Financial intelligent auditing method and system for enterprise financial accounting
By converting financial information in a unified format and performing intelligent audits based on the audit rule database, the problems of low efficiency and high risks in manual audits in traditional financial management are solved, and financial intelligent audits are realized, efficiency and quality are improved, and risks are reduced.
Patent Information
- Application Number
- CN202411893880.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-20
- Publication Date
- 2025-04-11
AI Technical Summary
Under the traditional financial management model, financial personnel need to manually review a large number of financial documents, resulting in large workload, low efficiency, high personnel costs, and risks of missed or misinterpreted review, making it difficult to effectively control financial risks.
After converting the financial information of multiple parties in a unified format, the financial information converted by multiple parties in a unified format corresponding to the financial document information to be reviewed will be retrieved, and a preliminary review will be conducted based on the pre-established audit rule base, and the subsequent audit process will be determined and implemented, including the refilling process and/or manual audit process until the final audit result of the financial document is obtained.
It has realized financial intelligent auditing, improved the efficiency and quality of financial work, reduced manual operations, reduced human operation risks, improved the financial audit automation rate and financial risk control capabilities, effectively avoiding the risks of missed audits and missed audits.
Smart Images

Figure CN119809559A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer processing, and in particular to a financial intelligent audit method for enterprise financial accounting, a financial intelligent audit system for enterprise financial accounting, a machine-readable storage medium and an electronic device. Background Art
[0002] Under the traditional financial management model, employees submit various types of expense reimbursement, purchase settlement and other reimbursement documents, which require financial personnel to manually review documents. Due to the large number of document types and invoices and other attachments, there are many practical problems such as large workload, low efficiency, high personnel costs, missed and wrong manual review, lengthy approval process, and repeated processes. The financial departments and financial shared centers of various units bear huge pressure on document review. The number of financial review documents surges at the end of the month and the end of the year, and the review timeliness, quality and risks face great challenges. Under the manual review model of financial personnel, financial risks are difficult to be effectively controlled. In addition, manual review makes it impossible to centralize, standardize, unify and complete the business content. Different financial personnel have different review standards, which leads to the inability to completely unify the review standards and content. It is easy to make mistakes and there is a risk of missed and wrong review when relying entirely on manual review of a large number of supporting documents such as data tables, charts, texts, and images.
[0003] With the progress of the times and the development of information technology, technologies such as artificial intelligence are deeply applied in the financial field, bringing opportunities for the intelligent and transformation development of financial management. In the context of financial digital transformation, it is urgent to carry out financial intelligent innovation and explore new models of financial intelligent auditing. Through the intelligent audit of documents, bills, contracts and other contents, the financial audit work model can be reshaped. The complexity of financial documents and the diversity of rules also put forward higher requirements for audit analysis. Therefore, how to use intelligent information technology to improve the efficiency and quality of financial work while avoiding the risks of missed audits and wrong audits is an urgent problem to be solved. Summary of the invention
[0004] The purpose of the embodiments of the present invention is to provide a financial intelligent audit method and system for enterprise financial accounting, so as to at least solve the above-mentioned problem of how to use intelligent information technology to improve the efficiency and quality of financial work while avoiding the risks of missed audits and wrong audits.
[0005] In order to achieve the above-mentioned object, the present invention provides a financial intelligent audit method for enterprise financial accounting in a first aspect, comprising:
[0006] After converting the acquired multi-party financial information into a unified format, retrieve the converted multi-party financial information in a unified format corresponding to the financial document information to be reviewed;
[0007] Based on the pre-established audit rule base and the multi-party financial information converted into a unified format corresponding to the financial document information to be audited, the corresponding preliminary audit results of the financial documents are obtained;
[0008] Based on the preliminary audit results of the corresponding financial documents, determine and execute the subsequent audit process to obtain the final audit results of the financial documents;
[0009] The subsequent review process includes at least a re-submission process and / or a manual review process.
[0010] Optionally, the above-mentioned multi-party financial information includes at least external financial information, system financial information and internal financial information;
[0011] The rules for obtaining financial information from multiple parties include:
[0012] Recover multiple document information and multiple image data collected by multiple preset accounting systems, and perform text information recognition of each document information based on OCR;
[0013] Perform structured data conversion on the text information recognition results of each document information and multiple image data to obtain external financial information;
[0014] Establish connections between multiple preset financial information systems and integrate data of multiple preset financial information systems to obtain system financial information;
[0015] Based on the identity information of the reimbursement user corresponding to each document information, the characteristic attributes of the reimbursement user corresponding to each document information are shared and reused to obtain internal financial information.
[0016] Optionally, the audit rule library includes a plurality of expected results corresponding to each preset audit file type;
[0017] The above-mentioned multi-party financial information converted into a unified format based on the pre-established audit rule base and the financial document information to be audited obtains the corresponding preliminary audit results of the financial documents, including:
[0018] Based on the pre-established audit rule library, the financial information of multiple parties converted into a unified format corresponding to the financial document information to be audited is analyzed and summarized in turn to obtain the corresponding actual results;
[0019] Compare and analyze the corresponding actual results with multiple expected results corresponding to the file type of the financial document information to be audited to determine the preliminary audit results of the financial documents.
[0020] Optionally, based on the preliminary review results of the corresponding financial documents, the subsequent review process is determined and executed, including:
[0021] In the case where the subsequent review process is determined to be a re-submission process, when the preliminary review result of the financial document is that the corresponding financial document information to be reviewed contains content that does not comply with the review rules in the review rule library, a re-submission instruction is sent based on the preliminary review result of the corresponding financial document and the financial document information to be reviewed, and the re-submitted financial document information to be reviewed is collected;
[0022] When it is determined that the subsequent audit process is a manual audit process, when the preliminary audit result of the financial document is that the corresponding financial document information to be audited contains content that does not comply with the audit rules in the audit rule library, a warning prompt message and a manual audit instruction are sent based on the corresponding preliminary audit result of the financial document and the financial document information to be audited.
[0023] Optionally, after obtaining the final audit result of the financial document, the method further includes:
[0024] Summarize and classify the final audit results of financial documents according to the preset audit category dimensions;
[0025] Generate an audit report based on the final audit results of the summarized and classified financial documents.
[0026] Optionally, after summarizing and classifying the final audit results of the financial documents, the method further includes:
[0027] Based on dynamic numerical models and visual data charts, the final audit results of the summarized and classified financial documents are displayed.
[0028] Optionally, before retrieving the multi-party financial information converted into a unified format corresponding to the financial document information to be reviewed, the method further includes:
[0029] Input the information of the financial documents to be audited into the pre-trained AI model to obtain the AI audit results;
[0030] Visualize the AI audit results;
[0031] The AI model is trained based on historical document data whose file type is the document business data type and complies with the audit rules of the document business data type.
[0032] Optionally, the above-mentioned intelligent financial audit method for enterprise financial accounting also includes:
[0033] Based on preset sensitive words, the preset sensitive words are identified in the financial document information to be reviewed;
[0034] When preset sensitive words appear in the financial document information to be reviewed, a review warning message is generated, and the preset sensitive words in the financial document information to be reviewed are displayed.
[0035] Optionally, the establishment rules of the above audit rule base include:
[0036] Based on the preset audit standards, the audit points of each preset audit file type are determined to establish an audit rule library; among them,
[0037] The preset audit file types include document business data type, attachment image data type and voucher data type;
[0038] The audit rule library at least includes audit rules corresponding to each preset audit file type.
[0039] A second aspect of the present invention provides a financial intelligence audit system for enterprise financial accounting, comprising:
[0040] A financial information retrieval module is used to convert the acquired multi-party financial information into a unified format, and retrieve the converted multi-party financial information in a unified format corresponding to the financial document information to be reviewed;
[0041] A preliminary review module is used to obtain the preliminary review results of the corresponding financial documents based on the pre-established review rule base and the multi-party financial information converted into a unified format corresponding to the financial document information to be reviewed;
[0042] The final review module is used to determine and execute the subsequent review process based on the preliminary review results of the corresponding financial documents to obtain the final review results of the financial documents;
[0043] The subsequent review process includes at least a re-submission process and / or a manual review process.
[0044] In a third aspect of the present invention, a machine-readable storage medium is provided, on which instructions are stored, and when the instructions are executed by a processor, the processor is configured to execute the above-mentioned financial intelligent audit method for enterprise business accounting.
[0045] In a fourth aspect of the present invention, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the financial intelligent audit method for enterprise financial accounting is implemented.
[0046] Through the above technical scheme, a financial intelligent audit method and system for enterprise financial accounting is provided. The multi-party financial information converted in a unified format corresponding to the financial document information to be audited is retrieved from the multi-party financial information converted in a unified format. Based on the pre-established audit rule library, the multi-party financial information converted in a unified format corresponding to the financial document information to be audited is audited to obtain the corresponding preliminary audit results of the financial documents. According to the preliminary audit results of the corresponding financial documents, it is determined to execute the re-submission process or the manual audit process to obtain the final audit results of the financial documents. Then, the intelligent audit of the enterprise's financial accounting business is automatically or semi-automatically performed, giving full play to the respective advantages of machines and financial personnel, reducing manual operations, and using the human-machine collaborative working mode to encourage financial personnel to handle business more accurately and efficiently, improve the quality of business accounting, reduce the risk of human operation, and improve the automation rate of financial auditing and financial risk management capabilities, effectively avoiding the risks of missed audits and wrong audits, thereby providing more technical support for the financial management of enterprises.
[0047] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:
[0049] Figure 1 It is a flow chart of a financial intelligent audit method for enterprise financial accounting provided by one embodiment of the present invention;
[0050] Figure 2 It is an information flow diagram of a financial intelligence audit method for enterprise financial accounting provided by an embodiment of the present invention;
[0051] Figure 3 It is a schematic diagram of audit content provided by an implementation mode of the present invention;
[0052] Figure 4 It is another schematic diagram of audit content provided by an embodiment of the present invention;
[0053] Figure 5 It is a block diagram of a financial intelligent audit system for enterprise financial accounting provided by one embodiment of the present invention;
[0054] Figure 6 It is a schematic diagram of the structure of an electronic device provided by a preferred embodiment of the present invention.
[0055] Description of Reference Numerals
[0056] 10 - electronic device, 100 - processor, 101 - memory, 102 - computer program. DETAILED DESCRIPTION
[0057] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.
[0058] Figure 1 It is a flow chart of a financial intelligent audit method for enterprise financial accounting provided by one embodiment of the present invention. Figure 2 This is an information flow diagram of a financial intelligence audit method for enterprise financial accounting provided by an embodiment of the present invention. Figure 1 and Figure 2 As shown, the embodiment of the present invention provides a financial intelligence audit method for enterprise financial accounting, including:
[0059] S110: after converting the acquired multi-party financial information into a unified format, retrieving the multi-party financial information converted into a unified format corresponding to the financial document information to be reviewed;
[0060] Specifically, after obtaining the financial information of multiple parties, the financial information of multiple parties is converted into a unified format, and the converted financial information of multiple parties can be easily and efficiently realized in the later stage of intelligent audit. Thus, the document code of the financial document information to be audited is used as the only dimension to retrieve the corresponding converted financial information of multiple parties in a unified format.
[0061] In some implementations of this embodiment, the multi-party financial information includes at least external financial information, system financial information and internal financial information;
[0062] Specifically, the method uses different channels to obtain the financial information of multiple parties. The rules for obtaining the financial information of multiple parties include:
[0063] Recover multiple document information and multiple image data collected by multiple preset accounting systems, and perform text information recognition of each document information based on OCR; perform structured data conversion on the text information recognition results of each document information and multiple image data to obtain external financial information;
[0064] The preset account and bill system at least includes an account reporting system, an imaging system and a taxation system. The account reporting system is used to obtain document information, the taxation system is used to obtain the authenticity information of the account and bill, and the imaging system is used to obtain image data.
[0065] Specifically, the data channel between the accounting system, imaging system, OCR recognition platform and the invoice platform of the tax system is opened. During the business document filling process, the text information in the bills, contracts and other attachments in the business documents is automatically collected with the help of OCR intelligent recognition technology (including special VAT invoices, general invoices, train tickets, taxi tickets, etc., as well as the text and layout information of documents such as outbound orders, inbound orders, contracts, etc.), and the text information recognition results and image data are converted into structured data for storage, so that the electronic image can be fully utilized to obtain external financial information.
[0066] Establish connections between multiple preset financial information systems and integrate data of multiple preset financial information systems to obtain system financial information;
[0067] Specifically, by connecting multiple preset financial information systems, data silos are broken, and system financial information is obtained through integration and data penetration with different preset financial information systems.
[0068] Based on the identity information of the reimbursement user corresponding to each document information, the characteristic attributes of the reimbursement user corresponding to each document information are shared and reused to obtain internal financial information.
[0069] Specifically, according to the identity information of the reimbursement user corresponding to each document information, the personnel characteristic attributes of the reimbursement user are mined and shared and reused to obtain internal financial information.
[0070] In some implementations of this embodiment, the document information is uploaded to the SAP HANA database in the form of original files, and the image system calls the OCR recognition platform to perform OCR intelligent recognition on the document information and convert it into structured data, which is stored in the SAP HANA database. The system financial information is stored in the SAP HANA database through the PO integration interface. The internal financial information is manually reported by the user on the Web UI of the SAP NetWeaver platform, and the reported information is integrated into SAP Fiori using ODATA technology, and finally stored in the SAP HANA database.
[0071] S120: Obtaining a preliminary audit result of the corresponding financial document based on a pre-established audit rule library and the multi-party financial information converted into a unified format corresponding to the financial document information to be audited;
[0072] In some implementations of the present embodiment, the above-mentioned audit rule library contains multiple expected results corresponding to each preset audit file type; the above-mentioned preliminary audit results of the financial documents are obtained based on the pre-established audit rule library and the multi-party financial information converted into a unified format corresponding to the financial document information to be audited, including: based on the pre-established audit rule library, the multi-party financial information converted into a unified format corresponding to the financial document information to be audited is analyzed and summarized in turn to obtain the corresponding actual results; the corresponding actual results are compared and analyzed with multiple expected results corresponding to the file type of the financial document information to be audited to determine the preliminary audit results of the financial documents.
[0073] Specifically, the audit rules in the audit rule library are built into SAP Fiori through the ABAP / 4 programming language, and the expected results are set. The expected results are divided into three types: audit passed, audit failed, and not audited. The document code is used as the only dimension to retrieve the multi-party financial information (external financial information, system financial information, and internal financial information) related to this document from the SAP HANA database. In SAP Fiori, the audit rules in the audit rule library are used as the logic, and the multi-party financial information converted into a unified format is converted into program code through the ABAP / 4 programming language. Comparison, analysis, addition, summary and other operations are performed to calculate the actual results. The expected results and actual results are compared and analyzed to determine the expected results that best match the actual results, and the preliminary audit results of the financial documents are obtained in SAP Fiori. Finally, the preliminary audit results of the financial documents are integrated into the front end of the SAP NetWeaver platform using ODATA technology, and displayed on the front end according to the designed UI interface using Java language for further review and decision-making by the handlers and auditors.
[0074] In the above implementation process, the method combines the obtained multi-party financial information and the formulated audit rules, and implements the audit logic and process through program code, so as to automatically or semi-automatically perform intelligent audits of the company's business and financial accounting business, give full play to the respective advantages of machines and financial personnel, and use the human-machine collaborative working mode to enable financial personnel to handle business more accurately and efficiently, improve the quality of business accounting, reduce the risk of human operation, and realize the record query of the entire financial audit process.
[0075] S130: Based on the preliminary audit result of the corresponding financial document, determine and execute the subsequent audit process to obtain the final audit result of the financial document; wherein the subsequent audit process at least includes a re-submission process and / or a manual audit process.
[0076] Specifically, the method retrieves the multi-party financial information converted in a unified format corresponding to the financial document information to be audited from the multi-party financial information converted in a unified format, and audits the multi-party financial information converted in a unified format corresponding to the financial document information to be audited based on the pre-established audit rule library to obtain the corresponding preliminary audit results of the financial documents. According to the preliminary audit results of the corresponding financial documents, determine to execute the re-submission process or the manual audit process to obtain the final audit results of the financial documents. Then, the intelligent audit of the enterprise's business and financial accounting business is automatically or semi-automatically performed, giving full play to the respective advantages of machines and financial personnel, reducing manual operations, and using a human-machine collaborative working mode to encourage financial personnel to handle business more accurately and efficiently, improve the quality of business accounting, reduce the risk of human operation, and improve the automation rate of financial audits and financial risk management capabilities, effectively avoiding the risks of missed audits and wrong audits, thereby providing more technical support for the financial management of enterprises.
[0077] It should be noted that the machine processing process involved in this method can continuously review documents 24 hours a day, thereby realizing intelligent document review, which in turn greatly improves the review work efficiency and automation rate of financial personnel, and helps financial personnel transform from repetitive work to analytical decision-making.
[0078] In some implementations of the present embodiment, the above-mentioned subsequent audit process is determined and executed based on the preliminary audit results of the corresponding financial documents, including: when the subsequent audit process is determined to be a re-reporting process, when the preliminary audit result of the financial document is that the corresponding financial document information to be reviewed contains content that does not comply with the audit rules in the audit rule library, then based on the corresponding preliminary audit result of the financial document and the financial document information to be reviewed, a re-reporting instruction is sent, and the re-reported financial document information to be reviewed is recovered; when the subsequent audit process is determined to be a manual audit process, when the preliminary audit result of the financial document is that the corresponding financial document information to be reviewed contains content that does not comply with the audit rules in the audit rule library, then based on the corresponding preliminary audit result of the financial document and the financial document information to be reviewed, a warning prompt message and a manual audit instruction are sent.
[0079] Specifically, after the multi-party financial information converted into the unified format corresponding to the information of the financial documents to be audited is intelligently audited based on the pre-established audit rule library, the preliminary audit results of the financial documents are sorted, summarized, classified and other logical operations, and then effectively combined with the flow of the financial documents to be audited, so as to control the financial documents to be audited and determine the next flow of the financial documents to be audited. The system control based on the preliminary audit results of the financial documents is divided into two types: weak control (system control plan corresponding to the manual audit process) and strong control (system control plan corresponding to the re-reporting process). When the system control plan is strong control, if there is content that does not comply with the audit rules in the business accounting business of the enterprise, it will be rejected to the person in charge, and the person in charge will check the reason for rejection through the preliminary audit results of the financial documents attached in the process monitoring and the information of the financial documents to be audited. When the system control is weak control, it is divided into two types: transfer to manual audit or warning and continue execution. When transferring to manual audit, the intelligent audit details are displayed, and the relevant audit points are prompted for the auditor's reference. The system control of warning and continuing execution means that if the audit rules are not met, a document warning prompt will be issued and the document can be passed to the next position node. The auditor will check the preliminary audit results of the financial documents attached to the process monitoring and the information of the financial documents to be audited.
[0080] During the above implementation process, when using this method to review the financial documents to be reviewed, the front end strictly controls the review points that are prone to errors in the process of the person in charge filling out the form, so as to achieve early detection, early prompts, and early control of problems, and avoid repeated transmission of documents; the middle end transfers the supplementary information in the process of document and attachment transmission to manual review to further review the financial documents to be reviewed; the back end adds intelligent review of voucher information in the financial certificate preparation and posting links.
[0081] In some implementations of this embodiment, after obtaining the final audit results of the financial documents, the method further includes: summarizing and classifying the final audit results of the financial documents according to preset audit category dimensions; and generating an audit report based on the summarized and classified final audit results of the financial documents.
[0082] Among them, the preset audit category dimension includes the first-level audit category and the second-level audit category.
[0083] Specifically, the final audit results of financial documents are summarized based on the audit category and divided into two levels, the first-level audit category and the second-level audit content. The first-level audit category corresponds to the detailed second-level audit content, as follows: The first-level audit category is divided according to the document content, bill attachment content, voucher and auxiliary accounting information, and seven audit steps are set, namely document standardization, bill compliance, amount accuracy, payment compliance, collection compliance, voucher standardization, and attachment standardization. The second-level audit content is based on the first-level audit category combined with various business documents, and according to the categories of document standardization, bill compliance, amount accuracy, payment compliance, collection compliance, voucher standardization, and attachment standardization, the three parts of document business details, attachment images, and voucher previews in the business and financial accounting business of the enterprise are classified and audited step by step. After the final audit results of the financial documents are summarized and classified, the summarized and classified final audit results of the financial documents will be issued in the form of an audit report. Users can view the contents of the audit report through a browser, such as Figure 3 and Figure 4 shown.
[0084] In some implementations of this embodiment, after the final audit results of the financial documents are summarized and classified, the method further includes: displaying the summarized and classified final audit results of the financial documents based on a dynamic numerical model and a visual data chart.
[0085] Specifically, the final audit results of the summarized and classified financial documents are displayed through dynamic numerical models and visual data charts to achieve the purpose of multi-dimensional display of intelligent audit operation results. And by building a two-layer data architecture of management and sharing of dynamic numerical models and visual data charts, the needs of multi-caliber financial management can be met. Dynamic numerical models and visual data charts are used to stimulate digital intelligence efficiency, achieve the purpose of real-time audit, accurate verification, visual results, and full-process traceability, so as to accurately locate the key points of monitoring. It also realizes all-weather online intelligent monitoring, real-time display of intelligent audit operation indicators, and promotes a leap in work efficiency and risk control.
[0086] In some implementations of this embodiment, before retrieving the multi-party financial information converted into a unified format corresponding to the financial document information to be audited, the method also includes: inputting the financial document information to be audited into a pre-trained AI model to obtain AI audit results; visually displaying the AI audit results; wherein the AI model is trained based on historical document data whose file type is a document business data type and complies with the audit rules of the document business data type.
[0087] Specifically, AI models are used to conduct intelligent pre-audit and visual display of the financial documents to be audited, further solving basic problems at the bill of lading stage, such as errors in invoice headers and document filling errors, etc. This significantly reduces the document rejection rate and improves document quality and user-friendly experience.
[0088] In some implementations of this embodiment, the above-mentioned financial intelligent audit method for enterprise financial accounting also includes: based on preset sensitive words, identifying preset sensitive words on the financial document information to be audited; when preset sensitive words appear in the financial document information to be audited, generating audit warning information, and displaying the preset sensitive words in the financial document information to be audited.
[0089] Specifically, this method independently developed a sensitive word recognition and warning function. As long as the information of the financial document to be reviewed contains preset sensitive words, an audit warning will be triggered, thereby guiding auditors to discover risk points.
[0090] In some implementations of the present embodiment, the establishment rules of the above-mentioned audit rule base include: based on the preset audit standards, the audit points of each preset audit document type are determined respectively to establish the audit rule base; wherein the preset audit document types include document business data types, attachment image data types and voucher data types; the audit rule base includes at least the audit rules corresponding to each preset audit document type.
[0091] Among them, the preset audit standards include the principles of business compliance, decision-making integrity, standard consistency, risk controllability and process standardization.
[0092] Specifically, this method follows the principles of business compliance, decision integrity, standard consistency, risk controllability and process standardization, starting from seven aspects: document specification, voucher specification, attachment specification, amount accuracy, bill compliance, payment compliance and collection compliance, and sorting out multiple business scenarios and multiple audit rules through accounting business documents including expense reimbursement, travel reimbursement, sales revenue, receivables provisional estimate, purchase settlement, purchase provisional estimate, purchase integration, asset increase, collection, fund collection, prepayment, payment, automatic deduction, loan, repayment, etc. Therefore, the audit points of the three parts of document business data type, attachment image data type and voucher data type are determined, and an audit rule library is established. The audit rule library includes but is not limited to the following audit rules: whether the filling of the document header content is standardized, tax compliance audit, whether the system filling of personnel information is standardized, whether the amount of expense details is correct, whether the reimbursement amount is not greater than the amount of the associated application form, the compliance of VAT invoice information, payment methods, payee and other payment information are compliant, and the review of attachment images, including whether necessary attachments are uploaded, whether the attachment content is standardized, whether the expense account is filled in correctly, whether the voucher content is compliant, etc. This method unifies and standardizes the business standards of enterprise financial intelligent audit, and organizes the key points of manual audit by financial personnel into clear intelligent audit rules, thereby effectively reducing the impact of human factors on the audit results.
[0093] Figure 5 FIG. 1 is a block diagram of a financial intelligence audit system for enterprise financial accounting provided by an embodiment of the present invention. Figure 5 As shown, the embodiment of the present invention provides a financial intelligent audit system for enterprise financial accounting, including:
[0094] A financial information retrieval module is used to convert the acquired multi-party financial information into a unified format, and retrieve the converted multi-party financial information in a unified format corresponding to the financial document information to be reviewed;
[0095] A preliminary review module is used to obtain the preliminary review results of the corresponding financial documents based on the pre-established review rule base and the multi-party financial information converted into a unified format corresponding to the financial document information to be reviewed;
[0096] The final review module is used to determine and execute the subsequent review process based on the preliminary review results of the corresponding financial documents to obtain the final review results of the financial documents;
[0097] The subsequent review process includes at least a re-submission process and / or a manual review process.
[0098] Specifically, the system retrieves the multi-party financial information converted in a unified format corresponding to the financial document information to be audited from the multi-party financial information converted in a unified format, and audits the multi-party financial information converted in a unified format corresponding to the financial document information to be audited based on the pre-established audit rule library to obtain the corresponding preliminary audit results of the financial documents. According to the preliminary audit results of the corresponding financial documents, determine to execute the re-submission process or the manual audit process to obtain the final audit results of the financial documents. Then, the intelligent audit of the enterprise's business and financial accounting business is automatically or semi-automatically performed, giving full play to the respective advantages of machines and financial personnel, reducing manual operations, and using a human-machine collaborative working mode to encourage financial personnel to handle business more accurately and efficiently, improve the quality of business accounting, reduce the risk of human operation, and improve the automation rate of financial audits and financial risk management capabilities, effectively avoiding the risks of missed audits and wrong audits, thereby providing more technical support for the financial management of enterprises.
[0099] An embodiment of the present invention also provides a machine-readable storage medium having instructions stored thereon, which, when executed by the processor 100, configures the processor 100 to execute the above-mentioned financial intelligent audit method for enterprise financial accounting.
[0100] Machine-readable storage media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.
[0101] The embodiment of the present invention also provides an electronic device 10, which includes a memory 101, a processor 100, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the above-mentioned financial intelligent audit method for enterprise financial accounting is implemented.
[0102] like Figure 6FIG. 1 is a schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 6 As shown, the electronic device 10 of this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the steps in the above method embodiment are implemented. Alternatively, when the processor 100 executes the computer program 102, the functions of each module / unit in the above device embodiment are implemented.
[0103] Exemplarily, the computer program 102 may be divided into one or more modules / units, one or more modules / units are stored in the memory 101, and are executed by the processor 100 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 102 in the electronic device 10. For example, the computer program 102 may be divided into a financial information retrieval module, a preliminary review module, and a final review module.
[0104] The electronic device 10 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 10 may include, but is not limited to, a processor 100 and a memory 101. Those skilled in the art will appreciate that Figure 6 It is only an example of the electronic device 10 and does not constitute a limitation of the electronic device 10. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.
[0105] The processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
[0106] The memory 101 may be an internal storage unit of the electronic device 10, such as a hard disk or memory of the electronic device 10. The memory 101 may also be an external storage device of the electronic device 10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 10. Further, the memory 101 may also include both an internal storage unit of the electronic device 10 and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the electronic device 10. The memory 101 may also be used to temporarily store data that has been output or is to be output.
[0107] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0108] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program 102 products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program 102 product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0109] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program 102 products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by the computer program 102 instructions. These computer program 102 instructions can be provided to a processor 100 of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor 100 of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0110] These computer program 102 instructions may also be stored in a computer readable memory 101 that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory 101 produce an article of manufacture including an instruction device that implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0111] These computer program 102 instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0112] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0113] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.
Claims
1. A financial intelligent audit method for enterprise financial accounting, characterized in that: include: After converting the acquired multi-party financial information into a unified format, retrieve the converted multi-party financial information in a unified format corresponding to the financial document information to be reviewed; Based on the pre-established audit rule base and the multi-party financial information converted into a unified format corresponding to the financial document information to be audited, the corresponding preliminary audit results of the financial documents are obtained; Based on the preliminary audit results of the corresponding financial documents, determine and execute the subsequent audit process to obtain the final audit results of the financial documents; The subsequent review process at least includes a re-submission process and / or a manual review process.
2. The financial intelligent audit method for enterprise financial accounting according to claim 1 is characterized in that: The multi-party financial information includes at least external financial information, system financial information and internal financial information; The rules for obtaining the multi-party financial information include: Recover multiple document information and multiple image data collected by multiple preset accounting systems, and perform text information recognition of each document information based on OCR; Perform structured data conversion on the text information recognition results of each document information and multiple image data to obtain external financial information; Establish connections between multiple preset financial information systems and integrate data of multiple preset financial information systems to obtain system financial information; Based on the identity information of the reimbursement user corresponding to each document information, the characteristic attributes of the reimbursement user corresponding to each document information are shared and reused to obtain internal financial information.
3. The financial intelligent audit method for enterprise financial accounting according to claim 1 is characterized in that: The audit rule library contains a plurality of expected results corresponding to each preset audit file type; The multi-party financial information converted into a unified format based on the pre-established audit rule base and the financial document information to be audited obtains the corresponding preliminary audit results of the financial documents, including: Based on the pre-established audit rule library, the financial information of multiple parties converted into a unified format corresponding to the financial document information to be audited is analyzed and summarized in turn to obtain the corresponding actual results; Compare and analyze the corresponding actual results with multiple expected results corresponding to the file type of the financial document information to be audited to determine the preliminary audit results of the financial documents.
4. The financial intelligent audit method for enterprise financial accounting according to claim 1 is characterized in that: Based on the preliminary review results of the corresponding financial documents, determine and execute the subsequent review process, including: In the case where the subsequent review process is determined to be a re-submission process, when the preliminary review result of the financial document is that the corresponding financial document information to be reviewed contains content that does not comply with the review rules in the review rule library, a re-submission instruction is sent based on the preliminary review result of the corresponding financial document and the financial document information to be reviewed, and the re-submitted financial document information to be reviewed is collected; When it is determined that the subsequent audit process is a manual audit process, when the preliminary audit result of the financial document is that the corresponding financial document information to be audited contains content that does not comply with the audit rules in the audit rule library, a warning prompt message and a manual audit instruction are sent based on the corresponding preliminary audit result of the financial document and the financial document information to be audited.
5. The financial intelligent audit method for enterprise financial accounting according to claim 1 is characterized in that: After obtaining the final audit result of the financial document, the method further includes: Summarize and classify the final audit results of financial documents according to the preset audit category dimensions; Generate an audit report based on the final audit results of the summarized and classified financial documents.
6. The financial intelligent audit method for enterprise financial accounting according to claim 5 is characterized in that: After summarizing and classifying the final audit results of the financial documents, the method further includes: Based on dynamic numerical models and visual data charts, the final audit results of the summarized and classified financial documents are displayed.
7. The financial intelligent audit method for enterprise financial accounting according to claim 1 is characterized in that: Before retrieving the multi-party financial information converted into a unified format corresponding to the financial document information to be reviewed, the method further includes: Input the information of the financial documents to be audited into the pre-trained AI model to obtain the AI audit results; Visually display the AI audit results; The AI model is trained based on historical document data whose file type is a document business data type and complies with the audit rules of the document business data type.
8. The financial intelligent audit method for enterprise financial accounting according to claim 1 is characterized in that: The method further comprises: Based on preset sensitive words, the preset sensitive words are identified in the financial document information to be reviewed; When preset sensitive words appear in the financial document information to be reviewed, a review warning message is generated, and the preset sensitive words in the financial document information to be reviewed are displayed.
9. The financial intelligent audit method for enterprise financial accounting according to claim 1, characterized in that: The establishment rules of the audit rule base include: Based on the preset audit standards, the audit points of each preset audit file type are determined to establish an audit rule library; among them, The preset audit file types include document business data type, attachment image data type and voucher data type; The audit rule library at least includes audit rules corresponding to each preset audit file type.
10. A financial intelligent audit system for enterprise financial accounting, characterized in that: include: A financial information retrieval module is used to convert the acquired multi-party financial information into a unified format, and retrieve the converted multi-party financial information in a unified format corresponding to the financial document information to be reviewed; A preliminary review module is used to obtain the preliminary review results of the corresponding financial documents based on the pre-established review rule base and the multi-party financial information converted into a unified format corresponding to the financial document information to be reviewed; The final review module is used to determine and execute the subsequent review process based on the preliminary review results of the corresponding financial documents to obtain the final review results of the financial documents; The subsequent review process at least includes a re-submission process and / or a manual review process.
11. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the financial intelligence audit method for enterprise business accounting as described in any one of claims 1 to 9.
12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the financial intelligent audit method for enterprise business accounting as described in any one of claims 1 to 9 is implemented.