Salary management system

Abstract

The invention relates to the technical field of salary management, in particular to a salary management system which comprises a data acquisition module, a data processing module, a data analysis module, a data comparison module and a control management module. The method comprises the steps of comparing analysis results of all deep learning processing units, judging whether different analysis results exist or not, comparing the same analysis result with analysis results of previous several months, judging whether data with large difference exist or not, guaranteeing the accuracy of the data, storing the same data through all the deep learning processing units, and storing the same data through all the deep learning processing units. The same data stored in each deep learning processing unit is randomly selected and compared daily through a data comparison module, the data consistency is guaranteed, then according to employee information, an analysis result is screenshot, and according to the employee information in a picture, the analysis result is sent to a corresponding employee mailbox, so that the convenience of the employees at the same time is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of salary management, and in particular to a salary management system. Background Art

[0002] Compensation management refers to the company formulating a set of scientific compensation strategies and systems based on its own development strategy and market competition conditions, giving corresponding economic and non-economic rewards to employees' labor contributions in order to motivate employees and improve work efficiency and company competitiveness. Traditionally, compensation management is done by professionals, but larger companies have more employees and require a large number of professionals to carry out compensation management, which is time-consuming and labor-intensive, and errors are prone to occur during the management process.

[0003] Therefore, there have emerged a method and system for enterprise salary management, such as the invention patent with publication number CN118608113A, and a method and electronic equipment for supervising the payment of wages to migrant workers, such as the invention patent with publication number CN118864124A, to carry out salary management work.

[0004] However, during use, it was found that the existing salary management system has a low calculation accuracy for salary, and it is difficult to detect errors in calculation. In addition, the data is easily tampered with, resulting in poor practicality. Therefore, a salary management system is urgently needed to improve the above problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a method of establishing multiple sub-databases by randomly selecting data from a total database, and then multiple deep learning processing units each select a sub-database as training data, and then analyze and process the same received data through multiple qualified deep learning processing units, and then compare the analysis results of each deep learning processing unit to determine whether there are different analysis results, and then compare the same analysis results with the analysis results of the previous few months to determine whether there are large differences in data to ensure the accuracy of the data. Secondly, the same data is stored in each deep learning processing unit, and the same data stored in each deep learning processing unit is randomly selected and compared through a data comparison module on a daily basis to ensure the sameness of the data, and the modification of the data requires the simultaneous confirmation and consent of multiple different managers to prevent the data from being tampered with. Then, according to the employee information, the analysis results are screenshoted, and sent to the corresponding employee mailbox according to the employee information in the picture, thereby improving the convenience of a salary management system for employees.

[0006] A salary management system of the present invention comprises: Data acquisition module: acquires the work completed, reimbursement documents and attendance data of each employee within this month; Data processing module: organize the format of the acquired text data, convert the acquired image data into text, and then the staff will check the converted data. After the verification is correct, the data will be sent to the data analysis module; After the data analysis is completed, the verified analysis results will be cut into several pictures according to the employee information, and sent to the corresponding employee mailbox according to the employee information in the pictures; Data analysis module: Analyze and process the received data, check the analysis results, and compare them with the analysis results of the previous few months to ensure the accuracy of the analysis results. Finally, the staff will make a final confirmation of the analysis results and store the received data and analysis results; Data comparison module: randomly selects some data from the same data stored in different locations and compares them to ensure the data is the same. If the data is different during the comparison process, an alert will be sent to multiple managers in the form of a pop-up window; Control management module: provides an interactive platform for staff and the system, centrally manages the data acquisition module, data processing module, data analysis module and data comparison module, verifies the identity information of the logged-in personnel, records the system's operating procedures and the staff's operating procedures, and sends the records to the data analysis module for storage.

[0007] Preferably, the data acquisition module includes: Work data acquisition unit: obtain the work completion status of each employee within this month; Reimbursement document acquisition unit: obtains the reimbursement documents of each employee within this month; Attendance data acquisition unit: obtain the attendance status of each employee within this month.

[0008] Preferably, the data processing module: Preprocessing unit: converts the format of received data to ensure the consistency of data format, and converts the uploaded image data into text data. Then the staff checks the converted text data. After it is correct, the data is compressed and sent to the data analysis module. Publication unit: Organize the analysis results and employee information into the consent form, take screenshots of each employee's information and analysis results, and then send them to the corresponding employee's mailbox based on the employee information in the picture.

[0009] Preferably, the pre-processing unit comprises: Format adjustment unit: convert text data in different formats into the same format; Image-text conversion unit: converts image data into text data; Data compression unit: compresses the processed data and sends it to the data analysis module.

[0010] Preferably, the publishing unit comprises: Form generation unit: organizes analysis results and employee information into consent forms and adjusts the proportions of the forms; Screenshot unit: screenshot the table according to employee information, and separate the information and analysis results of different employees; Sending unit: sends the information of the employees in the picture to the corresponding employee mailbox.

[0011] Preferably, the data analysis module includes: Database: stores the training data of the deep learning processing unit; Deep learning processing unit: There are multiple groups. The model is trained with data in the database. The PyTorch framework and long short-term memory network are used to analyze and process the data through the trained qualified model to calculate the employee salary. After that, multiple groups of deep learning processing units will compare the analysis results to check whether the analysis results are the same. If they are not the same, they will be recalculated. If the analysis results are the same, they will be compared with the analysis results of the previous few months to check whether the analysis results are significantly different from those of the previous few months. If the error is large, the analysis will be recalculated. If the analysis results are still different or the error is large after multiple recalculations, the analysis will be stopped and wait for the staff to check. Transmission unit: The number of transmission units is the same as that of deep learning processing units, and data is transmitted between each deep learning processing unit; Storage module: The number of storage modules is the same as the deep learning processing units, and is used to store the data and analysis results received by the deep learning processing units.

[0012] Preferably, the database includes: General database: to store the company's basic salary calculation methods, calculation cases and other types of salary calculation methods and calculation cases obtained from the Internet; Selection unit: There are multiple units that randomly select data from the total database and send the data to the corresponding sub-database; Sub-database: The number of sub-databases is the same as the number of selection units. They store the company's basic salary calculation method and selected data, and provide training data for the corresponding deep learning processing units.

[0013] Preferably, the storage module comprises: Management unit: classifies data according to the transmission route and adjusts the storage period; Time-limited storage unit: The classified data is stored for a limited time, and the data that exceeds the storage period is automatically deleted to ensure that the time-limited storage unit has enough space for use; Identity verification unit: Verify the identity of staff entering the limited-time storage unit. When data modification is required, multiple managers are required to confirm at the same time to ensure data security and prevent data tampering.

[0014] Preferably, the data comparison module includes: Comparison unit: randomly selects some data from multiple storage modules regularly and compares them; Alarm unit: When different data appear during the comparison process, an alarm is sent to the management staff in the form of a pop-up window.

[0015] Preferably, the control management module includes: Human-computer interaction unit: provides an interactive platform for staff and systems; Login unit: verify the identity information of the login personnel; Centralized control unit: Centralized management of data acquisition module, data processing module, data analysis module and data comparison module Recording unit: records the system's operating procedures and the staff's operating procedures, and sends the records to the data analysis module for storage.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. Multiple sub-databases are established by randomly selecting data from the total database. Then, multiple deep learning processing units each select a sub-database as training data. Then, multiple qualified deep learning processing units analyze and process the same received data. Then, the analysis results of each deep learning processing unit are compared to determine whether there are different analysis results. The same analysis results are then compared with the analysis results of the previous few months to determine whether there are large differences in data, thereby ensuring the accuracy of the data. 2. The same data is stored in each deep learning processing unit. The data comparison module is used to randomly select and compare the same data stored in each deep learning processing unit on a daily basis to ensure the sameness of the data. In addition, the modification of data requires the simultaneous confirmation and consent of multiple different managers to prevent data tampering; 3. Take a screenshot of the analysis results based on employee information, and send it to the corresponding employee's email address based on the employee information in the picture to improve convenience for employees. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural schematic diagram of the salary management system of the present invention; Figure 2 It is a structural schematic diagram of the data acquisition module of the present invention; Figure 3It is a structural schematic diagram of a data processing module of the present invention; Figure 4 It is a structural schematic diagram of the pretreatment unit of the present invention; Figure 5 It is a schematic diagram of the structure of the unit disclosed in the present invention; Figure 6 It is a structural schematic diagram of the data analysis module of the present invention; Figure 7 It is a schematic diagram of the structure of the database of the present invention; Figure 8 It is a structural schematic diagram of the storage module of the present invention; Fig. 9 It is a structural schematic diagram of the data comparison module of the present invention; Fig.10 It is a structural diagram of the control management module of the present invention; Fig.11 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0018] In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0019] Example: Figures 1 to 11 As shown, a salary management system includes: Data acquisition module: acquires the work completed, reimbursement documents and attendance data of each employee within this month; Data processing module: organize the format of the acquired text data, convert the acquired image data into text, and then the staff will check the converted data. After the verification is correct, the data will be sent to the data analysis module; After the data analysis is completed, the verified analysis results will be cut into several pictures according to the employee information, and sent to the corresponding employee mailbox according to the employee information in the pictures; Data analysis module: Analyze and process the received data, check the analysis results, and compare them with the analysis results of the previous few months to ensure the accuracy of the analysis results. Finally, the staff will make a final confirmation of the analysis results and store the received data and analysis results; Data comparison module: randomly selects some data from the same data stored in different locations and compares them to ensure the data is the same. If the data is different during the comparison process, an alert will be sent to multiple managers in the form of a pop-up window; Control management module: provides an interactive platform for staff and the system, centrally manages the data acquisition module, data processing module, data analysis module and data comparison module, verifies the identity information of the login personnel, records the system operation process and the staff's operation process, and sends the records to the data analysis module for storage; The data acquisition module comprises: Work data acquisition unit: obtain the work completion status of each employee within this month; Reimbursement document acquisition unit: obtains the reimbursement documents of each employee within this month; Attendance data acquisition unit: to obtain the attendance status of each employee within this month; The data processing module: Preprocessing unit: converts the format of received data to ensure the consistency of data format, and converts the uploaded image data into text data. Then the staff checks the converted text data. After it is correct, the data is compressed and sent to the data analysis module. Publication unit: organizes the analysis results and employee information into a consent form, takes screenshots of each employee's information and analysis results, and then sends them to the corresponding employee's mailbox based on the employee information in the picture; The pre-processing unit comprises: Format adjustment unit: convert text data in different formats into the same format; Image-text conversion unit: converts image data into text data; Data compression unit: compresses the processed data and sends it to the data analysis module; The publishing unit comprises: Form generation unit: organizes analysis results and employee information into consent forms and adjusts the proportions of the forms; Screenshot unit: screenshot the table according to employee information, and separate the information and analysis results of different employees; Sending unit: sends the employee information in the picture to the corresponding employee mailbox; The data analysis module includes: Database: stores the training data of the deep learning processing unit; Deep learning processing unit: There are multiple groups. The model is trained with data in the database. The PyTorch framework and long short-term memory network are used to analyze and process the data through the trained qualified model to calculate the employee salary. After that, multiple groups of deep learning processing units will compare the analysis results to check whether the analysis results are the same. If they are not the same, they will be recalculated. If the analysis results are the same, they will be compared with the analysis results of the previous few months to check whether the analysis results are significantly different from those of the previous few months. If the error is large, the analysis will be recalculated. If the analysis results are still different or the error is large after multiple recalculations, the analysis will be stopped and wait for the staff to check. Transmission unit: The number of transmission units is the same as that of deep learning processing units, and data is transmitted between each deep learning processing unit; Storage module: the same number as the deep learning processing units, storing the data and analysis results received by the deep learning processing units; The database includes: General database: to store the company's basic salary calculation methods, calculation cases and other types of salary calculation methods and calculation cases obtained from the Internet; Selection unit: There are multiple units that randomly select data from the total database and send the data to the corresponding sub-database; Sub-database: The number of sub-databases is the same as the number of selection units. They store the company's basic salary calculation method and selected data, and provide training data for the corresponding deep learning processing units. The storage module comprises: Management unit: classifies data according to the transmission route and adjusts the storage period; Time-limited storage unit: The classified data is stored for a limited time, and the data that exceeds the storage period is automatically deleted to ensure that the time-limited storage unit has enough space for use; Identity verification unit: Verify the identity of staff entering the time-limited storage unit. When data modification is required, multiple managers need to confirm at the same time to ensure data security and prevent data tampering; The data comparison module includes: Comparison unit: randomly selects some data from multiple storage modules regularly and compares them; Alarm unit: When different data appear during the comparison process, an alarm is sent to the management staff in the form of a pop-up window; The control management module includes: Human-computer interaction unit: provides an interactive platform for staff and systems; Login unit: verify the identity information of the login personnel; Centralized control unit: Centralized management of data acquisition module, data processing module, data analysis module and data comparison module Recording unit: records the system operation process and the staff's operation process, and sends the records to the data analysis module for storage; The main functions achieved by the present invention are: 1. Multiple sub-databases are established by randomly selecting data from the total database. Then, multiple deep learning processing units each select a sub-database as training data. Then, multiple qualified deep learning processing units analyze and process the same received data. Then, the analysis results of each deep learning processing unit are compared to determine whether there are different analysis results. The same analysis results are then compared with the analysis results of the previous few months to determine whether there are large differences in data, thereby ensuring the accuracy of the data. 2. The same data is stored in each deep learning processing unit. The data comparison module is used to randomly select and compare the same data stored in each deep learning processing unit on a daily basis to ensure the sameness of the data. In addition, the modification of data requires the simultaneous confirmation and consent of multiple different managers to prevent data tampering; 3. Take a screenshot of the analysis results based on employee information, and send it to the corresponding employee's email address based on the employee information in the picture to improve convenience for employees.

[0020] Technical personnel in this industry only need to install and operate it according to the accompanying instruction manual, without the need for technical personnel in this field to make creative efforts.

[0021] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A salary management system, characterized in that: include: Data acquisition module: acquires the work completed, reimbursement documents and attendance data of each employee within this month; Data processing module: organize the format of the acquired text data, convert the acquired image data into text, and then the staff will check the converted data. After the verification is correct, the data will be sent to the data analysis module; After the data analysis is completed, the verified analysis results will be cut into several pictures according to the employee information, and sent to the corresponding employee mailbox according to the employee information in the pictures; Data analysis module: Analyze and process the received data, check the analysis results, and compare them with the analysis results of the previous few months to ensure the accuracy of the analysis results. Finally, the staff will make a final confirmation of the analysis results and store the received data and analysis results; Data comparison module: randomly selects some data from the same data stored in different locations and compares them to ensure the data is the same. If the data is different during the comparison process, an alert will be sent to multiple managers in the form of a pop-up window; Control management module: provides an interactive platform for staff and the system, centrally manages the data acquisition module, data processing module, data analysis module and data comparison module, verifies the identity information of the logged-in personnel, records the system's operating procedures and the staff's operating procedures, and sends the records to the data analysis module for storage.

2. A salary management system as claimed in claim 1, characterized in that: The data acquisition module comprises: Work data acquisition unit: obtain the work completion status of each employee within this month; Reimbursement document acquisition unit: obtains the reimbursement documents of each employee within this month; Attendance data acquisition unit: obtain the attendance status of each employee within this month.

3. A salary management system as claimed in claim 1, characterized in that: The data processing module: Preprocessing unit: converts the format of received data to ensure the consistency of data format, and converts the uploaded image data into text data. Then the staff checks the converted text data. After it is correct, the data is compressed and sent to the data analysis module. Publication unit: Organize the analysis results and employee information into the consent form, take screenshots of each employee's information and analysis results, and then send them to the corresponding employee's mailbox based on the employee information in the picture.

4. A salary management system as claimed in claim 3, characterized in that: The pre-processing unit comprises: Format adjustment unit: convert text data in different formats into the same format; Image-text conversion unit: converts image data into text data; Data compression unit: compresses the processed data and sends it to the data analysis module.

5. A salary management system as claimed in claim 3, characterized in that: The publishing unit comprises: Form generation unit: organizes analysis results and employee information into consent forms and adjusts the proportions of the forms; Screenshot unit: screenshot the table according to employee information, and separate the information and analysis results of different employees; Sending unit: sends the information of the employees in the picture to the corresponding employee mailbox.

6. A salary management system as claimed in claim 1, characterized in that: The data analysis module includes: Database: stores the training data of the deep learning processing unit; Deep learning processing unit: There are multiple groups. The model is trained with data in the database. The PyTorch framework and long short-term memory network are used to analyze and process the data through the trained qualified model to calculate the employee salary. After that, multiple groups of deep learning processing units will compare the analysis results to check whether the analysis results are the same. If they are not the same, they will be recalculated. If the analysis results are the same, they will be compared with the analysis results of the previous few months to check whether the analysis results are significantly different from those of the previous few months. If the error is large, the analysis will be recalculated. If the analysis results are still different or the error is large after multiple recalculations, the analysis will be stopped and wait for the staff to check. Transmission unit: The number of transmission units is the same as that of deep learning processing units, and data is transmitted between each deep learning processing unit; Storage module: The number of storage modules is the same as the deep learning processing units, and is used to store the data and analysis results received by the deep learning processing units.

7. A salary management system as claimed in claim 6, characterized in that: The database includes: General database: to store the company's basic salary calculation methods, calculation cases and other types of salary calculation methods and calculation cases obtained from the Internet; Selection unit: There are multiple units that randomly select data from the total database and send the data to the corresponding sub-database; Sub-database: The number of sub-databases is the same as the number of selection units. They store the company's basic salary calculation method and selected data, and provide training data for the corresponding deep learning processing units.

8. A salary management system as claimed in claim 6, characterized in that: The storage module comprises: Management unit: classifies data according to the transmission route and adjusts the storage period; Time-limited storage unit: The classified data is stored for a limited time, and the data that exceeds the storage period is automatically deleted to ensure that the time-limited storage unit has enough space for use; Identity verification unit: Verify the identity of staff entering the limited-time storage unit. When data modification is required, multiple managers are required to confirm at the same time to ensure data security and prevent data tampering.

9. A salary management system as claimed in claim 1, characterized in that: The data comparison module includes: Comparison unit: randomly selects some data from multiple storage modules regularly and compares them; Alarm unit: When different data appear during the comparison process, an alarm is sent to the management staff in the form of a pop-up window.

10. A salary management system as claimed in claim 1, characterized in that: The control management module includes: Human-computer interaction unit: provides an interactive platform for staff and systems; Login unit: verify the identity information of the login personnel; Centralized control unit: Centralized management of data acquisition module, data processing module, data analysis module and data comparison module Recording unit: records the system's operating procedures and the staff's operating procedures, and sends the records to the data analysis module for storage.

Images