Employee data performance evaluation method and system based on data analysis

Abstract

The invention discloses an employee data performance evaluation method and system based on data analysis, and relates to the technical field of data evaluation. Employee workload data and employee behavior data are collected in real time through a big data technology, and meanwhile, the employee performance evaluation method and system based on the collected employee workload data and employee behavior data are obtained. The method comprises the following steps: processing in a data processing mode, collecting employee historical workload data and employee historical behavior data after processing is completed, determining an employee data performance evaluation index in a data analysis mode, and determining an employee data performance scoring system in a system construction mode based on the determined employee data performance evaluation index. And finally, in combination with a data twinning mode and an employee data performance evaluation system, constructing an employee data performance evaluation model through a model construction mode, and performing performance evaluation on the processed employee workload data and employee behavior data based on the constructed employee data performance evaluation model, thereby improving the comprehensiveness of employee performance evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data evaluation, in particular to an employee data efficiency evaluation method and system based on data analysis. BACKGROUND

[0002] At present, the performance evaluation mechanism of most companies is mostly directly related to the service efficiency of the network. The current evaluation system exposes the core defects: the design of employee performance indicators lacks scientificity, and the results have obvious shortcomings, which restricts the exertion of employee subjective initiative and weakens the comprehensive competitiveness of branch organizations.

[0003] The prior art, such as the invention patent application with the announcement number CN119228165A, discloses an evaluation system for the influence of enterprise digital transformation on employees, which comprises the following steps: obtaining the enterprise digital transformation level, the behavior data, the psychological state data, and the work efficiency data of employees during the use of social media under the corresponding level; wherein the behavior data includes the use frequency and the interaction type, and the evaluation result of the influence of enterprise digital transformation on employees is determined according to the enterprise digital transformation level, the employee behavior data, the psychological state data, and the work efficiency data; the present application can provide comprehensive and scientific evaluation of the influence of digital transformation for enterprises. By comprehensively considering the digital transformation level, the employee social media use behavior, the psychological state, and the work efficiency, enterprises can more accurately understand the actual influence of digital transformation on employees. This helps enterprises to discover problems in time, adjust strategies, and ensure that digital transformation can better serve the development of employees and enterprises.

[0004] According to the above scheme, the current employee evaluation system mostly focuses on the behavior data and psychological state data of employees during the use of social media, and lacks detailed attention and analysis of employee work content, which has certain limitations. SUMMARY

[0005] The present application provides an employee data efficiency evaluation method and system based on data analysis, which solves the problems in the background art.

[0006] To solve the above technical problems, the present application adopts the following technical scheme: the present application provides an employee data efficiency evaluation method based on data analysis, which specifically comprises the following steps: S1, collecting employee workload data and employee behavior data in real time through big data technology; S2, based on the collected employee workload data and employee behavior data, processing the data through data processing to obtain processed employee workload data and employee behavior data; S3, collecting employee historical workload data and employee historical behavior data, and determining employee data efficiency evaluation indicators through data analysis. S4, determining an employee data efficiency evaluation score system based on the determined employee data efficiency evaluation index; S5, constructing an employee data efficiency evaluation model based on the data twin method and the employee data efficiency evaluation score system, and performing efficiency evaluation on the processed employee workload data and employee behavior data based on the constructed employee data efficiency evaluation model.

[0007] Preferably, the real-time collection of employee workload data and employee behavior data through big data technology comprises the following steps: The employee workload data includes work content, work time and participation object; The employee behavior data includes work behavior and leave behavior; Set a three tuple Save the employee workload data; Among them, The work content in the employee workload data is represented by; The work time in the employee workload data is represented by; The participation object in the employee workload data is represented by; A Boolean type data is set to represent the employee behavior data, and the employee work behavior is represented by 1 and the employee leave behavior is represented by 0; Quantify the employee workload data, and after quantification, collect the employee workload data and employee behavior data in real time through big data technology and save them.

[0008] Preferably, the employee workload data and employee behavior data collected are processed through data processing to obtain processed employee workload data and employee behavior data, which comprises the following steps: S21, establish employee workload data and employee behavior data standards; A set of employee workload data must include work content, work time and participation object, and the work duration, required personnel and necessary cost in the work content data cannot exceed; A set of employee behavior data must include daily work behavior and leave behavior data, and an array is constructed by summarizing daily work behavior and leave behavior data; The constructed array represents a set of employee behavior data; S22, process the collected employee workload data and employee behavior data based on the established employee workload data and employee behavior data standards.

[0009] Preferably, the processing of the collected employee workload data and employee behavior data based on the established employee workload data and employee behavior data standards comprises the following steps: Filtering employee workload data and employee behavior data using the Bloom filter algorithm: Create an array of length m, and select... Each hash function iterates through each set of data in the employee workload data and employee behavior data, and stores the results in an array. During the hash function traversal, when two sets of data have the same traversal result, each unit of data in these two sets of data is compared. If the comparison results are consistent, the two data points are set as duplicate data, and one of the data sets is deleted. After the traversal is complete, the employee workload data and employee behavior data stored in the array during the traversal are summarized to obtain the processed employee workload data and employee behavior data.

[0010] Preferably, the process of collecting historical workload data and historical behavior data of employees, and determining employee data performance evaluation indicators through data analysis, includes the following steps: S31. Preliminarily determine the indicators for collecting historical employee workload data and historical employee behavior data through evaluation and analysis methods; The system collects expert ratings of employees' historical workload and behavior data. The expert rating calculation formula is as follows: ; in, This represents the expert's rating of the employee's historical workload data and the employee's historical behavior data. Indicates the first The expert rating data Indicates the number of experts; Set an expert rating threshold and remove historical workload data and historical behavior data of employees whose expert ratings are lower than the set threshold. Summarize the removed historical workload data and historical behavior data of employees, and preliminarily determine the indicators of historical workload data and historical behavior data of employees through objective analysis methods. Based on the historical workload data and historical behavior data of each employee group, the objective analysis and calculation formula is as follows: ; in, These are indicators that represent the preliminary determination of historical workload data and historical behavior data for each group of employees; S32. Based on data analysis, screen the initially determined historical workload data and historical behavior data indicators of employees, and summarize and determine the employee data performance evaluation indicators.

[0011] Preferably, the data analysis-based screening of the preliminarily determined employee historical workload data and employee historical behavior data indicators, and the aggregation of the employee data efficiency evaluation indicators comprise the following steps: The preliminarily determined employee historical workload data and employee historical behavior data indicators are normalized according to the positive indicator calculation formula and the negative indicator calculation formula; The preliminarily determined employee historical workload data and employee historical behavior data indicators are normalized by the normalization processing method, and a normalized matrix Z is outputted: ; Wherein, represents the normalized i-th group of employee historical workload data and employee historical behavior data indicators, represents the evaluation value of the positive indicators of the i-th group of employee historical workload data and employee historical behavior data, represents the evaluation value of the negative indicators of the i-th group of employee historical workload data and employee historical behavior data; The normalized employee historical workload data and employee historical behavior data indicators are set as the preliminarily determined employee data efficiency evaluation indicators.

[0012] Preferably, based on the determination of the employee data efficiency evaluation indicators, the employee data efficiency scoring system is determined by the system construction method, which comprises the following steps: S41, calculating the initial weight of the preliminarily determined employee data efficiency evaluation indicators by the entropy weight method; The formula for determining the initial weight of the indicators by the entropy weight method is: ; Wherein, is the initial weight of the i-th group of preliminarily determined employee data efficiency evaluation indicators; Based on the calculated initial weight of the indicators, the entropy value of the i-th group of preliminarily determined employee data efficiency evaluation indicators is calculated ; The entropy value calculation formula is as follows: ; Based on the calculated entropy value, the utility value of the i-th group of preliminarily determined employee data efficiency evaluation indicators is calculated , The utility value calculation formula of the employee data efficiency evaluation indicators is as follows:

[0013] Based on the utility value of the preliminarily determined employee data efficiency evaluation indicators, the indicator weight of the preliminarily determined employee data efficiency evaluation indicators is calculated; The index weight determination formula is as follows: ; Wherein, is the index weight of the i-th group of preliminarily determined employee data performance evaluation indexes; S42, after obtaining the index weight of the preliminarily determined employee data performance evaluation index, the employee data performance evaluation index is determined through the performance evaluation method; S43, according to The size of each employee data performance index is sorted, and the employee data performance scoring system is determined through the system construction method.

[0014] Preferably, after obtaining the index weight of the preliminarily determined employee data performance evaluation index, the employee data performance evaluation index is determined through the performance evaluation method, including the following steps: S421, calculate the group utility value of each group of employee historical workload data and employee historical behavior data And individual regret value , the formula is: ; ; Wherein, is the maximum value in the normalized matrix; is the minimum value in the normalized matrix; S422, according to the group utility value of each group of employee historical workload data and employee historical behavior data And individual regret value Calculate the employee data performance evaluation index ; The employee data performance evaluation index calculation formula is: ; Wherein, set λ = [0, 1], λ is the risk preference coefficient, Indicates the minimum value in the group utility value, Indicates the maximum value in the group utility value, Indicates the maximum value in the individual regret value, Indicates the minimum value in the individual regret value.

[0015] Preferably, the combination of data twin method and employee data performance scoring system, through the model construction method, constructs the employee data performance evaluation model, and based on the constructed employee data performance evaluation model, the processed employee workload data and employee behavior data are evaluated. Performance evaluation includes the following steps: S51, initialize the employee historical workload data and employee historical behavior data; Set employee data performance evaluation state set , wherein represents the first state of employee data performance evaluation, wherein represents the jth state of employee data performance evaluation; Set employee historical workload data and employee historical behavior data set , wherein represents the first set of employee historical workload data and employee historical behavior data in the first state of employee data performance evaluation, wherein represents the kth set of employee historical workload data and employee historical behavior data in the jth state of employee data performance evaluation; S52, based on the initialized employee historical workload data and employee historical behavior data, an employee data performance evaluation model is constructed by data twin method; The state transition probability of employee data performance evaluation is calculated by data twin method; The state transition probability calculation formula is as follows: State transition probability distribution: ; , wherein is the state transition probability of employee data performance evaluation calculated by data twin method, represents the state of employee data performance evaluation After the reward function H is processed, the probability of reaching the state of employee data performance evaluation , H represents the reward function, , represents the state The reward value under the first set of employee historical workload data and employee historical behavior data; The state transition probability of employee data performance evaluation is summarized to obtain an employee data performance evaluation model; S53, based on the constructed employee data performance evaluation model, the processed employee workload data and employee behavior data are evaluated.

[0016] The application also provides an employee data performance evaluation system based on data analysis, which is used to realize an employee data performance evaluation method based on data analysis, and the system comprises a data acquisition module, a data processing module, a data analysis module, an efficiency score system construction module and an efficiency evaluation module. The data acquisition module is used to collect employee workload data and employee behavior data; The data processing module is used to process the collected employee workload data and employee behavior data; The data analysis module is used to analyze the collected employee historical workload data and employee historical behavior data; The performance score system construction module is used for constructing an employee data performance score system based on the analysis result of the data analysis module. The performance evaluation module is used for constructing an employee data performance evaluation model, and performing performance evaluation on the processed employee workload data and employee behavior data based on the constructed employee data performance evaluation model.

[0017] The present application has the following advantages: (1) The present application collects employee workload data and employee behavior data in real time through big data technology, processes the collected employee workload data and employee behavior data through data processing, collects employee historical workload data and employee historical behavior data after processing, determines employee data performance evaluation indexes through data analysis, determines an employee data performance score system based on the determined employee data performance evaluation indexes, constructs an employee data performance evaluation model through model construction based on data twin and the employee data performance score system, and performs performance evaluation on the processed employee workload data and employee behavior data based on the constructed employee data performance evaluation model, thereby improving the comprehensiveness of employee performance evaluation.

[0018] (2) The present application collects expert scores of employee historical workload data and employee historical behavior data through expert scoring, analyzes and scores the employee historical workload data and employee historical behavior data through objective analysis and calculation, and determines employee data performance evaluation indexes according to the analysis and scores, thereby improving the reliability of employee performance evaluation.

[0019] (3) The present application normalizes the initially determined employee historical workload data and employee historical behavior data indexes through the combination of positive indexes and negative indexes, accurately determines employee data performance evaluation indexes through entropy weight method and data analysis based on the normalized employee data performance data, and improves the accuracy of employee data performance evaluation.

[0020] (4) The present application initializes employee historical workload data and employee historical behavior data, calculates employee data performance evaluation state transition probability through data twin after initialization, obtains an employee data performance evaluation model by summarizing the employee data performance evaluation state transition probability after calculation, and performs performance evaluation on the processed employee workload data and employee behavior data based on the constructed employee data performance evaluation model, thereby ensuring the real-time performance of employee data performance evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the employee data performance evaluation method of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] In a specific embodiment of the present invention, Reference Figure 1 As shown, this invention provides a method for evaluating employee data performance based on data analysis, comprising the following steps: S1. Collect employee workload and employee behavior data in real time through big data technology; S2. Based on the collected employee workload data and employee behavior data, the data is processed to obtain the processed employee workload data and employee behavior data. S3. Collect historical workload data and historical behavior data of employees, and determine the employee data performance evaluation indicators through data analysis. S4. Based on the determined employee data performance evaluation indicators, establish an employee data performance scoring system through system construction. S5. Combining data twin methods and employee data performance scoring systems, construct an employee data performance evaluation model through model building, and evaluate the performance of processed employee workload data and employee behavior data based on the constructed employee data performance evaluation model. Furthermore, referring to Figure 1 As shown, the real-time collection of employee workload and behavior data using big data technology includes the following steps: The employee workload data includes: work content, work time, and participants; The employee behavior data includes: work behavior and leave request behavior; Furthermore, let's define a triple. Save employee workload data; in, representing the work content in the employee workload data; representing the working time in the employee workload data, representing the participation object in the employee workload data; Further, a Boolean type data is set to represent the employee behavior data, and the employee work behavior is represented by 1, and the employee leave behavior is represented by 0; Further, the employee workload data is quantified, and after quantification, the employee workload data and the employee behavior data are collected in real time through big data technology and saved; The employee work processing flow is set, and the work content in the employee workload data is divided into small tasks based on the set employee work processing flow; The work content includes: working time, required personnel and necessary cost; Further, the divided small tasks are quantified by a quantification method; For example, when the divided small task needs employee work for a day, and costs funds, the quantified small task is represented as: ; Further, referring to Figure 1 , based on the collected employee workload data and employee behavior data, the processed employee workload data and employee behavior data are obtained by data processing, including the following steps: S21, establishing employee workload data and employee behavior data standards; A set of employee workload data must include work content, working time and participation object, and the working time, required personnel and necessary cost in the work content data cannot exceed; A set of employee behavior data must include daily work behavior and leave behavior data, and the daily work behavior and leave behavior data are summarized to construct an array; Further, the constructed array represents a set of employee behavior data; S22, processing the collected employee workload data and employee behavior data based on the established employee workload data and employee behavior data standards; Filtering the employee workload data and employee behavior data based on the Bloom filter algorithm: An array with a length of m is established, and hash functions are selected to traverse each set of data in the employee workload data and employee behavior data, and the traversal results are saved in the array; In the hash function traversal process, when the traversal results of two groups of data are the same, compare each unit data in the two data; When the comparison result is consistent, set the current two data as duplicate data, and delete one group of data; After the traversal is completed, the employee workload data and employee behavior data saved in the array during the traversal are summarized to obtain processed employee workload data and employee behavior data; Further, referring to Figure 1 As shown in the figure, collect employee historical workload data and employee historical behavior data, and determine employee data efficiency evaluation indexes through data analysis method including the following steps: S31, preliminarily determine the indexes of collecting employee historical workload data and employee historical behavior data through evaluation analysis method; Collect the scores of experts on employee historical workload data and employee historical behavior data through expert scoring method; The expert scoring calculation formula is as follows: ; Among them, represents the score of the expert on the employee historical workload data and the employee historical behavior data, represents the score data of the th expert, represents the number of experts; Further, set the expert score threshold, and remove the employee historical workload data and employee historical behavior data whose expert score is lower than the set expert score threshold; Further, summarize the removed employee historical workload data and employee historical behavior data, and preliminarily determine the indexes of employee historical workload data and employee historical behavior data through objective analysis method; Based on each group of employee historical workload data and employee historical behavior data, the objective analysis calculation formula is as follows: ; Among them, represents the indexes preliminarily determined by each group of employee historical workload data and employee historical behavior data; S32, based on the data analysis method, screen the preliminarily determined employee historical workload data and employee historical behavior data indexes, and summarize to determine the employee data efficiency evaluation indexes; According to the positive index calculation formula and the negative index calculation formula, the preliminarily determined employee historical workload data and employee historical behavior data indexes are normalized; Positive index calculation formula: ; Among them, an evaluation value of a positive indicator of the historical workload data and the historical behavior data of the i-th group of employees; a negative indicator calculation formula: ; wherein, an evaluation value of a negative indicator of the historical workload data and the historical behavior data of the i-th group of employees, a maximum value in the indicator data, a minimum value in the indicator data; Further, the initially determined employee historical workload data and employee historical behavior data indicators are normalized by a normalization processing method, and a normalized matrix Z is output: ; wherein, a normalized historical workload data and historical behavior data indicator of the i-th group of employees; The normalized historical workload data and historical behavior data indicators are set as the initially determined employee data performance evaluation indicators; Further, based on the determination of the employee data performance evaluation indicators, an employee data performance scoring system is determined by a system construction method, as shown in Figure 1 The employee data performance scoring system includes the following steps: S41, calculate the initial weight of the initially determined employee data performance evaluation indicators by an entropy weight method; The formula for determining the initial weight of the indicators by the entropy weight method is: ; wherein, is the initial weight of the i-th group of initially determined employee data performance evaluation indicators; Further, based on the calculated initial weight of the indicators, the entropy value of the i-th group of initially determined employee data performance evaluation indicators is calculated ; The entropy value calculation formula is as follows: ; Further, based on the calculated entropy value, the utility value of the i-th group of initially determined employee data performance evaluation indicators is calculated , The utility value calculation formula of the employee data performance evaluation indicators is as follows: ; Further, based on the utility value of the initially determined employee data performance evaluation indicators, the indicator weight of the initially determined employee data performance evaluation indicators is calculated; The indicator weight determination formula is as follows: ; wherein, is the index weight of the employee data performance evaluation index preliminarily determined in the i-th group; S42, after obtaining the index weight of the employee data performance evaluation index preliminarily determined, determining the employee data performance evaluation index through the performance evaluation method; S421, calculating the group utility value of the historical workload data and the historical behavior data of each group of employees and the individual regret value , the formula is: ; ; wherein, is the maximum value in the normalization matrix; is the minimum value in the normalization matrix; S422, according to the group utility value of the historical workload data and the historical behavior data of each group of employees and the individual regret value , calculating the employee data performance evaluation index ; The employee data performance evaluation index calculation formula is: ; wherein, set λ = [0, 1], λ is the risk preference coefficient, represents the minimum value in the group utility value, represents the maximum value in the group utility value, represents the maximum value in the individual regret value, represents the minimum value in the individual regret value; S43, according to , sort each employee data performance index, and determine the employee data performance score system through the system construction method; Further, the sorted employee data performance index is uniformly divided into five parts, and each employee data performance is divided into five parts, and five levels are set according to ; Further, the smaller the value of , the greater the employee data performance, and the greater the performance, the higher the employee work score; Further, referring to Figure 1 , combining the data twin method and the employee data performance score system, an employee data performance evaluation model is constructed through a model construction method, and the processed employee workload data and employee behavior data are evaluated based on the constructed employee data performance evaluation model, including the following steps: S51, initialize the employee historical workload data and the employee historical behavior data; Set the employee data performance evaluation state set , wherein represents the first state of the employee data performance evaluation, wherein represents the jth state of the employee data performance evaluation; Set the employee historical workload data and the employee historical behavior data set , wherein represents the first set of employee historical workload data and employee historical behavior data in the first state of the employee data performance evaluation, wherein represents the kth set of employee historical workload data and employee historical behavior data in the jth state of the employee data performance evaluation; S52, based on the initialized employee historical workload data and the employee historical behavior data, construct an employee data performance evaluation model by a data twin method; Calculate the state transition probability of the employee data performance evaluation by the data twin method; The state transition probability calculation formula is as follows: State transition probability distribution:

[0025] , wherein is the state transition probability of the employee data performance evaluation calculated by the data twin method, represents the state of the employee data performance evaluation after being processed by the reward function H to reach the state of the employee data performance evaluation , H represents the reward function, , represents the state under the first set of employee historical workload data and employee historical behavior data; Further, the employee data performance evaluation state transition probability is summarized to obtain the employee data performance evaluation model; S53, based on the constructed employee data performance evaluation model, perform performance evaluation on the processed employee workload data and employee behavior data; Input the processed employee workload data and employee behavior data and the corresponding employee historical performance evaluation state into the employee data performance evaluation model to obtain the corresponding employee performance evaluation state; Further, record the change amount of each employee performance evaluation state, and set a performance evaluation threshold based on the recorded performance evaluation state change amount; When the employee performance evaluation state exceeds the set performance evaluation threshold, it indicates that the corresponding employee has a work state anomaly and needs to be intervened; In one specific embodiment, the employee data efficiency evaluation system based on data analysis is used to implement an employee data efficiency evaluation method based on data analysis, and the system comprises a data collection module, a data processing module, a data analysis module, an efficiency score system construction module, and an efficiency evaluation module. The data collection module is used to collect employee workload data and employee behavior data. The data processing module is used to process the collected employee workload data and employee behavior data. The data analysis module is used to analyze the collected employee historical workload data and employee historical behavior data. The efficiency score system construction module is used to construct an employee data efficiency score system based on the analysis results of the data analysis module. The efficiency evaluation module is used to construct an employee data efficiency evaluation model, and to perform efficiency evaluation on the processed employee workload data and employee behavior data based on the constructed employee data efficiency evaluation model.

[0026] It should be noted that The above is only an example and explanation of the concept of the present application. Those skilled in the art can make various modifications or supplements to the described specific embodiments or use similar ways to replace them, as long as they do not deviate from the concept of the present application or exceed the scope defined by the present application.

Claims

1. A method for employee data effectiveness evaluation based on data analysis, characterized in that, The method comprises the following steps: S1, collecting employee workload data and employee behavior data in real time through big data technology; S2, processing the collected employee workload data and employee behavior data through data processing to obtain processed employee workload data and employee behavior data; S3, collecting employee historical workload data and employee historical behavior data, and determining employee data efficiency evaluation indexes through data analysis; S4, determining an employee data efficiency scoring system through system construction based on the determined employee data efficiency evaluation indexes; S5, combining the data twin method and the employee data efficiency scoring system, constructing an employee data efficiency evaluation model through model construction, and performing efficiency evaluation on the processed employee workload data and employee behavior data based on the constructed employee data efficiency evaluation model.

2. The method for employee data performance evaluation based on data analysis according to claim 1, characterized in that, The step of collecting employee workload data and employee behavior data in real time through big data technology comprises the following steps: The employee workload data includes work content, work time and participation object; The employee behavior data includes work behavior and leave behavior; Setting a triad Saving employee workload data; wherein, represents a work content in the employee work amount data; represents a work time in the employee work amount data, represents a participation object in the employee work amount data; A Boolean type data is set to represent employee behavior data, employee work behavior is represented by 1, and employee leave behavior is represented by 0; The employee workload data is quantified, and after quantification, the employee workload data and employee behavior data are collected in real time through big data technology and saved.

3. The method for employee data performance evaluation based on data analysis according to claim 1, characterized in that, The step of processing the collected employee workload data and employee behavior data through data processing to obtain processed employee workload data and employee behavior data comprises the following steps: S21, establishing employee workload data and employee behavior data standards; A set of employee workload data must include work content, work time and participation object, and the work duration, required personnel and necessary cost in the work content data cannot exceed; A set of employee behavior data must include daily work behavior and leave behavior data, and an array is constructed by summarizing daily work behavior and leave behavior data; The constructed array represents a set of employee behavior data; S22, processing the collected employee workload data and employee behavior data based on the established employee workload data and employee behavior data standards.

4. The method for employee data performance evaluation based on data analysis according to claim 3, characterized in that, The step of processing the collected employee workload data and employee behavior data based on the established employee workload data and employee behavior data standards comprises the following steps: Filtering the employee workload data and employee behavior data based on the Bloom filter algorithm: An array of length m is established, and a hash function is selected Each group of data in the employee workload data and the employee behavior data is traversed by using the hash function, and the traversal result is saved in the array. During the traversal of the hash function, when the traversal results of two sets of data are the same, compare each unit data in the two data; When the comparison result is consistent, set the current two data as duplicate data, and delete one set of data; After the traversal is completed, the employee workload data and employee behavior data saved in the array during the traversal are summarized to obtain the processed employee workload data and employee behavior data.

5. The method for employee data performance evaluation based on data analysis as claimed in claim 1 wherein, The step of collecting employee historical workload data and employee historical behavior data, and determining employee data efficiency evaluation indexes through data analysis comprises the following steps: S31, the historical workload data and the historical behavior data of the employees are preliminarily determined by an evaluation analysis method; The scores of the experts on the historical workload data and the historical behavior data of the employees are collected through expert scoring; The expert scoring calculation formula is as follows: ； wherein, represents the score of an expert on the employee historical workload data and the employee historical behavior data, represents the score data of the i th expert, represents the number of experts; The expert scoring threshold is set, and the historical workload data and the historical behavior data of the employees with scores lower than the set expert scoring threshold are removed; The removed historical workload data and the historical behavior data of the employees are summarized, and the historical workload data and the historical behavior data of the employees are preliminarily determined by an objective analysis method; Based on the historical workload data and the historical behavior data of each group of employees, the objective analysis calculation formula is as follows: ； wherein, representing the initially determined indicators of historical work volume data and historical behavior data for each group member; S32, the preliminarily determined historical workload data and the historical behavior data of the employees are screened based on a data analysis method, and the employee data efficiency evaluation index is determined.

6. The method for employee data performance evaluation based on data analysis according to claim 5, wherein, The steps of screening the preliminarily determined historical workload data and the historical behavior data of the employees based on a data analysis method and determining the employee data efficiency evaluation index include: The preliminarily determined historical workload data and the historical behavior data of the employees are normalized according to the positive index calculation formula and the negative index calculation formula; The preliminarily determined historical workload data and the historical behavior data of the employees are normalized by the normalization processing method, and a normalized matrix Z is output: ； wherein, represents the normalized historical workload data and historical behavior data indicators of the i-th group of employees, represents the evaluation value of the positive indicators of the historical workload data and historical behavior data of the i-th group of employees, represents the evaluation value of the negative indicators of the historical workload data and historical behavior data of the i-th group of employees. The normalized historical workload data and the historical behavior data of the employees are set as the preliminarily determined employee data efficiency evaluation index.

7. The method for employee data performance evaluation based on data analysis as claimed in claim 1 wherein, Based on the determination of the employee data efficiency evaluation index, the employee data efficiency scoring system is determined by a system construction method, which includes the following steps: S41, the initial weight of the preliminarily determined employee data efficiency evaluation index is calculated by an entropy weight method; The formula for determining the initial weight of the index by the entropy weight method is as follows: ； wherein, is the initial weight of the i-th group of initially determined employee data performance evaluation indicators; calculating an entropy value of the i-th group of the initially determined employee data performance evaluation indexes based on the initial weight of the indexes ; The entropy value calculation formula is as follows: ； calculating an entropy value based on the i set of preliminary determined employee data performance evaluation indicators , The utility value calculation formula of the employee data efficiency evaluation index is as follows: ； The index weight of the preliminarily determined employee data efficiency evaluation index is calculated based on the utility value of the preliminarily determined employee data efficiency evaluation index; The index weight determination formula is as follows: ； wherein, is the index weight of the employee data performance evaluation index preliminarily determined for the i-th group; S42, after obtaining the index weight of the preliminarily determined employee data efficiency evaluation index, the employee data efficiency evaluation index is determined by an efficiency evaluation method; S43、According to The size sorts each employee data performance index, and determines the employee data performance score system through the system construction mode.

8. The method for employee data performance evaluation based on data analysis according to claim 7, characterized in that, The steps of obtaining the index weight of the preliminarily determined employee data efficiency evaluation index and determining the employee data efficiency evaluation index by an efficiency evaluation method include: S421. calculating a group utility value for each group of historical work volume data and historical behavior data of the employees and individual regret values , as follows: ； ； wherein, is the maximum value in the normalized matrix; is the minimum value in the normalized matrix; S422, group utility values from each group member's historical workload data and historical behavior data and individual regret values calculating employee data effectiveness evaluation indicators ; The employee data efficiency evaluation index calculation formula is as follows: ； where λ = [0, 1] is set, and λ is a risk preference coefficient, denotes the minimum value in the group utility value, denotes the maximum value in the group utility value, denotes the maximum value in the individual regret value, denotes the minimum value in the individual regret value.

9. The method for employee data performance evaluation based on data analysis as claimed in claim 1 wherein, The steps of constructing an employee data efficiency evaluation model by a model construction method based on the combination of the data twin method and the employee data efficiency scoring system, and performing efficiency evaluation on the processed employee workload data and employee behavior data based on the constructed employee data efficiency evaluation model include: S51, the historical workload data and the historical behavior data of the employees are initialized; Setting employee data performance evaluation state set wherein represents a first state of the employee data performance evaluation, wherein represents a jth state of the employee data performance evaluation; Setting employee history workload data and employee history behavior data set wherein represents the first group of employee history workload data and employee history behavior data in the first state of the employee data performance evaluation, wherein represents the kth group of employee history workload data and employee history behavior data in the jth state of the employee data performance evaluation; S52, the employee data efficiency evaluation model is constructed based on the initialized historical workload data and the historical behavior data of the employees by a data twin method; The employee data efficiency evaluation state transition probability is calculated by the data twin method; The state transition probability calculation formula is shown as follows: State transition probability distribution: ; wherein, calculating the employee data performance evaluation state transition probability in the data twin way, denotes the employee data performance evaluation state after being processed by the reward function H, H denotes the reward function, denotes the probability of reaching the employee data performance evaluation state , denotes the state the reward value under the historical work data and the historical behavior data of the employees in the first group. The employee data performance evaluation model is obtained by aggregating the employee data performance evaluation state transition probability; S53, based on the constructed employee data performance evaluation model, the processed employee workload data and employee behavior data are evaluated.

10. A system for implementing the method of employee data performance evaluation based on data analysis as claimed in claims 1-9, wherein, It comprises: a data collection module, a data processing module, a data analysis module, an efficiency score system construction module, and an efficiency evaluation module; The data collection module is used to collect employee workload data and employee behavior data; The data processing module is used to process the collected employee workload data and employee behavior data; The data analysis module is used to analyze the collected employee historical workload data and employee historical behavior data; The efficiency score system construction module is used to construct an employee data performance score system based on the analysis results of the data analysis module; The efficiency evaluation module is used to construct an employee data performance evaluation model and evaluate the processed employee workload data and employee behavior data based on the constructed employee data performance evaluation model.

Images