Intelligent financial data anomaly auditing method and system
By using automated data processing and intelligent identification, the problem of low efficiency in traditional financial data auditing has been solved, enabling efficient identification and assessment of financial data anomalies, thereby improving audit quality and efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANDONG KAIWEN COLLEGE OF SCI & TECH
- Filing Date
- 2026-03-24
- Publication Date
- 2026-06-23
AI Technical Summary
Traditional financial data auditing methods are inefficient, struggle to identify complex anomalies, lack intelligent decision support, and fail to meet the requirements of timeliness and accuracy.
By employing automated data collection, cleaning, and standardization, combined with a rule base and machine learning model, a smart financial data anomaly audit system is constructed by identifying suspected abnormal data and assessing its severity through random binary trees and support vector machines.
It improves the efficiency of financial data auditing, reduces manual operation time, lowers the rate of missed and false detections, provides accurate assessment of the nature and severity of anomalies, and provides a reliable basis for decision-making.
Smart Images
Figure CN122264969A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, specifically to an intelligent method and system for auditing anomalies in financial data. Background Technology
[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.
[0003] In today's digital age, corporate financial data is experiencing explosive growth. Traditional financial data auditing methods mainly rely on manual operations, requiring auditors to spend a significant amount of time and effort verifying and analyzing financial statements, vouchers, and other data one by one. This approach is not only inefficient but also prone to oversights, failing to meet companies' requirements for the timeliness and accuracy of financial data audits.
[0004] With the development of big data and artificial intelligence technologies, although some enterprises have begun to try applying some technologies to financial data auditing, existing methods still have many problems. For example, most systems can only perform simple data comparison and rule matching, and are unable to effectively identify complex anomalies hidden behind large amounts of data; in terms of anomaly handling, there is a lack of intelligent decision support, and they cannot provide targeted handling suggestions based on the nature and severity of the anomalies. Summary of the Invention
[0005] To address the shortcomings of existing technologies, this invention provides an intelligent financial data anomaly auditing method and system. Through automated data collection, cleaning, standardization, and anomaly identification and analysis processes, it significantly reduces the time and workload of manual operations, enabling financial data audits to be completed in a shorter time and improving the efficiency of auditing work.
[0006] To achieve the above objectives, the present invention adopts the following technical solution:
[0007] In a first aspect, the present invention provides an intelligent method for auditing anomalies in financial data, comprising the following processes:
[0008] Collect various types of financial data from enterprises, clean the collected data, standardize the cleaned data, and generate the original financial dataset.
[0009] For each cleaned and standardized data in the original financial dataset, check whether it meets all the rules in the preset rule base. If it does not meet a certain rule, mark it as suspected abnormal data and generate the first suspected abnormal database.
[0010] For each cleaned and standardized data point in the original financial dataset, a score is obtained based on the average path length of the data in the random binary tree and the theoretical value of the average path length when the sample size is n. Data points with scores greater than a set threshold are added to the second suspected anomaly database.
[0011] The first and second suspected anomaly databases are combined to obtain the final anomaly database. For data that is not identified as anomaly, financial features are extracted to construct feature vectors. The probability of belonging to each type of anomaly is calculated using a support vector machine model. When the probability is greater than a set threshold, the corresponding data is added to the final anomaly database.
[0012] The final severity assessment of the anomalies is determined based on the amount of the anomalies, their importance to the business, and their impact on the financial situation.
[0013] As a further limitation of the first aspect of the present invention, the score of the i-th data is:
[0014] ;
[0015] in, This is the theoretical value for the average path length when the sample size is n. Let be the average path length of the i-th data item in the random binary tree. This represents the i-th data item in the original financial dataset.
[0016] As a further limitation of the first aspect of the invention, the theoretical value of the average path length when the sample size is n is:
[0017] ;
[0018] in, It is a harmonic number.
[0019] As a further limitation of the first aspect of the present invention, the final assessment result of the severity of the anomaly of the i-th anomaly is determined based on the amount of the anomaly data, the weight of its business importance, and the coefficient of its impact on the financial situation. ,include:
[0020] ;
[0021] in, For abnormal data amounts, Assigning weights based on business importance. The impact coefficient on financial condition, , and All are weighting coefficients. .
[0022] As a further limitation of the first aspect of the present invention, the various types of financial data include: accounting vouchers, financial statements, bank statements, purchase orders and sales contracts.
[0023] As a further limitation of the first aspect of the present invention, a rule base is constructed, which includes at least transaction amount thresholds and transaction frequency restriction rules. For each cleaned and standardized piece of data in the original financial dataset, it is checked one by one whether it meets all the rules in the preset rule base.
[0024] Secondly, this invention provides an intelligent financial data anomaly audit system, comprising:
[0025] The preprocessing unit is configured to: collect various types of financial data from the enterprise, clean the collected data, standardize the cleaned data, and generate the original financial dataset.
[0026] The first identification unit is configured to: check each cleaned and standardized data in the original financial dataset to see if it meets all the rules in the preset rule base; if it does not meet a certain rule, it is marked as suspected abnormal data and a first suspected abnormal database is generated.
[0027] The second identification unit is configured to: for each cleaned and standardized data in the original financial dataset, obtain a score for each data based on the average path length of the data in the random binary tree and the theoretical value of the average path length when the sample size is n, and add data with scores greater than a set threshold to the second suspected anomaly database.
[0028] The third identification unit is configured to: combine the first suspected abnormal database and the second suspected abnormal database to obtain the final abnormal database; extract financial-related features to construct feature vectors for data that is not determined to be abnormal; use a support vector machine model to calculate the probability of belonging to various types of abnormalities; and add the corresponding data to the final abnormal database when the probability is greater than a set threshold.
[0029] The anomaly assessment unit is configured to determine the final severity assessment result of the anomaly based on the amount of the anomaly data, the weight of its importance to the business, and the coefficient of its impact on the financial situation.
[0030] Thirdly, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium;
[0031] A processor, adapted to execute computer programs;
[0032] A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the intelligent financial data anomaly auditing method as described in the first aspect of the present invention.
[0033] Fourthly, the present invention provides a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed as described in the first aspect of the present invention for auditing abnormal financial data.
[0034] Fifthly, the present invention provides a computer program product comprising a computer program that, when executed by a processor, implements the intelligent financial data anomaly auditing method as described in the first aspect of the present invention.
[0035] Compared with the prior art, the beneficial effects of the present invention are:
[0036] This invention innovatively proposes an intelligent method for auditing financial data anomalies. Through automated data collection, cleaning, standardization, and anomaly identification and analysis, the final severity assessment result of the anomalies in the final anomaly database is determined based on the amount of the anomalies, the weight of business importance, and the coefficient of impact on the financial situation. This greatly reduces the time and workload of manual operations, enabling financial data audits to be completed in a shorter time and improving the efficiency of audit work.
[0037] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0038] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.
[0039] Figure 1 This is a flowchart illustrating the intelligent financial data anomaly auditing method provided in Embodiment 1 of the present invention;
[0040] Figure 2 This is a schematic diagram of an intelligent financial data anomaly audit system provided in Embodiment 2 of the present invention;
[0041] Figure 3 This is a schematic diagram of a computer device provided in Embodiment 3 of the present invention. Detailed Implementation
[0042] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0043] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0044] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.
[0045] Example 1:
[0046] This implementation proposes an intelligent method for auditing anomalies in financial data, breaking through the bottleneck of processing massive amounts of financial data. It achieves rapid and accurate identification of anomalies, reducing the rates of missed and false detections. It constructs a scientific anomaly data analysis system to accurately determine the nature and severity of anomalies, providing a reliable basis for decision-making. Furthermore, it creates an automated and intelligent anomaly auditing process, improving audit efficiency and reducing labor costs and audit risks. More specifically, it includes the following processes:
[0047] S101: Data Acquisition and Preprocessing
[0048] S101-1: Data Acquisition.
[0049] Through API interfaces, direct database connections, and other methods, it interfaces with enterprise financial systems, ERP systems, and business systems to collect comprehensive financial data, including accounting vouchers, financial statements, bank statements, purchase orders, and sales contracts. Let the collected data set be... , Representing the There are n data points, where n is the total number of data points.
[0050] S101-2: Data cleaning.
[0051] Duplicate data is removed using a duplicate detection algorithm. For missing values, numerical data is imputed using either the mean (for missing values below 10%) or random forest regression (for missing values between 10% and 30%), depending on the missing value ratio. Non-numerical data is imputed using either the mode or association rule-based prediction. Let the cleaned dataset be... , where m is the amount of data after cleaning, and m≤n.
[0052] S101-3: Perform Z-score standardization on numerical data.
[0053] (1);
[0054] (2);
[0055] (3);
[0056] in, The mean, Standard deviation, The standardized values are designed to conform to a normal distribution with a mean of 0 and a standard deviation of 1. Non-numerical data are converted into numerical vectors using one-hot encoding.
[0057] S102: Abnormal data identification.
[0058] S102-1: Rule-based anomaly identification.
[0059] Build a rule base This includes rules covering transaction amount thresholds (e.g., a single purchase cannot exceed 5% of the annual budget) and transaction frequency limits (no more than 3 transactions per day with the same supplier). Each data Each data point is verified to ensure it conforms to the rules. Data that does not meet any of the rules is marked as potentially abnormal and grouped into a set. (That is, the first suspected abnormal database) This represents the number of suspected abnormal data.
[0060] S102-2: Anomaly detection based on machine learning.
[0061] from Extracting data to construct a training set Training the Isolation Forest algorithm requires data... Its path length in the random binary tree is Average path length The average path length is obtained by averaging the path lengths across multiple trees. The theoretical value for the average path length when the sample size is n is:
[0062] (4);
[0063] in, It is a harmonic number.
[0064] The formula for calculating the anomaly score is:
[0065] (5);
[0066] Set a threshold θ. Data exceeding the threshold θ are added to the second suspected anomaly database.
[0067] S103: Abnormal data analysis.
[0068] S103-1: Judgment of abnormal properties.
[0069] For data in the first and second suspected anomaly databases that were not identified as anomaly (denoted as...), ), extract features such as transaction amount, time, object, and business type to construct vectors, Using support vector machines The model calculates the probability of various anomalies (fraud, operational error, system error, etc.):
[0070] (6);
[0071] in, For the j-th type of anomaly property, q is the total number of anomaly categories, if data P in S′ ij Exceeding the threshold If so, it is considered abnormal.
[0072] S103-2: Assessment of the severity of the anomaly.
[0073] Constructing an evaluation model:
[0074] (7);
[0075] in, For abnormal data amounts, Assigning weights based on business importance. The impact coefficient on financial condition, , and All are weighting coefficients. ,according to Classification by severity level: This is a serious abnormality. This is a relatively serious abnormality. This is a general abnormality.
[0076] S104: Abnormal data handling.
[0077] For general anomalies, such as data entry errors, the system automatically corrects them and automatically deletes duplicate data. For more serious and severe anomalies, a report containing details of the anomaly, its nature, and severity is generated and pushed to finance and audit personnel for review and processing. The processing results are fed back to the system to update the data. The system tracks the processing results, analyzes the impact on the financial situation, and optimizes the parameters of the anomaly identification model, adjusts the analysis algorithm, and updates the processing rules accordingly.
[0078] Example 2:
[0079] like Figure 2 As shown, this implementation provides an intelligent financial data anomaly audit system, including:
[0080] The preprocessing unit is configured to: collect various types of financial data from the enterprise, clean the collected data, standardize the cleaned data, and generate the original financial dataset.
[0081] The first identification unit is configured to: check each cleaned and standardized data in the original financial dataset to see if it meets all the rules in the preset rule base; if it does not meet a certain rule, it is marked as suspected abnormal data and a first suspected abnormal database is generated.
[0082] The second identification unit is configured to: for each cleaned and standardized data in the original financial dataset, obtain a score for each data based on the average path length of the data in the random binary tree and the theoretical value of the average path length when the sample size is n, and add data with scores greater than a set threshold to the second suspected anomaly database.
[0083] The third identification unit is configured to: combine the first suspected abnormal database and the second suspected abnormal database to obtain the final abnormal database; extract financial-related features to construct feature vectors for data that is not determined to be abnormal; use a support vector machine model to calculate the probability of belonging to various types of abnormalities; and add the corresponding data to the final abnormal database when the probability is greater than a set threshold.
[0084] The anomaly assessment unit is configured to determine the final severity assessment result of the anomaly based on the amount of the anomaly data, the weight of its importance to the business, and the coefficient of its impact on the financial situation.
[0085] The specific working process of each of the above units is described in Example 1, and will not be repeated here.
[0086] It is understood that the aforementioned units can be individually or entirely merged into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of this application. The aforementioned units are based on logical functional division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the system may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.
[0087] According to another embodiment of this application, the system described in this embodiment, and the method of embodiment 1 of this application, can be constructed and the method of embodiment 1 of this application implemented by running a computer program (including program code) capable of performing the steps involved in the corresponding method described in embodiment 1 on a general-purpose computing device including processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, loaded into the aforementioned computing device through the computer-readable recording medium, and run therein.
[0088] Example 3:
[0089] like Figure 3 As shown, this implementation provides an electronic device including a processor 1001, a communication interface 1002, and a computer-readable storage medium 1003. The processor 1001, communication interface 1002, and computer-readable storage medium 1003 can be connected via a bus or other means.
[0090] The communication interface 1002 is used to receive and send data. The computer-readable storage medium 1003 can be stored in the memory of the electronic device. The computer-readable storage medium 1003 is used to store computer programs, which include program instructions. The processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.
[0091] The processor 1001 (or CPU (Central Processing Unit)) is the computing and control core of electronic devices. It is suitable for implementing one or more instructions, specifically for loading and executing one or more instructions to achieve corresponding methods or functions.
[0092] The processor 1001 is configured to perform the following process:
[0093] Collect various types of financial data from enterprises, clean the collected data, standardize the cleaned data, and generate the original financial dataset.
[0094] For each cleaned and standardized data in the original financial dataset, check whether it meets all the rules in the preset rule base. If it does not meet a certain rule, mark it as suspected abnormal data and generate the first suspected abnormal database.
[0095] For each cleaned and standardized data point in the original financial dataset, a score is obtained based on the average path length of the data in the random binary tree and the theoretical value of the average path length when the sample size is n. Data points with scores greater than a set threshold are added to the second suspected anomaly database.
[0096] The first and second suspected anomaly databases are combined to obtain the final anomaly database. For data that is not identified as anomaly, financial features are extracted to construct feature vectors. The probability of belonging to each type of anomaly is calculated using a support vector machine model. When the probability is greater than a set threshold, the corresponding data is added to the final anomaly database.
[0097] The final severity assessment of the anomalies is determined based on the amount of the anomalies, their importance to the business, and their impact on the financial situation.
[0098] The specific working process is described in Example 1 and will not be repeated here.
[0099] Example 4:
[0100] This implementation provides a computer-readable storage medium (Memory), which is a memory device in an electronic device used to store programs and data. It is understood that the computer-readable storage medium here can include both built-in storage media in the electronic device and extended storage media supported by the electronic device. The computer-readable storage medium provides storage space that stores the processing system of the electronic device.
[0101] Furthermore, this storage space also contains one or more instructions suitable for loading and execution by the processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM memory or unstable memory, such as at least one disk storage device; optionally, it can also be at least one computer-readable storage medium located remotely from the aforementioned processor.
[0102] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to perform the following process:
[0103] Collect various types of financial data from enterprises, clean the collected data, standardize the cleaned data, and generate the original financial dataset.
[0104] For each cleaned and standardized data in the original financial dataset, check whether it meets all the rules in the preset rule base. If it does not meet a certain rule, mark it as suspected abnormal data and generate the first suspected abnormal database.
[0105] For each cleaned and standardized data point in the original financial dataset, a score is obtained based on the average path length of the data in the random binary tree and the theoretical value of the average path length when the sample size is n. Data points with scores greater than a set threshold are added to the second suspected anomaly database.
[0106] The first and second suspected anomaly databases are combined to obtain the final anomaly database. For data that is not identified as anomaly, financial features are extracted to construct feature vectors. The probability of belonging to each type of anomaly is calculated using a support vector machine model. When the probability is greater than a set threshold, the corresponding data is added to the final anomaly database.
[0107] The final severity assessment of the anomalies is determined based on the amount of the anomalies, their importance to the business, and their impact on the financial situation.
[0108] The specific working process is described in Example 1 and will not be repeated here.
[0109] Example 5:
[0110] This implementation provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the following process:
[0111] Collect various types of financial data from enterprises, clean the collected data, standardize the cleaned data, and generate the original financial dataset.
[0112] For each cleaned and standardized data in the original financial dataset, check whether it meets all the rules in the preset rule base. If it does not meet a certain rule, mark it as suspected abnormal data and generate the first suspected abnormal database.
[0113] For each cleaned and standardized data point in the original financial dataset, a score is obtained based on the average path length of the data in the random binary tree and the theoretical value of the average path length when the sample size is n. Data points with scores greater than a set threshold are added to the second suspected anomaly database.
[0114] The first and second suspected anomaly databases are combined to obtain the final anomaly database. For data that is not identified as anomaly, financial features are extracted to construct feature vectors. The probability of belonging to each type of anomaly is calculated using a support vector machine model. When the probability is greater than a set threshold, the corresponding data is added to the final anomaly database.
[0115] The final severity assessment of the anomalies is determined based on the amount of the anomalies, their importance to the business, and their impact on the financial situation.
[0116] The specific working process is described in Example 1 and will not be repeated here.
[0117] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0118] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).
[0119] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. An intelligent method for auditing anomalies in financial data, characterized in that, The process includes the following: Collect various types of financial data from enterprises, clean the collected data, standardize the cleaned data, and generate the original financial dataset. For each cleaned and standardized data in the original financial dataset, check whether it meets all the rules in the preset rule base. If it does not meet a certain rule, mark it as suspected abnormal data and generate the first suspected abnormal database. For each cleaned and standardized data point in the original financial dataset, a score is obtained based on the average path length of the data in the random binary tree and the theoretical value of the average path length when the sample size is n. Data points with scores greater than a set threshold are added to the second suspected anomaly database. The first and second suspected anomaly databases are combined to obtain the final anomaly database. For data that is not identified as anomaly, financial features are extracted to construct feature vectors. The probability of belonging to each type of anomaly is calculated using a support vector machine model. When the probability is greater than a set threshold, the corresponding data is added to the final anomaly database. The final severity assessment of the anomalies is determined based on the amount of the anomalies, their importance to the business, and their impact on the financial situation.
2. The intelligent financial data anomaly auditing method as described in claim 1, characterized in that, The score for the i-th data point is: ； in, This is the theoretical value for the average path length when the sample size is n. Let be the average path length of the i-th data item in the random binary tree. This represents the i-th data item in the original financial dataset.
3. The intelligent financial data anomaly auditing method as described in claim 2, characterized in that, The theoretical value of the average path length when the sample size is n is: ； in, It is a harmonic number.
4. The intelligent financial data anomaly auditing method as described in claim 1, characterized in that, Based on the amount of the abnormal data, the weight of its business importance, and the coefficient of its impact on the financial situation, the final assessment result of the severity of the abnormality of the i-th abnormal data is determined. ,include: ； in, For abnormal data amounts, Assigning weights based on business importance. The impact coefficient on financial condition, , and All are weighting coefficients. .
5. The intelligent financial data anomaly auditing method as described in claim 1, characterized in that, The various types of financial data include: accounting vouchers, financial statements, bank statements, purchase orders, and sales contracts.
6. The intelligent financial data anomaly auditing method as described in claim 1, characterized in that, Build a rule base that includes at least transaction amount thresholds and transaction frequency limits. For each cleaned and standardized piece of data in the original financial dataset, check whether it meets all the rules in the preset rule base.
7. An intelligent financial data anomaly audit system, characterized in that, include: The preprocessing unit is configured to: collect various types of financial data from the enterprise, clean the collected data, standardize the cleaned data, and generate the original financial dataset. The first identification unit is configured to: check each cleaned and standardized data in the original financial dataset to see if it meets all the rules in the preset rule base; if it does not meet a certain rule, it is marked as suspected abnormal data and a first suspected abnormal database is generated. The second identification unit is configured to: for each cleaned and standardized data in the original financial dataset, obtain a score for each data based on the average path length of the data in the random binary tree and the theoretical value of the average path length when the sample size is n, and add data with scores greater than a set threshold to the second suspected anomaly database. The third identification unit is configured to: combine the first suspected abnormal database and the second suspected abnormal database to obtain the final abnormal database; extract financial-related features to construct feature vectors for data that is not determined to be abnormal; use a support vector machine model to calculate the probability of belonging to various types of abnormalities; and add the corresponding data to the final abnormal database when the probability is greater than a set threshold. The anomaly assessment unit is configured to determine the final severity assessment result of the anomaly based on the amount of the anomaly data, the weight of its importance to the business, and the coefficient of its impact on the financial situation.
8. A computer device, characterized in that, include: Processor and computer-readable storage media; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the intelligent financial data anomaly auditing method as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed as described in any one of claims 1 to 6.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the intelligent financial data anomaly auditing method as described in any one of claims 1 to 6.