Information processing method, program, and information processing device

Abstract

To provide a platform for providing job information by appropriately calculating a matching rate of a worker to a job offer, or by using the matching rate to propose an appropriate job offer according to the worker. [Solution] The information processing method involves an information processing device acquiring location information for a specified location, inputting specified statistical data into a learning model that estimates the matching rate for a specified range, the learning model being trained using learning data that includes at least the matching rate and statistical data for each past job offer within a specified range identified based on the location information, and estimating the matching rate for a specified day for job offers within the specified range using data output from the learning model.

Description

[Technical Field]

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

[0002] In recent years, a technology has become known that takes into account information other than resume information to reduce mismatches between job offers and job seekers and improve the matching rate, thereby delivering job information that improves the matching rate between job offers and job seekers (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-169869 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in conventional technology, the matching rate only takes into account the matching rate between a specific job offer and an applicant (also called a "worker") for that job offer, and there is room for improvement and variation in the use of the matching rate.

[0005] Therefore, one of the objectives of the disclosed technology is to provide an information processing method, program, and information processing device that can appropriately calculate the matching rate of workers to job offers on a platform that provides job information, or that can use the matching rate to suggest appropriate job offers according to the worker. [Means for solving the problem]

[0006] An information processing method according to one embodiment of the present disclosure includes an information processing device acquiring location information for a predetermined location, inputting predetermined statistical data into a learning model that estimates a matching rate within a predetermined range, the learning model being trained using learning data including at least the matching rate and statistical data for each past job offer within a predetermined range identified based on the location information, and estimating the matching rate for a predetermined day for job offers within the predetermined range using data output from the learning model. [Effects of the Invention]

[0007] The disclosed technology enables a platform that provides job information to appropriately calculate the matching rate of workers to job offers, or to use the matching rate to suggest appropriate job offers according to the worker. [Brief explanation of the drawings]

[0008] [Figure 1] 1A to 1C are diagrams illustrating examples of configurations of an information processing system according to the disclosed technology. [Figure 2] 1 is a block diagram illustrating an example of an information processing device according to a first embodiment. [Figure 3] FIG. 2 is a block diagram showing an example of a server according to the first embodiment. [Figure 4] FIG. 10 is a diagram showing an example of the correlation between the number of applicants three days before application and the number of people who have finally completed work according to the first embodiment. [Figure 5] FIG. 3 is a diagram showing an example of user information according to the first embodiment. [Figure 6] FIG. 2 is a diagram showing an example of job information according to the first embodiment. [Figure 7] FIG. 3 is a diagram showing an example of usage history information according to the first embodiment. [Figure 8] 10 is a flowchart showing an example of a process related to estimating a matching rate in a predetermined area according to the first embodiment. [Figure 9] FIG. 10 is a diagram showing an example of displaying a matching rate calculated in the first embodiment. [Figure 10]FIG. 10 is a block diagram illustrating an example of a server according to the second embodiment. [Figure 11] 10 is a flowchart showing an example of a job recommendation process according to the second embodiment. [Figure 12] FIG. 11 is a diagram showing an example of a job offer narrowing down screen on the worker side according to the second embodiment. [Figure 13] FIG. 11 is a diagram showing an example of a job listing screen including recommended job listings according to the second embodiment. [Figure 14] FIG. 11 is a diagram showing an example of specific job information transitioning from the job listing according to the second embodiment. [Figure 15] FIG. 11 is a diagram showing an example of a proposal screen for a business operator according to the second embodiment. [Figure 16] FIG. 11 is a diagram showing an example of a setting screen of a business operator according to the second embodiment. [Figure 17] FIG. 11 is a block diagram showing an example of a server according to the third embodiment. [Figure 18] FIG. 11 is a diagram showing the current status of each job offer according to the third embodiment. [Figure 19] FIG. 11 is a diagram showing an example of transportation information for each job offer according to the third embodiment. [Figure 20] 13 is a flowchart showing an example of a job recommendation process according to the third embodiment. [Figure 21] FIG. 11 is a diagram illustrating an example of a push notification according to the third embodiment. [Figure 22] FIG. 13 is a diagram showing an example of a job listing screen according to the third embodiment. [Figure 23] FIG. 13 is a diagram showing an example of a job listing screen according to the third embodiment. [Figure 24] FIG. 11 is a diagram showing an example of a setting screen of a business operator according to the third embodiment. [Figure 25] FIG. 11 is a flowchart showing an example of each process in the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. Note that the same elements are denoted by the same reference numerals, and redundant description will be omitted.

[0010] [Disclosed Technology] The disclosed technology provides a service (hereinafter also referred to as the "recruitment service") that allows users to view and apply for job information on a platform that provides job information (also referred to as the "job information providing platform"). The disclosed technology not only calculates the matching rate between a specific job and a worker, but also calculates the matching rate for each job in a specified area, or suggests appropriate job offers to workers based on the worker's location and the matching rate for each job offer. Businesses aim to alleviate labor shortages by using the job information providing platform to solicit job offers from workers.

[0011] In the disclosed technology, "area" may refer to a predetermined range based on the location of a worker. For example, GPS (Global Positioning System) location information may be acquired from the processing terminal used by the worker, and a range within a predetermined distance based on this location information may be set as the area. This makes it possible to identify job information with work locations within an area that includes the worker's current location, rather than a general area such as a city, town, or village.

[0012] According to the above processing, for example, in a job information providing platform, by appropriately calculating the matching rate of workers for each job offer according to a predetermined area, it becomes possible to use this information to set up job information and analyze job information. Furthermore, in the job information providing platform, it becomes possible to propose appropriate job offers according to workers and adaptively change salaries, transportation costs, etc., by using the worker's location and the matching rate of each job offer, not limited to a predetermined area.

[0013] <System configuration example> Fig. 1 is a diagram showing an example of each configuration of an information processing system 1 in the disclosed technology. Hereinafter, workers and businesses may be collectively referred to as "users." In the example shown in Fig. 1, information processing devices 10A, 10B, and 10C used by each user, an information processing device 20 constituting a system that provides recruitment services, and a database 30 that manages user information, recruitment information, and usage history information of each worker, etc., are connected via a network N.

[0014] When any number of information processing devices 10A, 10B, and 10C are connected to a network N and are not distinguished from one another, they may also be referred to as information processing devices 10. When there are multiple devices, they may be referred to as the nth device (n is an integer) in order to distinguish them from one another.

[0015] The information processing device 10 is, for example, a smartphone, a computer, or a tablet terminal. By installing an application (also called a "native app") that executes the recruitment service of the disclosed technology, the information processing device 10 is able to provide the recruitment service to users. Furthermore, if the recruitment service is implemented on a web page, the information processing device 10 can also use the recruitment service using a web application (also called a "web app") on a web browser. Hereinafter, these applications are collectively referred to as "recruitment apps."

[0016] The information processing device 20 is, for example, a server, and may be composed of one or more devices. The information processing device 20 also manages a job information providing platform, provides job information, registers users, and processes job viewing, applications, etc. Hereinafter, the information processing device 20 will also be referred to as the server 20.

[0017] The database 30 has a storage unit that stores or manages user information of each worker registered with the recruitment service, recruitment information of each business, usage history information of each worker, learning model information, etc. Hereinafter, each embodiment that realizes the disclosed technology will be described.

[0018] [First embodiment] In the first embodiment, the matching rate for a specific job offer is not only used, but also calculated for a predetermined area from the number of people available and the number of applicants for each job offer included in the predetermined area. In the first embodiment, the platform performs various processes to improve user convenience, such as proposing job information content based on the area's matching rate to businesses that post job offers within the predetermined area, and changing the way workers can view job information.

[0019] For example, in the first embodiment, instead of using already-mastered data such as general prefectures, cities, towns, and villages, it is possible to identify an area for each worker based on the worker's location and set this area adaptively. In this case, by using an area according to the worker, it becomes possible to allow the worker to view and suggest appropriate job information using the matching rate of the area according to the worker.

[0020] <Example of the configuration of the user device> 2 is a block diagram showing an example of an information processing device 10 according to the first embodiment. The information processing device 10 includes one or more processing devices (processors: CPUs) 110, one or more network communication interfaces 120, a memory 130, a user interface 150, and one or more communication buses 170 for interconnecting these components.

[0021] The user interface 150 is, for example, a user interface including a display 151 and an input device (such as a keyboard and / or a mouse or any other pointing device) 152. The user interface 150 may also be a touch panel.

[0022] Memory 130 may be, for example, a high-speed random access memory such as DRAM, SRAM, DDR RAM, or other random access solid-state memory, or may be a non-volatile memory such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state memory devices. Memory 130 may also be a non-transitory computer-readable recording medium.

[0023] Another example of memory 130 may be one or more storage devices installed remotely from CPU 110. In one embodiment, memory 130 stores the following programs, modules, and data structures related to the recruitment application, or a subset thereof.

[0024] Operating system 131, for example, handles various basic system services and includes procedures for performing tasks with the hardware.

[0025] The network communication module 132 is used, for example, to connect the information processing device 10 to other computers via one or more network communication interfaces 120 and one or more communication networks, such as the Internet, other wide area networks, local area networks, metropolitan area networks, etc.

[0026] The application data 133 includes data that is processed when a user uses a job recruitment service. For example, the application data 133 includes user information and information acquired from the server 20a. Specifically, the application data 133 includes job recruitment information related to job recruitment.

[0027] The service processing module 134 executes each process in the job information providing platform provided by the server 20a. For example, the service processing module 134 has an acquisition module 135, an output module 136, and a processing module 137, which will be described later. The service processing module 134 may change the processing content depending on whether the user who has logged in to the job information providing platform is a business operator or a worker. The service processing module 134 corresponds to the above-mentioned job application.

[0028] For example, assume that information processing device 10A is a device used by a user on the business side, and information processing device 10B is a device used by a user on the worker side. In the following, the reference numeral A is attached to the reference numeral of information processing device 10A on the business side, and the reference numeral B is attached to the reference numeral of information processing device 10B on the worker side. Also, in the following, an example of dividing the processing for a job recruitment app depending on the logged-in user will be described, but it is also possible to implement separate applications for business users and applications for workers. Note that information processing device 10C is also a device used by a user on the worker side, but as it is similar to information processing device 10B, its description will be omitted.

[0029] ≪Business side≫ First, each process in the information processing device 10A on the business side will be described. The acquisition module 135A acquires a user operation on a button (an example of a UI widget) in a display screen displayed on the display 151A. For example, the acquisition module 135A acquires, via the user interface 150A, a command corresponding to a click operation on a job posting setting button for a job posting in a web page or an application screen (job posting setting screen). The job posting setting button is a button that a business uses to set recruitment conditions, etc. when posting a job posting.

[0030] The acquisition module 135A may also acquire a command corresponding to a click operation on a public setting button in a web page or an application screen (public setting screen) via the user interface 150A. The public setting button is a button used when a business operator wants to set and publish job information.

[0031] The output module 136A outputs to the server 20 the job information set by the user on the business side and a job setting request.

[0032] The processing module 137A sets the job information described above, and, as necessary, performs processes such as confirmation and / or approval of workers who have applied for the job information (also referred to as "applying workers"). For example, the processing module 137A accepts operations from the business operator, works in conjunction with the server 20a, sets condition information for individual jobs included in the job information, and, as necessary, performs confirmation and / or approval of the applying workers. Furthermore, the processing module 137 may also perform approval processing for workers matched by automatic matching as part of the automatic matching process. Automatic matching includes automatically determining the compatibility between the job information and the worker information, and automatically associating compatible workers with the job information.

[0033] The display control module 138A controls the display of one screen of the job application. For example, the display control module 138A controls the display 151A to display a job setting screen, a public setting screen, and, if necessary, a confirmation screen for the applied worker, a display screen for the work history information of the applied worker, and the like.

[0034] <Worker side> Next, each process in the worker's information processing device 10B will be explained. Based on the worker's operation, the operating system 131B downloads and installs the recruitment application program from a predetermined website or the like into its own information processing device 10B. This makes the service processing module 134B executable.

[0035] The service processing module 134B accesses the URL that provides the job information providing platform, acquires screen information related to the job service from the server 20a via the job application, and transmits information to the server 20a.

[0036] Acquisition module 135B acquires user operations on each UI component (button, input field, setting item, etc.) in the display screen displayed on display 151B. For example, acquisition module 135B acquires registration information set by a user operation of a worker on a new user registration screen, or acquires job search information set by a user operation of a worker on a job search information setting screen.

[0037] When the registration information of the new user is set based on the user's operation, the output module 136B transmits the registration information and a new registration request to the server 20a. The registration information includes, for example, the user's name, address, telephone number, etc. input by the worker. When the server 20a receives the new registration request, it performs a registration process for the new user based on the registration information. When the user's job search information is set based on the user's operation, the output module 136B transmits the job search information and a setting request to the server 20a. When the server 20a receives the setting request, it performs a process for setting the user's job search information based on the job search information.

[0038] Furthermore, when a worker performs an operation to view job information (including viewing a list of job information), the output module 136B outputs a viewing request to the server 20a. Furthermore, when a worker performs an operation to apply for a job from the job information viewing screen, the output module 136B outputs an application to the server 20a.

[0039] The processing module 137B may perform other processes related to the recruitment service. For example, as a function on the worker side, the processing module 137B may have various functions such as a notification function for favorite recruitments and a message function for communicating with businesses.

[0040] Display control module 138B controls the display of the screen of the job application. For example, display control module 138B controls the display of a new user registration screen in response to a new registration request, a job search information setting screen in response to a setting request, a job information viewing screen (including a job information list screen) in response to a viewing request, a job application screen in response to an application request, etc. on display 151B.

[0041] One or more processing units (CPUs) 110 read and execute each module from memory 130 as necessary. For example, one or more processing units (CPUs) 110 may configure a communication unit by executing network communication module 132 stored in memory 130. One or more processing units (CPUs) 110 may configure a service processing unit, an acquisition unit, an output unit, a processing unit, and a display control unit by respectively executing service processing module 134, acquisition module 135, output module 136, processing module 137, and display control module 138 stored in memory 130. Each of the processes of service processing module 134, acquisition module 135, output module 136, processing module 137, and display control module 138 may be executed by one or more processing units (CPUs) 110.

[0042] In other embodiments, service processing module 134, acquisition module 135, output module 136, processing module 137, and display control module 138 may be standalone applications stored in memory 130 of information processing device 10. Standalone applications include, but are not limited to, an acquisition application, an output application, a processing application, and a display control application. In yet other embodiments, service processing module 134, acquisition module 135, output module 136, processing module 137, and display control module 138 may be add-ons or plug-ins to another application.

[0043] Each of the above-identified elements may be stored in one or more of the storage devices described above. Each of the above-identified modules corresponds to a set of instructions for performing a function described above. The above-identified modules or programs (i.e., sets of instructions) need not be implemented as separate software programs, procedures, or modules, and thus various subsets of these modules may be combined or reconfigured in various embodiments. In some embodiments, memory 130 may store a subset of the modules and data structures described above. Additionally, memory 130 may store additional modules and data structures not described above.

[0044] As described above, the business-side application and the worker-side application may be implemented as separate applications. In this case, the worker downloads and installs the worker's recruitment app program from a predetermined website or the like onto their own information processing device 10B, and the business downloads and installs the business-side recruitment app program from a predetermined website or the like onto their own information processing device 10A, thereby enabling each of them to use the recruitment app described above.

[0045] <Example of the configuration of the server-side device> 3 is a block diagram showing an example of a server 20a according to the first embodiment. The server 20a includes one or more processing units (CPUs) 210a, one or more network communication interfaces 220a, a memory 230a, and one or more communication buses 270a for interconnecting these components.

[0046] The server 20a may optionally include a user interface 250a, which may include a display device (not shown) and a keyboard and / or mouse (or some other input device, such as a pointing device, not shown).

[0047] Memory 230a may be, for example, a high-speed random access memory such as DRAM, SRAM, DDR RAM, or other random access solid-state memory, or may be a non-volatile memory such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state memory devices. Memory 230a may also be a non-transitory computer-readable recording medium.

[0048] Another example of memory 230a may be one or more storage devices located remotely from CPU 210a. In one embodiment, memory 230a stores the following programs, modules, and data structures, or a subset thereof:

[0049] Operating system 231a, for example, handles various basic system services and includes procedures for performing tasks using hardware.

[0050] The network communication module 232a is used, for example, to connect the server 20a to other computers via one or more network communication interfaces 220a and one or more communication networks, such as the Internet, other wide area networks, local area networks, metropolitan area networks, etc.

[0051] The user information 233a includes information about users who use the job information providing platform. For example, the user information 233a includes the user's name, address, phone number, available working hours, evaluation, etc., associated with each user ID. The user information 233a will be described later with reference to FIG. 5.

[0052] The job information 234a includes one or more job information items registered in the job information providing platform (or job service). For example, the job information 234a includes information such as the job offer date, working hours or days, business operator, work location, hourly wage, and job content, all associated with a job offer ID. The job information 234a will be described later with reference to FIG. 6.

[0053] The usage history information 235a includes a job offer ID, location, work dates, work hours, salary, etc., associated with a user ID. The usage history information 235a may also include an evaluation of the work from the business operator, etc. The usage history information 235a will be described later with reference to FIG. 7.

[0054] The learning model information 236a includes learning model information for estimating the matching rate of an area, which is trained using learning data including at least the matching rate and statistical data for each past job offer within the area identified based on the predetermined location information. For example, the learning data includes at least the matching rate of the number of people who completed work relative to the number of people recruited for each past job offer and statistical data related to the work. For example, the learning model information 236a includes the structure of a neural network for estimating the above-mentioned matching rate, hyperparameters, etc. At least one of the user information 233a, job offer information 234a, usage history information 235a, and learning model information 236a may be stored in the database 30.

[0055] The service control module 237a provides a recruitment service that publishes recruitment jobs to workers, and manages processes related to recruitment setting, publication, matching, etc. on the recruitment information providing platform. For example, the service control module 237a has an acquisition module 238a, a learning module 239a, an estimation module 240a, and an output module 241a for processing related to recruitment setting, publication, matching, etc. Below, the process for calculating the matching rate for each area will be mainly explained. In the first embodiment, a learning model that estimates the matching rate is used to calculate the matching rate for an area.

[0056] <<Estimating the matching rate of an area>> The acquisition module 238a acquires location information of a predetermined location. For example, the acquisition module 238a acquires locations such as each worker's address, a location where the worker stays a predetermined number of times or for a predetermined period of time or more, a station used a predetermined number of times or more, a workplace for a job offer that has been matched a predetermined number of times or more, or the worker's current location. The acquisition module 238a may acquire the above-mentioned location information by analyzing data from past job applications, or may acquire location information set for the worker if such information is available, or may acquire location information from a satellite positioning system.

[0057] The learning module 239a inputs predetermined statistical data into a learning model that estimates the matching rate for an area (predetermined range) specified based on location information. The learning model is a learning model trained using learning data that includes at least the matching rate of the number of people who have completed work to the number of people recruited (also called the "work completion matching rate") for each past job posting in the specified area, and statistical data for work days. The area may be set not based on traditional divisions such as cities, towns, and villages, but on a map using a known regional mesh method (a map in which an area on a map is divided into a grid for statistical purposes) or a map using Hex (a map using a coordinate system with a hexagonal grid), within a predetermined distance from a predetermined location.

[0058] For example, the learning data includes data on each job vacancy as past information for each area, and data on work (statistical data). (1) Example of statistical data -Date (month and day) of each day (working day), working hours, day of the week, whether it is a public holiday or not, weather (actual weather, weather forecast data) (2) Example of data related to job offers Number of cancellations (number of cancellations from the work day until the designated day) - Matching rate of the number of people who completed work compared to the number of job openings By having the learning model learn the above learning data, it becomes possible to calculate the number of cancellations and matching rate on a given work day in a specified area by inputting statistical data into the learning model.

[0059] The learning module 239a may acquire regional weather forecast data, including location information for a predetermined location, via an API from a service that publishes weather forecast data as weather forecast data included in the predetermined statistical data to be input into the learning model. An example of a service that publishes weather forecast data is the weather forecast website of the Japan Meteorological Agency. The day for which the matching rate of an area is to be estimated may be any day in the future beyond the present time.

[0060] The estimation module 240a uses data output from the learning model to estimate the matching rate for a job offer in an area on a given day. For example, the estimation module 240a may estimate the matching rate for a given work day by inputting the matching rate for each area output from the learning model as a parameter into a predetermined calculation formula that calculates the matching rate for a given work day. The predetermined calculation formula may include a calculation formula that uses as parameters an estimated number of people who have completed work (number of people recruited x estimated matching rate), an estimated increase in the number of people recruited from the current time to the given work day, an estimated increase in the number of applicants, etc.

[0061] The above process makes it possible to calculate the matching rate for a specified area, and by specifying a future work date, it becomes possible to calculate the matching rate for each area on that day. As a result, it becomes possible to perform various processes that improve user convenience as a job information providing platform, such as proposing job information content based on the area's matching rate to businesses that post job openings within a specified area, and changing the way workers view job information.

[0062] In addition to the above-described processing, the acquisition module 238a may also acquire location information indicating the location of the worker from a processing device used by the worker (e.g., the information processing device 10B). For example, the location information indicating the location of the worker may be GPS location information acquired by the worker's processing device, or may be location information of a location specified by the worker.

[0063] The above processing makes it possible to adaptively set a specified area that includes the worker's current location and the location where the worker wishes to work, making it possible to appropriately estimate the matching rate of the area while meeting the worker's needs for work location.

[0064] In addition to the above-described processing, the learning module 239a may execute the learning model to learn learning data including statistical data including at least one of the data on the date, day of the week, holiday, and weather of past work days. For example, the learning module 239a may treat past days as work days, and use the data on the date, day of the week, whether it is a holiday, and weather (weather forecast and actual weather) of each day as learning data.

[0065] The above processing makes it possible to improve the accuracy of the matching rate for a specified area. For example, the matching rate can be improved by learning past data such as whether past days were weekends, holidays, or sunny weather. The learning model can calculate the matching rate for similar statistical data from past statistical data. As a specific example, it becomes possible to calculate the matching rate for a desired workday by taking into account past data such as a decrease in matching rate on rainy days and an increase in matching rate on holidays.

[0066] In addition to any of the above processes, the learning module 239a may train the learning model using learning data including at least the number of cancellations on work days. For example, the learning module 239a may use the cancellation rate for each past day as learning data to learn the matching rate. For example, it is possible to learn from past data that the cancellation rate increases when rain is forecast.

[0067] By taking the cancellation rate of a predetermined area into consideration through the above processing, it becomes possible to improve the accuracy of estimating the matching rate of a predetermined area.

[0068] In addition to any of the above processes, the estimation module 240a may acquire estimated values ​​for the increase in the number of employees recruited and the increase in the number of applicants until a future work day, estimated by a learning model based on current statistical data, the number of employees recruited, and the number of applicants. For example, the learning model can estimate the increase in the number of employees recruited and the increase in the number of applicants on a work day in the same area from past data. The learning model can also estimate the increase in the number of employees recruited and the increase in the number of applicants when it is sunny, cloudy, or rainy, based on past weather data. The number of applicants may also be the number of people who actually completed work (the number of people who completed work).

[0069] For example, the estimation module 240a inputs current statistical data, the number of positions available, and the number of applicants in a specified area into a learning model, and obtains from the learning model estimated values ​​for the increase in the number of positions available and the increase in the number of applicants until a future working day.

[0070] The estimation module 240a may estimate a match rate for future workdays using the current number of job openings, the number of applicants, and the estimated increase in the number of job openings and the increase in the number of applicants. For example, the estimation module 240a may use at least one function that estimates a match rate for future workdays, with the current number of job openings, the number of applicants, and the estimated increase in the number of job openings and the increase in the number of applicants as parameters.

[0071] Specifically, the estimation module 240a may estimate the matching rate for future workdays by inputting the current number of people recruited, the number of applicants, and each estimated value of the increase in the number of people recruited and the increase in the number of applicants into one or more of the above-mentioned functions.In addition to functions, the estimation module 240a may also use a machine learning model that has learned the relationship between each estimated value of the current number of people recruited, the number of applicants, the increase in the number of people recruited, and the increase in the number of applicants and the matching rate for future workdays, as a method of estimating the matching rate for future workdays.

[0072] By performing the above process, it is possible to improve the accuracy of estimating the matching rate in a specified area by taking into account the number of positions to be filled and the increase in the number of applicants up to future work dates in the specified area.

[0073] In addition to any of the above processes, the estimation module 240a may also include estimating a matching rate for future workdays based on the number of cancellations for those future workdays. For example, the estimation module 240a estimates the number of people who will cancel on that day by multiplying the number of applicants for that day by the past cancellation rate for that day corresponding to the future workday. In this case, the estimation module 240a estimates a matching rate that takes into account the number of people who will cancel on that day.

[0074] By performing the above process, it is possible to improve the accuracy of estimating the matching rate for a specified area by taking into account the cancellation rate on the working day in the specified area.

[0075] The estimation module 240a may estimate the increase in the number of available workers from the present to a future workday, and may estimate the matching rate for the future workday based on the increase in the number of workers. For example, the estimation module 240a estimates the increase in the number of new workers (new workers) using the recruitment app on a daily basis. For example, if five new workers are added per day, and there are three days until the workday, it estimates that the number of new workers will increase by 15 (5 x 3) from the present to the workday. The estimation module 240a may estimate the matching rate by taking this increase in the number of new workers into account when calculating the number of applicants.

[0076] The increase in the number of available workers may be calculated for each area, may be calculated using the number of new workers in the recruitment app on the same day in past data, or may be calculated based on the average increase in the number of new workers per day.

[0077] By taking into account the increase in the number of new workers in the job application, the above processing makes it possible to improve the accuracy of estimating the matching rate in a specified area.

[0078] In addition to any of the above processes, the learning module 239a may execute the learning model to learn learning data including category information of past job offers. For example, the learning module 239a uses learning data including information regarding understanding the work of job offers as category information to train the learning model that estimates the matching rate.

[0079] The learning module 239a may include causing the learning model to learn category information including the type and / or content of the job posting. For example, the learning module 239a may cause the learning model to learn the job content included in the job posting information shown in FIG. 6, which will be described later, by including it in the learning data.

[0080] In this case, the estimation module 240a may estimate a matching rate for each job category in a predetermined area. For example, the estimation module 240a estimates a matching rate not only for a predetermined area but also for each job category (such as job content). Furthermore, the job category may use information that can identify the job, so that a specific job can be identified.

[0081] By taking the above process into consideration, it is possible to improve the accuracy of estimating the matching rate for a given area. As a specific example, since the matching rates for delivery work and cashiering work are different, estimating the matching rate according to the job category allows for a more accurate estimation of the matching rate.

[0082] If applications or hiring for the number of positions to be recruited have not been completed, the output module 241a publishes the job information based on the publication time or publication period. For example, the output module 241a may publish job information for which the publication time has arrived to workers on a job information providing platform. Furthermore, if location information indicating the location of a worker is acquired, the output module 241a may publish to the worker job information whose workplace is within a predetermined area based on the location information. For example, the output module 241a may control the display of a job listing screen to the worker who made a viewing request.

[0083] The output module 241a may output to a predetermined device the matching rate for a predetermined area obtained by the above-mentioned processing, the estimated values ​​of the increase in the number of people recruited and the increase in the number of applicants until a future work day, the matching rate for a predetermined work day in a predetermined area, etc. For example, the output module 241a may output data such as the matching rate to the information processing device 10A of the business operator if the business operator uses it as a reference when setting job information, or to the information processing device 10B of the worker if the worker uses it as a reference when applying.

[0084] Through the above processing, the matching rate for a specified area can be used to propose to businesses the number of people to be recruited in each area and working conditions such as salary, and can also be used to propose to workers the timing of their application.

[0085] <Example 1> Next, we will explain how to estimate the matching rate for a given workday in a given area using a specific example. For example, the past data used as learning data includes the following information for each day: Date (month and day of the year), day of the week, public holidays, weather (actual weather and weather forecast data), number of cancellations (e.g., number of cancellations every day from 7 days before to the day of work), work completion matching rate (ratio of number of people who completed work to number of applicants for the job) The area may be divided using, for example, a mesh method or a hexadecimal method. The above-mentioned past data may be obtained for each area. Predetermined areas may be set based on location information acquired from the worker's terminal.

[0086] The learning module 239a uses the above-mentioned learning data to perform machine learning to estimate the matching rate in a predetermined area, and generates a trained learning model.

[0087] The learning module 239a inputs the current date, the date of the work day, and the weather on the work day into the learning model as statistical data. For example, it is assumed that the learning module 239a inputs the following data: Current date Example: Friday, November 8, 2024 -Date of work day Example: Monday, November 11, 2024 Weather forecast for the specified area on the working day. Example: Precipitation forecast for each time period (1:00 AM 0 mm, 2:00 AM 5 mm, ..., 24:00 AM 10 mm) Number of cancellations in a given area (number of cancellations per day from 7 days before to the day of work) Work completion matching rate (percentage of completed work)

[0088] Assume that the following data is output from the learning model: Estimated work completion matching rate 1 Example: 85% (November 11th) Estimated number of people who have completed work e.g. 85 people (estimated number of applicants 100 x work completion matching rate 0.85) Estimated daily increase in the number of applicants. Example: (Friday, November 8th: 4 people, Saturday, November 9th: 6 people, Sunday, November 10th: 8 people, Monday, November 11th: 10 people) Estimated increase in applicants per day. Example: (Friday, November 8th: 6 people, Saturday, November 9th: 10 people, Sunday, November 10th: 16 people, Monday, November 11th: -4 people) November 11th will be based on the number of cancellations.

[0089] An example of data showing the current matching situation (Friday, November 8, 2024) is as follows. Number of people recruited Example: 90 people Number of applicants Example: 60 people

[0090] The estimation module 240a calculates the matching rate for a given area on a work day based on the data output by the learning model and the data indicating the current matching situation, for example, using the following formula: Estimated number of people recruited on the day: 90 + 4 + 6 + 8 + 10 = 118 people Estimated number of people who completed work on the day: 60 + 6 + 10 + 16 - 4 = 88 people Estimated work completion matching rate: 2:88 / 118 = 74.6% Number of unfilled positions compared to the number of applicants: 118-88=30

[0091] The estimation module 240a may perform the correction process using, for example, an increase in the number of new workers who are potential new workers in a predetermined area. Estimated number of new applicants (newly added applicants): +10 The estimate of new worker applicants may be determined by either: Average daily increase in new workers in a given area: up to 10 The ratio of the number of users of other services linked to the job posting platform in a given area to the number of users available for work Estimated number of people who will complete work on the day: e.g., 88 + 10 (estimated number of new applicants) = 98 people Estimated workday matching rate for a given area3: e.g., 98 / 118 = 83% In the above example, the "estimated number of newly applied workers" was added as the "estimated number of people who will complete work on the day," but it is also possible to multiply the estimated number of newly applied workers by the probability of completing work and add the result.

[0092] According to the above example, the final matching rate for work days in a specified area is estimated value 3, which is 83%, but it is not limited to this and may be estimated value 1 or estimated value 2. Estimated values ​​1 to 3 have higher estimation accuracy in the order of estimated value 1, estimated value 2, and estimated value 3, as the amount of data to be considered increases. Note that the above example of calculating estimated values ​​is merely an example and is not limited to this example.

[0093] <Example 2> Next, in comparison with Specific Example 1, a case where an estimated value of the matching rate for a specific category (or a specific job offer) is to be described. In addition to the learning data of Specific Example 1, the learning data includes the type of work and / or the work content of past job offers in a specified area. The learning model learns the learning data including the type of work and / or the work content of past job offers, and estimates the matching rate for a specific job offer on a future working day. In the example shown below, a case where a specific job offer is used as the specific category is described.

[0094] The learning module 239a uses the above-mentioned learning data to perform machine learning to estimate the matching rate in a predetermined area, and generates a trained learning model.

[0095] The learning module 239a inputs the current date, the date of the working day, and the weather on the working day into the learning model in addition to the statistical data in the first specific example. Number of people available for a specific job: e.g. 5 people

[0096] Assume that the following data is output from the learning model: Estimated work completion matching rate in a given area: e.g., 85% Estimated matching rate for job completion for a specific job in a given area4: e.g., 80% Estimate of the number of people who have completed work for a particular job in a given area: e.g., 4 people

[0097] An example of data showing the current matching situation (Friday, November 8, 2024) is as follows. Number of people available for a specific job in a given area: e.g., 5 people Number of applicants for a specific job in a given area: e.g., 3 people

[0098] Next, the estimation module 240a corrects the estimated value of the final number of people who completed work based on the relationship between the number of applicants in the past and the number of people who finally completed work. FIG. 4 is a diagram showing an example of the correlation between the number of applicants three days before the application and the number of people who finally completed work in the first embodiment. The correlation shown in FIG. 4 can be used to calculate an average value from data on the number of people who completed work for each past day and the number of applicants three days before. In specific example 2, the number of applicants is three on November 8, three days before the work day of November 11. In the example shown in FIG. 4, when the number of applicants is three, the average number of people who finally completed work is 4.5.

[0099] The estimation module 240a calculates the final matching rate for a specific job offer in a predetermined area, for example, using the following formula: Estimated matching rate for a specific job on the day of work5: e.g., 4.5 / 5 = 90%

[0100] The above example of estimating the matching rate for a specific job offer is merely an example, and is not limited to the above example. For example, a learning model may be generated to estimate the matching rate for work days for a specific job offer.

[0101] In the above specific examples 1 and 2, we have explained examples of calculating the matching rate for a work day in a specified area using specific numerical values. However, in the first embodiment, in addition to the matching rate, it is also possible to obtain useful data for the job providing platform, such as the number of people who applied for a job on a work day but did not apply (the number of unfilled positions) being 30.

[0102] It should be noted that each of the elements identified above may be stored in one or more of the storage devices described above. Each of the modules identified above corresponds to a set of instructions for performing a function described above. The modules or programs (i.e., sets of instructions) identified above need not be implemented as separate software programs, procedures, or modules, and thus various subsets of these modules may be combined or reconfigured in various embodiments. In some embodiments, memory 230a may store a subset of the modules and data structures identified above. Additionally, memory 230a may store additional modules and data structures not described above.

[0103] Note that one or more processing units (CPUs) 210 read and execute each module from memory 230a as necessary. For example, one or more processing units (CPUs) 210a may configure a communication unit by executing network communication module 232a stored in memory 230a. Also, one or more processing units (CPUs) 210a may configure a service control unit, an acquisition unit, a learning unit, an estimation unit, and an output unit by respectively executing service control module 237a, acquisition module 238a, learning module 239a, estimation module 240a, and output module 241a stored in memory 230a. Also, the processing of each of service control module 237a, acquisition module 238a, learning module 239a, estimation module 240a, and output module 241a may be executed by one or more processing units (CPUs) 210a.

[0104] While Figure 3 illustrates "servers," it is intended as an illustration of various features that may be present in a set of servers, rather than as a structural overview of the embodiments described herein. In practice, as will be recognized by those skilled in the art, items shown separately may be combined and certain items may be configured separately. For example, items shown separately in Figure 3 may be implemented on a single server, and a single item may be implemented by one or more servers.

[0105] The database 30 may have a configuration similar to the hardware configuration shown in Fig. 3. Note that the user information 233a, job information 234a, usage history information 235a, and learning model information 236a shown in Fig. 3 may be stored in a storage unit of the database 30.

[0106] <Example of data structure> FIG. 5 is a diagram showing an example of user information 233a according to the first embodiment. The user information 233a manages information about each member user created by a user (e.g., worker) who uses the recruitment service. The "user ID" includes user identification information (user ID: Identifier) ​​that allows the server 20a to uniquely identify the user. The user ID is associated with "user information."

[0107] "User information" includes the user's personal information such as "name," "address," "telephone number," "available working hours," and "rating." "Available working hours" includes time information set based on the usage history information 235 described below, and may also include available working hours information set by the worker.

[0108] The "evaluation" includes the value of the user's work attitude, etc., evaluated by the business operator after the user has started work. The "evaluation" may be an average value or a cumulative value. The user ID may also be included as part of the user information. The user information may also include an email address, password, work location information, work category information, desired salary information, etc.

[0109] FIG. 6 is a diagram showing an example of job information 234a according to the first embodiment. The "job ID" includes identification information for the job information. The job information includes information such as "job offer date," "working hours," "business operator," "work location," "salary," "transportation expenses," and "job content" associated with the job ID. In the example shown in FIG. 6, "salary" is used, but "hourly wage" may also be used. For example, the "work location" may specify a station, and may be specified using n meters from the station or n meters from a specified location.

[0110] "Job Offer Date" includes the date (or a specified period) when the business needs a worker. "Working Hours" includes the start and end times of the worker's work on the job offer date. "Business" includes the name of the business that sets the job offer information and is seeking employment. "Work Location" includes at least one of the store name, location, place name, facility name, etc. where the worker will work. "Salary" includes the salary for the job offer. "Transportation Expenses" includes the salary paid to the worker. "Job Description" includes information indicating the job description (job category) set by the business. Job information 234a may also include the type of job offered (information identified as a higher-level concept than the job description).

[0111] FIG. 7 is a diagram showing an example of usage history information 235a according to the first embodiment. The "user ID" in the usage history information includes identification information of the user who uses the job recruitment service. The usage history information includes information such as "job recruitment ID," "location," "working date," "working hours," and "salary" associated with this user ID. Note that although "salary" is used in the example shown in FIG. 7, "hourly wage" may also be used.

[0112] The "job offer ID" includes identification information that identifies the first job offer that was accepted. The "location" includes the worker's work location. The "working date" includes the date the worker worked. The "working hours" includes the worker's working hours on the job offer date. The "hourly wage" includes the hourly wage for the first job offer. The usage history information may also include information about the "business operator" and evaluation information about the work. The usage history information may also include the number of times the worker worked within a specified period, the total working hours, etc.

[0113] Although not shown, the learning model information 236a includes a model that estimates the matching rate for a specific day in a specific area using each piece of data included in the learning data, and the learned parameters of the model. The learning model information 236a may temporarily include data during or after learning.

[0114] <Operation description> Next, the operation of the information processing system 1 according to the first embodiment will be described. Fig. 8 is a flowchart showing an example of processing related to estimating a matching rate in a predetermined area according to the first embodiment. In the example shown in Fig. 8, the server 20a is a device that implements a job information providing platform and provides job services, and the processing executed by this server 20a is shown.

[0115] In step S102, the acquisition module 238a acquires location information of a predetermined location. For example, the predetermined location may include the address of each worker, a location where the worker stays for a predetermined amount of time or more, a station used a predetermined number of times or more, a workplace of a job offer with a predetermined number of matches or more, or the worker's current location. It is sufficient that the location information to be used is set in advance.

[0116] In step S104, the learning module 239a inputs predetermined statistical data into a learning model that estimates a matching rate for an area (predetermined range) identified based on the location information. The learning model uses the previously trained learning model described above. For example, the area range may be set using a map partitioned using a known regional mesh method or hexadecimal notation. For example, the predetermined statistical data includes at least one of the date (month and day) of each day (working day), day of the week, whether it is a public holiday, and weather (actual weather, weather forecast data).

[0117] In step S106, the estimation module 240a estimates the matching rate for a predetermined day using the matching rate for the area (predetermined range) output from the learning model. For example, the estimation module 240a may use the matching rate for the area output from the learning model as the final matching rate, or may input this matching rate as a parameter into a predetermined calculation formula for calculating the matching rate for a predetermined workday. As an example of step S106, the processing of step S162 or step S164 may be performed. In step S162, the estimation module 240a may obtain estimated values ​​of the increase in the number of recruits and the increase in the number of applicants until a future workday, which are estimated (output) by the learning model based on the current statistical data, the number of recruits, and the number of applicants. In this case, the estimation module 240a may estimate the matching rate for a future workday using the estimated values ​​of the current number of recruits, the number of applicants, the increase in the number of recruits, and the increase in the number of applicants. In step S164, the estimation module 240a may execute learning data including category information of past job offers to the learning model. In this case, the estimation module 240a may estimate a matching rate for each job category.

[0118] Here, FIG. 9 is a diagram showing an example of the display of the matching rate calculated in the first embodiment. The example shown in FIG. 9 shows an example of a screen on which a business sets job information. The example shown in FIG. 9 displays the number of applicants relative to the number of positions available in the current job information. For example, for a job opening from 6:00 PM on July 25th, the number is 2 / 5 (number of applicants / number of positions available), which indicates that the number of positions available has not yet been met. At this time, the matching rate for a specified area including this workplace, calculated in the first embodiment, may be displayed. In the example shown in FIG. 9, "Estimated matching rate 85% at current hourly wage" is displayed.

[0119] 8, in step S108, the estimation module 240a may estimate the matching rate in a predetermined area using data that may be output from the learning model. For example, the estimation module 240a may calculate the estimated value 2 or the estimated value 3 described in the specific example 1.

[0120] In step S110, the estimation module 240a may estimate the matching rate of a specific job offer in a predetermined area using data that may be output from a learning model that has learned learning data including the job offer category. For example, the estimation module 240a may calculate the estimated value 4 or 5 described in specific example 2.

[0121] Through the above process, it is possible to calculate the matching rate for a specified area not only using the matching rate for a specific job offer, but also from the number of job openings and applicants for each job offer within the specified area, etc. This makes it possible to propose job information content based on the area's matching rate to businesses that post job offers within the specified area, change the way workers view job information, and perform various other processes to improve user convenience as a job information providing platform.

[0122] Furthermore, in the first embodiment, instead of using already-mastered data such as general prefectures, cities, towns, and villages, it is possible to identify an area for each worker based on the location of the worker and adaptively set the area. In this case, by using an area according to the worker, it becomes possible to allow the worker to view or suggest appropriate job information using the matching rate of the area according to the worker.

[0123] [Second embodiment] In the past, job information providing platforms have not given much consideration to the use of worker location information, and there has been room for improvement in providing services using worker location information. Therefore, in the second embodiment, in order to solve this problem, the job information providing platform performs various processes to improve user convenience, such as recommendations and dynamic pricing based on the matching rate between the worker's location and each job offer.

[0124] <Example of the configuration of the user device> The information processing device 10 according to the second embodiment has the same configuration as that described in the first embodiment. If there are any processes unique to the second embodiment, they will be explained in due course.

[0125] <Example of the configuration of the server-side device> 10 is a block diagram showing an example of a server 20b according to the second embodiment. Similar to the first embodiment, the server 20b includes one or more processing units (CPUs) 210b, one or more network communication interfaces 220b, a memory 230b, and one or more communication buses 270b for interconnecting these components. The following mainly describes processing that differs from the first embodiment.

[0126] The acquisition module 238b acquires location information of the worker's location. For example, the acquisition module 238b acquires information indicating each worker's current location (GPS location information of the worker's terminal) when each worker accesses the job service or requests to view a job. The service control module 237b may allow the worker to narrow down the job listings within an area based on the worker's location information. For example, the service control module 237b may narrow down the job listings to within a radius of 20 km and / or within a 30-minute commute time from the worker's location information (see, for example, FIG. 12).

[0127] The learning module 239b has a learning model that estimates the matching rate for each job, trained using learning data including at least the matching rate for each past job offer and job information. For example, the learning module 239b inputs the job information, the number of people being recruited, and the number of applicants for each currently recruiting job into the learning model that estimates the matching rate for each job offer, trained using learning data including at least the matching rate of the number of people who have worked to the number of people recruited for each past job offer and job information. As a specific example, the learning module 239b inputs the job information for each job offer, the total number of people being recruited for each job offer, and the total number of applicants into the learning model. The learning method in the second embodiment is basically the same as that in the first embodiment, although the learning data may differ.

[0128] The estimation module 240b uses data output from the learning model to estimate the matching rate for each currently recruited job on a specific date. The specific date may be any specific day, including a working day. For example, the estimation module 240b may use the matching rate output by the learning model for each job posting output from the learning model, or may use a corrected matching rate as in the first embodiment.

[0129] The setting module 242b sets each job offer to be recommended to a worker using the matching rate of each job offer for a predetermined date estimated by the estimation module 240b and the distance between the worker's location based on the worker's location information and the work location of each job offer currently being recruited. For example, the setting module 242b preferentially recommends to the worker a job offer whose work location is close to the worker's location.

[0130] In this case, the output module 241b may preferentially disclose the job information recommended by the setting module 242b to the worker. For example, the output module 241b may control so that a job listing screen on which the recommended job information is displayed at the top is displayed to the worker who made the viewing request (see, for example, FIG. 13).

[0131] By calculating the matching rate for each job offer through the above process, job offers can be recommended based on the worker's location based on the matching rate for each job offer. Since job offers are recommended to workers taking into account their location and matching rate, it becomes easier for them to match with a job offer.

[0132] The learning module 239b may train the learning model with learning data including job information for jobs that the worker has previously applied for, and output a matching rate for each currently recruiting job that is similar to the job information for the job that the worker has previously applied for.

[0133] The job information learned by the learning model includes at least one of the following: type of work, work content, working hours, work location, and salary. For example, the learning module 239b can learn application data such as the work content, work location, and salary of jobs that a worker has previously applied for into the learning model, thereby understanding the work content, work location, and salary (such as a predetermined amount or more) that the worker prefers.

[0134] In this case, the setting module 242b may set each job offer to be recommended to the worker based on the matching rate of each job offer on a specified day estimated by the estimation module 240b and trend data (job content, work location, salary, etc.) based on the worker's past data.

[0135] Through the above process, by using the worker's past application data as learning data, it becomes possible to recommend jobs based on the worker's application tendencies.

[0136] In addition to any of the above processes, the learning module 239b may also include inputting the job information, number of applicants, and number of applicants for each job currently being recruited in the area into a learning model trained using learning data for each past job in the area (predetermined range) specified based on the worker's location information. The learning method for the predetermined area is the same as in the first embodiment.

[0137] For example, the learning module 239b can reduce the amount of learning data and perform learning efficiently by identifying each job vacancy within a predetermined area based on the worker's location.

[0138] The above processing allows the server's processing resources to be used efficiently, which also contributes to faster processing.

[0139] The proposal module 243b proposes to the business operator that created the first job offer that an incentive be given to a worker for a first job offer whose matching rate on a predetermined day is equal to or lower than a predetermined value. For example, the proposal module 243b proposes to the business operator of the first job offer that a special benefit be given as an incentive to a worker for a first job offer whose matching rate on a working day is equal to or lower than 50% or whose recommendation ranking is 5th or lower. The incentive may be funded by the business operator of the job offer or the operator of the job information providing platform, etc.

[0140] Incentives may also vary depending on the number of workers (potential workers) who live near the workplace (residents, frequent users, currently present). For example, if there are many potential workers, there is a possibility of matching without any effort, but if there are few potential workers, incentives can be actively provided to encourage workers to apply.

[0141] Through the above process, it is possible to make proposals to businesses to improve the matching rate, which may result in an increase in applications from workers, helping to alleviate labor shortages at businesses.

[0142] In addition to any of the above processes, the suggestion module 243b may also include proposing to increase the salary information of the first job offer. For example, the suggestion module 243b may propose increasing the salary of the first job offer by a predetermined amount or by a predetermined percentage (see, for example, FIG. 14). Note that the incentive may be a perk for the worker other than a salary increase, such as an increase in transportation expenses, the provision of a predetermined coupon, or an increase in points.

[0143] The above process makes it possible to make specific proposals as incentives that can contribute to improving the matching rate, making dynamic pricing possible, for example.

[0144] In addition to any of the above processes, the suggestion module 243b may include proposing to increase the salary information of the first job offer based on the salary information of a job offer similar to the first job offer. For example, the suggestion module 243b may suggest a predetermined percentage increase, a predetermined amount increase, or the like based on the salary of another job offer that has similar work content to the first job offer and / or a matching rate of a predetermined value or higher. As a specific example, if the salary of a job offer similar to the first job offer and that has a matching rate of 90% or higher is higher, the suggestion module 243b may suggest to the business operator of the first job offer that the salary be increased to the same level as the salary of this job offer.

[0145] The above process makes it possible to improve the appropriateness of incentive increases based on objective data.

[0146] In addition to any of the processes described above, the learning module 239b may input the job information of the first job offer, including the increased salary information, into the learning model. For example, when a salary increase is proposed by the proposal module 243b and approved by the business, the learning module 239b retrains the learning model using the job information of the first job offer, including the increased salary information.

[0147] In this case, the estimation module 240b may obtain the matching rate of the first job offer based on the increased salary information from the learning model, and use this matching rate to estimate the increase in the matching rate for the first job offer on a given day. For example, the estimation module 240b may estimate the increase in the matching rate for the first job offer on a work day from the matching rates before and after the salary increase output from the learning model. As a specific example, if the matching rate before the salary increase is 85% and the matching rate after the salary increase is 92%, the increase in the matching rate is 7%. Note that estimating the increase in the matching rate is synonymous with estimating the matching rate after the increase.

[0148] The output module 241b may output the increase in the matching rate calculated by the above-described process to a predetermined device. For example, the output module 241b may output data on the increase in the matching rate due to the provision of an incentive to the information processing device 10A of the business operator. When making a proposal on a screen showing the application status of the business operator's job vacancies, the output module 241b may display a screen shown in FIG. 15 (described later), and when making a proposal on a setting screen for setting job vacancies, the output module 241b may display a screen shown in FIG. 16 (described later).

[0149] The above process makes it possible to determine the change in the matching rate when an incentive (especially a salary) is granted. Furthermore, by presenting the increase in the matching rate as a numerical value to the business operator, the business operator can realize the effect of granting the incentive. The estimation module 240b may estimate the increase in the matching rate using the matching rate of the first job offer based on the salary information to be increased, from a learning model that has been retrained in advance, without obtaining approval from the business operator. In this case, the output module 241b can notify the business operator of how much the matching rate will increase for this salary before approval.

[0150] Example 3 Next, a method for setting job offers to be recommended in the second embodiment will be described using a specific example. For example, job information for each job offer is included as training data. The training model can be generated by, for example, having the training model that estimates the matching rate for a specific job offer, as described in specific example 2, train the job information for each job offer.

[0151] For example, as of November 8th, the learning module 239b calculates the work completion matching rate for the workday of November 11th. For example, the learning module 239b identifies job openings within the area from the worker's location information and generates a job listing list including the identified job openings. For each job opening in the job listing list, the learning module 239b takes as input data the number of applicants / recruited people at the current time (November 11th) and the distance from the specific worker's location information to the workplace. A specific worker is a worker whose location information is acquired, and includes workers who make job listing viewing requests or access job listing services. The following is an example of input data to be input into the learning model. Input data Current number of applicants / recruitment for each job (A, B, C), distance (distance between specific worker and job location) Job A: 2 / 3, distance 1km ·Recruitment B: 3 / 4, distance 2km ·Recruitment C:0 / 2, distance 3km

[0152] Assume that the following data (work completion matching rate) is output from the learning model. Note that the output data may include the work completion matching rate for a specific job offer, as in Example 2. Note that the work completion matching rate in Example 3 may be an application rate that uses the number of applicants on a work day without taking cancellations into account. Work completion matching rate Job A: 95% ·Recruitment B:90% ·Recruitment C: 60% The parameter Z in the calculation formula described below means this work completion matching rate.

[0153] The setting module 242b assigns a first weight to the work location of the job for which the specific worker applies, based on the specific worker's past application data. The first weight is a weight related to the distance between the specific worker's location and the work location of the job for which the specific worker applied, using the specific worker's past application data. The first weight may be a preset value or a value determined by a learning model. The first weight may also be determined for each predetermined distance. Examples of first weight values ​​are shown below. First Weight ·Distance 0~3km:2 ·Distance 3~5km:1 ·Distance 5~20km: 0.5 Distance 20km or more: 0.1

[0154] Next, the setting module 242b calculates a second weight for the work completion matching rate (which may be the application rate) using the following formula: The second weight is a weight for the matching rate for the specific job offer. Second weight: 1.5-Z Job A: 0.55 (= 1.5 - 0.95) ·Recruitment B:0.6(=1.5-0.9) ·Recruitment C:0.9(=1.5-0.6)

[0155] Next, the setting module 242b acquires a third weight value related to the affinity between the specific worker and each job offer, which is output from the learning model. The third weight is a weight related to the affinity between each of the job offers A to C and the specific worker, using the past application data of the specific worker. Third Weight Job A: 1.0 ·Recruitment B:0.8 ·Recruitment C:1.6

[0156] The setting module 242b calculates the priority of the recommendation for each job offer by the following calculation using the first to third weights. Recommendation priority for each job (total weight) = 1st weight + 2nd weight + 3rd weight Job A: 3.55 (= 2 + 0.55 + 1.0) ·Recruitment B:3.4(=2+0.6+0.8) ·Recruitment C:3.6(=1+0.9+1.6)

[0157] The setting module 242b sets the priority of recommendations for each of the job offers A to C in the following order: 1.Recruitment C(3.6) 2. Job A (3.55) 3.Recruitment B(3.4)

[0158] For example, the output module 241b may publish job information to workers in the order of priority set by the setting module 242b. According to the above example, the output module 241b configures the job listing screen so that job C, job A, and job B are displayed on the screen in this order.

[0159] The job recommendation method in specific example 3 is merely an example and is not limited to the above example. For example, at least one of the first to third weights may be used, and the calculation method is not particularly important as long as job offers that are close to a specific worker and have high affinity are given higher priority. Regarding the screen display of recommended job offers, it is sufficient that the recommended job offers are displayed in an emphasized manner so as to be distinguished from other job offers.

[0160] <Example of data structure> Various data in the second embodiment are the same as the corresponding various data in the first embodiment. Note that in the second embodiment, the data output from the learning model and the final output data are different, but they may be stored in the memory 230b.

[0161] <Operation description> Next, the operation of the information processing system 1 according to the second embodiment will be described. Fig. 11 is a flowchart showing an example of processing related to job recommendations according to the second embodiment. In the example shown in Fig. 11, the server 20b is a device that implements a job information providing platform and provides a job service according to the second embodiment, and the processing executed by this server 20b is shown.

[0162] In step S202, the acquisition module 238b acquires location information indicating the location of the worker. For example, the location information may be location information from a GPS installed in the information processing device 10B used by the worker. For example, the service control module 237b may narrow down the search to within a radius of less than 20 km from the worker's location information and / or within a commuting time of 30 minutes (see, for example, FIG. 12).

[0163] Fig. 12 is a diagram showing an example of a job offer filtering screen on the worker side according to the second embodiment. The screen shown in Fig. 12 is a screen for filtering the displayed job offers when a worker makes a request to view job offers. In the example shown in Fig. 12, the filtering items include start time, working hours, benefits, whether or not transportation expenses are included, distance, and commuting time.

[0164] For "Start of work hours," the time period when work begins for the job posting can be selected (e.g., 12:00-15:00). For "Working hours," at least one of the following can be selected: less than 3 hours, 3-4 hours, 4-5 hours, 5-6 hours, etc. For "Benefits," at least one of the following can be selected: no experience necessary, casual dress code, hair coloring OK, nail polish OK, etc. For the availability of transportation expenses, it is possible to select, for example, whether to display only jobs that include transportation expenses, or whether to display jobs regardless of whether transportation expenses are included.

[0165] "Distance" and "Commute time" are examples of filter items based on the worker's location information. For "Distance," for example, it is possible to select within a certain number of kilometers a radius of the worker's current location information to display job offers. For "Commute time," it is possible to select within how many minutes the commute time is estimated based on a route search from the worker's current location information to the workplace. The worker's current location information may be location information specified by the user (such as the location information of the worker's home address or the location information of a frequently used station). In addition, route searches can be performed using the API of a publicly known web service that performs route searches, and the optimal transportation route (train, bus, etc.) can be obtained by setting the departure point and destination.

[0166] By setting the distance and commute time, workers can search for job information based on their location and using the matching rate described below.

[0167] 11, in step S204, the learning module 239b inputs the job information, the number of people recruited, and the number of applicants for each job currently being recruited into a learning model that estimates the matching rate for each job, the learning model being trained using learning data that includes at least the matching rate for each job in the past and the job information. For example, the learning module 239b inputs the job information for each job, the total number of people recruited for each job, and the total number of applicants into the learning model.

[0168] In step S206, the estimation module 240b uses the data output from the learning model to estimate the matching rate for each currently recruited job on a specific day. The specific day may be, for example, a work day. For example, the estimation module 240b may use the matching rate output by the learning model for the matching rate for each job vacancy output from the learning model, or may use a corrected matching rate as in the first embodiment.

[0169] In step S208, the setting module 242b recommends to the worker each job offer that has been set using the matching rate of each job offer for a given date estimated by the estimation module 240b and the distance between the worker's location based on the worker's location information and the work location of each job offer currently being recruited. For example, the setting module 242b preferentially recommends to the worker a job offer with a low matching rate and one whose work location is close to the worker's location. As a recommendation method, for example, the output module 241b may disclose job information to the worker in the order of priority set by the setting module 242b (see, for example, FIG. 13).

[0170] Fig. 13 is a diagram showing an example of a job listing screen including recommended job listings according to the second embodiment. The example shown in Fig. 13 shows a job listing for a specific date (e.g., June 5th) among the daily job listings, and the worker has selected "nearest distance / shortest commute time" as the display priority order. When "nearest distance / shortest commute time" is selected, the two "recommended" jobs at the top indicate jobs recommended by the setting module 242b.

[0171] As a specific example, when a worker selects "nearest distance / shortest commute time," the acquisition module 238b acquires the worker's location information (the timing of acquiring the worker's location information does not matter). The learning module 239b outputs the matching rate for each job offer, and the setting module 242b, for example, sets a higher priority to those that are closer to the worker's location. As a result, a screen such as that shown in FIG. 13 is displayed. Suppose the worker selects job offer W10. At this time, the screen transitions to the screen shown in FIG. 14.

[0172] 14 is a diagram showing an example of specific job information transitioning from the job listing according to the second embodiment. In the example shown in FIG. 14, the job information for job W10 is displayed, and it can be seen that the salary for the job has increased ("10% increase from usual due to weather influence") because the weather data for the work day is bad (rain, etc.) based on statistical data. The salary has been increased by 10% from 8,000 yen due to the weather forecast (dynamic pricing).

[0173] FIG. 15 is a diagram showing an example of a proposal screen for a business operator according to the second embodiment. On the screen shown in FIG. 15, the proposal module 243b makes a proposal to grant incentives to job offers with low matching rates. For example, the proposal module 243b suggests, "Why not increase the hourly wage to improve the matching rate?" for two job offers starting at 6:00 PM and 5:00 PM on July 25th. For these two job offers, there is ample time until the start of work, the number of applicants / number of positions available is "2 / 5," and the current matching rate is not high, so the proposal module 243b makes a proposal to grant incentives.

[0174] The proposal module 243b may calculate the increase in the hourly wage and the increase in the matching rate that would result from increasing the hourly wage based on other job information. In the example shown in Fig. 15, the proposal module 243b proposes to the business operator that increasing the hourly wage by 100 yen would result in a 100% matching rate. This allows the business operator to check the application status and understand to what extent the number of positions will be filled by providing incentives.

[0175] FIG. 16 is a diagram showing an example of a settings screen for an operator according to the second embodiment. In the screen shown in FIG. 16, the amount and matching rate are displayed in association with the hourly wage setting item on the job information settings screen. For example, the proposal module 243b calculates the hourly wage and matching rate from past data based on the matching rate on the working day, the job content of the job, weather data, etc. In the example shown in FIG. 16, the proposed information for the hourly wage is displayed as "1,250 yen or more, matching rate 90%." This allows the operator to set up job information based on a proposal from the job providing platform. Furthermore, at the stage of the settings screen shown in FIG. 16, the worker's location information does not need to be used to estimate the matching rate.

[0176] Through the above processing, according to the second embodiment, various processes that improve user convenience as a job information provision platform become possible, such as recommendations and dynamic pricing, based on the matching rate between the worker's location and each job offer.

[0177] [Third embodiment] In the past, in job information providing platforms, workers had to look up transportation information to their workplaces themselves, which required a lot of time and effort to find out the transportation costs and travel time to the job location. Furthermore, there is currently no job browsing service that takes transportation information into consideration. Therefore, in the third embodiment, to solve this problem, the job information providing platform performs various processes to improve user convenience, such as recommendations based on transportation information from the worker's location and dynamic pricing.

[0178] <Example of the configuration of the user device> The information processing device 10 according to the third embodiment has the same configuration as that described in the first and second embodiments. If there is any processing specific to the third embodiment, it will be explained in due course.

[0179] <Example of the configuration of the server-side device> 17 is a block diagram showing an example of a server 20c according to the third embodiment. Similar to the first and second embodiments, the server 20c includes one or more processing units (CPUs) 210c, one or more network communication interfaces 220c, a memory 230c, and one or more communication buses 270c for interconnecting these components. The following mainly describes processing that differs from the first and second embodiments.

[0180] The acquisition module 238c acquires location information indicating the location of the worker. The location information of the worker is the same as the location information described in the second embodiment. For example, the worker whose location information is acquired is defined as a specific worker.

[0181] The setting module 242c recommends to a worker each job offer that is set based on transportation information to the workplace of each job offer within a predetermined range identified based on the location information acquired by the acquisition module 238c from the location information acquired by the acquisition module 238c. For example, the setting module 242c sets each job offer to be recommended to a worker for each job offer within an area identified based on the location information acquired by the acquisition module 238c based on transportation information from this location information to the workplace of each job offer. For example, the setting module 242c sets each job offer to be recommended to a specific worker for each job offer that has a workplace within a predetermined area (predetermined range) from the location information of the specific worker, taking into consideration ease of commuting, travel time, travel effort, etc., based on the transportation route from the specific worker's location to the workplace.

[0182] As a specific example, the setting module 242c uses the location information of the specific worker who made the job viewing request to identify each job posting within a 20-kilometer radius and obtains a transportation route from the specific worker's location to the workplace of each identified job posting. The transportation route may be obtained from a known transportation information service that allows transportation route information to be obtained by setting a departure point and a destination. Note that the obtained transportation route may include multiple options indicating various routes from the departure point to the destination.

[0183] For example, the setting module 242c can acquire a transportation route by using an API published by the transportation information service to set the worker's location as the departure point and the workplace as the destination in the transportation information service via the API. The transportation route information may include transportation costs, number of transfers, walking distance, travel time, etc.

[0184] In addition to any of the above processes, the setting module 242c may select and set job offers to be recommended to a specific worker based on predetermined conditions for the recommendation for the acquired transportation route information. The predetermined conditions include at least one of conditions such as travel time being less than a predetermined time, the number of transfers being less than a predetermined number, and transportation costs being less than a predetermined amount, and include conditions such that the priority of the recommendation is higher for transportation routes that impose less burden on the specific worker (for example, fewer transfers, shorter travel time, lower transportation costs, etc.). On the other hand, the setting module 242c may set a higher priority for recommendations for job offers with poor conditions indicated by transportation routes, in order to make them easier to match.

[0185] The output module 241c publishes the job information of each job set by the setting module 242c to the specific worker. For example, the output module 241c may configure the job screen so that a job with a higher recommendation priority is displayed at the top of the job listing.

[0186] The above processing enables various processes that improve user convenience as a job information provision platform, such as recommendations based on traffic information from the worker's location and dynamic pricing.

[0187] In addition to any of the above processes, the learning module 239c inputs the number of people currently recruited and the number of applicants for each job posting in the area into a learning model that estimates the matching rate of the area, which is trained using learning data that includes at least the matching rate of the number of people who have worked to the number of people recruited for each past job posting in the area (predetermined range). For example, the learning model is a model that estimates the number of people who have worked / the number of people being recruited for each job posting on a future working day from the current application status (number of applicants / number of people being recruited) for each job posting in addition to traffic information. The learning model in the third embodiment may use the learning model in the second embodiment. For example, recommended job postings are sorted by weighting using the location of a specific worker.

[0188] The setting module 242c may include setting each job offer to be recommended to a worker based on the matching rate of each currently available job offer output from the learning model. For example, the setting module 242c may set a job offer with a matching rate lower than a predetermined value as a job offer to be recommended to a worker so as to increase the matching rate as much as possible.

[0189] Through the above processing, it becomes possible to set job offers to be recommended to workers based not only on traffic information but also on the matching rate of each job offer.

[0190] In addition to any of the above processes, the setting module 242c may also acquire traffic information for each job posting identified based on a predetermined condition. The predetermined condition may include, but is not limited to, the following conditions: Condition 1: The matching rate is equal to or less than a predetermined value (the matching rate calculated in the first embodiment can be used). Condition 2: Within a certain distance from the worker's location Condition 3: Conditions 1 and 2

[0191] By performing the above process, the amount of job offers for which traffic information is acquired can be reduced, thereby reducing the amount of processing by the computer.

[0192] In addition to any of the above processes, the proposal module 243c may also grant an incentive to each job offer recommended by the setting module 242c. The incentive may be, for example, a benefit for the user, and may be any benefit that encourages application. The incentive may be funded by the employer of the job offer or the operator of the job information providing platform.

[0193] According to the above process, for example, by providing incentives to workers for job openings where the workplace is located in an area with poor transportation access or where the matching rate is low, it is possible to increase the likelihood of applications.

[0194] The suggestion module 243c may include, as an incentive, increasing the travel expenses set for each job posting. For example, the suggestion module 243c may increase the travel expenses for a job posting that has a work location with poor transportation access so as to cover the worker's travel expenses. As a specific example, the suggestion module 243c may increase the travel expenses so as not to be less than the travel expenses included in the transportation information.

[0195] According to the above process, job postings with work locations inconvenient for transportation tend to have higher than normal transportation costs, but by increasing the worker's transportation costs, the worker will not feel disadvantaged in terms of the amount.

[0196] In addition to any of the above processes, the suggestion module 243c may also include setting an increased transportation expense amount that is equal to or less than the upper limit of the transportation expense amount set based on the salary. For example, the suggestion module 243c may set an upper limit so that the transportation expense amount does not become too high.

[0197] According to the above process, job offers with work locations in areas with poor transportation access tend to have higher-than-normal transportation costs, but even if workers' transportation costs are increased, setting a cap can prevent businesses from being forced to bear an excessive burden.

[0198] In addition to any of the above processes, the proposal module 243c may also execute a proposal to grant an incentive to the business operator that created a first job offer for a first job offer whose matching rate is below a predetermined value. For example, the proposal module 243c may propose to the business operator of the first job offer that a special benefit be granted as an incentive to workers for a first job offer whose matching rate on the work day is below 50% or whose recommendation ranking is 5th or lower. The reason for granting incentives to job offers with low matching rates is, for example, to match as many workers as possible and have them work for the job offer. Job offers with high matching rates may attract job applicants without any special measures, so it is advisable to implement measures for job offers with low matching rates.

[0199] Through the above process, it is possible to make proposals to improve the matching rate for businesses with workplaces in areas with poor transportation access, which may result in an increase in applications from workers and contribute to resolving labor shortages at businesses.

[0200] In addition to any of the above processes, the proposal module 243c may also notify the business operator that the number of applicants may increase as a result of the granting of the incentive. For example, the proposal module 243c may determine the possibility of an increase in the number of applicants using the increase in the matching rate described in the second embodiment. As a specific example, if the increase in the matching rate is positive, it may be determined that there is a possibility of an increase, and if the increase in the matching rate is negative, it may be determined that there is no possibility of an increase.

[0201] By performing the above process, it is possible to determine the change in the matching rate when incentives are granted. In addition, by presenting the increase in the matching rate to the business operator as a numerical value, it becomes possible to make the business operator realize the effect of granting incentives.

[0202] In addition to any of the above processes, the output module 241c may include a process of preferentially disclosing job offers with incentives. For example, the output module 241c may configure a screen so that job offers with incentives are displayed at the top of the job offer list.

[0203] The above process makes it possible to display job offers with incentives in a location where workers are likely to notice them, thereby increasing the likelihood of them applying.

[0204] <Example 4> Next, a method for setting job offers to be recommended in the third embodiment will be described using a specific example. For example, in the third embodiment, the job offers recommended to each worker are adaptively changed using transportation information to the workplace. For example, the matching probability is improved by increasing the display priority of job offers with poor transportation access or by offering incentives.

[0205] Fig. 18 is a diagram showing the current status of each job offer according to the third embodiment. In the example shown in Fig. 18, jobs D to F that satisfy a predetermined condition (for example, condition 3) for acquiring traffic information are identified. For example, the following conditions are used as the predetermined conditions: Condition 1: Work completion matching rate ≦ 80% Condition 2: Within 20 km from the worker's location (first weight > 0.1 in the second embodiment) Condition 3: Conditions 1 and 2

[0206] In the example shown in FIG. 18, "current number of applications" indicates the number of applicants / number of applicants. "Weight" is the priority (total weight) calculated in the second embodiment, but may be a weight calculated by other methods. The setting module 242c acquires traffic information for job offers D to F shown in FIG. 18. This narrows down the job information based on condition 3, thereby reducing the amount of processing.

[0207] FIG. 19 is a diagram showing an example of transportation information for each job offer according to the third embodiment. In the example shown in FIG. 19, the transportation route as transportation information includes transportation costs, number of transfers, walking distance, and travel time. If there are multiple transportation routes, it is preferable to acquire the top-ranked transportation route that the transportation information providing service proposes as optimal. In the examples shown in FIGS. 18 and 19, it is assumed that the setting module 242c has set job offers D to F as recommended jobs.

[0208] Next, the proposal module 243c calculates the incentive to be given to each job offer according to the following procedure. (1) Incentive limit = MIN (salary x 15%, 1,000 yen) Job D: MIN(450,1000) = 450 yen Job E: MIN(1100,1000) = 1000 yen Job F: MIN(750,1000)=750 yen

[0209] (2) Transportation cost incentive = MIN (incentive upper limit, transportation cost of transportation route × incentive coefficient - transportation cost of job offer set by the business operator) Transportation incentive coefficient: dynamically adjustable. Let's assume it's 1.3. Job D = MIN(450,150×1.3-200) = -5 yen *Adequate travel expenses are already set in the job offer Job E = MIN(1000,500×1.3-200) = 450 yen Job F = MIN(750,800×1.3-300) = 740 yen For example, the travel expense incentive may be set to 0 yen for Job D (sufficient travel expenses have already been set), 450 yen for Job E, and 740 yen for Job F. Note that the business operator may modify the travel expense incentive for each job as appropriate from the recommended amounts mentioned above.

[0210] (3) Weight of job listing order The weight determines the order in which recommendations are displayed in the job listing. Original weight (total weight) + |Travel expenses incentive| / 200 ·Recruitment D:3.6+5 / 200=3.625 Job E: 2.8 + 450 / 200 = 5.05 Jobs F: 2.1 + 800 / 200 = 6.1

[0211] The output module 241c configures the screen so that the job offers F, E, and D are displayed in the order of the weights calculated above on the worker's job offer list screen. Note that job offers that are eligible for incentives are those with a matching rate of a predetermined value (for example, 75%) or less. This is because job offers with a high matching rate are likely to attract applicants even without any countermeasures.

[0212] For example, the suggestion module 243c may recommend a travel expense incentive next to a job posting when the job posting is created or when the estimated matching rate is Y after X days from the posting. For example, "If you add 400 yen to travel expenses, the estimated matching rate will increase from 40% to 90%!"

[0213] If the business operator approves the proposal to increase the travel expenses, the output module 241c may add a weight to increase the exposure of this job offer. The following shows an example of a measure to increase exposure. Measure 1: For all job postings with incentives (e.g., increased travel expenses), add the weight of the job posting and tag the thumbnail image with "High travel expenses!" Example: Weight plus = (Travel expenses incentive / 400) Upper limit + 1.0 Measure 2: Post this job in the recommended section for workers within an Xkm radius Measure 3: Increase the frequency of CRM (Customer Relationship Management) notifications (push notifications, emails, etc.) for workers within an X km radius of the job posting.

[0214] The job recommendation method in Specific Example 4 is merely an example and is not limited to the above example. For example, the calculation formula for the transportation expense incentive and the calculation formula for the sorting weight are merely examples. It is sufficient to propose an appropriate transportation expense for a job with poor transportation access, and job offers from businesses whose proposals are approved should be displayed preferentially in the job listing.

[0215] <Example of data structure> Various data in the third embodiment are similar to the corresponding various data in the first and second embodiments. Note that in the third embodiment, the data output from the learning model and the final output data are different, but they may be stored in the memory 230c.

[0216] <Operation description> Next, the operation of the information processing system 1 according to the third embodiment will be described. Fig. 20 is a flowchart showing an example of processing related to job recommendations according to the third embodiment. In the example shown in Fig. 20, a server 20c is a device that implements a job information providing platform and provides a job service according to the third embodiment, and the processing executed by this server 20c is shown.

[0217] In step S302, the acquisition module 238c acquires location information indicating the location of the worker. For example, the location information may be location information from a GPS installed in the information processing device 10B used by the worker.

[0218] In step S304, the setting module 242c recommends to the worker each job offer within the area identified based on the location information acquired by the acquisition module 238c, based on transportation information from this location information to the workplace of each job offer. For example, the setting module 242c sets each job offer to be recommended to the specific worker for each job offer with a workplace within a predetermined area based on the location information of the specific worker, taking into account ease of commuting, travel time, travel effort, etc., based on the transportation route from the specific worker's location to the workplace. Note that as an example of step S304, the processing of steps S342 and S344 may be performed.

[0219] In step S342, the learning module 239c may input the number of people recruited and the number of applicants for each job currently being recruited in the area into a learning model that estimates the matching rate of the area, the learning model being trained using learning data that includes at least the matching rate of the number of people who have worked to the number of people recruited for each past job in the area. For example, the learning model is a model that estimates the number of people who have worked / the number of people being recruited for each job on a future working day for each job based on the current application status for each job (number of applicants / number of people recruited). The learning model in the third embodiment may use the learning model in the second embodiment.

[0220] In step S344, the setting module 242c may set each job offer to be recommended to the worker based on the matching rate of each currently available job offer output from the learning model. For example, the setting module 242c may set a job offer with a matching rate lower than a predetermined value as a job offer to be recommended to the worker so as to increase the matching rate as much as possible.

[0221] In step S306, the output module 241c publishes the job information of each job set by the setting module 242c to the specific worker. For example, the output module 241c may configure the job screen so that a job with a higher recommendation priority is displayed at the top of the job listing.

[0222] In step S308, the suggestion module 243c may add an incentive to each job offer recommended by the setting module 242c. The incentive may be, for example, a benefit for the user, and may be any benefit that encourages the user to apply.

[0223] In step S310, if the proposal module 243c obtains approval for the proposal from the business operator, it grants an incentive to the job offer. If the incentive is granted, the output module 241c executes, for example, the above-mentioned measures 1 to 3. Furthermore, the proposal module 243c may grant an incentive to the job offer even if approval is not obtained from the business operator.

[0224] FIG. 21 is a diagram showing an example of a push notification according to the third embodiment. In the example shown in FIG. 21, the output module 241c sends a push notification to proactively inform each worker of a job offer with increased travel expenses (measure 3). The push notification displays, "Job offer with increased travel expenses! A job offer with increased travel expenses than usual has been posted for a limited time only!", and the information processing device 10 used by the worker waits for an operation from the worker. When the worker operates the push notification, the job offer app is launched, and the screen shown in FIG. 22 may be displayed directly or indirectly.

[0225] FIG. 22 is a diagram showing an example of a job listing screen according to the third embodiment. The screen shown in FIG. 22 displays a job listing with the words "Increased travel expenses!" at the top of the screen (measure 2). This can make workers interested in job listings with increased travel expenses and increase the likelihood that they will refer to this job listing. Assume that a job listing W20 is operated by a worker on the screen shown in FIG. 22. At this time, a details screen for job listing W20 shown in FIG. 23 is displayed on the screen. Note that the screen shown in FIG. 22 can also be the screen displayed in step S306 without "Increased travel expenses" (for example, changed to "Recommended!") if the job listing would be recommended even without "Increased travel expenses."

[0226] Fig. 23 is a diagram showing an example of a job details screen according to the third embodiment. In the example shown in Fig. 23, it is easy to see that the transportation costs for this job have increased by 740 yen. In addition, since this is limited to workers within a specific distance, if the worker's location is within a specified distance from the workplace of this job, they can receive the push notification shown in Fig. 21 and check the job details screen shown in Fig. 23.

[0227] FIG. 24 is a diagram showing an example of a setting screen for an operator according to the third embodiment. In the screen shown in FIG. 24, the amount and matching rate are displayed in association with the travel expense setting item on the job information setting screen. For example, the proposal module 243c calculates the increase in travel expenses to be proposed to the operator based on the travel expenses included in the travel information. In the example shown in FIG. 24, the proposed information for travel expenses is displayed as "+400 yen with a matching rate of 85%." Furthermore, the screen shown in FIG. 24 displays "If the recommended content is reflected, this job offer will be displayed preferentially on the job offer screen." This allows the operator to know that by accepting this proposal, the job offer will be displayed preferentially. This allows the operator to set up job information based on the proposal from the job providing platform.

[0228] Through the above processing, according to the third embodiment, various processes that improve user convenience as a job information providing platform become possible, such as recommendations based on traffic information from the worker's location and dynamic pricing.

[0229] Furthermore, if it is assumed that the configurations in the third embodiment can execute the processes described in the first to third embodiments, then the processes shown in Fig. 25 can be executed. Fig. 25 is a diagram showing a flowchart illustrating an example of each process in the third embodiment.

[0230] In steps S402 and S404, the worker's device (information processing device 10B, etc.) acquires its own location information using a location estimation service (for example, GPS, etc.) and outputs it to server 20c. Note that use of the location estimation service is not essential, and location information set by a worker specifying a location on a map may be output.

[0231] In step S406, the setting module 242c of the server 20c identifies job vacancies with work locations to which the worker can apply, based on the worker's location. For example, job vacancies that can be applied for may be within a predetermined distance from the worker's location.

[0232] In step S408, the output module 241c of the server 20c makes the job listing available to the worker. At this time, in response to a view request from the worker, screen information of the job listing including available jobs may be output to the worker's device.

[0233] In step S410, the setting module 242c of the server 20c may rearrange the job offers according to the location of the worker. The rearrangement method may be the method of specific example 3 or 4.

[0234] In step S412, the setting module 242c of the server 20c accesses the traffic information providing service via the API to set the worker's location and the job location of the job offer and obtain traffic information.

[0235] In step S414, the setting module 242c of the server 20c acquires traffic route options as traffic information from the traffic information service, and acquires travel time, number of transfers, transportation costs, and the like as information for each route.

[0236] In step S416, the learning module 239c of the server 20c learns the job information of jobs that the worker has applied for in the past, thereby grasping the worker's tendency to apply.

[0237] In step S418, the learning module 239c of the server 20c estimates the user's tolerance for each mode of transportation, such as bus, train, walking, etc. The learning module 239c can estimate the user's tolerance by understanding the worker's application tendency.

[0238] In step S420, the setting module 242c of the server 20c sets a priority for recommendations to the worker based on each job posting sorted in step S410, the transportation information for each job posting obtained in step S414, and the worker's acceptability of their means of transportation obtained in step S418, and generates a job posting list based on the priority.

[0239] In steps S422 and S424, the estimation module 240c of the server 20c estimates the matching rate for each job offer. At this time, the matching rate may be estimated for each area. The matching rate may be calculated using past data, the current number of applicants, the number of job offers, etc. For example, the matching rate may be calculated using any of the matching rate estimation methods disclosed herein.

[0240] In step S426, the proposal module 243c of the server 20c calculates an incentive to propose for each job offer. The incentive is a benefit given to a worker, and includes at least one of salary, transportation expenses, points, service coupons, and the like.

[0241] In step S428, the proposal module 243c of the server 20c notifies or displays on the screen the incentive to be granted to a worker who applies for a job offer to which an incentive is granted. Through the above processing, the integrated processing of the first to third embodiments can be executed.

[0242] The disclosed technology is not limited to the above-described embodiment, and can be implemented in various other forms without departing from the spirit of the disclosed technology. Therefore, the above-described embodiment is merely an example in all respects and should not be interpreted as being limiting. For example, the order of the above-described processing steps can be arbitrarily changed or executed in parallel as long as no contradiction occurs in the processing content.

[0243] The program of the embodiment of the present disclosure may be provided in a state stored in a computer-readable storage medium. The storage medium can store the program in a "non-transitory tangible medium." The program includes, but is not limited to, a software program or a computer program.

[0244] The following are additional notes regarding the above-disclosed technology. [Appendix 1] The information processing device Obtaining location information of a predetermined location; inputting predetermined statistical data into a learning model that estimates a matching rate within a predetermined range, the learning model being trained using learning data that includes at least the matching rate and statistical data of each past job offer within the predetermined range identified based on the location information; Using data output from the learning model, estimating a matching rate for a given day for job offers within the given range; An information processing method that performs the above. [Appendix 2] The obtaining includes: 2. The information processing method of claim 1, further comprising obtaining location information indicating the location of the worker from a processing device used by the worker. [Appendix 3] An information processing method according to claim 1 or 2, which involves training the learning model to learn the learning data, which includes statistical data including at least one of data on past workday dates, days of the week, holidays, and weather. [Appendix 4] 4. The information processing method according to any one of appendices 1 to 3, wherein the learning model is made to learn the learning data including at least the number of cancellations on a workday. [Appendix 5] The estimating step comprises: Obtaining estimated increases in the number of applicants and the number of job openings until a future work date, estimated by the learning model based on current statistical data, the number of job openings, and the number of applicants; An information processing method described in any one of Appendices 1 to 4, which includes estimating the matching rate for the future workdays using the estimated values ​​of the current number of people recruited, the number of applicants, the increase in the number of people recruited, and the increase in the number of applicants. [Appendix 6] The estimating step comprises: 6. The information processing method of claim 5, further comprising estimating a matching rate for the future workdays based on the number of cancellations for the future workdays. [Appendix 7] The estimating step comprises: estimating the increase in the number of available workers from the present to the future work date; 6. The information processing method of claim 5, further comprising estimating a matching rate for the future workday based on the increase in the number of workers. [Appendix 8] Execute learning of the learning model using the learning data including category information of past job offers; The estimating step comprises: 8. The information processing method according to any one of claims 1 to 7, further comprising estimating the matching rate for each job category. [Appendix 9] The learning step includes: An information processing method as described in Appendix 8, which includes training the learning model to learn the category information including the type and / or content of the job posting. [Appendix 10] In the information processing device, Obtaining location information of a predetermined location; inputting predetermined statistical data into a learning model that estimates a matching rate within a predetermined range, the learning model being trained using learning data that includes at least a matching rate of the number of people who have completed work relative to the number of people recruited and statistical data on work days for each past job offer within the predetermined range identified based on the location information; Using data output from the learning model, estimating a matching rate for a given day for job offers within the given range; A program that executes the following. [Appendix 11] An information processing device including one or more processors, the one or more processors: Obtaining location information of a predetermined location; inputting predetermined statistical data into a learning model that estimates a matching rate within a predetermined range, the learning model being trained using learning data that includes at least a matching rate of the number of people who have completed work relative to the number of people recruited and statistical data on work days for each past job offer within the predetermined range identified based on the location information; Using data output from the learning model, estimating a matching rate for a given day for job offers within the given range; An information processing device that executes the above. [Appendix 21] The information processing device Obtaining worker location information; Inputting the job information, number of applicants, and number of applicants for each job currently being recruited into a learning model that estimates the matching rate for each job, the learning model being trained using learning data that includes at least the matching rate for each past job and the job information; Using the data output from the learning model, estimating a matching rate for each of the currently recruiting jobs on a given day; Recommending to the worker each job offer that is set using the estimated matching rate of each job offer on the specified date and the distance between the worker's location based on the location information and the work location of each job offer that is currently being recruited; An information processing method that performs the above. [Appendix 22] The information processing method of claim 1, wherein the learning model learns the learning data including job information for jobs that the worker has applied for in the past, and outputs a matching rate for each currently recruiting job that is similar to the job information for jobs that the worker has applied for in the past. [Appendix 23] An information processing method as described in Appendix 21 or 22, wherein the job information learned by the learning model includes at least one of work type, work content, working hours, work location, and salary. [Appendix 24] The inputting step comprises: An information processing method described in any one of Appendices 21 to 23, which includes inputting job information, number of applicants, and number of applicants for each job currently being recruited within a specified range into a learning model trained using the learning data of each past job opening within the specified range identified based on the location information. [Appendix 25] An information processing method described in any one of Appendices 21 to 24, which executes a proposal to the business operator that created a first job offer for which the matching rate on the specified day is below a specified value to grant an incentive to the worker. [Appendix 26] The proposal is: 26. The information processing method of claim 25, including suggesting increasing salary information for the first job offer. [Appendix 27] The proposal is: 27. The information processing method of claim 26, including suggesting an increase in salary information for the first job offer based on salary information for jobs similar to the first job offer. [Appendix 28] The inputting step comprises: inputting job information for the first job, including increased salary information, into the learning model; The estimating step comprises: 28. The information processing method of claim 26 or 27, further comprising estimating an increase in the matching rate for the first job offer on the specified day using the matching rate for the first job offer based on the increased salary information. [Appendix 29] In the information processing device, obtaining location information of the worker's location; Inputting the job information, number of applicants, and number of applicants for each job currently being recruited into a learning model that estimates the matching rate for each job, the learning model being trained using learning data that includes at least the matching rate for each past job and the job information; Using the data output from the learning model, estimating a matching rate for each of the currently recruiting jobs on a given day; Recommending to the worker each job offer that is set using the estimated matching rate of each job offer on the specified date and the distance between the worker's location based on the location information and the work location of each job offer that is currently being recruited; A program that executes. [Appendix 30] An information processing device including one or more processors, the one or more processors: Obtaining worker location information; Inputting the job information, number of applicants, and number of applicants for each job currently being recruited into a learning model that estimates the matching rate for each job, the learning model being trained using learning data that includes at least the matching rate for each past job and the job information; Using the data output from the learning model, estimating a matching rate for each of the currently recruiting jobs on a given day; Recommending to the worker each job offer that is set using the estimated matching rate of each job offer on the specified date and the distance between the worker's location based on the location information and the work location of each job offer that is currently being recruited; An information processing device that executes the above. [Appendix 41] The information processing device Obtaining worker location information; Recommending to the worker, from the location information, each job offer set based on transportation information to the work location of each job offer within a predetermined range identified based on the location information; An information processing method that performs the above. [Appendix 42] inputting the number of applicants and the number of positions available for each job currently being recruited within the predetermined range into a learning model that estimates the matching rate within the predetermined range and that has been trained using learning data that includes at least the matching rate of each past job offer within the predetermined range; The setting 42. The information processing method of claim 41, further comprising setting each job offer to be recommended to the worker based on the matching rate of each currently available job offer output from the learning model. [Appendix 43] The setting 43. The information processing method of claim 41 or 42, further comprising obtaining the traffic information for each job posting identified based on predetermined conditions. [Appendix 44] 44. The information processing method according to any one of appendices 41 to 43, further comprising providing an incentive for each of the recommended job offers. [Appendix 45] The providing step comprises: 45. The information processing method of claim 44, further comprising increasing the travel expenses set for each job offer. [Appendix 46] The providing step comprises: The information processing method of claim 45, which includes setting an increased transportation allowance that is less than or equal to the upper limit of transportation allowances set based on salary. [Appendix 47] An information processing method as described in Appendix 42, which executes a proposal to grant an incentive to the business that created a first job offer for which the matching rate is below a predetermined value. [Appendix 48] The proposal is: 48. The information processing method of claim 47, including notifying the business operator that the number of applicants may increase as a result of the granting of the incentive. [Appendix 49] 49. The information processing method according to claim 47 or 48, wherein the job offers to which the incentive is granted are preferentially published. [Appendix 50] In the information processing device, Obtaining worker location information; Recommending to the worker, from the location information, each job offer set based on transportation information to the work location of each job offer within a predetermined range identified based on the location information; A program that executes the following. [Appendix 51] An information processing device including one or more processors, the one or more processors: Obtaining worker location information; Recommending to the worker, from the location information, each job offer set based on transportation information to the work location of each job offer within a predetermined range identified based on the location information; An information processing device that executes the above. [Explanation of symbols]

[0245] 1. Information Processing Systems 10, 10A, 10B, 10C Information processing device 20 Information processing device (server) 110, 210 Processing Unit (CPU) 120, 220 network communication interface 130, 230 memory 131, 231 operating systems 132, 232 Network Communication Module 133 App Data 134 Service Processing Module 135 Acquisition Module 136 Output Module 137 Processing Module 138 Display Control Module 150 User Interface 170, 270 communication bus 233 User Information 234 Job Information 235 Usage history information 236 Learning Model Information 237 Service Control Module 238 Acquisition Module 239 Learning Modules 240 Estimation Module 241 Output Module 242 Settings Module 243 Suggestion Module

Claims

1. The information processing device acquiring position information for each predetermined position; inputting predetermined statistical data into a learning model that estimates a matching rate of job offers within each predetermined range, the learning model being trained using learning data that includes at least a matching rate of past job offers within each predetermined range specified based on the location information and statistical data that includes at least past work dates; Using the data output from the learning model, estimating a matching rate for a job offer within each predetermined range on a predetermined day; An information processing method that performs the above.

2. The obtaining includes: The information processing method according to claim 1 , further comprising acquiring location information indicating the location of each worker from each processing device used by the worker.

3. The information processing method according to claim 1 , further comprising the step of causing the learning model to learn the learning data, which includes the statistical data including at least one of data on days of the week, holidays, and weather of past work days.

4. The information processing method according to claim 1 , further comprising: causing the learning model to learn the learning data including at least the number of cancellations on a workday.

5. The estimating step comprises: Obtaining estimated increases in the number of applicants and the number of job openings until a future work date, estimated by the learning model based on current statistical data, the number of job openings, and the number of applicants; The information processing method according to claim 1 , further comprising estimating a match rate for the future workday using the current number of job openings, the number of applicants, the increase in the number of job openings, and the estimated increase in the number of applicants.

6. The estimating step comprises: The information processing method according to claim 5 , further comprising estimating a matching rate for the future workday based on the number of cancellations for the future workday.

7. The estimating step comprises: estimating the increase in the number of available workers from the present to the future work date; The information processing method according to claim 5 , further comprising estimating a matching rate for the future workday based on the increase in the number of workers.

8. Execute learning of the learning model using the learning data including category information of past job offers; The estimating step comprises: The information processing method according to claim 1 , further comprising estimating the matching rate for each job category.

9. The learning step includes: The information processing method according to claim 8 , further comprising causing the learning model to learn the category information including the type and / or content of the job posting.

10. In the information processing device, acquiring position information for each predetermined position; inputting predetermined statistical data into a learning model that estimates a matching rate of job offers within each predetermined range, the learning model being trained using learning data that includes at least a matching rate of past job offers within each predetermined range specified based on the location information and statistical data that includes at least past work dates; Using the data output from the learning model, estimating a matching rate for a job offer within each predetermined range on a predetermined day; A program that executes the following.

11. An information processing device including one or more processors, the one or more processors: acquiring position information for each predetermined position; inputting predetermined statistical data into a learning model that estimates a matching rate of job offers within each predetermined range, the learning model being trained using learning data that includes at least a matching rate of each past job offer and statistical data that includes at least past work dates for each past job offer within each predetermined range identified based on the location information; Using the data output from the learning model, estimating a matching rate for a job offer within each predetermined range on a predetermined day; An information processing device that executes the above.

Images