Artificial intelligence-based employee attendance data analysis method and system

Abstract

The invention discloses an employee attendance data analysis method and system based on artificial intelligence, and the method comprises the steps: a data processing module carries out the preprocessing of collected attendance data, and carries out the integration and construction of an employee attendance database; the model building module constructs a double-layer generative adversarial network model according to the employee attendance database; the attendance checking detection module performs pattern recognition on the employee attendance checking database according to the double-layer generative adversarial network model, and performs anomaly detection on attendance checking data in the employee attendance checking database according to the double-layer generative adversarial network model; and the trend prediction module predicts the attendance trend according to the simulated attendance data and the real-time attendance data in the employee attendance database. According to the invention, the monitoring capability of the enterprise on the employee attendance behavior can be enhanced, the prospective decision support is provided for the enterprise management layer, and the management order of the enterprise is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of mathematical modeling and data analysis, and in particular to an analysis method and system for employee attendance data based on artificial intelligence. Background Art

[0002] As business operations become increasingly digital and automated, employee attendance management becomes more complex and important. Traditional attendance management methods rely mainly on manual records and simple electronic clock-in systems. These methods are not only inefficient, but also fail to provide in-depth data analysis, resulting in a lack of data support for human resource decisions. In addition, due to the lack of effective data analysis tools, companies find it difficult to extract valuable information from large amounts of attendance data, such as employee work patterns, efficiency issues, and potential causes of the problems.

[0003] In the existing technology, the analysis of attendance data mostly remains at the simple statistical summary stage, and it is impossible to conduct in-depth analysis of employee behavior patterns, let alone predict future attendance trends. Therefore, developing a system that can intelligently process and analyze abnormal attendance data to cope with complex employee behavior patterns, thereby improving the analysis depth and prediction capabilities of attendance data, and providing more scientific decision-making support and more efficient management strategies for enterprise management has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The purpose of the present invention is to provide an analysis method and system for employee attendance data based on artificial intelligence. The present invention can intelligently process and analyze abnormal attendance data, thereby improving the analysis depth and prediction ability of attendance data, and providing more scientific decision support and more efficient management strategies for enterprise management.

[0005] To achieve this purpose, the present invention designs an analysis system for employee attendance data based on artificial intelligence, which includes:

[0006] The data processing module pre-processes the collected attendance data, and then integrates the pre-processed attendance data using big data processing technology to build an employee attendance database;

[0007] The model building module constructs a two-layer generative adversarial network model based on the employee attendance database. The first-layer generator in the two-layer generative adversarial network model is used to generate simulated attendance data based on the historical attendance data in the employee attendance database, and to generate real attendance behavior patterns based on the simulated attendance data; the second-layer generator is used to generate complex attendance behavior patterns;

[0008] The attendance detection module performs pattern recognition on the employee attendance database according to the double-layer generative adversarial network model, and identifies the employee's attendance behavior pattern as a real attendance behavior pattern or a complex attendance behavior pattern; and performs anomaly detection on the attendance data corresponding to the attendance behavior pattern in the employee attendance database according to the double-layer generative adversarial network model;

[0009] The trend prediction module predicts attendance trends based on simulated attendance data and real-time attendance data in the employee attendance database.

[0010] Beneficial effects of the present invention:

[0011] The present invention uses an innovative abnormal behavior detection and classification algorithm to automatically identify, extract features and classify potential abnormal behaviors in attendance data. The attendance data generated by a two-layer generative adversarial network is compared with the actual data to detect abnormal behaviors. The system can accurately analyze the frequency, duration and environmental characteristics of abnormal behaviors, and generate detailed abnormal behavior reports. It then predicts future attendance trends based on the attendance data and identifies possible attendance fluctuations and abnormal behaviors. This not only improves the depth and breadth of attendance data analysis and enhances the company's ability to monitor employee attendance behavior, but also provides forward-looking decision-making support for the company's management, helps to promptly discover and correct abnormal behavior patterns, and ensure the company's management order. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a structural schematic diagram of the present invention;

[0013] Figure 2 It is the overall flow chart of the present invention. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. 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.

[0015] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0016] Example 1

[0017] An analysis system for employee attendance data based on artificial intelligence, such as Figure 1 As shown, it includes:

[0018] The data processing module pre-processes the collected attendance data, and then integrates the pre-processed attendance data using big data processing technology to build an employee attendance database;

[0019] The model building module constructs a two-layer generative adversarial network model based on the employee attendance database. The first-layer generator in the two-layer generative adversarial network model is used to generate simulated attendance data based on the historical attendance data in the employee attendance database, and to generate real attendance behavior patterns based on the simulated attendance data; the second-layer generator is used to generate complex attendance behavior patterns;

[0020] The attendance detection module performs pattern recognition on the employee attendance database according to the double-layer generative adversarial network model, and identifies the employee's attendance behavior pattern as a real attendance behavior pattern or a complex attendance behavior pattern; and performs anomaly detection on the attendance data corresponding to the attendance behavior pattern in the employee attendance database according to the double-layer generative adversarial network model;

[0021] The trend prediction module predicts attendance trends based on simulated attendance data and real-time attendance data in the employee attendance database.

[0022] In the above technical solution, the preprocessing includes standardization of the timestamps of the collected attendance data, conversion of the data format and filling of missing data.

[0023] In the above technical solution, the collected attendance data are attendance records that already exist in the time collection system of the enterprise management software used by employees, including historical attendance data and real-time attendance data.

[0024] In the above technical solution, the specific method of obtaining various types of data in the collected attendance data is:

[0025] Monitor each employee's login time T through the user interface of the enterprise management software login and logout time T logout , and calculate the usage time T for each login usage :

[0026] T usage =T logout -T login ;

[0027] Among them, T login is the first login time of the employee in the enterprise management software, T logout The employee's last logout time in the enterprise management software, T usage The duration of use during a single login session for the employee;

[0028] Record and store each employee's multiple login and logout records every day, calculate and accumulate the total usage time T for the day total :

[0029]

[0030] Where n is the number of times an employee logs in on the day, T usage(i) The duration of the employee's i-th login;

[0031] By monitoring the active status of employees using the enterprise management software, including mouse movement and keyboard input operation records, the login session with no operation for more than a predetermined time is marked as "idle", and this period of time is deducted from the total usage time; based on the active time of employees using the enterprise management software, the actual effective working time T is further calculated. active :

[0032] T active =T total -T idle ;

[0033] Among them, T idle is the total idle time of employees in the non-operating state, T active The actual effective working hours of employees.

[0034] In the above technical solution, the specific processing steps of integrating the pre-processed attendance data using big data processing technology to build an employee attendance database are as follows:

[0035] The pre-processed attendance data is processed in a unified format, and the data formats from different sources are converted into the standard format required by the system, including the timestamp format, geographic location information format, and employee identity information format;

[0036] The pre-processed attendance data is deduplicated using a hash algorithm to avoid storing duplicate data, where the hash value H(d) is used to identify a unique attendance record, d is the original record of the attendance data, and H(d) is the unique hash value generated by it;

[0037] Based on data cleaning and filtering technology, attendance data that does not conform to the standard format or contains obvious errors is eliminated and corrected;

[0038] Store the cleaned attendance data and build the employee attendance database DB attendance ;

[0039] The data in the employee attendance database is optimized through indexing technology, and a multidimensional index based on employee identity information, timestamp, and geographic location is created to optimize the query efficiency of the database. The index is represented by IDX emp,time,loc, where emp is the employee identity information, time is the timestamp, and loc is the geographic location.

[0040] In the above technical solution, the data processing module ensures that data from different devices and systems can be processed consistently by adopting unified timestamp standardization processing, data format conversion and missing data filling technology, and constructs an employee attendance database using big data processing technology, solving the problem of data integration difficulties caused by inconsistent data sources and non-uniform formats in traditional attendance systems. The technical improvement not only improves the integrity and consistency of the data, but also lays a solid foundation for subsequent intelligent analysis and prediction.

[0041] In the above technical solution, the specific construction steps of the model building module are:

[0042] Two-layer Generative Adversarial Network Model GAN dual It consists of two parts: the generator and the discriminator: the first-layer generator G1 is used to generate simulated attendance data based on the historical attendance data in the employee attendance database; the first-layer discriminator D1 is used to judge the authenticity of the generated simulated attendance data; the second-layer generator G2 is used to generate complex attendance behavior patterns, including abnormal attendance behavior and normal behavior; the second-layer discriminator D2 is used to judge the authenticity of the generated complex attendance behavior patterns. The two-layer generative adversarial network model needs to use historical attendance data to generate simulated data and combine it with the real-time collected attendance data for analysis. The overall objective function L of the two-layer generative adversarial network model is GAN It is expressed as:

[0043]

[0044] Among them, p data (D real ) represents the distribution of real attendance data, and Respectively represent the noise distribution used to generate simulated attendance data and complex attendance behavior patterns, represents the mean, G1 and G2 are the first and second layer generators, D1 and D2 are the first and second layer discriminators, and the objective function L GAN Train a two-layer GAN model by minimizing the generator loss and maximizing the first and second layer discriminator losses;

[0045] Based on employee attendance database DB attendance The historical attendance data in the training layer is used to train the first-layer generator G1 to generate simulated attendance data D sim , the generation process of simulated attendance data is expressed as:

[0046] D sim =G1(z1)=σ(WG1 z1+b G1 );

[0047] Among them, z1 is the input random noise vector, W G1 and b G1 are the weight matrix and bias vector of the first layer generator, σ is the activation function, D sim The simulated attendance data is generated, G1 is the first layer generator, and the generator adjusts the weight W G1 and bias b G1 Learn the distribution of historical attendance data;

[0048] Train the first layer of discriminator D1 to discriminate the generated simulated attendance data D sim With real attendance data D real The authenticity of , the judgment process is expressed as:

[0049]

[0050] Among them, D input is the input attendance data, and the attendance data is the generated simulated attendance data D sim Or real attendance data D real , W D1 and b D1 are the weight matrix and bias vector of the first-layer discriminator, respectively. The first-layer discriminator optimizes the accuracy of discrimination by adjusting parameters;

[0051] Based on the training results of the first-layer generator and the first-layer discriminator, the real attendance behavior pattern is generated, and the second-layer generator G2 is constructed to integrate all the real attendance behavior patterns to generate a more complex attendance behavior pattern. The process of generating a complex attendance behavior pattern is expressed as:

[0052] B complex =G2(z2)=tanh(W G2 z2+b G2 );

[0053] Among them, z2 is the input random noise vector, W G2 and b G2 are the weight matrix and bias vector of the second-layer generator, tanh is the activation function, G2 is the second-layer generator, and the generator generates complex attendance behavior patterns B complex To mimic abnormal patterns in real attendance behavior;

[0054] Train the second layer discriminator D2 to discriminate the generated complex attendance behavior pattern B complex The authenticity of the actual attendance behavior pattern is determined by:

[0055]

[0056] Among them, B input The input behavior pattern data is used to generate complex attendance behavior pattern B complex Or real attendance behavior pattern B real The second layer discriminator adjusts the weight matrix W D2 and the bias vector b D2 Optimize discrimination ability;

[0057] By repeatedly training the first and second layer generative adversarial network models, optimizing the generation capabilities of the first and second layer generators G1 and G2, as well as the discrimination accuracy of the first and second layer discriminators D1 and D2, we finally obtain a two-layer generative adversarial network model GAN ​​that can simulate and recognize attendance behavior. dual During the training process, the loss functions of the generator and the discriminator are:

[0058]

[0059] Among them, L G1,G2 are the loss functions of the first and second layer generators G1 and G2, respectively, which represent the probability that the generated simulated attendance data and complex attendance behavior patterns are identified as real data. The authenticity of the generated data is improved by minimizing the loss function. D1,D2 is the loss function of the first and second layer discriminants D1 and D2, which represents the ability of the discriminator to correctly identify real data and generated data. By repeatedly optimizing the loss function, a two-layer generative adversarial network model is finally constructed to simulate and identify complex attendance behavior patterns.

[0060] In the above technical solution, the model building module can be implemented based on the deep learning framework (TensorFlow, PyTorch) to support the model training and reasoning process of the generative adversarial network.

[0061] In the above technical solution, the model building module realizes complex pattern recognition and anomaly detection of employee attendance behavior by constructing a two-layer generative adversarial network model. Different from the traditional simple rule-based algorithm, the two-layer generative adversarial network model simulates real attendance data through the first-layer generator and judges its authenticity through the first-layer discriminator; the second-layer generator further generates complex attendance behavior patterns, including potential abnormal behaviors, such as forged attendance records and abnormally frequent login and logout behaviors. The second-layer discriminator is used to verify the authenticity of these complex behavior patterns. The model significantly improves the recognition ability of complex attendance behaviors, can accurately detect and classify employees' normal and abnormal behaviors, and solves the shortcomings of traditional attendance systems in deep-level behavior recognition.

[0062] In the above technical solution, the method for identifying the specific employee attendance behavior pattern of the attendance detection module is:

[0063] The integrated employee attendance database DB attendance The data in is input into the two-layer generative adversarial network model GAN dual In the process of attendance behavior pattern recognition:

[0064]

[0065] Among them, M recog In order to identify the complex attendance behavior pattern, G1 and G2 are the first and second layer generators of the two-layer generative adversarial network model, D2 is the second layer discriminator, z2 is the input random noise vector, W G1 and W G2 are the weight matrices of the first and second layer generators, respectively, and b G1 and b G2 are their bias vectors, h is the activation function, f is the nonlinear mapping function, Represents a complex behavior pattern that selects the discriminator to maximize its output probability;

[0066] According to the identified complex attendance behavior pattern, the classification function is used to classify it into normal working hours M normal , Overtime work overtime 、Not logged in to use M absent and irregular use behavior irregular :

[0067]

[0068] Among them, M class is the set of complex attendance behavior patterns after classification, α i is the weight parameter in the classification model, g i (M) is the classification feature function of the complex attendance behavior pattern, k is the number of features used for classification, It represents the selection of the complex attendance behavior pattern with the maximum weighted sum of features;

[0069] Extract features for each complex attendance behavior pattern. The extracted features include login usage duration, operation frequency, and login interval:

[0070]

[0071] Among them, F extract is the extracted feature set, T usage is the usage time, F freq is the operating frequency, T interval is the login interval, β jis the weight parameter in the feature extraction model, h j (F) is the feature function for feature extraction, and n is the number of features used in the feature extraction model;

[0072] The extracted complex attendance behavior features are input into the pattern classifier to refine the classification of complex attendance behavior patterns. The output of the classifier is represented as follows:

[0073]

[0074] Among them, M final is the final classification result, C is the classifier function, γ l is the weight parameter in the pattern classifier, q l (F extract ) is the feature mapping function in the classifier, m is the number of features used in the classifier, and according to the final classification result, a report on the complex attendance behavior pattern of employees is automatically generated. The report content includes the employees’ normal working hours, overtime work, non-logged-in use, and irregular use behavior.

[0075] In the above technical solution, the specific abnormal behavior detection method of the attendance detection module is:

[0076] Anomaly detection is performed based on the simulated attendance data generated by the two-layer generative adversarial network model and the attendance data in the employee attendance database. The detection process identifies the existing abnormal behaviors.

[0077] According to the abnormal behaviors detected, they are classified into forged usage records, abnormally frequent login and logout behaviors, and abnormal behaviors of not using the software for a long time;

[0078] Perform feature extraction on each abnormal behavior pattern to extract the frequency of abnormal behavior, the duration of abnormal behavior and the environmental characteristics when the abnormal behavior occurs;

[0079] Based on the extracted abnormal behavior features, they are input into the abnormal behavior discriminator to further determine and refine the abnormal behavior, and finally determine the type and characteristics of the abnormal behavior;

[0080] Based on the abnormal behavior finally determined, an abnormal behavior report is generated, which includes the type of abnormal behavior identified, its frequency, duration, and the environment in which it occurs.

[0081] In the above technical solution, the attendance detection module uses a two-layer generative adversarial network model combined with a dynamic adjustment algorithm. When the employee attendance behavior data changes in real time, it can quickly generate and update the employee attendance behavior pattern, and timely detect and report potential abnormal behaviors, ensuring that the attendance management system is always in an efficient and accurate operating state, greatly improving the timeliness and effectiveness of management decisions.

[0082] In the above technical solution, the specific attendance trend prediction steps of the trend prediction module are: based on the historical attendance data D in the employee attendance database hist And the two-layer generative adversarial network model GAN dual Generated simulated data D sim , analyze the working hours and usage frequency of employees, and extract the main features F trend :

[0083]

[0084] Among them, α i is the weight of each feature, φ i is the nonlinear feature mapping function, and They represent the working hours and usage frequency of the i-th historical period respectively. G1 and G2 are the first and second layer generators of the two-layer generative adversarial network model respectively. and Respectively represent the historical data and simulation data of the i-th period;

[0085] The time series analysis model TSM is used to perform trend analysis on the extracted feature data and predict the working hours T of employees in the future. future and frequency of use F future , the prediction process is expressed as:

[0086]

[0087] in, is the weight of each time series feature, ψ j is the time series feature conversion function, is the jth time series feature, Δt j is the time interval, θ j is the parameter set of the time series model, TSM is the time series analysis model function, and outputs the predicted future working time T future and frequency of use F future ;

[0088] Based on the prediction results of the time series analysis model, the attendance trend prediction model PTM is generated to predict the future attendance patterns of employees, including possible attendance fluctuations and potential abnormal attendance behaviors:

[0089]

[0090] Among them, γ k is the weight coefficient of the attendance trend model, ξ k is the attendance trend feature mapping function, and are the predicted working hours and usage frequency of the kth future period, respectively, k is the parameter set used to generate the attendance trend model, and PTM is the final attendance trend prediction model.

[0091] In the above technical solution, the trend prediction module effectively predicts the future attendance trends of employees by reconstructing the attendance data and applying the time series analysis algorithm, and generates targeted management decisions based on this, such as arranging personnel scheduling or adjusting attendance policies in advance, which significantly improves the foresight and flexibility of enterprise management and reduces the operational risks caused by improper personnel arrangements.

[0092] In the above technical solution, the results of the attendance trend prediction model are visualized to generate a predictive analysis report, which includes future working hours trends, changes in usage frequency, and possible attendance anomalies; an attendance data analysis report is generated through a visualization tool, which displays the analysis results of the attendance data in a graphical form and provides real-time monitoring functions; the predictive analysis results are integrated with the enterprise management system, and the attendance data analysis results are applied to employee performance appraisal, salary calculation, and work scheduling management functions.

[0093] In the above technical solution, the prediction depends not only on the attendance data but also on the complex attendance behavior patterns and real attendance behavior patterns generated by the system. Combining the attendance behavior patterns can make the data more comprehensive for trend prediction.

[0094] Example 2

[0095] An analysis method of employee attendance data based on artificial intelligence, such as Figure 2 As shown, attendance data is collected by detecting the length of time employees use enterprise management software; the collected attendance data is preprocessed; the preprocessed attendance data is integrated using big data processing technology to build an employee attendance database; a two-layer generative adversarial network model is built; the two-layer generative adversarial network model is used to perform pattern recognition on the employee attendance database to identify the employee's attendance behavior pattern; anomaly detection is performed on the attendance data in the employee attendance database based on the two-layer generative adversarial network model to identify potential abnormal behaviors; attendance trend prediction is performed based on real-time attendance data and generated simulation data to predict the employee's working hours and usage frequency in the future, and predictive analysis results are provided; the predictive analysis results are integrated with the enterprise management system, and the attendance data analysis results are applied to employee performance appraisal, salary calculation, and work scheduling management functions.

[0096] The specific analysis method of employee attendance data includes the following steps:

[0097] Pre-process the collected attendance data, and then use big data processing technology to integrate the pre-processed attendance data to build an employee attendance database;

[0098] A two-layer generative adversarial network model is constructed based on the employee attendance database. The first-layer generator in the two-layer generative adversarial network model is used to generate simulated attendance data based on the historical attendance data in the employee attendance database, and to generate real attendance behavior patterns based on the simulated attendance data; the second-layer generator is used to generate complex attendance behavior patterns;

[0099] Perform pattern recognition on the employee attendance database according to the two-layer generative adversarial network model to identify the employee's attendance behavior pattern as a real attendance behavior pattern or a complex attendance behavior pattern; perform anomaly detection on the attendance data corresponding to the attendance behavior pattern in the employee attendance database according to the two-layer generative adversarial network model;

[0100] Attendance trend prediction is performed based on simulated attendance data and real-time attendance data in the employee attendance database.

[0101] Example 3

[0102] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the steps of the method described in Embodiment 2 are implemented.

[0103] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0104] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0106] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0108] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

Claims

1. An analysis system for employee attendance data based on artificial intelligence, characterized in that: include: The data processing module pre-processes the collected attendance data, and then integrates the pre-processed attendance data using big data processing technology to build an employee attendance database; The model building module constructs a two-layer generative adversarial network model based on the employee attendance database. The first-layer generator in the two-layer generative adversarial network model is used to generate simulated attendance data based on the historical attendance data in the employee attendance database, and to generate real attendance behavior patterns based on the simulated attendance data; the second-layer generator is used to generate complex attendance behavior patterns; The attendance detection module performs pattern recognition on the employee attendance database according to the double-layer generative adversarial network model, and identifies the employee's attendance behavior pattern as a real attendance behavior pattern or a complex attendance behavior pattern; and performs anomaly detection on the attendance data corresponding to the attendance behavior pattern in the employee attendance database according to the double-layer generative adversarial network model; The trend prediction module predicts attendance trends based on simulated attendance data and real-time attendance data in the employee attendance database.

2. The employee attendance data analysis system based on artificial intelligence according to claim 1 is characterized by: The preprocessing includes standardization of the timestamp of the collected attendance data, conversion of the data format and filling of the missing data.

3. The employee attendance data analysis system based on artificial intelligence according to claim 1 is characterized by: The collected attendance data are attendance records that already exist in the time collection system of the enterprise management software used by employees, including historical attendance data and real-time attendance data.

4. The employee attendance data analysis system based on artificial intelligence according to claim 3 is characterized by: The specific method of obtaining various types of data in the collected attendance data is as follows: Monitor each employee's login time T through the user interface of the enterprise management software login and logout time T logout , and calculate the usage time T for each login usage : T usage =T logout -T login ; Among them, T login is the first login time of the employee in the enterprise management software, T logout The employee's last logout time in the enterprise management software, T usage The duration of use during a single login session for the employee; Record and store each employee's multiple login and logout records every day, calculate and accumulate the total usage time T for the day total : Where n is the number of times an employee logs in on the day, T usage(i) The duration of the employee's i-th login; Based on the active time of employees using the enterprise management software, the actual effective working time T is further calculated active : T active =T total -T idle ; Among them, T idle is the total idle time of employees in the non-operating state, T active The actual effective working hours of employees.

5. The employee attendance data analysis system based on artificial intelligence according to claim 1 is characterized by: The specific processing steps of integrating the pre-processed attendance data using big data processing technology to build an employee attendance database are as follows: Unify the data format of the pre-processed attendance data; The pre-processed attendance data is deduplicated using a hash algorithm; Based on data cleaning and filtering technology, attendance data that does not conform to the standard format or contains obvious errors is eliminated and corrected; The cleaned attendance data is stored to build an employee attendance database.

6. The employee attendance data analysis system based on artificial intelligence according to claim 1 is characterized by: The specific construction steps of the model building module are: Two-layer Generative Adversarial Network Model GAN dual It consists of two parts: the generator and the discriminator: the first layer generator G1 is used to generate simulated attendance data based on the historical attendance data in the employee attendance database; the first layer discriminator D1 is used to judge the authenticity of the generated simulated attendance data; the second layer generator G2 is used to generate complex attendance behavior patterns, including abnormal attendance behavior and normal behavior; the second layer discriminator D2 is used to judge the authenticity of the generated complex attendance behavior patterns. The overall objective function L of the two-layer generative adversarial network model GAN It is expressed as: Among them, p data (D real ) represents the distribution of real attendance data, and Respectively represent the noise distribution used to generate simulated attendance data and complex attendance behavior patterns, represents the mean, G1 and G2 are the first and second layer generators, D1 and D2 are the first and second layer discriminators, and the objective function L GAN Train a two-layer GAN model by minimizing the generator loss and maximizing the first and second layer discriminator losses; Based on employee attendance database DB attendance The historical attendance data in the training layer is used to train the first-layer generator G1 to generate simulated attendance data D sim , the generation process of simulated attendance data is expressed as: D sim =G1(z1)=σ(W G1 z1+b G1 ); Among them, z1 is the input random noise vector, W G1 and b G1 are the weight matrix and bias vector of the first layer generator, σ is the activation function, D sim The simulated attendance data is generated, G1 is the first layer generator, and the generator adjusts the weight W G1 and bias b G1 Learn the distribution of historical attendance data; Train the first layer of discriminator D1 to discriminate the generated simulated attendance data D sim With real attendance data D real The authenticity of , the judgment process is expressed as: Among them, D input is the input attendance data, and the attendance data is the generated simulated attendance data D sim Or real attendance data D real , W D1 and b D1 are the weight matrix and bias vector of the first-layer discriminator, respectively. The first-layer discriminator optimizes the accuracy of discrimination by adjusting parameters; Based on the training results of the first-layer generator and the first-layer discriminator, the real attendance behavior pattern is generated, and the second-layer generator G2 is constructed to integrate all the real attendance behavior patterns to generate a more complex attendance behavior pattern. The process of generating a complex attendance behavior pattern is expressed as: B complex =G2(z2)=tanh(W G2 z2+b G2 ); Among them, z2 is the input random noise vector, W G2 and b G2 are the weight matrix and bias vector of the second-layer generator, tanh is the activation function, G2 is the second-layer generator, and the generator generates a complex attendance behavior pattern B complex To mimic abnormal patterns in real attendance behavior; Train the second layer discriminator D2 to discriminate the generated complex attendance behavior pattern B complex The authenticity of the actual attendance behavior pattern is determined by: Among them, B input The input behavior pattern data is used to generate complex attendance behavior pattern B complex Or real attendance behavior pattern B real The second layer discriminator adjusts the weight matrix W D2 and the bias vector b D2 Optimize discrimination ability; By repeatedly training the first and second layer generative adversarial network models, optimizing the generation capabilities of the first and second layer generators G1 and G2, as well as the discrimination accuracy of the first and second layer discriminators D1 and D2, we finally obtain a two-layer generative adversarial network model GAN ​​that can simulate and recognize attendance behavior. dual During the training process, the loss functions of the generator and the discriminator are: Among them, L G1,G2 are the loss functions of the first and second layer generators G1 and G2, respectively, indicating the probability that the generated simulated attendance data and complex attendance behavior patterns are identified as real data, L D1,D2 The loss functions for discriminating D1 and D2 in the first and second layers are used. By repeatedly optimizing the loss functions, a two-layer generative adversarial network model is finally constructed to simulate and recognize complex attendance behavior patterns.

7. The employee attendance data analysis system based on artificial intelligence according to claim 1 is characterized by: The specific employee attendance behavior pattern recognition method of the attendance detection module is: The integrated employee attendance database DB attendance The data in is input into the two-layer generative adversarial network model GAN dual In the process of attendance behavior pattern recognition: Among them, M recog In order to identify the complex attendance behavior pattern, G1 and G2 are the first and second layer generators of the two-layer generative adversarial network model, D2 is the second layer discriminator, z2 is the input random noise vector, W G1 and W G2 are the weight matrices of the first and second layer generators, respectively, and b G1 and b G2 are their bias vectors, h is the activation function, f is the nonlinear mapping function, Represents a complex behavior pattern that selects the discriminator to maximize its output probability; According to the identified complex attendance behavior pattern, the classification function is used to classify it into normal working hours M normal , Overtime work overtime 、Not logged in to use M absent and irregular use behavior irregular : Among them, M class is the set of complex attendance behavior patterns after classification, α i is the weight parameter in the classification model, g i (M) is the classification feature function of the complex attendance behavior pattern, k is the number of features used for classification, It represents the selection of the complex attendance behavior pattern with the maximum weighted sum of features; Extract features for each complex attendance behavior pattern. The extracted features include login usage duration, operation frequency, and login interval: Among them, F extract is the extracted feature set, T usage is the usage time, F freq is the operating frequency, T interval is the login interval, β j is the weight parameter in the feature extraction model, h j (F) is the feature function for feature extraction, and n is the number of features used in the feature extraction model; The extracted complex attendance behavior features are input into the pattern classifier to refine the classification of complex attendance behavior patterns. The output of the classifier is represented as follows: Among them, M final is the final classification result, C is the classifier function, γ l is the weight parameter in the pattern classifier, q l (F extract ) is the feature mapping function in the classifier, and m is the number of features used in the classifier.

8. The employee attendance data analysis system based on artificial intelligence according to claim 1 is characterized by: The specific abnormal behavior detection method of the attendance detection module is: Anomaly detection is performed based on the simulated attendance data generated by the two-layer generative adversarial network model and the attendance data in the employee attendance database. The detection process identifies the existing abnormal behaviors. According to the abnormal behaviors detected, they are classified into forged usage records, abnormally frequent login and logout behaviors, and abnormal behaviors of not using the software for a long time; Perform feature extraction on each abnormal behavior pattern to extract the frequency of abnormal behavior, the duration of abnormal behavior and the environmental characteristics when the abnormal behavior occurs; Based on the extracted abnormal behavior features, they are input into the abnormal behavior discriminator to further determine and refine the abnormal behavior, and finally determine the type and characteristics of the abnormal behavior; Based on the abnormal behavior finally determined, an abnormal behavior report is generated, which includes the type of abnormal behavior identified, its frequency, duration, and the environment in which it occurs.

9. The employee attendance data analysis system based on artificial intelligence according to claim 1, characterized in that: The specific attendance trend prediction steps of the trend prediction module are: based on the historical attendance data D in the employee attendance database hist And the two-layer generative adversarial network model GAN dual Generated simulated data D sim , analyze the working hours and usage frequency of employees, and extract the main features F trend : Among them, α i is the weight of each feature, φ i is the nonlinear feature mapping function, and They represent the working hours and usage frequency of the i-th historical period respectively. G1 and G2 are the first and second layer generators of the two-layer generative adversarial network model respectively. and Respectively represent the historical data and simulation data of the i-th period; The time series analysis model TSM is used to perform trend analysis on the extracted feature data and predict the working hours T of employees in the future. future and frequency of use F future , the prediction process is expressed as: in, is the weight of each time series feature, ψ j is the time series feature conversion function, is the jth time series feature, Δt j is the time interval, θ j is the parameter set of the time series model, TSM is the time series analysis model function, and outputs the predicted future working time T future and frequency of use F future ; Based on the prediction results of the time series analysis model, the attendance trend prediction model PTM is generated to predict the future attendance patterns of employees, including possible attendance fluctuations and potential abnormal attendance behaviors: Among them, γ k is the weight coefficient of the attendance trend model, ξ k is the attendance trend feature mapping function, and are the predicted working hours and usage frequency of the kth future period, respectively, k is the parameter set used to generate the attendance trend model, and PTM is the final attendance trend prediction model.

10. An analysis method for employee attendance data based on artificial intelligence, characterized in that: It follows the steps: Pre-process the collected attendance data, and then use big data processing technology to integrate the pre-processed attendance data to build an employee attendance database; A two-layer generative adversarial network model is constructed based on the employee attendance database. The first-layer generator in the two-layer generative adversarial network model is used to generate simulated attendance data based on the historical attendance data in the employee attendance database, and to generate real attendance behavior patterns based on the simulated attendance data; the second-layer generator is used to generate complex attendance behavior patterns; Perform pattern recognition on the employee attendance database according to the two-layer generative adversarial network model to identify the employee's attendance behavior pattern as a real attendance behavior pattern or a complex attendance behavior pattern; perform anomaly detection on the attendance data corresponding to the attendance behavior pattern in the employee attendance database according to the two-layer generative adversarial network model; Attendance trend prediction is performed based on simulated attendance data and real-time attendance data in the employee attendance database.

11. A computer program product, comprising a computer program, characterized in that The computer program implements the steps of the method according to claim 10 when executed by a processor.

Images