Financial document quality analysis processing method and device

Abstract

The invention provides a financial document quality analysis processing method and device. The method comprises the following steps: generating a quality inspection task corresponding to financial document quality analysis processing; performing random sampling processing according to the quality inspection task to obtain corresponding financial document information to be subjected to quality inspection; performing data quality inspection processing on the financial document to be subjected to quality inspection based on a preset auditing rule to obtain a financial document quality inspection result; wherein the auditing rule comprises the limit of the amount corresponding to the financial document to be subjected to quality inspection and the prohibited target field corresponding to the financial document to be subjected to quality inspection of the target type. According to the financial document quality analysis processing method provided by the invention, the efficiency and accuracy of financial document quality analysis processing can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of computer application technologies, and in particular, to a method and device for analyzing and processing the quality of financial documents. Additionally, it also relates to an electronic device, a non-transitory computer-readable storage medium, and a computer program product. Background Art

[0002] In recent years, with the continuous development of computer technologies, financial management systems have become increasingly widespread in various fields. The main technology is to conduct sampling quality inspections on financial documents. Usually, financial documents will go through multiple levels of approval, financial audits, and financial reviews, and finally accounting vouchers are generated and stored in the financial management system. Financial approval, audit, and review are all actions to confirm the accuracy of financial document information, which can generally ensure the accuracy of financial documents. However, currently, the analysis and processing of the quality of financial documents are usually completed manually, which is prone to errors and has low efficiency. To avoid small-probability financial document errors caused by human inadvertence and intention, resulting in property losses to enterprises, it is still necessary to conduct sampling inspections on financial documents, that is, to achieve financial quality management. Especially when the business volume is huge, single manual sampling according to proportion and quantity will lead to insufficient efficiency in sampling financial documents. Therefore, how to design a more efficient financial document quality analysis and processing solution has become an urgent technical problem to be solved currently. Summary of the Invention

[0003] The present invention provides a method for analyzing and processing the quality of financial documents to solve the defect that the existing financial document quality analysis and processing solution has high limitations, resulting in poor efficiency in analyzing and processing the quality of financial documents.

[0004] The present invention provides a method for analyzing and processing the quality of financial documents, including: Generating a quality inspection task corresponding to the analysis and processing of the quality of financial documents; Performing random sampling processing according to the quality inspection task to obtain corresponding financial document information to be quality inspected; Performing data quality inspection processing on the financial document to be quality inspected based on a preset audit rule to obtain a financial document quality inspection result; wherein, the audit rule includes the limit of the amount corresponding to the financial document to be quality inspected and the target fields that are prohibited from appearing in the financial document to be quality inspected of the target type.

[0005] According to the method for analyzing and processing the quality of financial documents of the present invention, the performing random sampling processing according to the quality inspection task to obtain corresponding financial document information to be quality inspected includes: According to the type of the financial document and the time interval when the financial document is generated, obtaining the digital identifiers of all financial documents corresponding to the quality inspection task, and storing the digital identifiers of all financial documents in a preset storage area in ascending order; Extract digital identifiers of all financial documents in the storage area according to the sampling ratio or sampling quantity of the financial documents, and obtain a target quantity of digital identifiers; extract corresponding financial documents according to the target quantity of digital identifiers to obtain first target financial documents; Perform analysis and processing on the first target financial documents based on a preset financial document weight prediction model, and obtain weight values respectively corresponding to the first target financial documents output by the financial document weight prediction model; wherein, the financial document weight prediction model is a neural network model obtained by iterative training based on preset sample financial documents and weight value labels corresponding to the sample financial documents; Sort the weight values corresponding to the first target financial documents from high to low to obtain a weight value sorting result; extract the first target financial documents with a preset target quantity according to the weight value sorting result as financial documents to be quality inspected.

[0006] According to a financial document quality analysis and processing method of the present invention, performing data quality inspection processing on the financial documents to be quality inspected based on a preset audit rule, and obtaining a financial document quality inspection result, including: Match and analyze the data in the financial documents to be quality inspected with the content in the audit rule. In the case where the amount data in the financial documents to be quality inspected exceeds the limit of the corresponding amount of the financial documents to be quality inspected, and / or in the case where the field data in the financial documents to be quality inspected has a field that matches a target field that is prohibited from appearing corresponding to the financial documents to be quality inspected, determine the financial documents to be quality inspected as abnormal financial documents; in the case where the amount data in the financial documents to be quality inspected does not exceed the limit of the corresponding amount of the financial documents to be quality inspected, and in the case where the field data in the financial documents to be quality inspected does not have a field that matches a target field that is prohibited from appearing corresponding to the financial documents to be quality inspected, determine the financial documents to be quality inspected as normal financial documents; use the abnormal financial documents and the normal financial documents as the financial document quality inspection result.

[0007] According to a financial document quality analysis and processing method of the present invention, the extracting digital identifiers of all financial documents in the storage area according to the sampling ratio or sampling quantity of the financial documents, and obtaining a target quantity of digital identifiers specifically includes: Call the preset random sampling algorithm, and according to the sampling ratio or sampling quantity of the financial documents, generate a set of non-repeating random numbers in the corresponding random value range in a loop; wherein, the value of the random number corresponds to the value of the digital identifier of the financial document in the storage area; the random value range is the value range formed between the minimum value of the digital identifier of the financial document and the maximum value of the digital identifier of the financial document; the number of the random numbers is N times the number of financial documents to be quality inspected corresponding to the sampling ratio or sampling quantity of the financial documents, where N is a positive integer greater than or equal to 2; Extract the digital identifiers of all the financial documents in the storage area based on the random numbers to obtain the digital identifiers of the target quantity.

[0008] According to a financial document quality analysis and processing method of the present invention, after performing data quality inspection processing on the financial documents to be quality inspected based on a preset audit rule and obtaining a financial document quality inspection result, it further includes: in the case that the financial document quality inspection result includes abnormal financial documents, sending the abnormal financial documents included in the financial document quality inspection result to a preset audit node or a review node.

[0009] According to a financial document quality analysis and processing method of the present invention, the generation of the quality inspection task corresponding to the financial document quality analysis and processing specifically includes: Obtain the type of the financial document input by the user terminal, the sampling ratio or sampling quantity of the financial document, the target completion time of the financial document processing task, the time interval when the financial document is generated, and custom conditions; Generate a corresponding quality inspection task according to the type of the financial document, the sampling ratio or sampling quantity of the financial document, the target completion time of the financial document processing task, the date interval when the financial document is generated, and the custom conditions; wherein, each quality inspection task in the quality inspection task generates corresponding multiple financial document information when performing random sampling quality inspection.

[0010] The present invention further provides a financial document quality analysis and processing device, including: A quality inspection task generation unit, configured to generate a quality inspection task corresponding to the financial document quality analysis and processing; A financial document obtaining unit, specifically performing random sampling processing according to the quality inspection task to obtain corresponding financial document information to be quality inspected; A financial document audit unit, configured to perform data quality inspection processing on the financial document to be quality inspected based on a preset audit rule to obtain a financial document quality inspection result; wherein, the audit rule includes the limit of the amount corresponding to the financial document to be quality inspected and the target fields that are prohibited from appearing in the financial document to be quality inspected of the target type.

[0011] A financial document quality analysis and processing device according to the present invention, the financial document acquisition unit is specifically used for: According to the type of the financial document and the time interval when the financial document is generated, obtain the digital identifiers of all financial documents corresponding to the quality inspection task, and store the digital identifiers of all financial documents in ascending order in a preset storage area; Extract the digital identifiers of all financial documents in the storage area according to the sampling ratio or sampling quantity of the financial documents, and obtain a target quantity of digital identifiers; extract the corresponding financial documents according to the target quantity of digital identifiers to obtain the first target financial documents; Based on a preset financial document weight prediction model, analyze and process the first target financial documents, and obtain the weight values corresponding to the first target financial documents output by the financial document weight prediction model; wherein, the financial document weight prediction model is a neural network model obtained by iterative training based on preset sample financial documents and the weight value labels corresponding to the sample financial documents; Sort the weight values corresponding to the first target financial documents from high to low to obtain a weight value sorting result; extract the first target financial documents with the top preset target quantity according to the weight value sorting result as the financial documents to be quality inspected.

[0012] A financial document quality analysis and processing device according to the present invention, the financial document review unit is specifically used for: Match and analyze the data in the financial documents to be quality inspected with the content in the review rules. In the case where the amount data in the financial documents to be quality inspected exceeds the limit of the corresponding amount of the financial documents to be quality inspected, and / or in the case where the field data in the financial documents to be quality inspected has a field that matches the target field that is prohibited from appearing in the financial documents to be quality inspected, determine the financial documents to be quality inspected as abnormal financial documents; in the case where the amount data in the financial documents to be quality inspected does not exceed the limit of the corresponding amount of the financial documents to be quality inspected, and the field data in the financial documents to be quality inspected does not have a field that matches the target field that is prohibited from appearing in the financial documents to be quality inspected, determine the financial documents to be quality inspected as normal financial documents; use the abnormal financial documents and the normal financial documents as the financial document quality inspection results.

[0013] A financial document quality analysis and processing device according to the present invention, the extracting the digital identifiers of all financial documents in the storage area according to the sampling ratio or sampling quantity of the financial documents, and obtaining a target quantity of digital identifiers specifically includes: Call the preset random sampling algorithm, and generate a set of non-repeating random numbers in a corresponding random value range according to the sampling ratio or sampling quantity of the financial documents; wherein, the value of the random number corresponds to the value of the digital identifier of the financial document in the storage area; the random value range is the value range formed between the minimum value of the digital identifier of the financial document and the maximum value of the digital identifier of the financial document; the number of random numbers is N times the number of financial documents to be quality inspected corresponding to the sampling ratio or sampling quantity of the financial documents, where N is a positive integer greater than or equal to 2; Extract the digital identifiers of all the financial documents in the storage area based on the random numbers to obtain a target number of digital identifiers.

[0014] According to a financial document quality analysis and processing device of the present invention, after performing data quality inspection processing on the financial documents to be quality inspected based on a preset review rule and obtaining a financial document quality inspection result, it further includes: an abnormal document processing unit, configured to, when the financial document quality inspection result includes abnormal financial documents, send the abnormal financial documents included in the financial document quality inspection result to a preset review node or a review node.

[0015] According to a financial document quality analysis and processing device of the present invention, the quality inspection task generation unit is specifically configured to: Obtain the type of financial document, the sampling ratio or sampling quantity of the financial document, the target completion time of the financial document processing task, the time interval when the financial document is generated, and custom conditions input by the user terminal; Generate corresponding quality inspection tasks according to the type of the financial document, the sampling ratio or sampling quantity of the financial document, the target completion time of the financial document processing task, the date interval when the financial document is generated, and the custom conditions; wherein, each quality inspection task in the quality inspection task generates corresponding multiple financial document information when performing random sampling quality inspection.

[0016] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, it implements the financial document quality analysis and processing method described in any one of the above.

[0017] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the financial document quality analysis and processing method described in any one of the above.

[0018] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the financial document quality analysis and processing method described in any one of the above.

[0019] The financial document quality analysis and processing method provided by the present invention generates a quality inspection task corresponding to the financial document quality analysis and processing, performs random sampling processing according to the quality inspection task to obtain corresponding financial document information to be quality inspected, and then performs data quality inspection processing on the financial document to be quality inspected based on a preset audit rule to obtain a financial document quality inspection result. The audit rule includes the limit of the amount corresponding to the financial document to be quality inspected and the target fields that are prohibited from appearing in the financial document to be quality inspected of the target type, which can effectively improve the efficiency and accuracy of the financial document quality analysis and processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0021] Figure 1 is one of the flow diagrams of the financial document quality analysis and processing method provided by the present invention.

[0022] Figure 2 is the second flow diagram of the financial document quality analysis and processing method provided by the present invention.

[0023] Figure 3 is the structural diagram of the financial document quality analysis and processing device provided by the present invention.

[0024] Figure 4 is the structural diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0026] At present, in the process of financial quality management, it is required that the extracted financial documents be random, and random sampling is used to ensure that the sampling data is not false due to human interference. Since the enterprise production activities corresponding to different types of financial documents are different, the importance of different types of financial documents for sampling inspection is also different. For example, accounts receivable financial documents and accounts payable financial documents have a significant impact on the enterprise's production and operation activities. Therefore, for this type of financial documents, a higher sampling probability should be supported for sampling inspection. It is necessary to propose a set of efficient and feasible financial quality management methods to ensure efficient quality inspection of financial documents. For this reason, the present invention provides a method for analyzing and processing the quality of financial documents. The following combines Figures 1-4 Describe the method and device for analyzing and processing the quality of financial documents of the present invention, and describe its embodiments in detail.

[0027] The following is a detailed description of the embodiments based on the method for analyzing and processing the quality of financial documents according to the present invention. As Figure 1 shown, it is one of the flow diagrams of the method for analyzing and processing the quality of financial documents provided by the present invention, and the specific implementation process includes the following steps: Step 101, generate a quality inspection task corresponding to the analysis and processing of the quality of financial documents.

[0028] In the embodiment of the present invention, the server needs to first obtain the type of financial documents input by the user terminal, the sampling ratio or sampling quantity of the financial documents, the target completion time of the financial document processing task, the time interval when the financial documents are generated, and custom conditions. According to the type of the financial documents, the sampling ratio or sampling quantity of the financial documents, the target completion time of the financial document processing task, the date interval when the financial documents are generated, and the custom conditions, a corresponding quality inspection task is generated. Among them, each quality inspection task in the quality inspection task generates a corresponding plurality of financial document information when performing random sampling quality inspection.

[0029] Specifically, the custom conditions can be used to customize the extraction scope of financial documents. For example, an amount range can be set for payment - type financial documents, and data of financial documents with an amount greater than a fixed amount can be quality - inspected. The type of the financial document can be different in the financial management system, with different financial documents carrying different operations. When conducting quality inspection, the specific type of the financial document can be selected to perform quality inspection on certain types of operations. In the sampling ratio or sampling quantity of the financial document, if the sampling ratio is set, the number of tasks will be obtained according to the total quantity of financial documents to be quality - inspected; if the sampling quantity is set, the quality inspection will be directly carried out according to the sampling quantity. Regardless of which strategy is adopted, the extraction process should conform to the binomial distribution. The target completion time of the financial document processing task is that after the quality inspection task is issued, the quality inspection task should be completed before the specified date (i.e., the target completion time). The time interval when the financial document is generated is used to set the time range of the financial documents to be quality - inspected. For example, the time range for quality inspection is the financial documents of a certain month or a certain quarter.

[0030] In addition, pre - sampling processing can be performed based on the quality inspection task. By pre - sampling, the number, proportion, etc. of different documents extracted can be viewed to obtain the pre - sampling processing result. According to the pre - sampling processing result, it is judged whether the setting of the quality inspection task meets the preset conditions (i.e., to confirm whether the setting of the quality inspection task is reasonable). When the setting of the quality inspection task meets the preset conditions (such as after confirming that the setting of the quality inspection task is correct), random sampling processing is performed according to the quality inspection task to obtain the corresponding information of the financial documents to be quality - inspected.

[0031] Step 102: Perform random sampling processing according to the quality inspection task to obtain the corresponding information of the financial documents to be quality - inspected.

[0032] In an embodiment of the present invention, the server can obtain the digital identifiers of all financial documents corresponding to the quality inspection task according to the type of the financial document and the time interval when the financial document is generated, and store the digital identifiers of all the financial documents in a preset storage area in ascending order. Extract the digital identifiers of all the financial documents in the storage area according to the sampling ratio or sampling quantity of the financial documents to obtain a target number of digital identifiers; extract the corresponding financial documents according to the target number of digital identifiers to obtain the first target financial documents. Analyze and process the first target financial documents based on a preset financial document weight prediction model to obtain the weight values respectively corresponding to the first target financial documents output by the financial document weight prediction model. Among them, the financial document weight prediction model is a neural network model obtained by iterative training based on preset sample financial documents and the weight value labels corresponding to the sample financial documents. Sort the weight values corresponding to the first target financial documents from high to low to obtain a weight value sorting result. Extract the first target financial documents with the preset target number according to the weight value sorting result as the financial documents to be quality inspected. For example,

[0033] Obtain all document identifiers within this range (i.e., the digital identifiers of all financial documents corresponding to the quality inspection task) according to the type of the financial document and the time interval when the financial document is generated, and then place all the document identifiers in a preset storage area. Each financial document corresponds to a unique subscript (i.e., digital identifier), which is arranged in ascending order from 0 and increases sequentially. Calculate the number of samples to be inspected according to the set sampling ratio. If the quality inspection is set by quantity, directly use the set quantity. Use a random sampling algorithm, and the random value range is from 0 to the maximum subscript of the preset storage area. Generate a set of non-repeating random numbers in a loop, and the number of random times is the number of financial documents to be extracted * N (for example, N is 2). The subscripts corresponding to these random numbers are the subscripts of the financial documents to be extracted. Extract the corresponding financial document information according to the subscript of the financial document to obtain the first target financial document, and calculate the weight of the financial document (i.e., the first target financial document) using the financial document weight prediction model. For example, the weight value can be a weight value from 0.1 to 1. Then sort according to the corresponding weight value. For example, take 1 / 2 (this 1 / 2 corresponds to N. If N is 3, then 1 / 3 can be taken) of the financial documents to generate the financial documents to be quality inspected. The financial document weight prediction model is a document weight prediction model. It can be a neural network model obtained by training in combination with manual annotation using past business data.

[0034] Among them, when the server extracts the digital identifiers of all the financial documents in the storage area according to the sampling ratio or sampling quantity of the financial documents to obtain the target quantity of digital identifiers, it can call a preset random sampling algorithm and, according to the sampling ratio or sampling quantity of the financial documents, generate a set of non-repeating random numbers in the corresponding random value range in a loop; among them, the value of the random number corresponds to the value of the digital identifier of the financial document in the storage area; the random value range is the value range formed between the minimum value of the digital identifier of the financial document and the maximum value of the digital identifier of the financial document; the quantity of the random numbers is N times the quantity of the financial documents to be quality-checked corresponding to the sampling ratio or sampling quantity of the financial documents, where N is a positive integer greater than or equal to 2, such as N = 2. Based on the random numbers, the digital identifiers of all the financial documents in the storage area are extracted to obtain the target quantity of digital identifiers. That is, according to the quality-check task, random sampling is performed through the random sampling algorithm, and a batch of financial document information to be quality-checked will be generated for each quality-check task.

[0035] Step 103: Perform data quality-check processing on the financial documents to be quality-checked based on a preset audit rule to obtain a financial document quality-check result; among them, the audit rule includes the limit of the amount corresponding to the financial document to be quality-checked and the target fields that are prohibited from appearing in the financial document to be quality-checked of the target type.

[0036] Specifically, the server performs matching analysis on the data in the financial document to be quality-checked and the content in the audit rule. In the case where the amount data in the financial document to be quality-checked exceeds the limit of the amount corresponding to the financial document to be quality-checked, and / or in the case where the field data in the financial document to be quality-checked has a field that matches the target field prohibited from appearing in the financial document to be quality-checked corresponding thereto, the financial document to be quality-checked is determined as an abnormal financial document; in the case where the amount data in the financial document to be quality-checked does not exceed the limit of the amount corresponding to the financial document to be quality-checked, and the field data in the financial document to be quality-checked does not have a field that matches the target field prohibited from appearing in the financial document to be quality-checked corresponding thereto, the financial document to be quality-checked is determined as a normal financial document; the abnormal financial document and the normal financial document are used as the financial document quality-check result. After performing data quality-check processing on the financial documents to be quality-checked based on a preset audit rule to obtain a financial document quality-check result, it further includes: in the case where the financial document quality-check result includes an abnormal financial document, sending the abnormal financial document included in the financial document quality-check result to a preset audit node or a review node. The server is a computer system.

[0037] That is, the server determines whether the financial document to be quality-checked is qualified according to a preset review rule. The review rule is that according to business requirements, the server system provides a set of rule judgment functions. It supports different business rules for configuring different types of financial documents. For example, for contract documents, the amount cannot be less than 100,000; for reimbursement documents, the remarks cannot contain words such as 'field x' and 'field xx', and the amount cannot exceed 2,000. In addition, after performing data quality inspection processing on the financial document to be quality-checked based on the preset review rule and obtaining the financial document quality inspection result, it further includes: in the case that the financial document quality inspection result includes abnormal financial documents, sending the abnormal financial documents included in the financial document quality inspection result to a preset review node or review node. The user terminal of the review node or review node can also modify the judgment result according to the user input parameter to handle the financial documents misjudged by the review rule. As Figure 2 shown, during the rectification task assignment process, for unqualified data (i.e., abnormal financial documents), the computer system will query the approval process of the abnormal financial document, judge whether there is a review node or review node in the approval process, and automatically obtain the information of the corresponding original reviewer or reviewer. The computer system assigns the rectification task to the original reviewer or reviewer. During the rectification process, the user can perform off-line account adjustment operations according to the instructions of the computer system. The results of the rectification operations are recorded in the computer system. During the rectification feedback process, after the rectification is completed, the original reviewer or reviewer fills in the rectification feedback form in the computer system. If the abnormal financial document cannot be rectified, the original reviewer or reviewer also needs to fill in the rectification feedback form in the system and explain the reason, so as to obtain the rectification feedback form filled in by the original reviewer or reviewer and the reason explained by it. During the re-quality inspection process, after the rectification feedback form is submitted, the computer system automatically performs quality inspection again.

[0038] When formulating the quality inspection task of the present invention, the scope of quality inspection documents can be determined according to multiple dimensions to ensure strengthened quality inspection of key documents. For example, the scope to be quality-checked can be customized according to the time range, amount range, document business conditions (such as: whether it is a contract type, whether payment is required), etc. Provide pre-sampling prediction, and the prediction results include the total number of documents to be quality-checked and the number of samples to be taken this time, so as to reasonably allocate the quality inspection tasks.

[0039] The financial document quality analysis and processing method of the present invention generates a quality inspection task corresponding to the financial document quality analysis and processing, performs random sampling processing according to the quality inspection task to obtain the corresponding information of the financial document to be quality-checked, and then performs data quality inspection processing on the financial document to be quality-checked based on a preset review rule to obtain a financial document quality inspection result. The review rule includes the limit of the amount corresponding to the financial document to be quality-checked and the target fields that are prohibited from appearing in the target type of financial documents to be quality-checked, and it can effectively improve the efficiency and accuracy of the financial document quality analysis and processing.

[0040] The financial document quality analysis and processing device provided by the present invention will be described below. The financial document quality analysis and processing device described below can be correspondingly referred to the financial document quality analysis and processing method described above. Refer to Figure 3 As shown, it is a schematic structural diagram of the financial document quality analysis and processing device provided by the present invention. The financial document quality analysis and processing device described in the present invention specifically includes the following parts: A quality inspection task generation unit 301, configured to generate a quality inspection task corresponding to the financial document quality analysis and processing.

[0041] A financial document acquisition unit 302, specifically performing random sampling processing according to the quality inspection task to obtain corresponding financial document information to be quality inspected.

[0042] A financial document review unit 303, configured to perform data quality inspection processing on the financial document to be quality inspected based on a preset review rule to obtain a financial document quality inspection result; wherein, the review rule includes a limit on the amount corresponding to the financial document to be quality inspected and a target field that is prohibited from appearing in the financial document to be quality inspected of the target type.

[0043] According to a financial document quality analysis and processing device of the present invention, the financial document acquisition unit is specifically configured to: According to the type of the financial document and the time interval when the financial document is generated, obtain digital identifiers of all financial documents corresponding to the quality inspection task, and store the digital identifiers of all financial documents in a preset storage area in ascending order; Extract digital identifiers of the all financial documents in the storage area according to the sampling ratio or sampling quantity of the financial document to obtain a target quantity of digital identifiers; extract corresponding financial documents according to the target quantity of digital identifiers to obtain a first target financial document; Perform analysis processing on the first target financial document based on a preset financial document weight prediction model to obtain weight values respectively corresponding to the first target financial document output by the financial document weight prediction model; wherein, the financial document weight prediction model is a neural network model obtained by iterative training based on preset sample financial documents and weight value labels corresponding to the sample financial documents; Sort the weight values corresponding to the first target financial document from high to low to obtain a weight value sorting result; extract the first target financial documents of a preset target quantity according to the weight value sorting result as the financial documents to be quality inspected.

[0044] According to a financial document quality analysis and processing device of the present invention, the financial document review unit is specifically configured to: Match and analyze the data in the financial document to be quality - inspected with the content in the audit rule. When the amount data in the financial document to be quality - inspected exceeds the limit of the corresponding amount of the financial document to be quality - inspected, and / or when there is a field in the field data of the financial document to be quality - inspected that matches the target field that is prohibited from appearing in the corresponding financial document to be quality - inspected, determine the financial document to be quality - inspected as an abnormal financial document; when the amount data in the financial document to be quality - inspected does not exceed the limit of the corresponding amount of the financial document to be quality - inspected, and there is no field in the field data of the financial document to be quality - inspected that matches the target field that is prohibited from appearing in the corresponding financial document to be quality - inspected, determine the financial document to be quality - inspected as a normal financial document; use the abnormal financial document and the normal financial document as the financial document quality - inspection result.

[0045] According to a financial document quality analysis and processing device of the present invention, the method of extracting digital identifiers of all the financial documents in the storage area according to the sampling ratio or sampling quantity of the financial documents specifically includes: Call a preset random sampling algorithm, and generate a set of non - repeating random numbers in a corresponding random value range according to the sampling ratio or sampling quantity of the financial documents; wherein, the value of the random number corresponds to the value of the digital identifier of the financial document in the storage area; the random value range is the value range formed between the minimum value of the digital identifier of the financial document and the maximum value of the digital identifier of the financial document; the number of random numbers is N times the number of financial documents to be quality - inspected corresponding to the sampling ratio or sampling quantity of the financial documents, where N is a positive integer greater than or equal to 2. Extract digital identifiers of all the financial documents in the storage area based on the random numbers to obtain a target number of digital identifiers.

[0046] According to a financial document quality analysis and processing device of the present invention, after obtaining the financial document quality - inspection result by performing data quality - inspection processing on the financial document to be quality - inspected based on a preset audit rule, it further includes: an abnormal document processing unit, which is used to send the abnormal financial documents included in the financial document quality - inspection result to a preset audit node or review node when the financial document quality - inspection result includes abnormal financial documents.

[0047] According to a financial document quality analysis and processing device of the present invention, the quality - inspection task generation unit specifically is used for: Obtain the type of the financial document, the sampling ratio or sampling quantity of the financial document, the target completion time of the financial document processing task, the time interval when the financial document is generated, and custom conditions input by the user terminal. Generate corresponding quality inspection tasks according to the type of the financial document, the sampling ratio or sampling quantity of the financial document, the target completion time of the financial document processing task, the date range when the financial document is generated, and the custom conditions; wherein, when each quality inspection task in the quality inspection tasks performs random sampling quality inspection, a corresponding plurality of financial document information is generated.

[0048] The financial document quality analysis and processing device provided by the present invention generates a quality inspection task corresponding to the financial document quality analysis and processing, performs random sampling processing according to the quality inspection task, obtains corresponding financial document information to be quality inspected, and then performs data quality inspection processing on the financial document to be quality inspected based on a preset audit rule to obtain a financial document quality inspection result. The audit rule includes the limit of the amount corresponding to the financial document to be quality inspected and the target fields that are prohibited from appearing in the financial document to be quality inspected of the target type, which can effectively improve the efficiency and accuracy of the financial document quality analysis and processing.

[0049] Figure 4 An example of a schematic physical structure diagram of an electronic device is as Figure 4 shown. The electronic device (i.e., the electronic device) may include: a processor 401, a communication interface 404, a memory 402, and a communication bus 403. Among them, the processor 401, the communication interface 404, and the memory 402 complete mutual communication through the communication bus 403. The processor 401 can call the logic instructions in the memory 402 to execute the financial document quality analysis and processing method, and the method includes: generating a quality inspection task corresponding to the financial document quality analysis and processing; performing random sampling processing according to the quality inspection task to obtain corresponding financial document information to be quality inspected; performing data quality inspection processing on the financial document to be quality inspected based on a preset audit rule to obtain a financial document quality inspection result; wherein, the audit rule includes the limit of the amount corresponding to the financial document to be quality inspected and the target fields that are prohibited from appearing in the financial document to be quality inspected of the target type.

[0050] In addition, when the logical instructions in the above-mentioned memory 402 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0051] On the other hand, the present application also provides a computer program product. The computer program product includes a computer program that can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the financial document quality analysis processing method provided by the above-mentioned various methods. The method includes: generating a quality inspection task corresponding to the financial document quality analysis processing; performing random sampling processing according to the quality inspection task to obtain corresponding financial document information to be quality inspected; performing data quality inspection processing on the financial document to be quality inspected based on a preset audit rule to obtain a financial document quality inspection result; where the audit rule includes the limit of the amount corresponding to the financial document to be quality inspected and the target fields that are prohibited from appearing in the financial document to be quality inspected of the target type.

[0052] On another aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium includes a stored program. When the program runs, it executes the financial document quality analysis processing method provided by the above-mentioned various methods. The method includes: generating a quality inspection task corresponding to the financial document quality analysis processing; performing random sampling processing according to the quality inspection task to obtain corresponding financial document information to be quality inspected; performing data quality inspection processing on the financial document to be quality inspected based on a preset audit rule to obtain a financial document quality inspection result; where the audit rule includes the limit of the amount corresponding to the financial document to be quality inspected and the target fields that are prohibited from appearing in the financial document to be quality inspected of the target type.

[0053] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative effort.

[0054] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0055] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A method for analyzing and processing financial document quality, characterized in that: include: Generate quality inspection tasks corresponding to financial document quality analysis and processing; Perform random sampling according to the quality inspection tasks to obtain corresponding financial document information to be inspected; Based on preset audit rules, data quality inspection is performed on the financial documents to be inspected to obtain financial document quality inspection results; wherein the audit rules include a limit on the amount corresponding to the financial documents to be inspected and a prohibited target field corresponding to the target type of financial documents to be inspected.

2. The financial document quality analysis and processing method according to claim 1, characterized in that: The random sampling process is performed according to the quality inspection task to obtain the corresponding financial document information to be inspected, including: According to the type of the financial document and the time interval in which the financial document was generated, the digital identifiers of all the financial documents corresponding to the quality inspection task are obtained, and the digital identifiers of all the financial documents are stored in a preset storage area in ascending order; Extracting the digital identifiers of all the financial documents in the storage area according to the sampling ratio or the sampling quantity of the financial documents to obtain the digital identifiers of a target number; extracting the corresponding financial documents according to the digital identifiers of the target number to obtain a first target financial document; The first target financial document is analyzed and processed based on a preset financial document weight prediction model to obtain weight values ​​corresponding to the first target financial document output by the financial document weight prediction model; wherein the financial document weight prediction model is a neural network model obtained by iterative training based on preset sample financial documents and weight value labels corresponding to the sample financial documents; The weight values ​​corresponding to the first target financial documents are sorted from high to low to obtain a weight value sorting result; and a preset target quantity of first target financial documents are extracted according to the weight value sorting result as the financial documents to be inspected.

3. The financial document quality analysis and processing method according to claim 1, characterized in that: The data quality inspection process is performed on the financial documents to be inspected based on the preset audit rules to obtain the financial document quality inspection results, specifically including: The data in the financial document to be quality inspected is matched and analyzed with the content in the audit rules. When the amount data in the financial document to be quality inspected exceeds the limit of the amount corresponding to the financial document to be quality inspected, and / or when the field data in the financial document to be quality inspected contains a field that matches the prohibited target field corresponding to the financial document to be quality inspected, the financial document to be quality inspected is determined to be an abnormal financial document; when the amount data in the financial document to be quality inspected does not exceed the limit of the amount corresponding to the financial document to be quality inspected, and when the field data in the financial document to be quality inspected does not contain a field that matches the prohibited target field corresponding to the financial document to be quality inspected, the financial document to be quality inspected is determined to be a normal financial document; the abnormal financial document and the normal financial document are used as the financial document quality inspection results.

4. The financial document quality analysis and processing method according to claim 2, characterized in that: The step of extracting the digital identifiers of all the financial documents in the storage area according to the sampling ratio or the sampling quantity of the financial documents to obtain the digital identifiers of a target quantity specifically includes: Calling a preset random sampling algorithm, according to the sampling ratio or sampling quantity of the financial document, cyclically generating a group of non-repeating random numbers within a corresponding random value range; wherein the value of the random number corresponds to the value of the digital identification of the financial document in the storage area; the random value range is a value range formed between the minimum value of the digital identification of the financial document and the maximum value of the digital identification of the financial document; the number of the random numbers is N times the number of financial documents to be inspected corresponding to the sampling ratio or sampling quantity of the financial document, wherein N is a positive integer greater than or equal to 2; The digital identifications of all the financial documents in the storage area are extracted based on the random number to obtain a target number of digital identifications.

5. The financial document quality analysis and processing method according to claim 1, characterized in that: After performing data quality inspection on the financial documents to be inspected based on the preset audit rules and obtaining the financial document quality inspection results, the method further includes: In the case that the financial document quality inspection result includes an abnormal financial document, the abnormal financial document included in the financial document quality inspection result is sent to a preset audit node or a review node.

6. The financial document quality analysis and processing method according to claim 1, characterized in that: The quality inspection tasks corresponding to the generated financial document quality analysis and processing specifically include: Obtain the type of financial document input by the user, the sampling ratio or sampling quantity of the financial document, the target completion time of the financial document processing task, the time interval for the generation of the financial document, and the custom conditions; Generate corresponding quality inspection tasks according to the type of the financial document, the sampling ratio or sampling quantity of the financial document, the target completion time of the financial document processing task, the date range in which the financial document is generated, and the custom conditions; wherein each quality inspection task in the quality inspection task generates corresponding multiple financial document information when performing random sampling quality inspection.

7. A financial document quality analysis and processing device, characterized in that: include: A quality inspection task generation unit is used to generate quality inspection tasks corresponding to the quality analysis and processing of financial documents; A financial document acquisition unit performs random sampling according to the quality inspection task to obtain corresponding financial document information to be inspected; A financial document review unit is used to perform data quality inspection on the financial document to be quality inspected based on preset review rules to obtain financial document quality inspection results; wherein the review rules include the limit on the amount corresponding to the financial document to be quality inspected and the prohibited target fields corresponding to the target type of financial document to be quality inspected.

8. 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 program, the financial document quality analysis and processing method as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the financial document quality analysis and processing method as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the financial document quality analysis and processing method as claimed in any one of claims 1 to 6 is implemented.

Images