An intelligent human resource management system

Abstract

The present application relates to human resource management technical field, specifically, it relates to a kind of intelligent human resource management system, comprising: input module, based on big data and staff historical work data, gather the original data of staff, the difference of staff original data is carried out through DM-KNN algorithm, form the multiple classification data of staff based on similarity value;Evaluation module, construct staff competency evaluation model, with the multiple classification data of staff as standard input into staff competency evaluation model, divided into the first competency of staff, the second competency of staff, the third competency of staff, the competency of staff is analyzed by integrating division, obtain the competency evaluation result of staff;Management module, the competency evaluation result of staff is managed according to position distribution, and it is judged whether there is vacancy position, based on the preset value of staff competency required by vacancy position, staff is screened, complete the human resource management of staff.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of human resource management, in particular to an intelligent human resource management system. BACKGROUND

[0002] Human resource management is a series of activities for effectively utilizing the human resources inside and outside the organization, meeting the needs of the current and future development of the organization, and ensuring the maximization of the realization of the organization's goals and the development of the members. At present, when the enterprise's position is vacant, the employees are usually screened by written test and interview to identify the position, but there are several problems: 1. It is too subjective to judge whether the employee is competent for the position, which may lead to the situation that the employee is not suitable for the position, causing dissatisfaction among other employees, which is not conducive to the subsequent development of the company; 2. It is impossible to screen the ability factors, behavior factors and execution factors of the employees, such as some employees have strong ability but poor execution, who are not suitable for the position. Based on this, in view of the above problems, we design an intelligent human resource management system. SUMMARY

[0003] The purpose of the present application is to provide an intelligent human resource management system which solves the above technical problems.

[0004] The embodiments of the present application are realized by the following technical solutions:

[0005] An intelligent human resource management system comprises:

[0006] An input module based on big data and historical work data of employees aggregates the original data of employees, differentiates the original data of employees through DM-KNN algorithm, and forms various classification data of employees based on similarity values;

[0007] An evaluation module constructs an employee competence evaluation model, inputs various classification data of employees into the employee competence evaluation model as standard, divides the employee competence evaluation model into the first competence of employees, the second competence of employees and the third competence of employees, analyzes the divided employee competence, and obtains the competence evaluation result of employees;

[0008] A management module manages the competence evaluation result of employees according to the distribution of positions, judges whether there is a vacant position, screens employees based on the preset value of the competence of employees required by the vacant position, and completes the human resource management of employees.

[0009] Optionally, the application process of DM-KNN algorithm is as follows:

[0010] The original data of the employees are divided into a training set and a test set, wherein, the feature vectors in the test set are labeled and divided to form multiple test data, and the employee data in the training set are divided into layers to represent a tree structure with a set number of layers;

[0011] The test data are selected, and the similarity of the data in the training set is calculated in sequence with the selected test data, and the data in the training set with a similarity to the selected test data reaching a preset value are filtered according to the result to obtain a set number of specific data;

[0012] The weights of the set number of specific data are calculated in sequence, and the weights of the specific data are sorted, and the set classification data of the employees are formed based on the differential comparison of the weights of the sorted specific data, and then the above steps are repeated to obtain multiple classification data of the employees.

[0013] Optionally, the calculation formula of the similarity is:

[0014]

[0015] Wherein, m i is the feature vector of the test data, m 1j is the center vector of the first layer and the jth class, M is the dimension of the feature vector, Y k is the kth dimension of the vector.

[0016] Optionally, the multiple classification data of the employees specifically include: an ability factor of the employees, a behavior factor of the employees, and an execution factor of the employees.

[0017] Optionally, the division mode of the first competency degree of the employees, the second competency degree of the employees, and the third competency degree of the employees is: the first competency degree of the employees is evaluated by comprehensively considering the ability factor of the employees, wherein, the ability factor of the employees includes an employee seniority factor, an employee education factor, and an employee ability certificate factor; the second competency degree of the employees is evaluated according to the risk handling level of the employees, wherein, the behavior factor of the employees includes an employee character factor and an employee work state factor; the third competency degree of the employees is evaluated according to the value degree of the employees, wherein, the execution factor of the employees includes an employee processing rhythm factor, an employee processing efficiency factor, and an employee processing result factor.

[0018] Optionally, the mathematical expression of the employee competency evaluation model is:

[0019] E uv =f(CF,BF,IF)

[0020] Wherein, E uvFor the employee competence evaluation result, CF is the employee's ability factor, BF is the employee's behavior factor, and IF is the employee's execution factor.

[0021] Optionally, the employee is screened based on the preset value of the required employee competence of the vacant position, wherein the screening method specifically applies a voting method, and the calculation formula is:

[0022]

[0023] Wherein, g is the category number, which is 1 or 2, r is the total number of preset voting managers, Hrg is the screening result of the preset voting manager Hr, which is 0 or 1, wherein 1 represents the screening result is agreed, and 0 represents the screening result is denied.

[0024] The technical scheme of the embodiment of the present application has at least the following advantages and beneficial effects:

[0025] The embodiment can screen the ability factor, behavior factor and execution factor of the employee based on big data and the historical work data of the employee, in combination with the employee competence evaluation model, comprehensively evaluate the competence of the employee, and objectively judge the position competence of the employee, so as to avoid the situation that the employee is not suitable for the position, cause dissatisfaction of other employees, and is not conducive to the subsequent development of the company. In addition, the embodiment also aims at the situation that the enterprise may have employees who need to be trained, and after screening out the employees who do not meet the standard, the voting result of the preset voting manager is determined by the voting method to determine the employee to fill the vacant position, which is more feasible.

[0026] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be understood by those skilled in the art through implementation of the embodiments of the present application. The purpose and other advantages of the present application can be achieved and obtained by the structure specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 A principle schematic diagram of an intelligent human resource management system provided by the present application;

[0028] Figure 2 A method flow schematic diagram of an intelligent human resource management system provided by the present application;

[0029] Figure 3 An application process schematic diagram of the DM-KNN algorithm provided by the present application. DETAILED DESCRIPTION

[0030] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. The components of the embodiments of the present application generally described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0031] It should be noted that: similar reference numerals or letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second" and the like are only used to distinguish description, and cannot be understood as indicating or implying relative importance.

[0032] As shown in Figure 1 , Figure 2 , the present application provides one of the embodiments: an intelligent human resource management system, comprising:

[0033] An input module, based on big data and historical work data of employees, gathers original data of employees, differentiates the original data of employees through DM-KNN algorithm, and forms various classification data of employees based on similarity values;

[0034] An evaluation module, which constructs an employee competence evaluation model, takes various classification data of employees as standard input into the employee competence evaluation model, divides the employee competence evaluation model into a first competence of employees, a second competence of employees, and a third competence of employees, integrates and analyzes the divided employee competence to obtain an employee competence evaluation result;

[0035] A management module, which manages the employee competence evaluation result according to position distribution, judges whether there is a vacant position, filters employees based on a preset value of the required employee competence of the vacant position, and completes human resource management of employees.

[0036] Before the system is applied, the complex data is usually classified by KNN algorithm, which has the characteristics of good stability, high accuracy and easy use. For the complex data classification situation, KNN algorithm has the following shortcomings: 1. The distance between each text to be classified and all known samples must be calculated to obtain the K nearest neighbors, and the typical characteristics of complex data are massive data information and low value density, which easily leads to a lot of invalid calculation; 2. When determining the category of the test sample, KNN algorithm only calculates the nearest neighbor sample, and complex data generally involves many fields, and the category boundary is not obvious, which easily causes deviation of the judgment result. Based on this, the improved KNN algorithm, i.e. the DM-KNN algorithm described in the embodiment, is used to differentially process the complex data.

[0037] In one application of the embodiment, the DM-KNN algorithm constructs a tree-like hierarchical structure to compare the upper layer first, and then compare the next layer according to the different comparison results of the upper layer, which significantly reduces the calculation amount and improves the operation speed compared with directly calculating the distance of all texts. Differential comparison: data usually has the characteristic of class domain crossing, and DM-KNN algorithm is not directly judged after weight comparison, but a differential comparison is made for the class domain crossing of big data, which can effectively prevent the misjudgment of the nearest neighbor and the second nearest neighbor. Dynamically increase the category: the information in the data usually has unpredictability, and DM-KNN algorithm can dynamically increase new categories in DM-KNN algorithm for the situation that the final comparison result cannot determine which category it belongs to.

[0038] As shown in Figure 3 In the embodiment, the application process of DM-KNN algorithm is as follows:

[0039] The original data of the employees is divided into a training set and a test set, wherein the feature vectors in the test set are labeled and divided into multiple test data, and the employee data in the training set is divided into hierarchical categories to represent a tree structure with a set number of layers;

[0040] Select test data, and calculate the similarity of the data in the training set with the selected test data in sequence, and filter the data in the training set with a similarity to the selected test data reaching a preset value based on the result to obtain a certain number of specific data;

[0041] The weights of the certain number of specific data are calculated in sequence, and the weights of the specific data are sorted, and the specific data after sorting are differentially compared based on the weights to form the set classification data of the employees, and then the above steps are repeated to obtain multiple classification data of the employees.

[0042] In the embodiment, the DM-KNN algorithm adopts a tree-shaped hierarchical structure, and preferentially compares the upper layer, and then sequentially compares the lower layer according to the comparison result of the upper layer, so as to reduce the data calculation amount and improve the data calculation speed. In addition, the big data in the embodiment has the characteristic of cross, so the embodiment differentiates the data again through the cross of the big data, so as to effectively prevent the judgment error of the nearest neighbor data and the second nearest neighbor data.

[0043] In the embodiment, the similarity calculation formula is:

[0044]

[0045] Wherein, m i is the feature vector of the test data, m 1j is the center vector of the first layer and the jth type, M is the dimension of the feature vector, Y k is the kth dimension of the vector.

[0046] In the embodiment, the various classification data of the employee specifically includes: the ability factor of the employee, the behavior factor of the employee, and the execution factor of the employee.

[0047] In the embodiment, the division method of the first competency degree of the employee, the second competency degree of the employee, and the third competency degree of the employee is: comprehensively considering the ability factor of the employee to evaluate the first competency degree of the employee, wherein the ability factor of the employee includes the employee seniority factor, the employee education factor, and the employee ability certificate factor; comprehensively considering the behavior factor of the employee to calculate the risk handling level of the employee, and evaluating the second competency degree of the employee according to the risk handling level, wherein the behavior factor of the employee includes the employee character factor and the employee working state factor; comprehensively considering the execution factor of the employee to calculate the value degree of the employee according to the execution factor, and evaluating the third competency degree of the employee according to the value degree, wherein the execution factor of the employee includes the employee processing rhythm factor, the employee processing efficiency factor, and the employee processing result factor.

[0048] In the embodiment, the mathematical expression of the employee competency evaluation model is:

[0049] E uv =f(CF,BF,IF)

[0050] Wherein, E uv is the competency evaluation result of the employee, CF is the ability factor of the employee, BF is the behavior factor of the employee, and IF is the execution factor of the employee.

[0051] In the embodiment, the employee is screened based on the preset value of the required employee competency of the vacant position, wherein the screening method specifically applies the voting method, and the calculation formula is:

[0052]

[0053] wherein g is the number of categories, which takes a value of 1 or 2, r is the total number of preset ticket selection managers, Hrg is the screening result of the preset ticket selection manager Hr, which takes a value of 0 or 1, wherein 1 represents the screening result is agreed, and 0 represents the screening result is denied.

[0054] In the specific application of the embodiment, when a position of an enterprise is vacant, the data of each employee in the enterprise is acquired, and the data is input into the constructed employee competence evaluation model in combination with big data, integrated analysis is performed, the competence evaluation result of each employee is obtained, then the employees are first screened according to the set competence, and the employees who cannot be competent are eliminated, then the employees are sorted according to the competence, and in the case that the employees who need to be trained are excluded, the employees are selected to fill the position according to the order from large to small of the competence; in the case that the employees who need to be trained are needed, a ticket selection method is adopted, and the ticket selection result of the preset ticket selection manager is used to determine the employees to fill the position.

[0055] Corresponding to the system embodiment above, the embodiment also provides an intelligent human resource management device, and the intelligent human resource management device described below can be correspondingly referred to the intelligent human resource management system described above.

[0056] An intelligent human resource management device can include a processor, a memory. The intelligent human resource management device can also include one or more of a multimedia component, an input / output (I / O) interface, and a communication component.

[0057] The processor is configured to control the overall operation of the intelligent human resource management device to complete all or part of the functions of the intelligent human resource management system described above. The memory is configured to store various types of data to support the operation of the intelligent human resource management device, which can include, for example, instructions for any application or method operating on the intelligent human resource management device, and application-related data, such as contact data, messages, pictures, audio, video, and the like. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The multimedia component can include a screen and an audio component. The screen can be a touch screen, for example, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory or transmitted through the communication component. The audio component also includes at least one speaker configured to output audio signals.

[0058] In one of the applications of the present embodiment, the intelligent human resource management device can be implemented by one or more of Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic components, for executing the intelligent human resource management system as described above.

[0059] In one of the applications of the present embodiment, a computer readable storage medium including program instructions is also provided, which, when executed by a processor, implements the functions of the intelligent human resource management system as described above. For example, the computer readable storage medium can be the memory as described above including program instructions, which can be executed by the processor of the intelligent human resource management device to complete the intelligent human resource management system as described above.

[0060] Corresponding to the system embodiment above, the present embodiment also provides a readable storage medium, which can be mutually corresponding with the intelligent human resource management system as described above.

[0061] A readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the functions of the intelligent human resource management system of the method embodiment as described above.

[0062] The readable storage medium can be specifically a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various readable storage media that can store program codes.

[0063] To sum up, the embodiment can screen the ability factor, behavior factor and execution factor of the staff, comprehensively evaluate the competency of the staff, and objectively judge the position competency of the staff based on big data and historical work data of the staff, in combination with the staff competency evaluation model, so that the situation that the staff is not competent for the position is avoided, dissatisfaction of other staff is caused, and the subsequent development of the company is not conducive; in addition, the embodiment also aims at the situation that the staff who needs to be trained by the enterprise may exist, and after the staff who does not meet the standard is screened out, the staff vacancy position can be determined through the voting result of the voting of the preset management personnel, and the embodiment has higher feasibility.

[0064] The preferred embodiments of the present application have been described above by way of example only, and it should be appreciated that modifications and variations of the present application can be made by those skilled in the art without departing from the spirit and scope of the application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An intelligent human resource management system, characterized in that, include: The input module, based on big data and employees' historical work data, gathers the employees' raw data, performs differential analysis on the raw employee data using the DM-KNN algorithm, and forms multiple categories of employee data based on similarity values; The assessment module constructs an employee competency assessment model. Employees' various classification data are input into the model as standards, dividing them into three levels of competency: primary competency, secondary competency, and tertiary competency. The resulting competency assessment is then analyzed by integrating these categories to obtain the overall employee competency assessment results. The management module manages the employee competency assessment results according to job distribution, determines whether there are vacant positions, and screens employees based on the preset competency values ​​required for vacant positions, thus completing the human resource management of employees. The application process of the DM-KNN algorithm is as follows: The original employee data is divided into a training set and a test set. The feature vectors in the test set are labeled and divided into multiple test data. The employee data in the training set is hierarchically categorized to represent a tree structure with a set number of levels. Select test data, and calculate the similarity between the selected test data and the data in the training set in turn. Based on the results, filter the data in the training set that have a preset similarity value with the selected test data to obtain a set number of specific data. Calculate the weights of a set number of specific data points sequentially, sort the weights of each specific data point, perform differential comparisons based on the sorted weights of the specific data points to form the set category data of employees, and then repeat the above steps to obtain multiple categories of employee data. The formula for calculating similarity is: in, For the feature vector of the test data, Let M be the center vector of the j-th class in the first layer, and M be the dimension of the feature vector.

2. The intelligent human resource management system according to claim 1, characterized in that, The various categories of employee data specifically include: employee competency factors, employee behavioral factors, and employee performance factors.

3. The intelligent human resource management system according to claim 2, characterized in that, The classification of an employee's primary competence, secondary competence, and tertiary competence is as follows: First competence is assessed by comprehensively considering the employee's ability factors, including seniority, education level, and certifications. Second competence is assessed based on the employee's behavioral factors, which include personality traits and work performance. Third competence is assessed based on the employee's execution factors, which include processing pace, efficiency, and outcome.

4. The intelligent human resource management system according to claim 3, characterized in that, The mathematical expression for the employee competency assessment model is: in, The results represent the employee's competency assessment, with CF representing the employee's ability factors, BF representing the employee's behavioral factors, and IF representing the employee's performance factors.

5. The intelligent human resource management system according to claim 1, characterized in that, Based on preset competency levels required for vacant positions, employees are screened using a voting method, the calculation formula of which is as follows: Where g is the number of categories, which takes the value of 1 or 2; r is the total number of managers to be voted on in the preset voting; and Hrg is the screening result of the preset voting manager Hr, which takes the value of 0 or 1, where 1 represents the screening result as agreeable and 0 represents the screening result as disagreeable.

Images