiving step, an acquisition step, and an organization information summary creation step. In the receiving step, input of first access information for accessing the organization information site is accepted. In the acquisition step, information about the organization is acquired as summary creation information from the organization information site and at least one secondary access site linked to the organization information site based on the first access information. In the organization information summary creation step, the summary creation information acquired from the organization information site and the secondary access site is input to a summary creation model, and the summary creation model is caused to output an organization information summary.

[0113] 7 is an activity diagram showing the flow of information processing (processing for creating an organization information summary) executed by the information processing system 1. Below, the information processing will be explained along with each activity in this activity diagram.

[0114] The process of creating an organization information summary begins with the input of primary access information by an information user. The information user inputs the primary access information (e.g., the URL of an organization information site) into the information user terminal 20 (activity A101). The server device 10 accepts the input of the primary access information from the information user terminal 20 and acquires secondary access information (e.g., the URL of a secondary access site) included in the organization information site (activity A102).

[0115] After acquiring the second access information, the server device 10 acquires summary creation information from the organization information site and the secondary access site (activity A103). Next, the server device 10 creates an organization information summary by inputting the summary creation information into a summary creation model (activity A104). Furthermore, the server device 10 outputs the created organization information summary to the information consumer terminal 20 (activity A105). As a result, the organization information summary is displayed (presented) on the information consumer terminal 20 (activity A106).

[0116] 4. Effect The operation of this embodiment can be summarized as follows: A user can input primary access information (e.g., the URL of an organization information site) to create an organization information summary based on public information. Furthermore, when creating the organization information summary, in addition to the organization information site, secondary access sites linked to the organization information site are also referenced, so an organization information summary of consistent quality can be obtained.

[0117] 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.

[0118] 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.

[0119] The control unit 11 does not necessarily have to use the organizational information summary created by the organizational information summary creation unit 114 in the job posting creation unit 115 and the scout document creation unit 116. In addition, the control unit 11 does not necessarily have to have the position information creation unit 117.

[0120] The aspect of this embodiment is not limited to the information processing system 1, but may be an information processing method or a program. The job search support 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.

[0121] It may be provided in the following manner.

[0122] (1) An information processing system including at least one processor, the processor configured to execute each of the following steps by reading a program: a receiving step receiving input of first access information for accessing an organization information site, the organization information site being a website containing information about the organization; an acquisition step acquiring information about the organization from the organization information site and at least one secondary access site linked to the organization information site based on the first access information, the secondary access site being a website accessible from second access information included in the organization information site; an organization information summary creation step inputting the summary creation information acquired from the organization information site and the secondary access site into a summary creation model and causing the summary creation model to output an organization information summary, the organization information summary being a document summarizing the information about the organization; and a learning model trained to be able to input the summary creation information and output the organization information summary.

[0123] (2) In the information processing system described in (1) above, the organizational information summary is a document that summarizes information about the organization by item.

[0124] (3) In the information processing system described in (1) or (2) above, in the organizational information summary creation step, the names of items included in the organizational information summary are input to the summary creation model along with an instruction to output the organizational information summary.

[0125] (4) In the information processing system described in (3) above, in the organizational information summary creation step, an instruction is further input to the summary creation model not to output as the organizational information summary any item corresponding to the item name whose corresponding description or content is not included in the summary creation information.

[0126] (5) In an information processing system described in any one of (1) to (4) above, in the acquisition step, reference access information to be referenced to acquire the summary creation information is selected from the second access information contained in the organization information site based on the URL of the secondary access site and reference information contained in the second access information, wherein the reference information includes a correspondence between a character string contained in the URL and the reference access information.

[0127] (6) In the information processing system described in (5) above, in the obtaining step, the second access information in which the URL includes a predetermined first character string is selected as the reference access information.

[0128] (7) In the information processing system described in (5) or (6) above, in the acquisition step, the second access information in which the URL contains a predetermined second string is not selected as the reference access information.

[0129] (8) In the information processing system described in any one of (1) to (7) above, the processor is configured to further execute the following steps: in the job posting creation step, a selection of a recruitment background from among a plurality of recruitment background options, which includes at least one option output by the recruitment background creation model by inputting the organizational information summary into the recruitment background creation model, and a job posting is created based on the selected recruitment background; and wherein the recruitment background creation model is a learning model that has been trained to be able to input the organizational information summary and output the recruitment background options.

[0130] (9) In the information processing system described in any one of (1) to (8) above, the processor is configured to further execute the following steps: in the job posting creation step, a job posting is created with the organizational information summary inserted.

[0131] (10) In the information processing system described in any one of (1) to (9) above, the processor is configured to further perform the following steps: in the scouting document creation step, a scouting document for the job seeker is created, with the organizational information summary inserted therein.

[0132] (11) In the information processing system described in any one of (1) to (10) above, the processor is configured to further execute the following steps: in the position information creation step, the organizational information summary is input into a hiring position information creation model, and the hiring position information creation model is caused to output at least one hiring position information, wherein the hiring position information is information about a position estimated to be needed by the organization, and the hiring position information creation model is a learning model that takes the organizational information summary as input and is trained to be able to output the hiring position information.

[0133] (12) In the information processing system described in (11) above, the organizational information summary includes the challenges of the organization, and in the position information creation step, an instruction is input to the hiring position information creation model to output the hiring position information by referring to the challenges included in the organizational information summary.

[0134] (13) In the information processing system described in (11) or (12) above, in the position information creation step, recommended positions for recruitment in the organization are estimated based on the plurality of employment position information and information on job openings in the organization registered in a job database, and the estimated recommended positions are presented.

[0135] (14) In the information processing system described in any one of (11) to (13) above, in the position information creation step, the information processing system presents the number of candidates who meet the conditions of the hiring position information among the human resources within the organization or job seekers registered in the job seeker database, or the number of job openings in organizations other than the organization registered in the job openings database that have conditions similar to those of the hiring position information.

[0136] (15) An information processing method, comprising steps executed by the information processing system according to any one of (1) to (14) above.

[0137] (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.

[0138] 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]

[0139] 1: Information processing system 2: Communication line 10: Server device 11: Control section 12: Storage section 13: Communications Department 14: Communication bus 20: Information user 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: Reception 113: Acquisition Department 114: Organization Information Summary Creation Department 115: Job posting department 116: Scout Document Creation Department 117: Position Information Creation Department 120: Artificial Intelligence Department 211:Display section 212: Operation acquisition section 311: Display section 312: Operation reception section

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 receiving step, input of first access information for accessing the organization information site is received, Here, the organization information site is a website that includes information about the organization, In the obtaining step, information about the organization is obtained as summary creation information from the organization information site and at least one secondary access site linked to the organization information site based on the first access information; wherein the secondary access site is a website accessible from second access information included in the organization information site, In the organization information summary creation step, the summary creation information acquired from the organization information site and the secondary access site is input to a summary creation model, and an organization information summary is output from the summary creation model; Here, the organizational information summary is a document summarizing information about the organization, and the summary creation model is a learning model that has been trained to take the summary creation information as input and output the organizational information summary, in this information processing system.

2. 2. The information processing system according to claim 1, An information processing system, wherein the organizational information summary is a document summarizing information about the organization by item.

3. 2. The information processing system according to claim 1, In the organizational information summary creation step, an instruction to output the organizational information summary and item names included in the organizational information summary are input to the summary creation model.

4. 4. The information processing system according to claim 3, In the organizational information summary creation step, an information processing system further inputs into the summary creation model an instruction not to output as the organizational information summary any item corresponding to the item name whose corresponding description or content is not included in the summary creation information.

5. 2. The information processing system according to claim 1, In the acquiring step, based on the URL of the secondary access site and the reference information included in the second access information, reference access information to be referenced to acquire the summary creation information is selected from the second access information included in the organization information site; Here, the reference information includes a correspondence between a character string included in the URL and the reference access information.

6. 6. The information processing system according to claim 5, In the acquiring step, the second access information in which the URL includes a predetermined first character string is selected as the reference access information.

7. 6. The information processing system according to claim 5, In the acquiring step, the second access information in which the URL includes a predetermined second character string is not selected as the reference access information.

8. 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, a selection of a recruitment background is accepted from among a plurality of recruitment background options, the selection including at least one option outputted from the recruitment background creation model by inputting the organization information summary into the recruitment background creation model, and a job posting is created based on the selected recruitment background; Here, the recruitment background creation model is a learning model that has been trained to be able to input the organizational information summary and output options for the recruitment background, in this information processing system.

9. 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 organization information summary is inserted.

10. 2. The information processing system according to claim 1, The processor is further configured to perform the steps of: In the scout document creation step, the information processing system creates a scout document for the job seeker, into which the organization information summary is inserted.

11. 2. The information processing system according to claim 1, The processor is further configured to perform the steps of: In the position information creation step, the organizational information summary is input to a hiring position information creation model, and the hiring position information creation model is caused to output at least one hiring position information; Here, the recruitment position information is information on positions that are estimated to be needed in the organization, An information processing system, wherein the hiring position information creation model is a learning model that is trained so as to be able to input the organizational information summary and output the hiring position information.

12. 12. The information processing system according to claim 11, the organizational information summary includes the organization's challenges; In the position information creation step, an instruction to output the employment position information by referring to the assignment included in the organizational information summary is input to the employment position information creation model, in an information processing system.

13. 12. The information processing system according to claim 11, In the position information creation step, an information processing system estimates recommended positions for recruitment in the organization based on the multiple pieces of hiring position information and job information for the organization registered in a job database, and presents the estimated recommended positions.

14. 12. The information processing system according to claim 11, In the position information creation step, the information processing system presents the number of candidates who meet the conditions of the hiring position information among the human resources within the organization or job seekers registered in a job seeker database, or the number of job openings in organizations other than the organization registered in a job openings database that have conditions similar to those of the hiring position information.

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