Re-employment support device

Abstract

To provide a re-employment support device for providing re-employment support reflecting diverse information exemplified by desired treatment conditions, etc. brought from background of resignation circumstances of re-employment applicants.SOLUTION: A re-employment support device 1 includes: a re-employment applicant extraction unit 114 for extracting re-employment applicant information satisfying a designated condition from a re-employment applicant database 132 for storing desired treatment conditions of the re-employment applicant in association with the re-employment applicant information; a condition receiving unit 112 for receiving working conditions; and a condition generation unit 113 that, when the working conditions are received, causes a large-scale language model 131 to generate conditions (first conditions) that the user is a re-employment applicant associated with the desired treatment conditions that do not conflict with the working conditions. When the first conditions are generated, the re-employment applicant extraction unit 114 extracts a first re-employment applicant information satisfying the first conditions from the re-employment applicant database 132.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a re-employment support device. [Background technology]

[0002] Workers, such as nurses, may resign for various reasons, such as childbirth, childcare, injury, illness, family circumstances, etc. Re-employment of former workers has the advantage of stabilizing the lives of the former workers and providing them with excellent human resources with work experience. However, it is not easy for former workers to find new jobs that meet their desired conditions for benefits, and it is not easy for companies to find former workers who meet their desired working conditions. Therefore, there is a need for a means to support former workers in finding new jobs.

[0003] (Prior Art) As an example of a conventional technique for supporting reemployment of former employees, Patent Document 1 discloses a reemployment support system that, when a former employee's desired working conditions are input, adds personnel data including the former employee's career history to the desired working conditions to create job-seeking data, which is stored in a job-seeking database, and when an employer's working conditions are input, adds work environment data of the employer's place of employment to the desired working conditions to create job offer data, which is stored in the job offer database, and when an employment introduction is made, the working conditions are compared with the job-seeking data, and the job offer data is presented to the former employee when the working conditions and the job-seeking data almost match. The technique of Patent Document 1 can easily build a highly reliable job-seeking database, and can provide a reemployment support system that can efficiently reemploy former employees in suitable positions in response to their job searches and job offers. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2003-256551 A Summary of the Invention [Problem to be solved by the invention]

[0005] For example, workers who quit their jobs to give birth or raise children may need to balance work with childcare and the changes in lifestyle that come with childcare when they return to work. Workers who quit their jobs due to injury or illness may need to adjust their work schedule to take into account the changes in their health due to the injury or illness when they return to work. Workers who quit their jobs for family reasons may need to adjust their work schedule to take into account their family circumstances when they return to work.

[0006] In this way, unlike workers who are hired as new graduates, former employees who seek reemployment may have diverse backgrounds related to the circumstances of their resignation. The technology of Patent Document 1 can efficiently carry out reemployment by matching working conditions with job-seeking data. However, it is considered difficult to respond to diverse backgrounds by simply matching working conditions with job-seeking data. Therefore, the technology of Patent Document 1 has room for further improvement in terms of providing reemployment support that takes diverse backgrounds into account.

[0007] One possible employment support service for outplacement would be to create a database of job seekers in collaboration with social networking services (SNS) and provide a fixed-price subscription service to introduce job seekers registered in the database to companies with job openings. Unlike employment support that incurs a success fee for each introduction, this type of employment support is capable of providing continuous employment support. For this reason, this type of employment support is considered suitable for outplacement support in that it allows the re-employment to proceed step by step, for example, from part-time employment to promotion to full-time permanent employment. However, even when providing such employment support as outplacement support, consideration must be given to a variety of backgrounds at the stage of matching the re-employment seekers with the new employers.

[0008] The present invention has been made in consideration of the above circumstances. The purpose of the present invention is to provide re-employment support that reflects various information exemplified by desired conditions of treatment, etc., that are derived from the background of the re-employment of the re-employment seeker. [Means for solving the problem]

[0009] As a result of intensive research into solving the above problems, the inventors have found that the above object can be achieved by extracting information from a database via a large-scale language model, etc. Thus, the inventors have completed the present invention. Specifically, the present invention provides the following.

[0010] The present invention provides a re-employment support device comprising a re-employment applicant extraction unit that extracts re-employment applicant information that satisfies specified conditions from a specified database in which the desired treatment conditions of re-employment applicants are stored in association with information related to the re-employment applicants (re-employment applicant information), a condition receiving unit that receives working conditions, and a condition generation unit that, when the working conditions are received, causes a large-scale language model to generate a condition (first condition) that the re-employment applicant is associated with desired treatment conditions that do not contradict the working conditions, wherein the re-employment applicant extraction unit extracts first re-employment applicant information that satisfies the first condition from the specified database when the first condition is generated.

[0011] The employment seeker extraction unit of the present invention can extract information on employment seekers who satisfy working conditions from a predetermined database in which the desired working conditions of the employment seekers are stored in association with the employment seeker information. Meanwhile, information is extracted from a database using processing based on data extraction commands written in a query language (database language) for performing data operations in a database, such as SQL (Structured Query Language), or commands written in a database language, such as software processing via an API (Application Programming Interface).

[0012] However, unlike new graduates, former employees who seek re-employment may have a variety of backgrounds related to the circumstances of their resignation. Therefore, the desired conditions of employment of those seeking re-employment may include a variety of desired conditions of employment written in natural language. On the other hand, database languages ​​are computer languages ​​designed for the specific task of using databases, and have different grammar from natural languages.

[0013] Due to the nature of desired working conditions and database languages, it is not easy to generate data extraction commands written in database languages ​​based on various working conditions and various desired working conditions written in natural language. For example, a procedure for generating data extraction commands based on data classification using a neural network is conceivable, but creating a program that can generate data extraction commands corresponding to a huge number of classifications corresponding to various working conditions and various desired working conditions is considered difficult to realize because it requires a great deal of effort.

[0014] Here, the large-scale language model is a language model that has been pre-trained using a large amount of text written in various languages ​​such as the languages ​​of various countries, database languages, etc. Through such pre-training, the large-scale language model has acquired an emergent ability to generate text with similar content in other languages ​​used in the pre-training based on natural language relating to various working conditions and various desired treatment conditions exemplified by sentences expressing requests regarding balancing childcare and work.

[0015] The present invention can generate first conditions written in a database language based on various working conditions and various desired treatment conditions written in a natural language by having a large-scale language model generate conditions (first conditions) that the job seeker is associated with desired treatment conditions that do not contradict the working conditions. As a result, the present invention can simultaneously utilize a database of the prior art operated using a database language and extract first job seeker information from the database based on the various working conditions and various desired treatment conditions written in natural language. Effect of the Invention

[0016] The present invention can provide out-employment support that reflects a variety of information, such as desired conditions of treatment, that are derived from the background of the job seeker's circumstances related to his or her resignation. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a block diagram showing the hardware and software configurations of a system S according to the present embodiment. [Diagram 2] FIG. 2 is an example of information stored in the job seeker database 132. [Diagram 3] FIG. 3 is an example of a job advertisement stored in the job advertisement database 133. [Figure 4] FIG. 4 is a main flowchart showing an example of a preferable flow of the support process executed by the support device 1 of this embodiment. [Diagram 5] FIG. 5 is a continuation of FIG. [Figure 6] FIG. 6 is a continuation of FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the drawings.

[0019] <System S> 1 is a block diagram showing the hardware and software configurations of a system S of this embodiment. Hereinafter, an example of a preferred embodiment of the hardware and software configurations of the system S of this embodiment will be described with reference to FIG.

[0020] The system S includes a reemployment support device 1 that provides reemployment support reflecting a variety of information, and a terminal T that is configured to be able to communicate with the support device 1 via a network N.

[0021] System S can be used for out-employment support by linking with social networking services (SNS) to create a database of job seekers and providing a service for introducing job seekers registered in the database to companies with job openings, on a fixed-price subscription basis. In out-employment support provided through subscriptions, System S can provide continuous employment support, unlike employment support in which a success fee is charged for each introduction. Specifically, System S provides continuous out-employment support by, for example, matching job seekers with new employers through the support process described below, and then managing the flow of the out-employment support so that job seekers can progress through the stages of re-employment, from part-time employment to promotion to full-time permanent employment.

[0022] [Support device 1] The support device 1 includes a control unit 11, a storage unit 13, and a communication unit 14. There is no particular limitation on the type of the support device 1. Examples of the type include a server, a cloud server, and the like.

[0023] The support device 1, using the hardware and software configurations of the system S of this embodiment described below, generates in the large-scale language model 131 conditions that the job seeker is associated with desired treatment conditions that do not contradict the received working conditions, and extracts information on job seekers who satisfy the conditions from the job seeker database 132. A preferred flow of the support process performed by the support device 1 will be described after an example of a preferred aspect of the hardware and software configurations of the system S of this embodiment.

[0024] The assistance device 1 is configured to execute a process of making the large-scale language model 131, which has been pre-trained using 500 GB or more of text, perform machine learning, and a process of making the large-scale language model 131, which has been subjected to the machine learning, generate advice. The execution of these processes is realized, for example, via an API related to the use of the large-scale language model 131. An example of a more detailed configuration of the assistance device 1 is given below.

[0025] [Control unit 11] The control unit 11 includes a central processing unit (CPU), a random access memory (RAM), and a read only memory (ROM).

[0026] The control unit 11 cooperates with the storage unit 13 and / or the communication unit 14 as necessary. The control unit 11 then realizes the following software components of the program of this embodiment executed by the support device 1: a machine learning unit 111, a condition receiving unit 112, a condition generating unit 113, a job seeker extraction unit 114, a solicitation message generating unit 115, a job advertisement generating unit 116, an advertisement providing unit 117, an advertisement evaluation receiving unit 118, a job advertisement extraction unit 119, a workplace evaluation receiving unit 120, a workplace evaluation analysis generating unit 121, and the like. The functions provided by each of the software components of the program of this embodiment will be described in the description of a preferred flow of the support process described later.

[0027] [Storage section 13] The memory unit 13 is a device in which data and / or files are stored, and includes a storage unit that stores data non-temporarily using a hard disk, a semiconductor memory, a recording medium, a memory card, and the like.

[0028] The storage unit 13 may have a mechanism that enables connection via the network N to a storage device or storage system such as a network attached storage (NAS), a storage area network (SAN), cloud storage, a file server, and / or a distributed file system.

[0029] The memory unit 13 stores programs executed by a microcomputer, a large-scale language model 131, a job seeker database 132, a job advertisement database 133, information related to workplaces such as job seekers who have subscriptions to recruitment services related to job seeker support, information related to the SNS for job seekers, various data received by the support device 1, various data generated by the support device 1, etc.

[0030] (Large-scale language model 131) The large-scale language model 131 (LLM) in this embodiment is a type of probabilistic model used in natural language processing, and is a model for probabilistically predicting how likely a given word or sentence is to occur in natural language. The large-scale language model 131 in this embodiment cooperates with the condition generating unit 113 and the like to generate a condition (first condition) that the applicant is an employment seeker associated with desired treatment conditions that do not contradict the working conditions.

[0031] The large-scale language model 131 may be stored in an external cloud server or the like and executed via an API (Application Programming Interface) related to the use of the large-scale language model 131, or may be stored in the storage unit 13. Since the large-scale language model 131 is executed via an API, the support device 1 has a simpler configuration and is more cost-effective than a configuration in which the large-scale language model 131 is stored in the storage unit 13. Since the large-scale language model 131 is stored in the storage unit 13, the support device 1 can execute processing related to the large-scale language model 131 without communicating with an external device such as a cloud server one by one. This allows the support device 1 to reduce processing delays related to communication, risks in information security, and the like.

[0032] It is preferable that the large-scale language model 131 is trained on a large amount of text, at least 500 GB (gigabytes). Examples of such models include ChatGPT, GPT-3.5, and GPT-4 from OpenAI (registered trademark), and LLaMa from Meta AI (registered trademark). It is considered that as the amount of training data increases, the performance of the language model increases along the broken neural scaling law (BNSL), and the model acquires emergent ability when transitioning between segments in the BNSL. Therefore, the large-scale language model 131 of this embodiment has an emergent ability related to the generation of the first condition, which is acquired according to the amount of text used in pre-training.

[0033] The large-scale language model 131 preferably has an upper limit of 30,000 or more contexts used to generate text when counting tokens, which are semantic chunks of text (words, etc.). This allows the large-scale language model 131 to generate the first condition that takes into account the working conditions described using a large number of tokens to include many conditions as context, and the first job advertisement that reflects the working conditions.

[0034] This also enables the large-scale language model 131 to generate solicitation letters addressed to job seekers relating to job seeker information written using a large number of tokens, generate analysis results of advertising evaluation text written using a large number of tokens, and generate analysis results for multiple workplace evaluations, which are multiple and therefore written using a large number of tokens.

[0035] It is preferable that the large-scale language model 131 is trained on text containing 10 trillion or more tokens. This is believed to give the large-scale language model 131 an emergent ability to generate first conditions, solicitation texts, analysis results of advertisement evaluation texts, analysis results of workplace evaluations, and the like, that reflect nuances according to the type of job at the workplace where the job is being recruited.

[0036] The large-scale language model 131 is preferably a model having a large number of parameters, at least 10 billion or more, so that the large-scale language model 131 can execute processing that fully reflects the emergent capabilities obtained from a large amount of text.

[0037] (Re-employment applicant database 132) The re-employment applicant database 132 (predetermined database) stores the desired treatment conditions of re-employment applicants in association with information related to the re-employment applicants (re-employment applicant information). The means for realizing the association is not particularly limited. The association may be realized, for example, in a manner in which the desired treatment conditions and the re-employment applicant information are associated on the re-employment applicant database 132, which is a relational database (RDB), or in a manner in which the desired treatment conditions are included in the re-employment applicant information. The re-employment applicant database 132 is configured so that the re-employment applicant extraction unit 114 can extract information on re-employment applicants who satisfy predetermined conditions.

[0038] In the following explanation, it is assumed that the association is realized in a manner in which various information associated with the re-employment applicant information, exemplified by desired working conditions, etc., is included in the re-employment applicant information. However, it will be understood by those skilled in the art that the association can be realized in a similar manner by using an RDB.

[0039] The information on re-employment applicants includes various personal information on the re-employment applicants, such as their name, age, sex, work history, and qualifications.

[0040] By including work history (e.g., years working as a registered nurse, years working as a medical office worker, work history at a care facility, etc.) as personal information in the re-employment applicant information, the support device 1 can handle working conditions including conditions related to work history. In other words, the support device 1 can extract re-employment applicants whose working conditions are consistent with their work history in addition to their desired treatment conditions. Therefore, the support device 1 can provide re-employment support that reflects a wider variety of information.

[0041] By including the qualifications held (e.g., registered nurse, assistant nurse, care worker, registered dietitian, etc.) and information related to the qualifications held (e.g., a nurse's history of attending specific practice training) as personal information in the re-employment applicant information, the support device 1 can handle working conditions including conditions related to the qualifications held. In other words, the support device 1 can extract re-employment applicants whose working conditions are consistent with their qualifications in addition to their desired treatment conditions. Therefore, the support device 1 can provide re-employment support that reflects a wider variety of information.

[0042] Desired treatment conditions include a wide variety of conditions, exemplified by, for example, job content, work location, whether or not there is a transfer and details thereof, working hours (including non-standard desired hours such as desired hours that vary depending on the day of the week or desired hours that vary only on specific days), working days (days of the week, etc.), contract period, employment type (contract employee, full-time employee, etc.), salary and salary increase system, whether or not there is social insurance and details thereof, whether or not there is childcare facilities and details thereof, whether or not there is childcare support and details thereof, whether or not there is retraining support and details thereof, whether or not there is support for obtaining qualifications and details thereof, and compliance efforts (measures against industrial accidents, measures against sexual harassment, measures against power harassment, health management support, etc.).

[0043] FIG. 2 is an example of information stored in the re-employment applicant database 132. In the example shown in FIG. 2, the re-employment applicant information of a re-employment applicant having personal information of the name "Yamada Hanako" includes, as personal information, age and gender "32-year-old female", qualification held "registered nurse (has completed specific practice training (adjustment of insulin dosage))", and work history "worked in the nephrology ward of △△ Hospital from △△ to △△ years". The re-employment applicant information further includes desired treatment conditions such as desired work content "nursing job", desired work location, etc. "preferred to be around △△ City, no transfers allowed", desired working hours, etc. "Monday to Thursday from 9:00 to 16:00, Friday to Saturday from 9:00 to 13:00, no work on the 10th to 25th of each month", desired employment type "no questions", preference regarding childcare support "it would be helpful if you could take care of my child after 15:00", and compliance compliance initiative "preferred to work at a place where sexual harassment prevention training is thoroughly conducted for female part-timers as well".

[0044] As a result, the support device 1 executes the support process described below based on the above-mentioned information stored in the re-employment applicant database 132, and can provide re-employment support that reflects a variety of information, such as personal information including the qualification of having received specific procedure training useful in a specific medical department, as well as desired working hours, which are irregular and include requests to take days off not only on days of the week but also on specific days, and desired conditions for treatment that call for an approach to compliance that differs from the implementation of typical harassment prevention training.

[0045] (Job Advertisement Database 133) Job advertisement database 133 (specific database) stores various job advertisements, such as job advertisements generated by job advertisement generation unit 116. Job advertisement database 133 is configured so that job advertisement extraction unit 119 can extract job advertisements that satisfy predetermined conditions.

[0046] The recruitment advertisements stored in the recruitment advertisement database 133 are not particularly limited. The recruitment advertisements include advertisements of various forms exemplified by, for example, a text form suitable for transmission via e-mail, transmission via short message, posting to a social networking service (SNS), a modified text form (e.g., HTML (HyperText Markup Language), etc.) that can achieve a higher expressiveness than text in transmission via e-mail, a form including text and images (e.g., PDF (Portable Document Format), web pages, etc.), a sound form suitable for transmission via voice calls, voice messages, etc., an image form suitable for image advertisements, an expressive video form, etc.

[0047] The job advertisements stored in the job advertisement database 133 preferably include text. When the job advertisements include text, it becomes easier to extract the text based on the condition of the text generated by the large-scale language model 131. When the job advertisements include multimedia information such as images, audio, and video, it is preferable that the job advertisements are associated with text indicating the contents of the multimedia information generated by various recognition processes for the multimedia information, in order to make it easier to extract the text based on the condition of the text.

[0048] FIG. 3 is an example of a job advertisement stored in the job advertisement database 133. In the example shown in FIG. 3, the job advertisement identified by ID "C0001" includes a job description "Nephrology experience preferred! Registered nurse wanted, welcome to work 3 days a week. Would you like to work in the nephrology ward of △△ City Hospital?" corresponding to the employment condition "Registered nurse who can work in the ward of nephrology at △△ City Hospital, can work 3 days a week, preferential treatment for those with experience in nephrology" and an image of a heart-shaped drip container. The job advertisement is also associated with text indicating the contents of the multimedia information of the text "Image of heart-shaped drip container" indicating the image. In the example shown in FIG. 3, the job advertisement identified by ID "C0002" includes a job description "Nursing worker who can work night shifts wanted! Work at △△ Special Nursing Home, nursing care workers are especially welcome." corresponding to the employment condition "Nursing worker working at △△ Special Nursing Home, night shifts available, preferential treatment for nursing care workers."

[0049] As a result, the support device 1 can execute the support processing described below based on the above-mentioned information stored in the job advertisement database 133, and provide job reemployment support that reflects diverse information, such as diverse types of job advertisements that reflect diverse working conditions.

[0050] [Communications Section 14] The communication unit 14 is not particularly limited as long as it can connect the support device 1 to the network N and communicate with the terminal T, etc. Examples of the communication unit 14 include a wireless device compatible with a mobile phone network, a device connectable to a wireless LAN, and a network card compatible with the Ethernet standard.

[0051] [Network N] The type of the network N is not particularly limited as long as it enables communication between the support device 1 and the terminal T, etc. The type of the network N is, for example, the Internet, a mobile phone network, a wireless LAN, etc.

[0052] [Terminal T] The terminal T includes a predetermined terminal used by a job seeker, a specific terminal used by a workplace such as a recruiter, etc. The type of the terminal T is not particularly limited. The terminal T is, for example, a personal computer, a laptop computer, a smartphone, a tablet terminal, etc. The terminal T is configured to execute a process of providing the support device 1 with desired working conditions input by the job seeker, etc., a process of providing the support device 1 with working conditions input by the recruiter, etc., a process of displaying a solicitation message received from the support device 1, a process of displaying a job advertisement received from the support device 1, etc.

[0053] [Main Flowchart of Support Processing] Fig. 4 is a main flow chart showing an example of a preferred flow of the support process executed by the support device 1 of this embodiment. Fig. 5 is a diagram continued from Fig. 4. Fig. 6 is a diagram continued from Fig. 5. The following is an example of a preferred flow of the support process executed by the support device 1 of this embodiment using Figs. 4 to 6.

[0054] The support process preferably includes a series of processes (steps S1 to S2) related to machine learning of the large-scale language model 131. This enables the support device 1 to generate text in the large-scale language model 131 with higher accuracy, such as a condition (first condition) that the job seeker is associated with desired treatment conditions that do not contradict the working conditions.

[0055] [Step S1: Determine whether to perform machine learning] The control unit 11 executes the machine learning unit 111 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process of determining whether to perform machine learning of the large-scale language model 131 by the machine learning unit 111 (step S1, machine learning determination step). If it is determined that machine learning is to be performed, the control unit 11 shifts the process to step S2. If it is not determined that machine learning is to be performed, the control unit 11 shifts the process to step S3.

[0056] The procedure of the machine learning determination step is not particularly limited as long as it performs the above-mentioned determination. For example, the procedure includes a procedure of determining that machine learning is to be performed when any of various learning data described later is stored in the storage unit 13 and when the storage is notified to the control unit 11.

[0057] [Step S2: Run machine learning] The control unit 11 executes a process of executing machine learning of the large-scale language model 131 based on the learning data by the machine learning unit 111 (step S2, machine learning step). The control unit 11 shifts the process to step S3.

[0058] (Learning data) The learning data in the machine learning step is not particularly limited. For example, the learning data includes one or more of the following. Below, examples of the learning data and the machine learning performed in the machine learning step based on the learning data are described.

[0059] The learning data in the machine learning step preferably includes learning data that includes working conditions as an explanatory function and includes a condition (first condition) that the job seeker is associated with desired treatment conditions that do not contradict the working conditions as an objective variable. In this way, the machine learning step can cause the large-scale language model 131 to machine-learn the generation of the first condition using the working conditions as an input. The first condition in the learning data is preferably written in a database language used to extract job seeker information from the job seeker database 132. In this way, the machine learning step can cause the large-scale language model 131 to machine-learn the generation of the first condition written in the database language used for extraction from the job seeker database 132.

[0060] The learning data in the machine learning step preferably includes learning data including desired working conditions as an explanatory function and including solicitation messages addressed to job seekers associated with the desired working conditions as a target variable. Thereby, the machine learning step allows the large-scale language model 131 to machine-learn the generation of solicitation messages addressed to job seekers related to the first job seeker information, using the desired working conditions associated with the first job seeker information as an input.

[0061] The learning data in the machine learning step preferably includes learning data that includes working conditions as explanatory functions and includes a job advertisement (first job advertisement) reflecting the working conditions as a target variable. In this way, the machine learning step allows the large-scale language model 131 to perform machine learning to generate the first job advertisement using the working conditions as an input.

[0062] The learning data in the machine learning step preferably includes learning data that includes a job advertisement and an evaluation of the job advertisement (advertising evaluation) as an explanatory function, and includes a condition (second condition) that the job advertisement is similar in content to a job advertisement related to a favorable advertising evaluation as a target variable. In this way, the machine learning step can cause the large-scale language model 131 to machine-learn the generation of the second condition using the advertisement evaluation as an input. The first condition in the learning data is preferably written in a database language used to extract job advertisements from the job advertisement database 133. In this way, the machine learning step can cause the large-scale language model 131 to machine-learn the generation of the second condition written in the database language used for extraction from the job advertisement database 133.

[0063] The learning data in the machine learning step preferably includes learning data including the advertisement evaluation text as an explanatory function and including the analysis result of the advertisement evaluation text as a target variable. In this way, the machine learning step can allow the large-scale language model 131 to machine-learn the generation of the analysis result of the advertisement evaluation text using the advertisement evaluation text as an input.

[0064] The learning data in the machine learning step preferably includes a plurality of workplace evaluations as explanatory functions and includes analysis results of the plurality of workplace evaluations as a response variable. In this way, the machine learning step allows the large-scale language model 131 to perform machine learning to generate analysis results related to the plurality of workplace evaluations using the plurality of workplace evaluations as input.

[0065] The support device 1 preferably includes a series of processes (steps S3 to S5) for extracting job seekers from the job seeker database 132 by generating first conditions from working conditions using the large-scale language model 131. This enables the support device 1 to simultaneously utilize a database of the prior art operated using a database language as the job seeker database 132 and extract first job seeker information from the job seeker database 132 based on various working conditions and various desired conditions for treatment described in natural language.

[0066] [Step S3: Determine whether working conditions have been received] The control unit 11 executes the condition receiving unit 112 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process of determining whether the working conditions have been received from the terminal T or the like by the condition receiving unit 112 (step S3, condition receiving step). If it is determined that the working conditions have been received, the control unit 11 stores the received working conditions in the storage unit 13 and moves the process to step S4. If it is not determined that the working conditions have been received, the control unit 11 moves the process to step S11.

[0067] (Working conditions) The working conditions received in the condition receiving step are not particularly limited as long as they can be given as input text to the large-scale language model 131. The working conditions include a wide variety of conditions, exemplified by, for example, the job content, the place of work, the presence or absence of transfer and details thereof, working hours (including non-standard desired time periods such as desired time periods that differ depending on the day of the week and desired time periods that differ only on a specific day), working days (days of the week, etc.), contract period, employment type (contract employee, full-time employee, etc.), salary and salary increase system, the presence or absence of social insurance and details thereof, the presence or absence of childcare facilities and details thereof, the presence or absence of childcare support and details thereof, the presence or absence of retraining support and details thereof, the presence or absence of support for obtaining qualifications and details thereof, and efforts regarding compliance (measures against industrial accidents, measures against sexual harassment, measures against power harassment, health management support, etc.), the atmosphere of the workplace, the hobbies of the superior, workplace customs, etc.

[0068] [Step S4: Generate the first condition] The control unit 11 executes the condition generating unit 113 in cooperation with the storage unit 13 and the communication unit 14. The control unit 11 then executes a process in which the condition generating unit 113 provides the large-scale language model 131 with an input including the working conditions received in step S3, and causes the large-scale language model 131 to generate a condition (first condition) that the job seeker is associated with desired treatment conditions that do not contradict the working conditions (step S4, first condition generating step). The control unit 11 moves the process to step S5.

[0069] As described above, the large-scale language model 131 of this embodiment is pre-trained using a large amount of text written in various languages ​​such as the languages ​​of various countries, database languages, etc. Through such pre-training, the large-scale language model 131 has acquired an emergent ability to generate text with similar content in another language used in the pre-training based on natural language relating to various working conditions and various desired treatment conditions exemplified by sentences expressing a desire to balance childcare and work.

[0070] Therefore, the first condition generation step generates a condition (first condition) that the applicant is an employment seeker associated with desired treatment terms that do not contradict the working conditions in the large-scale language model 131, thereby generating the first condition written in a database language based on the various working conditions and various desired treatment terms written in natural language.

[0071] [Step S5: Extract job seekers who meet the first condition] The control unit 11 executes the re-employment applicant extraction unit 114 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process of extracting, by the re-employment applicant extraction unit 114, information on re-employment applicants who satisfy the first condition generated in step S4 (first re-employment applicant information) from the re-employment applicant database 132 (step S5, re-employment applicant extraction step). The control unit 11 shifts the process to step S6.

[0072] By pre-training the large-scale language model 131 described above and generating the first conditions using the large-scale language model 131 that has been pre-trained, the support device 1 can simultaneously utilize a database of the conventional technology that is operated using a database language, and extract information on first re-employment applicants from the database based on various working conditions and various desired treatment conditions described in natural language.

[0073] The support process preferably includes a series of processes (steps S6 to S7) related to sending solicitation messages. This allows the support device 1 to support reducing the burden on recruiters by automatically sending solicitation messages addressed to job seekers. At this time, it is preferable that the large-scale language model 131 includes desired working conditions as an explanatory function, and machine learning is performed using learning data including solicitation messages addressed to job seekers associated with the desired working conditions as objective variables.

[0074] [Step S6: Generate solicitation text] The control unit 11 executes the solicitation message generation unit 115 in cooperation with the storage unit 13 and the communication unit 14. The control unit 11 then executes a process in which the solicitation message generation unit 115 causes the large-scale language model 131 to generate a solicitation message addressed to the job seeker related to the first job seeker information based on the desired treatment conditions, etc., related to the first job seeker information extracted in step S5 (step S6, solicitation message generation step). The control unit 11 shifts the process to step S7.

[0075] By pre-training the large-scale language model 131 described above and generating a solicitation message using the large-scale language model 131 that has been pre-trained, the support device 1 generates a solicitation message that attracts the interest of the job seeker related to the first job seeker information based on the desired working conditions, etc. The solicitation message generation step preferably includes a procedure of causing the large-scale language model 131 to generate a solicitation message that attracts the interest of the job seeker related to the first job seeker information based on the desired working conditions described above and the working conditions related to step S3, and that does not contradict the working conditions. This allows the support device 1 to generate a solicitation message that reflects the convenience of both parties regarding job seeking.

[0076] [Step S7: Sending solicitation letters] The control unit 11, in cooperation with the storage unit 13 and the communication unit 14, executes a process of sending the invitation message generated in step S6 to the terminal T used by the job seeker related to the first job seeker information extracted in step S5 (step S7, invitation message sending step). The control unit 11 moves the process to step S8.

[0077] The support process preferably includes a series of processes (steps S8 to S10) related to the generation and provision of job advertisements. This allows the support device 1 to support reducing the burden on recruiters by automatically providing job advertisements. At this time, it is preferable that the large-scale language model 131 includes working conditions as explanatory functions, and machine learning is performed using learning data including job advertisements associated with the working conditions as objective variables.

[0078] [Step S8: Determine whether to generate a job advertisement] The control unit 11 cooperates with the memory unit 13 and the communication unit 14 to execute the job advertisement generation unit 116. The control unit 11 then executes a process to determine whether or not to generate a job advertisement based on the working conditions received in step S3 using the job advertisement generation unit 116 (step S8, job advertisement generation determination step). If it is determined that a job advertisement should be generated, the control unit 11 moves the process to step S9. If it is determined that a job advertisement should not be generated, the control unit 11 moves the process to step S11.

[0079] The procedure of the determination in the step of determining whether or not to generate a job advertisement is not particularly limited. For example, the procedure may be a procedure of determining that a job advertisement is to be generated when data instructing the generation of an advertisement associated with the working conditions is received.

[0080] [Step S9: Generate job advertisement] The control unit 11 executes the job advertisement generation unit 116 in cooperation with the storage unit 13 and the communication unit 14. The control unit 11 then executes a process in which the job advertisement generation unit 116 generates a job advertisement (first job advertisement) reflecting the working conditions received in step S3 in the large-scale language model 131 based on the working conditions (step S9, job advertisement generation step). The control unit 11 moves the process to step S10.

[0081] By performing pre-training in the large-scale language model 131 described above and generating a job advertisement using the pre-trained large-scale language model 131, the support device 1 generates a job advertisement that reflects working conditions based on working conditions, etc. This allows the support device 1 to reduce the labor of recruiters.

[0082] The job advertisements generated in the job advertisement generation step include, for example, a landing page on a job advertisement site, a job advertisement post on a job seeker SNS, and a job direct mail sent to job seekers via email or the like.

[0083] [Step S10: Provide job advertisements] The control unit 11 executes the advertisement provision unit 117 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process of providing the job advertisement generated in step S9 to the terminal T, etc., by the advertisement provision unit 117 (step S10, first advertisement provision step). The control unit 11 shifts the process to step S11.

[0084] The destination of the job advertisement in the first advertisement providing step is not particularly limited. The destination of the job advertisement preferably includes, in addition to various job advertisement sites, an SNS (job seeker SNS) managed in the SNS management step described below. This allows the support device 1 to reduce the labor of recruiters involved in providing job advertisements via SNS. By providing the job advertisement to the job seeker SNS among SNSs, the support device 1 can provide the job advertisement to the job seeker SNS that is expected to be seeking information related to reemployment. This allows the support device 1 to provide job advertisements in which the number of job seekers relative to the number and frequency of job advertisements is greater than that of a job advertisement site.

[0085] If a landing page of a job advertisement site is generated in the job advertisement generating step, the destination of the job advertisement in the first advertisement providing step is preferably the job advertisement site.If a job advertisement post to be posted to a job seeker SNS is generated in the job advertisement generating step, the destination of the job advertisement in the first advertisement providing step is preferably the job seeker SNS.If a job direct mail is generated in the job advertisement generating step, the destination of the job advertisement in the first advertisement providing step is preferably job seekers.

[0086] [Step S11: Determine whether advertisement evaluation has been received] The control unit 11 executes the advertisement evaluation receiving unit 118 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process of determining whether an advertisement evaluation has been received from the terminal T or the like by the advertisement evaluation receiving unit 118 (step S11, advertisement evaluation receiving step). If it is determined that the advertisement evaluation has been received, the control unit 11 stores the received advertisement evaluation in the storage unit 13 and transfers the process to step S12. If it is not determined that the advertisement evaluation has been received, the control unit 11 transfers the process to step S15.

[0087] [Step S12: Generate second condition] The control unit 11 executes the condition generating unit 113 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process of causing the condition generating unit 113 to generate a condition (second condition) in the large-scale language model 131 that the job advertisement has a similar content to the job advertisement related to the favorable advertising evaluation among the advertising evaluations received in step S11 (step S12, second condition generating step). The control unit 11 shifts the process to step S13.

[0088] As described above, the large-scale language model 131 of this embodiment is pre-trained using a large amount of text written in various languages ​​such as the languages ​​of various countries, database languages, etc. Through such pre-training, the large-scale language model 131 has acquired an emergent ability to understand the working conditions shown in the job advertisement reflecting the various evaluations and working conditions that can be expressed in text, and to generate text in another language used for pre-training that has the same content as the working conditions shown in the job advertisement related to the evaluations that are determined to be favorable in the understanding.

[0089] Therefore, the second condition generation step can generate a second condition written in the database language by having the large-scale language model 131 generate a condition (second condition) that the job advertisement has content similar to that of a job advertisement related to a favorable advertising evaluation.

[0090] The advertisement evaluation received in the advertisement evaluation receiving step and referenced in the second condition generating step is not particularly limited as long as it can be expressed in text. Examples of the advertisement evaluation include information indicating a favorable evaluation of the job advertisement, exemplified by "Like!" on SNS, comments added to the job advertisement, reviews of the job advertisement, and the like. By having the large-scale language model 131 generate the second condition in the second condition generating step, the support device 1 can determine whether various evaluations that can be expressed in text are favorable evaluations. Then, based on the determination, the large-scale language model 131 can generate the second condition, which is a condition that the job advertisement is similar in content to the job advertisement related to the favorable advertisement evaluation.

[0091] [Step S13: Extract job advertisements] Control unit 11 executes job advertisement extraction unit 119 in cooperation with storage unit 13 and communication unit 14. Control unit 11 then executes a process of extracting job advertisements (second job advertisements) that satisfy the second condition generated in step S12 from job advertisement database 133 using job advertisement extraction unit 119 (step S13, job advertisement extraction step). Control unit 11 then shifts the process to step S14.

[0092] By pre-training the large-scale language model 131 described above and generating the second conditions using the large-scale language model 131 that has been pre-trained, the support device 1 can simultaneously utilize a conventional database operated using a database language and extract job advertisements from the database based on various evaluations that can be expressed in text and various working conditions described in natural language.

[0093] [Step S14: Provide job advertisement] The control unit 11 executes the advertisement provision unit 117 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process of providing the job advertisement extracted in step S13 to the terminal T or the like by the advertisement provision unit 117 (step S14, second advertisement provision step). The control unit 11 shifts the process to step S15.

[0094] [Advertising evaluation analysis step] The support process preferably includes, as a process related to an advertisement evaluation analysis generation unit (not shown), an advertisement evaluation analysis generation step of receiving an advertisement evaluation (advertisement evaluation text) written in a natural language, which is an advertisement evaluation of the job advertisement provided in the first advertisement providing step or the second advertisement providing step, and generating an analysis result of the advertisement evaluation text in the large-scale language model 131. This allows the support device 1 to provide the result of the analysis to the recruiter as material for improving the job advertisement.

[0095] [Work experience management steps] It is preferable that the support device 1 executes a work experience management step of managing a work experience program for re-employment seekers who wish to undergo work experience related to re-employment among the re-employment seekers extracted in step S5, or for work experience seekers who wish to undergo work experience related to re-employment after seeing the job advertisement provided in step S10 or step S14.

[0096] The work experience management step preferably includes a step of generating a work experience program that does not contradict the desired working conditions of the re-employment applicant and the working conditions of the workplace where the work experience will be performed (work experience program generation step), a step of notifying the contents of the work experience program (work experience program notification step), and a step of storing the progress of the work experience program in memory unit 13 and updating the progress based on information provided by the work experience applicant or the workplace (work experience program progress update step).

[0097] By including the work experience management step of generating a work experience program, the recruiter can proceed with the work experience for the work experience applicant according to the generated work experience program or a program in which the recruiter or the like has modified the generated work experience program, without expending the effort of generating a work experience program from scratch. The work experience program generation step preferably includes a procedure for generating a work experience program in the large-scale language model 131 based on the above-mentioned desired treatment conditions and working conditions. This allows the support device 1 to generate a work experience program that reflects a variety of desired treatment conditions and working conditions.

[0098] By including the work experience management step of the work experience program notification step, the recruiter can provide the work experience applicant with the generated notification or a notification that the recruiter or the like has modified from the generated notification, without expending the effort of generating a notification from scratch. The work experience program notification step preferably includes a procedure for generating a notification related to the work experience program in the large-scale language model 131 based on the above-mentioned work experience program. This allows the support device 1 to generate a notification about the work experience program that reflects a variety of desired treatment conditions and working conditions.

[0099] By including the work experience management step of updating the progress of the work experience program, the recruiter can manage the progress of the work experience program without having to spend time manually managing the progress of the work experience program one by one. This also enables the support device 1 to generate a notification according to the progress in the work experience program notification step.

[0100] [Reemployment Management Steps] It is preferable that the support device 1 executes a re-employment management step for managing the careers, etc., of re-employment seekers who have found new employment among the re-employment seekers extracted in step S5, or who have found new employment after seeing a job advertisement provided in step S10 or step S14.

[0101] By executing the reemployment management step, the support device 1 can, for example, treat the reemployed person as a part-time employee for a given period (e.g., about three to four years) or a given number of shifts set after reemployment, and then automatically promote the reemployed person to a full-time employee. Also, in the reemployment management step, the support device 1 can manage the acquisition of comments on reemployment from the reemployed person (word of mouth after reinstatement).

[0102] The support process preferably includes a series of processes (steps S15 to S17) for receiving a workplace evaluation from the work experience applicant on the workplace where the work experience took place or a workplace evaluation from the re-employed applicant on the new employer, and analyzing the workplace evaluation. This allows the support device 1 to provide the results of the analysis to the recruiter as materials for the hiring process and career management of the work experience applicant or the re-employed applicant.

[0103] [Step S15: Determine whether workplace evaluation has been received] The control unit 11 executes the workplace evaluation receiving unit 120 in cooperation with the storage unit 13 and the communication unit 14. The control unit 11 then executes a process to determine whether the workplace evaluation has been received from the terminal T or the like by the workplace evaluation receiving unit 120 (step S15, workplace evaluation receiving step). If it is determined that the workplace evaluation has been received, the control unit 11 stores the received workplace evaluation in the storage unit 13 and moves the process to step S16. If it is determined that the workplace evaluation has not been received, the control unit 11 returns the process to step S1 and repeats the processes from step S1 to step S17.

[0104] [Step S16: Generate analysis results of workplace evaluation] The control unit 11 executes the workplace evaluation analysis generation unit 121 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process in which the workplace evaluation analysis generation unit 121 generates analysis results of a plurality of workplace evaluations in the large-scale language model 131 with respect to the workplace evaluations received in step S15 (step S16, workplace evaluation analysis generation step). The control unit 11 moves the process to step S17.

[0105] The workplace evaluation received in the workplace evaluation receiving step and analyzed in the workplace evaluation analysis generating step is not particularly limited as long as it can be expressed in text. Examples of the workplace evaluation include a score indicating an evaluation of the workplace, comments and reviews on the workplace, etc. The workplace evaluation analysis generating step causes the large-scale language model 131 to generate the analysis results, so that the support device 1 can generate the analysis results for various workplace evaluations that can be expressed in text.

[0106] The analysis results generated in the workplace evaluation analysis generation step preferably include advice on improving the work environment of the workplace related to the workplace evaluation. The workplace evaluation is expected to include text showing the work environment of the workplace, text showing hints on improving the work environment, and the like. However, it may require a huge amount of work for a human recruiter to check a large number of workplace evaluations one by one and obtain hints on improving the work environment. By including advice on improving the work environment in the analysis results generated in the workplace evaluation analysis generation step, the support device 1 can provide the advice to the recruiter.

[0107] The analysis results generated in the workplace evaluation analysis generation step preferably include analysis results on the personality tendencies of the job seeker who provided the multiple workplace evaluations. There is a view that there is concern that posters who post negative comments, etc. on SNS, etc., tend to have personality tendencies that also cause negative behavior in the workplace, etc., that discourage other workers from working. By including analysis results on the personality tendencies of the job seeker in the analysis results generated in the workplace evaluation analysis generation step, the support device 1 can provide the recruiter with the analysis results on the personality tendencies of the job seeker as materials related to the hiring process of the job seeker.

[0108] [Step S17: Provide the analysis results of workplace evaluation] The control unit 11, in cooperation with the storage unit 13 and the communication unit 14, executes a process of providing the analysis result generated in step S16 to the terminal T, etc. (step S17, workplace evaluation analysis providing step). The control unit 11 returns the process to step S1, and repeats the processes from step S1 to step S17.

[0109] [SNS Management Steps] The support process preferably includes an SNS management step of managing a job-seeker SNS, which is an SNS whose main members are job-seekers. The management may be realized, for example, by a means for executing a program that realizes the job-seeker SNS in the support device 1, or by a means for transmitting and receiving information via an API to and from an external server that realizes the job-seeker SNS.

[0110] The SNS management step allows the support device 1 to send a solicitation message via the job seeker SNS in the solicitation message sending step. In addition, the SNS management step allows the support device 1 to provide a job advertisement via the job seeker SNS in the advertisement providing step.

[0111] The SNS management step preferably includes a procedure for reflecting information regarding desired working conditions and personal information described in the profiles of members of the job-seeker SNS in the job-seeker database 132. This allows the support device 1 to reflect members of the job-seeker SNS, their profiles, and the like in the job-seeker database 132.

[0112] When a job advertisement is provided via a job seeker SNS in the advertisement providing step, it is preferable that the SNS management step receives from the job seeker SNS the activity of members related to the provided job advertisement (viewing history of posts of the job advertisement etc. on the SNS, posts of comments and reviews on the job advertisement, evaluations of the job advertisement, etc.) as advertisement evaluations in the advertisement evaluation receiving step. This allows the support device 1 to obtain evaluations of the job advertisement from the job seeker SNS where interest in job seeker re-employment is expected to be high, and use the evaluations for support related to job seeker re-employment.

[0113] When a job advertisement is provided via a job-seeker SNS in the advertisement providing step, the SNS management step preferably includes a series of processes (matching step) in which an input including activity of job-seekers regarding the job advertisement is provided to the large-scale language model 131, a condition (third condition) that the job advertisement does not contradict the activity is generated in the large-scale language model 131, and job advertisements that satisfy the third condition are extracted from the job advertisement database 133.

[0114] As described above, the large-scale language model 131 of this embodiment is pre-trained using a large amount of text written in various languages ​​such as the languages ​​of various countries, database languages, etc. Through such pre-training, the large-scale language model 131 acquires an emergent ability to generate text with similar content in other languages ​​used in the pre-training based on the activity shown in the text.

[0115] The matching step can generate a third condition written in a database language based on various activities by having the large-scale language model 131 generate a condition (third condition) that the job advertisement is not inconsistent with the activity. This allows the support device 1 to realize a process (recommendation step) of introducing the workplace related to the extracted job advertisement to the job seeker based on the activity on the job seeker SNS, a process (scouting step) of introducing the job seeker to the recruiter of the workplace related to the extracted job advertisement, and the like.

[0116] [Reemployment document generation step] Re-employment applicants may have a variety of backgrounds, exemplified by the backgrounds related to the circumstances of their resignation. For this reason, re-employment applicants may have difficulty describing information including their backgrounds, exemplified by resumes, curriculum vitae, etc., in documents (re-employment documents) to be submitted to a new employer. For this reason, it is preferable that the support process includes a re-employment documents generation step that automatically generates re-employment documents. The re-employment documents are, for example, resumes, curriculum vitae, etc.

[0117] This automatic generation is realized by a series of processes including, for example, an interactive information gathering step in which information regarding re-employment documents entered by the re-employment seeker is used as input and large-scale language model 131 is made to generate text (information request text) that prompts the provision of information necessary for creating the re-employment documents, and a re-employment document generation execution step in which information entered by the re-employment seeker in response to the information request text is used as input and the re-employment documents are generated in large-scale language model 131.

[0118] The large-scale language model 131 of this embodiment has an emergent ability to generate information request text and new employment documents, which is acquired according to the amount of text used in pre-learning. Therefore, the support device 1 can extract various information from the new employment seeker, exemplified by desired working conditions, etc., derived from the background related to the circumstances of the new employment seeker's resignation, and generate new employment documents reflecting such information. Then, the support device 1 can register information related to the new employment seeker in the new employment seeker database 132 based on the new employment documents. In this way, the support device 1 can support the new employment seeker in creating new employment documents. Therefore, the support device 1 can reduce the burden on the new employment seeker and provide new employment support reflecting various information exemplified by desired working conditions, etc., derived from the background related to the circumstances of the new employment seeker's resignation.

[0119] [Recruitment interview support steps] The support process preferably includes a job interview support step of automatically generating questions to be asked by a new employer to a new job applicant at the job interview. The automatic generation is realized, for example, by a procedure of inputting information on the new job applicant stored in the new job applicant database 132 and generating questions in the large-scale language model 131.

[0120] The large-scale language model 131 of this embodiment has an emergent ability to generate job interview questions, which is acquired according to the amount of text used in pre-learning. Therefore, the support device 1 can generate questions that reflect a variety of information exemplified by the desired working conditions and working conditions at the new job, etc., that are derived from the background of the re-employment circumstances of the re-employment applicant. This allows the support device 1 to reduce the burden on the recruiter at the new job and provide re-employment support that reflects a variety of information exemplified by the desired working conditions and working conditions, etc., that are derived from the background of the re-employment circumstances of the re-employment applicant.

[0121] [Automatic response step] The support process preferably includes an automatic recruitment response step of automatically responding to a call, chat, or other communication received from a job seeker. The automatic response is realized, for example, by an interactive information collection step of converting an incoming communication into text using a voice recognition module as necessary, generating a response text for responding to the communication in the large-scale language model 131 using information about the job seeker stored in the job seeker database 132 and the text-type communication as input, converting the generated response text into voice using a voice synthesis module as necessary, and transmitting a response based on the response text in a format corresponding to the contact means by which the call was received (voice for a call, text for a chat, etc.), and a procedure of generating questions in the large-scale language model 131 using information input by the job seeker in response to the information request text as input.

[0122] The large-scale language model 131 of this embodiment has an emergent ability for generating response text, which is acquired according to the amount of text used in pre-learning. Therefore, the support device 1 can generate response text that reflects various information exemplified by the desired working conditions and working conditions at the new job, etc., that are derived from the background related to the circumstances of the re-employment of the job seeker. This allows the support device 1 to reduce the burden on the recruiter at the new job seeker and provide re-employment support that reflects various information exemplified by the desired working conditions and working conditions, etc., that are derived from the background related to the circumstances of the re-employment of the job seeker.

[0123] [Effects of Support Processing] In the above-mentioned support process, the re-employment applicant extraction unit 114 extracts information on re-employment applicants who satisfy the working conditions from a re-employment applicant database 132 (a specified database) in which the re-employment applicants' desired working conditions are stored in association with re-employment applicant information.

[0124] Incidentally, information is usually extracted from a database using processing based on data extraction commands written in a query language (database language) for performing data manipulation in a database, such as SQL (Structured Query Language), or commands written in a database language, such as software processing via an API (Application Programming Interface). Therefore, it is not easy to extract data under conditions that reflect a variety of working conditions and a variety of desired conditions for treatment.

[0125] The large-scale language model 131 of this embodiment is a language model that has been pre-trained using a large amount of text written in various languages ​​such as the languages ​​of various countries, database languages, etc. Through such pre-training, the large-scale language model 131 has acquired an emergent ability to generate text with similar content in another language used in the pre-training based on natural language relating to various working conditions and various desired treatment conditions, exemplified by sentences expressing a desire to balance childcare and work.

[0126] In the above-mentioned support process, the condition generating unit 113 can generate the first conditions described in a database language based on the various working conditions and various desired treatment conditions described in a natural language by having the large-scale language model 131 generate conditions (first conditions) that the job seeker is associated with desired treatment conditions that do not contradict the working conditions. This allows the support device 1 of this embodiment to simultaneously utilize a database of the prior art operated using a database language and extract first job seeker information from the job seeker database 132 based on the various working conditions and various desired treatment conditions described in a natural language.

[0127] Therefore, the support device 1 of this embodiment can provide re-employment support that reflects a variety of information exemplified by desired conditions of treatment and the like that are brought about based on the background related to the circumstances of the re-employment of the re-employment seeker.

[0128] <Usage example> The following is an example of how the support device 1 of this embodiment is used.

[0129] [Database update] The support device 1 updates the information stored in the job seeker database 132 based on the desired conditions of employment and personal information provided by the job seekers, and the profiles of members acquired from the job seeker SNS.

[0130] [Providing a recruitment platform] The support device 1 receives working conditions from a terminal T or the like used by a recruiter at the new employment destination who has a fixed-price subscription to a service that introduces new employment seekers. The support device 1 generates in the large-scale language model 131 a condition (first condition) that the new employment seeker is associated with desired treatment conditions that do not contradict the working conditions, and extracts information on the first new employment seeker who satisfies the first condition from the new employment seeker database 132. In this way, the support device 1 can provide a recruiting platform that introduces new employment seekers who meet the working conditions to recruiters, etc.

[0131] [Matching for re-employment] Based on the desired conditions of treatment as well as the activity of the job seeker on the job advertisement on the job seeker's SNS (for example, a job advertisement / employment that has been "liked", a job advertisement / employment with a favorable comment, a job advertisement / employment that has been favorably reviewed, etc.), the support device 1 generates a condition (third condition) that the job advertisement is not inconsistent with the activity in the large-scale language model 131, and extracts job advertisements that satisfy the third condition from the job advertisement database 133. Then, based on the job advertisement that is considered to be compatible with the job seeker related to the activity extracted based on the third condition, the support device 1 performs matching such as sending the job seeker an invitation to scout for the job destination related to the job advertisement and recommending the job seeker to the recruiter related to the job advertisement.

[0132] [Work experience registration] The support device 1 registers in the storage unit 13 the work experience applicants who have come to wish to undergo work experience at the new employer through the above-mentioned recruiting platform and matching. The support device 1 then generates a work experience program, transmits a notification related to the work experience program to the work experience applicants, and manages the progress status related to the work experience program. The support device 1 also receives word-of-mouth regarding the work experience (work experience word-of-mouth) and the like as workplace evaluations, generates the analysis results thereof, and provides advice regarding improvement of the working environment and analysis results regarding the personality tendencies of the new employers to the recruiting staff.

[0133] [Management after returning to work] The support device 1 registers in the storage unit 13 reemployed individuals (returnees) who have found employment (returned to work) at a new employment destination through the above-mentioned recruiting platform and matching. The support device 1 then generates a work experience program and manages the careers, etc., of the reemployed individuals. The support device 1 also receives word-of-mouth (word-of-mouth after reinstatement) and the like about the new employment destination as workplace evaluations, generates the analysis results, and provides advice about improving the work environment and analysis results about the personality tendencies of reemployment applicants to recruiters.

[0134] It should be noted that within the scope of the concept of the present invention, a person skilled in the art may come up with various modifications and alterations. It is understood that such modifications and alterations fall within the scope of the present invention. For example, even if a person skilled in the art appropriately adds, deletes, or modifies the design of the above-described embodiment, or adds, omits, or modifies the conditions of a process, these modifications and alterations are included in the scope of the present invention as long as they include the gist of the present invention. [Explanation of symbols]

[0135] S System 1 Support equipment 11 Control section 111 Machine Learning Department 112 Condition Receiving Unit 113 Condition generator 114 Reemployment applicant extraction department 115 Solicitation Text Generation Unit 116 Job Advertisement Generation Department 117 Advertising Department 118 Advertising Evaluation Reception Department 119 Job Advertisement Extraction Unit 120 Workplace Evaluation Reception Department 121 Workplace Evaluation Analysis and Generation Department 13 Storage section 131 Large-scale language models 132 Re-employment applicant database (prescribed database) 133 Job Advertisement Database (Specific Database) 14 Communications Department N Network T-Terminal

Claims

1. a re-employment applicant extraction unit that extracts information on re-employment applicants who satisfy designated conditions from a predetermined database in which the desired treatment conditions of re-employment applicants are stored in association with information on the re-employment applicants (re-employment applicant information); A condition receiving unit that receives working conditions; a condition generating unit that, when the working conditions are received, generates in a large-scale language model a condition (first condition) that the job seeker is associated with desired treatment conditions that do not contradict the working conditions; Equipped with the job seeker extraction unit extracts, when the first condition is generated, first job seeker information satisfying the first condition from a predetermined database; A device to assist with reemployment.

2. 2. The support device according to claim 1, further comprising a solicitation message generation unit that, when the first re-employment applicant information is extracted from a predetermined database, causes the large-scale language model to generate a solicitation message addressed to the re-employment applicant related to the first re-employment applicant information based on desired conditions of treatment associated with the first re-employment applicant information.

3. The support device according to claim 1 , further comprising a job advertisement generation unit that, when the working conditions are received, causes the large-scale language model to generate a first job advertisement that reflects the working conditions.

4. an advertisement providing unit that provides the job advertisement to a predetermined terminal used by the job seeker; an advertisement evaluation receiving unit that receives an evaluation of the job advertisement (advertising evaluation) from the specified terminal; A job advertisement extraction unit that extracts the job advertisements that satisfy specified conditions from a specific database in which the job advertisements are stored; Further equipped with The condition generating unit generates, in the large-scale language model, a condition (second condition) that the job advertisement has content similar to the job advertisement related to the favorable advertisement evaluation; The job advertisement extraction unit extracts, when the second condition is generated, a second job advertisement that satisfies the second condition from a specific database. The support device according to claim 3.

5. The advertisement evaluation includes an advertisement evaluation written in a natural language (advertisement evaluation text), The support device includes: An advertisement evaluation analysis generation unit that generates an analysis result of the plurality of advertisement evaluation texts in the large-scale language model, 5. The support device according to claim 4.

6. a workplace evaluation receiving unit that receives an evaluation of a workplace where the new employee will be employed (workplace evaluation) from the new employee; a workplace evaluation analysis generation unit that generates analysis results of the plurality of workplace evaluations in the large-scale language model; Further comprising: The support device according to claim 1 .

Images