A system that outputs information related to the pricing of personnel.

Abstract

To provide a system which outputs information for determining whether or not the price is appropriate according to attributes of human resources.SOLUTION: A system for outputting information on a price related to human resource, is configured to: acquire, as an input, a human resource dataset including information related to a plurality of human resources, the human resource dataset being formed by associating information identifying a cluster to which each of the human resources belongs, the price of the human resource, and a first attribute value other than the price of the human resource; acquire, as an input, a price of a new human resource and a first attribute value; determine a cluster of the new human resource, based on the first attribute value of the new human resource; and output a result of determination regarding the price of the new human resource on the basis of the price of the new human resource and a distribution of prices of human resources belonging to the cluster determined for the new human resource.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to a system for outputting information regarding the price of human resources.

Background Art

[0002] In organizations such as companies, analysis is performed by clustering a large number of human resources. For example, Patent Document 1 describes a system for determining whether to hire a job applicant based on clusters of human resources.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the conventional technology has a problem that it is difficult to appropriately evaluate the price of newly recruited human resources. In particular, it is difficult to evaluate an appropriate price according to the attributes of human resources.

[0005] The present invention has been made to solve such problems, and an object thereof is to provide a system for outputting information for determining whether a price is appropriate according to the attributes of human resources.

Means for Solving the Problems

[0006] In an example of a system for outputting information regarding the price of human resources according to the present invention, the system acquires, as an input, a human resource dataset including information regarding a plurality of human resources, and the human resource dataset associates, for each human resource, information for identifying the cluster to which the human resource belongs, the price of the human resource, and a first attribute value other than the price of the human resource. The system is - Obtain the price and primary attribute value of the new employee as input, - Based on the first attribute value of the new personnel, the cluster of the new personnel is determined. - Based on the distribution of prices of personnel belonging to the determined cluster of the new personnel and the price of the new personnel, a determination result regarding the price of the new personnel is output.

[0007] In one example, the distribution is in the distribution of prices of personnel belonging to each cluster. -upper limit, -lower limit, - At least one of the quartiles, - Average value, It contains information that represents at least one of the following.

[0008] In one example, the determination result includes a message indicating whether the price of the new employee falls within a predetermined range from the average or median price of employees in the cluster in which the new employee was determined. [Effects of the Invention]

[0009] The system according to the present invention can output information for determining whether the price is appropriate based on the attributes of the personnel. [Brief explanation of the drawing]

[0010] [Figure 1] A diagram showing the configuration and processing contents of a human resource management system 100 according to Embodiment 1 of the present invention. [Figure 2] Overview of the processing of the clustering device 10 in Figure 1. [Figure 3] An example of personnel evaluation information 53 in Figure 1. [Modes for carrying out the invention]

[0011] Hereinafter, embodiments of the present invention will be described based on the attached drawings. [Embodiment 1] Figure 1 is a diagram showing the configuration and processing contents of a human resource management system 100 according to Embodiment 1 of the present invention. The human resource management system 100 is a system that outputs information related to the price of human resources. The human resource management system 100 comprises a clustering device 10, a price reasonableness evaluation device 20, a new human resource registration device 30, and a machine learning model construction device 40.

[0012] The clustering device 10, the price reasonableness evaluation device 20, the new personnel registration device 30, and the machine learning model construction device 40 each have a hardware configuration as a known computer, and include, for example, computing means and storage means. The computing means includes, for example, a processor, and the storage means includes, for example, storage media such as semiconductor memory devices and magnetic disk devices. Some or all of the storage media may be non-transitory storage media.

[0013] Furthermore, the clustering device 10, the price reasonableness evaluation device 20, the new personnel registration device 30, and the machine learning model construction device 40 each include input means and output means. The input means include, for example, input devices such as a keyboard and a mouse. The output means include, for example, output devices such as a display and a printer. The input means and output means may also include communication devices such as a network interface.

[0014] The storage means of the clustering device 10, the price reasonableness evaluation device 20, the new personnel registration device 30, and the machine learning model construction device 40 may each store a program. Each device may perform the functions described in this embodiment by executing this program through the processor of each device.

[0015] In the clustering device 10, the calculation means constitutes the information processing unit 11, and the output means constitutes the output unit 13. The storage means constitutes the personnel information storage unit 14 and the personnel data set storage unit 15.

[0016] In the price validity evaluation device 20, the arithmetic means constitutes the information processing unit 21, the input means constitutes the input unit 22, and the output means constitutes the output unit 23. Further, the storage means constitutes the human resource data set storage unit 25, the parameter storage unit 26, and the human resource evaluation information storage unit 27.

[0017] In the new human resource registration device 30, the output means constitutes the output unit 33. Further, the storage means constitutes the new human resource information storage unit 34.

[0018] In the machine learning model construction device 40, the arithmetic means constitutes the information processing unit 41, the input means constitutes the input unit 42, and the storage means constitutes the human resource data set storage unit 44 and the machine learning model storage unit 45.

[0019] Fig. 2 shows an outline of the processing of the clustering device 10. Hereinafter, the operation of the clustering device 10 will be described using Figs. 1 and 2. The clustering device 10 is configured to be communicable with an external environment. The external environment is, for example, another computer or a storage medium or the like. The clustering device 10 copies and acquires the human resource information 51 from the external environment and stores it in the human resource information storage unit 14.

[0020] The human resource information 51 includes information on a plurality of human resources currently employed or previously employed in an organization using, for example, the human resource management system 100. The human resource information 51 associates, for each of the plurality of human resources, the price of the human resource with attribute values other than the price of the human resource (including the first attribute value described later). In the present embodiment, the number of attribute values is 1 or more, and the content and format thereof can be appropriately defined by those skilled in the art, but in the present embodiment, it includes years of experience, languages used, and work fields. The expression format of the price is arbitrary, but for example, it is a unit price per hour.

[0021] The information processing unit 11 of the clustering device 10 acquires personnel information from the personnel information storage unit 14, clusters personnel based on attribute values, and generates multiple personnel clusters. The specific clustering process can be appropriately designed by those skilled in the art based on known technologies, and for example, the k-means method can be used. In Figure 2, a total of five clusters, from cluster 0 to cluster 4, are shown as an example, but the number of clusters to be generated is not limited to this and can be designed arbitrarily, or the clustering device 10 may determine it automatically.

[0022] As a result of the clustering process, a personnel dataset is generated. For each personnel, the personnel dataset associates information that identifies the cluster to which the personnel belongs, in addition to the information contained in the personnel information 51. That is, the personnel dataset storage unit 15 contains cluster information and personnel information, and for each personnel, the personnel dataset associates information that identifies the cluster to which the personnel belongs, the price of the personnel, and the attribute values ​​of the personnel. The information processing unit 11 stores the generated personnel dataset in the personnel dataset storage unit 15.

[0023] Next, the operation of the new personnel registration device 30 will be described. The new personnel registration device 30 is configured to communicate with the external environment, similar to the clustering device 10. The new personnel registration device 30 copies and acquires new personnel information 52 from the external environment and stores it in the new personnel information storage unit 34.

[0024] New personnel information 52 includes information on one or more new personnel. New personnel are, for example, individuals who should be considered for new employment or continued employment within an organization using the personnel management system 100. New personnel information 52 can be in the same format as personnel information 51, and for each of the multiple personnel, the price of the personnel and attribute values ​​other than the price of the personnel (including the first attribute values ​​described below) are associated with it.

[0025] Next, the operation of the machine learning model building device 40 will be described. The machine learning model building device 40 is configured to communicate with the external environment, similar to the clustering device 10.

[0026] The input unit 42 acquires the personnel dataset as input from the output unit 13 of the clustering device 10 and stores it in the personnel dataset storage unit 44. The machine learning model storage unit 45 stores the machine learning model. The information processing unit 41 acquires the personnel dataset (including personnel information) from the personnel dataset storage unit 44. Furthermore, the information processing unit 41 performs machine learning processing on the machine learning model based on this information and generates a trained model.

[0027] Machine learning takes the attribute values ​​of each individual as input and attempts to infer the cluster to which that individual belongs as output. The aforementioned individual dataset associates the attribute values ​​of each individual with the cluster to which that individual belongs, and can therefore be used as training data. The specific model format of the machine learning model can be designed as appropriate by those skilled in the art, but for example, it can be an SVM (Support Vector Machine).

[0028] In the learning process, it is not necessary to use all of the personnel's attribute values; at least one type of attribute value is sufficient. The attribute values ​​used in the learning process (one or more attribute values) are called the "first attribute values." The first attribute values ​​do not include price. In this embodiment, the first attribute values ​​do not include each personnel's years of experience, but as a modification, the first attribute values ​​may include years of experience.

[0029] Next, the operation of the price reasonableness evaluation device 20 will be explained. The input unit 22 acquires the personnel dataset as input from the output unit 13 of the clustering device 10, and also acquires new personnel information as input from the output unit 33 of the new personnel registration device 30, and stores these in the personnel dataset storage unit 25. At this point, the personnel dataset includes the price of personnel, the first attribute value, and cluster information, but the new personnel information includes only the price and first attribute value of the new personnel, and does not include cluster information.

[0030] The information processing unit 21 uses the trained model generated by the machine learning model building device 40 to determine the cluster of each new employee based on their first attribute value. When determining the cluster, the employee dataset stored in the employee dataset storage unit 25 may also be used, as shown in Figure 1 (this step is optional).

[0031] After each new employee's cluster is determined, the information processing unit 21 determines the price of each new employee based on the price distribution of employees belonging to the cluster in which the new employee was assigned, and the price of the new employee, in accordance with the determination criteria stored in the parameter storage unit 26. The information processing unit 21 generates employee evaluation information 53 including the determination result and stores it in the employee evaluation information storage unit 27.

[0032] The output unit 23 retrieves the personnel evaluation information 53 from the personnel evaluation information storage unit 27 and outputs it. This allows users of the personnel management system 100 to view the personnel evaluation information 53.

[0033] Figure 3 shows an example of personnel evaluation information 53. In this example, the evaluation results for 10 new personnel are shown. The evaluation criteria in this example determine which of the following ranges A to E the price of each new personnel falls into. Personnel evaluation information 53 includes information indicating which range each new personnel falls into. - Range A: The price of the new talent is below the lower limit (minimum value) in the price distribution of the cluster to which the new talent belongs. - Range B: The price of the new talent falls within the bottom 25% range (above the minimum value, but below the first quartile) of the price distribution for the cluster to which the new talent belongs. - Range C: The price of the new talent falls within the median range (first quartile and above, third quartile and below) of the price distribution of the cluster to which the new talent belongs. - Range D: The price of the new talent falls within the top 25% range (above the third quartile and below the maximum value) of the price distribution of the cluster to which the new talent belongs. - Range E: The price of a new employee exceeds the upper limit (maximum value) in the price distribution of the cluster to which that new employee belongs.

[0034] In the example in Figure 3, the price of new talent No. 1 (the "requested price" or "requested unit price" in Figure 3) is 8,048 yen, and this new talent No. 1 is classified as cluster No. 0. In this example, the price of 8,048 yen is considered to fall within range D (the top 25%) of the price distribution for cluster No. 0. The talent evaluation information 53 includes the message for new talent No. 1 that corresponds to range D: "The requested unit price is within the top 25% range of the cluster predicted by the AI ​​(greater than 7,758 yen), so please confirm its validity." In particular, in this embodiment, this message includes the price "7,758 yen," which corresponds to the third quartile.

[0035] Similarly, messages corresponding to each range are included for other new talent (note that new talent in ranges A and E are not shown in the example in Figure 3). By including the price corresponding to the minimum value for range A, the price corresponding to the first quartile for range B, the price corresponding to the third quartile for range D, and the price corresponding to the maximum value for range E in the message, users of the talent management system 100 can easily find out how far the price of that new talent is from the median of the cluster.

[0036] Furthermore, the assessment is not based solely on the price of the new employee, but rather on a comparison with the distribution of similar attributes within clusters of similar employees. Therefore, employers can determine whether the price of a new employee is appropriate based not on an absolute benchmark price, but on a relative benchmark price tailored to their attributes.

[0037] In this embodiment, if the price falls within range C, no warning message is displayed to the user; in the example in Figure 3, the message "No particular problem" is displayed. On the other hand, if the price falls within range A, B, D, or E, a warning message is displayed to the user. In the example in Figure 3, the message "Confirm validity" is displayed. This ensures that users of the personnel management system 100 do not overlook new personnel with prices far from the median and can reliably verify their validity.

[0038] Messages that draw attention may be highlighted. In the example in Figure 3, they are highlighted with an underline, but other forms of highlighting (e.g., coloring the background) are also possible.

[0039] Furthermore, the personnel evaluation information 53 may include information other than the evaluation result. In the example in Figure 3, the personnel evaluation information 53 includes the cluster name. The cluster name can be determined and entered as appropriate by the user of the personnel management system 100. In this embodiment, the personnel evaluation information 53 also includes price, years of experience, and other attribute values ​​(work area group, etc.) for each new employee.

[0040] In the above-described Embodiment 1, the specific processing for the determination can be modified as appropriate. For example, the information representing the distribution used for the determination is not limited to that used in Embodiment 1. In Embodiment 1, the information representing the distribution includes the upper limit, lower limit, first quartile, and third quartile in the price distribution of personnel belonging to each cluster, but it is not necessary to use all of these. In the modified example, the distribution is the price distribution of personnel belonging to each cluster, -upper limit, -lower limit, - At least one of the quartiles, - Average value, It is sufficient to include information that represents at least one of the following. It is also possible to use other types of information.

[0041] The format of the judgment result can be arbitrarily changed. The judgment result of the personnel evaluation information 53 may include a message indicating whether the price of the new personnel is close to the average price in the cluster, and / or a message indicating whether the price of the new personnel is close to the median price in the cluster. Furthermore, the judgment result of the personnel evaluation information 53 may include a message indicating whether the price of the new personnel falls within a predetermined range from the average price in the cluster, and / or a message indicating whether the price of the new personnel falls within a predetermined range from the median price in the cluster. Such specifications can be realized, for example, through the judgment criteria of the parameter storage unit 26.

[0042] Those skilled in the art may, in the above-described Embodiment 1, arbitrarily add, change, or delete components within the scope of the present invention. For example, in the personnel management system 100, any of the clustering device 10, price reasonableness evaluation device 20, new personnel registration device 30, and machine learning model construction device 40 may be divided among multiple computers, or two or more of the clustering device 10, price reasonableness evaluation device 20, new personnel registration device 30, and machine learning model construction device 40 may be configured by a single computer.

[0043] The clustering device 10 may be omitted. A known clustering device may be used instead of the clustering device 10, and even if a clustering device is not used, it is sufficient if a human resources dataset in an appropriate format is prepared. If a clustering device is not used, the input unit 22 of the price reasonableness evaluation device 20 may directly acquire a dataset in an appropriate format.

[0044] The new personnel registration device 30 may be omitted. In that case, the input unit 22 of the price reasonableness evaluation device 20 may directly acquire new personnel information 52 from the external environment.

[0045] The machine learning model building device 40 may be omitted. A known machine learning model building device may be used instead of the machine learning model building device 40, and even if a machine learning model building device is not used, an existing trained model may be used. [Explanation of Symbols]

[0046] 10…Clustering device 11…Information Processing Section 13…Output section 14…Human Resources Information Storage Department 15…Human Resource Dataset Storage Unit 20…Price justification evaluation device 21… Information Processing Section 22...Input section 23…Output section 25…Human Resource Dataset Storage Unit 26...Parameter storage unit 27…Personnel Evaluation Information Storage Unit 30... New Personnel Registration Device 33…Output section 34…New Human Resources Information Storage Department 40…Machine learning model building device 41…Information Processing Section 44…Human Resource Dataset Storage Unit 45…Machine learning model memory unit 51…Personnel Information 52…New Talent Information 53…Personnel evaluation information 100... Human Resources Management System

Claims

1. A system that outputs information regarding the price of personnel, The system takes a personnel dataset containing information relating to multiple personnel as input, and for each personnel, the personnel dataset associates information identifying the cluster to which the personnel belong, the personnel's price, and a first attribute value other than the personnel's price. The aforementioned system, - The price and primary attribute value of the new employee are obtained as input. - Based on the first attribute value of the new personnel, determine which cluster in the personnel dataset the new personnel belongs to. -The distribution of prices of personnel belonging to the determined cluster of the new personnel is obtained from the personnel dataset. - Obtain from the storage unit a determination criterion for determining which range of the price distribution of the cluster to which the price of the new personnel belongs. - Based on the price distribution of personnel belonging to the determined cluster of the new personnel, the price of the new personnel, and the judgment criteria, the system determines which range the price of the new personnel falls within the price distribution of the cluster to which the new personnel belong, and outputs the result of that determination. system.

2. The aforementioned distribution is in the distribution of prices of personnel belonging to each cluster, -upper limit, -lower limit, - At least one of the quartiles, - Average value, The system according to claim 1, comprising information representing at least one of the following.

3. The system determines whether the price of the new personnel falls within a predetermined range from the average or median price of personnel in the determined cluster of the new personnel, The system according to claim 1, wherein the system outputs a message indicating whether the price of the new personnel falls within a predetermined range from the average or median price of personnel in the cluster in which the new personnel was determined.

Images