Intelligent financial management system and method based on machine learning

Abstract

The invention relates to the field of data processing, in particular to an intelligent financial management system and method based on machine learning, and is used for solving the problems that an existing intelligent financial management system cannot analyze all financial data, cannot analyze financial accounting personnel, cannot perform intelligent matching, and cannot analyze financial accounting personnel. The problems that financial accounting is low in efficiency and high in error rate, and adverse effects are easily caused to the operation condition of a company are solved. The intelligent financial management system comprises a database, a data management module, a data distribution module, a personnel distribution module and a financial management platform. According to the intelligent financial management system, financial data needing to be processed urgently can be screened out, then accounting personnel with excellent comprehensive conditions are screened out for accounting the financial data, the high efficiency of financial data processing can be guaranteed, the processing accuracy of complex and urgent financial data is guaranteed, accounting errors of the financial data are avoided, and the financial data processing efficiency is improved. And adverse effects on the operation condition of a company are avoided.

Description

Technical Field

[0001] This invention relates to the field of data processing, and more specifically to an intelligent financial management system and method based on machine learning. Background Technology

[0002] With the rapid development of technology and the increasing demands for financial informatization, enterprises, especially large enterprise groups, have increasingly higher requirements for the integration of business and financial data. Financial systems have experienced rapid development and application, greatly alleviating the workload of financial personnel, improving work efficiency, and reducing errors in financial work. Patent application number CN201911046867.X discloses an intelligent financial management system. A high-speed document scanner is fixed to the center of the edge of a positioning plate, and a data entry terminal is electrically connected to the high-speed document scanner. A QR code recognition module is built into the high-speed document scanner, and a QR code generation module is built into the financial data generation terminal. The QR code generation module generates a QR code from the financial data in a unified table. When the QR code on the table is entered using the high-speed document scanner, the QR code recognition module effectively recognizes the QR code on the table. By recognizing the data carried in the QR code, it compares it with the QR code information in the information comparison module, and stores the table captured by the high-speed document scanner into the corresponding information storage module. The financial management terminal is electrically connected to both the information storage module and the information viewing module. When entering financial archive information, the storage location of financial information and the financial data converted from QR codes are effectively checked to avoid errors in the storage location and conversion of financial data. However, the following shortcomings still exist: it is not possible to analyze all financial data or financial accounting personnel, and it is not possible to match intelligently, resulting in low efficiency and high error rate in financial accounting, which can easily have an adverse impact on the company's operation. Summary of the Invention

[0003] To overcome the aforementioned technical problems, the present invention aims to provide an intelligent financial management system and method based on machine learning: The administrator uploads the financial data to be processed to a database for storage, and sequentially marks all financial data as data to be processed. By acquiring the data parameters of the data to be processed, including storage time value and capacity value, the data allocation module obtains the data value based on the data parameters and allocates data accordingly. Upon receiving personnel analysis instructions, the personnel allocation module acquires information on all accounting personnel in the accounting group and obtains the optimal allocation parameters for the accounting personnel, including work value, accounting value, and allocation value. The financial management platform obtains the optimal allocation coefficient based on the optimal allocation parameters and assigns personnel based on the optimal allocation coefficient. The personnel allocation module then allocates the data to the assigned personnel. After allocation, the allocation data and personnel are re-acquired and reassigned until all allocation data is completed. This solves the problem that existing intelligent financial management systems cannot analyze all financial data or financial accounting personnel, and cannot intelligently match data, resulting in low efficiency and high error rates in financial accounting, which can adversely affect the company's operations.

[0004] The objective of this invention can be achieved through the following technical solutions: An intelligent financial management system based on machine learning, comprising: The database is used by administrators to upload and store financial data that needs to be processed, and to mark all financial data as pending data in sequence. The data management module is used to obtain the data parameters of the data to be processed i and send the data parameters to the data allocation module; the data parameters include the storage time value CS and the capacity value SR. The data allocation module is used to obtain the data value SJ based on the data parameters, obtain the allocation data based on the data value SJ, and send the allocation data to the financial management platform. The personnel allocation module is used to obtain information on all accounting personnel in the accounting group after receiving personnel analysis instructions, obtain the optimal allocation parameters of the accounting personnel based on the accounting personnel information, and send the optimal allocation parameters to the financial management platform. The optimal allocation parameters include the work value GZ, the accounting value HS, and the allocation value FP. It is also used to allocate the allocation data to the assigned personnel. After the allocation is completed, the allocation data is obtained again and the personnel are reassigned until all allocation data is allocated. The financial management platform is used to obtain the optimal allocation coefficient YP based on the optimal allocation parameters, and to obtain the personnel to be allocated based on the optimal allocation coefficient YP. The allocation data and the personnel to be allocated are then sent to the personnel allocation module.

[0005] As a further aspect of the present invention, the specific process by which the data management module acquires data parameters is as follows: Get the storage time and the current time of the data to be processed i, get the time difference between the two and mark it as the storage time value CS; Obtain the data capacity of the data to be processed i and mark it as the capacity value SR; Send the storage time value CS and the capacity value SR to the data distribution module.

[0006] As a further aspect of the present invention, the specific process by which the data allocation module obtains the data value SJ is as follows: Substitute the storage time value CS and the capacity value SR into the formula. The data value SJ is obtained, where s1 and s2 are the preset proportional coefficients of the storage time value CS and the data capacity value SR, respectively, and s1+s2=1, 0<s1<s2<1, and s1=0.44 and s2=0.56 are taken. Sort the data to be processed i in descending order of data value SJ, mark the data i at the top as the allocated data, and send the allocated data to the financial management platform.

[0007] As a further aspect of the present invention, the specific process by which the personnel allocation module obtains the optimal allocation parameters is as follows: Upon receiving the personnel analysis instruction, retrieve information on all accounting personnel in the accounting group; Based on the personnel information, obtain the personnel's start date and start time. Calculate the time difference between the start date and the current time and label it as the "job time value ZS". Calculate the time difference between the start time and the current time and label it as the "work time value HS". Substitute the job time value ZS and the work time value HS into the formula. The working value GZ is obtained from the above, where g1 and g2 are the preset proportional coefficients of the working time value ZS and the working time value HS, respectively, and g1+g2=1, 0<g1<g2<1, and g1=0.45 and g2=0.55 are taken. Based on the personnel information, obtain the total number of times each person processed the pending data i and label it as the number of processing times (HC). Also, obtain the total number of times errors occurred in the results of processing the pending data i and label it as the error value (HW). Substitute the number of processing times (HC) and the error value (HW) into the formula. The calculated value HS is obtained from the calculation, where h1 and h2 are the preset proportional coefficients of the number of times the calculation is performed (HC) and the error value (HW) respectively, and h1 + h2 = 1, 0 < h1 < h2 < 1. We take h1 = 0.31 and h2 = 0.69. Based on the information of the accounting personnel, obtain the quantity and size of the data allocated under each accounting personnel's name, and label them as allocation value PE and allocation capacity value PR. Substitute the allocation value PE and allocation capacity value PR into the formula. The allocation value FP is obtained, where f1 and f2 are the preset proportional coefficients of the allocation value PE and the capacity value PR, respectively, and f1+f2=1, 0<f2<f1<1, and f1=0.58 and f2=0.42 are taken. Send the work value GZ, accounting value HS, and allocation value FP to the financial management platform.

[0008] As a further aspect of the present invention, the specific process by which the financial management platform obtains the optimal matching coefficient YP is as follows: Substitute the working value GZ, the accounting value HS, and the allocation value FP into the formula. The optimal allocation coefficient YP is obtained, where β is the error adjustment factor, β=0.925, π is a mathematical constant, p1, p2 and p3 are the preset weight coefficients of working value GZ, accounting value HS and allocation value FP respectively, and p3>p2>p1>1.54, p1=1.79, p2=2.13 and p3=2.80 are taken; Sort the data i to be processed by the accounting personnel in descending order of the allocation coefficient YP, mark the accounting personnel at the top as the allocation personnel, and send the allocation data and allocation personnel to the personnel allocation module.

[0009] As a further aspect of the present invention: the personnel allocation module includes an accounting group and a review group. The accounting group is used to calculate the data to be processed i, and the review group is used to review the data to be processed i after the accounting group has calculated it.

[0010] As a further aspect of the present invention: an intelligent financial management method based on machine learning, comprising the following steps: Step Q1: The administrator uploads the financial data to be processed to the database for storage, and marks all the financial data as data to be processed i, i=1, ..., n, where n is a natural number; Step Q2: The data management module obtains the storage time of the data to be processed i and the current time, obtains the time difference between the two and marks it as the storage time value CS; Step Q3: The data management module obtains the data capacity of the data to be processed i and marks it as the capacity value SR; Step Q4: The data management module sends the storage time value CS and the data capacity value SR to the data allocation module; Step Q5: The data allocation module substitutes the storage time value CS and the capacity value SR into the formula. The data value SJ is obtained, where s1 and s2 are the preset proportional coefficients of the storage time value CS and the data capacity value SR, respectively, and s1+s2=1, 0<s1<s2<1, and s1=0.44 and s2=0.56 are taken. Step Q6: The data allocation module sorts the data to be processed i in descending order of data value SJ, marks the data i at the top as the allocated data, and sends the allocated data to the financial management platform. Step Q7: After receiving the allocation data, the financial management platform generates personnel analysis instructions and sends the personnel analysis instructions to the personnel allocation module; Step Q8: After receiving the personnel analysis instruction, the personnel allocation module obtains information on all accounting personnel in the accounting group; Step Q9: The personnel allocation module obtains the onboarding time and entry time of each accounting staff member based on the accounting staff information. It then calculates the time difference between the onboarding time and the current time and marks it as the onboarding time value ZS. It also calculates the time difference between the entry time and the current time and marks it as the entry time value HS. Finally, it substitutes the onboarding time value ZS and the entry time value HS into the formula. The working value GZ is obtained from the above, where g1 and g2 are the preset proportional coefficients of the working time value ZS and the working time value HS, respectively, and g1+g2=1, 0<g1<g2<1, and g1=0.45 and g2=0.55 are taken. Step Q10: The personnel allocation module obtains the total number of times each person calculates the pending data i based on the personnel information and marks it as the calculation count value HC. It also obtains the total number of times errors occurred in the results of each person's calculation of the pending data i and marks it as the error value HW. The calculation count value HC and the error value HW are then substituted into the formula. The calculated value HS is obtained from the calculation, where h1 and h2 are the preset proportional coefficients of the number of times the calculation is performed (HC) and the error value (HW) respectively, and h1 + h2 = 1, 0 < h1 < h2 < 1. We take h1 = 0.31 and h2 = 0.69. Step Q11: The personnel allocation module obtains the quantity and size of the data allocated under each accountant's name based on the accountant information, and marks them as allocation value PE and allocation capacity value PR. The allocation value PE and allocation capacity value PR are then substituted into the formula. The allocation value FP is obtained, where f1 and f2 are the preset proportional coefficients of the allocation value PE and the capacity value PR, respectively, and f1+f2=1, 0<f2<f1<1, and f1=0.58 and f2=0.42 are taken. Step Q12: The personnel allocation module sends the work value GZ, accounting value HS, and allocation value FP to the financial management platform; Step Q13: The financial management platform substitutes the work value GZ, accounting value HS, and allocation value FP into the formula. The optimal allocation coefficient YP is obtained, where β is the error adjustment factor, β=0.925, π is a mathematical constant, p1, p2 and p3 are the preset weight coefficients of working value GZ, accounting value HS and allocation value FP respectively, and p3>p2>p1>1.54, p1=1.79, p2=2.13 and p3=2.80 are taken; Step Q14: The financial management platform sorts the data to be processed i according to the allocation coefficient YP from largest to smallest, marks the accounting personnel at the top as the allocation personnel, and sends the allocation data and allocation personnel to the personnel allocation module; Step Q15: The personnel allocation module assigns the allocation data to the assigned personnel. After the allocation is completed, it retrieves the allocation data again and assigns personnel again until all allocation data is completed.

[0011] The beneficial effects of this invention are: This invention discloses an intelligent financial management system and method based on machine learning. The administrator uploads the financial data to be processed to a database for storage, and sequentially marks all financial data as pending data. By acquiring data parameters of the pending data, including storage time and capacity values, the data allocation module obtains data values ​​based on these parameters and assigns allocation data accordingly. Upon receiving personnel analysis instructions, the personnel allocation module acquires information on all accounting personnel in the accounting group and obtains optimal allocation parameters for each personnel, including workload, accounting value, and allocation value. The financial management platform obtains an optimal allocation coefficient based on these parameters and assigns personnel accordingly. The personnel allocation module then assigns the allocated data to the assigned personnel. After allocation, the system re-acquires allocation data and re-assigns personnel until all allocation data is completed. This intelligent financial management system first acquires… The system obtains data parameters, and the data values ​​obtained from these parameters are used to comprehensively measure the priority of processing the data to be processed. The larger the data value, the higher the priority it needs to be processed. Then, the allocation data is obtained based on the data values. After that, the information of the accounting personnel is analyzed to obtain the optimal allocation parameters. The optimal allocation coefficient obtained from the optimal allocation parameters can comprehensively measure the priority of the accounting personnel allocation. The larger the optimal allocation coefficient, the higher the priority allocation. Finally, the allocated data is assigned to the assigned personnel, who are then instructed to perform the accounting. Afterwards, the audit team reviews the allocated data that has been calculated. This intelligent financial management system can filter out the financial data that urgently needs to be processed, and then select accounting personnel with excellent overall performance to perform the accounting. This ensures the efficiency of financial data processing and the accuracy of processing complex and urgent financial data, avoiding accounting errors and preventing adverse effects on the company's operations. Attached Figure Description

[0012] Figure 1 This is a block diagram illustrating the principle of an intelligent financial management system based on machine learning, as described in this invention. Detailed Implementation

[0013] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0014] Example 1: Please see Figure 1 As shown, this embodiment is an intelligent financial management system based on machine learning, including the following modules: database, data management module, data allocation module, personnel allocation module, and financial management platform; The database is used by administrators to upload financial data that needs to be processed for storage, and to mark all financial data as pending data in sequence. The data management module is used to acquire the data parameters of the data to be processed i and send the data parameters to the data allocation module; the data parameters include the storage time value CS and the capacity value SR. The data allocation module is used to obtain the data value SJ according to the data parameters, obtain the allocation data according to the data value SJ, and send the allocation data to the financial management platform. The personnel allocation module is used to obtain information on all accounting personnel in the accounting group after receiving the personnel analysis instruction, obtain the optimal allocation parameters of the accounting personnel based on the accounting personnel information, and send the optimal allocation parameters to the financial management platform. The optimal allocation parameters include the work value GZ, the accounting value HS, and the allocation value FP. It is also used to allocate the allocation data to the names of the allocated personnel. After the allocation is completed, the allocation data is obtained again and the personnel are reassigned until all the allocation data is allocated. The financial management platform is used to obtain the optimal allocation coefficient YP based on the optimal allocation parameters, obtain the allocated personnel based on the optimal allocation coefficient YP, and send the allocation data and allocated personnel to the personnel allocation module.

[0015] Example 2: Please see Figure 1 As shown, this embodiment is an intelligent financial management method based on machine learning, including the following steps: Step Q1: The administrator uploads the financial data to be processed to the database for storage, and marks all the financial data as data to be processed i, i=1, ..., n, where n is a natural number; Step Q2: The data management module obtains the storage time of the data to be processed i and the current time, obtains the time difference between the two and marks it as the storage time value CS; Step Q3: The data management module obtains the data capacity of the data to be processed i and marks it as the capacity value SR; Step Q4: The data management module sends the storage time value CS and the data capacity value SR to the data allocation module; Step Q5: The data allocation module substitutes the storage time value CS and the capacity value SR into the formula. The data value SJ is obtained, where s1 and s2 are the preset proportional coefficients of the storage time value CS and the data capacity value SR, respectively, and s1+s2=1, 0<s1<s2<1, and s1=0.44 and s2=0.56 are taken. Step Q6: The data allocation module sorts the data to be processed i in descending order of data value SJ, marks the data i at the top as the allocated data, and sends the allocated data to the financial management platform. Step Q7: After receiving the allocation data, the financial management platform generates personnel analysis instructions and sends the personnel analysis instructions to the personnel allocation module; Step Q8: After receiving the personnel analysis instruction, the personnel allocation module obtains information on all accounting personnel in the accounting group; Step Q9: The personnel allocation module obtains the onboarding time and entry time of each accounting staff member based on the accounting staff information. It then calculates the time difference between the onboarding time and the current time and marks it as the onboarding time value ZS. It also calculates the time difference between the entry time and the current time and marks it as the entry time value HS. Finally, it substitutes the onboarding time value ZS and the entry time value HS into the formula. The working value GZ is obtained from the above, where g1 and g2 are the preset proportional coefficients of the working time value ZS and the working time value HS, respectively, and g1+g2=1, 0<g1<g2<1, and g1=0.45 and g2=0.55 are taken. Step Q10: The personnel allocation module obtains the total number of times each person calculates the pending data i based on the personnel information and marks it as the calculation count value HC. It also obtains the total number of times errors occurred in the results of each person's calculation of the pending data i and marks it as the error value HW. The calculation count value HC and the error value HW are then substituted into the formula. The calculated value HS is obtained from the calculation, where h1 and h2 are the preset proportional coefficients of the number of times the calculation is performed (HC) and the error value (HW) respectively, and h1 + h2 = 1, 0 < h1 < h2 < 1. We take h1 = 0.31 and h2 = 0.69. Step Q11: The personnel allocation module obtains the quantity and size of the data allocated under each accountant's name based on the accountant information, and marks them as allocation value PE and allocation capacity value PR. The allocation value PE and allocation capacity value PR are then substituted into the formula. The allocation value FP is obtained, where f1 and f2 are the preset proportional coefficients of the allocation value PE and the capacity value PR, respectively, and f1+f2=1, 0<f2<f1<1, and f1=0.58 and f2=0.42 are taken. Step Q12: The personnel allocation module sends the work value GZ, accounting value HS, and allocation value FP to the financial management platform; Step Q13: The financial management platform substitutes the work value GZ, accounting value HS, and allocation value FP into the formula. The optimal allocation coefficient YP is obtained, where β is the error adjustment factor, β=0.925, π is a mathematical constant, p1, p2 and p3 are the preset weight coefficients of working value GZ, accounting value HS and allocation value FP respectively, and p3>p2>p1>1.54, p1=1.79, p2=2.13 and p3=2.80 are taken; Step Q14: The financial management platform sorts the data to be processed i according to the allocation coefficient YP from largest to smallest, marks the accounting personnel at the top as the allocation personnel, and sends the allocation data and allocation personnel to the personnel allocation module; Step Q15: The personnel allocation module assigns the allocation data to the assigned personnel. After the allocation is completed, it retrieves the allocation data again and assigns personnel again until all allocation data is completed.

[0016] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0017] The above description is merely an example and illustration of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the invention or exceed the scope defined in the claims, they should all fall within the protection scope of the present invention.

Claims

1. An intelligent financial management system based on machine learning, characterized in that, include: The database is used by administrators to upload and store financial data that needs to be processed, and to mark all financial data as pending data in sequence. The data management module is used to obtain the data parameters of the data to be processed and send the data parameters to the data allocation module; the data parameters include storage time value and data capacity value. The data allocation module is used to obtain data values ​​based on data parameters, obtain allocation data based on data values, and send the allocation data to the financial management platform. The personnel allocation module receives a personnel analysis command, retrieves information on all accounting personnel in the accounting group, obtains optimal allocation parameters for each personnel based on this information, and sends these parameters to the financial management platform. The optimal allocation parameters include work value, accounting value, and allocation value. The module also allocates data to assigned personnel, and after allocation, re-acquires allocation data and re-assigns personnel until all allocation data is completed. The specific process by which the personnel allocation module obtains optimal allocation parameters is as follows: Upon receiving the personnel analysis instruction, retrieve information on all accounting personnel in the accounting group; Based on the personnel information, obtain the personnel's start date and start date, obtain the time difference between the start date and the current time and mark it as the job time value, obtain the time difference between the start date and the current time and mark it as the work time value, and analyze the job time value and work time value to obtain the work value; Based on the information of the accounting personnel, obtain the total number of times the accounting personnel calculate the data to be processed and mark it as the number of times the data to be processed is calculated. Obtain the total number of times the results of the accounting personnel's calculation of the data to be processed are incorrect and mark it as the error value. Analyze the number of times the data calculates the data and the error value to obtain the accounting value. Based on the information of the accounting personnel, obtain the quantity and size of the data allocated under the name of the accounting personnel, and mark them as allocation value and capacity value. The allocation value is obtained by analyzing the allocation value and capacity value. Send the work value, accounting value, and allocation value to the financial management platform; The financial management platform is used to obtain the allocation coefficient based on the allocation parameters, and to allocate personnel based on the allocation coefficient. The allocation data and the allocated personnel are then sent to the personnel allocation module.

2. The intelligent financial management system based on machine learning according to claim 1, characterized in that, The specific process by which the data management module obtains data parameters is as follows: Obtain the storage time and current time of the data to be processed, obtain the time difference between the two and mark it as the storage time value; Obtain the data capacity of the data to be processed and mark it as the capacity value; Send the storage time value and the data capacity value to the data distribution module.

3. The intelligent financial management system based on machine learning according to claim 1, characterized in that, The specific process by which the data allocation module obtains data values ​​is as follows: The data value is obtained by analyzing the storage time value and the number capacity value; The data to be processed is sorted in descending order of data value. The data at the top is marked as the allocated data and then sent to the financial management platform.

4. The intelligent financial management system based on machine learning according to claim 1, characterized in that, The specific process by which the financial management platform obtains the optimal matching coefficient is as follows: The optimal allocation coefficient is obtained by analyzing the working value, the accounting value, and the allocation value. The accounting personnel are sorted according to the allocation coefficient from largest to smallest. The accounting personnel at the top are marked as the allocation personnel, and the allocation data and allocation personnel are sent to the personnel allocation module.

5. The intelligent financial management system based on machine learning according to claim 1, characterized in that, The personnel allocation module includes an accounting group and a review group. The accounting group is used to calculate the data to be processed, and the review group is used to review the data to be processed after the accounting group has calculated it.

6. An intelligent financial management method based on machine learning, characterized in that, Includes the following steps: Step Q1: The administrator uploads the financial data that needs to be processed to the database for storage, and marks all the financial data as pending data in sequence; Step Q2: The data management module obtains the storage time and the current time of the data to be processed, obtains the time difference between the two and marks it as the storage time value; Step Q3: The data management module obtains the data size of the data to be processed and marks it as the data capacity value; Step Q4: The data management module sends the storage time value and data capacity value to the data allocation module; Step Q5: The data allocation module analyzes the stored time value and the data capacity value to obtain the data value; Step Q6: The data allocation module sorts the data to be processed in descending order of data value, marks the data at the top as the allocated data, and sends the allocated data to the financial management platform; Step Q7: After receiving the allocation data, the financial management platform generates personnel analysis instructions and sends the personnel analysis instructions to the personnel allocation module; Step Q8: After receiving the personnel analysis instruction, the personnel allocation module obtains information on all accounting personnel in the accounting group; Step Q9: The personnel allocation module obtains the onboarding time and entry time of the accounting personnel based on the accounting personnel information, obtains the time difference between the onboarding time and the current time and marks it as the job time value, obtains the time difference between the entry time and the current time and marks it as the entry time value, and analyzes the job time value and the entry time value to obtain the work value; Step Q10: The personnel allocation module obtains the total number of times the personnel calculate the pending data based on the personnel information and marks it as the number of times the personnel calculate the pending data. It also obtains the total number of times the results of the personnel's calculation of the pending data have errors and marks them as the error values. The number of times the personnel calculate the pending data and the error values ​​are analyzed to obtain the calculation value. Step Q11: The personnel allocation module obtains the quantity and size of the data allocated under the name of the accounting personnel based on the accounting personnel information, and marks them as allocation value and capacity value. The allocation value and capacity value are analyzed to obtain the allocation value. Step Q12: The personnel allocation module sends the work value, accounting value, and allocation value to the financial management platform; Step Q13: The financial management platform analyzes the work value, accounting value, and allocation value to obtain the optimal allocation coefficient; Step Q14: The financial management platform sorts the data to be processed by the accounting personnel in descending order of their allocation coefficients, marks the accounting personnel at the top as the allocation personnel, and sends the allocation data and allocation personnel to the personnel allocation module. Step Q15: The personnel allocation module assigns the allocation data to the assigned personnel. After the allocation is completed, it retrieves the allocation data again and assigns personnel again until all allocation data is completed.

Images