Management accounting system based on financial data and decision making method

Abstract

The invention relates to the technical field of operation accounting, and discloses an operation accounting system and a decision making method based on financial data, and the operation accounting system comprises a data acquisition module, an accounting processing module, a prediction generation module, a monitoring verification module and a decision adjustment module. The decision making method corresponds to the operation accounting system. According to the application, the data acquisition module is used for capturing the operation accounting demand in real time, and the whole-process closed-loop management of the operation accounting is realized in combination with the dynamic strategy matching of the accounting processing module, the cross-time prediction of the prediction generation module, the confidence evaluation of the monitoring verification module and the strategy iteration mechanism of the decision adjustment module; the dynamic accuracy of an accounting result is ensured through bidirectional verification of a response data set, a prediction data set and a real data set, when the average relative error of the prediction data set and the real data set exceeds a threshold value, strategy adjustment is automatically triggered, accounting model parameters are corrected, the enterprise decision response speed is increased, and the accounting error rate is reduced.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of business accounting, and particularly relates to a business accounting system based on financial data and a decision-making method. BACKGROUND

[0002] In enterprise management, business accounting and scientific decision-making in the process are crucial. Traditional business accounting methods often rely on simple financial data statistics and analysis, lack systematic and dynamic decision-making, and are difficult to accurately respond to complex and changing market environments based on decision-making, resulting in unreliable accounting results.

[0003] Chinese Patent No. CN119494740A discloses an intelligent financial management system based on data feature analysis, which achieves a certain degree of intelligent analysis, but has many deficiencies. Specifically, it does not form a complete closed loop of business accounting, lacks a chain from demand to result verification and adjustment. Further, it lacks sufficient fine processing of data in the time dimension, making it difficult to effectively use data in different time periods. Importantly, it lacks an effective verification mechanism for business accounting results, and the accounting strategy lacks pertinence and flexibility, which cannot be flexibly adjusted according to actual conditions to ensure the accuracy of the accounting results, thereby affecting the quality of decision-making.

[0004] In summary, there is an urgent need for a new business accounting and decision-making method based on financial data to improve the accuracy and effectiveness of decision-making about accounting strategies in enterprise business accounting and its process. SUMMARY

[0005] The purpose of the present application is to provide a business accounting system based on financial data and a decision-making method to solve the technical problems raised in the background art.

[0006] To achieve the above-mentioned purpose, the present application discloses the following technical solutions: In a first aspect, the present application discloses a business accounting system based on financial data, comprising: The data acquisition module is configured to acquire business accounting requirements, determine a response data set for a corresponding time period based on the business accounting requirements, and use the response data set for business accounting; The accounting processing module is configured to match an accounting strategy based on the business accounting requirements and the response data set, generate an accounting result, and include an accounting algorithm and a corresponding parameter set, and correct the parameter set when matching; The prediction generation module is configured to generate a prediction data set based on the response data set and the accounting result, and use the prediction data set to represent the prediction of subsequent business data; The monitoring and verifying module is configured to continuously monitor the business data and generate a real data set, and perform confidence verification on the business accounting result based on a comparison result of the predicted data set and the real data set. The decision adjustment module is configured to replace the business accounting strategy and re-account when the confidence does not satisfy the preset confidence threshold.

[0007] Preferably, the business accounting requirement includes a requirement accounting strategy, a requirement data type, and a requirement data amount, and the business accounting requirement is a specific goal of the enterprise operation at a moment .

[0008] Preferably, the determination of the response data set comprises: determining a response data type and a redundant data type based on the requirement data type by traversing the business data, the redundant data type being a data type having an association degree greater than a preset association threshold with the response data type, the association degree being used to represent an association degree of the response data type and the redundant data type; determining a response data time period based on the response data type and the requirement data amount , the determination being that, in the business data before the moment , the business data corresponding to the response data type is forwardly filtered, and when the data amount of the filtered business data is greater than or equal to the requirement data amount, the corresponding moment is determined as a starting moment of collecting business data, and the time period is output and defined as a response data time period; collecting corresponding response data and redundant data within the response data time period based on the response data type and the redundant data type , and determining the collected response data and redundant data as a response data set; wherein the redundant data is used to verify the response data.

[0009] Preferably, the matching of the business accounting strategy based on the business accounting requirement and the response data set comprises: matching a first business accounting strategy satisfying the requirement accounting strategy in a preset business accounting strategy library based on the requirement accounting strategy and outputting, the requirement accounting strategy at least including any one or more of a cost accounting requirement, a profit accounting requirement, and a fund flow accounting requirement, the first business accounting strategy including an accounting algorithm and a corresponding first parameter set, the first parameter set being an original parameter set of the accounting algorithm; generating a second parameter set by modifying the first parameter set based on the response data set, the modification including the following steps: A1: calculating a correlation degree of a parameter in the first parameter set and the response data, screening and deleting parameters less than a preset correlation degree threshold, the correlation degree being used to represent a degree of correlation between a parameter and the response data; A2: adjusting a parameter value of a parameter screened in A1 based on the correlation degree; A3: outputting the parameter adjusted in A2, and generating a second parameter set; replacing the first parameter set in the first business accounting strategy with the second parameter set, and generating a second business accounting strategy, which is a matched business accounting strategy.

[0010] Preferably, the generation of the business accounting result comprises: performing business accounting on the response data by using the second business accounting strategy, and outputting a first business accounting result; verifying the first business accounting result by using the redundant data, which is: mapping and associating the redundant data with each item of data in the first business accounting result, calculating corresponding difference indicators based on the mapping and association, and judging whether each difference indicator satisfies a preset difference indicator threshold, if yes, outputting the first business accounting result as the business accounting result, otherwise, replacing the response data with the redundant data, re-performing business accounting, replacing corresponding data in the first business accounting result with a result of the re-performed business accounting to generate a second business accounting result, and outputting the second business accounting result as the business accounting result.

[0011] Preferably, the generation of the prediction data set comprises: calculating prediction data of a time period by using a preset prediction data calculation formula, wherein the time point is a preset cut-off output time point of the business accounting result, and packaging the prediction data to generate a prediction data set, wherein the prediction data calculation formula is: wherein, is a preset smoothing coefficient, is a preset correction coefficient, is prediction data of data at the time point , is real data of data at a time point one unit time before the time point , is prediction data of data at a time point two unit times before the time point , a correction value of data at time point , , and: wherein, is a total number of data in the business accounting result at time point , is a corresponding number in the total number, and , is a true value of data at time point , , and .

[0012] Preferably, the generation of the real data set comprises: based on the real business data corresponding to the time point of each data in the predicted data set, generating a real data set based on time series.

[0013] Preferably, the confidence verification of the business accounting result based on the comparison result of the predicted data set and the real data set comprises: point-by-point comparison of the predicted data set and the real data set based on time series, calculation of the relative error of each corresponding time point data, calculation of the average relative error based on the relative error, and then the confidence , wherein, the average relative error, when the confidence is greater than the preset confidence threshold, output the business accounting result; otherwise, replace the business accounting strategy and recalculate.

[0014] Preferably, the confidence verification of the business accounting result based on the comparison result of the predicted data set and the real data set further comprises: when the confidence is greater than the preset confidence threshold and the corresponding business accounting result will be used for high-risk scene adjustment, the confidence is corrected to obtain a corrected confidence , and the confidence correction formula is: wherein, represents the correction value of the data with the number at time point .

[0015] In a second aspect, the application discloses a decision-making method based on financial data, which is suitable for the business accounting system based on financial data as described above, and comprises the following steps: S1: Obtain the business accounting demand, determine the response data set of the corresponding period based on the business accounting demand, and the response data set is used for business accounting; S2: Match the business accounting strategy based on the business accounting demand and the response data set, and generate the business accounting result; the business accounting strategy includes the accounting algorithm and the corresponding parameter set, and the parameter set is corrected when matched; S3: Generate the prediction data set based on the response data set and the business accounting result, and the prediction data set is used to represent the prediction of subsequent business data; S4: Continuously monitor the business data and generate the real data set, and perform confidence verification on the business accounting result based on the comparison result of the prediction data set and the real data set; S5: When the confidence does not satisfy the preset confidence threshold, replace the business accounting strategy and re-account.

[0016] Beneficial effects: The business accounting system and decision making method based on financial data provided by the application realize the whole-process closed-loop management of business accounting by using the data acquisition module to capture the business accounting demand in real time, combining the dynamic strategy matching of the accounting processing module, the cross-period prediction of the prediction generation module, the confidence evaluation of the monitoring verification module, and the strategy iteration mechanism of the decision adjustment module; through the bidirectional verification of the response data set and the prediction and real data set, the dynamic accuracy of the accounting result is ensured; when the average relative error of the prediction data set and the real data set exceeds the threshold, the strategy adjustment is automatically triggered, the accounting model parameters are corrected, so that the traditional static accounting is upgraded to the adaptive dynamic accounting system, and the response speed of enterprise decision is improved and the accounting error rate is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 The structural block diagram of the business accounting system based on financial data provided by the embodiments of the application is provided. Figure 2 The flowchart of the decision making method based on financial data provided by the embodiments of the application is provided. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of them. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0020] In this document, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or further includes elements inherent to such a process, method, article or device. Without more limitations, the elements defined by the statement "comprising" do not exclude the presence of additional identical elements in the process, method, article or device including the elements.

[0021] The first aspect of the embodiment discloses a business accounting system based on financial data as shown in Figure 1 The business accounting system based on financial data comprises: The data acquisition module is configured to acquire a business accounting demand, determine a response data set of a corresponding time period based on the business accounting demand, and use the response data set for business accounting; The accounting processing module is configured to match a business accounting strategy based on the business accounting demand and the response data set, and generate a business accounting result. The business accounting strategy comprises an accounting algorithm and a corresponding parameter set, and the parameter set is corrected when matched; The prediction generation module is configured to generate a prediction data set based on the response data set and the business accounting result, and use the prediction data set to represent a prediction of subsequent business data; The monitoring and verification module is configured to continuously monitor business data and generate a real data set, and perform confidence verification on the business accounting result based on a comparison result of the prediction data set and the real data set; The decision adjustment module is configured to replace the business accounting strategy and re-account when the confidence does not satisfy a preset confidence threshold.

[0022] Through the above, the embodiment uses the data acquisition module to capture the business accounting demand in real time, uses the dynamic strategy matching of the accounting processing module, uses the cross-period prediction of the prediction generation module, uses the confidence evaluation of the monitoring and verification module, and uses the strategy iteration mechanism of the decision adjustment module, to realize the whole-process closed-loop management of business accounting. Through the bidirectional verification of the response data set, the prediction data set and the real data set, the dynamic accuracy of the accounting result is ensured. When the average relative error of the prediction data set and the real data set exceeds a threshold, the strategy adjustment is automatically triggered, the accounting model parameters are corrected, the traditional static accounting is upgraded to an adaptive dynamic accounting system, and the response speed of enterprise decision is improved and the accounting error rate is reduced.

[0023] Specifically, the business accounting demand includes a demand accounting strategy, a demand data type, and a demand data amount, and the business accounting demand is a moment when a specific goal of business operation is achieved.

[0024] Through the above, the embodiment realizes accurate determination of the accounting goal by decomposing the business accounting demand into three dimensions of accounting strategy, data type, and data amount. In a simple example, when the enterprise proposes a "2023 annual R&D cost accounting" demand at a moment , the system is automatically associated to the R&D expense account, and specific data types such as R&D material requisition slips and manual work hour records in the time period are filtered to ensure that the accounting range completely matches the actual demand of the enterprise.

[0025] Specifically, the determination of the response data set includes: determining a response data type and a redundant data type based on the demand data type traversing the business data, the redundant data type being a data type having an association degree greater than a preset association threshold with the response data type, the association degree being used to represent the degree of association between the response data type and the redundant data type; determining a response data time period based on the response data type and the demand data amount, the determination being: in the business data before a moment , forward filtering the business data corresponding to the response data type, and when the data amount of the filtered business data is greater than or equal to the demand data amount, determining the corresponding moment as the starting moment of collecting business data, and defining the time period as the response data time period and outputting it; based on the response data type and the redundant data type, collecting corresponding response data and redundant data in the response data time period , and determining the collected response data and redundant data as the response data set; wherein the redundant data is used to verify the response data.

[0026] Through the above, the embodiment realizes double verification of the response data through the verification mechanism of the redundant data. In a simple example, when determining the response data of the raw material procurement cost, the system synchronously collects the supplier invoice as the response data and the quality inspection report as the redundant data, and through cross comparison ensures the consistency of the procurement unit price and the quality inspection batch. Further, the association degree threshold can be set to 0.8.

[0027] Specifically, the matching of the business accounting demand and the response data set to the business accounting strategy includes: According to the demand accounting strategy, a first business accounting strategy that meets the demand accounting strategy is matched from a preset business accounting strategy library and output, the demand accounting strategy including at least any one or more of a cost accounting demand, a profit accounting demand and a fund flow accounting demand, and the first business accounting strategy including an accounting algorithm and a corresponding first parameter set, the first parameter set being an original parameter set of the accounting algorithm; According to the response data set, the first parameter set is corrected to generate a second parameter set, and the correction includes the following steps: A1: calculating a correlation degree of a parameter in the first parameter set and the response data, screening and deleting parameters less than a preset correlation degree threshold, and the correlation degree being used to represent a correlation degree of the parameter and the response data; A2: adjusting a parameter value of the parameter screened in A1 based on the correlation degree; A3: outputting the parameter adjusted in A2 to generate the second parameter set; The second parameter set is used to replace the first parameter set in the first business accounting strategy to generate a second business accounting strategy, and the second business accounting strategy is the matched business accounting strategy.

[0028] According to the above, the embodiment realizes dynamic optimization of the accounting strategy through the parameter set correction algorithm. In a simple example, when the activity-based costing method is used for accounting, the system recalculates the weight parameters of each activity driver according to the response data characteristics, such as production order quantity, machine working hours, etc., and upgrades the traditional fixed parameter model to a data-driven dynamic model.

[0029] Specifically, the generation of the business accounting result includes: The second business accounting strategy is used to perform business accounting on the response data to output a first business accounting result; The first business accounting result is verified by using the redundant data, and the verification is: The redundant data and each item of data in the first business accounting result are mapped and associated, each corresponding difference index is calculated based on the mapping and association, and it is judged whether each difference index meets a preset difference index threshold, if yes, the first business accounting result is output as the business accounting result, and if not, the response data is replaced by the redundant data to perform re-accounting, a second business accounting result is generated by using a result of the re-accounting to replace corresponding data in the first business accounting result, and the second business accounting result is output as the business accounting result.

[0030] Through the above, this embodiment achieves secondary confirmation of the calculation result by using a redundant data replacement verification mechanism. For example, when the difference between the transportation cost in the redundant data and the first calculation result exceeds a threshold, the system automatically replaces the transportation cost record in the response data and recalculates to ensure the reliability of the final result.

[0031] Specifically, the generation of the prediction dataset includes: Calculate the time period using a preset forecast data calculation formula. The predicted data, where time... At a preset cutoff time for outputting the operational accounting results, the predicted data is packaged to generate a predicted dataset, wherein the formula for calculating the predicted data is: in, The preset smoothing coefficient, The preset correction factor. For at any time Data at time The predicted data, For a moment Data from the previous unit of time Real data, For a moment Data from the previous two units of time The predicted data, Data obtained based on operational accounting results The correction value, ,and: in, For a moment The total number of data points in the operating accounting results. It is the corresponding number in the total number, and , For a moment Data The true value, and .

[0032] Based on the above, this embodiment achieves accurate prediction of operating data across time periods through the prediction data calculation formula. For example, when predicting sales revenue for the next quarter, the system combines historical sales data, accounting result correction values, and dynamic smoothing coefficients to generate a prediction dataset.

[0033] Specifically, the generation of the real dataset includes: Based on the real operating data collected at the corresponding time points in the predicted dataset, a real dataset is generated based on the time series.

[0034] By the above, the embodiment realizes the integrity construction of the real data set, and ensures the timeliness and continuity of data collection.

[0035] Specifically, the confidence verification of the business accounting result based on the comparison result of the prediction data set and the real data set comprises: point-by-point comparison of the prediction data set and the real data set based on time series, calculation of the relative error of each corresponding time data, calculation of the average relative error based on the relative error, and then confidence , wherein the average relative error, when the confidence is greater than a preset confidence threshold, outputting the business accounting result; otherwise, replacing the business accounting strategy and re-accounting.

[0036] By the above, the embodiment realizes the scientific evaluation of the accounting result. In a simple example, when the average relative error of the prediction data set and the real data set is , the confidence , and the system determines that the accounting result is reliable. Otherwise, if , a strategy adjustment process is triggered.

[0037] Specifically, the confidence verification of the business accounting result based on the comparison result of the prediction data set and the real data set further comprises: when the confidence is greater than a preset confidence threshold and the corresponding business accounting result is to be used for high-risk scene adjustment, the confidence is corrected to obtain a corrected confidence using a confidence correction formula, and the confidence correction formula is: wherein, represents the corrected value of the data with the number at time .

[0038] By the above, the embodiment realizes the decision optimization in the high-risk scene (which may be but is not limited to the auxiliary business strategy adjustment in the embodiment) through the confidence correction formula. For example, when the business accounting result is used for a major investment decision, the system adjusts the confidence The second aspect of the embodiment discloses a decision making method based on financial data as shown in Figure 2 , which is applicable to the business accounting system based on financial data as described above, and comprises the following steps: S1: obtaining a business accounting demand, determining a response data set of a corresponding time period based on the business accounting demand, and using the response data set for business accounting; S2: matching the business accounting strategy based on the business accounting demand and the response data set, generating the business accounting result; the business accounting strategy includes the accounting algorithm and the corresponding parameter set, and the parameter set is corrected when matching; S3: generating the prediction data set based on the response data set and the business accounting result, the prediction data set is used to represent the prediction of the subsequent business data; S4: continuously monitoring the business data and generating the real data set, and verifying the confidence of the business accounting result based on the comparison result of the prediction data set and the real data set; S5: when the confidence does not satisfy the preset confidence threshold, replacing the business accounting strategy and re-accounting.

[0039] It should be noted that the decision making method of the embodiment corresponds to the aforementioned business accounting system, therefore, the contents not specifically described in the decision making method of the embodiment can be, but are not limited to, the function definition, working principle and technical effect, which can refer to the records of the aforementioned business accounting system, and the text will not be repeated here.

[0040] In summary, the business accounting system and the decision making method based on financial data of the embodiment realize the whole-process closed-loop management of the business accounting by using the data acquisition module to capture the business accounting demand in real time, combining the dynamic strategy matching of the accounting processing module, the cross-period prediction of the prediction generation module, the confidence evaluation of the monitoring verification module, and the strategy iteration mechanism of the decision adjustment module; through the bidirectional verification of the response data set and the prediction, real data set, the dynamic accuracy of the accounting result is ensured, when the average relative error of the prediction data set and the real data set exceeds the threshold, the strategy adjustment is automatically triggered, the accounting model parameters are corrected, thereby upgrading the traditional static accounting to the adaptive dynamic accounting system, and the response speed of enterprise decision and the accounting error rate are improved.

[0041] In the embodiments provided by the present application, it should be understood that the embodiments described herein can be realized by hardware, software, firmware, middleware, codes or any proper combination thereof. For hardware implementation, the processor can be realized in one or more of the following components: an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For software implementation, the procedures described herein can be implemented with a computer program that is written in any suitable programming language. The program can be stored in a computer readable storage medium or transmitted as one or more instructions or codes on the computer readable storage medium. The computer readable storage medium includes any storage medium that can be accessed by a computer. The computer readable storage medium can include but is not limited to the following media: a RAM, a ROM, an EEPROM, a CD-ROM or other optical disc storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer.

[0042] Finally, it should be noted that the above only describes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, modifications or equivalent replacements of some technical features described in the foregoing embodiments can be made by those skilled in the art, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A business accounting system based on financial data, characterized in that, include: The data acquisition module is used to acquire operational accounting requirements, determine the response dataset for the corresponding time period based on the operational accounting requirements, and use the response dataset for operational accounting. The accounting processing module is used to match the business accounting needs and response datasets with the business accounting strategy and generate the business accounting results. The business accounting strategy includes the accounting algorithm and the corresponding parameter set, and the parameter set is modified during the matching process. The prediction generation module is used to generate a prediction dataset based on the response dataset and the operating accounting results. This prediction dataset is used to characterize the prediction of subsequent operating data. The monitoring and verification module is used to continuously monitor operational data and generate real datasets, and to verify the confidence level of operational accounting results based on the comparison results between the predicted dataset and the real dataset. The decision adjustment module is used to change the business accounting strategy and recalculate when the confidence level does not meet the preset confidence level threshold.

2. The business accounting system based on financial data according to claim 1, characterized in that, The operational accounting requirements include the accounting strategy, the data type of the requirements, and the volume of the requirements data, and the operational accounting requirements are time-based. The specific goals of a company's operations at that time.

3. The business accounting system based on financial data according to claim 2, characterized in that, The determination of the response dataset includes: Based on the required data type, the response data type and redundant data type are determined by traversing the operational data. The redundant data type is a data type whose correlation with the response data type is greater than a preset correlation threshold. The correlation is used to characterize the degree of correlation between the response data type and the redundant data type. The response data period is determined based on the response data type and the required data volume. This should be defined as: at time... From the existing operational data, filter forward for operational data corresponding to the data type of the response, and when the amount of the filtered operational data is greater than or equal to the amount of the required data, the corresponding time period is determined. The time period is determined as the start time for collecting operational data. Output and define the response data period; Based on the response data type and the redundant data type, during the response data period Within the system, corresponding response data and redundant data are collected, and the collected response data and redundant data are determined as a response dataset; wherein, the redundant data is used to verify the response data.

4. The business accounting system based on financial data according to claim 3, characterized in that, The matching of operational accounting strategies based on operational accounting needs and response datasets includes: Based on the demand accounting strategy, a first business accounting strategy that meets the demand accounting strategy is matched in the preset business accounting strategy library and output. The demand accounting strategy includes at least one or more of cost accounting demand, profit accounting demand and cash flow accounting demand. The first business accounting strategy includes an accounting algorithm and a corresponding first parameter set. The first parameter set is the original parameter set of the accounting algorithm. The first parameter set is modified based on the response dataset to generate a second parameter set. This modification includes the following steps: A1: Calculate the correlation between the parameters in the first parameter set and the response data, filter and delete parameters that are less than a preset correlation threshold, whereby the correlation is used to characterize the degree of correlation between the parameters and the response data; A2: Adjust the parameter values ​​of the parameters filtered by A1 based on the relevance; A3: Output the parameters adjusted by A2 to generate the second parameter set; The first parameter set in the first business accounting strategy is replaced with the second parameter set to generate a second business accounting strategy, which is the matched business accounting strategy.

5. The business accounting system based on financial data according to claim 4, characterized in that, The generation of the operating accounting results includes: The response data is processed using the second business accounting strategy to perform business accounting, and a first business accounting result is output. The first operating accounting result is verified using the redundant data, and the verification is as follows: The redundant data is mapped and associated with each data item in the first operating accounting result. Based on the mapping and association, the corresponding difference indicators are calculated. It is determined whether each difference indicator meets the preset difference indicator threshold. If so, the first operating accounting result is output as the operating accounting result output. Otherwise, for the data that does not meet the difference indicator threshold, the response data is replaced with the redundant data and recalculated. The result of the recalculation is used to replace the corresponding data in the first operating accounting result to generate a second operating accounting result. The second operating accounting result is output as the operating accounting result.

6. The business accounting system based on financial data according to claim 1, characterized in that, The generation of the prediction dataset includes: Calculate the time period using a preset forecast data calculation formula. The predicted data, where time... At a preset cutoff time for outputting the operational accounting results, the predicted data is packaged to generate a predicted dataset, wherein the formula for calculating the predicted data is: in, The preset smoothing coefficient, The preset correction factor. For at any time Data at time The predicted data, For a moment Data from the previous unit of time Real data, For a moment Data from the previous two units of time The predicted data, Data obtained based on operational accounting results The correction value, ,and: in, For a moment The total number of data points in the operating accounting results. It is the corresponding number in the total number, and , For a moment Data The true value, and .

7. The business accounting system based on financial data according to claim 1, characterized in that, The generation of the real dataset includes: Based on the real operating data collected at the corresponding time points in the predicted dataset, a real dataset is generated based on the time series.

8. The business accounting system based on financial data according to claim 6, characterized in that, The confidence verification of the operational accounting results based on the comparison results between the predicted dataset and the real dataset includes: The predicted dataset and the real dataset are compared point-by-point based on time series data. The relative error of the data at each corresponding time point is calculated, and the average relative error is calculated based on this relative error. Then, the confidence level is determined. , among which, Mean relative error, when confidence level If the confidence level exceeds the preset threshold, output the business accounting result; otherwise, change the business accounting strategy and recalculate.

9. The business accounting system based on financial data according to claim 8, characterized in that, The confidence verification of the operating accounting results based on the comparison results of the predicted dataset and the real dataset also includes: When confidence level When the confidence level exceeds a preset confidence threshold and the corresponding operational accounting results will be used for adjustments in high-risk scenarios, the confidence level is adjusted using a confidence level correction formula. The corrected confidence level is obtained by making corrections. The confidence level correction formula is as follows: in, Indicates time The number is The corrected value of the data.

10. A decision-making method based on financial data, applicable to the financial data-based business accounting system as described in any one of claims 1-9, characterized in that, Includes the following steps: S1: Obtain operational accounting requirements, determine the response dataset for the corresponding time period based on the operational accounting requirements, and use the response dataset for operational accounting. S2: Match the operational accounting strategy with the operational accounting needs and response dataset to generate operational accounting results; the operational accounting strategy includes the accounting algorithm and the corresponding parameter set, and the parameter set is modified during matching; S3: Generate a forecast dataset based on the response dataset and the operating accounting results. This forecast dataset is used to characterize the forecast of subsequent operating data. S4: Continuously monitor operational data and generate real datasets, and verify the confidence level of operational accounting results based on the comparison between predicted datasets and real datasets; S5: If the confidence level does not meet the preset confidence level threshold, change the business accounting strategy and recalculate.

Images