Cost budget execution monitoring and analysis method, system and medium
The method and system address the limitations of manual budget monitoring by using predictive models to analyze and alert on budget deviations, ensuring real-time precision and comprehensive understanding of expenditure patterns.
Patent Information
- Application Number
- CN202510392753.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-31
- Publication Date
- 2025-07-15
AI Technical Summary
The traditional budget execution monitoring method relies on manual regular statistical reports, making it difficult to monitor abnormal expenditures in real time, cannot comprehensively analyze budget execution, lack of in-depth exploration of cost structure and departmental correlation, and cannot provide sufficient support for corporate decision-making.
By obtaining the historical budget execution data and daily budget consumption data of various departments of the enterprise, training and optimizing the budget consumption prediction model, comparing it with the budget benchmark data, calculating the budget consumption deviation rate and threshold comparison, and achieving accurate monitoring and intelligent analysis of the cost budget.
Real-time monitoring and intelligent analysis of expense budgets are realized, abnormalities can be detected in a timely manner, accurate budget execution evaluation and early warning, and support corporate decision-making.
Smart Images
Figure CN120317822A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of financial management, and more particularly, to a method, system, and medium for monitoring and analyzing the execution of expense budgets. Background Art
[0002] Traditional methods for monitoring budget execution mainly rely on manual periodic statistical reports. Such methods have many obvious defects. First, they rely on monthly or quarterly manual summaries, making it difficult to monitor abnormal expenditures in real time and unable to detect and handle deviations in the budget execution process promptly. Second, they lack in-depth exploration of aspects such as expense structure and departmental relevance, making it difficult to comprehensively analyze budget execution from multiple perspectives and unable to provide sufficient and powerful support for corporate decision-making.
[0003] In view of the above problems, there is an urgent need for effective technical solutions. Summary of the Invention
[0004] The purpose of the present application is to provide a method, system, and medium for monitoring and analyzing the execution of expense budgets, which can achieve precise monitoring and intelligent analysis of expense budgets by comparing predicted budget consumption data with daily budget consumption benchmark data.
[0005] The present application also provides a method for monitoring and analyzing the execution of expense budgets, including the following steps:
[0006] Obtain the first historical budget execution data and the first daily budget consumption data of each department in the enterprise during the first preset time period;
[0007] Train a preset initial budget consumption prediction model based on the first historical budget execution data and the first daily budget consumption data to obtain a trained optimized budget consumption prediction model;
[0008] Obtain the second historical budget execution data of each department in the enterprise during the second preset time period and input it into the optimized budget consumption prediction model for processing to obtain the first daily budget consumption prediction data corresponding to the department;
[0009] Obtain the budget benchmark data and historical budget benchmark average data of each department in the enterprise for processing to obtain the daily budget consumption benchmark data;
[0010] Process the first daily budget consumption prediction data and the daily budget consumption benchmark data to obtain the daily budget consumption deviation rate;
[0011] Compare the daily budget consumption deviation rate with a preset daily budget consumption deviation rate threshold to obtain the daily consumption status.
[0012] Optionally, in the method for monitoring and analyzing the execution of the cost budget described in this application, the obtaining of the first historical budget execution data and the first daily budget consumption data of each department in the enterprise during the first preset time period includes:
[0013] Obtain the first historical budget execution data and the first daily budget consumption data of each department in the enterprise during the first preset time period;
[0014] The first historical budget execution data includes the actual consumption amount on the first day, the first cumulative consumption ratio, and the first consumption rate.
[0015] Optionally, in the method for monitoring and analyzing the execution of the cost budget described in this application, the obtaining of the second historical budget execution data of each department in the enterprise during the second preset time period and inputting the data into the optimized budget consumption prediction model for processing to obtain the predicted data of the daily budget consumption corresponding to the department includes:
[0016] Obtain the second historical budget execution data of each department in the enterprise during the second preset time period, including the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate;
[0017] Input the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate into the optimized budget consumption prediction model to obtain the predicted data of the daily budget consumption corresponding to the department.
[0018] Optionally, in the method for monitoring and analyzing the execution of the cost budget described in this application, the obtaining of the budget benchmark data and the historical budget benchmark average data of each department in the enterprise for processing to obtain the daily budget consumption benchmark data includes:
[0019] Obtain the budget benchmark data and the historical budget benchmark average data of each department in the enterprise;
[0020] Process according to the budget benchmark data and the historical budget benchmark average data to obtain the budget deviation rate;
[0021] Compare the budget deviation rate with the preset budget deviation rate threshold;
[0022] If the budget deviation rate is less than or equal to the preset budget deviation rate threshold, it is determined that the budget is approved, and the daily budget consumption benchmark data is obtained according to the preset budget decomposition method;
[0023] If the budget deviation rate is greater than the preset budget deviation rate threshold, it is determined that the budget is inaccurate, and the manual confirmation process is activated.
[0024] Optionally, in the method for monitoring and analyzing the execution of the cost budget described in this application, the comparing of the daily budget consumption deviation rate with the preset daily budget consumption deviation rate threshold to obtain the daily consumption status includes:
[0025] Compare the daily budget consumption deviation rate with a preset daily budget consumption deviation rate threshold.
[0026] If the daily budget consumption deviation rate is less than or equal to the preset daily budget consumption deviation rate threshold, determine that the daily consumption status is normal.
[0027] If the daily budget consumption deviation rate is greater than the preset daily budget consumption deviation rate threshold, determine that the daily consumption status is abnormal and output a warning response.
[0028] Optionally, in the method for monitoring and analyzing the execution of cost budget described in this application, it further includes:
[0029] Obtain the average daily consumption data and the actual consumption amount on the third day within a third preset time period, and process them to obtain a daily consumption momentum factor.
[0030] Obtain holiday marking data within a fourth preset time period.
[0031] Obtain the real-time remaining rate of the budget.
[0032] Perform feature fusion processing on the average daily consumption data, daily consumption momentum factor, holiday marking data, and real-time remaining rate of the budget to obtain a multi-dimensional fusion feature vector.
[0033] Input the multi-dimensional fusion feature vector into a preset multi-feature budget consumption prediction model for processing to obtain the predicted second-day budget consumption data corresponding to the department.
[0034] In a second aspect, this application provides a system for monitoring and analyzing the execution of cost budget. The system includes: a memory and a processor. The memory includes a program for a method for monitoring and analyzing the execution of cost budget. When the program for the method for monitoring and analyzing the execution of cost budget is executed by the processor, the following steps are implemented:
[0035] Obtain the first historical budget execution data and the first-day budget consumption data of each department in the enterprise within a first preset time period.
[0036] Train a preset initial budget consumption prediction model based on the first historical budget execution data and the first-day budget consumption data to obtain a trained optimized budget consumption prediction model.
[0037] Obtain the second historical budget execution data of each department in the enterprise within a second preset time period, and input it into the optimized budget consumption prediction model for processing to obtain the predicted first-day budget consumption data corresponding to the department.
[0038] Obtain the budget benchmark data and historical budget benchmark average data of each department in the enterprise for processing to obtain the daily budget consumption benchmark data.
[0039] Process the first-day budget consumption prediction data and the daily budget consumption benchmark data to obtain the daily budget consumption deviation rate;
[0040] Compare the daily budget consumption deviation rate with a preset daily budget consumption deviation rate threshold to obtain the daily consumption status.
[0041] Optionally, in a cost budget execution monitoring and analysis system according to the present application, the obtaining of the first historical budget execution data and the first-day budget consumption data of each department in the enterprise in the first preset time period includes:
[0042] Obtain the first historical budget execution data and the first-day budget consumption data of each department in the enterprise in the first preset time period;
[0043] The first historical budget execution data includes the first-day actual consumption amount, the first cumulative consumption ratio, and the first consumption rate.
[0044] Optionally, in a cost budget execution monitoring and analysis system according to the present application, the obtaining of the second historical budget execution data of each department in the enterprise in the second preset time period and inputting the data into the optimized budget consumption prediction model for processing to obtain the first-day budget consumption prediction data corresponding to the department includes:
[0045] Obtain the second historical budget execution data of each department in the enterprise in the second preset time period, including the second-day actual consumption amount, the second cumulative consumption ratio, and the second consumption rate;
[0046] Input the second-day actual consumption amount, the second cumulative consumption ratio, and the second consumption rate into the optimized budget consumption prediction model to obtain the first-day budget consumption prediction data corresponding to the department.
[0047] In a third aspect, the present application also provides a computer-readable storage medium, in which a program for a cost budget execution monitoring and analysis method is stored. When the program for the cost budget execution monitoring and analysis method is executed by a processor, the steps of a cost budget execution monitoring and analysis method as described in any one of the above are implemented.
[0048] As can be seen from the above, a cost budget execution monitoring and analysis method, system, and medium provided by the present application can achieve precise monitoring and intelligent analysis of cost budgets by comparing budget consumption prediction data and daily budget consumption benchmark data.
[0049] Other features and advantages of the present application will be described in the subsequent specification. Moreover, some of them will become apparent from the specification or can be understood by implementing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures specifically pointed out in the written specification and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative efforts.
[0051] Figure 1 It is a flowchart of a method for monitoring and analyzing the execution of a cost budget provided by an embodiment of the present application;
[0052] Figure 2 It is a flowchart of a method for obtaining the predicted daily budget consumption data corresponding to the department for a method for monitoring and analyzing the execution of a cost budget provided by an embodiment of the present application;
[0053] Figure 3 It is a flowchart of a method for obtaining the daily budget consumption benchmark data for a method for monitoring and analyzing the execution of a cost budget provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all of them. The components of the embodiments of the present application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.
[0055] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, the terms "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.
[0056] Please refer to Figure 1 , Figure 1It is a flowchart of a method for monitoring and analyzing the execution of cost budgets in some embodiments of the present application. This method for monitoring and analyzing the execution of cost budgets is used in terminal devices, such as computers, mobile phone terminals, etc. This method for monitoring and analyzing the execution of cost budgets includes the following steps:
[0057] S11. Obtain the first historical budget execution data and the first daily budget consumption data of each department in the enterprise during the first preset time period;
[0058] S12. Train a preset initial budget consumption prediction model according to the first historical budget execution data and the first daily budget consumption data to obtain a trained optimized budget consumption prediction model;
[0059] S13. Obtain the second historical budget execution data of each department in the enterprise during the second preset time period, and input it into the optimized budget consumption prediction model for processing to obtain the first daily budget consumption prediction data corresponding to the department;
[0060] S14. Process the budget benchmark data and the historical budget benchmark average data of each department in the enterprise to obtain the daily budget consumption benchmark data;
[0061] S15. Process the first daily budget consumption prediction data and the daily budget consumption benchmark data to obtain the daily budget consumption deviation rate;
[0062] S16. Compare the daily budget consumption deviation rate with a preset daily budget consumption deviation rate threshold to obtain the daily consumption status.
[0063] It should be noted that, in order to achieve precise monitoring and intelligent analysis of the budget execution of each department in an enterprise, first, the first historical budget execution data and the first-day budget consumption data of each department in the enterprise during the first preset time period are obtained to train a preset initial budget consumption prediction model, and a trained optimized budget consumption prediction model is obtained. In this embodiment, the first preset time period is the past three years, with 30 days as a historical budget execution data extraction unit. The preset initial budget consumption prediction model is obtained by querying a preset cost budget monitoring platform, which is the information data source for information data acquisition, interaction, and processing during the implementation of this solution. Then, the second historical budget execution data of each department in the enterprise during the second preset time period is obtained and input into the optimized budget consumption prediction model to obtain the first-day budget consumption prediction data corresponding to the department. In this embodiment, the second preset time period is 30 days before the budget monitoring. Then, based on the budget benchmark data and the historical budget benchmark average data of each department in the enterprise, processing is performed to obtain the daily budget consumption benchmark data, which is used as the benchmark for evaluating the budget execution situation and is compared with the first-day budget consumption prediction data to obtain the daily budget consumption deviation rate. The daily budget consumption deviation rate refers to the ratio of the absolute value of the difference between the daily budget consumption benchmark data and the first-day budget consumption prediction data to the daily budget consumption benchmark data. Finally, through threshold comparison, the daily consumption status is determined to represent the budget execution situation of each department.
[0064] According to an embodiment of the present invention, the obtaining of the first historical budget execution data and the first-day budget consumption data of each department in the enterprise during the first preset time period includes:
[0065] Obtaining the first historical budget execution data and the first-day budget consumption data of each department in the enterprise during the first preset time period;
[0066] The first historical budget execution data includes the first-day actual consumption amount, the first cumulative consumption ratio, and the first consumption rate.
[0067] It should be noted that, in order to train the preset initial budget consumption prediction model, first, the first historical budget execution data including the first-day actual consumption amount, the first cumulative consumption ratio, and the first consumption rate is extracted. The first cumulative consumption ratio refers to the ratio of the consumption amount on that day to the total budget, and the first consumption rate is the consumption amount on that day divided by the product of the remaining days and the remaining budget. For example, if the consumption amount on that day is 300 yuan, the remaining days are 30 days, and the remaining budget is 1000 yuan, 300 / (30x1000) = 0.01 is the first consumption rate.
[0068] Please refer to Figure 2 , Figure 2It is a flowchart for obtaining the first-day budget consumption prediction data corresponding to the department of a method for monitoring and analyzing the execution of cost budgets in some embodiments of the present application. According to the embodiments of the present invention, the steps of obtaining the second historical budget execution data of each department in the enterprise during the second preset time period and inputting the data into the optimized budget consumption prediction model for processing to obtain the first-day budget consumption prediction data corresponding to the department include:
[0069] S21. Obtain the second historical budget execution data of each department in the enterprise during the second preset time period, including the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate;
[0070] S22. Input the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate into the optimized budget consumption prediction model to obtain the first-day budget consumption prediction data corresponding to the department.
[0071] It should be noted that, in order to achieve accurate prediction of budget consumption, the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate obtained are input into the optimized budget consumption prediction model to obtain the first-day budget consumption prediction data corresponding to the department, which is used to evaluate whether the current budget consumption is reasonable.
[0072] Please refer to Figure 3 , Figure 3 It is a flowchart for obtaining the daily budget consumption benchmark data of a method for monitoring and analyzing the execution of cost budgets in some embodiments of the present application. According to the embodiments of the present invention, the steps of obtaining the budget benchmark data and the historical budget benchmark average data of each department in the enterprise for processing to obtain the daily budget consumption benchmark data include:
[0073] S31. Obtain the budget benchmark data and the historical budget benchmark average data of each department in the enterprise;
[0074] S32. Process the budget benchmark data and the historical budget benchmark average data to obtain the budget deviation rate;
[0075] S33. Compare the budget deviation rate with the preset budget deviation rate threshold;
[0076] S34. If the budget deviation rate is less than or equal to the preset budget deviation rate threshold, it is determined that the budget is approved, and the daily budget consumption benchmark data is obtained according to the preset budget decomposition method;
[0077] S35. If the budget deviation rate is greater than the preset budget deviation rate threshold, it is determined that the budget is inaccurate, and the manual confirmation process is activated.
[0078] It should be noted that, in order to evaluate whether the budget benchmark data of each department is reasonable, first obtain the budget benchmark data of each department and the historical budget benchmark average data for the same period in history, then compare the two to obtain the budget deviation rate. The budget deviation rate is the ratio of the absolute value of the difference between the budget benchmark data and the historical budget benchmark average data to the historical budget benchmark average data. Finally, through threshold comparison, determine whether there is a problem with the budget. In this embodiment, the preset budget deviation rate threshold is set to 0.25. For example, if the obtained budget deviation rate is 0.2, which is less than the preset budget deviation rate threshold, it is determined that the budget is qualified, and further processing is performed according to the preset budget decomposition method to obtain the daily budget consumption benchmark data. The preset budget decomposition method is equal division or allocation according to the department plan. If the obtained budget deviation rate is 0.3, which is greater than the preset budget deviation rate threshold, indicating a relatively large fluctuation compared to the same period in history, it is determined that the budget is inaccurate, and manual further confirmation and processing are activated.
[0079] According to an embodiment of the present invention, the threshold comparison of the daily budget consumption deviation rate with the preset daily budget consumption deviation rate threshold to obtain the daily consumption status includes:
[0080] Perform threshold comparison of the daily budget consumption deviation rate with the preset daily budget consumption deviation rate threshold;
[0081] If the daily budget consumption deviation rate is less than or equal to the preset daily budget consumption deviation rate threshold, it is determined that the daily consumption status is a normal status;
[0082] If the daily budget consumption deviation rate is greater than the preset daily budget consumption deviation rate threshold, it is determined that the daily consumption status is an abnormal status, and a warning response is output.
[0083] It should be noted that after determining the daily budget consumption benchmark data corresponding to each department, compare the obtained first daily budget consumption prediction data with the daily budget consumption benchmark data to obtain the daily budget consumption deviation rate. The daily budget consumption deviation rate is the ratio of the absolute value of the difference between the first daily budget consumption prediction data and the daily budget consumption benchmark data to the daily budget consumption benchmark data. Perform threshold comparison of the obtained daily budget consumption deviation rate with the preset daily budget consumption deviation rate threshold. In this embodiment, the preset daily budget consumption deviation rate threshold is set to 0.35. For example, if the obtained daily budget consumption deviation rate is 0.2, which is less than the preset daily budget consumption deviation rate threshold, it is determined that the daily consumption status is a normal status. If the obtained daily budget consumption deviation rate is 0.5, which is greater than the preset daily budget consumption deviation rate threshold, indicating that there is a deviation in budget execution, it is determined that the daily consumption status is an abnormal status, and a warning response is output.
[0084] According to an embodiment of the present invention, it further includes:
[0085] Obtain the average daily consumption data and the actual consumption amount on the third day within the third preset time period, and perform processing to obtain the daily consumption momentum factor;
[0086] Obtain the holiday flag data within the fourth preset time period;
[0087] Obtain the real-time budget remaining rate;
[0088] Perform feature fusion processing on the average daily consumption data, daily consumption momentum factor, holiday flag data, and real-time budget remaining rate to obtain a multi-dimensional fusion feature vector;
[0089] Input the multi-dimensional fusion feature vector into a preset multi-feature budget consumption prediction model for processing to obtain the second-day budget consumption prediction data corresponding to the department.
[0090] It should be noted that, in order to achieve a more accurate prediction of the second-day budget consumption prediction data, the average daily consumption data and the daily consumption momentum factor within the third preset time period are obtained. In this embodiment, the third preset time period is 7 days, and the calculation formula for the daily consumption momentum factor is:
[0091]
[0092] where d c is the daily consumption momentum factor, c a , c v are the actual consumption amount on the third day and the average daily consumption data respectively; in order to reduce the impact of holidays on the evaluation of the budget execution situation, the holiday flag data within the fourth preset time period is obtained. In this embodiment, the fourth preset time period is 3 days. If there is a holiday within the next 3 days, it is marked as 1, and if there is no holiday, it is marked as 0. Then, the real-time budget remaining rate is obtained. The real-time budget remaining rate refers to 1 minus the cumulative consumption ratio within the budget period; finally, the average daily consumption data, daily consumption momentum factor, holiday flag data, and real-time budget remaining rate are subjected to feature fusion processing to obtain a multi-dimensional fusion feature vector, and through processing in a preset multi-feature budget consumption prediction model, the second-day budget consumption prediction data corresponding to the department is obtained, where the preset multi-feature budget consumption prediction model is trained by using the multi-dimensional fusion feature vectors of a large number of historical samples and the corresponding daily budget consumption prediction data.
[0093] It is worth mentioning that, according to the embodiment of the present invention, it further includes:
[0094] Compare the first-day budget consumption prediction data and the second-day budget consumption prediction data to obtain the budget consumption prediction deviation rate;
[0095] Compare the budget consumption prediction deviation rate with a preset deviation rate benchmark threshold;
[0096] If it is less than or equal to the preset deviation rate benchmark threshold, the budget consumption forecast data for the second day is excluded;
[0097] If it is greater than the preset deviation rate benchmark threshold, the budget consumption forecast data for the first day is excluded.
[0098] It should be noted that in order to determine the accuracy of the budget consumption forecast data for the first day, relevant data closer to the forecast date is introduced for re-evaluation, and the deviation between the budget consumption forecast data for the first day and the budget consumption forecast data for the second day is analyzed to obtain the budget consumption forecast deviation rate. The budget consumption forecast deviation rate is the ratio of the absolute value of the difference between the budget consumption forecast data for the first day and the budget consumption forecast data for the second day to the budget consumption forecast data for the first day. Finally, a threshold comparison is made. In this embodiment, the preset deviation rate benchmark threshold is set to 0.3. If the obtained budget consumption forecast deviation rate is 0.1, which is less than the preset deviation rate benchmark threshold, the budget consumption forecast data for the second day is excluded, and only the budget consumption forecast data for the first day is retained for comparison with the budget benchmark; if the obtained budget consumption forecast deviation rate is 0.4, which is greater than the preset deviation rate benchmark threshold, it indicates that the prediction deviation of the budget consumption forecast data for the first day is large, so it is excluded, and the budget consumption forecast data for the second day is retained for comparison with the budget benchmark.
[0099] It is worth mentioning that according to the embodiment of the present invention, it further includes:
[0100] Obtain the number of employees, annual budget, and number of projects corresponding to the department, and extract the minimum number of employees, maximum number of employees, minimum annual budget, maximum annual budget, minimum number of projects, and maximum number of projects;
[0101] Perform a weighted summation process according to the number of employees, annual budget, and number of projects in combination with the minimum number of employees, maximum number of employees, minimum annual budget, maximum annual budget, minimum number of projects, and maximum number of projects to obtain the department scale characteristic value;
[0102] Obtain the quarterly type characteristic data;
[0103] Perform processing according to the quarterly type characteristic data and the department scale characteristic value in combination with the multi-dimensional fusion feature vector to obtain an optimized multi-dimensional fusion feature vector.
[0104] It should be noted that in order to further enrich the fusion feature vector, first, the obtained number of employees, annual budget, and number of projects are processed to obtain the department scale characteristic value, and at the same time, a normalization process is performed;
[0105] The calculation formula for the department characteristic value is:
[0106]
[0107] where ds is the characteristic value of department scale, n y , b u , n p are the number of employees, annual budget and number of projects respectively, n i , n x , b i , b x , n pi , n px are the minimum number of employees, maximum number of employees, minimum annual budget, maximum annual budget, minimum number of projects and maximum number of projects respectively. ω1, ω2, ω3 are preset weight values (the preset weight values are obtained by querying through the preset cost budget monitoring platform); then further obtain the quarterly type characteristic data, such as the first quarter is [1, 0, 0, 0]. Finally, fuse the normalized department scale characteristic value and quarterly type characteristic data into the multi-dimensional fusion feature vector for processing to obtain the optimized multi-dimensional fusion feature vector.
[0108] The present invention also discloses a cost budget execution monitoring and analysis system, including a memory and a processor. The memory includes a cost budget execution monitoring and analysis method program. When the cost budget execution monitoring and analysis method program is executed by the processor, the following steps are implemented:
[0109] Obtain the first historical budget execution data and the first daily budget consumption data of each department in the enterprise during the first preset time period;
[0110] Train the preset initial budget consumption prediction model according to the first historical budget execution data and the first daily budget consumption data to obtain a trained optimized budget consumption prediction model;
[0111] Obtain the second historical budget execution data of each department in the enterprise during the second preset time period, and input it into the optimized budget consumption prediction model for processing to obtain the first daily budget consumption prediction data corresponding to the department;
[0112] Obtain the budget benchmark data and historical budget benchmark mean data of each department in the enterprise for processing to obtain the daily budget consumption benchmark data;
[0113] Process the first daily budget consumption prediction data and the daily budget consumption benchmark data to obtain the daily budget consumption deviation rate;
[0114] Compare the daily budget consumption deviation rate with the preset daily budget consumption deviation rate threshold to obtain the daily consumption status.
[0115] It should be noted that, in order to achieve precise monitoring and intelligent analysis of the budget execution of each department in the enterprise, first, the first historical budget execution data and the first-day budget consumption data of each department in the enterprise for the first preset time period are obtained to train the preset initial budget consumption prediction model, and a trained optimized budget consumption prediction model is obtained. In this embodiment, the first preset time period is the past three years, with 30 days as a historical budget execution data extraction unit. The preset initial budget consumption prediction model is obtained by querying the preset expense budget monitoring platform, which is the information data source for information data acquisition, interaction, and processing in the implementation process of this solution. Then, the second historical budget execution data of each department in the enterprise for the second preset time period is obtained and input into the optimized budget consumption prediction model to obtain the first-day budget consumption prediction data corresponding to the department. In this embodiment, the second preset time period is 30 days before the budget monitoring. Then, based on the budget benchmark data and the historical budget benchmark average data of each department in the enterprise, processing is performed to obtain the daily budget consumption benchmark data, which is used as the benchmark for evaluating the budget execution situation and is compared with the first-day budget consumption prediction data to obtain the daily budget consumption deviation rate. The daily budget consumption deviation rate is the ratio of the absolute value of the difference between the daily budget consumption benchmark data and the first-day budget consumption prediction data to the daily budget consumption benchmark data. Finally, through threshold comparison, the daily consumption status is determined to represent the budget execution situation of each department.
[0116] According to an embodiment of the present invention, the obtaining of the first historical budget execution data and the first-day budget consumption data of each department in the enterprise for the first preset time period includes:
[0117] Obtaining the first historical budget execution data and the first-day budget consumption data of each department in the enterprise for the first preset time period;
[0118] The first historical budget execution data includes the first-day actual consumption amount, the first cumulative consumption ratio, and the first consumption rate.
[0119] It should be noted that, in order to train the preset initial budget consumption prediction model, first, the first historical budget execution data including the first-day actual consumption amount, the first cumulative consumption ratio, and the first consumption rate is extracted. The first cumulative consumption ratio is the ratio of the consumption amount on that day to the total budget. The first consumption rate is the consumption amount on that day divided by the product of the remaining days and the remaining budget. For example, if the consumption amount on that day is 300 yuan, the remaining days are 30 days, and the remaining budget is 1000 yuan, 300 / (30x1000) = 0.01 is the first consumption rate.
[0120] According to an embodiment of the present invention, the obtaining of the second historical budget execution data of each department in the enterprise for the second preset time period and inputting the data into the optimized budget consumption prediction model for processing to obtain the first-day budget consumption prediction data corresponding to the department includes:
[0121] Obtain the second historical budget execution data of each department in the enterprise for the second preset time period, including the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate;
[0122] Input the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate into the optimized budget consumption prediction model to obtain the budget consumption prediction data for the first day corresponding to the department.
[0123] It should be noted that, in order to achieve accurate prediction of budget consumption, the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate obtained are input into the optimized budget consumption prediction model to obtain the budget consumption prediction data for the first day corresponding to the department, which is used to evaluate whether the current budget consumption is reasonable.
[0124] According to the embodiments of the present invention, the budget benchmark data and historical budget benchmark mean data of each department in the enterprise are obtained and processed to obtain the daily budget consumption benchmark data, including:
[0125] Obtain the budget benchmark data and historical budget benchmark mean data of each department in the enterprise;
[0126] Process according to the budget benchmark data and historical budget benchmark mean data to obtain the budget deviation rate;
[0127] Compare the budget deviation rate with the preset budget deviation rate threshold;
[0128] If the budget deviation rate is less than or equal to the preset budget deviation rate threshold, it is determined that the budget is approved, and it is processed according to the preset budget decomposition method to obtain the daily budget consumption benchmark data;
[0129] If the budget deviation rate is greater than the preset budget deviation rate threshold, it is determined that the budget is inaccurate, and the manual confirmation process is activated.
[0130] It should be noted that, in order to evaluate whether the budget benchmark data of each department is reasonable, first obtain the budget benchmark data of each department and the historical budget benchmark average data in the same period of history, then compare the two to obtain the budget deviation rate. The budget deviation rate refers to the ratio of the absolute value of the difference between the budget benchmark data and the historical budget benchmark average data to the historical budget benchmark average data. Finally, through threshold comparison, determine whether there is a problem with the budget. In this embodiment, the preset budget deviation rate threshold is set to 0.25. For example, if the obtained budget deviation rate is 0.2, which is less than the preset budget deviation rate threshold, it is determined that the budget is compliant, and further processing is performed according to the preset budget decomposition method to obtain the daily budget consumption benchmark data. The preset budget decomposition method is equal division or allocation according to the department plan. If the obtained budget deviation rate is 0.3, which is greater than the preset budget deviation rate threshold, indicating a relatively large fluctuation compared to the same period of history, it is determined that the budget is inaccurate, and manual further confirmation and processing are activated.
[0131] According to an embodiment of the present invention, the threshold comparison of the daily budget consumption deviation rate with the preset daily budget consumption deviation rate threshold to obtain the daily consumption status includes:
[0132] Performing a threshold comparison of the daily budget consumption deviation rate with the preset daily budget consumption deviation rate threshold;
[0133] If the daily budget consumption deviation rate is less than or equal to the preset daily budget consumption deviation rate threshold, it is determined that the daily consumption status is a normal status;
[0134] If the daily budget consumption deviation rate is greater than the preset daily budget consumption deviation rate threshold, it is determined that the daily consumption status is an abnormal status, and a warning response is output.
[0135] It should be noted that after determining the daily budget consumption benchmark data corresponding to each department, compare the obtained first daily budget consumption prediction data with the daily budget consumption benchmark data to obtain the daily budget consumption deviation rate. The daily budget consumption deviation rate refers to the ratio of the absolute value of the difference between the first daily budget consumption prediction data and the daily budget consumption benchmark data to the daily budget consumption benchmark data. Perform a threshold comparison of the obtained daily budget consumption deviation rate with the preset daily budget consumption deviation rate threshold. In this embodiment, the preset daily budget consumption deviation rate threshold is set to 0.35. For example, if the obtained daily budget consumption deviation rate is 0.2, which is less than the preset daily budget consumption deviation rate threshold, it is determined that the daily consumption status is a normal status. If the obtained daily budget consumption deviation rate is 0.5, which is greater than the preset daily budget consumption deviation rate threshold, indicating that there is a deviation in budget execution, it is determined that the daily consumption status is an abnormal status, and a warning response is output.
[0136] According to an embodiment of the present invention, it further includes:
[0137] Obtain the average daily consumption data and the actual consumption amount on the third day within the third preset time period, and perform processing to obtain the daily consumption momentum factor;
[0138] Obtain the holiday flag data within the fourth preset time period;
[0139] Obtain the real-time budget surplus rate;
[0140] Perform feature fusion processing on the average daily consumption data, the daily consumption momentum factor, the holiday flag data, and the real-time budget surplus rate to obtain a multi-dimensional fusion feature vector;
[0141] Input the multi-dimensional fusion feature vector into a preset multi-feature budget consumption prediction model for processing to obtain the second-day budget consumption prediction data corresponding to the department.
[0142] It should be noted that, in order to achieve a more accurate prediction of the daily budget consumption prediction data, the average daily consumption data and the daily consumption momentum factor within the third preset time period are obtained. In this embodiment, the third preset time period is 7 days, and the calculation formula for the daily consumption momentum factor is:
[0143]
[0144] where d c is the daily consumption momentum factor, and c a , c v are the actual consumption amount on the third day and the average daily consumption data respectively; in order to reduce the impact of holidays on the evaluation of the budget execution situation, the holiday flag data within the fourth preset time period is obtained. In this embodiment, the fourth preset time period is 3 days. If there is a holiday within the next 3 days, it is marked as 1, and if there is no holiday, it is marked as 0. Then, the real-time budget surplus rate is obtained. The real-time budget surplus rate refers to 1 minus the cumulative consumption ratio within the budget period; finally, the average daily consumption data, the daily consumption momentum factor, the holiday flag data, and the real-time budget surplus rate are subjected to feature fusion processing to obtain a multi-dimensional fusion feature vector, and through processing in a preset multi-feature budget consumption prediction model, the second-day budget consumption prediction data corresponding to the department is obtained, where the preset multi-feature budget consumption prediction model is trained by using the multi-dimensional fusion feature vectors of a large number of historical samples and the corresponding daily budget consumption prediction data.
[0145] It is worth mentioning that, according to the embodiment of the present invention, it further includes:
[0146] Compare the first-day budget consumption prediction data and the second-day budget consumption prediction data to obtain the budget consumption prediction deviation rate;
[0147] Compare the budget consumption prediction deviation rate with a preset deviation rate benchmark threshold;
[0148] If it is less than or equal to the preset deviation rate benchmark threshold, the predicted data of the budget consumption on the second day is eliminated;
[0149] If it is greater than the preset deviation rate benchmark threshold, the predicted data of the budget consumption on the first day is eliminated.
[0150] It should be noted that in order to determine the accuracy of the predicted data of the budget consumption on the first day, relevant data closer to the predicted date is introduced for re-evaluation, the deviation between the predicted data of the budget consumption on the first day and the predicted data of the budget consumption on the second day is analyzed, and the predicted deviation rate of the budget consumption is obtained. The predicted deviation rate of the budget consumption refers to the ratio of the absolute value of the difference between the predicted data of the budget consumption on the first day and the predicted data of the budget consumption on the second day to the predicted data of the budget consumption on the first day. Finally, a threshold comparison is carried out. In this embodiment, the preset deviation rate benchmark threshold is set to 0.3. If the obtained predicted deviation rate of the budget consumption is 0.1, which is less than the preset deviation rate benchmark threshold, the predicted data of the budget consumption on the second day is eliminated, and only the predicted data of the budget consumption on the first day is retained for comparison with the budget benchmark; if the obtained predicted deviation rate of the budget consumption is 0.4, which is greater than the preset deviation rate benchmark threshold, it indicates that the prediction deviation of the predicted data of the budget consumption on the first day is large, and it is eliminated, and the predicted data of the budget consumption on the second day is retained for comparison with the budget benchmark.
[0151] It is worth mentioning that according to the embodiment of the present invention, it further includes:
[0152] Obtain the number of employees, annual budget, and number of projects corresponding to the department, and extract the minimum number of employees, maximum number of employees, minimum annual budget, maximum annual budget, minimum number of projects, and maximum number of projects;
[0153] Perform weighted summation processing on the number of employees, annual budget, and number of projects in combination with the minimum number of employees, maximum number of employees, minimum annual budget, maximum annual budget, minimum number of projects, and maximum number of projects to obtain the department scale characteristic value;
[0154] Obtain the quarterly type characteristic data;
[0155] Process the quarterly type characteristic data and the department scale characteristic value in combination with the multi-dimensional fusion feature vector to obtain an optimized multi-dimensional fusion feature vector.
[0156] It should be noted that in order to further enrich the fusion feature vector, first process the obtained number of employees, annual budget, and number of projects to obtain the department scale characteristic value, and at the same time perform normalization processing;
[0157] The calculation formula for the department characteristic value is:
[0158]
[0159] where ds is the eigenvalue of department scale, n y , b u , n p are the number of employees, annual budget and number of projects respectively, n i , n x , b i , b x , n pi , n px are the minimum number of employees, maximum number of employees, minimum annual budget, maximum annual budget, minimum number of projects and maximum number of projects respectively. ω1, ω2, ω3 are preset weight values (the preset weight values are obtained by querying the preset cost budget monitoring platform); then further obtain the quarterly type feature data, such as the first quarter is [1, 0, 0, 0], and finally fuse the normalized department scale feature values and quarterly type feature data into the multi-dimensional fusion feature vector for processing to obtain the optimized multi-dimensional fusion feature vector.
[0160] The third aspect of the present invention provides a readable storage medium, in which a program for a method of monitoring and analyzing the execution of cost budget is stored. When the program for the method of monitoring and analyzing the execution of cost budget is executed by a processor, the steps of a method of monitoring and analyzing the execution of cost budget as described in any one of the above are implemented.
[0161] A method, system and medium for monitoring and analyzing the execution of cost budget disclosed by the present invention realizes the accurate monitoring and intelligent analysis of cost budget by comparing the budget consumption prediction data and the daily budget consumption benchmark data.
[0162] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling or communication connection between the components shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0163] The units described as separate components above may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0164] In addition, each functional unit in the embodiments of the present invention may be entirely integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.
[0165] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks and other various media that can store program codes.
[0166] Alternatively, if the above-mentioned integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks, or optical disks and other various media that can store program codes.
Claims
1. A method for monitoring and analyzing the execution of a cost budget, characterized in that Including the following steps: Obtain the first historical budget execution data and the first-day budget consumption data of each department in the enterprise during the first preset time period; Train a preset initial budget consumption prediction model according to the first historical budget execution data and the first-day budget consumption data to obtain a trained optimized budget consumption prediction model; Obtain the second historical budget execution data of each department in the enterprise during the second preset time period, and input it into the optimized budget consumption prediction model for processing to obtain the first-day budget consumption prediction data corresponding to the department; Obtain the budget benchmark data and the historical budget benchmark average data of each department in the enterprise for processing to obtain the daily budget consumption benchmark data; Process according to the first-day budget consumption prediction data and the daily budget consumption benchmark data to obtain the daily budget consumption deviation rate; Compare the daily budget consumption deviation rate with a preset daily budget consumption deviation rate threshold to obtain the daily consumption status.
2. The cost budget execution monitoring and analysis method according to claim 1, wherein The obtaining of the first historical budget execution data and the first-day budget consumption data of each department in the enterprise during the first preset time period includes: Obtain the first historical budget execution data and the first-day budget consumption data of each department in the enterprise during the first preset time period; The first historical budget execution data includes the actual consumption amount on the first day, the first cumulative consumption ratio, and the first consumption rate.
3. The cost budget execution monitoring and analysis method according to claim 2, characterized in that The obtaining of the second historical budget execution data of each department in the enterprise during the second preset time period and inputting it into the optimized budget consumption prediction model for processing to obtain the first-day budget consumption prediction data corresponding to the department includes: Obtain the second historical budget execution data of each department in the enterprise during the second preset time period, including the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate; Input the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate into the optimized budget consumption prediction model to obtain the first-day budget consumption prediction data corresponding to the department.
4. The cost budget execution monitoring and analysis method according to claim 3, wherein The obtaining of the budget benchmark data and the historical budget benchmark average data of each department in the enterprise for processing to obtain the daily budget consumption benchmark data includes: Obtain the budget benchmark data and the historical budget benchmark average data of each department in the enterprise; Process according to the budget benchmark data and the historical budget benchmark average data to obtain the budget deviation rate; Compare the budget deviation rate with a preset budget deviation rate threshold; If the budget deviation rate is less than or equal to the preset budget deviation rate threshold, it is determined that the budget is approved, and it is processed according to the preset budget decomposition method to obtain the daily budget consumption benchmark data; If the budget deviation rate is greater than the preset budget deviation rate threshold, it is determined that the budget is inaccurate, and the manual confirmation process is activated.
5. The cost budget execution monitoring and analysis method according to claim 4, wherein The comparing of the daily budget consumption deviation rate with a preset daily budget consumption deviation rate threshold to obtain the daily consumption status includes: Compare the daily budget consumption deviation rate with a preset daily budget consumption deviation rate threshold; If the daily budget consumption deviation rate is less than or equal to the preset daily budget consumption deviation rate threshold, it is determined that the daily consumption status is normal; If the daily budget consumption deviation rate is greater than the preset daily budget consumption deviation rate threshold, it is determined that the daily consumption status is abnormal, and a warning response is output.
6. The cost budget execution monitoring and analysis method according to claim 5, wherein It also includes: Obtain the average daily consumption data and the actual consumption amount on the third day within the third preset time period, and process them to obtain the daily consumption momentum factor; Obtain the holiday marking data within the fourth preset time period; Obtain the real-time remaining budget rate; Perform feature fusion processing on the average daily consumption data, daily consumption momentum factor, holiday marking data, and real-time remaining budget rate to obtain a multi-dimensional fusion feature vector; Input the multi-dimensional fusion feature vector into a preset multi-feature budget consumption prediction model for processing to obtain the predicted second-day budget consumption data corresponding to the department.
7. A cost budget execution monitoring and analysis system, characterized in that, It includes a memory and a processor. The memory includes a program for the expense budget execution monitoring and analysis method. When the program for the expense budget execution monitoring and analysis method is executed by the processor, the following steps are implemented: Obtain the first historical budget execution data and the first-day budget consumption data of each department in the enterprise within the first preset time period; Train a preset initial budget consumption prediction model according to the first historical budget execution data and the first-day budget consumption data to obtain a trained optimized budget consumption prediction model; Obtain the second historical budget execution data of each department in the enterprise within the second preset time period, and input it into the optimized budget consumption prediction model for processing to obtain the predicted first-day budget consumption data corresponding to the department; Obtain the budget benchmark data and the historical budget benchmark average data of each department in the enterprise for processing to obtain the daily budget consumption benchmark data; Process the predicted first-day budget consumption data and the daily budget consumption benchmark data to obtain the daily budget consumption deviation rate; Compare the daily budget consumption deviation rate with a preset daily budget consumption deviation rate threshold to obtain the daily consumption status.
8. The cost budget execution monitoring and analysis system according to claim 7, wherein The obtaining of the first historical budget execution data and the first-day budget consumption data of each department in the enterprise within the first preset time period includes: Obtain the first historical budget execution data and the first-day budget consumption data of each department in the enterprise within the first preset time period; The first historical budget execution data includes the actual consumption amount on the first day, the first cumulative consumption ratio, and the first consumption rate.
9. The cost budget execution monitoring and analysis system according to claim 8, wherein The obtaining of the second historical budget execution data of each department in the enterprise within the second preset time period and inputting it into the optimized budget consumption prediction model for processing to obtain the predicted first-day budget consumption data corresponding to the department includes: Obtain the second historical budget execution data of each department in the enterprise within the second preset time period, including the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate; Input the actual consumption amount on the second day, the second cumulative consumption ratio, and the second consumption rate into the optimized budget consumption prediction model to obtain the predicted first-day budget consumption data corresponding to the department.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for the expense budget execution monitoring and analysis method. When the program for the expense budget execution monitoring and analysis method is executed by the processor, the steps of an expense budget execution monitoring and analysis method as described in any one of claims 1 to 6 are implemented.