JP6613433B2 - Information processing apparatus and program - Google Patents

Description

  The present invention relates to an information processing apparatus and a program.

  In various fields, AI (Artificial Intelligence) technology is being used. As an application example of AI technology, there is a system that uses a teacher data to execute a matching simulation for predicting a matching between a population including a plurality of elements and a certain target element. Such a system is used, for example, to predict matching between a company and a job seeker.

  In general, the smaller the teacher data population, the lower the accuracy of simulation results. On the other hand, in Patent Document 1, in the method of performing similarity learning between job offer information and resume information using an analysis method based on a topic model, the accuracy of simulation results is improved even when the population is small. A method for improving is disclosed.

JP 2017-134732 A

  However, in the technique of Patent Document 1, since the matching simulation is performed using the processed data elements after processing the data elements constituting the population, the accuracy of the simulation result may be low.

  An object of the present invention is to improve the accuracy of simulation results even when the number of elements included in a set is small in a matching simulation between a set including a plurality of elements and a target element to be matched. It is.

One embodiment of the present invention provides:
An information processing device that performs matching between an individual and an organization,
By comparing member information relating to members belonging to the target organization to be matched with member information relating to members belonging to non-target organizations other than the target organization, And means for identifying at least one similar tissue similar to the target tissue,
Means for creating teacher data including member information relating to members belonging to the target organization and member information relating to members belonging to the similar organization;
Means for determining a matching level between the target person and the target organization based on the target personal information on the target person to be matched and the teacher data;
Information processing apparatus.

  According to the present invention, in the matching simulation with the target element to be matched, the accuracy of the simulation result can be improved even when the number of elements included in the set is small.

It is a block diagram which shows the structure of the information processing system of this embodiment. It is explanatory drawing of the outline | summary of this embodiment. It is explanatory drawing of an example of the outline | summary of this embodiment. It is a figure which shows the data structure of the company information database of this embodiment. It is a figure which shows the data structure of the employee information database of this embodiment. It is a figure which shows the data structure of the job seeker information database of this embodiment. It is a flowchart of the information processing of this embodiment. It is a figure which shows the example of a screen displayed on a client apparatus in the information processing of FIG. It is explanatory drawing of the information processing of this embodiment. 10 is an explanatory diagram of an outline of Modification 1. FIG. It is explanatory drawing of the outline | summary of the modification 2. FIG. FIG. 10 is a diagram illustrating an example of a screen displayed on a client device in information processing according to modification example 4;

  Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Note that in the drawings for describing the embodiments, the same components are denoted by the same reference symbols in principle, and the repetitive description thereof will be omitted.

(1) Configuration of Information Processing System The configuration of the information processing system will be described. FIG. 1 is a block diagram showing the configuration of the information processing system of this embodiment.

As illustrated in FIG. 1, the information processing system 1 includes a client device 10 and a server 30.
The client device 10 and the server 30 are connected via a network (for example, the Internet or an intranet) NW.

  The client device 10 is an example of an information processing device that transmits a request to the server 30. The client device 10 is, for example, a smartphone, a tablet terminal, or a personal computer.

  The server 30 is an example of an information processing apparatus that provides the client apparatus 10 with a response corresponding to the request transmitted from the client apparatus 10. The server 30 is, for example, a web server.

(1-1) Configuration of Client Device The configuration of the client device 10 will be described with reference to FIG.

  As shown in FIG. 1, the client device 10 includes a storage device 11, a processor 12, an input / output interface 13, and a communication interface 14.

  The storage device 11 is configured to store a program and data. The storage device 11 is, for example, a combination of ROM (Read Only Memory), RAM (Random Access Memory), and storage (for example, flash memory or hard disk).

The programs include, for example, the following programs.
-OS (Operating System) program-Application (for example, web browser) program that executes information processing

The data includes, for example, the following data.
-Database referenced in information processing-Data obtained by executing information processing (that is, information processing execution result)

  The processor 12 is configured to realize the function of the client device 10 by starting a program stored in the storage device 11. The processor 12 is an example of a computer.

The input / output interface 13 is configured to acquire a user instruction from an input device connected to the client apparatus 10 and to output information to an output device connected to the client apparatus 10.
The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof.
The output device is, for example, a display.

  The communication interface 14 is configured to control communication between the client device 10 and the server 30.

(1-2) Server Configuration The configuration of the server 30 will be described with reference to FIG.

  As illustrated in FIG. 1, the server 30 includes a storage device 31, a processor 32, an input / output interface 33, and a communication interface 34.

  The storage device 31 is configured to store a program and data. The storage device 31 is, for example, a combination of ROM, RAM, and storage (for example, flash memory or hard disk).

The programs include, for example, the following programs.
-OS program-Application program that executes information processing

The data includes, for example, the following data.
・ Database referenced in information processing ・ Results of information processing

  The processor 32 is configured to realize the function of the server 30 by starting a program stored in the storage device 31. The processor 32 is an example of a computer.

The input / output interface 33 is configured to acquire a user instruction from an input device connected to the server 30 and output information to an output device connected to the server 30.
The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof.
The output device is, for example, a display.

  The communication interface 34 is configured to control communication between the server 30 and the client device 10.

(2) Outline of the present embodiment An outline of the present embodiment will be described. FIG. 2 is an explanatory diagram of the outline of the present embodiment.

  As illustrated in FIG. 2, the server 30 according to the present embodiment executes a matching simulation for predicting matching between a target element TE that is a matching target and a set G1 that is a matching target.

  Target element information related to the target element is associated with the target element TE.

Each of the plurality of sets G1 to G3 includes a plurality of elements.
Element information relating to elements included in the set is associated with each set G1 to G3.

  In the matching simulation regarding the target element TE and the set G1, the server 30 refers to element information of the set G2 similar to the set G1 as teacher data TD in addition to the element information of the set G1.

In a general matching simulation, only information associated with the set G1 to be matched is referred to as the teacher data TD.
In contrast, the server 30 refers not only to the information associated with the set G1 to be matched but also the information associated with the set G2 similar to the matching target as the teacher data TD. That is, the server 30 extends the teacher data TD.

  An example of the outline of the present embodiment will be described. FIG. 3 is an explanatory diagram of an example of the outline of the present embodiment.

  As shown in FIG. 3, the server 30 of the present embodiment executes a matching simulation between the job seeker APP (an example of “individual”) and a company (an example of “organization”).

  Job seeker APP is associated with job seeker information related to the job seeker APP.

At least one employee (an example of “member”) belongs to each of the plurality of companies COM1 to COM3.
Employee information (an example of “member information”) related to employees is associated with each of the companies COM1 to COM3.

  In the matching simulation between the job seeker APP and the company COM1, the server 30 refers to the employee information of the company COM2 similar to the company COM1 as teacher data TD in addition to the employee information of the company COM1.

  Thereby, even if the population of elements of the company COM1 to be matched is small, the accuracy of the simulation result can be improved. Specifically, the accuracy of the simulation result can be improved even when the number of employees belonging to the company COM1 is small (that is, the data amount of employee information of the company COM1 is small).

(3) Database The database of this embodiment will be described. The following database is stored in the storage device 31.

(3-1) Company Information Database The company information database of this embodiment will be described. FIG. 4 is a diagram showing the data structure of the company information database of this embodiment.

The company information database in FIG. 4 stores company information about the company (an example of “organization information”).
The company information database includes a “company ID” field, a “company name” field, a “company attribute” field, an “achievement” field, and a “object variable” field. Each field is associated with each other.

  The “company ID” field stores a company ID for identifying a company. The company ID is determined by the server 30.

  In the “company name” field, information (for example, text) indicating the company name is stored. The company name is arbitrarily determined by an operator who registers company information in the server 30.

  The “company attribute” field stores company attribute information related to the attributes of the company. The “company attribute” field includes an “industry” field, an “number of employees” field, and a “location” field. The company attribute information is arbitrarily determined by an operator who registers the company information in the server 30, or the server 30 acquires it from an external server.

  The “business type” field stores information on the business type of the company.

  The “number of employees” field stores information on the number of employees in the company.

  The “location” field stores information on the location of the company (for example, the location where the head office is located).

  The “performance” field stores performance information related to the performance of the company. The “company attribute” field includes a “sales” field and a “profit” field. The performance information is arbitrarily determined by an operator who registers company information in the server 30, or the server 30 acquires it from an external server.

  The “sales” field stores information related to the sales of the company.

  The “profit” field stores information related to the profit of the company.

  In the “object variable” field, an object variable indicating the human resource required by the company is stored. The objective variable is arbitrarily determined by an operator who registers company information in the server 30.

(3-2) Employee information database The employee information database of this embodiment is demonstrated. FIG. 5 is a diagram showing a data structure of the employee information database of the present embodiment.

The employee information database of FIG. 5 stores employee information regarding employees belonging to the company.
The employee information database includes an “employee ID” field, an “employee name” field, a “department code” field, an “employee attribute” field, an “pre-entry objective evaluation” field, and a “pre-employment subjective evaluation” field. , An “objective evaluation after joining the company” field and a “subjective evaluation after joining the company” field.
The employee information database is associated with the company ID.

  The “employee ID” field stores an employee ID for identifying the employee.

  The “employee name” field stores information (for example, text) indicating the employee name.

  The “department code” field stores a department code for identifying the department to which the employee belongs.

  In the “employee attribute” field, employee attribute information related to the attribute of the employee is stored. The “employee attribute” field includes a “sex” field, an “educational background” field, a “motivation motivation” field, and a “personality” field. The information in the “employee attribute” field is determined based on, for example, a resume submitted before joining the company.

  The “gender” field stores information on the gender of the employee.

  In the “educational history” field, information related to the educational background of the employee is stored.

  The “motivation motive” field stores information on the employee's desire motive.

  In the “personality” field, information related to the personality of the employee is stored.

In the “pre-entry objective evaluation” field, pre-entry objective evaluation information (an example of “evaluation information”) regarding objective evaluation obtained by a test performed on employees before joining the company is stored. The “pre-entry objective evaluation” field includes a plurality of “index” fields.
Each “index” field stores a score indicating an evaluation (for example, employee ability) for each index measured in the test.
The index includes, for example, the following.
・ Future / challenge / collaboration

  In the “Pre-employment Subjective Evaluation” field, the pre-entry subjective evaluation information (“Evaluation”) regarding the subjective evaluation (for example, the satisfaction of the employee before joining the company) obtained by the test conducted on the employees before joining the company. An example of “information” is stored.

The “post-entry objective evaluation” field stores post-entry objective evaluation information (an example of “evaluation information”) related to objective evaluation obtained by a test conducted on employees who have joined the company. The “post-entry objective evaluation” field includes a plurality of “index” fields.
Each “index” field stores a score indicating an evaluation (for example, employee ability) for each index measured in the test. Each “index” field of the “post-entry objective evaluation” field corresponds to each “index” field of the “pre-entry objective evaluation” field.

  In the “Pre-employment Subjective Evaluation” field, post-entry subjective evaluation information (“evaluation”) regarding subjective evaluation (for example, employee satisfaction after joining the company) obtained by a test conducted on employees after joining the company. An example of “information” is stored.

(3-3) Job Seeker Information Database The job seeker information database of this embodiment will be described. FIG. 6 is a diagram illustrating a data structure of the job seeker information database according to the present embodiment.

The job seeker information database in FIG. 6 stores job seeker information related to job seekers.
The job applicant information database includes a “job applicant ID” field, a “job applicant name” field, a “job applicant image” field, a “job applicant attribute” field, a “pre-employment objective evaluation” field, It includes a “subjective evaluation” field and a “matching score” field.
The job seeker information database is associated with the company ID.

  The “job seeker ID” field stores a job seeker ID for identifying a job seeker.

  In the “job seeker name” field, information (for example, text) indicating the job seeker name is stored.

  In the “job seeker image” field, image data of the job seeker is stored.

  The “job seeker attribute” field stores job seeker attribute information related to job seeker attributes. The “job seeker attribute” field includes a “sex” field, an “education” field, a “motivation motivation” field, and a “personality” field.

  The “gender” field stores information on the job seeker's gender.

  In the “educational history” field, information on the educational background of the job seeker is stored.

  The “motivation motive” field stores information on the job applicant's desire motive.

  The “personality” field stores information on the personality of the job seeker.

In the “pre-entry objective evaluation” field, pre-entry objective evaluation information obtained from the results of tests conducted on job seekers before entering the company is stored. The “pre-entry objective evaluation” field includes a plurality of “index” fields.
Each “index” field stores a score indicating the ability of each index measured in the test. Each “index” field corresponds to each “index” field in the “objective evaluation before joining” field of FIG.

  The “pre-entry subjective assessment” field stores pre-entry subjective assessment information obtained by a test conducted on a job seeker before joining the company.

  The “matching score” field stores a matching score indicating a matching level between the company identified by the company ID associated with the job applicant information database and the job seeker. The matching score is a simulation result of the matching simulation.

(4) Information processing The information processing of this embodiment is demonstrated. FIG. 7 is a flowchart of information processing according to this embodiment. FIG. 8 is a diagram showing an example of a screen displayed on the client device in the information processing of FIG. FIG. 9 is an explanatory diagram of information processing according to the present embodiment.

As shown in FIG. 7, the client device 10 executes a matching request (S100).
Specifically, the processor 12 displays the screen P100 (FIG. 8) on the display.

The screen P100 includes an operation object B100 and an input field object F100.
The input field object F100 is an object that receives an input of a company ID.
The operation object B100 is an object for receiving a user instruction of a matching request.

When a user (for example, a company recruiter) inputs a company ID in the input field object F100 and designates the operation object B100, the processor 12 transmits matching request data to the server 30.
The matching request data includes the company ID input to the input field object F100.

After step S100, the server 30 executes a first variable importance calculation (S300).
Specifically, the processor 32 includes, in the employee information database (FIG. 5) associated with each company ID included in the company information database (FIG. 4), a “department code” field, an “employee attribute” field, Information in the “pre-entry evaluation” field, “subjective evaluation before joining” field, “post-entry objective evaluation” field, and “post-entry subjective evaluation” field is specified as explanatory variables.
The processor 32 refers to the company information database and identifies an objective variable associated with the company ID included in the matching request data.
The processor 32 uses the first mathematical model (for example, the multiple regression analysis model of Equation 1) to calculate the first variable importance indicating the contribution rate of each explanatory variable to the target variable (for example, “future”). .
That is, the first variable importance is a variable importance of employee information of each company registered in the company information database.
y _m = b ₀ + b ₁ x ₁ + b ₂ x ₂ +... b _n x _n (Formula 1)
Y is an objective variable of company information, x is an explanatory variable of company information, m (≧ 1) is the number of objective variables of company information, n is the number of explanatory variables of company information, b _i (i = 0 to n) are constants

  For example, when m = 1, in step S300, the first variable importance related to the “future” of the companies COM1 to COMn (n is an integer of 2 or more) is obtained.

As shown in FIG. 7, after S300, the server 30 executes identification of a similar set (S301).
Specifically, the first variable importance of the employee information database associated with the company ID included in the matching request data (that is, the first variable importance of the target company) and the company ID other than the company ID are associated. The company ID of the non-target company (hereinafter referred to as “similar company”) similar to the target company by comparing the first variable importance of the employee information database (that is, the first variable importance of the non-target company) Is identified.
For example, the processor 32 identifies a non-target company that satisfies at least one of the following similar conditions as a similar company.
A non-target company similar to the target company for the distribution of the first variable importance calculated in step S300. A predetermined number (for example, three) of the first variable importance calculated in step S300 from the top. Regarding the difference in the importance of one variable, the ratio of the first variable importance of a predetermined number (for example, three) from the top among the first variable importance calculated in step S300, which is not more than a predetermined value. Identical non-target companies ・ Non-target companies whose cosine similarity obtained by substituting the first variable importance calculated in step S300 into the cosine similarity model is a predetermined value or more.

  For example, as shown in FIG. 9, in step S301, as a result of comparing the first variable importance of the target company COM1 and the first variable importance of the non-target company COMn, the first variable importance satisfying the similarity condition is satisfied. The non-target company COM2 corresponding to is identified as a similar company.

  The processor 32 transmits similar company information regarding the specified similar company to the client device 10. The similar company information includes the company ID of the similar company, the company name of the similar company, and the first variable importance of the similar company.

As shown in FIG. 7, after step S301, the client device 10 performs screen display (S101).
Specifically, the processor 12 displays the screen P101 on the display based on the similar company information transmitted in step S301.

As shown in FIG. 8, the screen P101 includes a display object A101 and operation objects B101a to B101b.
The display object A101 displays the company name of the similar company and the first variable importance regarding the “future” of the similar company.
The operation object B101a is a check box object for receiving the designation of the company referred to in step S302 from the companies displayed on the display object A101. A company ID included in the similar company information is assigned to the operation object B101a. The operated operation object B101a is selected.
The operation object B101b is an object that receives a user instruction for confirming the selection state.

When the user operates the operation object B 101a corresponding to an arbitrary company on the screen P101, the processor 12 specifies the company ID assigned to the operated operation object B 101a.
When the user operates the operation object B101b, the processor 12 transmits the specified company ID to the server 30.

As shown in FIG. 7, after step S101, the server 30 executes creation of teacher data (S302).
Specifically, the processor 32 creates teacher data including the following information.
-Information in the employee information database associated with the company ID included in the matching request data (that is, employee information of employees belonging to the target company)
Information in the employee information database associated with the company ID transmitted from the client device 10 in step S101 (that is, employee information of employees belonging to similar companies)

  For example, as shown in FIG. 9, in step S302, teacher data including employee information 1 of the target company COM1 and employee information 2 of the similar company COM2 is obtained.

・ｊ（＞ｍ）は、対象企業及び類似企業の社員情報の目的変数の数
・α_ｊは、定数
・β_１ｊは、係数
・Ｘ_Ｋｊは、対象企業及び類似企業の社員情報の説明変数 As shown in FIG. 7, after step S302, the server 30 executes the second variable importance calculation (S303).
Specifically, the processor 32 has the same information (that is, “department code” as the information specified as the explanatory variable in step S300 among the teacher data (that is, employee information of the target company and similar companies) created in step S302. ”Field,“ employee attribute ”field,“ objective evaluation before joining ”field,“ subjective subjective evaluation ”field,“ post-employment objective evaluation ”field, and“ post-entry subjective evaluation ”field information) in step S303 Identified as an explanatory variable.
The processor 32 refers to the company information database and identifies an objective variable associated with the company ID included in the matching request data.
The processor 32 uses the second mathematical model (for example, the multinomial logit model of Equation 2) composed of more mathematical formulas than the number of the mathematical formulas constituting the first mathematical model (ie, the teacher data (that is, the target) The second variable importance indicating the contribution rate of each explanatory variable to the objective variable is calculated.
That is, the second variable importance is a variable importance of employee information of the target company and similar companies.

• j (> m) is the number of objective variables of employee information of the target company and similar companies • α _j is a constant • β _1j is a coefficient • X _Kj is an explanatory variable for employee information of the target company and similar companies

  For example, as shown in FIG. 9, in step S303, the second variable importance of a plurality of objective variables is obtained for teacher data (employee information 1 of the target company COM1 and employee information 2 of the similar company COM2). For example, when j = 3, the second variable importance of “future”, “changing spirit”, and “cooperation” is obtained.

As shown in FIG. 7, after step S303, the server 30 executes a matching level determination (S304).
Specifically, the processor 32 specifies a job applicant information database (FIG. 6) associated with the job applicant ID included in the matching request data. In the identified job seeker information database, job seeker information (an example of "target element information" and "target personal information") of the target job seeker (an example of "target element" and "target individual") to be matched Is stored.

Based on the information in the specified job applicant information database (FIG. 6) and the second variable importance calculated in step S303, the processor 32 determines each of the target companies identified by the company ID included in the matching request data and each of the target companies. Calculate matching score with job seeker.
As an example, the processor 32 may arbitrarily set information on each “index” field in the “pre-employment objective evaluation” field of the job applicant information database and the second variable importance corresponding to the index as follows. By assigning to a linear model (for example, multiple regression model), a score for each objective variable (for example, future potential, challenge spirit, and cooperation) is calculated.
The processor 32 calculates a matching score by substituting the score of each objective variable into an arbitrary statistical model (for example, a weighted estimation model).
The plurality of weights constituting the weight estimation model are determined by, for example, information in the “object variable” field of the company information database (FIG. 4). More specifically, when the information in the “target variable” field is “future”, the weight of the target variable “future” is the largest.

After step S304, the server 30 executes database update (S305).
Specifically, the processor 32 stores the matching score calculated in step S304 in the “matching score” field of the job seeker information database (FIG. 6) specified in S300.

After step S305, the server 30 executes a matching response (S306).
Specifically, the processor 32 transmits matching response data to the client device 10. The matching response data includes information (for example, job seeker ID, job seeker name, and matching score) in the job seeker information database (FIG. 6) updated in step S305.

After step S306, the client apparatus 10 performs presentation of simulation results (S102).
Specifically, the processor 12 displays the screen P102 (FIG. 8) on the display.
The screen P102 displays a job seeker ID, a job seeker name, and a matching score list A102 calculated in step S304.

  According to the present embodiment, the server 30 refers to not only information on the target company COM1 but also employee information on a similar company COM2 similar to the target company COM1, and executes matching simulation. Thereby, even when the amount of employee information of the target company COM1 (for example, the number of employees belonging to the target company COM1) is small, the accuracy of the simulation result can be improved. That is, for the target company COM1, it is possible to present the optimum job seeker APP regardless of the number of employees.

In particular, a small number of employees belonging to the target company COM1 means that there are few achievements for selecting job seekers. In other words, it is extremely difficult for companies with a small number of employees to select job seekers suitable for their own company. Similarly, it is difficult for job seekers to select a company that is suitable for themselves from companies with a small number of employees.
According to the present embodiment, not only information on a company but also information on a similar company is referred to as teacher data even for a company with a small number of employees. Thereby, it is possible to present a highly accurate simulation result of matching between a company with a small number of employees and a job seeker who wants to seek a job with a company with a small number of employees.

  In particular, in step S300, the number of items of the first variable importance displayed on the screen P101 can be suppressed by using the first mathematical model composed of a smaller number of mathematical expressions than the second mathematical model. Thereby, comparison of similar companies by a user becomes clear and easy.

  In particular, in step S303, the accuracy of the matching score obtained in step S306 can be improved by using the second mathematical model composed of a larger number of mathematical expressions than the first mathematical model.

(5) Modification A modification of the present embodiment will be described.

(5-1) Modification 1
Modification 1 will be described. Modification 1 is an example of matching simulation between a group constituting an organization and members belonging to the organization.

  An overview of Modification 1 will be described. FIG. 10 is an explanatory diagram of an outline of the first modification.

  As illustrated in FIG. 10, the server 30 according to the present embodiment executes a matching simulation between an employee EMP3 (an example of “individual”) belonging to the department DIV3 and a department DIV2 (an example of “group”).

  Employee information related to the employee EMP3 is associated with the employee EMP3.

At least one employee (an example of “member”) belongs to each of the plurality of departments DIV1 to DIV3.
Each department DIV1 to DIV3 is associated with employee information (an example of “member information”) regarding employees belonging to the department.

  In the matching simulation between the employee EMP3 and the department DIV2, the server 30 refers to the employee information of the department DIV1 similar to the department DIV2 as teacher data TD in addition to the employee information of the department DIV2.

  Thereby, even if the population of the elements of the target department to be matched is small, the accuracy of the simulation result can be improved. Specifically, even when the number of employees belonging to the department DIV2 is small (that is, the data amount of employee information of the department DIV2 is small), the simulation result (for example, the prediction result of the department to which the employee EMP3 should be assigned) ) Accuracy can be improved.

(5-2) Modification 2
Modification 2 will be described. Modification 2 is an example in which a similar company is specified in consideration of company information. FIG. 11 is an explanatory diagram of the second modification.

The server 30 of the modification 2 specifies a non-target company having company information similar to the company information of the target company COM1 before step S300 of FIG. As an example, the server 30 specifies a non-target company in which at least one of the company attribute information and the performance information (FIG. 4) of the target company 1 is the same or similar.
For example, as shown in FIG. 11, non-target companies COM3 and COM4 corresponding to employee information similar to the employee information of the target company COM1 among the companies COMn are specified as candidate companies.

In step S300 of FIG. 7, the server 30 calculates the first variable importance of the employee information 1 of the target company COM1 and the employee information 3 and 4 of the candidate companies (non-target companies COM3 and COM4).
In step S301, the server 30 identifies a similar company by comparing the first variable importance of the target company COM1 with the first variable importance of the non-target companies COM3 and COM4.
For example, as shown in FIG. 11, the non-target company COM3 similar to the target company COM1 is identified as a similar company with respect to the first variable importance.

In step S302 of FIG. 7, the server 30 creates teacher data including employee information 1 of the target company COM1 and employee information 3 of the similar company COM3 (FIG. 11).
In step S303, the server 30 calculates the second variable importance of the teacher data (employee information 1 of the target company COM1 and employee information 3 of the similar company COM3).

  According to the second modification, a similar company is selected from candidate companies whose company information is closer to the target company. Therefore, compared with the present embodiment, the error between the first variable importance of the target company and the second variable importance of the teacher data is reduced. Thereby, the precision of a simulation result can be improved more.

(5-3) Modification 3
Modification 3 will be described. Modification 3 is a modification regarding the start condition of the matching simulation (FIG. 7).

The server 30 according to the third modification may execute a matching simulation in response to the matching request from the job seeker APP.
In this case, the server 30 presents a matching score for each company to the job seeker APP.
Thereby, job seeker APP can know the company suitable for himself.

The server 30 of the third modification may execute a matching simulation every time a job applicant APP is newly registered (that is, a new record is added to the job applicant information database in FIG. 6).
Thereby, the company can know the job applicant APP suitable for the company every time the job applicant APP who desires the company is registered.
In particular, when a job applicant APP whose matching score between the company and the job applicant APP is a predetermined value or more is specified, the server 30 notifies the company of job applicant information related to the job applicant APP (for example, email transmission). You may do it. Accordingly, the company can easily know that the job applicant APP suitable for the company has been registered.

(5-4) Modification 4
Modification 4 will be described. The modification 4 is an example in which the matching score of each company is presented to the job seeker. FIG. 12 is a diagram illustrating an example of a screen displayed on the client device in the information processing according to the fourth modification.

  As shown in FIG. 12, the processor 12 displays a screen P200 (FIG. 12) on the display in step S100 (FIG. 7).

Screen P200 includes an operation object B100 and an input field object F200.
The input field object F200 is an object that receives an input of a job seeker ID.

When a user (for example, a job seeker) inputs his job seeker ID in the input field object F200 and designates the operation object B100, the processor 12 transmits matching request data to the server 30.
The matching request data includes the company ID input to the input field object F200.

  In step S304, the processor 12 calculates a matching score between the job seeker identified by the job seeker ID included in the matching request data and each target company.

  In step S102 (FIG. 7), the processor 12 displays the screen P202 (FIG. 12) on the display.

After step S306 (FIG. 7), the client apparatus 10 executes presentation of simulation results (S102).
Specifically, the processor 12 displays the screen P202 (FIG. 12) on the display.
The screen P202 displays a company ID, a company name, and a matching score list A202 calculated in step S304.

  According to the modified example 4, a highly accurate simulation result of matching with the company can be presented to a job seeker of a company with a small number of employees.

(6) Summary of this embodiment This embodiment is summarized.

The first aspect of this embodiment is
An information processing apparatus (for example, server 30) that performs matching between an individual and an organization,
Compare member information related to members (for example, employees) belonging to the target organization (for example, target company COM1) to be matched with member information related to members belonging to non-target organizations other than the target organization. Thus, a means (for example, the processor 32 that executes the process of step S301) for specifying at least one similar organization (for example, similar company COM2) similar to the target organization from among the non-target organizations is provided,
Means (for example, a processor 32 that executes the process of step S302) for creating teacher data TD including member information related to members belonging to the target organization and member information related to members belonging to the similar organization is provided. ,
Means for determining the matching level between the target individual and the target organization based on the target personal information related to the target target to be matched (for example, job seeker APP) and the teacher data TD (for example, the process of step S304). A processor 32) for executing,
Information processing device.

  According to the first aspect, the teacher data TD includes not only the target company COM1 but also employee information of the similar company COM2. Thereby, even when the number of employees of the target company COM1 is small, it is possible to improve the decrease in the accuracy of the simulation result.

In the second aspect of this embodiment,
The means to identify
Calculate the first variable importance of the member information variable,
A similar organization is specified by comparing the first variable importance of the target organization with the first variable importance of the organization other than the target organization.

  According to the 2nd aspect, the specific precision of a similar structure | tissue can be improved. As a result, the accuracy of the simulation result is further improved.

In the third aspect of this embodiment,
The means to determine
Calculating the second variable importance of the member information variable included in the teacher data TD;
The matching level is determined by comparing the second variable importance level with the target personal information.

  According to the 3rd aspect, the specific precision of a similar structure | tissue can be improved. As a result, the accuracy of the simulation result is further improved.

In the fourth aspect of this embodiment,
Means for identifying candidate organizations (for example, non-target companies COM3 and COM4) that are candidates for similar organizations among non-target organizations by comparing the organization information about the target organization and the organization information about the non-target organization. Prepared,
A means for identifying a similar organization is to compare member information related to members belonging to the target organization with member information related to members belonging to the candidate organization, so that similar organizations (for example, Identify similar companies COM3).

  According to the fourth aspect, a similar company is selected from candidate companies with similar company information. Thereby, the precision of a simulation result can be improved more.

In the fifth aspect of this embodiment,
The member information includes at least one of employee attribute information regarding attributes of employees belonging to the company, objective evaluation information before entering the company regarding the results of the test for the employees, and evaluation information regarding the evaluation of the employees,
The target personal information is job seeker attribute information regarding the attributes of job seekers who wish to apply for a company, and objective evaluation information before joining the company regarding the results of examinations for job seekers.

  According to the fifth aspect, matching between a company (particularly a small and medium-sized company with a small number of employees) and a job seeker seeking a job with the company can be executed with high accuracy.

  In the sixth aspect of the present embodiment, a means (for example, step S306) of presenting a matching level with each of a plurality of target individuals (for example, job seekers) to a target organization (for example, a person in charge of an abstract company). A processor 32) for performing the processing.

  In the seventh aspect of the present embodiment, there is provided means for presenting a matching level with each of a plurality of target organizations (for example, abstract companies) to a target individual (for example, job seeker).

The eighth aspect of this embodiment is
An organization contains multiple groups,
Member information includes information about the group to which the member belongs,
The means for specifying the non-target organization by comparing member information related to members belonging to the target group to be matched with member information related to members belonging to non-target groups other than the target group. Identify at least one similar group that is similar to the target organization,
The means for creating creates teacher data including member information relating to members belonging to the target group and member information relating to members belonging to the similar group,
A matching level between the target individual and the target group is determined based on the target personal information regarding the target individual and the teacher data.

  According to the eighth aspect, matching between a plurality of groups included in an organization and members can be performed with high accuracy.

In the ninth aspect of the present embodiment,
The member information is employee attribute information related to the attributes of employees belonging to the company.
The target personal information is employee attribute information of an employee who is assigned to a department.

  According to the ninth aspect, matching between a department (particularly a department with a small number of employees) and an employee who wishes to transfer to the department can be executed with high accuracy.

The tenth aspect of this embodiment is
An information processing apparatus (for example, server 30) that performs matching between a set composed of a plurality of elements and each element,
By comparing the element information of the elements constituting the target set G1 to be matched with the element information on the elements of the non-target sets G2 to G3 other than the target set, from among the non-target sets G2 to G3, Means for specifying a similar set G2 similar to the target set G1,
Means for creating teacher data TD including element information relating to elements of the target set G1 and element information relating to elements of the similar set G2,
Means for determining a matching level between the target element TE and the target set G1 based on the target element information regarding the target element TE to be matched and the teacher data TD;
Information processing apparatus.

  According to the tenth aspect, as in the first aspect, in the matching simulation between the set including a plurality of elements and the target element, the accuracy of the simulation result is improved even when the number of elements included in the set is small. Can be improved.

(7) Other variations

  The storage device 11 may be connected to the client device 10 via the network NW. The storage device 31 may be connected to the server 30 via the network NW.

Although this embodiment mainly shows an example of an individual and a company, this embodiment can also be applied to the following example.
・ Matching part-time job and store location ・ Matching worker and factory ・ Matching patient and hospital ・ Matching student and school ・ Matching student and class ・ Matching care recipient and care facility Matching workers and hospitals

In the above-described embodiment, the multiple regression analysis model is exemplified as the first mathematical model used in step S300 in FIG. 7 and the multinomial logit model is exemplified as the second mathematical model used in step S303. The mathematical model is not limited to this example.
An arbitrary mathematical model may be used as the first analysis model. In this case, it is preferable to use a mathematical model composed of a larger number of mathematical formulas than the first analytical model as the second analytical model.
In particular, the first mathematical model is preferably an arbitrary generalized linear model. In this case, the second mathematical model is preferably a generalized linear model composed of a larger number of mathematical formulas than the first mathematical model.

  Step S101 in FIG. 7 can be omitted. In this case, step S301 is executed based on the first variable importance calculated in step S300. Since the screen P101 in FIG. 8 is not displayed, when the user inputs the company ID in the input field object F100 and designates the operation object B100, the server 30 executes Steps S300 to S306. Accordingly, the screen P102 is displayed on the display of the client device 10 after the screen P100.

  As mentioned above, although embodiment of this invention was described in detail, the scope of the present invention is not limited to said embodiment. The above-described embodiment can be variously improved and changed without departing from the gist of the present invention. Moreover, said embodiment and modification can be combined.

1: Information processing system 10: Client device 11: Storage device 12: Processor 13: Input / output interface 14: Communication interface 30: Server 31: Storage device 32: Processor 33: Input / output interface 34: Communication interface

Claims (10)

An information processing device that performs matching between an individual and an organization,
By comparing member information relating to members belonging to the target organization to be matched with member information relating to members belonging to non-target organizations other than the target organization, And means for identifying at least one similar tissue similar to the target tissue,
Means for creating teacher data including member information relating to members belonging to the target organization and member information relating to members belonging to the similar organization;
An information processing apparatus comprising: means for determining a matching level between the target individual and the target organization based on target personal information regarding the target target to be matched and the teacher data. The means for specifying is
Calculating the first variable importance of the member information variable;
Identifying the similar organization by comparing the first variable importance of the target organization and the first variable importance of the organization other than the target organization;
The information processing apparatus according to claim 1. The means for determining is
Calculating the second variable importance of the member information variable included in the teacher data;
The matching level is determined by comparing the second variable importance with the target personal information.
The information processing apparatus according to claim 2. A means for identifying candidate organizations that are candidates for the similar organization among the non-target organizations by comparing organization information related to the target organizations and organization information about the non-target organizations;
The means for specifying the similar organization compares the member information related to the members belonging to the target organization and the member information related to the members belonging to the candidate organization, thereby comparing the similar information from the candidate organizations. Identify the organization,
The information processing apparatus according to claim 1. The member information includes at least one of employee attribute information related to attributes of employees belonging to a company, evaluation information related to a result of a test for the employees, and evaluation information related to evaluation of the employees,
The target personal information is job seeker attribute information related to job seeker attributes that desire the company, and evaluation information related to the results of the test for the job seeker.
The information processing apparatus according to claim 1. Means for presenting a matching level with each of a plurality of target individuals to the target organization;
The information processing apparatus according to claim 1. A means for presenting a matching level with each of a plurality of target organizations to the target individual;
The information processing apparatus according to claim 1. The organization includes a plurality of groups,
The member information includes information about a group to which the member belongs,
The identifying means compares the member information related to members belonging to a target group to be matched with member information related to members belonging to a non-target group other than the target group, Identifying at least one similar group similar to the target organization from non-target organizations;
The creating means creates teacher data including member information relating to members belonging to the target group and member information relating to members belonging to the similar group,
Determining a matching level between the target individual and the target group based on the target personal information on the target individual and the teacher data;
The information processing apparatus according to claim 1. The group is a department included in the company,
The member information is employee attribute information regarding attributes of employees belonging to the company,
The target personal information is employee attribute information of an employee to be assigned to the department.
The information processing apparatus according to claim 8. Program for causing a computer to function as each means according to any one of claims 1-9.

Images