Employee evaluation method and system, electronic equipment and storage medium

Abstract

The invention provides an employee evaluation method and system, electronic equipment and a storage medium, the evaluation method is applied to the employee evaluation system, and the evaluation system comprises a data acquisition layer, a data processing layer and a data service layer; the evaluation method comprises the steps that the data acquisition layer acquires multi-source evaluation data of a target employee from multiple data channels; the data processing layer stores multi-source evaluation data and extracts a feature data set of a target employee from the multi-source evaluation data through data governance and feature engineering; and the data service layer obtains an evaluation result of the target employee by using an evaluation model corresponding to the evaluation demand of the user and the feature data set of the target employee. Thus, by collecting the multi-source evaluation data of the target employee, extracting the feature data set and obtaining the evaluation result through the evaluation model, all-around, digital and intelligent comprehensive evaluation can be performed on the employee, the accuracy and integrity of employee evaluation are improved, and a data decision support is provided for a data application scene of employee selection and employee use.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to an employee evaluation method, evaluation system, electronic device and storage medium. Background Art

[0002] As the scale of enterprises continues to expand, there is an urgent need to select high-quality professional employees to help enterprises achieve high-quality development. As the number of employees continues to increase, how to conduct a comprehensive and accurate evaluation of the employee group is the key.

[0003] When evaluating employees in an enterprise, the existing technology has data "islands" and security issues such as incomplete information, low quality, and poor data freshness. This makes it impossible to fully and accurately outline the user portrait of the target users, resulting in a low level of digitization and intelligence in employee evaluation and inaccurate evaluation of employees. Summary of the invention

[0004] In view of this, the purpose of this application is to provide an employee evaluation method, evaluation system, electronic device and storage medium. By collecting multi-source evaluation data of target employees, extracting feature data sets and obtaining evaluation results from evaluation models, it is possible to conduct a comprehensive, digital and intelligent evaluation of employees, improve the accuracy and completeness of employee evaluation, and provide data decision support for data application scenarios in personnel selection and employment.

[0005] The embodiment of the present application provides an employee evaluation method, which is applied to an employee evaluation system, wherein the evaluation system includes a data collection layer, a data processing layer, and a data service layer; the evaluation method includes:

[0006] The data collection layer collects multi-source evaluation data of target employees from multiple data channels;

[0007] The data processing layer stores the multi-source evaluation data, and extracts the feature data set of the target employee from the multi-source evaluation data through data governance and feature engineering;

[0008] The data service layer uses the evaluation model corresponding to the user's evaluation requirements and the characteristic data set of the target employee to obtain the evaluation result of the target employee.

[0009] Furthermore, the data processing layer includes: a data resource pool, a data governance module and a data analysis module; the data processing layer stores the multi-source evaluation data, and extracts the feature data set of the target employee from the multi-source evaluation data through data governance and feature engineering, including:

[0010] The data resource pool stores the multi-source evaluation data;

[0011] The data governance module uses data governance measures to govern the multi-source evaluation data stored in the data resource pool; the data governance measures include at least one of the following: metadata management, master data management, data quality management, data standard management and data asset management;

[0012] The data analysis module extracts the feature vectors of the target employee under different categories from the multi-source evaluation data, and assigns a weight to each feature vector to generate the feature data set.

[0013] Furthermore, the data resource pool includes a collection library, a standard library, a theme library and an indicator library; the data resource pool stores the multi-source evaluation data, including:

[0014] Storing the multi-source evaluation data as raw data in the collection library;

[0015] Converting the multi-source evaluation data into standard data and storing the data in the standard library;

[0016] Classifying the standard data according to a pre-constructed classification standard, and storing the obtained classified data in the subject library;

[0017] The index values ​​of different indicators are calculated according to the classified data and stored in the index library.

[0018] Furthermore, the data processing layer also includes a data security module; the evaluation method includes:

[0019] The data security module uses a data security algorithm to ensure data security for the multi-source evaluation data; wherein the data security algorithm includes at least one of the following: federated learning, trusted computing, and data sandbox.

[0020] Furthermore, the evaluation model includes a multi-dimensional comprehensive evaluation model; the data service layer uses the evaluation model corresponding to the user's evaluation requirements and the characteristic data set of the target employee to obtain the evaluation result of the target employee, including:

[0021] The data service layer determines the service mode as a standardized scenario service mode or a trusted scenario service mode according to the evaluation requirements of the user;

[0022] If it is the standardized scenario service mode, then the pre-built multi-dimensional comprehensive evaluation model is retrieved;

[0023] If it is the entrusted scenario service mode, constructing the multi-dimensional comprehensive evaluation model according to the evaluation requirements;

[0024] Inputting the feature data set into the multi-dimensional comprehensive evaluation model to obtain the evaluation result of the target employee in each assessment dimension;

[0025] According to the evaluation results of the target employee in each assessment dimension, the comprehensive evaluation result of the target employee is determined.

[0026] Furthermore, the evaluation model also includes a decision item early warning model; the data service layer uses the evaluation model corresponding to the user's evaluation requirements and the characteristic data set of the target employee to obtain the evaluation result of the target employee, and also includes:

[0027] Inputting the characteristic data set of the target employee into the decision item early warning model to determine whether the target employee triggers the decision item early warning mechanism;

[0028] If triggered, the evaluation result of the target employee is determined according to the negative severity of the decision item early warning mechanism triggered and an alarm is issued.

[0029] Furthermore, the method also includes: the data service layer generates an employee group evaluation product according to the evaluation results of multiple employees, and generates an employee recommendation plan according to the selection needs of the user and provides it to the user.

[0030] The embodiment of the present application also provides an employee evaluation system, the evaluation system comprising a data collection layer, a data processing layer and a data service layer;

[0031] The data collection layer is used to collect multi-source evaluation data of target employees from multiple data channels;

[0032] The data processing layer is used to store the multi-source evaluation data and extract the feature data set of the target employee from the multi-source evaluation data through data governance and feature engineering;

[0033] The data service layer is used to obtain the evaluation result of the target employee by using the evaluation model corresponding to the user's evaluation requirements and the feature data set of the target employee.

[0034] An embodiment of the present application also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of an employee evaluation method as described above are performed.

[0035] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the employee evaluation method as described above are executed.

[0036] The embodiment of the present application provides an employee evaluation method, evaluation system, electronic device and storage medium, which can collect multi-source evaluation data of target employees, extract feature data sets and obtain evaluation results from evaluation models, so as to conduct a comprehensive, digital and intelligent evaluation of employees, improve the accuracy and completeness of employee evaluation, and provide data decision support for data application scenarios of personnel selection and employment. In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following is a detailed description of the preferred embodiments and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flow chart of an employee evaluation method provided in an embodiment of the present application is shown;

[0039] Figure 2 One of the structural schematic diagrams of an employee evaluation system provided in an embodiment of the present application is shown;

[0040] Figure 3 A second structural diagram of an employee evaluation system provided in an embodiment of the present application is shown;

[0041] Figure 4 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0042] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here 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 application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0043] Research has found that as the scale of enterprises continues to expand, there is an urgent need to screen out high-quality professional employees to help enterprises achieve high-quality development. As the number of employees continues to increase, how to conduct a comprehensive and accurate evaluation of the employee group is the key.

[0044] When evaluating employees in an enterprise, the existing technology has data "islands" and security issues such as incomplete information, low quality, and poor data freshness. This makes it impossible to fully and accurately outline the user portrait of the target users, resulting in a low level of digitization and intelligence in employee evaluation and inaccurate evaluation of employees.

[0045] Based on this, the embodiments of the present application provide an employee evaluation method, evaluation system, electronic device and storage medium to conduct a comprehensive, digital and intelligent evaluation of employees, improve the accuracy and completeness of employee evaluation, and provide data decision support for data application scenarios in personnel selection and employment.

[0046] See also Figure 1 and Figure 2 , Figure 1 A flowchart of an employee evaluation method provided in an embodiment of the present application; Figure 2 This is one of the structural diagrams of an employee evaluation system provided in an embodiment of the present application. Figure 1 and Figure 2 As shown, the evaluation method provided in the embodiment of the present application is applied to an employee evaluation system, the evaluation system includes a data collection layer, a data processing layer and a data service layer; the evaluation method includes:

[0047] S101. The data collection layer collects multi-source evaluation data of target employees from multiple data channels.

[0048] In this step, the data collection layer can automatically collect employee evaluation data periodically (such as maintaining a monthly or quarterly update frequency) or trigger under data authorization. It also provides a manual data collection interface, that is, the data collection operation is initiated manually. The data freshness can be guaranteed by the on-time and on-demand data collection frequency. At the same time, in order to ensure the authenticity and security of the data during transmission, the data needs to be encrypted when the message is sent. Data transmission methods such as secure data interface, asynchronous file processing, and offline data synchronization are adopted.

[0049] Here, multiple data channels include enterprise data channels, government data channels, and Internet data channels, etc.; enterprise data collected from enterprise data channels include system data from the enterprise's internal human resources management system, project management system, and financial management system, etc.; government data collected from government data channels include civil affairs marriage data, financial personal asset data, and housing and construction real estate data, etc.; Internet data collected from Internet data channels include Internet consumption and behavior data, etc. In this way, by collecting and integrating evaluation data from rich sources, the multi-source evaluation data obtained is authoritative, high-quality, and comprehensive.

[0050] S102: The data processing layer stores the multi-source evaluation data, and extracts a feature data set of the target employee from the multi-source evaluation data through data governance and feature engineering.

[0051] In this step, the data processing layer stores the multi-source evaluation data collected by the data collection layer and performs a series of data governance processes and feature engineering on it to extract feature data sets that can characterize individual behavior characteristics from the multi-source evaluation data.

[0052] Wherein, the data processing layer includes: a data resource pool, a data governance module and a data analysis module; then step S102 may include:

[0053] The data resource pool stores the multi-source evaluation data; the data governance module uses data governance measures to govern the multi-source evaluation data stored in the data resource pool; the data analysis module extracts the feature vectors of the target employees under different categories from the multi-source evaluation data, and assigns a weight to each feature vector to generate the feature data set.

[0054] The data resource pool includes a collection library, a standard library, a theme library and an indicator library; the data resource pool stores the multi-source evaluation data, including:

[0055] The multi-source evaluation data is stored as raw data in the collection library; the multi-source evaluation data is converted into standard data and stored in the standard library; the standard data is classified according to a pre-constructed classification standard, and the obtained classified data is stored in the subject library; the indicator values ​​of different indicators are calculated according to the classified data and stored in the indicator library.

[0056] For example, GB / T 2261-2003 personal basic information classification and code, GB / T4658-2006 education code, GB / T 6565-2015 occupation classification and code, GB / T 4762-1984 political status code, GB / T 4761-2008 family relationship code, GB / T 3304 Romanization and code of names of various ethnic groups in China, GB / T 12404-1997 unit affiliation code and other standards can be referred to establish a personal information standard library; multi-source evaluation data is converted into standard data according to the specifications of the personal information standard library and stored in the standard library. For example, for gender, some data systems use male and female, and some data systems use 0 and 1 to mark male and female respectively. The embodiment of the present application processes the data according to the relevant standards, with 0 representing unknown gender, 1 representing male, 2 representing female, and 9 representing unspecified gender.

[0057] Afterwards, the processed standard data will be classified according to different topics such as personal basic information, family member information, work experience, income information, reward information, disciplinary information, wedding and funeral information, marriage and change information, going abroad information, real estate information, physical health information, qualification information, etc., and the classified data will be stored in the subject library; and the indicator value of the corresponding indicator is calculated based on each type of data and stored in the indicator library.

[0058] For the data governance module, the data governance measures it adopts include at least one of the following: metadata management, master data management, data quality management, data standard management and data asset management. Through these governance measures, the data governance module can improve the data quality of employee personal information according to pre-set standards;

[0059] For the data analysis module, feature extraction algorithms provided in AI data analysis and mining tools such as neural networks and machine learning can be used to extract feature vectors that can characterize employees' personal behavior characteristics under different categories from multi-source evaluation data in multiple libraries of the data resource pool, and weights can be set according to importance and risk levels to obtain feature data sets.

[0060] Furthermore, the data processing layer also includes a data security module; then the evaluation method includes:

[0061] The data security module uses a data security algorithm to ensure data security for the multi-source evaluation data; wherein the data security algorithm includes at least one of the following: federated learning, trusted computing, and data sandbox.

[0062] The data security module includes data collection security unit, data storage security unit, data sharing security unit, data application security unit, data encryption unit, etc. By using federated learning, trusted computing, data sandbox and other technologies, different tools can be used in different units to encrypt and secure employee personal information data to ensure data security.

[0063] S103: The data service layer uses the evaluation model corresponding to the user's evaluation requirements and the characteristic data set of the target employee to obtain the evaluation result of the target employee.

[0064] In this step, the data service layer can input the feature data set into the evaluation model corresponding to the evaluation requirements to obtain the evaluation results of the target employees. In the specific implementation, the evaluation model includes a multi-dimensional comprehensive evaluation model; then step S103 may include:

[0065] S1031. The data service layer determines, according to the evaluation requirements of the user, that the service mode is a standardized scenario service mode or a trusted scenario service mode.

[0066] At present, according to the evaluation needs of users, such as the degree of enterprise data openness and data development capabilities, the embodiments of the present application provide two service modes: standardized scenario service mode and entrusted scenario service mode; the standardized operation mode means that enterprises, organizations or individuals store data in the data bank, support data sets or standardized data products through data fusion, and put them on the platform shelves in the form of standardized data APIs, solutions, data products, etc. for users to use for a fee or free of charge; the entrusted service operation means that due to the lack of data development technology or data source of data demand users, customized data requirements are put forward, and services are provided to data demand users by integrating and developing data to form new data products.

[0067] S1032: If it is the standardized scenario service mode, then retrieve the pre-built multi-dimensional comprehensive evaluation model.

[0068] S1033: If it is the entrusted scenario service model, construct the multi-dimensional comprehensive evaluation model according to the evaluation requirements.

[0069] In steps S1032 and S1033, for the standardized scenario service mode, the standardized pre-built multi-dimensional comprehensive evaluation model can be directly called; for the entrusted scenario service mode, it is necessary to re-customize and create a multi-dimensional comprehensive evaluation model according to the user's evaluation requirements. Specifically, the evaluation requirements are subject to compliance review. If they pass, multiple evaluation dimensions are established according to the evaluation requirements, and a multi-dimensional comprehensive evaluation model is constructed using data analysis and mining tools to support data application services under the entrusted scenario service model.

[0070] It should be noted that in order to ensure the accuracy of the evaluation model, the pre-built multi-dimensional comprehensive evaluation model in the standardized scenario service model also needs to be updated regularly. For example, the input feature vector of the model can be updated on a monthly / quarterly / yearly basis or on demand, and the multi-dimensional comprehensive evaluation model can be updated using data analysis and mining tools.

[0071] S1034. Input the feature data set into the multi-dimensional comprehensive evaluation model to obtain the evaluation result of the target employee in each assessment dimension.

[0072] In a possible implementation, the assessment dimensions may include integrity evaluation, business capability evaluation, management capability evaluation, learning capability evaluation, and customer evaluation, etc. Then the multi-dimensional comprehensive evaluation model may include multiple single-dimensional evaluation models; the way in which the evaluation model of any dimension outputs the evaluation result of the target employee in the assessment dimension can be expressed by the formula:

[0073]

[0074] In the formula, i∈(1,N), and f i Between (0,1), f is the action function, ω k is the weight of the evaluation model of the kth assessment dimension, and satisfies: where x k Input feature vector for the kth dimension.

[0075] S1035. Determine a comprehensive evaluation result of the target employee based on the evaluation result of the target employee in each assessment dimension.

[0076] In this step, the comprehensive evaluation result of the target employee is the final evaluation result of the target employee. The method of determining the comprehensive evaluation result based on the evaluation result of the target employee in each assessment dimension can be expressed by the formula:

[0077]

[0078] Among them, θ i is the weight of the i-th output vector and satisfies:

[0079] Here, the evaluation results of each assessment dimension and the comprehensive evaluation results can be evaluation scores, and the evaluation scores can also be further mapped into evaluation levels.

[0080] Furthermore, the evaluation model also includes a decision item early warning model; then step S103 may also include:

[0081] The characteristic data set of the target employee is input into the decision item warning model to determine whether the target employee triggers the decision item warning mechanism; if triggered, the evaluation result of the target employee is determined according to the negative severity of the triggering of the decision item warning mechanism and an alarm is issued.

[0082] Here, the decision item refers to a major risk item that is decisive for the employee evaluation, such as a criminal record and a dishonest debtor, etc. Different decision items correspond to different levels of negative severity. In this step, the feature data set is input into the decision item warning model. If the decisive warning mechanism is triggered, it often means that the target employee has poor compliance. The evaluation result of the target employee can be determined according to the negative severity triggered by the decision item warning mechanism, such as directly determining the score as a low score or the evaluation level as a low level, and an alarm is issued to notify the employee's superior or a dedicated human resources person in charge.

[0083] It should be noted that when the evaluation model includes both a multidimensional comprehensive evaluation model and a decision item warning model, due to the decisive significance of the decision items in the decision item warning model for employee evaluation, even if the multidimensional comprehensive evaluation model gives a higher comprehensive evaluation result, if the decision item warning mechanism of the decision item warning model is triggered, the evaluation result determined according to the negative severity triggered by the decision item warning mechanism will be directly determined as the employee's final evaluation result and an alarm will be issued. For example, the employee's final score will be directly determined as a low score or the evaluation level will be directly determined as a low level, etc., so as to achieve a full understanding of the employee's major risks and thus improve the compliance and safety of personnel selection and employment.

[0084] Furthermore, the method also includes: the data service layer generates an employee group evaluation product based on the evaluation results of multiple employees, and generates an employee recommendation plan based on the selection needs of the user and provides it to the user. In specific implementation, technical means such as text analysis can be used to match the selection needs with the employee's evaluation results, and then generate an employee recommendation plan based on the matching results. In addition, the employee recommendation plan or employee group evaluation product can be presented in the form of multiple data products such as data API, analysis report, data project, etc. In this way, an accurate and comprehensive evaluation of the employee group can be carried out, providing data decision support for the data application scenario of personnel selection.

[0085] An employee evaluation method provided in an embodiment of the present application collects multi-source evaluation data of target employees, extracts feature data sets and obtains evaluation results from an evaluation model; on the basis of full storage, comprehensive aggregation, standardized rights confirmation and efficient governance of massive data, a data bank with a "quasi-bank" concept is formed, which can promote efficient sharing and circulation of data, enhance data integration and application value-added, and ultimately realize full-scenario application of data, and is an effective tool for realizing data openness and integration.

[0086] Compared with the prior art, the advantages of this application are: (1) This application is based on a data bank system, focuses on the security of employees' personal data information, and improves data compliance and security from the stages of data collection, storage, governance, analysis and application. (2) This application is based on a data bank. Under the premise of data authorization compliance, it collects and integrates multi-source evaluation data from internal corporate, government data and Internet data, which can ensure the authority, quality and comprehensiveness of the data. At the same time, it can collect data on a regular basis or on demand to ensure the freshness of the data. (3) The multi-dimensional comprehensive evaluation model proposed in the present invention can conduct a comprehensive, digital and intelligent evaluation of employees and employee groups, improve the accuracy and completeness of employee evaluation, and meet the supervision, regulation and selection requirements of different departments of the enterprise for employees.

[0087] In summary, the embodiments of the present application can conduct an all-round, digital, and intelligent comprehensive evaluation of employees, improve the accuracy and completeness of employee evaluation, and provide data decision support for data application scenarios in personnel selection and employment.

[0088] Based on the same inventive concept, the present application also provides an employee evaluation system. Figure 3 , Figure 3 This is a second structural diagram of an employee evaluation system provided in an embodiment of the present application. Figure 3 As shown in , the evaluation system 300 includes: a data collection layer 310, a data processing layer 320 and a data service layer 330;

[0089] The data collection layer 310 is used to collect multi-source evaluation data of target employees from multiple data channels;

[0090] The data processing layer 320 is used to store the multi-source evaluation data and extract the feature data set of the target employee from the multi-source evaluation data through data governance and feature engineering;

[0091] The data service layer 330 is used to obtain the evaluation result of the target employee by using the evaluation model corresponding to the user's evaluation requirements and the feature data set of the target employee.

[0092] Furthermore, the data processing layer includes: a data resource pool, a data governance module and a data analysis module;

[0093] The data resource pool is used to store the multi-source evaluation data;

[0094] The data governance module is used to manage the multi-source evaluation data stored in the data resource pool using data governance measures; the data governance measures include at least one of the following: metadata management, master data management, data quality management, data standard management and data asset management;

[0095] The data analysis module is used to extract the feature vectors of the target employees under different categories from the multi-source evaluation data, and assign a weight to each feature vector to generate the feature data set.

[0096] Furthermore, the data resource pool includes a collection library, a standard library, a theme library and an indicator library; when the data resource pool is used to store the multi-source evaluation data, the data resource pool is used to:

[0097] Storing the multi-source evaluation data as raw data in the collection library;

[0098] Converting the multi-source evaluation data into standard data and storing the data in the standard library;

[0099] Classifying the standard data according to a pre-constructed classification standard, and storing the obtained classified data in the subject library;

[0100] The index values ​​of different indicators are calculated according to the classified data and stored in the index library.

[0101] Furthermore, the data processing layer also includes a data security module;

[0102] The data security module is used to use a data security algorithm to ensure the data security of the multi-source evaluation data; wherein the data security algorithm includes at least one of the following: federated learning, trusted computing, and data sandbox.

[0103] Furthermore, the evaluation model includes a multi-dimensional comprehensive evaluation model; when the data service layer is used to obtain the evaluation result of the target employee by using the evaluation model corresponding to the user's evaluation requirements and the characteristic data set of the target employee, the data service layer is used to:

[0104] The data service layer determines the service mode as a standardized scenario service mode or a trusted scenario service mode according to the evaluation requirements of the user;

[0105] If it is the standardized scenario service mode, then the pre-built multi-dimensional comprehensive evaluation model is retrieved;

[0106] If it is the entrusted scenario service mode, constructing the multi-dimensional comprehensive evaluation model according to the evaluation requirements;

[0107] Inputting the feature data set into the multi-dimensional comprehensive evaluation model to obtain the evaluation result of the target employee in each assessment dimension;

[0108] According to the evaluation results of the target employee in each assessment dimension, the comprehensive evaluation result of the target employee is determined.

[0109] Furthermore, the evaluation model also includes a decision item early warning model; when the data service layer is used to use the evaluation model corresponding to the user's evaluation requirements and the characteristic data set of the target employee to obtain the evaluation result of the target employee, the data service layer is also used to:

[0110] Inputting the characteristic data set of the target employee into the decision item early warning model to determine whether the target employee triggers the decision item early warning mechanism;

[0111] If triggered, the evaluation result of the target employee is determined according to the negative severity of the decision item early warning mechanism triggered and an alarm is issued.

[0112] Furthermore, the data service layer is also used to: generate an employee group evaluation product based on the evaluation results of multiple employees, and generate an employee recommendation plan based on the selection needs of the user and provide it to the user.

[0113] It should be noted that since the principle of solving the problem by the evaluation system in the embodiment of the present application is similar to the above-mentioned evaluation method in the embodiment of the present application, the implementation of the system can refer to the implementation of the method, and the repeated parts will not be repeated.

[0114] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown in , the electronic device 400 includes a processor 410 , a memory 420 and a bus 430 .

[0115] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, the above-mentioned Figure 1 The steps of an employee evaluation method in the method embodiment shown are described in detail in the method embodiment, and the specific implementation method can be found in the method embodiment, which will not be described in detail here.

[0116] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1The steps of an employee evaluation method in the method embodiment shown are described in detail in the method embodiment, and the specific implementation method can be found in the method embodiment, which will not be described in detail here.

[0117] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0118] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0121] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0122] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for evaluating employees, characterized in that: The evaluation method is applied to an employee evaluation system, which includes a data collection layer, a data processing layer and a data service layer; the evaluation method includes: The data collection layer collects multi-source evaluation data of target employees from multiple data channels; The data processing layer stores the multi-source evaluation data, and extracts the feature data set of the target employee from the multi-source evaluation data through data governance and feature engineering; The data service layer uses the evaluation model corresponding to the user's evaluation requirements and the characteristic data set of the target employee to obtain the evaluation result of the target employee.

2. The evaluation method according to claim 1, characterized in that: The data processing layer includes: a data resource pool, a data governance module and a data analysis module; the data processing layer stores the multi-source evaluation data and extracts the feature data set of the target employee from the multi-source evaluation data through data governance and feature engineering, including: The data resource pool stores the multi-source evaluation data; The data governance module uses data governance measures to govern the multi-source evaluation data stored in the data resource pool; the data governance measures include at least one of the following: metadata management, master data management, data quality management, data standard management and data asset management; The data analysis module extracts the feature vectors of the target employee under different categories from the multi-source evaluation data, and assigns a weight to each feature vector to generate the feature data set.

3. The evaluation method according to claim 2, characterized in that: The data resource pool includes a collection library, a standard library, a theme library and an indicator library; the data resource pool stores the multi-source evaluation data, including: Storing the multi-source evaluation data as raw data in the collection library; Converting the multi-source evaluation data into standard data and storing the data in the standard library; Classifying the standard data according to a pre-constructed classification standard, and storing the obtained classified data in the subject library; The index values ​​of different indicators are calculated according to the classified data and stored in the index library.

4. The evaluation method according to claim 2, characterized in that: The data processing layer also includes a data security module; the evaluation method includes: The data security module uses a data security algorithm to ensure data security for the multi-source evaluation data; wherein the data security algorithm includes at least one of the following: federated learning, trusted computing, and data sandbox.

5. The evaluation method according to claim 1, characterized in that: The evaluation model includes a multi-dimensional comprehensive evaluation model; the data service layer uses the evaluation model corresponding to the user's evaluation requirements and the characteristic data set of the target employee to obtain the evaluation result of the target employee, including: The data service layer determines the service mode as a standardized scenario service mode or a trusted scenario service mode according to the evaluation requirements of the user; If it is the standardized scenario service mode, then the pre-built multi-dimensional comprehensive evaluation model is retrieved; If it is the entrusted scenario service mode, constructing the multi-dimensional comprehensive evaluation model according to the evaluation requirements; Inputting the feature data set into the multi-dimensional comprehensive evaluation model to obtain the evaluation result of the target employee in each assessment dimension; According to the evaluation results of the target employee in each assessment dimension, the comprehensive evaluation result of the target employee is determined.

6. The evaluation method according to claim 5, characterized in that: The evaluation model also includes a decision item early warning model; the data service layer uses the evaluation model corresponding to the user's evaluation requirements and the characteristic data set of the target employee to obtain the evaluation result of the target employee, and also includes: Inputting the characteristic data set of the target employee into the decision item early warning model to determine whether the target employee triggers the decision item early warning mechanism; If triggered, the evaluation result of the target employee is determined according to the negative severity of the decision item early warning mechanism triggered and an alarm is issued.

7. The evaluation method according to claim 1, characterized in that: The method further includes: the data service layer generates an employee group evaluation product according to the evaluation results of multiple employees, and generates an employee recommendation plan according to the selection needs of the user and provides it to the user.

8. An employee evaluation system, characterized in that: The evaluation system includes a data collection layer, a data processing layer and a data service layer; The data collection layer is used to collect multi-source evaluation data of target employees from multiple data channels; The data processing layer is used to store the multi-source evaluation data and extract the feature data set of the target employee from the multi-source evaluation data through data governance and feature engineering; The data service layer is used to obtain the evaluation result of the target employee by using the evaluation model corresponding to the user's evaluation requirements and the feature data set of the target employee.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are run by the processor, the steps of an employee evaluation method as described in any one of claims 1 to 7 are executed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the employee evaluation method according to any one of claims 1 to 7 are executed.

Images