Employee behavior risk prediction method and system based on big data analysis
By collecting and integrating multi-source employee behavior data in the enterprise ERP system, conducting big data analysis, and building a behavior risk prediction model, the problems of subjective bias, limited data and time-consuming and labor-consuming in traditional methods are solved, and accurate prediction and efficient management of employee behavior are achieved.
Patent Information
- Application Number
- CN202510062930.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-15
- Publication Date
- 2025-05-23
AI Technical Summary
Traditional employee behavior risk prediction methods have problems such as managers' subjective judgment bias, limited data sources, time-consuming and labor-consuming, and it is difficult to conduct efficient and personalized employee behavior prediction and management in large-scale enterprises.
The employee behavior risk prediction method based on big data analysis is adopted. By obtaining the basic information of employees, multi-source behavior data is collected from multiple sub-platform databases of the enterprise ERP system, fusion processing, feature extraction and integration, and a pre-constructed behavior risk prediction model is input to obtain the behavior risk prediction results and early warning processing.
It realizes accurate prediction and management of employee behavior, improves the degree of automation, is suitable for large-scale enterprises, and can provide personalized risk warning and management decision-making basis.
Smart Images
Figure CN120031185A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of computer technology, and specifically relates to a method and system for predicting employee behavior risks based on big data analysis. Background Art
[0002] With the rapid development of information technology and the increasing complexity of enterprise management, the standardization and risk prediction of employee behavior have become important issues in enterprise management. Traditional employee behavior risk prediction mainly relies on managers' experience judgment, performance appraisal and questionnaire surveys to understand employees' work status in order to achieve behavioral risk assessment of employees. However, in the process of using the existing technology, the inventors found that there are at least the following problems in the existing technology: on the one hand, the subjective judgment of managers may be biased, and new managers lack sufficient experience and find it difficult to accurately judge the behavioral risks of employees; on the other hand, the traditional methods rely on limited data sources, such as attendance records and performance evaluations, which cannot fully and timely reflect the behavioral status of employees; in addition, the existing methods are generally time-consuming and labor-intensive, making it difficult to conduct efficient and personalized employee behavior prediction and management in large-scale enterprises. Summary of the invention
[0003] The present invention aims to solve the above technical problems at least to a certain extent. The present invention provides an employee behavior risk prediction method and system based on big data analysis.
[0004] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides an employee behavior risk prediction method based on big data analysis, comprising: Obtaining basic employee information of a designated employee, and based on the basic employee information, collecting multi-source behavior data of the designated employee from multiple sub-platform databases of an enterprise ERP system; Performing fusion processing on the multi-source behavior data to obtain the multi-source aligned behavior data of the designated employee; Performing feature extraction processing on the multi-source aligned behavior data to obtain multi-source behavior feature data, and integrating the multi-source behavior feature data to obtain a set of behavior feature data of the designated employee; Inputting the behavioral feature data set into a pre-built behavioral risk prediction model to obtain a behavioral risk prediction result for the designated employee; Based on the behavior risk prediction result, a behavior risk warning is performed on the designated employee.
[0005] In a possible design, when multi-source behavior data of a designated employee is collected from multiple sub-platform databases of an enterprise ERP system, the data is collected uniformly based on a preset big data platform; the big data platform uses Hadoop and / or Spark.
[0006] In one possible design, the sub-platform database of the enterprise ERP system includes an employee attendance system database, an enterprise email system database, a project management system database and a social network platform database; correspondingly, the multi-source behavior data includes attendance data collected from the employee attendance system database, email communication records collected from the enterprise email system database, project execution data collected from the project management system database and social data collected from the social network platform database.
[0007] In a possible design, the multi-source behavior data is fused to obtain a behavior feature data set of the designated employee, including: Preprocessing the multi-source behavior data to obtain multi-source preprocessed behavior data; Performing dimensionality reduction processing on the multi-source pre-processed behavior data to obtain multi-source dimensionality reduced behavior data; Data alignment is performed on the multi-source dimensionality-reduced behavior data to obtain multi-source aligned behavior data.
[0008] In a possible design, the reduced-dimensional behavior data of any data source is:
[0009] in, N The pre-processed behavior data corresponding to the dimension-reduced behavior data of any one of the data sources; δ It is a preset data mining operator; L m is the relationship distance between data dimensions of the behavior data after dimensionality reduction of any one of the data sources; L n is the relationship distance between data dimensions of the pre-processed behavior data corresponding to the dimensionality-reduced behavior data of any one of the data sources; log is the logarithmic sign.
[0010] In a possible design, after obtaining the behavioral characteristic data set of the designated employee, the method further includes: Performing vectorization processing on the multi-source behavior feature data in the behavior feature data set to obtain multiple behavior feature vectors; A user profile of the designated employee is constructed based on a plurality of behavioral feature vectors.
[0011] In a second aspect, the present invention provides an employee behavior risk prediction system based on big data analysis, which is used to implement any of the employee behavior risk prediction methods based on big data analysis described above; the employee behavior risk prediction system based on big data analysis includes: A behavior data acquisition module is used to acquire basic employee information of a designated employee, and based on the basic employee information, collect multi-source behavior data of the designated employee from multiple sub-platform databases of the enterprise ERP system; A data fusion module, connected to the communication, for fusing the multi-source behavior data to obtain the multi-source aligned behavior data of the designated employee; A feature extraction module, which is in communication connection with the data fusion module, is used to perform feature extraction processing on the multi-source aligned behavior data to obtain multi-source behavior feature data, and integrate the multi-source behavior feature data to obtain a set of behavior feature data of the designated employee; a risk prediction module, which is in communication with the feature extraction module and is used to input the behavioral feature data set into a pre-built behavioral risk prediction model to obtain a behavioral risk prediction result of the designated employee; The risk warning module is in communication with the risk prediction module and is used to perform behavioral risk warning processing on the designated employee based on the behavioral risk prediction result.
[0012] In a third aspect, the present invention provides an electronic device, comprising: a memory for storing computer program instructions; and, A processor is used to execute the computer program instructions to complete the operation of the employee behavior risk prediction method based on big data analysis as described in any one of the above.
[0013] In a fourth aspect, the present invention provides a computer-readable storage product having instructions stored thereon. When the instructions are run on a computer, the employee behavior risk prediction method based on big data analysis as described above is executed.
[0014] In a fifth aspect, the present invention provides a computer program product, including a computer program or instructions, which, when executed by a computer, implements the employee behavior risk prediction method based on big data analysis as described in any one of the above.
[0015] The beneficial effects of the present invention are: The present invention discloses a method and system for predicting employee behavior risks based on big data analysis, which can realize accurate prediction and management of employee behavior by integrating data from different sources. Specifically, in the implementation process of the present invention, first, the basic information of the designated employee is obtained, and based on the basic information of the employee, the multi-source behavior data of the designated employee is collected from multiple sub-platform databases of the enterprise ERP system; then, the multi-source behavior data is fused to obtain the multi-source aligned behavior data of the designated employee; then, the multi-source aligned behavior data is subjected to feature extraction processing to obtain multi-source behavior feature data, and the multi-source behavior feature data is integrated to obtain the behavior feature data set of the designated employee; then, the behavior feature data set is input into a pre-constructed behavior risk prediction model to obtain the behavior risk prediction result of the designated employee; finally, based on the behavior risk prediction result, the designated employee is subjected to behavior risk warning processing. Based on the above scheme, the present invention realizes the behavior risk prediction of employees by integrating the multi-source behavior data of the enterprise ERP system, which can be conducive to the accurate prediction and management of employee behavior, and has a high degree of automation, and can be applied to large-scale enterprises.
[0016] Other beneficial effects of the present invention will be further described in the specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 is a flow chart of an employee behavior risk prediction method based on big data analysis in an embodiment; Figure 2 This is a module block diagram of an employee behavior risk prediction system based on big data analysis in an embodiment; Figure 3 It is a module block diagram of an electronic device in an embodiment. DETAILED DESCRIPTION
[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.
[0019] Embodiment 1: This embodiment discloses an employee behavior risk prediction method based on big data analysis, which can be executed by, but is not limited to, a computer device or a virtual machine with certain computing resources, such as a personal computer, a smart phone, a personal digital assistant, or a wearable device, or by a virtual machine.
[0020] like Figure 1 As shown, a method for predicting employee behavior risks based on big data analysis may include but is not limited to the following steps: S1. Obtain the basic information of the designated employee, and based on the basic information, collect the multi-source behavior data of the designated employee from multiple sub-platform databases of the enterprise ERP system; specifically, in this embodiment, the basic information of the employee includes but is not limited to the employee's name, work number, telephone number and / or ID number and other information that can represent the employee's identity. When it is necessary to predict the behavior risk of an employee, it is only necessary to collect the multi-source behavior data that uniquely matches the employee from multiple sub-platform databases of the enterprise ERP system based on the basic information of the employee, and perform subsequent behavior risk analysis and prediction on the employee based on the multi-source behavior data.
[0021] In order to avoid repeated collection of data from the same data source to improve data quality, and to store behavioral data from different sources in a decentralized manner to improve subsequent data utilization and further reduce data collection costs, this embodiment further makes the following technical improvements: when collecting multi-source behavioral data of specified employees from multiple sub-platform databases of the enterprise ERP system, the data is collected uniformly based on a preset big data platform; the big data platform uses Hadoop and / or Spark.
[0022] It should be noted that in order to improve the overall development efficiency of this solution and to make it applicable to different application scenarios, in this embodiment, the big data platform is implemented using both Hadoop (a distributed system infrastructure developed by the Apache Foundation that can realize the storage and analytical calculation of massive data) and Spark (a fast, general, and scalable big data analysis engine). Hadoop excels in big data collection and offline processing, especially in scenarios that require high scalability and fault tolerance, while Spark, with its in-memory computing and rapid iteration capabilities, has an advantage in real-time data processing and complex data processing tasks. The combination of the two can give full play to their respective advantages.
[0023] Specifically, in this embodiment, the sub-platform database of the enterprise ERP system includes an employee attendance system database, an enterprise email system database, a project management system database, and a social network platform database; correspondingly, the multi-source behavior data includes attendance data collected from the employee attendance system database, email communication records collected from the enterprise email system database, project execution data collected from the project management system database, and social data collected from the social network platform database. It should be noted that the multiple sub-platform databases can be the databases of each subsystem in the enterprise ERP (Enterprise Resource Planning) system. The enterprise ERP system can help the enterprise to grasp the work status of projects and employees in real time while improving the work efficiency of employees, thereby effectively controlling manpower and operating costs, reducing employment risks, and improving the service quality of the enterprise. Specifically, among the subsystems of the enterprise ERP system, the employee attendance system is used to record the attendance of employees, and can generate attendance records such as sign-in, scheduling, and leave, and can generate corresponding statistical reports. The enterprise email system is used to process the sending and receiving of emails through email servers and user agents to ensure the timeliness and accuracy of information transmission. The project management system is used to manage and track project progress, resource allocation, and cost control. The social networking platform is used to meet the employees' social functions such as internal corporate communication and dynamic sharing, based on which the employees' social interaction data can be obtained. In this embodiment, by collecting multi-source behavioral data of specified employees from multiple sub-platform databases, it is possible to fully understand the employees' behavior patterns, so as to conduct comprehensive behavioral analysis and behavioral risk prediction of employees.
[0024] S2. Perform fusion processing on the multi-source behavior data to obtain the multi-source aligned behavior data of the designated employee.
[0025] Specifically, in step S2, the multi-source behavior data is fused to obtain a behavior feature data set of the designated employee, including: S201. Preprocess the multi-source behavior data to obtain multi-source preprocessed behavior data; specifically, in this embodiment, after data collection, the big data platform directly performs preprocessing such as data cleaning, data denoising and data standardization on the multi-source behavior data to form a data set in a unified format, thereby ensuring the consistency and accuracy of the data and improving the subsequent data processing efficiency.
[0026] S202. Perform dimensionality reduction processing on the multi-source pre-processed behavior data to obtain multi-source reduced-dimensionality behavior data; it should be noted that performing dimensionality reduction processing on the multi-source pre-processed behavior data to convert the multi-source pre-processed behavior data into multi-source reduced-dimensionality behavior data of the same dimension can retain the main information in the multi-source pre-processed behavior data and simplify the difficulty of subsequent behavior data analysis.
[0027] In step S202 of this embodiment, the behavior data after dimension reduction of any data source is:
[0028] in, N The pre-processed behavior data corresponding to the behavior data after dimensionality reduction of any one of the data sources, that is, the data before dimensionality reduction processing; δ is a preset data mining operator. It should be understood that the data mining operator The dimension of matches the dimension of the behavior data after dimensionality reduction of any one of the data sources; L m is the relationship distance between data dimensions of the behavior data after dimensionality reduction of any one of the data sources; L n is the relationship distance between data dimensions of the pre-processed behavior data corresponding to the dimensionality-reduced behavior data of any one of the data sources; log It is a logarithmic symbol. It should be noted that the relationship distance between the data dimensions of any data is used to characterize the relevance of the metadata in the data under the current data dimension. When the metadata in the data has multiple features or attributes, this relationship distance can be used to measure the relationship between metadata of different dimensions.
[0029] Based on the above expression, it can be known that when the present embodiment performs dimensionality reduction processing on the preprocessed behavior data of any data source, the relationship distance between the data dimensions of the reduced-dimensional behavior data to be obtained is obtained in advance according to the data dimensions of the original preprocessed behavior data, and the relationship distance between the data dimensions is obtained according to the data dimensions of the reduced-dimensional behavior data to be obtained, and at the same time, the data mining operator is set according to the data dimensions of the reduced-dimensional behavior data to be obtained, and then the reduced-dimensional behavior data can be obtained based on the preprocessed behavior data. Based on this, the present embodiment can quickly realize the dimensionality reduction processing of multi-source preprocessed behavior data.
[0030] S203. Perform data alignment processing on the multi-source dimensionality-reduced behavioral data to obtain multi-source aligned behavioral data. It should be noted that the alignment processing can be used to ensure the temporal alignment of the dimensionality-reduced behavioral data from different sources, and realize the association and integration of data from different sources. In the implementation process, data alignment processing is realized by synchronizing the data timestamps of different acquisition terminals (i.e., sub-platform databases), so that the employee behavior risk status at different times can be reflected in the subsequent employee behavior risk analysis.
[0031] S3. Perform feature extraction processing on the multi-source aligned behavior data to obtain multi-source behavior feature data, and integrate the multi-source behavior feature data to obtain the behavior feature data set of the specified employee. It should be understood that, in this embodiment, the behavior feature data set includes multi-source behavior feature data that matches the multi-source behavior data; it should be noted that the behavior feature data is data that can describe employee behavior. Specifically, in this embodiment, the multi-source behavior feature data in the behavior feature data set includes attendance rate that matches attendance data, email communication frequency that matches the email communication record, project completion rate that matches the project execution data, and social interaction frequency that matches the social data.
[0032] S4. Input the behavioral feature data set into a pre-built behavioral risk prediction model to obtain the behavioral risk prediction result of the designated employee. Specifically, in this embodiment, the behavioral risk prediction result includes a risk score, a risk classification, and a risk event identifier, wherein the higher the risk score value, the greater the employee risk, and the risk classification is low risk, medium risk, or high risk. The risk event identifier is used to display specific risk events, such as violations of regulations, data leakage, or fraud, etc., to provide managers with a decision-making basis for employee management.
[0033] It should be noted that, in this embodiment, the behavior risk prediction model is trained based on multiple sets of sample feature data sets with risk labels, so as to effectively identify and predict the risky behavior of employees.
[0034] S5. Based on the behavioral risk prediction results, conduct behavioral risk warning processing for the designated employee.
[0035] In this embodiment, after obtaining the behavior characteristic data set of the designated employee, the method further includes: S6. performing vectorization processing on the multi-source behavior feature data in the behavior feature data set to obtain a plurality of behavior feature vectors; S7. Construct a user profile of the designated employee based on multiple behavioral feature vectors.
[0036] It should be noted that, in this embodiment, the user portrait is a multi-dimensional employee behavior description data, including the employee's basic information, social habits, work habits, performance information, etc., which is not limited here.
[0037] This embodiment can achieve accurate prediction and management of employee behavior by integrating data from different sources. Specifically, during the implementation of this embodiment, first, the basic information of the designated employee is obtained, and based on the basic information of the employee, the multi-source behavior data of the designated employee is collected from multiple sub-platform databases of the enterprise ERP system; then, the multi-source behavior data is fused to obtain the multi-source aligned behavior data of the designated employee; then, the multi-source aligned behavior data is subjected to feature extraction processing to obtain multi-source behavior feature data, and the multi-source behavior feature data is integrated to obtain the behavior feature data set of the designated employee; then, the behavior feature data set is input into the pre-built behavior risk prediction model to obtain the behavior risk prediction result of the designated employee; finally, based on the behavior risk prediction result, the designated employee is subjected to behavior risk warning processing. Based on the above scheme, this embodiment realizes the behavior risk prediction of employees by integrating the multi-source behavior data of the enterprise ERP system, which can facilitate the accurate prediction and management of employee behavior, and has a high degree of automation, and can be applied to large-scale enterprises.
[0038] Embodiment 2: This embodiment discloses an employee behavior risk prediction system based on big data analysis, which is used to implement the employee behavior risk prediction method based on big data analysis in Example 1; Figure 2 As shown, the employee behavior risk prediction system based on big data analysis includes: A behavior data acquisition module is used to acquire basic employee information of a designated employee, and based on the basic employee information, collect multi-source behavior data of the designated employee from multiple sub-platform databases of the enterprise ERP system; A data fusion module, connected to the communication, for fusing the multi-source behavior data to obtain the multi-source aligned behavior data of the designated employee; A feature extraction module, which is in communication connection with the data fusion module, is used to perform feature extraction processing on the multi-source aligned behavior data to obtain multi-source behavior feature data, and integrate the multi-source behavior feature data to obtain a set of behavior feature data of the designated employee; a risk prediction module, which is in communication with the feature extraction module and is used to input the behavioral feature data set into a pre-built behavioral risk prediction model to obtain a behavioral risk prediction result of the designated employee; The risk warning module is in communication with the risk prediction module and is used to perform behavioral risk warning processing on the designated employee based on the behavioral risk prediction result.
[0039] It should be noted that the working process, working details and technical effects of the employee behavior risk prediction system based on big data analysis provided in this embodiment 2 can be found in embodiment 1 and will not be repeated here.
[0040] Embodiment 3: Based on Embodiment 1 or 2, this embodiment discloses an electronic device, which may be a smart phone, a tablet computer, a laptop computer, or a desktop computer. The electronic device may be referred to as a user terminal, a portable terminal, a desktop terminal, etc. Figure 3 As shown, the electronic equipment includes: a memory for storing computer program instructions; and, A processor is used to execute the computer program instructions to complete the operation of the employee behavior risk prediction method based on big data analysis as described in any one of Example 1.
[0041] Specifically, the processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen.
[0042] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, which is used to be executed by the processor 301 to implement the employee behavior risk prediction method based on big data analysis provided in Example 1 of the present application.
[0043] In some embodiments, the terminal may further optionally include: a communication interface 303 and at least one peripheral device. The processor 301, the memory 302 and the communication interface 303 may be connected via a bus or a signal line. Each peripheral device may be connected to the communication interface 303 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 304, a display screen 305 and a power supply 306.
[0044] The communication interface 303 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the communication interface 303 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.
[0045] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with a communication network and other communication devices through electromagnetic signals.
[0046] The display screen 305 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof.
[0047] The power supply 306 is used to supply power to various components in the electronic device.
[0048] Embodiment 4: Based on any one of Embodiments 1 to 3, this embodiment discloses a computer-readable storage product, on which instructions are stored, and when the instructions are run on a computer, the employee behavior risk prediction method based on big data analysis as described in any one of Embodiments 1 is executed. The computer-readable storage product refers to a carrier for storing data, which may include but is not limited to computer-readable storage media such as floppy disks, optical disks, hard disks, flash memories, USB flash drives, and / or memory sticks, and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
[0049] Embodiment 5: Based on any one of Examples 1 to 3, this embodiment discloses a computer program product, including a computer program or instructions, which, when executed by a computer, implements the employee behavior risk prediction method based on big data analysis as described in any one of Example 1.
[0050] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for predicting employee behavior risks based on big data analysis, characterized in that: include: Obtaining basic employee information of a designated employee, and based on the basic employee information, collecting multi-source behavior data of the designated employee from multiple sub-platform databases of an enterprise ERP system; Performing fusion processing on the multi-source behavior data to obtain the multi-source aligned behavior data of the designated employee; Performing feature extraction processing on the multi-source aligned behavior data to obtain multi-source behavior feature data, and integrating the multi-source behavior feature data to obtain a set of behavior feature data of the designated employee; Inputting the behavioral feature data set into a pre-built behavioral risk prediction model to obtain a behavioral risk prediction result for the designated employee; Based on the behavior risk prediction result, a behavior risk warning is performed on the designated employee.
2. The employee behavior risk prediction method based on big data analysis according to claim 1 is characterized by: When collecting multi-source behavior data of a designated employee from multiple sub-platform databases of an enterprise ERP system, the data is collected uniformly based on a preset big data platform; the big data platform uses Hadoop and / or Spark.
3. The employee behavior risk prediction method based on big data analysis according to claim 1 is characterized by: The sub-platform database of the enterprise ERP system includes an employee attendance system database, an enterprise email system database, a project management system database and a social network platform database; correspondingly, the multi-source behavior data includes attendance data collected from the employee attendance system database, email communication records collected from the enterprise email system database, project execution data collected from the project management system database and social data collected from the social network platform database.
4. The employee behavior risk prediction method based on big data analysis according to claim 1 is characterized by: The multi-source behavior data is fused to obtain a behavior feature data set of the designated employee, including: Preprocessing the multi-source behavior data to obtain multi-source preprocessed behavior data; Performing dimensionality reduction processing on the multi-source pre-processed behavior data to obtain multi-source dimensionality reduced behavior data; Data alignment is performed on the multi-source dimensionality-reduced behavior data to obtain multi-source aligned behavior data.
5. The employee behavior risk prediction method based on big data analysis according to claim 4 is characterized by: The behavior data after dimensionality reduction of any data source is: in, N The pre-processed behavior data corresponding to the dimension-reduced behavior data of any one of the data sources; δ It is a preset data mining operator; L m is the relationship distance between data dimensions of the behavior data after dimensionality reduction of any one of the data sources; L n is the relationship distance between data dimensions of the pre-processed behavior data corresponding to the dimensionality-reduced behavior data of any one of the data sources; log is the logarithmic sign.
6. The employee behavior risk prediction method based on big data analysis according to claim 1 is characterized by: After obtaining the behavioral characteristic data set of the designated employee, the method further includes: Performing vectorization processing on the multi-source behavior feature data in the behavior feature data set to obtain multiple behavior feature vectors; A user profile of the designated employee is constructed based on a plurality of behavioral feature vectors.
7. An employee behavior risk prediction system based on big data analysis, characterized by: Used to implement the employee behavior risk prediction method based on big data analysis as described in any one of claims 1 to 6; The employee behavior risk prediction system based on big data analysis includes: A behavior data acquisition module is used to acquire basic employee information of a designated employee, and based on the basic employee information, collect multi-source behavior data of the designated employee from multiple sub-platform databases of the enterprise ERP system; A data fusion module, connected to the communication, for fusing the multi-source behavior data to obtain the multi-source aligned behavior data of the designated employee; A feature extraction module, which is in communication connection with the data fusion module, is used to perform feature extraction processing on the multi-source aligned behavior data to obtain multi-source behavior feature data, and integrate the multi-source behavior feature data to obtain a set of behavior feature data of the designated employee; a risk prediction module, which is in communication with the feature extraction module and is used to input the behavioral feature data set into a pre-built behavioral risk prediction model to obtain a behavioral risk prediction result of the designated employee; The risk warning module is in communication with the risk prediction module and is used to perform behavioral risk warning processing on the designated employee based on the behavioral risk prediction result.
8. An electronic device, characterized in that: include: a memory for storing computer program instructions; as well as, A processor is used to execute the computer program instructions to complete the operation of the employee behavior risk prediction method based on big data analysis as described in any one of claims 1 to 6.
9. A computer readable storage product, characterized in that: The computer-readable storage product stores instructions, and when the instructions are executed on a computer, the employee behavior risk prediction method based on big data analysis as described in any one of claims 1 to 6 is executed.
10. A computer program product comprising a computer program or instructions, characterized in that: When the computer program or the instruction is executed by a computer, the method for predicting employee behavior risks based on big data analysis as described in any one of claims 1 to 6 is implemented.