Accounting document integrated intelligent management system

Abstract

The invention relates to the technical field of accounting and financial management, in particular to an accounting document integrated intelligent management system which comprises a data acquisition module, a data processing module, a data storage module, a data analysis module, an auditing and approving module and a visualization module. The data processing module is used for cleaning, formatting and verifying the collected data, the data storage module is used for storing the processed accounting document data, the data analysis module is used for analyzing the stored accounting document data, and the auditing and approving module is used for auditing and approving the accounting document data; and the visualization module provides a visualization interaction interface and is used for displaying the accounting document data and the auditing result. According to the invention, through automation and intelligentization technologies, the efficiency and accuracy of accounting document management are improved, the intelligentization level and decision support capability of financial management are enhanced, and powerful financial management support is provided for enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of accounting and financial management, and in particular to an integrated intelligent management system for accounting vouchers. Background Art

[0002] As the scale of enterprises expands and the business becomes more complicated, the management of accounting documents becomes more and more important. Accounting documents are an important part of enterprise financial management, recording the economic business and financial activities of enterprises, and directly affecting the accuracy and completeness of financial statements. Traditional accounting document management usually relies on manual operations, including document entry, review, filing and analysis, which not only consumes a lot of manpower and time, but is also prone to human errors and data loss.

[0003] Although the existing technology has achieved digital management of accounting documents to a certain extent, there are still many technical problems. First, the efficiency of data collection and processing is low. When processing a large amount of accounting document data, the existing system is difficult to achieve efficient automatic processing, and the accuracy and integrity of the data are difficult to guarantee. Secondly, the data analysis and decision support capabilities are insufficient. The existing system usually only provides simple reports and statistical analysis, which cannot effectively identify anomalies in the data and predict future financial trends, and lacks intelligent data analysis methods. In addition, the review and approval process is complicated and inefficient, the manual review workload is large, and omissions and errors are prone to occur. There is a lack of systematic and standardized review mechanism. Summary of the invention

[0004] Based on the above objectives, the present invention provides an integrated intelligent management system for accounting vouchers.

[0005] An integrated intelligent management system for accounting vouchers, comprising a data collection module, a data processing module, a data storage module, a data analysis module, an audit and approval module and a visualization module, wherein;

[0006] The data acquisition module is used to collect various accounting voucher data, obtain images of paper accounting vouchers through a high-resolution scanner or camera, or receive electronic accounting vouchers through a preset interface;

[0007] The data processing module is used to clean, format and verify the collected data;

[0008] The data storage module is used to store the processed accounting voucher data;

[0009] The data analysis module is used to analyze the stored accounting voucher data;

[0010] The data analysis module includes an anomaly detection unit and a trend prediction unit, wherein the anomaly detection unit is used to identify anomalies in accounting voucher data, and the trend prediction unit is used to predict future financial trends;

[0011] The review and approval module is used to review and approve accounting voucher data;

[0012] The audit and approval module includes an automatic audit unit and a manual audit unit. The automatic audit unit performs a preliminary audit on the accounting voucher data based on preset rules, and the manual audit unit is used to review the accounting voucher data after the automatic audit.

[0013] The visualization module provides a visual interactive interface for displaying accounting voucher data and audit results.

[0014] Optionally, the data acquisition module specifically includes:

[0015] Image acquisition: Use a high-resolution scanner or camera to scan or photograph paper accounting documents to obtain clear images, and transmit the collected images to the data acquisition module via a wired or wireless network;

[0016] Electronic voucher reception: Receive electronic accounting vouchers through the preset interface to ensure the integrity and accuracy of the data;

[0017] Data preprocessing: adjust the brightness and contrast of the image to ensure the image is clear, and perform image tilt correction to make the text and digital information in a horizontal state;

[0018] Field extraction: Extract text and digital information from images or electronic documents.

[0019] Optionally, the data processing module includes a data cleaning unit, a data formatting unit and a data verification unit, the data cleaning unit is used to remove noise and redundant information in the accounting voucher data, the data formatting unit is used to convert the cleaned data into a unified format, and the data verification unit is used to verify the accuracy and completeness of the formatted data.

[0020] Optionally, the data processing module specifically includes:

[0021] Data cleaning unit: Use median filtering algorithm to remove noise in accounting voucher data, and use rule filtering and duplicate value detection algorithm to remove redundant information in the data;

[0022] Data formatting unit: converts the cleaned data into a unified format, including data type conversion and data unit standardization;

[0023] Data verification unit: Verify the accuracy and completeness of formatted data.

[0024] Optionally, the data storage module specifically includes:

[0025] Data storage architecture design: Use distributed database technology to store processed accounting voucher data and configure distributed database clusters, including the number of nodes, data sharding strategy, and replica strategy;

[0026] Data writing: Distribute the processed accounting voucher data to different nodes according to the sharding strategy, write the data to the corresponding shards to ensure data consistency and integrity, and write copies of the data to multiple nodes to improve data reliability and availability;

[0027] Data reading: Read data from the corresponding node and merge data from multiple shards to return complete query results.

[0028] Optionally, the abnormality detection unit specifically includes:

[0029] Data extraction: The anomaly detection unit extracts the stored accounting voucher data from the data storage module;

[0030] Data processing: standardize the data and remove noise and outliers;

[0031] Anomaly detection: The isolation forest algorithm is used to identify anomalies in accounting document data, including constructing an isolation forest, calculating path length, calculating anomaly scores, and marking outliers.

[0032] Optionally, the trend prediction unit specifically includes:

[0033] Data extraction: The trend prediction unit extracts the stored accounting voucher data from the data storage module;

[0034] Data processing: sort accounting voucher data by time, construct time series data, and smooth the time series data;

[0035] Data segmentation: divide the time series data into training set and test set;

[0036] Trend prediction: Build a trend prediction model through long short-term memory network to predict future financial trends, including model construction, model training, model prediction and result evaluation.

[0037] Optionally, the automatic review unit specifically includes:

[0038] Preset rule definition: define a set of rules for reviewing accounting document data;

[0039] Automatic audit process: read the accounting voucher data to be audited from the data storage module, and check whether each accounting voucher data complies with the preset rules one by one;

[0040] Audit result processing: For accounting documents that meet all rules, they are marked as passed automatic audit. For accounting documents that do not meet any rules, they are marked as failed and the audit results and reasons are recorded.

[0041] Optionally, the manual review unit specifically includes:

[0042] Review task allocation: Assign accounting voucher data that fails automatic review to manual reviewers;

[0043] Manual review process: The reviewer reads the accounting voucher data to be reviewed from the system and checks the accounting voucher data item by item based on corporate policies, accounting standards and personal experience;

[0044] Processing of audit results: For accounting documents that meet all inspection items, they are marked as having passed manual review. For accounting documents with problems, the audit results and reasons are recorded, and relevant personnel are notified to make corrections.

[0045] Optionally, the visualization module specifically includes:

[0046] Accounting voucher data display: Use table format to display detailed information of accounting vouchers, including voucher number, date, amount, account and person in charge;

[0047] Audit result display: The audit results are displayed in a table format, marking the accounting documents that have passed and failed, and showing the reasons for failure;

[0048] Financial trend forecast display: Use a line chart to display the financial trend forecast results and show future financial trends.

[0049] Beneficial effects of the present invention:

[0050] The present invention automatically collects accounting voucher data through a high-resolution scanner or camera, the data cleaning unit removes noise and redundant information in the accounting voucher data, the data formatting unit converts the cleaned data into a unified format, and the data verification unit verifies the accuracy and integrity of the formatted data. The automatic audit unit performs a preliminary audit based on preset rules, quickly identifies and marks abnormal data, and greatly improves the efficiency of data processing. The automation and standardization of the entire data processing process reduces manual intervention and human errors, and ensures the high quality and consistency of accounting voucher data.

[0051] In the present invention, the data analysis module constructs a trend prediction model through a long short-term memory network, performs trend prediction on financial data, captures the long-term dependencies of time series data, and realizes accurate prediction of future financial trends. The anomaly detection unit uses the isolation forest algorithm to identify anomalies in the data, providing strong decision support for enterprises. The interactive interface provided by the visualization module displays accounting voucher data, audit results and financial trend predictions, helping users better understand and analyze data change trends.

[0052] In the present invention, the audit and approval module combines the automatic audit unit and the manual audit unit to realize an audit mechanism that combines automatic and manual audits. The preliminary audit is completed by the automatic audit unit, which quickly checks the accounting voucher data based on preset rules; the manual audit unit reviews the data after the automatic audit to ensure the accuracy and completeness of the data. This audit mechanism with clear division of labor and clear process effectively reduces the workload of manual audits and improves audit efficiency. The system also records the audit process and results of each accounting voucher, including detailed information on automatic and manual audits, provides comprehensive audit records for subsequent audits, and enhances the transparency and traceability of financial management. Through detailed audit records and traceability, enterprises can better comply with financial regulations and internal policies, and improve the compliance and reliability of financial management. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0055] Figure 2 Schematic diagram of the data analysis module flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0057] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0058] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0059] like Figure 1-Figure 2 As shown, an integrated intelligent management system for accounting vouchers includes a data collection module, a data processing module, a data storage module, a data analysis module, an audit and approval module and a visualization module, wherein;

[0060] The data acquisition module is used to collect various accounting voucher data, obtain images of paper accounting vouchers through high-resolution scanners or cameras, or receive electronic accounting vouchers through a preset interface;

[0061] The data processing module is used to clean, format and verify the collected data;

[0062] The data storage module is used to store the processed accounting voucher data;

[0063] The data analysis module is used to analyze the stored accounting voucher data;

[0064] The data analysis module includes an anomaly detection unit and a trend prediction unit. The anomaly detection unit is used to identify anomalies in accounting voucher data, and the trend prediction unit is used to predict future financial trends.

[0065] The review and approval module is used to review and approve accounting voucher data;

[0066] The audit and approval module includes an automatic audit unit and a manual audit unit. The automatic audit unit conducts a preliminary audit on the accounting voucher data based on preset rules, and the manual audit unit is used to review the accounting voucher data after the automatic audit.

[0067] The visualization module provides a visual interactive interface for displaying accounting document data and audit results.

[0068] The data acquisition module specifically includes:

[0069] Image acquisition: Use a high-resolution scanner or camera to scan or photograph paper accounting documents to obtain clear images, and transmit the collected images to the data acquisition module via a wired or wireless network;

[0070] Electronic voucher reception: Receive electronic accounting vouchers through the preset interface to ensure the integrity and accuracy of the data;

[0071] Data preprocessing: adjust the brightness and contrast of the image to ensure that the image is clear, and perform image tilt correction to make the text and digital information horizontal. The specific formula is as follows:

[0072] Brightness adjustment is expressed as: I′(x, y)=I(x, y)+β;

[0073] Where I(x, y) is the pixel value of the original image, β is the brightness adjustment coefficient, and I′(x, y) is the adjusted pixel value;

[0074] Contrast adjustment is expressed as: I′(x, y)=α·(I(x, y)-128)+128;

[0075] Where α is the contrast adjustment coefficient, I(x, y) is the pixel value of the original image, I′(x, y) is the adjusted pixel value, and 128 is the middle value of the pixel value, which is used to balance the contrast adjustment;

[0076] Tilt Correction:

[0077] Hough transform is used to detect straight lines in an image:

[0078] ρ = xcosθ + ysinθ, where ρ is the vertical distance from the line to the origin, θ is the angle between the line and the x-axis, and xy is the pixel coordinate in the image;

[0079] The tilt correction angle is calculated as:

[0080] θ correct =-θ detected ;

[0081] Among them, θ detected is the tilt angle detected by Hough transform, θ correct is the angle that needs to be corrected;

[0082] Field extraction: extract text and digital information from images or electronic vouchers, such as invoice number, date, amount, etc.

[0083] Assuming the information position in the image is known, use the following formula to extract it:

[0084] F(i)=I(x i ,y i );

[0085] Among them, F(i) is the information of the i-th field, I(x i ,y i ) is the pixel value or text information at the corresponding position in the image, x i y i is the pixel coordinate in the image, indicating the location of the i-th field.

[0086] The data processing module includes a data cleaning unit, a data formatting unit and a data verification unit. The data cleaning unit is used to remove noise and redundant information in the accounting voucher data, the data formatting unit is used to convert the cleaned data into a unified format, and the data verification unit is used to verify the accuracy and completeness of the formatted data.

[0087] The data processing module specifically includes:

[0088] Data cleaning unit: Use median filtering algorithm to remove noise in accounting voucher data, and use rule filtering and duplicate value detection algorithm to remove redundant information in the data;

[0089] The median filter algorithm is expressed as:

[0090] I'(x, y)=median{I(x+i, y+j)}, (i, j)∈W;

[0091] Where W is the filter window, median is the median of the pixel values ​​in the window, I(x, y) is the pixel value of the original image, and I′(x, y) is the pixel value after denoising;

[0092] The duplicate value detection algorithm is expressed as:

[0093] D′={d∈D|isUnique(d)};

[0094] Where D is the original data set, D′ is the data set after removing redundant information, which means the filtered data, isUnique(d) is a function to determine whether the data d is unique, and returns a Boolean value (true or false);

[0095] Data formatting unit: converts the cleaned data into a unified format, including data type conversion and data unit standardization;

[0096] Data type conversion: Convert data into a predefined type, such as converting a string type date into a standard date format, expressed as:

[0097] Date formatted = toDate(Date string , ′YYYY-MM-DD′);

[0098] Among them, Date formatted Is the formatted date, Date string is the date of the original string type, 'toDate' is a function that converts a string into a date, 'YYYY-MM-DD' is the target date format, which means year-month-day;

[0099] Data unit standardization: convert data in different units into a unified unit, for example, convert the amount into RMB, expressed as:

[0100] Amount CNY =convert(Amount original , Currency);

[0101] Among them, Amount CNY is the amount after conversion, Amount original is the original amount, Currency is the currency unit of the original amount, and 'convert' is the function that converts the currency unit;

[0102] Data verification unit: Verify the accuracy and completeness of formatted data;

[0103] Accuracy check: Use rule check and range check to check whether the data is within the expected range, expressed as:

[0104]

[0105] Where d is the data to be verified, indicating the specific data value, min is the minimum expected value of the data, max is the maximum expected value of the data, and 'isvalid' is a function that checks whether the data is within the expected range and returns a Boolean value (true or false);

[0106] Integrity check: Use integrity rules to check whether the data contains all required fields, expressed as:

[0107]

[0108] Where D is the data set to be checked, which means all data; F is the set of required fields, which means all fields that need to be checked; 'hasField' is a function that checks whether data d contains field f and returns a Boolean value (true or false); 'iscomplete' is a function that checks whether the data set is complete and returns a Boolean value (true or false);

[0109] Through the above specific steps and formulas, the data processing module can efficiently and accurately clean, format and verify the collected data, providing a reliable foundation for subsequent data storage, analysis and review, and ensuring the integrity and consistency of the entire system solution.

[0110] The data storage module specifically includes:

[0111] Data storage architecture design: Use distributed database technology to store processed accounting voucher data and configure distributed database clusters, including the number of nodes, data sharding strategy, and replica strategy;

[0112] Data writing: Distribute the processed accounting voucher data to different nodes according to the sharding strategy, write the data to the corresponding shards to ensure data consistency and integrity, and write copies of the data to multiple nodes to improve data reliability and availability;

[0113] Data reading: Read data from the corresponding node and merge data from multiple shards to return complete query results.

[0114] The anomaly detection unit specifically includes:

[0115] Data extraction: The anomaly detection unit extracts the stored accounting voucher data from the data storage module;

[0116] Data processing: standardize the data and remove noise and outliers;

[0117] The standardized formula is calculated as:

[0118] Among them, z is the standardized data value, x is the original data value, μ is the mean value of the data, and σ is the standard deviation of the data;

[0119] Anomaly detection: The isolation forest algorithm is used to identify anomalies in accounting voucher data, including building an isolation forest, calculating path length, calculating anomaly scores, and marking outliers. The specific steps are as follows:

[0120] (1) Construct an isolation forest: randomly select a feature from the data set, randomly select a split point within the value range of the feature, divide the data set into two parts according to the split point, and repeat the above steps until each data point is isolated or the tree reaches the maximum height;

[0121] (2) Calculate the path length: For each data point, calculate its average path length in all trees. The shorter the path of a data point, the easier it is to be isolated, and the more likely it is to be an outlier.

[0122] (3) Anomaly score calculation: The anomaly score of each data point is calculated based on the path length, ranging from 0 to 1. The closer the score is to 1, the more likely it is an outlier, expressed as:

[0123]

[0124] Where score(x) is the anomaly score of data point x, E(h(x)) is the average path length of data point x in the isolated tree, and c(n) is a normalized constant determined by the size of the dataset n, which is approximately:

[0125] Among them, H(i) is the harmonic number of the i-th natural number;

[0126] (4) Marking outliers: According to the anomaly score, a threshold is set and data points whose anomaly scores exceed the threshold are marked as outliers.

[0127] The trend forecasting unit specifically includes:

[0128] Data extraction: The trend prediction unit extracts the stored accounting voucher data from the data storage module;

[0129] Data processing: Sort the accounting voucher data by time, construct time series data, and smooth the time series data, which can be expressed as:

[0130] Smoothed t =α·x t +(1-α)·Smoothed t-1 ;

[0131] Among them, Smoothed t is the smoothed value at time t, x t is the original data value at time t, α is the smoothing coefficient, and its value range is 0 to 1;

[0132] Data segmentation: divide the time series data into training set and test set;

[0133] Trend prediction: Build a trend prediction model through long short-term memory network to predict future financial trends, including model construction, model training, model prediction and result evaluation. The specific steps are as follows:

[0134] (1) Model building: used to predict future financial trends, including network hierarchy design and long short-term memory units:

[0135] A. The network hierarchy design includes input layer, long short-term memory layer, fully connected layer and output layer, where;

[0136] Input layer: receives input time series data;

[0137] Long short-term memory layer: One or more long short-term memory layers to capture long-term dependencies of time series;

[0138] Fully connected layer: converts the output of the long short-term memory layer into a prediction value;

[0139] Output layer: Generates the final prediction results.

[0140] B. Long-term short-term memory unit: The core of the long-term short-term memory unit consists of the cell state and the input gate, forget gate and output gate. The input gate controls the impact of input information, the forget gate determines how much past information to retain, and the output gate determines the output content.

[0141] (2) Model training: The model is trained using the training set data. The mean square error is used as the loss function during the training process to measure the difference between the predicted value and the true value.

[0142]

[0143] Where N is the number of training samples, y i is the true value, is the predicted value;

[0144] (3) Model prediction: Use the trained model to predict the test data;

[0145] Input test data: Input the standardized test data into the long short-term memory network;

[0146] Generate prediction results: Long short-term memory network outputs the predicted value;

[0147] Denormalization: Denormalize the prediction results and convert them back to the original data range, expressed as:

[0148] y = x′·σ+μ;

[0149] Among them, x′ is the predicted value after standardization, y is the predicted value after de-standardization, σ is the standard deviation of the data, and μ is the mean of the data;

[0150] (4) Result evaluation: The root mean square error and mean absolute error were used to evaluate the prediction performance of the model;

[0151]

[0152]

[0153] Where N is the number of samples, y i is the true value, is the predicted value;

[0154] By building a trend prediction model through a long short-term memory network, we can effectively capture the long-term dependencies of time series data, achieve accurate predictions of future financial trends, and provide strong data support for corporate managers.

[0155] The automatic audit unit specifically includes:

[0156] Preset rule definition: define a set of rules for reviewing accounting document data, which can be based on internal corporate policies, accounting standards and regulatory requirements;

[0157] Example rule:

[0158] Each accounting voucher must include basic information such as voucher number, date, amount and person in charge;

[0159] The amount field must be a positive number and within a reasonable range;

[0160] Accounting accounts must conform to the company’s chart of accounts;

[0161] Automatic audit process: read the accounting voucher data to be audited from the data storage module, and check whether each accounting voucher data complies with the preset rules one by one;

[0162] Audit result processing: For accounting documents that meet all rules, they are marked as passed automatic audit. For accounting documents that do not meet any rules, they are marked as failed and the audit results and reasons are recorded.

[0163] The manual review unit specifically includes:

[0164] Review task allocation: Assign accounting voucher data that fails automatic review to manual reviewers. The allocation method can be based on factors such as workload and expert expertise.

[0165] Manual review process: The reviewer reads the accounting voucher data to be reviewed from the system and checks the accounting voucher data item by item based on corporate policies, accounting standards and personal experience;

[0166] Examples of inspection items:

[0167] Confirm the completeness and accuracy of basic information of the voucher;

[0168] Check the rationality of voucher amounts and accounting items;

[0169] Confirm whether the approval signature of the voucher is complete;

[0170] Processing of audit results: For accounting documents that meet all inspection items, they are marked as having passed manual review. For accounting documents with problems, the audit results and reasons are recorded, and relevant personnel are notified to make corrections;

[0171] The audit and approval module can audit and approve accounting document data efficiently and accurately to ensure the accuracy and completeness of the data.

[0172] The visualization module specifically includes:

[0173] Accounting voucher data display: The detailed information of accounting vouchers is displayed in a table format, including voucher number, date, amount, subject and person in charge. Users can filter and sort by voucher number, date, amount, etc.

[0174] Audit result display: The audit results are displayed in a table format, marking the accounting documents that have passed and failed, and showing the reasons for failure. Users can filter out the accounting documents that have failed and view the specific audit issues;

[0175] Financial trend forecast display: Use line chart to display financial trend forecast results and show future financial trends. Users can select different time ranges to view the corresponding financial trends.

[0176] The visualization module can efficiently and intuitively display accounting document data, audit results and financial trend forecasts, helping users better understand and analyze data and improve decision-making efficiency and accuracy.

[0177] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0178] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An integrated intelligent management system for accounting vouchers, characterized in that: It includes data acquisition module, data processing module, data storage module, data analysis module, review and approval module and visualization module, among which; The data acquisition module is used to collect various accounting voucher data, obtain images of paper accounting vouchers through a scanner or camera, or receive electronic accounting vouchers through a preset interface; The data processing module is used to clean, format and verify the collected data; The data storage module is used to store the processed accounting voucher data; The data analysis module is used to analyze the stored accounting voucher data; The data analysis module includes an anomaly detection unit and a trend prediction unit, wherein the anomaly detection unit is used to identify anomalies in accounting voucher data, and the trend prediction unit is used to predict future financial trends; The review and approval module is used to review and approve accounting voucher data; The audit and approval module includes an automatic audit unit and a manual audit unit. The automatic audit unit performs a preliminary audit on the accounting voucher data based on preset rules, and the manual audit unit is used to review the accounting voucher data after the automatic audit. The visualization module provides a visual interactive interface for displaying accounting voucher data and audit results.

2. The integrated intelligent management system for accounting vouchers according to claim 1 is characterized in that: The data acquisition module specifically includes: Image acquisition: Use a scanner or camera to scan or photograph paper accounting documents to obtain images, and transmit the collected images to the data acquisition module through a wired or wireless network; Electronic voucher reception: receiving electronic accounting vouchers through the preset interface; Data preprocessing: adjust the brightness and contrast of the image, and perform image tilt correction to make the text and digital information horizontal; Field extraction: Extract text and digital information from images or electronic documents.

3. The integrated intelligent management system for accounting vouchers according to claim 2 is characterized in that: The data processing module includes a data cleaning unit, a data formatting unit and a data verification unit. The data cleaning unit is used to remove noise and redundant information in the accounting voucher data, the data formatting unit is used to convert the cleaned data into a unified format, and the data verification unit is used to verify the accuracy and completeness of the formatted data.

4. The integrated intelligent management system for accounting vouchers according to claim 3 is characterized in that: The data processing module specifically includes: Data cleaning unit: Use median filtering algorithm to remove noise in accounting voucher data, and use rule filtering and duplicate value detection algorithm to remove redundant information in the data; Data formatting unit: converts the cleaned data into a unified format, including data type conversion and data unit standardization; Data verification unit: Verify the accuracy and completeness of formatted data.

5. The integrated intelligent management system for accounting vouchers according to claim 4 is characterized in that: The data storage module specifically includes: Data storage architecture design: Use distributed database technology to store processed accounting voucher data and configure distributed database clusters, including the number of nodes, data sharding strategy, and replica strategy; Data writing: Distribute the processed accounting voucher data to different nodes according to the sharding strategy, write the data to the corresponding shards, and write copies of the data to multiple nodes to improve data reliability and availability; Data reading: Read data from the corresponding node and merge data from multiple shards to return complete query results.

6. The integrated intelligent management system for accounting vouchers according to claim 1 is characterized in that: The abnormality detection unit specifically includes: Data extraction: The anomaly detection unit extracts the stored accounting voucher data from the data storage module; Data processing: standardize the data and remove noise and outliers; Anomaly detection: The isolation forest algorithm is used to identify anomalies in accounting document data, including constructing an isolation forest, calculating path length, calculating anomaly scores, and marking outliers.

7. The integrated intelligent management system for accounting vouchers according to claim 1 is characterized in that: The trend prediction unit specifically includes: Data loading: The trend forecasting unit loads the accounting voucher data stored in the data storage module; Smoothing: sort accounting voucher data by time, construct time series data, and perform smoothing on the time series data; Data segmentation: divide the time series data into training set and test set; Trend prediction: Build a trend prediction model through long short-term memory network to predict future financial trends, including model construction, model training, model prediction and result evaluation.

8. The integrated intelligent management system for accounting vouchers according to claim 1 is characterized in that: The automatic audit unit specifically includes: Preset rule definition: define a set of rules for reviewing accounting document data; Automatic audit process: read the accounting voucher data to be audited from the data storage module, and check whether each accounting voucher data complies with the preset rules one by one; Audit result processing: For accounting documents that meet all rules, they are marked as passed automatic audit. For accounting documents that do not meet any rules, they are marked as failed and the audit results and reasons are recorded.

9. The integrated intelligent management system for accounting vouchers according to claim 1 is characterized in that: The manual review unit specifically includes: Review task allocation: Assign accounting voucher data that fails automatic review to manual reviewers; Manual review process: The reviewer reads the accounting voucher data to be reviewed and checks the accounting voucher data item by item based on corporate policies, accounting standards and personal experience; Processing of audit results: For accounting documents that meet all inspection items, they are marked as having passed manual review. For accounting documents with problems, the audit results and reasons are recorded, and relevant personnel are notified to make corrections.

10. The integrated intelligent management system for accounting vouchers according to claim 1 is characterized in that: The visualization module specifically includes: Accounting voucher data display: Use table format to display detailed information of accounting vouchers, including voucher number, date, amount, account and person in charge; Audit result display: The audit results are displayed in a table format, marking the accounting documents that have passed and failed, and showing the reasons for failure; Financial trend forecast display: Use a line chart to display the financial trend forecast results and show future financial trends.

Images