Estimation device, estimation method, and estimation program

Abstract

A training device (100) includes an acquisition unit (121), a feature extraction unit (122), and a model construction unit (123). The acquisition unit (121) acquires data relating to personnel. The feature extraction unit (122) extracts a feature amount from the data relating to personnel acquired by the acquisition unit (121). The model construction unit (123) uses the feature amount extracted by the feature extraction unit (122) to construct a model for estimating a probability relating to personnel reassignment.

Description

[Technical Field]

[0001] The present invention provides recommendation fixed device , recommendation Sadakata Law and estimation programs. [Background technology]

[0002] Traditionally, personnel transfer proposals are created manually by human resources personnel. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] NTTLS, "Basic Knowledge of Human Resource Development, Part 7: Career Design," https: / / hr.nttls.co.jp / column / knowledge / step1 / detail-07.html Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional technology has the problem of being unable to efficiently create personnel transfer plans. For example, creating personnel transfer plans requires identifying the characteristics of each person, department, and job type, and considering the wishes of the person, so it requires human resources personnel with specialized knowledge, skills, and experience to spend a lot of time on the process.

[0005] The present invention has been made in view of the above, and is capable of efficiently creating personnel transfer proposals. recommendation fixed device , recommendation Sadakata Law The purpose of this document is to provide a method and estimation program. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object,The estimation device is characterized by having an acquisition unit that acquires personnel-related data, a feature extraction unit that extracts features from the personnel-related data acquired by the acquisition unit, an estimation unit that estimates the probability of personnel changes using the features extracted by the feature extraction unit as input data, and a creation unit that creates personnel change proposals based on the probabilities of personnel changes estimated by the estimation unit. [Effects of the Invention]

[0008] According to the present invention, it is possible to efficiently create personnel transfer proposals. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of a learning device. [Figure 2] FIG. 2 is a diagram illustrating an example of a model construction process of the learning device. [Figure 3] FIG. 3 is a block diagram illustrating an example of the configuration of the estimation device. [Figure 4] FIG. 4 is a diagram illustrating an example of the estimation process of the estimation device. [Figure 5] FIG. 5 is a diagram illustrating an example of the creation process of the estimation device. [Figure 6] FIG. 6 is a diagram illustrating an example of the creation process of the estimation device. [Figure 7] FIG. 7 is a flowchart showing an example of the flow of the learning process of the learning device. [Figure 8] FIG. 8 is a flowchart showing an example of the flow of the estimation process of the estimation device. [Figure 9] FIG. 9 is a diagram illustrating an example of a computer that executes a learning program or an estimation program. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, with reference to the drawings, embodiments of a learning device, an estimation device, a learning method, an estimation method, a learning program, and an estimation program according to the present application will be described in detail. Note that the present invention is not limited to these embodiments. Furthermore, in the description of the drawings, identical parts are denoted by the same reference numerals, and duplicated explanations will be omitted.

[0011] [Summary of the Invention] The learning device according to this embodiment extracts features from acquired personnel-related data and constructs a model that estimates the probability of personnel changes.

[0012] In addition, the estimation device according to this embodiment extracts features from the acquired personnel data, inputs the features into a trained model that estimates the probability of personnel transfers, estimates the probability of personnel transfers, and creates personnel transfer proposals.

[0013] [Learning device configuration] First, the configuration of the learning device will be described using Fig. 1. As shown in Fig. 1, the learning device 100 has a communication unit 110, a control unit 120, and a storage unit 130. Note that these units may be distributed and held by multiple devices. The processing of these units will be described below.

[0014] The communication unit 110 is realized by a NIC (Network Interface Card) or the like, and enables communication between an external device and the control unit 120 via a telecommunication line such as a LAN (Local Area Network) or the Internet. For example, the communication unit 110 enables communication between the external device and the control unit 120.

[0015] The storage unit 130 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The information stored in the storage unit 130 includes, for example, personnel-related data, feature values, data related to machine learning algorithms, training data, trained models, and other information necessary for building a model for estimating the probability of personnel transfers. For example, the personnel-related data stored in the storage unit 130 includes basic information, qualification information, training information, family information, affiliation information, intention information, supervisor judgment information, department information, region information, transfer history, career history, evaluations, interview records, and other data held by the personnel department. The information stored in the storage unit 130 is not limited to the information described above.

[0016] The control unit 120 is realized using a CPU (Central Processing Unit), an NP (Network Processor), an FPGA (Field Programmable Gate Array), etc., and executes a processing program stored in a memory. As shown in Fig. 1, the control unit 120 has an acquisition unit 121, a feature extraction unit 122, and a model construction unit 123. Each unit of the control unit 120 will be described below.

[0017] The acquisition unit 121 acquires personnel-related data. For example, the acquisition unit 121 acquires, as personnel-related data, supervisor judgment information such as the characteristics of an employee and specific opinions on whether or not to transfer. Furthermore, for example, the acquisition unit 121 acquires, as personnel-related data, preference information such as the employee's desired work. Here, the personnel-related data acquired by the acquisition unit 121 includes basic information, qualification information, training information, relative information, affiliation information, preference information, supervisor judgment information, department information, region information, transfer history, career history, evaluations, interview records, and other data held by the personnel department.

[0018] The feature extraction unit 122 extracts feature amounts from the personnel-related data acquired by the acquisition unit 121. For example, the feature extraction unit 122 extracts feature amounts by quantifying the supervisor judgment information acquired by the acquisition unit 121. For example, the feature extraction unit 122 performs linguistic analysis on the text data of the supervisor judgment information, generates a feature vector from the presence or absence of specific keywords and the content of the sentence, and extracts feature amounts.

[0019] The model construction unit 123 constructs a model that estimates the probability of a personnel transfer using the feature amounts extracted by the feature extraction unit 122. For example, the model construction unit 123 constructs a model that estimates the probability of whether or not a personnel transfer will occur using the feature amounts extracted by the feature extraction unit 122. Also, for example, the model construction unit 123 constructs a model that estimates the probability of a department to which a personnel transfer will occur using the feature amounts extracted by the feature extraction unit 122. Also, for example, the model construction unit 123 constructs a model that estimates the probability of a region to which a personnel transfer will occur using the feature amounts extracted by the feature extraction unit 122.

[0020] [Model building process] Next, the model construction process by the learning device 100 will be described with reference to Fig. 2. First, the acquisition unit 121 acquires personnel-related data, such as intentions, considerations, and qualifications registered by employees and their superiors, as well as personnel-related data, such as transfer history, career history, evaluations, interview records, and other data held by the personnel department. Next, the feature extraction unit 122 extracts features by quantifying the personnel-related data.

[0021] The model construction unit 123 then constructs a model using the personnel-related data that has been characterized by the feature extraction unit 122. At this time, the model construction unit 123 can use personnel-related data from any period depending on the purpose, such as personnel-related data from the previous fiscal year, for learning. The model construction unit 123 uses the features extracted by the feature extraction unit 122 to construct a model that estimates the probability of whether or not there will be a personnel transfer, a model that estimates the probability of the department to which the personnel will be transferred, and a model that estimates the probability of the region to which the personnel will be transferred.

[0022] For example, when constructing a classification model that estimates whether or not there will be a transfer in the following year, the model construction unit 123 defines a flag as "transfer" if the affiliation (region, department, section) in year N is different from the affiliation (region, department, section) in year N+1, and defines a flag as "current position" if they are the same, and constructs a model by setting this flag as the objective variable and learning.

[0023] Furthermore, for example, when constructing a classification model that predicts departments to which employees will be transferred in the following year, the model construction unit 123 constructs the model by setting a certain year as year N and the affiliation (department / section) in year N+1 as the objective variable and learning it.

[0024] Furthermore, for example, when constructing a classification model that predicts the region of transfer in the following year, the model construction unit 123 constructs the model by setting a certain year as year N, and setting the affiliation (region) in year N+1 as the objective variable, and learning.

[0025] [Configuration of the estimation device] Next, the configuration of the estimation device will be described with reference to Fig. 3. As shown in Fig. 3, the estimation device 200 has a communication unit 210, a control unit 220, and a storage unit 230. Note that these units may be held in a distributed manner in multiple devices. The processing of these units will be described below.

[0026] The communication unit 210 is realized by a NIC (Network Interface Card) or the like, and enables communication between an external device and the control unit 220 via an electric communication line such as a LAN (Local Area Network) or the Internet. For example, the communication unit 210 enables communication between the external device and the control unit 220.

[0027] The storage unit 230 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. Information stored in the storage unit 230 includes, for example, personnel-related data, feature values, data related to machine learning algorithms, training data, trained models, other information necessary for estimating the probability of personnel transfers, rules for creating personnel transfer proposals, and other information necessary for creating personnel transfer proposals. The personnel-related data stored in the storage unit 230 includes basic information, held qualification information, training information, relative information, affiliation information, intention information, supervisor judgment information, department information, region information, transfer history, career history, evaluations, interview records, and other data held by the personnel department. Note that the information stored in the storage unit 230 is not limited to the information described above.

[0028] The control unit 220 is realized using a CPU (Central Processing Unit), an NP (Network Processor), an FPGA (Field Programmable Gate Array), etc., and executes a processing program stored in a memory. As shown in Fig. 3, the control unit 220 has an acquisition unit 221, a feature extraction unit 222, an estimation unit 224, and a creation unit 225. Each unit of the control unit 220 will be described below.

[0029] The acquisition unit 221 acquires personnel-related data. For example, the acquisition unit 221 acquires, as personnel-related data, supervisor judgment information such as the characteristics of an employee and specific opinions on whether or not to transfer. Furthermore, for example, the acquisition unit 221 acquires, as personnel-related data, preference information such as the employee's desired work. Here, the personnel-related data acquired by the acquisition unit 221 includes basic information, qualification information, training information, relative information, affiliation information, preference information, supervisor judgment information, department information, region information, transfer history, career history, evaluations, interview records, and other data held by the personnel department.

[0030] The feature extraction unit 222 extracts feature amounts from the personnel-related data acquired by the acquisition unit 221. For example, the feature extraction unit 222 extracts feature amounts by quantifying the supervisor judgment information acquired by the acquisition unit 221. For example, the feature extraction unit 222 performs linguistic analysis on the text data of the supervisor judgment information, generates a feature vector from the presence or absence of specific keywords and the content of the sentence, and extracts feature amounts.

[0031] The estimation unit 224 inputs the feature amounts extracted by the feature extraction unit 222 as input data into a trained model that estimates the probability of personnel transfers, and estimates the probability of personnel transfers. For example, the estimation unit 224 inputs the feature amounts extracted by the feature extraction unit 222 as input data into a trained model that estimates the probability of personnel transfers, and estimates one or more of the probability of whether or not there will be a personnel transfer, the probability of the department to which the personnel will be transferred, and the probability of the region to which the personnel will be transferred.

[0032] The creation unit 225 creates a personnel change plan based on the probability of a personnel change estimated by the estimation unit 224. For example, the creation unit 225 creates a personnel change plan in accordance with a predetermined rule based on the probability of a personnel change estimated by the estimation unit 224. The specific processing performed by the creation unit 225 will be described later in the creation processing section.

[0033] [Estimation process] Next, the estimation process performed by the estimation device 200 will be described with reference to Fig. 4. First, the acquisition unit 221 acquires data related to personnel. Next, the feature extraction unit 222 extracts features and converts the data related to personnel into features.

[0034] The estimation unit 224 then estimates the probability of a personnel transfer using the personnel-related data that has been characterized by the feature extraction unit 222. For example, the estimation unit 224 outputs a transfer presence / absence score as the probability of whether or not a personnel transfer will occur. Furthermore, for example, the estimation unit 224 outputs a transfer department prediction result as the probability of the department to which the personnel will be transferred. Furthermore, for example, the estimation unit 224 outputs a transfer region prediction result as the probability of the region to which the personnel will be transferred. In this case, the estimation unit 224 can use personnel-related data for any period depending on the purpose, such as personnel-related data for the current fiscal year, for the estimation.

[0035] [Create Process] Next, the creation process by the estimation device 200 will be described with reference to Figs. 4 to 6. First, in Fig. 4, the creation unit 225 derives a transfer department score using the probability related to the department to which the personnel will be transferred (transfer department prediction result) and the probability related to the area to which the personnel will be transferred (transfer area prediction result) output by the estimation unit 224.

[0036] More specifically, the creation unit 225 scores the results of the transfer department prediction and the transfer region prediction using a method such as harmonic mean, and derives a transfer department score that takes into account the transfer department and the transfer region. At this time, the creation unit 225 may process a combination of a transfer department and a transfer region that does not exist in the organization list, etc., as an exception to the score.

[0037] 5, the creation unit 225 makes a provisional decision on whether or not to transfer using the possibility of whether or not to transfer (transfer presence / absence score). Here, the provisional decision on whether or not to transfer made by the creation unit 225 means that, for employees whose transfer presence / absence has not yet been decided by the personnel department, they are provisionally decided as transfer targets in descending order of the probability of whether or not to transfer will occur estimated by the estimation unit 224 (transfer presence / absence score) until a predetermined number or a predetermined percentage is reached.

[0038] Next, the creation unit 225 provisionally determines the transfer department using the possibility of a personnel transfer (transfer score) and the transfer department score. Here, the provisional determination of the transfer department made by the creation unit 225 refers to setting transfer slots for each category, such as department, administrative / technical category, business category, and position, for employees for whom a transfer provisional decision has been made, and provisionally determining the transfer destination department. At this time, if the number of transfer destination slots is odd, the creation unit 225 may set employees with low transfer scores as ineligible for transfer. Alternatively, the creation unit 225 may set the transfers in order of employees with high transfer scores to departments with high transfer department scores and available transfer slots.

[0039] Furthermore, the creation unit 225 may apply individual rules different from the above rules when provisionally determining whether or not to transfer an employee or provisionally determining the department to transfer to. For example, when multiple employees are transferred from the same department, the creation unit 225 may set the department to which the employees will be transferred so that each employee will be transferred to a different department. For example, the creation unit 225 may set the department to which the employee to be transferred has a relative so that the department to which the employee is transferred will not be the department to which the employee is transferred. For example, the creation unit 225 may set the department to which the employee to be transferred has a relative so that the department to which the employee to be transferred has a previous job will not be the department to which the employee to be transferred will be the department to which the employee to be transferred will be transferred. Note that the individual rules applied by the creation unit 225 can be added and applied uniquely for each organization.

[0040] Then, the creation unit 225 outputs the personnel transfer proposal (FIG. 6). Here, the creation unit 225 may repeat the above process until all of the personnel department decisions made by personnel personnel are finalized.

[0041] [flowchart] Next, the flow of the model construction process by the learning device 100 will be described with reference to Fig. 7. Note that the following steps S11 to S13 may be executed in a different order. Also, some of the following steps S11 to S13 may be omitted.

[0042] First, the acquisition unit 121 acquires personnel-related data (step S11). For example, the acquisition unit 121 acquires supervisor judgment information as personnel-related data. Here, the personnel-related data acquired by the acquisition unit 121 includes basic information, qualification information, training information, relative information, affiliation information, intention information, supervisor judgment information, department information, region information, transfer history, career history, evaluation, interview record, and other data held by the personnel department.

[0043] Next, the feature extraction unit 122 extracts feature amounts from the personnel-related data acquired by the acquisition unit 121 (step S12). For example, the feature extraction unit 122 extracts feature amounts by quantifying the superior judgment information acquired by the acquisition unit 121.

[0044] Then, the model construction unit 123 constructs a model that estimates the probability of personnel transfer using the feature amounts extracted by the feature extraction unit 122 (step S13). For example, the model construction unit 123 constructs a model that estimates the probability of personnel transfer destination regions using the feature amounts extracted by the feature extraction unit 122.

[0045] [flowchart] Next, the flow of the estimation process by the estimation device 200 will be described with reference to Fig. 8. Note that the following steps S11 to S14 may be executed in a different order. Also, some of the following steps S11 to S14 may be omitted.

[0046] First, the acquisition unit 221 acquires personnel-related data (step S11). For example, the acquisition unit 221 acquires supervisor judgment information as personnel-related data. Here, the personnel-related data acquired by the acquisition unit 221 includes basic information, qualification information, training information, relatives information, affiliation information, intention information, supervisor judgment information, department information, region information, transfer history, career history, evaluation, interview records, and other data held by the personnel department.

[0047] Next, the feature extraction unit 222 extracts feature amounts from the personnel-related data acquired by the acquisition unit 221 (step S12). For example, the feature extraction unit 222 extracts feature amounts by quantifying the superior judgment information acquired by the acquisition unit 221.

[0048] Then, the estimation unit 224 inputs the feature amount extracted by the feature extraction unit 223 as input data into a trained model that estimates the probability of personnel transfer, and estimates the probability of personnel transfer (step S13). For example, the estimation unit 224 inputs the feature amount extracted by the feature extraction unit 223 as input data into a trained model that estimates the probability of personnel transfer, and estimates the probability of the department to which the personnel will be transferred.

[0049] Then, the creating unit 225 creates a personnel change plan based on the probability of personnel change estimated by the estimating unit 224 (step S14).

[0050] [effect] The learning device 100 according to the embodiment includes an acquisition unit 121, a feature extraction unit 122, and a model construction unit 123. The acquisition unit 121 acquires personnel-related data. The feature extraction unit 122 extracts features from the personnel-related data acquired by the acquisition unit 121. The model construction unit 123 uses the features extracted by the feature extraction unit 122 to construct a model that estimates the probability of personnel changes.

[0051] As a result, the learning device 100 can convert personnel-related data into features and build a model that estimates the probability of personnel changes, thereby enabling the efficient creation of personnel change plans. In other words, the learning device 100 can estimate the status of future personnel changes from data on past personnel changes, thereby making it possible to efficiently create personnel change plans.

[0052] The estimation device 200 according to the embodiment includes an acquisition unit 221, a feature extraction unit 222, an estimation unit 224, and a creation unit 225. The acquisition unit 221 acquires personnel-related data. The feature extraction unit 222 extracts features from the personnel-related data acquired by the acquisition unit 221. The estimation unit 224 estimates the probability of a personnel change using the features extracted by the feature extraction unit 222 as input data. The creation unit 225 creates a personnel change plan based on the probability of a personnel change estimated by the estimation unit 224.

[0053] This allows the estimation device 200 to estimate the probability of personnel changes from personnel-related data and efficiently create personnel change proposals.

[0054] The estimation unit 224 in the estimation device 200 according to the embodiment estimates one or more of the probability of whether or not there will be a personnel transfer, the probability of the department to which the personnel transfer will be made, and the probability of the region to which the personnel transfer will be made. This allows the estimation device 200 to estimate whether or not there will be a personnel transfer, the department to which the personnel transfer will be made, and the region to which the personnel transfer will be made, and to efficiently create a personnel transfer plan.

[0055] The creation unit 225 in the estimation device 200 according to the embodiment creates personnel change proposals in accordance with predetermined rules. This allows the estimation device 200 to efficiently create personnel change proposals by using the estimation results of the trained model and the rule base.

[0056] [System configuration, etc.] Furthermore, the components of each device shown in the figure are conceptual functional units and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of each device can be functionally or physically distributed and integrated in any unit depending on various loads and usage conditions. For example, each processing function performed by each device can be realized, in whole or in part, by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

[0057] Furthermore, among the processes described in this embodiment, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method.In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

[0058] [program] It is also possible to create a program written in a computer-executable language that describes the processing performed by the learning device 100 or the estimation device 200 described in the above embodiments. In this case, the same effects as those of the above embodiments can be obtained by having a computer execute the program. Furthermore, such a program may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read and executed by a computer to achieve processing similar to that of the above embodiments.

[0059] 9 is a diagram showing an example of a computer that executes a learning program or an estimation program. As shown in FIG. 9, a computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0060] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120. The video adapter 1060 is connected to, for example, a display 1130.

[0061] 9, the hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. The tables described in the above embodiments are stored in the hard disk drive 1090 or the memory 1010, for example.

[0062] The learning program or estimation program is stored in the hard disk drive 1090, for example, as a program module in which instructions to be executed by the computer 1000 are written. Specifically, the hard disk drive 1090 stores a program module 1093 in which each process executed by the computer 1000 described in the above embodiment is written.

[0063] Furthermore, data used in the learning process by the learning program or the estimation process by the estimation program is stored as program data, for example, in the hard disk drive 1090. Then, the CPU 1020 reads out the program module 1093 and the program data 1094 stored in the hard disk drive 1090 into the RAM 1012 as necessary, and executes each of the above-described procedures.

[0064] The program module 1093 and program data 1094 related to the learning program or estimation program are not limited to being stored in the hard disk drive 1090, but may be stored in a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 related to the control program may be stored in another computer connected via a network such as a LAN (Local Area Network) or a WAN (Wide Area Network), and read by the CPU 1020 via the network interface 1070.

[0065] [others] Although various embodiments have been described in detail herein with reference to the drawings, these embodiments are merely examples and are not intended to limit the present invention. The features described herein can be realized in various ways, including various modifications and improvements based on the knowledge of those skilled in the art.

[0066] Furthermore, the above-mentioned "module (-er suffix, -or suffix)" can be read as a unit, means, circuit, etc. For example, a communication module, a control module, and a storage module can be read as a communication unit, a control unit, and a storage unit, respectively. [Explanation of symbols]

[0067] 100 Learning Device 110 Communications Department 120 control section 121 Acquisition Department 122 Feature Extraction Unit 123 Model Construction Department 200 Estimation device 210 Communications Department 220 Control Unit 221 Acquisition Department 222 Feature Extraction Unit 224 Estimation Department 225 Creation Department 230 Storage section

Claims

1. an acquisition unit that acquires personnel-related data; a feature extraction unit that extracts features from the personnel data acquired by the acquisition unit; an estimation unit that estimates a probability of personnel transfer using the feature quantity extracted by the feature extraction unit as input data; a creation unit that creates a personnel transfer plan based on the probability of personnel transfer estimated by the estimation unit; An estimation device comprising:

2. 2. The estimation device according to claim 1, wherein the estimation unit estimates one or more of the probability of whether or not there will be a personnel transfer, the probability of the department to which the personnel transfer will be made, and the probability of the region to which the personnel transfer will be made.

3. The estimation device according to claim 1 , wherein the creation unit creates a personnel transfer plan in accordance with a predetermined rule.

4. An estimation method implemented by an estimation device, an acquisition step of acquiring personnel-related data; a feature extraction step of extracting features from the personnel data acquired by the acquisition step; an estimation step of estimating a probability of personnel transfer using the feature quantities extracted by the feature extraction step as input data; a creation step of creating a personnel transfer plan based on the probability of personnel transfer estimated by the estimation step; An estimation method comprising:

5. An estimation program for causing a computer to function as the estimation device according to any one of claims 1 to 3.

Images