Financial account closing method and device based on big data, equipment and medium

Abstract

The invention relates to the technical field of big data, and discloses a big-data-based financial account closing method, device, equipment and medium, and the method comprises the steps: collecting various financial related data from a financial system, a business system and an external data source in an enterprise, and carrying out the cleaning and unification processing of the various financial related data, obtaining standard financial data; for the standard financial data, invoice repeated reimbursement checking, tax risk checking, expense overbudget checking and supplier risk checking are carried out in sequence, and if at least one checking result is abnormal, a first-level early warning signal is prompted; and if all the checking results are not abnormal, key feature extraction is carried out on the standard financial data, the key feature extraction is input into a financial checking model, the checking result of the standard financial data is output, and if the checking result is not compliant, a second-level early warning signal is prompted. According to the invention, the problem of low efficiency of account closing review can be solved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a financial account closing method, device, equipment and medium based on big data. Background Art

[0002] Accounting vouchers, also known as accounting vouchers, are accounting vouchers that accountants use to register accounting books. They are classified according to the content and nature of economic business matters based on the documents and relevant information of the auditors, and the accounting entries are determined. The basic contents usually include: name, date, number, content summary, subject, accounting direction, amount, accounting items, number of attachments, accounting personnel, etc. Accounting vouchers are a must for all companies and are widely used.

[0003] Financial audit and account closing are important links in corporate financial management. When closing financial accounts, it is necessary to check whether all business data has been recorded. The current account closing model has the following problems: the account closing check requires a full table scan of all business tables, which scans a large amount of data, resulting in low efficiency, and the check time is too concentrated. Verification is only done when closing accounts, which is time-sensitive. Summary of the invention

[0004] The present invention provides a financial account closing method, device, equipment and medium based on big data to solve the technical problem of low efficiency of financial account closing review in the prior art.

[0005] In a first aspect, a financial closing method based on big data is provided, comprising:

[0006] Collect various financial data from the company's internal financial system, business system and external data sources, and clean and unify the various financial data to obtain standard financial data;

[0007] For the standard financial data, invoice duplicate reimbursement verification, tax risk verification, expense over-budget verification and supplier risk verification are carried out in sequence. If at least one of the verification results is abnormal, a first-level warning signal is prompted;

[0008] If all the verification results are normal, key features are extracted from the standard financial data and input into the financial audit model, and the audit results of the standard financial data are output. If the audit results are non-compliant, a secondary warning signal is prompted;

[0009] Among them, the key features include expense amount, revenue amount, debt-to-asset ratio, and profit margin; the audit results include compliance judgment, abnormal prompts, and risk assessment; the compliance judgment includes whether the expense reimbursement amount is compliant, whether the revenue confirmation conditions are compliant, whether the debt-to-asset ratio is compliant, and whether the profit margin is compliant.

[0010] In a second aspect, a financial account closing device based on big data is provided, comprising:

[0011] The collection module is used to collect various financial-related data from the enterprise's internal financial system, business system and external data sources, and clean and unify the various financial-related data to obtain standard financial data;

[0012] A first checking module is used to perform invoice duplicate reimbursement checking, tax risk checking, expense over-budget checking and supplier risk checking on the standard financial data in sequence, and if at least one of the checking results is abnormal, a first-level warning signal is prompted;

[0013] The second verification module is used to extract key features of the standard financial data if all verification results are normal, input the key features into the financial audit model, output the audit results of the standard financial data, and prompt a secondary warning signal if the audit results are non-compliant;

[0014] Among them, the key features include expense amount, revenue amount, debt-to-asset ratio, and profit margin; the audit results include compliance judgment, abnormal prompts, and risk assessment; the compliance judgment includes whether the expense reimbursement amount is compliant, whether the revenue confirmation conditions are compliant, whether the debt-to-asset ratio is compliant, and whether the profit margin is compliant.

[0015] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned financial closing method based on big data when executing the computer program.

[0016] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned financial closing method based on big data are implemented.

[0017] In the scheme implemented by the above-mentioned financial closing method, device, equipment and medium based on big data, the user instruction can be received through the client. After the server receives the user instruction, it first collects various financial-related data from the internal financial system, business system and external data source of the enterprise, and obtains standard financial data after cleaning and unification; the standard financial data is checked for duplicate invoice reimbursement, tax risk, cost over-budget and supplier risk. These checks do not involve complex big data calculations and can almost be considered to be time-saving. If there are problems in these checks, a first-level warning signal can be directly output, so that the staff can process the standard financial data, and there is no need for subsequent financial audits, thereby speeding up the efficiency of financial closing audits; if there are no problems in these checks, the subsequent financial audits will continue, and the key features of the extracted standard financial data will be input into the financial audit model to obtain the audit results. If there is an unqualified audit, a second-level warning signal will be output.

[0018] In the embodiment of the present invention, the standard financial data is first checked for invoice duplicate reimbursement, tax risk, cost over-budget and supplier risk, which are relatively simple and do not require much time. When problems are found in these items, a first-level warning signal is directly prompted. When it is determined that these items do not have the above problems, a financial review is performed, and it is determined whether to output a second-level warning signal based on the review results. By dividing the standard financial data into two levels of review, the efficiency of closing the account can be accelerated. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0020] Figure 1 is a schematic diagram of an application environment of a financial account closing method based on big data in one embodiment of the present invention;

[0021] Figure 2 It is a flow chart of a financial account closing method based on big data in one embodiment of the present invention;

[0022] Figure 3 for Figure 2 A schematic diagram of a process of step S10;

[0023] Figure 4 for Figure 2 A schematic diagram of a process of step S30;

[0024] Figure 5 is a structural schematic diagram of a financial account closing device based on big data in one embodiment of the present invention;

[0025] Figure 6 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0026] Figure 7 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The financial account closing method based on big data provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In an application environment, the client communicates with the server through a network. The server can receive user instructions through the client, and according to the user instructions, collect various types of financial-related data from the internal financial system, business system and external data source of the enterprise, and clean and unify the various types of financial-related data to obtain standard financial data; for the standard financial data, invoice reimbursement verification, tax risk verification, cost over-budget verification and supplier risk verification are carried out in sequence, and if at least one verification result is abnormal, a first-level warning signal is prompted; if all verification results are normal, key features of the standard financial data are extracted and input into the financial audit model, and the audit results of the standard financial data are output, and if the audit results are non-compliant, a second-level warning signal is prompted; wherein the key features include the amount of expenses, the amount of income, the debt-to-asset ratio, and the profit rate, and the audit results include compliance judgment, abnormal prompts and risk assessment, and the compliance judgment includes whether the expense reimbursement amount is compliant, whether the confirmation conditions of the income are compliant, whether the debt-to-asset ratio is compliant, and whether the profit rate is compliant.

[0029] In the solution implemented by the financial closing method based on big data, the client can receive user instructions. After receiving the user instructions, the server first collects various financial-related data from the company's internal financial system, business system and external data source, and obtains standard financial data after cleaning and unification. The standard financial data is checked for duplicate invoice reimbursement, tax risk, expense overbudget and supplier risk. These checks do not involve complex big data calculations and can almost be considered to be time-saving. If there are problems in these checks, a first-level warning signal can be directly output, so that the staff can process the standard financial data and there is no need for subsequent financial audits, thereby speeding up the efficiency of financial closing audits. If there are no problems in these checks, the subsequent financial audits will continue, and the key features of the extracted standard financial data will be input into the financial audit model to obtain the audit results. If there is an unqualified audit, a second-level warning signal will be output.

[0030] In the embodiment of the present invention, the standard financial data is first checked for invoice duplicate reimbursement, tax risk, cost over-budget and supplier risk, which are relatively simple and do not require much time. When problems are found in these items, a first-level warning signal is directly prompted. When it is determined that these items do not have the above problems, a financial review is performed, and it is determined whether to output a second-level warning signal based on the review results. By dividing the standard financial data into two levels of review, the efficiency of closing the account can be accelerated.

[0031] The client may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0032] A flowchart of an intelligent question-answering processing method based on artificial intelligence provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown, the following steps are included:

[0033] S10: Collect various financial-related data from the enterprise's internal financial system, business system and external data sources, and clean and unify the various financial-related data to obtain standard financial data;

[0034] Financial closing is an important part of enterprise financial management, and generally requires data collection. The embodiment of the present invention first collects various types of financial-related data from the enterprise's internal financial system, business system, and external data sources. Since these data come from different systems, their data formats may not be unified. Therefore, these data need to be cleaned and unified to obtain standard financial data with a standard and unified format.

[0035] As an implementation method, Figure 3 As shown, in step S10, various types of financial-related data are collected from the internal financial system, business system and external data sources of the enterprise, and the various types of financial-related data are cleaned and unified to obtain standard financial data. The steps include:

[0036] S11: Collecting financial data from the internal financial system of the enterprise, wherein the financial data includes accounting vouchers, financial statements, expense reimbursement forms, purchase orders, and sales orders;

[0037] First, collect the financial data within the enterprise, including accounting vouchers, financial statements, expense reimbursement forms, purchase orders, sales orders, etc. Among them, accounting vouchers are written proofs that record economic transactions, clarify economic responsibilities, and are compiled in a certain format to register accounting books. The content of accounting vouchers includes the name of the voucher, the date of filling in the voucher, the name of the unit that filled in the voucher or the name of the person who filled in the voucher, etc.

[0038] Financial statements are written documents that reflect the financial status and operating results of an enterprise, mainly including the balance sheet, income statement, cash flow statement, statement of changes in owners' equity and notes.

[0039] An expense reimbursement form is a document filled out by employees when reimbursing various expenses. It is used to record the details of the expenses and submit them to the finance department for review and reimbursement. The main contents of the expense reimbursement form include the reimbursement date, the person making the reimbursement, the department, the expense details, the expense items, the amount, the number of invoices, and the contents of the attachments.

[0040] A purchase order is a written document issued by an enterprise to a supplier to purchase goods or services, which specifies the specific requirements such as the purchased variety, quantity, price, delivery date, delivery location, quality standards, etc.

[0041] A sales order is a written document generated when a company accepts an order from a customer. It records the customer's needs and the company's commitment, including information such as the products or services sold, quantity, price, delivery date, and delivery location.

[0042] S12: Integrate the business data of the enterprise's external business system, where the business data includes industry data, market data, and economic data;

[0043] Then integrate business data outside the enterprise, such as industry data, market data, economic data, etc., to obtain more comprehensive information.

[0044] Industry data is the statistics and analysis of relevant information within a specific industry, reflecting the status and trends of the industry's production, operations, market, etc. These data are of great significance for understanding the development dynamics of the industry, the competitive landscape, and the position of enterprises in the industry.

[0045] Market data mainly refers to information about market transactions, market supply and demand, market prices, etc. It reflects the market operation status and consumer behavior. Market data is of great reference value for enterprises to formulate marketing strategies, understand market demand, and evaluate market competitiveness.

[0046] Economic data is statistical information that reflects the overall economic status of a country or region, including indicators such as gross domestic product (GDP), inflation rate, unemployment rate, interest rate, exchange rate, trade balance, etc. Economic data is of great guiding significance for the government to formulate economic policies, enterprises to make investment decisions, and investors to allocate assets.

[0047] S13: Collecting external data from the banking system and the tax system, wherein the external data includes bank statements and tax data;

[0048] Then, external data can be obtained from the company's banking system, tax system, database and external data sources, including bank reconciliation data and tax data. Bank reconciliation data is the information between the company's bank account and bank records. It includes transaction details, balances and other information of the company's bank account, as well as the corresponding data on the bank statement. Through bank reconciliation, the accuracy of the company's bank account and the security of funds can be ensured.

[0049] Tax data refers to information related to corporate taxation, including sales revenue, costs, tax payable, tax incentives, etc. Tax data is of great significance for enterprises to comply with tax laws, accurately declare and pay taxes, and reasonably carry out tax planning.

[0050] S14: Clean and preprocess the financial data, the business data and the external data respectively, and perform deduplication, standardization and missing data supplementation in turn to obtain the standard financial data.

[0051] Integrate financial data, business data and external data from different systems and data sources, establish a unified database, use data cleaning and conversion technology to remove duplicate data, correct erroneous data, and convert data into a unified format and standard to obtain standard financial data.

[0052] S20: For the standard financial data, invoice duplicate reimbursement check, tax risk check, expense over-budget check and supplier risk check are performed in sequence. If at least one of the check results is abnormal, a first-level warning signal is prompted;

[0053] After obtaining the standard financial data, the invoice reimbursement check, tax risk check, expense overbudget check and supplier risk check are carried out in sequence. Among the above five verification results of the standard financial data, if at least one verification result is abnormal, a first-level warning signal will be prompted; if all five verification results are normal, proceed to the subsequent steps.

[0054] As an implementation method, the steps of checking duplicate invoice reimbursement include:

[0055] Collect key information of the received current invoice, including invoice code, invoice number, invoice date, amount, buyer name, and seller name;

[0056] A hash algorithm is used to compare the key information with historical invoices stored in a database. If there is a historical invoice in the database that is exactly the same as the key information, the current invoice is determined to be a duplicate reimbursement and the first-level warning signal is triggered. The database includes the key information of the historical invoice.

[0057] In an embodiment of the present invention, when a historical invoice is received, key information of the historical invoice is collected, including the invoice code, invoice number, invoice date, amount, purchaser's name, seller's name, etc., and the historical invoice information is stored in a database for subsequent query and comparison.

[0058] When a new current invoice is received, a hash algorithm is used to compare the key information of the newly entered current invoice with the key information of the historical invoices stored in the database. If it is found that the key information of the new current invoice is exactly the same as that of the existing historical invoice, it is determined to be a duplicate invoice reimbursement and an early warning is triggered.

[0059] Specifically, invoice duplicate reimbursement warning information can be sent to financial personnel through pop-up windows, emails, SMS notifications, etc. The warning information should include detailed information on the duplicate invoices so that the financial personnel can verify and process them.

[0060] As an implementation method, the cost over-budget verification includes the following steps:

[0061] Set the expense budget for each department and project in the enterprise for each time period;

[0062] Monitor each expense reimbursement in real time, record the type, amount, reimbursement department, and reimbursement time of the expense reimbursement, and accumulate the total expense expenditures of each department and project in each time period, compare them with the expense budget corresponding to each time period, and output the abnormal expense verification results.

[0063] In the embodiment of the present invention, an expense over-budget check is also performed. The budget is first set and allocated, and the expense budget for each department and project is set, and the budget is allocated to a specific time period (such as month, quarter, year). The budget can be reasonably adjusted according to the company's business objectives, historical data and business needs.

[0064] Then monitor the expenses in real time, monitor each expense reimbursement in real time, record the expense type, amount, reimbursement department, reimbursement time and other information, accumulate the expense expenditures of each department and project, and compare them with the corresponding budget.

[0065] When the expenditure of a department or project is close to the budget, an early warning will be issued to remind the financial staff and related departments to pay attention to cost control. Different early warning levels can be set, for example, when the expenditure reaches 80%, 90%, and 100% of the budget, different levels of early warning will be triggered respectively.

[0066] After receiving the warning of over-budget expenses, the financial staff should verify the rationality of the expenses in a timely manner and communicate and coordinate with the relevant departments. If necessary, the budget can be adjusted or other measures can be taken to control the expenses.

[0067] As an implementation method, the supplier risk verification includes the following steps:

[0068] Monitor suppliers’ risk signals, including credit status, delivery timeliness, and product quality;

[0069] When the supplier shows risk signals such as a decline in credit rating and / or frequent delays in delivery, it is determined that the supplier is abnormal.

[0070] In the embodiment of the present invention, the credit status, delivery timeliness, product quality, etc. of the supplier are monitored. When a supplier shows risk signals, such as a drop in credit rating, frequent delays in delivery, etc., an early warning is issued.

[0071] As an implementation method, the steps for tax risk verification are to issue early warnings for possible tax risks based on changes in tax laws and regulations and the company's tax declaration status, such as incorrect application of tax rates, overdue tax declarations, etc.

[0072] In the embodiment of the present invention, the standard financial data is firstly checked for duplicate invoice reimbursement, tax risk, expense over-budget and supplier risk, which are relatively simple and do not require much time.

[0073] S30: If all the verification results are normal, extract key features from the standard financial data, input them into the financial audit model, and output the audit results of the standard financial data. If the audit results are non-compliant, a secondary warning signal is prompted;

[0074] Among them, the key features include expense amount, revenue amount, debt-to-asset ratio, and profit margin; the audit results include compliance judgment, abnormal prompts, and risk assessment; the compliance judgment includes whether the expense reimbursement amount is compliant, whether the revenue confirmation conditions are compliant, whether the debt-to-asset ratio is compliant, and whether the profit margin is compliant.

[0075] If the verification results of the above-mentioned invoice duplicate reimbursement verification, tax risk verification, expense overbudget verification and supplier risk verification are all normal, key features are extracted from the standard financial data, and the key features can be statistical features; then the statistical features are input into the financial audit model to obtain the audit results.

[0076] As an implementation method, Figure 4 As shown, the key features of the standard financial data are extracted and input into the financial audit model, and the audit results of the standard financial data are output, the steps include:

[0077] S31: extracting statistical features of the standard financial data using a statistical analysis method;

[0078] S32: Input the statistical features into the financial audit model to obtain the audit results. The financial audit model is a neural network model, which is trained by training samples and labels. The training evaluation indicators of the financial audit model include accuracy and recall.

[0079] The embodiment of the present invention determines key financial features, such as expense amount, income amount, debt-to-asset ratio, profit margin, etc., based on the objectives and requirements of financial audit, and selects features related to key links and risk points in the business process. Statistical analysis methods, such as mean, standard deviation, median, etc., can be used to extract statistical features of data.

[0080] Formulate rules and standards for financial audits based on historical data and business experience. For example, set limits on expense reimbursement, conditions for revenue recognition, reasonable ranges for debt-to-asset ratios, etc. Rules can be quantitative or qualitative, and must be operational and measurable. Select appropriate machine learning algorithms and models as financial audit models, such as decision trees, random forests, support vector machines, neural networks, etc. Select appropriate models for training and optimization based on data characteristics and audit objectives. Use historical data to train the model, adjust the model parameters, and improve the model's accuracy and generalization capabilities.

[0081] In some embodiments, the method further comprises:

[0082] According to the first-level warning signal, the standard financial data is further audited by manual review;

[0083] According to the secondary warning signal, the standard financial data is matched with the historical financial range. If the match fails, the standard financial data is manually reviewed for closing audit. If the match succeeds, the standard financial data is added to the training set. When the number of training data in the training set reaches a preset number, the training set is used again to train the financial audit model.

[0084] After receiving the first-level warning signal, the embodiment of the present invention uses manual review to perform closing audit processing on the standard financial data; after receiving the second-level warning signal, the standard financial data and the historical financial range are matched. If the match fails, the standard financial data is manually reviewed and processed. If the match is successful, the standard financial data is added to the training set. When the number of training data in the training set reaches a preset number, the training set is used to retrain the financial audit model.

[0085] In the solution implemented by the above-mentioned financial closing method based on big data, various types of financial-related data are first collected from the company's internal financial system, business system and external data sources, and then cleaned and unified to obtain standard financial data; the standard financial data is checked for duplicate invoice reimbursement, tax risk, expense overbudget and supplier risk. These checks do not involve complex big data calculations and can almost be considered to be time-saving. If there are problems in these checks, a first-level warning signal can be directly output, so that the staff can process the standard financial data, and there is no need for subsequent financial audits, thereby speeding up the efficiency of financial closing audits; if there are no problems in these checks, the subsequent financial audit will continue, and the key features of the extracted standard financial data will be input into the financial audit model to obtain the audit results. If there is an unqualified audit, a second-level warning signal will be output.

[0086] In the embodiment of the present invention, the standard financial data is first checked for invoice duplicate reimbursement, tax risk, cost over-budget and supplier risk, which are relatively simple and do not require much time. When problems are found in these items, a first-level warning signal is directly prompted. When it is determined that these items do not have the above problems, a financial review is performed, and it is determined whether to output a second-level warning signal based on the review results. By dividing the standard financial data into two levels of review, the efficiency of closing the account can be accelerated.

[0087] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0088] In one embodiment, a financial account closing device based on big data is provided, and the financial account closing device based on big data corresponds to the financial account closing method based on big data in the above embodiment. Figure 5 As shown, the intelligent question-answering processing device includes a collection module 501, a first verification module 502, and a second verification module 503. The functional modules are described in detail as follows:

[0089] The collection module 501 is used to collect various financial-related data from the enterprise's internal financial system, business system and external data sources, and clean and unify the various financial-related data to obtain standard financial data;

[0090] The first checking module 502 is used to perform invoice duplicate reimbursement checking, tax risk checking, expense over-budget checking and supplier risk checking on the standard financial data in sequence, and if at least one of the checking results is abnormal, a first-level warning signal is prompted;

[0091] The second verification module 503 is used to extract key features from the standard financial data if all verification results are normal, input the key features into the financial audit model, output the audit results of the standard financial data, and prompt a secondary warning signal if the audit results are non-compliant;

[0092] Among them, the key features include expense amount, revenue amount, debt-to-asset ratio, and profit margin; the audit results include compliance judgment, abnormal prompts, and risk assessment; the compliance judgment includes whether the expense reimbursement amount is compliant, whether the revenue confirmation conditions are compliant, whether the debt-to-asset ratio is compliant, and whether the profit margin is compliant.

[0093] In one embodiment, the financial account closing device based on big data further includes:

[0094] A first early warning module is used to perform a closing audit process on the standard financial data by manual review according to the first-level early warning signal;

[0095] The second warning module is used to match the standard financial data with the historical financial range according to the secondary warning signal. If the match fails, the standard financial data is manually reviewed for closing and auditing. If the match succeeds, the standard financial data is added to the training set. When the number of training data in the training set reaches a preset number, the training set is used again to train the financial audit model.

[0096] In one embodiment, the first checking module 502 is specifically configured to:

[0097] Collect key information of the received current invoice, including invoice code, invoice number, invoice date, amount, buyer name, and seller name;

[0098] A hash algorithm is used to compare the key information with historical invoices stored in a database. If there is a historical invoice in the database that is exactly the same as the key information, the current invoice is determined to be a duplicate reimbursement and the first-level warning signal is triggered. The database includes the key information of the historical invoice.

[0099] In one embodiment, the first checking module 502 is further configured to:

[0100] Set the expense budget for each department and project in the enterprise for each time period;

[0101] Monitor each expense reimbursement in real time, record the type, amount, reimbursement department, and reimbursement time of the expense reimbursement, and accumulate the total expense expenditures of each department and project in each time period, compare them with the expense budget corresponding to each time period, and output the abnormal expense verification results.

[0102] In one embodiment, the first checking module 502 is specifically configured to:

[0103] Monitor suppliers’ risk signals, including credit status, delivery timeliness, and product quality;

[0104] When the supplier shows risk signals such as a decline in credit rating and / or frequent delays in delivery, it is determined that the supplier is abnormal.

[0105] In one embodiment, the first checking module 502 is specifically configured to:

[0106] Using statistical analysis methods to extract statistical characteristics of the standard financial data;

[0107] The statistical features are input into the financial audit model to obtain the audit results. The financial audit model is a neural network model, which is trained by training samples and labels. The training evaluation indicators of the financial audit model include accuracy and recall.

[0108] In one embodiment, the acquisition module 501 is specifically used for:

[0109] Collecting financial data from the internal financial system of the enterprise, the financial data including accounting vouchers, financial statements, expense reimbursement forms, purchase orders, and sales orders;

[0110] Integrate the business data of the enterprise's external business system, the business data including industry data, market data, and economic data;

[0111] Collect external data from banking systems and tax systems, including bank statements and tax data;

[0112] The financial data, the business data and the external data are cleaned and preprocessed respectively, and deduplication, standardization and missing data supplementation are performed in turn to obtain the standard financial data.

[0113] The present invention provides a financial account closing device based on big data. First, various types of financial related data are collected from the internal financial system, business system and external data source of an enterprise, and standard financial data is obtained after cleaning and unification. First, the standard financial data is checked for duplicate invoice reimbursement, tax risk, expense over-budget and supplier risk. These checks do not involve complex big data calculations and do not require time. If there are problems in these calculations, a first-level warning signal can be directly output, so that the staff can process the standard financial data, and there is no need for subsequent financial audits, thereby speeding up the efficiency of account closing audits. If there are no problems in these calculations, subsequent financial audits are continued, and the key features of the extracted standard financial data are input into the financial audit model to obtain the audit results. If there is an audit failure, a second-level warning signal is output.

[0114] In the embodiment of the present invention, the standard financial data is first checked for duplicate invoice reimbursement, tax risk, over-budget expenses and supplier risk, which are relatively simple and do not require much time. When problems are found in these items, a first-level warning signal is directly prompted. When it is determined that these items do not have the above problems, a financial review is performed, and it is determined whether to output a second-level warning signal based on the review results. By dividing the standard financial data into two levels of review, the efficiency of closing the account can be accelerated.

[0115] For the specific definition of the financial closing device based on big data, please refer to the definition of the financial closing method based on big data above, which will not be repeated here. Each module in the above-mentioned financial closing device based on big data can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0116] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the service side of a financial closing method based on big data.

[0117] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, it realizes the functions or steps of the client side of a financial closing method based on big data

[0118] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0119] Collect various financial data from the company's internal financial system, business system and external data sources, and clean and unify the various financial data to obtain standard financial data;

[0120] For the standard financial data, invoice duplicate reimbursement verification, tax risk verification, expense over-budget verification and supplier risk verification are carried out in sequence. If at least one of the verification results is abnormal, a first-level warning signal is prompted;

[0121] If all the verification results are normal, key features are extracted from the standard financial data and input into the financial audit model, and the audit results of the standard financial data are output. If the audit results are non-compliant, a secondary warning signal is prompted;

[0122] Among them, the key features include expense amount, revenue amount, debt-to-asset ratio, and profit margin; the audit results include compliance judgment, abnormal prompts, and risk assessment; the compliance judgment includes whether the expense reimbursement amount is compliant, whether the revenue confirmation conditions are compliant, whether the debt-to-asset ratio is compliant, and whether the profit margin is compliant.

[0123] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0124] Collect various financial data from the company's internal financial system, business system and external data sources, and clean and unify the various financial data to obtain standard financial data;

[0125] For the standard financial data, invoice duplicate reimbursement verification, tax risk verification, expense over-budget verification and supplier risk verification are carried out in sequence. If at least one of the verification results is abnormal, a first-level warning signal is prompted;

[0126] If all the verification results are normal, key features are extracted from the standard financial data and input into the financial audit model, and the audit results of the standard financial data are output. If the audit results are non-compliant, a secondary warning signal is prompted;

[0127] Among them, the key features include expense amount, revenue amount, debt-to-asset ratio, and profit margin; the audit results include compliance judgment, abnormal prompts, and risk assessment; the compliance judgment includes whether the expense reimbursement amount is compliant, whether the revenue confirmation conditions are compliant, whether the debt-to-asset ratio is compliant, and whether the profit margin is compliant.

[0128] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0129] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0130] Those skilled in the art 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. In actual applications, the above-mentioned functions can be distributed and 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.

[0131] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A financial account closing method based on big data, characterized in that: include: Collect various financial data from the company's internal financial system, business system and external data sources, and clean and unify the various financial data to obtain standard financial data; For the standard financial data, invoice duplicate reimbursement verification, tax risk verification, expense over-budget verification and supplier risk verification are carried out in sequence. If at least one of the verification results is abnormal, a first-level warning signal is prompted; If all the verification results are normal, key features are extracted from the standard financial data and input into the financial audit model, and the audit results of the standard financial data are output. If the audit results are non-compliant, a secondary warning signal is prompted; Among them, the key features include expense amount, revenue amount, debt-to-asset ratio, and profit margin; the audit results include compliance judgment, abnormal prompts, and risk assessment; the compliance judgment includes whether the expense reimbursement amount is compliant, whether the revenue confirmation conditions are compliant, whether the debt-to-asset ratio is compliant, and whether the profit margin is compliant.

2. The financial account closing method based on big data as claimed in claim 1, characterized in that: The method further comprises: According to the first-level warning signal, the standard financial data is further processed for closing and auditing by manual review; According to the secondary warning signal, the standard financial data is matched with the historical financial range. If the match fails, the standard financial data is manually reviewed for closing audit. If the match succeeds, the standard financial data is added to the training set. When the number of training data in the training set reaches a preset number, the training set is used again to train the financial audit model.

3. The financial account closing method based on big data according to claim 1, characterized in that: The steps of checking duplicate invoice reimbursement include: Collect key information of the received current invoice, including invoice code, invoice number, invoice date, amount, buyer name, and seller name; A hash algorithm is used to compare the key information with historical invoices stored in a database. If there is a historical invoice in the database that is exactly the same as the key information, the current invoice is determined to be a duplicate reimbursement and the first-level warning signal is triggered. The database includes the key information of the historical invoice.

4. The financial account closing method based on big data according to claim 1, characterized in that: The steps of conducting the cost over-budget verification include: Set the expense budget for each department and project in the enterprise for each time period; Monitor each expense reimbursement in real time, record the type, amount, reimbursement department, and reimbursement time of the expense reimbursement, and accumulate the total expense expenditures of each department and project in each time period, compare them with the expense budget corresponding to each time period, and output the abnormal expense verification results.

5. The financial account closing method based on big data as claimed in claim 1, characterized in that: The steps of supplier risk verification include: Monitor suppliers’ risk signals, including credit status, delivery timeliness, and product quality; When the supplier shows risk signals such as a decline in credit rating and / or frequent delays in delivery, it is determined that the supplier is abnormal.

6. The financial account closing method based on big data according to any one of claims 1 to 5, characterized in that: The steps of extracting key features from the standard financial data, inputting the key features into the financial audit model, and outputting the audit results of the standard financial data include: Using statistical analysis methods to extract statistical characteristics of the standard financial data; The statistical features are input into the financial audit model to obtain the audit results. The financial audit model is a neural network model, which is trained by training samples and labels. The training evaluation indicators of the financial audit model include accuracy and recall.

7. The financial account closing method based on big data according to any one of claims 1 to 5, characterized in that: The steps of collecting various financial-related data from the enterprise's internal financial system, business system and external data sources, and cleaning and unifying the various financial-related data to obtain standard financial data include: Collecting financial data from the enterprise's internal financial system, including accounting vouchers, financial statements, expense reimbursement forms, purchase orders, and sales orders; Integrate the business data of the enterprise's external business system, the business data including industry data, market data, and economic data; Collect external data from banking systems and tax systems, including bank statements and tax data; The financial data, the business data and the external data are cleaned and preprocessed respectively, and deduplication, standardization and missing data supplementation are performed in turn to obtain the standard financial data.

8. A financial account closing device based on big data, characterized in that: include: The collection module is used to collect various financial-related data from the enterprise's internal financial system, business system and external data sources, and clean and unify the various financial-related data to obtain standard financial data; A first checking module is used to perform invoice duplicate reimbursement checking, tax risk checking, expense over-budget checking and supplier risk checking on the standard financial data in sequence, and if at least one of the checking results is abnormal, a first-level warning signal is prompted; The second verification module is used to extract key features of the standard financial data if all verification results are normal, input the key features into the financial audit model, output the audit results of the standard financial data, and prompt a secondary warning signal if the audit results are non-compliant; Among them, the key features include expense amount, revenue amount, debt-to-asset ratio, and profit margin; the audit results include compliance judgment, abnormal prompts, and risk assessment; the compliance judgment includes whether the expense reimbursement amount is compliant, whether the revenue confirmation conditions are compliant, whether the debt-to-asset ratio is compliant, and whether the profit margin is compliant.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the financial closing method based on big data as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the financial closing method based on big data as claimed in any one of claims 1 to 7 are implemented.

Images