A performance board device data display method and device of a power grid manpower system

Abstract

The present application relates to the technical field of performance data display, and particularly relates to a performance board device data display method and device for a power grid human system. The method comprises the following steps: obtaining basic information and evaluation indexes of each employee in a power grid enterprise in a preset time period, screening reference employees corresponding to each employee according to differences in various types of basic information of each two employees, differences in word vectors corresponding to evaluation indexes of the same dimension of each two departments, and overall differences in performance; and obtaining a to-be-displayed data queue of each employee and displaying the data queue on a performance board by comprehensively considering similarities between performance fluctuation trends of each employee and the corresponding reference employee, and differences between overall performance distributions in a historical time period. The present application evaluates overall similarities of work according to correlations between employees in different departments, screens employees with high overall similarities with each employee in the entire power grid enterprise, and displays performance data of the employees together.

Description

Technical Field

[0001] This invention relates to the field of performance data display technology, specifically to a data display method and device for a performance dashboard in a power grid human resources system. Background Technology

[0002] With the modernization and informatization of enterprise management, performance management, as an important tool for improving organizational efficiency and employee motivation, has been widely applied in various enterprises. In the power grid industry, due to the complexity of its operations and high requirements for safety and stability, employee performance management is particularly important. Traditional performance dashboards, when viewing an employee's performance, often only display the performance of the employee being viewed and other employees in their department. This cannot comprehensively reflect the performance of employees in all departments across the entire power grid company, and thus fails to effectively motivate the entire company's employees. However, in power grid companies, the operations are complex and the requirements for safety and stability are high, and the work of employees in different departments is highly interconnected. Therefore, the performance of employees in different departments also has a certain reference value. Thus, how to evaluate the overall similarity of work based on the correlation between the work of employees in different departments within the power grid company, select employees with high overall similarity to each individual employee across the entire power grid company, and uniformly display their performance on the performance dashboard to mobilize the work enthusiasm of employees throughout the entire power grid company is a problem that needs to be solved. Summary of the Invention

[0003] To address the problem that existing methods cannot evaluate employees across different departments within a power grid company based on overall work similarity, and to identify employees with high overall similarity to each individual across the entire power grid company, the present invention aims to provide a data display method and device for a performance dashboard in a power grid human resources system. The specific technical solution adopted is as follows:

[0004] In a first aspect, the present invention provides a data display method for a performance dashboard device in a power grid human resources system, the method comprising the following steps:

[0005] Acquire basic information and evaluation indicators of different dimensions for each employee in the power grid company within a preset time period, where the preset time period includes historical time periods;

[0006] Analyze the differences in various basic information of each pair of employees to obtain the attribute similarity value of each pair of employees; combine the differences between word vectors corresponding to the same dimension of evaluation indicators of each pair of departments within the historical time period and the overall differences in performance corresponding to the evaluation indicators to determine the similarity indicators between each pair of departments for each dimension.

[0007] By combining the attribute similarity values ​​and the similarity indicators, reference factors are obtained between different employees, and these reference factors are used to filter reference employees for each employee.

[0008] By combining the similarities between the performance fluctuation trends of each employee and their corresponding reference employees over a historical period, the differences between the overall performance distribution, and the corresponding similar indicators, a data queue to be displayed for each employee is obtained and then displayed on the performance dashboard.

[0009] Preferably, the analysis of the differences in various basic information between each pair of employees to obtain the attribute similarity value between each pair of employees includes:

[0010] Based on the differences between the data values ​​of each type of basic information of the first employee and the second employee, the attribute similarity value between the first employee and the second employee is calculated, wherein the difference between the data values ​​is negatively correlated with the attribute similarity value;

[0011] The first employee and the second employee are any two employees in the power grid company.

[0012] Preferably, the step of determining similarity indicators between each pair of departments for each dimension by combining the differences in word vectors corresponding to evaluation indicators of the same dimension within a historical time period and the overall differences in performance corresponding to the evaluation indicators includes:

[0013] The average performance of all employees in each department for each dimension within the historical time period is used as the comprehensive performance value for each department for each dimension.

[0014] Based on the differences between word vectors corresponding to the evaluation indicators of candidate dimensions for each pair of departments within a historical time period and the differences between the comprehensive performance values ​​of candidate dimensions, a similarity index is obtained for each pair of candidate dimensions. The differences between word vectors and the differences between comprehensive performance values ​​are negatively correlated with the similarity index. The candidate dimension can be any dimension.

[0015] Preferably, the step of combining the attribute similarity value and the similarity index to obtain the reference factor between different employees includes:

[0016] Based on the overall distribution of similar indicators across all dimensions for each pair of departments, the comparison factor between each pair of departments is obtained.

[0017] The product of the attribute similarity value between the first employee and the second employee and the comparison factor between the departments of the first employee and the second employee is determined as the reference factor between the first employee and the second employee.

[0018] Preferably, obtaining the comparison factor between each pair of departments based on the overall distribution of similarity indicators across all dimensions includes:

[0019] The normalized result of the average of the similarity indicators across all dimensions for each pair of departments is used as the comparison factor between the corresponding two departments.

[0020] Preferably, the step of using the reference factor to screen reference employees for each employee includes:

[0021] Employees whose reference factor with the candidate employee is greater than the preset reference threshold are used as the reference employees corresponding to the candidate employees.

[0022] The candidate employee can be any employee of the power grid company.

[0023] Preferably, the similarity between the performance fluctuation trends of each employee and its corresponding reference employee within the comprehensive historical time period, the differences between the overall performance distribution, and the corresponding similarity indicators are used to obtain the data queue to be displayed for each employee, including:

[0024] Calculate the similarity of the performance fluctuation trends of candidate employees and their corresponding reference employees for each dimension of evaluation indicators within a historical period.

[0025] Based on the differences in the overall performance distribution of each dimension of the evaluation indicators of the candidate employee and each of their corresponding reference employees within a historical period, the similarity, and the similarity indicators between the candidate employee's department and the departments of each of their corresponding reference employees, a historical performance similarity indicator between the candidate employee and each of their corresponding reference employees is obtained. The differences in the overall performance distribution are negatively correlated with the historical performance similarity indicator, while the similarity and the similarity indicators between the candidate employee's department and the departments of each of their corresponding reference employees are positively correlated with the historical performance similarity indicator.

[0026] Target reference employees were selected based on the aforementioned historical performance similarity indicators to screen candidate employees.

[0027] The performance data of candidate employees and their target reference employees across all dimensions of evaluation indicators constitute the candidate employee's data sequence to be displayed; the preset time period also includes the current time period.

[0028] Preferably, the target reference employees for screening candidate employees based on the historical performance similarity indicators include:

[0029] The candidate employees are ranked in descending order of their historical performance similarity indicators to obtain a reference employee sequence.

[0030] The first preset number of reference employees in the reference employee sequence will be used as the target reference employees for the candidate employees.

[0031] Preferably, the acquisition of word vectors includes:

[0032] NLP technology is used to convert evaluation metrics into corresponding word vectors.

[0033] Secondly, the present invention provides a performance dashboard data display device for a power grid human resources system, the device comprising:

[0034] The data acquisition module is used to acquire basic information and evaluation indicators of different dimensions for each employee in the power grid company within a preset time period, where the preset time period includes historical time periods.

[0035] The similarity index calculation module is used to analyze the differences in various basic information of each and two employees and obtain the attribute similarity value of each and two employees; combined with the differences in word vectors corresponding to the same dimension of evaluation indicators of each and two departments within the historical time period and the overall differences in performance corresponding to the evaluation indicators, the similarity index between each dimension of evaluation indicators of each and two departments is determined.

[0036] The reference employee screening module is used to combine the attribute similarity value and the similarity index to obtain reference factors between different employees, and to screen the reference employees corresponding to each employee using the reference factors.

[0037] The performance display module is used to synthesize the similarities between the performance fluctuation trends of each employee and their corresponding reference employees over a historical period, the differences between the overall performance distribution and the corresponding similar indicators, to obtain the data queue to be displayed for each employee and to display it on the performance dashboard.

[0038] The present invention has at least the following beneficial effects:

[0039] This invention first analyzes the differences in basic information among different employees in a power grid company, obtaining the attribute similarity value between each pair of employees. Employees with similar attributes often exhibit certain similarities in their work performance. Then, it evaluates the similarity between each pair of departments for each dimension of evaluation indicators by combining the differences in word vectors corresponding to the same dimension of evaluation indicators within a historical period and the overall differences in performance corresponding to the evaluation indicators. Based on the above analysis and evaluation results, employees similar to each employee are initially screened, obtaining reference employees for each employee. Considering that the performance of similar employees should be relatively similar within a historical period, a second screening of similar employees is conducted to improve the accuracy of the similar employee screening results. This is achieved by comprehensively considering the similarity between the performance fluctuation trends of each employee and their corresponding reference employees within a historical period, the differences in the overall performance distribution, and similar indicators, resulting in a data queue for each employee to be displayed. The data in the data queue to be displayed is more referential, so it is displayed on the performance dashboard, making the display results more referential. In this way, personalized performance display of the performance dashboard device is realized, improving the reference value of the performance dashboard content for current employees and further stimulating the enthusiasm of employees in the power grid company. Attached Figure Description

[0040] To more clearly illustrate the technical solutions and advantages 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.

[0041] Figure 1 A flowchart illustrating a data display method for a performance dashboard device in a power grid human resources system, provided in an embodiment of the present invention;

[0042] Figure 2 A flowchart illustrating the process of obtaining similar indicators provided in embodiments of the present invention;

[0043] Figure 3 A flowchart illustrating the process of obtaining reference employees as provided in an embodiment of the present invention;

[0044] Figure 4 This is a structural block diagram of a performance dashboard data display device for a power grid human resources system provided in an embodiment of the present invention. Detailed Implementation

[0045] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, describes a data display method and apparatus for a performance dashboard device in a power grid human resource system according to the present invention.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0047] The following description, in conjunction with the accompanying drawings, details the specific scheme of the data display method and device for a performance dashboard in a power grid human resources system provided by the present invention.

[0048] An embodiment of a data display method for a performance dashboard device in a power grid human resource system:

[0049] The specific scenario addressed in this embodiment is as follows: In a power grid company, the work of employees in different departments is highly correlated, meaning they have a certain degree of similarity. Therefore, in order to motivate all employees in the entire power grid company, this embodiment considers the differences in basic information, evaluation indicators, and performance of employees in different departments. In the entire power grid industry, employees whose overall situation is relatively similar to each employee are selected as their corresponding reference employees. The information of the reference employees is then displayed on the performance dashboard to stimulate the work enthusiasm of all employees in the power grid company and promote the overall improvement of the team.

[0050] This embodiment proposes a data display method for a performance dashboard device in a power grid human resource system, such as... Figure 1 As shown in the figure, the data display method of a performance dashboard device for a power grid human resource system in this embodiment includes the following steps:

[0051] Step S1: Obtain basic information and evaluation indicators of different dimensions for each employee in the power grid company within a preset time period.

[0052] First, the basic information of all users in the power grid enterprise and performance data of various evaluation indicators within a preset time period are obtained through the power grid human resources system database. The basic information consists of the user's inherent attributes; in this embodiment, it includes the employee's age, gender, length of service, department, skills, professional title, and job level. There are many types of evaluation indicators, which the implementer selects according to specific circumstances. In this embodiment, the preset time period is the set of all historical moments whose time interval from the current moment is less than or equal to a preset duration. In this embodiment, the preset duration is set to three months. The preset time period consists of historical time periods (two months each) and the current time period (one month each). In other words, the preset time period is divided into historical and current time periods. In specific applications, the implementer can set the preset duration, historical time periods, and current time periods according to specific circumstances. In this embodiment, the performance of each employee for each evaluation indicator within the preset time period and the performance of each employee for each evaluation indicator within the current time period are obtained separately.

[0053] Thus, the evaluation indicators for each dimension and the performance of each evaluation indicator for each dimension of the power grid company have been obtained for each employee within a preset time period. It should be noted that if some employees in certain departments do not have the evaluation indicators for a certain dimension of other employees, then these missing evaluation indicators and their corresponding performance positions are padded with 0, so that the number of dimensions of the evaluation indicators for all employees in this embodiment is equal.

[0054] Step S2: Analyze the differences in various basic information of each pair of employees to obtain the attribute similarity value of each pair of employees; combine the differences between word vectors corresponding to the same dimension of evaluation indicators of each pair of departments within the historical time period and the overall differences in performance corresponding to the evaluation indicators to determine the similarity indicators between each pair of departments for each dimension.

[0055] The human resources of the power grid are typically diverse and complex, with significant differences in basic information among employees, such as age and length of service. Among all employees, those with more similar basic information exhibit higher attribute similarity and are more valuable for comparison. Therefore, the analysis will first examine the differences in basic information among different employees to obtain their attribute similarity values.

[0056] Human resources in power grids typically encompass multiple departments. Therefore, judging performance comparability solely based on the similarity of attributes among different employees is unreasonable; the differences in job content must also be considered. Within a power grid company, the job content of different departments can be reflected through performance indicators. The more similar the performance indicators, the more similar the business content of different departments, and the stronger the comparability.

[0057] To motivate all employees in the power grid company, when displaying performance dashboards for a specific employee, other employees with similar historical performance are selected from across the entire power grid company. These employees' performance is then displayed alongside the current employee's recent performance, allowing the current employee to have a clearer understanding of their performance positioning and providing better motivation. Therefore, it is necessary to analyze the differences in word vectors corresponding to the same dimension of evaluation indicators between any two departments over a historical period, as well as the overall differences in performance corresponding to these indicators, to determine the similarity between evaluation indicators for each dimension in each pair of departments.

[0058] Step S21: Based on the differences in various basic information of each pair of employees, obtain the attribute similarity value of each pair of employees.

[0059] If, for a given employee in a power grid company, the differences between each type of basic information of that employee and each type of basic information of other employees are small, it indicates that the basic attributes of the two employees are similar.

[0060] Taking two employees in a current power grid company as an example, this method can be applied to all other employees. Since the data formats differ between different basic information types, it is first necessary to digitize the non-numerical attributes: for non-numerical basic information, it is mapped to data values; this process is existing technology and will not be elaborated upon here. Then, any two employees in the current power grid company are designated as Employee 1 and Employee 2. Based on the differences in the data values ​​of each type of basic information between Employee 1 and Employee 2, the attribute similarity value between Employee 1 and Employee 2 is calculated, where the difference in data values ​​is negatively correlated with the attribute similarity value.

[0061] The difference between data values ​​can be represented by indicators such as the square of the difference between two data values ​​or the absolute value of the difference between two data values.

[0062] A negative correlation indicates that the dependent variable decreases as the independent variable increases, and vice versa. It can be a subtraction relationship, a division relationship, etc., which is determined by the actual application.

[0063] In this embodiment, the attribute similarity value between the i-th employee and the j-th employee in the power grid company can be represented as:

[0064]

[0065] Where S(i,j) represents the attribute similarity value between the i-th employee and the j-th employee in the power grid company, R represents the number of basic information categories, and B i,r B represents the data value of the r-th type of basic information of the i-th employee. j,rLet || represent the data value of the r-th type of basic information of the j-th employee, || represents the absolute value sign, and exp() represents the exponential function with the natural constant as the base.

[0066] |B i,r -B j,r This value represents the difference between the data values ​​of the r-th type of basic information of the i-th employee and the j-th employee. The larger the value, the greater the difference between the two. This value reflects the overall difference between the basic information of employee i and employee j. The larger the value, the greater the overall difference between the basic information of employee i and employee j. When the difference between the data values ​​of the basic information of employee i and employee j is greater, it means that the basic information of employee i and employee j is less similar, that is, the smaller the attribute similarity value between employee i and employee j.

[0067] Using the above method, the attribute similarity value of every two employees in a power grid company can be obtained.

[0068] Step S22: Based on the differences between word vectors corresponding to the same dimension of evaluation indicators for each of the two departments within the historical time period and the overall differences in performance corresponding to the evaluation indicators, determine the similarity indicators between each of the two departments for each dimension.

[0069] While the performance indicators of different departments may be similar, their comparability varies due to differences in their business operations. For example, although different external liaison departments all deal with clients, there are significant differences in the indicator values ​​for corporate clients and individual clients. Therefore, it is necessary to combine the specific indicator values ​​of each department to make a comparability judgment.

[0070] Based on this, Natural Language Processing (NLP) technology is used to convert all evaluation indicators into corresponding word vectors. Then, the differences between the word vectors corresponding to the same dimension of evaluation indicators for each pair of departments and the overall differences in performance corresponding to the evaluation indicators are comprehensively analyzed over historical periods to evaluate each pair of departments for each dimension of evaluation indicators.

[0071] Specifically, based on the differences between word vectors corresponding to the evaluation indicators of each pair of candidate dimensions within a historical time period and the differences between the comprehensive performance values ​​of the candidate dimensions, a similarity index is obtained for each pair of candidate dimensions. The differences between word vectors and the differences between comprehensive performance values ​​are both negatively correlated with the similarity index; the candidate dimension can be any dimension. For example... Figure 2As shown in the figure, this is a flowchart of the process for obtaining similarity indicators. Using this method, similarity indicators for each dimension of every two departments can be obtained. Then, based on the overall distribution of similarity indicators across all dimensions for every two departments, the comparison factor between each two departments can be obtained.

[0072] For a department within a power grid company, the overall distribution of performance corresponding to each dimension of the evaluation indicators can be represented by indicators such as the mean, mode, median, and cumulative sum of the performance of all employees in that department for each dimension of the evaluation indicators.

[0073] In this embodiment, the average performance of all employees in each department for each dimension of evaluation indicators is used to represent the overall distribution of performance for each department for each dimension of evaluation indicators. That is, the average performance of all employees in each department for each dimension of evaluation indicators is used as the comprehensive performance value for each department for each dimension. It should be noted that each department has one comprehensive performance value for each dimension. The overall difference in performance corresponding to evaluation indicators can be represented by indicators such as the square of the difference between two comprehensive performance values ​​or the absolute value of the difference between two comprehensive performance values.

[0074] In this embodiment, the absolute value of the difference between the comprehensive performance values ​​is used to characterize the difference between the two comprehensive performance values, that is, the absolute value of the difference between the two comprehensive performance values ​​is used as the difference between the two comprehensive performance values.

[0075] The differences between word vectors can be represented by the negative correlation mapping value of cosine similarity, Manhattan distance, Minkowski distance, dynamic time-warped distance, or the negative correlation mapping value of Jaccard similarity coefficient, etc. Specifically, the smaller the cosine similarity, the larger the negative correlation mapping value, indicating a greater difference between the two word vectors, and thus a less similar pair. Similarly, a larger Manhattan distance, a larger Minkowski distance, a larger dynamic time-warped distance, and a smaller Jaccard similarity coefficient all indicate a greater difference between the two word vectors. The overall distribution of similarity indicators across all dimensions can be represented using the mean, mode, median, and cumulative sum of all similarity indicators.

[0076] The negative correlation mapping value of cosine similarity between word vectors is used to characterize the differences between them. Specifically, for any two word vectors, the cosine similarity between them is calculated, and the difference between the two word vectors is represented by an exponential function with the natural constant as the base and the negative cosine similarity as the exponent. The normalized result of the average of all dimensions of similarity indicators for each pair of departments is used as the comparison factor between the corresponding two departments.

[0077] In this embodiment, the comparison factor between the u-th department and the v-th department in the power grid enterprise can be expressed as:

[0078]

[0079] in, Let C(u,v) represent the similarity index between the u-th department and the v-th department in a power grid enterprise, representing the k-th dimension of the evaluation index. Let C(u,v) represent the comparison factor between the u-th department and the v-th department in the power grid enterprise, and let K represent the number of dimensions of the evaluation index. This represents the difference between the word vectors corresponding to the evaluation indicators of the u-th department and the v-th department in the k-th dimension within a historical time period. This represents the difference between the comprehensive performance values ​​of the u-th department and the v-th department in the k-th dimension within a historical time period. λ1 represents the preset first adjustment parameter, which is greater than 0. sigmoid() represents the normalization function.

[0080] In this embodiment, a preset first adjustment factor is introduced into the calculation formula for the similarity index to prevent the denominator from being 0. In this embodiment, the preset first adjustment factor is 0.01. In specific applications, implementers can set it according to specific circumstances. The smaller the difference between the comprehensive performance values ​​of the u-th department and the v-th department in the k-th dimension, and the smaller the difference between the comprehensive performance values, the more similar the business of the u-th department and the v-th department in the k-th dimension is within the historical time period. The greater the referenceability of the u-th department and the v-th department regarding the k-th dimension, that is, the greater the similarity index between the evaluation indicators of the u-th department and the v-th department in the k-th dimension. When the referenceability of all dimensions of the u-th department and the v-th department is greater, it indicates that the similarity of the work of the employees in these two departments is higher, that is, the greater the comparison factor between the u-th department and the v-th department in the power grid enterprise.

[0081] Using the above method, the comparison factor between every two departments in a power grid company can be obtained.

[0082] Step S3: Combine the attribute similarity value and the similarity index to obtain the reference factor between different employees, and use the reference factor to filter the reference employees corresponding to each employee.

[0083] When displaying employee performance on a performance dashboard, it's necessary to showcase the performance of employees with similar situations to the current employee to motivate them. Therefore, the first step is to select employees with similar situations. This embodiment evaluates the similarity between employees from two perspectives: the similarity of basic information and the similarity of performance corresponding to evaluation indicators over historical time periods. This comprehensive consideration of similarity between different employees allows for the selection of employees similar to each current employee, who are then designated as reference employees.

[0084] Step S31: Combine the attribute similarity value and the similarity index to obtain the reference factor between different employees.

[0085] In this embodiment, the first employee and the second employee are still used as examples for explanation. The method provided in this embodiment can be used to process any other two employees.

[0086] Specifically, the reference factor between the first and second employees is determined by multiplying the similarity value of their attributes by the comparison factor between the departments of the first and second employees. It should be noted that if the first and second employees are in the same department, the comparison factor between their departments is set to 1.

[0087] Using this method, reference factors between every two employees in a power grid company can be obtained.

[0088] Step S32: Use the reference factors to screen the reference employees corresponding to each employee.

[0089] This embodiment has determined the reference factor between each employee and other employees. The larger the reference factor, the higher the overall similarity of the work among the corresponding employees, and the more referential and comparable their performance is. Therefore, for any employee, employees in the current power grid company whose reference factor with that employee is greater than a preset reference threshold are taken as the corresponding reference employees. In this embodiment, the preset reference threshold is 0.5. In specific applications, the implementer can set it according to specific circumstances.

[0090] Thus, using the above method, reference employees for each employee have been selected, such as... Figure 3 As shown, this diagram is a flowchart of the process for obtaining reference employees.

[0091] Step S4: By combining the similarities between the performance fluctuation trends of each employee and their corresponding reference employees within the historical time period, the differences between the overall performance distribution, and the corresponding similar indicators, a data queue to be displayed for each employee is obtained and displayed on the performance dashboard.

[0092] For any given employee, the more similar their performance is to that of other employees within the power grid company over a historical period, the more valuable their performance is for reference in the current period. Therefore, it is necessary to further screen reference employees by considering the similarity in performance fluctuation trends between each employee and their corresponding reference employees over a historical period, the differences in overall performance distribution, and similarity indicators. This will ensure that the final selected employees have a higher degree of similarity to the current employee, thereby improving the credibility of the performance display results.

[0093] Specifically, for any employee, the performance of each evaluation indicator across all dimensions is sorted chronologically to obtain the performance sequence for each dimension of the employee's historical data. The following analysis uses a candidate employee as an example; the method provided in this embodiment can be applied to other employees. The similarity between the performance sequences of each candidate employee and each corresponding reference employee across all dimensions of the evaluation indicators is calculated. This similarity is used to characterize the similarity of the performance fluctuation trends of each reference employee across all dimensions of the evaluation indicators over the historical time period. It should be noted that similarity is calculated only between performance sequences corresponding to the same dimension of the evaluation indicators; similarity is not calculated between performance sequences corresponding to different dimensions of the evaluation indicators. The similarity between two performance sequences can be represented by indicators such as correlation coefficient, negative correlation mapping value of DTW distance, and negative correlation mapping value of Euclidean distance. In this embodiment, the correlation coefficient is used.

[0094] Furthermore, based on the differences in the overall performance distribution of each dimension of the evaluation indicators of the candidate employee and each of their corresponding reference employees within a historical period, the similarity, and the similarity indicators between the candidate employee's department and the departments of each of their corresponding reference employees, a historical performance similarity indicator between the candidate employee and each of their corresponding reference employees is obtained. The differences in the overall performance distribution are negatively correlated with the historical performance similarity indicator, while the similarity and the similarity indicators between the candidate employee's department and the departments of each of their corresponding reference employees are positively correlated with the historical performance similarity indicator.

[0095] For any employee in a power grid company, the overall performance distribution over a historical period can be represented by the mean, mode, median, and cumulative sum of all performance metrics for each dimension of the employee's evaluation over that historical period. In this embodiment, the average of all performance metrics for each dimension of the employee's evaluation over that historical period is used to characterize the overall performance distribution; that is, the average of all performance metrics for each dimension of the employee's evaluation over that historical period is used as the overall performance distribution for each dimension of the employee's evaluation over that historical period.

[0096] The difference between overall performance distributions can be represented by indicators such as the square of the difference between two overall performance distributions or the absolute value of the difference between two overall performance distributions. In this embodiment, the absolute value of the difference between two overall performance distributions is used to characterize the corresponding difference; that is, the absolute value of the difference between two overall performance distributions is taken as the difference between the two.

[0097] A positive correlation indicates that the dependent variable increases as the independent variable increases, and decreases as the independent variable decreases. Specific relationships can include multiplication, addition, or exponential functions. A negative correlation indicates that the dependent variable decreases as the independent variable increases, and increases as the independent variable decreases. Such relationships can include subtraction or division, and the specific relationship depends on the application.

[0098] In this embodiment, a specific formula for calculating the historical performance similarity index is given. The historical performance similarity index between the i-th employee and the corresponding f-th reference employee in a power grid company can be expressed as:

[0099]

[0100] Where Q(i,f) represents the historical performance similarity index between the i-th employee and the f-th reference employee in the power grid company, K represents the number of dimensions of the evaluation index, and M i,k Let represent the performance sequence corresponding to the k-th dimension of the evaluation index for the i-th employee. Let represent the performance sequence corresponding to the k-th dimension of the evaluation index for the f-th reference employee corresponding to the i-th employee. M represents i,k and Correlation coefficient, T i,k Let represent the overall performance distribution of the k-th dimension of the evaluation indicators for the i-th employee within a historical time period. X represents the overall performance distribution of the k-th dimension of the evaluation indicators for the f-th reference employee corresponding to the i-th employee within a historical time period. k (i,f) represents the similarity index between the department of the i-th employee and the evaluation index of the k-th dimension of the department of the corresponding f-th reference employee, and λ2 represents the preset first adjustment parameter, which is greater than 0.

[0101] In this embodiment, a preset second adjustment factor is introduced into the calculation formula of the historical performance similarity index to prevent the denominator from being 0. In this embodiment, the preset second adjustment factor is 0.01. In specific applications, implementers can set it according to specific circumstances. This represents the difference between the overall performance distribution of the k-th dimension of the evaluation indicators of the i-th employee and its corresponding f-th reference employee. The larger this value, the greater the difference between the two. When the correlation coefficient of the performance sequences corresponding to the evaluation indicators of the i-th employee and its corresponding f-th reference employee is larger, the difference between the overall performance distribution of the evaluation indicators of the i-th employee and its corresponding f-th reference employee is smaller, and the similarity index of all dimensions of the evaluation indicators between the department of the i-th employee and the department of its corresponding f-th reference employee is larger, it indicates a higher similarity between the i-th employee and its corresponding f-th reference employee; that is, a greater historical performance similarity index between the i-th employee and its corresponding f-th reference employee.

[0102] It should be noted that if two employees are in the same department, then in this embodiment, the similarity index between the evaluation indicators of each dimension of their department is set to 1.

[0103] Using the above method, we can obtain historical performance similarity indicators between candidate employees and their corresponding reference employees.

[0104] For candidate employees, reference employees are sorted in descending order of historical performance similarity indicators to obtain a reference employee sequence. The top preset number of reference employees in the reference employee sequence are used as target reference employees for the candidate employees. In this embodiment, the preset number is 5, but in specific applications, the implementer can set it according to the specific situation.

[0105] The performance data of candidate employees and their target reference employees across all dimensions of evaluation indicators constitute the candidate employee's data sequence to be displayed. When viewing the candidate employee's performance, the candidate employee's data sequence to be displayed is shown on the performance dashboard device of the power grid human resources system.

[0106] The method provided in this embodiment can be used to process the data of each employee in the power grid company, obtain the data sequence to be displayed for each employee, and display it on the performance dashboard device to publicly and intuitively show the work performance of the power grid company employees and stimulate their work enthusiasm.

[0107] This embodiment first analyzes the differences in basic information among different employees in a power grid company, obtaining the attribute similarity value for every two employees. Employees with similar attributes often have certain similarities in their work performance. Then, it combines the differences in word vectors corresponding to the same dimension of evaluation indicators between two departments over a historical period, as well as the overall differences in performance corresponding to the evaluation indicators, to evaluate the similarity between each dimension of evaluation indicators between two departments. Based on the above analysis and evaluation results, employees similar to each employee are initially screened, obtaining reference employees for each employee. Considering that the performance of similar employees should be relatively similar over a historical period, in order to improve the accuracy of the similar employee screening results, a second screening of similar employees is conducted by comprehensively considering the similarity between the performance fluctuation trends of each employee and their corresponding reference employees over a historical period, the differences in the overall performance distribution, and similar indicators, obtaining a data queue to be displayed for each employee. The data in the data queue to be displayed is more referential, so it is displayed on the performance dashboard, making the display results more referential. In this way, personalized performance display of the performance dashboard device is realized, improving the reference value of the performance dashboard content for current employees and further stimulating the enthusiasm of employees in the power grid company.

[0108] An embodiment of a performance dashboard data display device for a power grid human resource system:

[0109] See Figure 4 The diagram illustrates a structural block diagram of a performance dashboard data display device for a power grid human resources system according to an embodiment of the present invention. The device may include a data acquisition module, a similar indicator calculation module, a reference employee screening module, and a performance display module.

[0110] The data acquisition module is used to acquire basic information and evaluation indicators of different dimensions for each employee in the power grid company within a preset time period, including historical time periods.

[0111] The similarity index calculation module is used to analyze the differences in various basic information of each and two employees and obtain the attribute similarity value of each and two employees; combined with the differences in word vectors corresponding to the same dimension of evaluation indicators of each and two departments within the historical time period and the overall differences in performance corresponding to the evaluation indicators, the similarity index between each dimension of evaluation indicators of each and two departments is determined.

[0112] The reference employee screening module is used to combine the attribute similarity value and the similarity index to obtain reference factors between different employees, and to screen the reference employees corresponding to each employee using the reference factors.

[0113] The performance display module is used to synthesize the similarities between the performance fluctuation trends of each employee and their corresponding reference employees over a historical period, the differences between the overall performance distribution and the corresponding similar indicators, to obtain the data queue to be displayed for each employee and to display it on the performance dashboard.

[0114] The methods performed by these modules have been described in detail in an embodiment of a data display method for a performance dashboard device in a power grid human resources system.

[0115] In other embodiments, a computer program product is also provided, which, when run on a computer, causes the computer to perform the aforementioned related steps to realize the data display method of the performance dashboard device for a power grid human resources system provided in the above embodiments.

[0116] In other embodiments, a computer-readable storage medium is also provided, which stores computer program code. When the computer program code is run on a computer, the computer executes the above-described related method steps to implement the data display method of the performance dashboard device for a power grid human resources system provided in the above embodiments.

[0117] The systems, devices, computer program products, and computer-readable storage media provided are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0118] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for displaying data from a performance dashboard device in a power grid human resource system, characterized in that, The method includes the following steps: Acquire basic information and evaluation indicators of different dimensions for each employee in the power grid company within a preset time period, where the preset time period includes historical time periods; The differences in various basic information of each pair of employees are analyzed to obtain the attribute similarity value of each pair of employees. Combining the differences between word vectors corresponding to the same dimension of evaluation indicators of each pair of departments within a historical time period and the overall differences in performance corresponding to the evaluation indicators, the similarity index between each pair of departments for each dimension is determined. The similarity index is obtained based on the differences between word vectors corresponding to the evaluation indicators of candidate dimensions of each pair of departments within a historical time period and the differences between the comprehensive performance values ​​of candidate dimensions. The differences between word vectors and the differences between comprehensive performance values ​​are negatively correlated with the similarity index. The candidate dimension can be any dimension, and the comprehensive performance value of each dimension of each department is the average performance of all employees in each department for each dimension of evaluation indicators within a historical time period. The reference factor between different employees is obtained by combining the attribute similarity value and the similarity index. The reference factor is then used to screen reference employees for each employee. The reference employee corresponding to a candidate employee is an employee whose reference factor is greater than a preset reference threshold. The candidate employee can be any employee in the power grid company. The step of obtaining the reference factor between different employees by combining the attribute similarity value and the similarity index includes: obtaining the comparison factor between each pair of departments based on the overall distribution of similarity indicators across all dimensions of each pair of departments; and determining the reference factor between the first employee and the second employee as the product of the attribute similarity value between the first employee and the second employee and the comparison factor between the departments of the first employee and the second employee. By combining the similarities between the performance fluctuation trends of each employee and their corresponding reference employees over a historical period, the differences between the overall performance distribution, and the corresponding similar indicators, a data queue to be displayed for each employee is obtained and then displayed on the performance dashboard.

2. The data display method for a performance dashboard device in a power grid human resource system according to claim 1, characterized in that, The analysis examines the differences in various basic information between each pair of employees to obtain the attribute similarity value between each pair of employees, including: Based on the differences between the data values ​​of each type of basic information of the first employee and the second employee, the attribute similarity value between the first employee and the second employee is calculated, wherein the difference between the data values ​​is negatively correlated with the attribute similarity value; The first employee and the second employee are any two employees in the power grid company.

3. The data display method for a performance dashboard device in a power grid human resource system according to claim 1, characterized in that, The comparison factor between each pair of departments is obtained based on the overall distribution of similarity indicators across all dimensions, including: The normalized result of the average of the similarity indicators across all dimensions for each pair of departments is used as the comparison factor between the corresponding two departments.

4. The data display method for a performance dashboard device in a power grid human resource system according to claim 1, characterized in that, By comprehensively analyzing the similarities between the performance fluctuation trends of each employee and their corresponding reference employees within a historical time period, the differences in the overall performance distribution, and the corresponding similarity indicators, a data queue to be displayed for each employee is obtained, including: Calculate the similarity of the performance fluctuation trends of candidate employees and their corresponding reference employees for each dimension of evaluation indicators within a historical period. Based on the differences in the overall performance distribution of each dimension of the evaluation indicators of the candidate employee and each of their corresponding reference employees within a historical period, the similarity, and the similarity indicators between the candidate employee's department and the departments of each of their corresponding reference employees, a historical performance similarity indicator between the candidate employee and each of their corresponding reference employees is obtained. The differences in the overall performance distribution are negatively correlated with the historical performance similarity indicator, while the similarity and the similarity indicators between the candidate employee's department and the departments of each of their corresponding reference employees are positively correlated with the historical performance similarity indicator. Target reference employees were selected based on the aforementioned historical performance similarity indicators to screen candidate employees. The performance data of candidate employees and their target reference employees across all dimensions of evaluation indicators constitute the candidate employee's data sequence to be displayed; the preset time period also includes the current time period.

5. The data display method for a performance dashboard device in a power grid human resource system according to claim 4, characterized in that, The target reference employees for screening candidate employees based on the historical performance similarity indicators include: The candidate employees are ranked in descending order of their historical performance similarity indicators to obtain a reference employee sequence. The first preset number of reference employees in the reference employee sequence will be used as the target reference employees for the candidate employees.

6. The data display method for a performance dashboard device in a power grid human resource system according to claim 1, characterized in that, The acquisition of word vectors includes: NLP technology is used to convert evaluation metrics into corresponding word vectors.

7. A performance dashboard data display device for a power grid human resource system, characterized in that, The device includes: The data acquisition module is used to acquire basic information and evaluation indicators of different dimensions for each employee in the power grid company within a preset time period, where the preset time period includes historical time periods. The similarity index calculation module is used to analyze the differences in various basic information of each and two employees to obtain the attribute similarity value of each and two employees. Combining the differences between word vectors corresponding to the same dimension of evaluation indicators of each and two departments within a historical time period and the overall differences in performance corresponding to the evaluation indicators, the similarity index between each and two departments for each dimension of evaluation indicators is determined. The similarity index is obtained based on the differences between word vectors corresponding to the evaluation indicators of candidate dimensions of each and two departments within a historical time period and the differences between the comprehensive performance values ​​of candidate dimensions. The differences between word vectors and the differences between comprehensive performance values ​​are negatively correlated with the similarity index. The candidate dimension can be any dimension, and the comprehensive performance value of each dimension of each department is the average performance of all employees in each department within a historical time period for each dimension of evaluation indicators. The reference employee screening module is used to obtain reference factors between different employees by combining the attribute similarity values ​​and the similarity indicators, and to screen reference employees corresponding to each employee using the reference factors; the reference employees corresponding to the candidate employees are employees whose reference factors with the candidate employees are greater than a preset reference threshold, and the candidate employees are any employees in the power grid company; the step of obtaining reference factors between different employees by combining the attribute similarity values ​​and the similarity indicators includes: obtaining the comparison factor between each pair of departments based on the overall distribution of similarity indicators of all dimensions of each pair of departments; and determining the reference factor between the first employee and the second employee as the product of the attribute similarity value between the first employee and the second employee and the comparison factor between the departments of the first employee and the second employee. The performance display module is used to synthesize the similarities between the performance fluctuation trends of each employee and their corresponding reference employees over a historical period, the differences between the overall performance distribution and the corresponding similar indicators, to obtain the data queue to be displayed for each employee and to display it on the performance dashboard.

Images