Intelligent salary management method and system for human resource industry

Abstract

The invention discloses an intelligent salary management method and system for the human resource industry, and relates to the technical field of data processing, and the method comprises the steps: carrying out the abnormal screening of to-be-counted salary data; performing performance evaluation based on the to-be-counted salary data; based on the to-be-counted salary data and the performance evaluation result, performing salary accounting by using fluctuation anomaly analysis to obtain target salary data; on the basis of the target salary data, performance target correction data and work target correction data are obtained through salary influence analysis; acquiring data attributes of to-be-desensitized data in the target salary data, the performance target correction data and the work target correction data to determine a desensitization mode, and desensitizing the to-be-desensitized data based on the desensitization mode; and storing the target salary data, the performance target correction data and the work target correction data in a storage node. The intelligent degree of salary management is greatly improved, and the salary management achieves a more ideal effect.

Description

Technical Field

[0001] The present invention mainly relates to the field of data processing technology, and in particular to an intelligent salary management method and system for the human resources industry. Background Art

[0002] With the increase in the demand for employment in enterprises and the rise of flexible employment models, the human resources industry is also developing continuously. For the human resources industry, the salary management of personnel is a very important work content. At present, in the salary management of the human resources industry, the performance evaluation in the salary data is mostly carried out by relevant personnel according to the analysis data, but this method is too dependent on the professional qualities of the relevant personnel, and its human cost is high and inefficient. At the same time, in the current salary management, after the salary data of the personnel is counted according to the performance evaluation results and salary data, only a simple check is performed to determine the final salary data, and the abnormal analysis of salary fluctuations is not considered, resulting in a large error rate in salary calculation. And for salary management, how to correct the corresponding performance goals and work content goals according to the salary of the personnel is also a very important part, which affects the development of enterprises and personnel. After obtaining the salary data and work goal correction data, the data needs to be desensitized to protect the privacy of the relevant personnel. At present, data desensitization is usually performed through data perturbation methods, but the data desensitization accuracy of this method is insufficient, resulting in the inability to protect the privacy of personnel well, so that the reliability of salary management cannot be effectively guaranteed. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a method and system for intelligent salary management for the human resources industry, which greatly improves the intelligence level of salary management and enables salary management to achieve more ideal results.

[0004] In order to solve the above technical problems, the present invention provides a method for intelligent salary management in the human resources industry, the method comprising:

[0005] Obtaining the salary data to be counted of each relevant person, performing abnormal screening on the salary data to be counted, and obtaining the salary data to be counted after the abnormal screening;

[0006] Perform performance evaluation based on the salary data to be counted after abnormal screening and obtain performance evaluation results;

[0007] Based on the salary data to be counted and the performance evaluation results after abnormal screening, salary calculation is performed using fluctuation abnormality analysis to obtain the target salary data of each relevant person;

[0008] Based on the target salary data, using salary impact analysis to perform a revised analysis on the performance goals and work goals of each relevant person, and obtain performance goal revised data and work goal revised data;

[0009] Obtaining data attributes of the data to be desensitized in the target salary data, performance target revised data, and work target revised data, determining a desensitization method based on the data attributes combined with attribute feature analysis, and performing desensitization processing on the target salary data, performance target revised data, and work target revised data based on the desensitization method to obtain the target salary data, performance target revised data, and work target revised data after desensitization processing;

[0010] The desensitized target salary data, performance target revised data and work target revised data are stored in the storage node corresponding to the database.

[0011] Optionally, performing abnormal screening on the salary data to be counted to obtain the salary data to be counted after the abnormal screening includes:

[0012] Acquire a single data exception rule and a global data exception rule, and perform identification processing on the salary data to be counted based on the single data exception rule and the global data exception rule to obtain the salary data to be counted after identification processing;

[0013] A binary tree is established, and abnormal screening is performed on the salary data to be counted after the identification processing based on the binary tree to obtain the salary data to be counted after the abnormal screening processing.

[0014] Optionally, performing abnormal screening on the salary data to be counted after the identification processing based on the binary tree to obtain the salary data to be counted after the abnormal screening processing includes:

[0015] Converting the binary tree into a balanced binary tree, and dividing the training data set based on the balanced binary tree to obtain a normal training data set and an abnormal training data set;

[0016] Training an abnormal character recognition model based on the normal training data set and the abnormal training data set to obtain a trained abnormal character recognition model;

[0017] Based on the trained abnormal character recognition model, abnormal characters are recognized on the salary data to be counted after identification processing to obtain the salary data to be counted after abnormal character recognition, and abnormal screening is performed on the salary data to be counted after abnormal character recognition to obtain the salary data to be counted after abnormal screening processing.

[0018] Optionally, the performance evaluation is performed based on the salary data to be counted after the abnormal screening process to obtain the performance evaluation result, including:

[0019] Extract working hours data, personnel cooperation data and evaluation text data from the salary data to be counted after abnormal screening;

[0020] Obtaining the degree of correlation between the working time data and the performance data, and performing an initial performance evaluation based on the degree of correlation to obtain an initial performance evaluation result;

[0021] Segmenting the evaluation text data to obtain a number of segmented word groups, generating a word vector matrix based on the number of segmented word groups, and determining the ability evaluation level based on the word vector matrix;

[0022] Based on the personnel cooperation data, cooperation contribution analysis is performed using a cooperation network model to obtain cooperation contribution data;

[0023] The initial performance evaluation result is adjusted based on the capability evaluation level and the cooperation contribution data to obtain a performance evaluation result.

[0024] Optionally, the salary data to be counted and the performance evaluation results after the abnormal screening process are used to perform salary calculation using fluctuation abnormality analysis to obtain the target salary data of each relevant person, including:

[0025] Obtaining salary calculation rules corresponding to each relevant person, performing salary statistics based on the salary calculation rules using the salary data to be counted after abnormal screening and the performance evaluation results, and obtaining salary data of each relevant person;

[0026] Obtaining the call address of the adapted accounting engine based on the load balancing algorithm, and transmitting the salary data of each relevant person to the corresponding accounting engine based on the call address;

[0027] The accounting engine obtains the same-level salary data of a number of personnel of the same level corresponding to each relevant personnel, and performs data fluctuation characteristic analysis based on the same-level salary data to obtain fluctuation characteristic data;

[0028] Performing singular point identification on the salary data based on the fluctuation characteristic data to obtain a singular point identification result;

[0029] The salary data of each relevant person is verified and processed based on the singular point identification result and the fluctuation characteristic data to obtain a verification result, and the target salary data of each relevant person is determined based on the verification result.

[0030] Optionally, the revising analysis of the performance targets and work targets of each relevant person using the remuneration impact analysis based on the target remuneration data to obtain performance target revised data and work target revised data includes:

[0031] Obtaining salary-related data, and performing salary impact analysis based on the salary-related data and target salary data using salary indicators and constraints to obtain salary impact analysis data;

[0032] Calculating the work value using a value analysis model based on the salary impact analysis data, and comparing the work value with a preset threshold to obtain a comparison result;

[0033] Based on the comparison results, a revised analysis of the performance goals and work goals of each relevant person is performed to obtain performance goal revised data and work goal revised data.

[0034] Optionally, obtaining data attributes of the data to be desensitized in the target salary data, performance target revised data, and work target revised data, and determining a desensitization method based on the data attributes combined with attribute feature analysis includes:

[0035] Obtain sample sensitive data and select a corresponding desensitization algorithm based on the data attributes of the sample sensitive data;

[0036] Adding the corresponding desensitization algorithm as a desensitization method label to the sample sensitive data, and building a desensitization method database based on the sample sensitive data after adding the desensitization method label;

[0037] Identify the data attributes of the data to be desensitized in the target salary data, performance target correction data and work target correction data, perform attribute feature analysis based on the data attributes of the data to be desensitized and the data in the desensitization method database, obtain the desensitization method label corresponding to the data to be desensitized, and determine the desensitization method of the data to be desensitized based on the corresponding desensitization method label.

[0038] Optionally, performing desensitization processing on the target salary data, the performance target revised data, and the work target revised data based on the desensitization method to obtain the desensitized target salary data, the performance target revised data, and the work target revised data includes:

[0039] Based on the programmable logic gate array comparator, the target position corresponding to the data to be desensitized is marked in the target salary data, the performance target correction data and the work target correction data;

[0040] Acquire a function stack pointer array based on the target pointer, and acquire a corresponding compact function name string array based on the function stack pointer array;

[0041] Converting the compact function name string array into a corresponding standard function string based on a demangle function, and obtaining a target replacement character based on the corresponding standard function string;

[0042] Based on the desensitizing method, the target replacement character is used to perform character replacement processing at the target position corresponding to the data to be desensitized, so as to obtain the target salary data, performance target correction data and work target correction data after desensitization processing.

[0043] Optionally, storing the desensitized target salary data, performance target revised data, and work target revised data in a storage node corresponding to the database includes:

[0044] Obtain the priority coefficient and node encryption summary value of each storage node in the database, and perform activity analysis on the target salary data, performance target correction data, and work target correction data after desensitization processing to obtain corresponding activity information, and determine the data storage strategy based on the activity information, priority coefficient, and node encryption summary value;

[0045] Based on the data storage strategy, the desensitized target salary data, performance target revision data and work target revision data are stored in the storage node corresponding to the database.

[0046] In addition, the present invention also provides an intelligent salary management system for the human resources industry, the system comprising:

[0047] Data anomaly screening module: used to obtain the salary data to be counted of each relevant person, perform anomaly screening on the salary data to be counted, and obtain the salary data to be counted after the anomaly screening;

[0048] Performance evaluation module: used to evaluate performance based on the salary data to be counted after abnormal screening and obtain performance evaluation results;

[0049] Salary calculation module: used to calculate salary based on the salary data to be counted and the performance evaluation results after abnormal screening, using fluctuation anomaly analysis to obtain the target salary data of each relevant person;

[0050] Target revision analysis module: used to perform revision analysis of the performance targets and work targets of each relevant person based on the target salary data by using salary impact analysis, and obtain performance target revision data and work target revision data;

[0051] Data desensitization module: used for obtaining data attributes of the data to be desensitized in the target salary data, performance target correction data and work target correction data, determining a desensitization method based on the data attributes combined with attribute feature analysis, and desensitizing the target salary data, performance target correction data and work target correction data based on the desensitization method to obtain the target salary data, performance target correction data and work target correction data after desensitization;

[0052] Data storage module: used to store the desensitized target salary data, performance target correction data and work target correction data in the storage node corresponding to the database.

[0053] In an embodiment of the present invention, the salary data to be counted is screened out by using a binary tree and data anomaly rules, so that the abnormal data can be more accurately eliminated, ensuring the accuracy of subsequent data statistical analysis. Performance evaluation is performed based on the working hour data, personnel cooperation data and evaluation text data in the salary data to be counted after the abnormal screening process, so that a more comprehensive performance evaluation result can be obtained, avoiding the one-sidedness and limitations brought by a single factor. Salary accounting is performed using fluctuation anomaly analysis based on the salary data to be counted and the performance evaluation results after the abnormal screening process, so that more accurate salary data can be obtained, which greatly reduces the error rate of salary accounting. Based on the target salary data, the salary impact analysis is used to perform a correction analysis of the performance goals and work goals of each relevant person, which can optimize the rationality of personnel work, realize closed-loop salary management of human resources, and improve the intelligence of salary management. Determine the desensitization method based on data attributes combined with attribute feature analysis, and desensitize the target salary data, performance goal correction data and work goal correction data based on the desensitization method, which can improve the accuracy of data desensitization, protect relevant privacy data, and effectively improve the reliability of salary management. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 It is a flowchart of an intelligent salary management method for the human resources industry in an embodiment of the present invention;

[0056] Figure 2 is a flow chart of an intelligent salary management method for the human resources industry in another embodiment of the present invention;

[0057] Figure 3 It is a schematic diagram of the structural composition of an intelligent salary management system for the human resources industry in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] Embodiment 1

[0060] See also Figure 1 , Figure 1 : is a flow chart of an intelligent salary management method for the human resources industry in an embodiment of the present invention, the method comprising:

[0061] S11: Obtain the salary data to be counted of each relevant person, perform abnormal screening on the salary data to be counted, and obtain the salary data to be counted after the abnormal screening;

[0062] In the specific implementation process of the present invention, the salary data to be counted is subjected to abnormal screening to obtain the salary data to be counted after the abnormal screening, including: obtaining individual data abnormality rules and global data abnormality rules, and marking the salary data to be counted based on the individual data abnormality rules and the global data abnormality rules to obtain the salary data to be counted after the marking; establishing a binary tree, and based on the binary tree, performing abnormal screening on the salary data to be counted after the marking, to obtain the salary data to be counted after the abnormal screening.

[0063] Furthermore, the salary data to be counted after identification processing is subjected to abnormal screening based on the binary tree to obtain the salary data to be counted after abnormal screening processing, including: converting the binary tree into a balanced binary tree, dividing the training data set based on the balanced binary tree to obtain a normal training data set and an abnormal training data set; training an abnormal character recognition model based on the normal training data set and the abnormal training data set to obtain a trained abnormal character recognition model; performing abnormal character recognition on the salary data to be counted after identification processing based on the trained abnormal character recognition model to obtain the salary data to be counted after abnormal character recognition, and performing abnormal screening processing on the salary data to be counted after abnormal character recognition to obtain the salary data to be counted after abnormal screening processing.

[0064] Specifically, the salary data to be counted of each relevant person is obtained. The relevant person may be a staff member dispatched by a human resources company through recruitment software or a staff member recruited internally by the company, etc. The salary data to be counted includes the working hours data, personnel cooperation data, evaluation text data, project commission data, and work completion data of each relevant person. Obtain the single data exception rule and the global data exception rule. The single data exception rule is the exception identification rule for a single data analysis object, and the global data exception rule is the exception identification rule for the overall data. The specific exception identification rule is set by the management personnel according to the actual situation, and the salary data to be counted is identified based on the single data exception rule and the global data exception rule to obtain the salary data to be counted after identification. The single data exception rule and the global data exception rule can better avoid the error of data exception identification. Establish a binary tree through a binary tree template; convert the binary tree into a balanced binary tree, perform in-order traversal on the binary tree to obtain an ordered array, and use a recursive method to construct a balanced binary tree using the ordered array. The training data set is divided based on the balanced binary tree, and each data in the training data set is traversed according to the balanced binary tree, and the depth of each data in the balanced binary tree is calculated. The target score of each data is calculated according to the depth, and the training data set is divided into a normal training data set and an abnormal training data set according to the target score using a preset division threshold. The abnormal character recognition model is trained based on the normal training data set and the abnormal training data set. The abnormal character recognition model can adopt a deep neural network model to obtain a trained abnormal character recognition model. Based on the trained abnormal character recognition model, the salary data to be counted after the identification processing is subjected to abnormal character recognition, and the salary data to be counted after the abnormal character recognition is obtained. The abnormal character refers to a character that does not meet the standard in the data set, such as a special symbol or letter in a digital field, etc. The abnormal character may cause a large deviation in the statistical analysis results of the data. The salary data to be counted after the abnormal character recognition is subjected to abnormal screening processing, that is, the abnormal data and abnormal characters in the salary data to be counted are eliminated. The abnormal data is data that does not conform to the actual law, and the salary data to be counted after the abnormal screening processing is obtained. The abnormal screening of the salary data to be counted can retain valid data to ensure the reliability of subsequent data statistical analysis.

[0065] S12: Perform performance evaluation based on the salary data to be counted after abnormal screening, and obtain performance evaluation results;

[0066] In the specific implementation process of the present invention, the performance appraisal is performed based on the salary data to be counted after the abnormal screening process to obtain the performance appraisal result, including: extracting working hour data, personnel cooperation data and evaluation text data from the salary data to be counted after the abnormal screening process; obtaining the degree of correlation between the working hour data and the performance data, and performing an initial performance appraisal based on the degree of correlation to obtain an initial performance appraisal result; performing word segmentation on the evaluation text data to obtain a number of word segmentation phrases, and generating a word vector matrix based on the number of word segmentation phrases, and determining the ability evaluation level based on the word vector matrix; performing a cooperation contribution analysis based on the personnel cooperation data using a cooperation network model to obtain cooperation contribution data; adjusting the initial performance appraisal result based on the ability evaluation level and cooperation contribution data to obtain a performance appraisal result.

[0067] Specifically, the working time data, personnel cooperation data and evaluation text data are extracted from the salary data to be counted after the abnormal screening process. The working time data includes normal working hours and overtime hours. The personnel cooperation data includes cooperation project information, cooperation personnel information, project module responsibility information and completion information. The evaluation text data is the work evaluation text of the management personnel on the relevant personnel, which contains phrases related to the completion of work tasks, the performance of work responsibilities and the development of employees. The degree of correlation between the working time data and the performance data is obtained. The performance data includes performance evaluation standards and performance distribution data, etc., and an initial performance evaluation is performed based on the degree of correlation. According to the normal working hours and overtime hours in the working time data, a preliminary performance evaluation is performed using the degree of correlation to obtain the initial performance evaluation results. The evaluation text data is segmented, the evaluation text data is segmented coarsely to obtain the coarse-grained segmentation result, the evaluation text data is segmented finely to obtain the fine-grained segmentation result, the coarse-grained segmentations in the coarse-grained segmentation result are traversed, the character length of each coarse-grained segmentation is determined, the coarse-grained segmentation is corrected according to the character length of each coarse-grained segmentation, and the corrected coarse-grained segmentation result is obtained, and the segmentation of the evaluation text data is determined according to the corrected coarse-grained segmentation result and the fine-grained segmentation result, that is, a number of segmentation phrases are obtained. A word vector matrix is ​​generated based on the several segmentation phrases, each segmentation phrase is vectorized to obtain several word vectors, and the word vector matrix is ​​obtained by splicing according to the several word vectors. The ability evaluation level is determined based on the word vector matrix. The ability evaluation model is a convergence model obtained by inputting a sample data set into a deep neural network for training. The ability evaluation level includes excellent assessment ability and good assessment ability. Based on the personnel cooperation data, the cooperation contribution analysis is performed using the cooperation network model, with the cooperation personnel information as nodes and the cooperation project information as edges. A weight is assigned to each node according to the preset rules, and the mutual influence weight between nodes is calculated according to the weight of each node. A cooperation network model is constructed according to the nodes, edges, weights and mutual influence weights. The cooperation contribution of each relevant person is calculated according to the personnel cooperation data of the cooperation network model, that is, the cooperation contribution data is obtained. The initial performance evaluation result is adjusted based on the ability evaluation level and the cooperation contribution data, the corresponding ability performance evaluation level is matched according to the ability evaluation level, the corresponding cooperation performance evaluation level is matched according to the cooperation contribution data, and the initial performance evaluation result is adjusted according to the ability performance evaluation level and the cooperation performance evaluation level to obtain the performance evaluation result. The final performance evaluation result is generated by the initial performance evaluation of the working time data, the ability evaluation level and the cooperation contribution data, which can improve the accuracy and comprehensiveness of the performance evaluation, avoid the one-sidedness and limitations brought about by the performance evaluation of a single factor, and make the obtained performance evaluation result more objective.

[0068] S13: Based on the salary data to be counted and the performance evaluation results after the abnormal screening process, salary calculation is performed using fluctuation abnormality analysis to obtain the target salary data of each relevant person;

[0069] In the specific implementation process of the present invention, the salary data to be counted and the performance evaluation results after abnormal screening are used for salary accounting by using fluctuation anomaly analysis to obtain the target salary data of each relevant personnel, including: obtaining the salary calculation rules corresponding to each relevant personnel, and performing salary statistics based on the salary calculation rules using the salary data to be counted and the performance evaluation results after abnormal screening to obtain the salary data of each relevant personnel; obtaining the calling address of the adaptation accounting engine based on the load balancing algorithm, and transmitting the salary data of each relevant personnel to the corresponding accounting engine based on the calling address; the accounting engine obtains the same-level salary data of several personnel of the same level corresponding to each relevant personnel, and performs data fluctuation feature analysis based on the salary data of the same level to obtain fluctuation feature data; performs singularity point identification on the salary data based on the fluctuation feature data to obtain singularity point identification results; performs verification processing on the salary data of each relevant personnel based on the singularity point identification results and the fluctuation feature data to obtain verification processing results, and determines the target salary data of each relevant personnel based on the verification processing results.

[0070] Specifically, the salary calculation rules corresponding to each relevant person are obtained. The salary calculation rules include salary calculation for normal working hours, salary calculation for overtime hours, and salary commission calculation for cooperative projects, etc. Salary statistics are performed based on the salary calculation rules using the salary data to be counted after abnormal screening and the performance evaluation results. Preliminary salary data is calculated using the salary calculation rules based on the salary data to be counted after abnormal screening. The performance salary of each relevant person is determined based on the performance evaluation results. The two are combined into the final salary data, that is, the salary data of each relevant person is obtained. The calling address of the adaptive accounting engine is obtained based on the load balancing algorithm. The load balancer determines the corresponding accounting engine according to the weight polling and the minimum number of connections, that is, the adaptive accounting engine, and obtains the calling address of the adaptive accounting engine. Based on the calling address, the salary data of each relevant person is transmitted to the corresponding accounting engine, that is, transmitted to the corresponding adaptive accounting engine, which can effectively improve the execution efficiency of salary accounting. The accounting engine obtains the same-level salary data of several peers corresponding to each relevant person. Peer personnel refer to employees with the same labor contract as the person who conducts salary verification. The same-level salary data is the actual salary of the same-level personnel, and performs data fluctuation feature analysis based on the same-level salary data, that is, analyzes the mean value, standard deviation and variance of the same-level salary data to form fluctuation feature data and obtain fluctuation feature data. Based on the fluctuation feature data, singular points of the salary data are identified, and the salary data is decomposed based on the non-negative matrix decomposition algorithm to obtain the basic feature vectors and corresponding weight coefficients of the salary data. Multidimensional feature mapping data is generated using latent space feature mapping based on the basic feature vectors and the corresponding weight coefficients. Singular points of the multidimensional feature mapping data are identified using the fluctuation feature data according to the local anomaly factor algorithm to obtain singular points or outliers in the salary data, and obtain singular point identification results, which can more accurately identify data points that are obviously inconsistent with the conventional salary model. The salary data of each relevant personnel is verified based on the singular point identification result and the fluctuation characteristic data, and the error probability of the salary statistics is determined based on the singular point identification result and the fluctuation characteristic data. If the error probability is greater than or equal to the preset value, the salary statistics are performed again until the obtained error probability is less than the preset value. If the error probability is less than the preset value, the salary data of each relevant personnel calculated is correct, and the verification processing result is obtained. Based on the verification processing result, the target salary data of each relevant personnel is determined, which can ensure the reliability of salary accounting.

[0071] S14: Based on the target salary data, using salary impact analysis to perform a correction analysis on the performance target and work target of each relevant person, and obtain performance target correction data and work target correction data;

[0072] In the specific implementation process of the present invention, the performance goals and work goals of each relevant person are corrected and analyzed by using the salary impact analysis based on the target salary data to obtain performance goal correction data and work goal correction data, including: obtaining salary-related data, and performing salary impact analysis based on the salary-related data and the target salary data using salary indicators and constraints to obtain salary impact analysis data; calculating the work value based on the salary impact analysis data using a value analysis model, and comparing the work value with a preset threshold to obtain a comparison result; and performing a correction analysis of the performance goals and work goals of each relevant person based on the comparison result to obtain performance goal correction data and work goal correction data.

[0073] Specifically, salary-related data are obtained, including attendance information, performance settlement results, and effective overtime information, etc. Salary impact analysis is performed based on the salary-related data and target salary data using salary indicators and constraints, where the salary indicators may include performance target ratios and project completion ratios, etc. An objective function is constructed based on the salary indicators, and constraints are constructed based on the salary-related data. An impact analysis model is constructed using the objective function and constraints, and the cost data consumed by relevant personnel to achieve the target salary data is analyzed based on the impact analysis model, thereby obtaining salary impact analysis data. Work value is calculated based on the salary impact analysis data using a value analysis model, and the salary impact analysis data is input into the value analysis model to obtain work value, which is the value obtained by completing the salary indicator, and the work value is compared with a preset threshold to obtain a comparison result. Based on the comparison results, a revised analysis of the performance goals and work goals of each relevant personnel is performed. If the resulting work value is greater than or equal to a preset threshold, the performance goals and work goals can be appropriately increased according to the proportion exceeding the preset threshold. If the resulting work value is less than the preset threshold, the performance goals and work goals can be appropriately reduced according to the proportion below the preset threshold, and performance goal revision data and work goal revision data are obtained to ensure the rationality of specifying performance goals and work goals for relevant personnel.

[0074] S15: obtaining data attributes of the data to be desensitized in the target salary data, the performance target revised data, and the work target revised data, determining a desensitization method based on the data attributes combined with attribute feature analysis, and performing desensitization processing on the target salary data, the performance target revised data, and the work target revised data based on the desensitization method to obtain the target salary data, the performance target revised data, and the work target revised data after desensitization processing;

[0075] In the specific implementation process of the present invention, the data attributes of the data to be desensitized in the target salary data, performance target correction data and work target correction data are obtained, and the desensitization method is determined based on the data attributes combined with the attribute feature analysis, including: obtaining sample sensitive data, and selecting a corresponding desensitization algorithm based on the data attributes of the sample sensitive data; adding the corresponding desensitization algorithm as a desensitization method label to the sample sensitive data, and constructing a desensitization method database based on the sample sensitive data after adding the desensitization method label; identifying the data attributes of the data to be desensitized in the target salary data, performance target correction data and work target correction data, performing attribute feature analysis based on the data attributes of the data to be desensitized and the data in the desensitization method database, obtaining the desensitization method label corresponding to the data to be desensitized, and determining the desensitization method of the data to be desensitized based on the corresponding desensitization method label.

[0076] Furthermore, the target salary data, performance target correction data and work target correction data are desensitized based on the desensitizing method to obtain the target salary data, performance target correction data and work target correction data after desensitization, including: marking the target position corresponding to the data to be desensitized in the target salary data, performance target correction data and work target correction data based on a programmable logic gate array comparator; obtaining a function stack pointer array based on a target pointer, and obtaining a corresponding compact function name string array based on the function stack pointer array; converting the compact function name string array into a corresponding standard function string based on a demangle function, and obtaining a destination replacement character based on the corresponding standard function string; performing character replacement processing at the target position corresponding to the data to be desensitized using the destination replacement character based on the desensitizing method to obtain the target salary data, performance target correction data and work target correction data after desensitization.

[0077] Specifically, sample sensitive data is obtained, and a corresponding desensitization algorithm is selected based on the data attributes of the sample sensitive data. The data attributes can be key fields of the data, such as performance, total salary, and work goals. The desensitization algorithm includes data encryption, privacy data masking, and random function transformation. The corresponding desensitization algorithm is added to the sample sensitive data as a desensitization method label, and a desensitization method database is constructed based on the sample sensitive data after adding the desensitization method label. The data attributes of the data to be desensitized in the target salary data, performance target correction data, and work target correction data are identified, and attribute feature analysis is performed based on the data attributes of the data to be desensitized and the data in the desensitization method database. According to the data attributes of the data to be desensitized, feature value matching is performed in the desensitization method database, and the desensitization method label is determined according to the matched feature values, and the desensitization method label corresponding to the data to be desensitized is obtained, and the desensitization method of the data to be desensitized is determined based on the corresponding desensitization method label. Based on the programmable logic gate array comparator, the target position corresponding to the data to be desensitized is marked in the target salary data, performance target correction data, and work target correction data. The target pointer can be determined at the target position, and the function stack pointer array is obtained based on the target pointer, and the corresponding compact function name string array is obtained based on the function stack pointer array, and the relevant arrays are matched in the database. Based on the demangle function, the compact function name string array is converted into a corresponding standard function string, and the demangle function can be used to parse the character name, and the target replacement character is obtained based on the corresponding standard function string, and the target replacement character is determined according to the corresponding standard function string combined with the desensitization method. Based on the desensitization method, the target replacement character is used to perform character replacement processing at the target position corresponding to the data to be desensitized. If the desensitization method is irreversible desensitization, character replacement processing is adopted. If the desensitization method is reversible desensitization, encryption processing is adopted to obtain the target salary data, performance target correction data and work target correction data after desensitization processing. Data desensitization operation is an important part of salary information management in human resources enterprises. For some sensitive information, such as salary and performance, reasonable shielding is required. Therefore, desensitizing the target salary data, performance target correction data and work target correction data can protect the privacy information of relevant personnel and prevent data leakage.

[0078] S16: The desensitized target salary data, performance target revised data, and work target revised data are stored in the storage node corresponding to the database.

[0079] In the specific implementation process of the present invention, the target salary data, performance target correction data and work target correction data after desensitization are stored in the storage node corresponding to the database, including: obtaining the priority coefficient and node encryption summary value of each storage node in the database, and performing activity analysis on the target salary data, performance target correction data and work target correction data after desensitization to obtain corresponding activity information, and determining the data storage strategy based on the activity information, priority coefficient and node encryption summary value; based on the data storage strategy, the target salary data, performance target correction data and work target correction data after desensitization are stored in the storage node corresponding to the database.

[0080] Specifically, the priority coefficient and node encryption summary value of each storage node in the database are obtained, the node identification and node capacity of each storage node are obtained, and the node encryption summary value is generated according to the node identification and node capacity; the number of data reads, the number of data reconstruction reads, the average data read delay and the bandwidth of each storage node are obtained, and the priority coefficient of each storage node is calculated according to the number of data reads, the number of data reconstruction reads, the average data read delay and the bandwidth. The calculation expression of the priority coefficient is:

[0081] y=(a*ω a +b*ω b +c*ω c +d*ω d )σ,

[0082] Among them, y is the priority coefficient, a is the number of data reads, ω a is the weight corresponding to the number of data readings, b is the number of data reconstruction readings, ω b is the weight corresponding to the number of data reconstruction reads, c is the average data read delay, ω c is the weight corresponding to the average delay of data reading, d is the bandwidth, ω d is the weight corresponding to the bandwidth, and σ is the correction coefficient. The target salary data, performance target correction data, and work target correction data after desensitization are analyzed for their activity level. Based on the data access frequency judgment rule and creation time judgment rule in the preset timing rules and Apache Doris technology, the target salary data, performance target correction data, and work target correction data after desensitization are analyzed for their activity level, and the corresponding activity level information is obtained. The data storage strategy is determined based on the activity level information, priority coefficient, and node encryption summary value, that is, the required storage node is determined according to the activity level information, priority coefficient, and node encryption summary value. Based on the data storage strategy, the target salary data, performance target correction data, and work target correction data after desensitization are stored in the storage nodes corresponding to the database, which can ensure the reliability of data storage.

[0083] In an embodiment of the present invention, the salary data to be counted is screened out by using a binary tree and data anomaly rules, so that the abnormal data can be more accurately eliminated, ensuring the accuracy of subsequent data statistical analysis. Performance evaluation is performed based on the working hour data, personnel cooperation data and evaluation text data in the salary data to be counted after the abnormal screening process, so that a more comprehensive performance evaluation result can be obtained, avoiding the one-sidedness and limitations brought by a single factor. Salary accounting is performed using fluctuation anomaly analysis based on the salary data to be counted and the performance evaluation results after the abnormal screening process, so that more accurate salary data can be obtained, which greatly reduces the error rate of salary accounting. Based on the target salary data, the salary impact analysis is used to perform a correction analysis of the performance goals and work goals of each relevant person, which can optimize the rationality of personnel work, realize closed-loop salary management of human resources, and improve the intelligence of salary management. Determine the desensitization method based on data attributes combined with attribute feature analysis, and desensitize the target salary data, performance goal correction data and work goal correction data based on the desensitization method, which can improve the accuracy of data desensitization, protect relevant privacy data, and effectively improve the reliability of salary management.

[0084] Embodiment 2

[0085] See also Figure 2 , Figure 2 : is a flow chart of an intelligent salary management method for the human resources industry in another embodiment of the present invention, the method comprising:

[0086] S201: Obtaining the salary data to be counted of each relevant person, performing abnormal screening on the salary data to be counted, and obtaining the salary data to be counted after the abnormal screening;

[0087] S202: Performing performance evaluation based on the salary data to be counted after abnormal screening, and obtaining a performance evaluation result;

[0088] S203: Obtaining salary calculation rules corresponding to each relevant person, and performing salary statistics based on the salary calculation rules using the salary data to be counted after abnormal screening and the performance evaluation results to obtain salary data of each relevant person;

[0089] S204: obtaining a call address of an adaptive accounting engine based on a load balancing algorithm, and transmitting salary data of each relevant person to a corresponding accounting engine based on the call address;

[0090] S205: The accounting engine obtains the same-level salary data of a number of personnel of the same level corresponding to each relevant personnel, and performs data fluctuation characteristic analysis based on the same-level salary data to obtain fluctuation characteristic data;

[0091] S206: performing singular point identification on the salary data based on the fluctuation characteristic data to obtain a singular point identification result;

[0092] S207: verifying and processing the salary data of each relevant person based on the singular point identification result and the fluctuation characteristic data, and determining the error probability of salary statistics according to the singular point identification result and the fluctuation characteristic data;

[0093] S208: Determine whether the error probability is greater than or equal to a preset threshold;

[0094] S209: Determine the target salary data of each relevant person based on the verification processing result;

[0095] S210: Based on the target salary data, using salary impact analysis to perform correction analysis on the performance targets and work targets of each relevant person, and obtain performance target correction data and work target correction data;

[0096] S211: obtaining data attributes of the data to be desensitized in the target salary data, performance target revised data, and work target revised data, determining a desensitization method based on the data attributes combined with attribute feature analysis, and performing desensitization processing on the target salary data, performance target revised data, and work target revised data based on the desensitization method to obtain the target salary data, performance target revised data, and work target revised data after desensitization processing;

[0097] S212: Storing the desensitized target salary data, performance target revised data, and work target revised data in a storage node corresponding to the database.

[0098] In an embodiment of the present invention, the salary data to be counted is screened out by using a binary tree and data anomaly rules, so that the abnormal data can be more accurately eliminated, ensuring the accuracy of subsequent data statistical analysis. Performance evaluation is performed based on the working hour data, personnel cooperation data and evaluation text data in the salary data to be counted after the abnormal screening process, so that a more comprehensive performance evaluation result can be obtained, avoiding the one-sidedness and limitations brought by a single factor. Salary accounting is performed using fluctuation anomaly analysis based on the salary data to be counted and the performance evaluation results after the abnormal screening process, so that more accurate salary data can be obtained, which greatly reduces the error rate of salary accounting. Based on the target salary data, the salary impact analysis is used to perform a correction analysis of the performance goals and work goals of each relevant person, which can optimize the rationality of personnel work, realize closed-loop salary management of human resources, and improve the intelligence of salary management. Determine the desensitization method based on data attributes combined with attribute feature analysis, and desensitize the target salary data, performance goal correction data and work goal correction data based on the desensitization method, which can improve the accuracy of data desensitization, protect relevant privacy data, and effectively improve the reliability of salary management.

[0099] Embodiment 3

[0100] See also Figure 3 , Figure 3 : is a schematic diagram of the structure of an intelligent salary management system for the human resources industry in an embodiment of the present invention, the system includes:

[0101] The data anomaly screening module 31 is used to obtain the salary data to be counted of each relevant person, perform anomaly screening on the salary data to be counted, and obtain the salary data to be counted after the anomaly screening;

[0102] Performance evaluation module 32: used to perform performance evaluation based on the salary data to be counted after abnormal screening, and obtain performance evaluation results;

[0103] Salary calculation module 33: used to calculate salary based on the salary data to be counted and the performance evaluation results after abnormal screening by using fluctuation abnormality analysis to obtain the target salary data of each relevant person;

[0104] The target revision analysis module 34 is used to perform revision analysis of the performance targets and work targets of each relevant person based on the target salary data by using salary impact analysis to obtain performance target revision data and work target revision data;

[0105] Data desensitization module 35: used to obtain data attributes of the data to be desensitized in the target salary data, performance target correction data and work target correction data, determine the desensitization method based on the data attributes combined with attribute feature analysis, and perform desensitization processing on the target salary data, performance target correction data and work target correction data based on the desensitization method to obtain the target salary data, performance target correction data and work target correction data after desensitization processing;

[0106] The data storage module 36 is used to store the desensitized target salary data, performance target revised data and work target revised data in the storage node corresponding to the database.

[0107] In the specific implementation process of the present invention, the specific implementation methods of the system items can be referred to the above embodiments, which will not be repeated here.

[0108] In an embodiment of the present invention, the salary data to be counted is screened out by using a binary tree and data anomaly rules, so that the abnormal data can be more accurately eliminated, ensuring the accuracy of subsequent data statistical analysis. Performance evaluation is performed based on the working hour data, personnel cooperation data and evaluation text data in the salary data to be counted after the abnormal screening process, so that a more comprehensive performance evaluation result can be obtained, avoiding the one-sidedness and limitations brought by a single factor. Salary accounting is performed using fluctuation anomaly analysis based on the salary data to be counted and the performance evaluation results after the abnormal screening process, so that more accurate salary data can be obtained, which greatly reduces the error rate of salary accounting. Based on the target salary data, the salary impact analysis is used to perform a correction analysis of the performance goals and work goals of each relevant person, which can optimize the rationality of personnel work, realize closed-loop salary management of human resources, and improve the intelligence of salary management. Determine the desensitization method based on data attributes combined with attribute feature analysis, and desensitize the target salary data, performance goal correction data and work goal correction data based on the desensitization method, which can improve the accuracy of data desensitization, protect relevant privacy data, and effectively improve the reliability of salary management.

[0109] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0110] In addition, the above is a detailed introduction to an intelligent salary management method and system for the human resources industry provided by an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in the field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for intelligent salary management in the human resources industry, characterized in that: The method comprises: Obtaining the salary data to be counted of each relevant person, performing abnormal screening on the salary data to be counted, and obtaining the salary data to be counted after the abnormal screening; Perform performance evaluation based on the salary data to be counted after abnormal screening and obtain performance evaluation results; Based on the salary data to be counted and the performance evaluation results after abnormal screening, salary calculation is performed using fluctuation abnormality analysis to obtain the target salary data of each relevant person; Based on the target salary data, using salary impact analysis to perform a revised analysis on the performance goals and work goals of each relevant person, and obtain performance goal revised data and work goal revised data; Obtaining data attributes of the data to be desensitized in the target salary data, performance target revised data, and work target revised data, determining a desensitization method based on the data attributes combined with attribute feature analysis, and performing desensitization processing on the target salary data, performance target revised data, and work target revised data based on the desensitization method to obtain the target salary data, performance target revised data, and work target revised data after desensitization processing; The desensitized target salary data, performance target revised data and work target revised data are stored in the storage node corresponding to the database.

2. The intelligent salary management method for the human resources industry according to claim 1 is characterized in that: The step of performing abnormal screening on the salary data to be counted to obtain the salary data to be counted after the abnormal screening is performed includes: Acquire a single data exception rule and a global data exception rule, and perform identification processing on the salary data to be counted based on the single data exception rule and the global data exception rule to obtain the salary data to be counted after identification processing; A binary tree is established, and abnormal screening is performed on the salary data to be counted after the identification processing based on the binary tree to obtain the salary data to be counted after the abnormal screening processing.

3. The intelligent salary management method for the human resources industry according to claim 2 is characterized in that: The step of performing abnormal screening on the salary data to be counted after the identification processing based on the binary tree to obtain the salary data to be counted after the abnormal screening processing comprises: Converting the binary tree into a balanced binary tree, and dividing the training data set based on the balanced binary tree to obtain a normal training data set and an abnormal training data set; Training an abnormal character recognition model based on the normal training data set and the abnormal training data set to obtain a trained abnormal character recognition model; Based on the trained abnormal character recognition model, abnormal characters are recognized on the salary data to be counted after identification processing to obtain the salary data to be counted after abnormal character recognition, and abnormal screening is performed on the salary data to be counted after abnormal character recognition to obtain the salary data to be counted after abnormal screening processing.

4. The intelligent salary management method for the human resources industry according to claim 1 is characterized in that: The performance evaluation is performed based on the salary data to be counted after the abnormal screening process to obtain the performance evaluation result, including: Extract working hours data, personnel cooperation data and evaluation text data from the salary data to be counted after abnormal screening; Obtaining the degree of correlation between the working time data and the performance data, and performing an initial performance evaluation based on the degree of correlation to obtain an initial performance evaluation result; Segmenting the evaluation text data to obtain a number of segmented word groups, generating a word vector matrix based on the number of segmented word groups, and determining the ability evaluation level based on the word vector matrix; Based on the personnel cooperation data, cooperation contribution analysis is performed using a cooperation network model to obtain cooperation contribution data; The initial performance evaluation result is adjusted based on the capability evaluation level and the cooperation contribution data to obtain a performance evaluation result.

5. The intelligent salary management method for the human resources industry according to claim 1 is characterized in that: The salary data to be counted and the performance evaluation results after the abnormal screening process are used to perform salary calculation using fluctuation abnormality analysis to obtain the target salary data of each relevant person, including: Obtaining salary calculation rules corresponding to each relevant person, and performing salary statistics based on the salary calculation rules using the salary data to be counted after abnormal screening and the performance evaluation results to obtain the salary data of each relevant person; Obtaining the call address of the adapted accounting engine based on the load balancing algorithm, and transmitting the salary data of each relevant person to the corresponding accounting engine based on the call address; The accounting engine obtains the same-level salary data of a number of personnel of the same level corresponding to each relevant personnel, and performs data fluctuation characteristic analysis based on the same-level salary data to obtain fluctuation characteristic data; Performing singular point identification on the salary data based on the fluctuation characteristic data to obtain a singular point identification result; The salary data of each relevant person is verified and processed based on the singular point identification result and the fluctuation characteristic data to obtain a verification result, and the target salary data of each relevant person is determined based on the verification result.

6. The intelligent salary management method for the human resources industry according to claim 1 is characterized in that: The method of performing a correction analysis of the performance targets and work targets of each relevant person by using the salary impact analysis based on the target salary data to obtain performance target correction data and work target correction data includes: Obtaining salary-related data, and performing salary impact analysis based on the salary-related data and target salary data using salary indicators and constraints to obtain salary impact analysis data; Calculating the work value using a value analysis model based on the salary impact analysis data, and comparing the work value with a preset threshold to obtain a comparison result; Based on the comparison results, a revised analysis of the performance goals and work goals of each relevant person is performed to obtain performance goal revised data and work goal revised data.

7. The intelligent salary management method for the human resources industry according to claim 1 is characterized in that: The step of obtaining data attributes of the data to be desensitized in the target salary data, the performance target revised data, and the work target revised data, and determining a desensitization method based on the data attributes combined with attribute feature analysis, includes: Obtain sample sensitive data and select a corresponding desensitization algorithm based on the data attributes of the sample sensitive data; Adding the corresponding desensitization algorithm as a desensitization method label to the sample sensitive data, and building a desensitization method database based on the sample sensitive data after adding the desensitization method label; Identify the data attributes of the data to be desensitized in the target salary data, performance target correction data and work target correction data, perform attribute feature analysis based on the data attributes of the data to be desensitized and the data in the desensitization method database, obtain the desensitization method label corresponding to the data to be desensitized, and determine the desensitization method of the data to be desensitized based on the corresponding desensitization method label.

8. The intelligent salary management method for the human resources industry according to claim 1 is characterized in that: The desensitizing process is performed on the target salary data, the performance target revised data, and the work target revised data based on the desensitizing method to obtain the target salary data, the performance target revised data, and the work target revised data after the desensitization process, including: Based on the programmable logic gate array comparator, the target position corresponding to the data to be desensitized is marked in the target salary data, the performance target correction data and the work target correction data; Acquire a function stack pointer array based on the target pointer, and acquire a corresponding compact function name string array based on the function stack pointer array; Converting the compact function name string array into a corresponding standard function string based on a demangle function, and obtaining a target replacement character based on the corresponding standard function string; Based on the desensitizing method, the target replacement character is used to perform character replacement processing at the target position corresponding to the data to be desensitized, so as to obtain the target salary data, performance target correction data and work target correction data after desensitization processing.

9. The intelligent salary management method for the human resources industry according to claim 1 is characterized in that: The storing of the desensitized target salary data, performance target revised data, and work target revised data into the storage node corresponding to the database includes: Obtain the priority coefficient and node encryption summary value of each storage node in the database, and perform activity analysis on the target salary data, performance target correction data, and work target correction data after desensitization processing to obtain corresponding activity information, and determine the data storage strategy based on the activity information, priority coefficient, and node encryption summary value; Based on the data storage strategy, the desensitized target salary data, performance target revision data and work target revision data are stored in the storage node corresponding to the database.

10. An intelligent salary management system for the human resources industry, characterized in that: The system comprises: Data anomaly screening module: used to obtain the salary data to be counted of each relevant person, perform anomaly screening on the salary data to be counted, and obtain the salary data to be counted after the anomaly screening; Performance evaluation module: used to evaluate performance based on the salary data to be counted after abnormal screening and obtain performance evaluation results; Salary calculation module: used to calculate salary based on the salary data to be counted and the performance evaluation results after abnormal screening, using fluctuation anomaly analysis to obtain the target salary data of each relevant person; Target revision analysis module: used to perform revision analysis of the performance targets and work targets of each relevant person based on the target salary data by using salary impact analysis, and obtain performance target revision data and work target revision data; Data desensitization module: used for obtaining data attributes of the data to be desensitized in the target salary data, performance target correction data and work target correction data, determining a desensitization method based on the data attributes combined with attribute feature analysis, and desensitizing the target salary data, performance target correction data and work target correction data based on the desensitization method to obtain the target salary data, performance target correction data and work target correction data after desensitization; Data storage module: used to store the desensitized target salary data, performance target correction data and work target correction data in the storage node corresponding to the database.

Images