Financial file analysis method and device and storage medium
Through the financial document analysis method, the problem of manual participation in financial data automation technology is solved, and the rapid audit and early warning of financial data is realized, work efficiency is improved, and manual dependence and error rate are reduced.
Patent Information
- Application Number
- CN202411527894.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-30
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the existing financial data automation technology, data conversion, auditing and early warning triggering still require manual participation, resulting in an increase in the risk of inefficiency and human error.
Provide a financial document analysis method, by receiving financial documents, judging its format, adjusting the row and column of the table or OCR identification, generating standardized reports, and performing verification and analysis items based on preset audit rules to reduce manual dependence and achieve rapid audit and early warning.
It improves the degree of automation of financial data processing, reduces manual intervention, reduces error rate, improves work efficiency, and achieves rapid audit and early warning of financial data.
Smart Images

Figure CN119047715A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of financial analysis, and in particular to an analysis method, device and storage medium for financial documents. Background Art
[0002] As enterprises expand in size and their businesses become more complex, the processing and analysis of financial statements has become increasingly arduous. Traditional financial statement processing methods mainly rely on manual operations, which are inefficient and prone to errors. In this situation, enterprises need more efficient and accurate solutions to cope with the growing volume and complexity of data. Therefore, many companies have begun to turn to automated and digital financial statement processing tools, such as enterprise resource planning (ERP) systems, accounting software, and advanced data analysis platforms.
[0003] These tools can automate data entry, classification and reporting processes, reduce manual intervention, thereby reducing error rates and improving work efficiency. Through integrated financial systems, companies can monitor financial status in real time, quickly generate financial statements, and conduct in-depth financial analysis. In addition, using big data analysis and artificial intelligence technology, companies can more accurately predict financial trends and make more informed decisions.
[0004] However, with the development of technology, enterprises are also facing new challenges. In the processing of financial data automation systems in existing technologies, human participation is highly relied on. In the entire process, especially in data conversion, auditing, and early warning triggering, human participation and intervention may still be required. This high degree of manual dependence not only reduces work efficiency, but also increases the risk of human error. Therefore, in view of the problem that human participation is still required in data conversion, auditing, and early warning triggering in the current financial data automation technology, a technology is needed to solve the current technical problems. Summary of the invention
[0005] The main purpose of the present invention is to solve the technical problem that in the current financial data automation technology, human participation is still required in the links of data conversion, auditing and early warning triggering.
[0006] A first aspect of the present invention provides a method for analyzing financial documents, the method comprising: receiving financial documents; Determine whether the financial document is an Excel format report; When the report is in Excel format, the financial document is adjusted in rows and columns according to a preset subject adjustment algorithm to obtain a standardized report; When the report is not in Excel format, the financial document is traversed and recognized according to a preset OCR recognition algorithm to obtain sorting recognition data and row and column vectors corresponding to the sorting recognition data, and the sorting recognition data is written into a preset result matrix frame according to the row and column vectors to obtain a recognition result matrix; Based on the preset standard subject sorting, the identification result matrix is sorted, adjusted and converted to obtain a standardized report; According to the preset audit rules, the standardized reports are checked and analyzed item by item to obtain audit analysis data.
[0007] Optionally, in a first implementation of the first aspect of the present invention, the traversing and recognizing the financial document according to a preset OCR recognition algorithm to obtain the sorting recognition data and the row and column vectors corresponding to the sorting recognition data include: Based on the preset read_model function, access the address path of the financial file to obtain the access result; When the access result is valid, based on the preset read_keys function, the data in the address path of the financial file is traversed and extracted to generate a key vector; Based on the preset scoreToTextLine function, text conversion processing is performed on the key vector to generate sorting identification data and row and column vectors corresponding to the sorting identification data.
[0008] Optionally, in a second implementation of the first aspect of the present invention, the step of performing table row and column adjustment processing on the financial document according to a preset subject adjustment algorithm to obtain a standardized report includes: Based on the preset standard subject sorting, the subject rows of the financial file are sorted and adjusted to obtain a financial sorting file; According to the preset financial template, the financial sorting file is subjected to matrix replacement processing to obtain a standardized report.
[0009] Optionally, in a third implementation of the first aspect of the present invention, the sorting based on preset standard subjects, performing sorting adjustment and conversion processing on the recognition result matrix to obtain a standardized report includes: Based on the preset standard subject sorting, the subject rows and columns of the recognition result matrix are sorted and adjusted to obtain a recognition sorting matrix; The identification and sorting matrix is converted into an Excel table to generate a standardized report.
[0010] Optionally, in a fourth implementation of the first aspect of the present invention, after the standardized report is checked and analyzed item by item according to the preset audit rules to obtain the audit analysis data, the method further includes: Summarizing and arranging the abnormal data of the audit analysis data to obtain audit abnormal data; The audit exception data is visually converted to generate visual data, and the visual data is sent to a preset display port to visually display the audit exceptions in the financial document.
[0011] Optionally, in a fifth implementation of the first aspect of the present invention, after sending the visualization data to a preset display port so as to visually display the audit anomaly in the financial document, the method further includes: Receive action annotation instructions from users; According to the measure marking instruction, the visual data is marked and processed to generate visual data with measure markings.
[0012] Optionally, in a sixth implementation of the first aspect of the present invention, before the standardized report is checked and analyzed item by item according to the preset audit rules to obtain the audit analysis data, the method further includes: Receive the user's audit setting command; According to the audit setting command, the financial data in the preset audit rules and the early warning supervision threshold corresponding to the financial data are adjusted to generate new audit rules.
[0013] Optionally, in a seventh implementation manner of the first aspect of the present invention, determining whether the financial file is an Excel format report includes: Read the file header of the financial file to obtain the file header characters; Determine whether the file header characters are characters corresponding to the Excel format report.
[0014] A second aspect of the present invention provides an analysis device for financial documents, comprising: a memory and at least one processor, wherein the memory stores instructions, and the memory and the at least one processor are interconnected via a line; the at least one processor calls the instructions in the memory so that the analysis device for financial documents executes the above-mentioned analysis method for financial documents.
[0015] A third aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned financial document analysis method.
[0016] In the embodiment of the present invention, it is first necessary to analyze whether the financial document is an Excel table. When the financial document is not an Excel table, the financial document is subjected to OCR recognition, and the OCR recognition data is converted to a standard format to obtain a standard report. When the financial document is an Excel table, the financial document is converted to a standard format to obtain a standard report. According to the preset audit rules, the standard report is audited and early-warning processed, reducing manual dependence and improving work efficiency, realizing rapid review and early warning of financial data, and solving the technical problem that manual participation is still required in data conversion, auditing and early-warning triggering in the current financial data automation technology. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 A schematic diagram of an embodiment of a method for analyzing financial documents in an embodiment of the present invention; Figure 2 It is a schematic diagram of an embodiment of step 103 of the method for analyzing financial documents in an embodiment of the present invention; Figure 3 A schematic diagram of an embodiment of step 104 of the method for analyzing financial documents in an embodiment of the present invention; Figure 4 It is a schematic diagram of an embodiment of step 105 of the method for analyzing financial documents in an embodiment of the present invention; Figure 5 Schematic diagram of an embodiment of a financial document analysis device in an embodiment of the present invention. DETAILED DESCRIPTION
[0018] The embodiments of the present invention provide a method, a device and a storage medium for analyzing a financial document.
[0019] The embodiments disclosed in the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments disclosed in the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments disclosed in the present invention are only for exemplary purposes and are not intended to limit the scope of protection disclosed in the present invention.
[0020] In the description of the embodiments disclosed in the present invention, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.
[0021] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 An embodiment of the method for analyzing financial documents in the embodiment of the present invention includes: 101. Receiving financial documents; In this embodiment, financial documents are actually input from multiple sources, such as Excel, PDF, pictures, paper, etc. Not all data from sources such as Excel, PDF, pictures, and paper can be directly processed automatically, because financial documents have problems such as incompatible data formats and incompatible file content formats. Financial documents need to be standardized before they can be input into pre-set audit rules for auditing and obtaining audit results.
[0022] 102. Determine whether the financial document is an Excel format report; In this embodiment, whether the financial file is an Excel format report can be analyzed by reading the file name suffix of the financial file. When the file name suffix of the financial file is a format table such as .xls, .xlsx, .xlsm, .xlsb, .xltx, .xltm, etc., it means that the financial file is Excel table data. If the financial file has other types of suffixes, it is considered that it is not Excel table data.
[0023] Specifically, step 102 also includes the following specific implementation methods: 1021. Read the file header of the financial file to obtain the file header characters; 1022. Determine whether the file header characters are characters corresponding to the Excel format report.
[0024] In steps 1021-1022, the file header of the financial file is read to obtain the file header characters. For Excel format files, there are specific file headers, for example: .xls files usually start with D0 CF 11 E0 A1 B1 1A E1, and .xlsx files start with 50 4B 03 04. It is determined whether the file header characters belong to specific bytes to determine whether the financial file is in Excel format.
[0025] 103. When the report is in Excel format, the financial document is adjusted in terms of table rows and columns according to a preset subject adjustment algorithm to obtain a standardized report; In this embodiment, if the financial file is an Excel report, the table data of the financial file is not necessarily in the subject order of the standard file. For example, the table data that can be audited is set as the financial subjects with vertical subjects A, B, C, D, E, and the subject order of the financial file is: E, C, A, D, B. The subject order of the financial file is not standard, and the subject order and the data corresponding to the subject need to be adjusted. After adjusting the subject order of the financial file, a standardized report data is obtained.
[0026] For details, please refer to Figure 2 , Figure 2 This is an embodiment of step 103 of the method for analyzing financial documents in an embodiment of the present invention, and step 103 includes the following specific implementation methods: 1031. Based on the preset standard subject sorting, the subject rows of the financial file are sorted and adjusted to obtain a financial sorting file; 1032. Perform matrix replacement processing on the financial sorting file according to a preset financial template to obtain a standardized report.
[0027] In steps 1031-1032, the financial accounts with vertical accounts A, B, C, D, and E are first queried, and then the financial accounts and corresponding account data of the financial file are sorted and adjusted to obtain a financial sorting file. Then, since the financial file may be a table of horizontal accounts and financial data corresponding to the horizontal accounts, the matrix of the financial data and the report matrix in the standard format are in an inverted relationship. Therefore, it is necessary to perform matrix format verification on the data of the financial sorting file, and perform matrix replacement processing on the financial sorting file that does not conform to the matrix format to obtain a standardized report.
[0028] 104. When the report is not in Excel format, the financial document is traversed and recognized according to a preset OCR recognition algorithm to obtain sorting recognition data and row and column vectors corresponding to the sorting recognition data, and the sorting recognition data is written into a preset result matrix frame according to the row and column vectors to obtain a recognition result matrix; In this embodiment, if the financial file is not in Excel format, it is necessary to use the OCR recognition algorithm to recognize each page of the financial file one by one, and obtain the identification characters and the indication vectors of the rows and columns where the identification characters are located. When using the OCR recognition algorithm, the API interface of existing algorithms such as the CRNN algorithm, CNN+Seq2Seq+Attention algorithm, and CTPN algorithm can be used to perform the recognition process to achieve the corresponding data conversion of financial files in PDF and image formats. Based on the recognition row and column vectors, the sorted recognition data is written into the preset result matrix framework to obtain the recognition result matrix.
[0029] For details, please refer to Figure 3 , Figure 3 This is an embodiment of step 104 of the method for analyzing financial documents in an embodiment of the present invention, and step 104 includes the following specific implementation methods: 1041. Based on the preset read_model function, access the address path of the financial file to obtain an access result; 1042. When the access result is valid, based on the preset read_keys function, character traversal and extraction are performed on the data in the address path of the financial file to generate a key vector; 1043. Based on the preset scoreToTextLine function, perform text conversion processing on the key vector to generate sorting identification data and row and column vectors corresponding to the sorting identification data.
[0030] In steps 1041-1043, to achieve docking with the external algorithm, it is necessary to first perform character traversal and extraction of the data in the address path of the financial file based on the preset read_keys function to generate a key vector. For example: int CrnnNet::read_model(std::string param_path, std::string bin_path, std::string key_path, bool use_gpu) { / / ... return true; } The read_keys function accepts the model parameter file path, the model binary file path, the key (category) file path, and a boolean value to decide whether to use the GPU to call the OCR algorithm.
[0031] When the access file has been identified, the read_keys function is used to perform character traversal and extraction on the data in the address path of the financial file to generate a key vector, for example: int CrnnNet::read_keys(std::string key_path) { / / ... return keys.size(); } The read_keys function is used to read a set of characters from the specified path and store them in a key vector.
[0032] Finally, based on the scoreToTextLine function, the key vector is subjected to text conversion processing to generate sorting identification data and row and column vectors corresponding to the sorting identification data, for example: TextLine CrnnNet::scoreToTextLine(const std::vector <float>&outputData, int h, int w) { / / ... return { strRes, scores}; } The output of the model is converted into text lines and the characters are concatenated to form strings, which together form the sorted recognition data with row and column vectors specifying the position of the characters.
[0033] 105. Based on the preset standard subject sorting, the recognition result matrix is sorted, adjusted and converted to obtain a standardized report; In this embodiment, since the data format of the identification matrix follows the content in the pdf file or the image file, it is necessary to adjust the subject sorting of the identification matrix data and to perform matrix format verification and replacement to obtain a matrix data that meets the audit standards. Then, the matrix is converted in format to obtain a standardized report that meets the audit standards.
[0034] For details, please refer to Figure 4 , Figure 4 This is an embodiment of step 105 of the method for analyzing financial documents in an embodiment of the present invention, and step 105 includes the following specific implementation methods: 1051. Based on the preset standard subject sorting, sort and adjust the subject rows and columns of the recognition result matrix to obtain a recognition sorting matrix; 1052. Convert the identification and sorting matrix into an Excel table to generate a standardized report.
[0035] In steps 1051-1052, the financial accounts A, B, C, D, and E are first used to sort the account order of the recognition result matrix, and then the rows and columns of the matrix are checked to see if they need to be replaced, and the matrix data is replaced by standard processing to obtain the recognition sorting matrix. The recognition sorting matrix is formatted and converted into an Excel table to obtain a standardized report.
[0036] 106. According to the preset audit rules, the standardized reports are checked and analyzed item by item to obtain audit analysis data.
[0037] In this embodiment, audit rules are used, such as early warning indicators year-on-year, financial management indicators, business indicators, cost and expense indicators, red and yellow regulatory thresholds, custom calculation formulas and other data, to check and analyze standardized reports one by one. The system imports the converted structured data into the audit rule library and compares it with the preset accounting subjects, end-of-period and beginning-of-period rules to discover potential financial problems. When the indicator changes beyond the set range, the system automatically triggers the corresponding management measures. The system supports the analysis of indicators in multiple dimensions such as financial management, business operations and cost and expenses to comprehensively evaluate the financial status and operating conditions of the enterprise. Based on the above analysis process, the standardized reports are analyzed one by one to obtain audit analysis data.
[0038] Specifically, before step 106, the following specific implementation methods are also included: 1061. Receive the audit setting command from the user; 1062. According to the audit setting command, the financial data in the preset audit rules and the early warning supervision threshold corresponding to the financial data are adjusted to generate new audit rules.
[0039] In steps 1061-1062, before the audit rules are checked, the user can set the audit rules. Through the audit setting command, the financial data items of the audit rules and the early warning supervision values corresponding to the financial data items are adjusted to generate new audit rules to meet the specific needs of different enterprises.
[0040] Specifically, after step 106, the following specific implementation methods are also included: 1063. Summarize and organize the abnormal data of the audit analysis data to obtain audit abnormal data; 1064. Visually convert the audit exception data to generate visualization data, and send the visualization data to a preset display port to visually display the audit exceptions in the financial document.
[0041] In steps 1063-1064, the abnormal data of the audit analysis data are summarized and then visualized in the form of a large-screen display or data warehouse for review and analysis by regulators.
[0042] Specifically, after step 1064, the following specific implementation methods are also included: 10641. Receive a user's action marking instruction; 10642. According to the measure marking instruction, mark and add processing are performed on the visual data to generate visual data with measure markings.
[0043] In steps 10641-10642, the user's annotation instructions such as measures and solutions for each abnormal data are received. Based on the measures annotation instructions, the measures annotation and solution annotation information are added to the visual data to obtain visual data with measures marks so that it can be flexibly displayed and modified.
[0044] In the embodiment of the present invention, it is first necessary to analyze whether the financial document is an Excel table. When the financial document is not an Excel table, the financial document is subjected to OCR recognition, and the OCR recognition data is converted to a standard format to obtain a standard report. When the financial document is an Excel table, the financial document is converted to a standard format to obtain a standard report. According to the preset audit rules, the standard report is audited and early-warning processed, reducing manual dependence and improving work efficiency, realizing rapid review and early warning of financial data, and solving the technical problem that manual participation is still required in data conversion, auditing and early-warning triggering in the current financial data automation technology.
[0045] Figure 5 1 is a schematic diagram of the structure of a financial document analysis device provided by an embodiment of the present invention. The financial document analysis device 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 510 (for example, one or more processors) and a memory 520, and one or more storage media 530 (for example, one or more mass storage devices) storing application programs 533 or data 532. Among them, the memory 520 and the storage medium 530 may be temporary storage or permanent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the financial document analysis device 500. Furthermore, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the financial document analysis device 500.
[0046] The financial document-based analysis device 500 may further include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input and output interfaces 560, and / or one or more operating systems 531, such as Windows Serve, Mac OS X, Unix, Linux, Free BSD, etc. It will be appreciated by those skilled in the art that Figure 5 The structure of the analysis device for financial documents shown does not constitute a limitation on the analysis device based on financial documents, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0047] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the financial document analysis method.
[0048] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0049] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.
[0050] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.< / float>
Claims
1. A method for analyzing financial documents, characterized in that: Includes steps: receiving financial documents; Determine whether the financial document is an Excel format report; When the report is in Excel format, the financial document is adjusted in rows and columns according to a preset subject adjustment algorithm to obtain a standardized report; When the report is not in Excel format, the financial document is traversed and recognized according to a preset OCR recognition algorithm to obtain sorting recognition data and row and column vectors corresponding to the sorting recognition data, and the sorting recognition data is written into a preset result matrix frame according to the row and column vectors to obtain a recognition result matrix; Based on the preset standard subject sorting, the identification result matrix is sorted, adjusted and converted to obtain a standardized report; According to the preset audit rules, the standardized reports are checked and analyzed item by item to obtain audit analysis data.
2. The method for analyzing financial documents according to claim 1, characterized in that: The traversal recognition of the financial document according to the preset OCR recognition algorithm to obtain the sorting recognition data and the row and column vectors corresponding to the sorting recognition data include: Based on the preset read_model function, access the address path of the financial file to obtain the access result; When the access result is valid, based on the preset read_keys function, the data in the address path of the financial file is traversed and extracted to generate a key vector; Based on the preset scoreToTextLine function, text conversion processing is performed on the key vector to generate sorting identification data and row and column vectors corresponding to the sorting identification data.
3. The method for analyzing financial documents according to claim 1, characterized in that: The process of adjusting the table rows and columns of the financial document according to the preset subject adjustment algorithm to obtain a standardized report includes: Based on the preset standard subject sorting, the subject rows of the financial file are sorted and adjusted to obtain a financial sorting file; According to the preset financial template, the financial sorting file is subjected to matrix replacement processing to obtain a standardized report.
4. The method for analyzing financial documents according to claim 1, characterized in that: The sorting adjustment and conversion processing of the recognition result matrix based on the preset standard subject sorting to obtain the standardized report includes: Based on the preset standard subject sorting, the subject rows and columns of the recognition result matrix are sorted and adjusted to obtain a recognition sorting matrix; The identification and sorting matrix is converted into an Excel table to generate a standardized report.
5. The method for analyzing financial documents according to claim 1, characterized in that: After the standardized report is checked and analyzed item by item according to the preset audit rules to obtain the audit analysis data, the following is further included: Summarizing and arranging the abnormal data of the audit analysis data to obtain audit abnormal data; The audit exception data is visually converted to generate visual data, and the visual data is sent to a preset display port to visually display the audit exceptions in the financial document.
6. The method for analyzing financial documents according to claim 5, characterized in that: After sending the visualization data to a preset display port so as to visualize the audit anomalies in the financial document, the method further includes: Receive action annotation instructions from users; According to the measure marking instruction, the visual data is marked and processed to generate visual data with measure markings.
7. The method for analyzing financial documents according to claim 1, characterized in that: Before the standardized report is checked and analyzed item by item according to the preset audit rules to obtain the audit analysis data, the method further includes: Receive the user's audit setting command; According to the audit setting command, the financial data in the preset audit rules and the early warning supervision threshold corresponding to the financial data are adjusted to generate new audit rules.
8. The method for analyzing financial documents according to claim 1, characterized in that: The determining whether the financial file is an Excel format report comprises: Read the file header of the financial file to obtain the file header characters; Determine whether the file header characters are characters corresponding to the Excel format report.
9. An analysis device for financial documents, characterized in that: The financial document analysis device comprises: a memory and at least one processor, the memory stores instructions, and the memory and the at least one processor are interconnected via a line; The at least one processor calls the instructions in the memory to enable the financial document analysis device to perform the financial document analysis method according to any one of claims 1-8.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for analyzing financial documents according to any one of claims 1 to 8 is implemented.
Citation Information
Patent Citations
Tax declaration form generation method, device and equipment
CN110347998A
Report file processing method and device and electronic equipment
CN117709317A
Financial data auditing tool
CN117974333A
Cited By
Money report key information extraction method and system
CN120198928A
