Reconciliation method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of data processing, and provides a reconciliation method, which comprises the following steps of: obtaining data to be reconciliated; preprocessing the business data and the financial data to obtain standard business data and standard financial data; screening the standard business data and the standard financial data through a preset account checking rule to obtain target business data and target financial data; performing difference identification on the target business data and the target financial data through a difference identification model to obtain a difference identification result; and when the difference identification result represents that at least one data difference item exists, performing data analysis on all the data difference items to obtain a difference reason, and generating an account checking report according to the data difference items and the difference reason. The method is applied to the financial field. According to the invention, screening is carried out through the preset reconciliation rule and identification is carried out through the difference identification model, so that automatic reconciliation of the data is realized, identification of the data difference item is realized, and the efficiency and accuracy of data reconciliation are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a reconciliation method, device, computer equipment and storage medium. Background Art

[0002] Usually, enterprises use business systems to record business data and financial systems to record financial data. These two types of data are often stored independently. When financial personnel check financial data and business data, they need to operate in the business system to query the business data associated with the financial data. Since financial personnel have to repeatedly compare and determine the relationship between business data and financial data during the query process, the checking efficiency is low. In addition, due to the complexity of business processes and the diversity of data sources, traditional manual reconciliation methods are often inefficient and have low accuracy, and are difficult to meet the needs of rapidly developing businesses. Summary of the invention

[0003] The embodiments of the present invention provide a reconciliation method, apparatus, computer equipment and storage medium to solve the problem of low reconciliation efficiency and low accuracy caused by manual reconciliation in the prior art.

[0004] A reconciliation method, comprising: Acquire the data to be reconciled, wherein the data to be reconciled includes business data in the business system and financial data in the financial system; Preprocessing the business data and the financial data to obtain standard business data and standard financial data; Obtaining a preset reconciliation rule, and filtering and processing the standard business data and the standard financial data according to the preset reconciliation rule to obtain target business data and target financial data; Performing difference identification on the target business data and the target financial data through a difference identification model to obtain a difference identification result; When the difference identification result indicates that there is at least one data difference item, data analysis is performed on all the data difference items to obtain the difference reasons corresponding to each of the data difference items, and a reconciliation report corresponding to the data to be reconciled is generated based on the data difference items and the difference reasons.

[0005] A reconciliation device, comprising: A data acquisition module, used to acquire data to be reconciled, wherein the data to be reconciled includes business data in the business system and financial data in the financial system; A data processing module, used for preprocessing the business data and the financial data to obtain standard business data and standard financial data; A data screening module, used to obtain preset reconciliation rules, and screen the standard business data and the standard financial data according to the preset reconciliation rules to obtain target business data and target financial data; A difference identification module, used to identify the difference between the target business data and the target financial data through a difference identification model to obtain a difference identification result; A report generation module is used to perform data analysis on all the data difference items when the difference identification result indicates the existence of at least one data difference item, obtain the difference reason corresponding to each data difference item, and generate a reconciliation report corresponding to the data to be reconciled based on the data difference items and the difference reason.

[0006] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned reconciliation method when executing the computer program.

[0007] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned reconciliation method is implemented.

[0008] The present invention provides a reconciliation method, device, equipment and medium. The method realizes the conversion and standardization of financial data and business data by preprocessing financial data and business data, and realizes the acquisition of standard business data and standard financial data. The standard business data and standard financial data are screened and processed by preset reconciliation rules, so as to realize the acquisition of target business data and target financial data, and reduce the number of subsequent reconciliations. The target business data and target financial data are identified by a difference recognition model, and the difference recognition results are obtained, thereby realizing the identification of data difference items, realizing automatic reconciliation of data, and thus improving the accuracy and efficiency of data reconciliation. By performing data analysis on all data difference items, the analysis of the causes of the differences is realized, the causes of the differences are obtained, and then the generation of reconciliation reports is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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.

[0010] Figure 1 Schematic diagram of an application environment of a reconciliation method in one embodiment of the present invention; Figure 2is a flow chart of a reconciliation method in one embodiment of the present invention; Figure 3 is a flow chart of a reconciliation method in another embodiment of the present invention; Figure 4 is a principle block diagram of an account reconciliation device in one embodiment of the present invention; Figure 5 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0011] 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.

[0012] The reconciliation method provided in the embodiment of the present invention can be applied as follows: Figure 1 Specifically, the reconciliation method is applied in a reconciliation device, which includes Figure 1 The client and server shown in the figure communicate with each other through the network to solve the problem that the local stylization of the image in the prior art cannot achieve the expected effect. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The client, also known as the user end, refers to a program that corresponds to the server and provides classification services to customers. The client can be installed on, but is not limited to, various computers, laptops, smart phones, tablets, and portable wearable devices.

[0013] In one embodiment, if Figure 2 As shown, a reconciliation method is provided, which is applied in Figure 1 The server in the example is used as an example to illustrate the process, including the following steps: S10: Acquire the data to be reconciled, where the data to be reconciled includes business data in the business system and financial data in the financial system.

[0014] S20: Preprocessing the business data and the financial data to obtain standard business data and standard financial data.

[0015] It can be understood that the data to be reconciled includes business data in the business system and financial data in the financial system. Business data refers to data generated in business activities recorded in the business system. Financial data refers to data generated in financial activities recorded in the financial system. Standard business data refers to data obtained after conversion and standardization of business data. Standard financial data refers to data obtained after conversion and standardization of financial data.

[0016] Specifically, the data to be reconciled is obtained, that is, through access request and verification of access rights, and when the access rights are granted, business data is obtained from the business system, and financial data is obtained from the financial system. Then, the business data and financial data are pre-processed, that is, the business data and financial data are converted and processed respectively, that is, the business data and financial data are converted into a preset format, and then the converted business data and financial data are standardized, that is, the converted business data and financial data are processed again according to the standard, so as to obtain standard business data corresponding to the business data, and standard financial data corresponding to the financial data.

[0017] S30, obtaining a preset reconciliation rule, and screening the standard business data and the standard financial data according to the preset reconciliation rule to obtain target business data and target financial data.

[0018] Understandably, the target business data refers to the business data that complies with the preset reconciliation rules. The target financial data refers to the financial data that complies with the preset reconciliation rules. The preset reconciliation rules refer to the reconciliation scenario requirements set in advance and used to filter data.

[0019] Specifically, the preset reconciliation rules are obtained, and the standard business data and standard financial data are screened and processed by the preset reconciliation rules, that is, the data in the standard business data that meets the reconciliation scenario is screened by the reconciliation scenario corresponding to the reconciliation link in the preset reconciliation rules. When the standard business data does not meet the reconciliation scenario, the standard business data is deleted; when the standard business data meets the reconciliation scenario, the standard business data is determined as the target business data. Similarly, the data in the standard financial data that meets the reconciliation scenario is screened by the reconciliation scenario corresponding to the reconciliation link in the preset reconciliation rules. When the standard financial data does not meet the reconciliation scenario, the standard financial data is deleted; when the standard financial data meets the reconciliation scenario, the standard financial data is determined as the target financial data.

[0020] S40, performing difference identification on the target business data and the target financial data through a difference identification model to obtain a difference identification result.

[0021] Understandably, data difference items refer to different data information between the target business data and the target financial data. For example, the business data contains information that is not contained in the financial data, or the amounts in the business data and the financial data are different. The difference identification model refers to the model used to identify different data in different data.

[0022] Specifically, a difference recognition model is obtained, and all target business data and all target financial data are input into the difference recognition model, and the difference recognition between all input target business data and all target financial data is performed through the difference recognition ability learned during training, that is, the target business data and the target financial data are matched one by one, and when the target business data and the target financial data are matched successfully, the target business data and the target financial data are associated, so that all target business data and the target financial data are matched and identified, and a difference recognition result can be obtained. Among them, all successfully matched data are identified and determined as a difference recognition result representing that there is no difference, and the remaining target business data are determined as a difference recognition result of data difference items with business and financial types, and the remaining target financial data are determined as a difference recognition result of data difference items with business and financial types. Then, the data amount is compared between all associated target business data and target financial data, so as to detect whether the data amount between the target business data and the target financial data is the same. If not, it is determined as a difference recognition result of data difference items with different amounts.

[0023] S50, when the difference identification result indicates that there is at least one data difference item, data analysis is performed on all the data difference items to obtain the difference reasons corresponding to each of the data difference items, and a reconciliation report corresponding to the data to be reconciled is generated according to the data difference items and the difference reasons.

[0024] It can be understood that the difference reason refers to the reason for the data difference obtained through analysis. The reconciliation report refers to the reconciliation result displayed to the user.

[0025] Specifically, after obtaining the difference recognition result, the difference recognition result is parsed to determine the meaning of the difference recognition result representation. When the difference recognition result representation has at least one data difference item, data analysis is performed on all data difference items, that is, based on the data content in the data difference item and the node corresponding to the data difference item, a cause analysis is performed to obtain the difference cause corresponding to the data difference item. Among them, the cause of each data difference item is analyzed one by one, that is, when there are data difference items of different types of amounts, the business process from business data to financial data is detected to determine whether the process is not standardized, or the data processing method in the business process is detected and compared with the document data to determine whether there is an input error, so as to determine the cause of the difference. When there are data difference items of the business type but not of the financial type, the information of the data difference item is detected to determine whether it complies with the business process, and the business data is re-issued to determine the node with the problem, or the log of the financial system is queried to determine whether the corresponding financial data is deleted by mistake, so as to obtain the cause of the difference. When there is a data difference item of the business type but not of the financial type, the log of the business system is queried to determine whether the corresponding business data is deleted by mistake, or the time when the data difference item appears in the financial system is analyzed to obtain the reason for the difference. Further, a reconciliation report corresponding to the data to be reconciled is generated according to the data difference item and the reason for the difference, that is, a reconciliation report template is obtained, and the data difference item and the reason for the difference are filled into the reconciliation report template to obtain the reconciliation report.

[0026] In an embodiment of the present invention, a reconciliation method is provided. The method realizes conversion and standardization of financial data and business data by preprocessing financial data and business data, and realizes acquisition of standard business data and standard financial data. The standard business data and standard financial data are screened and processed by preset reconciliation rules, so as to realize acquisition of target business data and target financial data, and reduce the number of subsequent reconciliations. Differences between target business data and target financial data are identified by a difference identification model, so as to realize acquisition of difference identification results, thereby realizing identification of data difference items, realizing automatic reconciliation of data, and thus improving the accuracy and efficiency of data reconciliation. By performing data analysis on all data difference items, analysis of the causes of the differences is realized, and the causes of the differences are obtained, so as to realize generation of a reconciliation report.

[0027] In one embodiment, before step S10, that is, before obtaining the data to be reconciled, the process further includes: S101, obtaining an account reconciliation access request including user related information, and verifying whether the user related information has access rights.

[0028] S102, when the user-related information has access rights, obtaining target data in a target system; the target system refers to at least one of the business system and the financial system.

[0029] S103, performing desensitization processing on the target data according to preset desensitization rules to obtain data to be reconciled.

[0030] Understandably, user-related information refers to information such as the account number for accessing the system, the system organization code, etc. A reconciliation access request refers to a request to access the corresponding target system. Access rights refer to the rights to access the system. The target system refers to at least one of the business system and the financial system. Preset desensitization rules refer to the data desensitization requirements and methods set in advance.

[0031] Specifically, before obtaining the data to be reconciled, obtain the reconciliation access request sent by the user, and then verify whether the user has the access right to access the target system based on the user-related information in the reconciliation access request, that is, compare the user-related information with the preset authorization information, so as to determine whether the preset authorization information includes the user-related information. When the preset authorization information includes the user-related information, it is determined that the user-related information has the access right. When the preset authorization information does not include the user-related information, it is determined that the user-related information does not have the access right. Further, when the user-related information has the access right, obtain the target data in the target system, that is, when the access right is obtained, access the target system, that is, access the business system, and obtain the business data in the business system. Similarly, access the financial system, obtain the financial data in the financial system, and determine all the acquired business data and all the financial data as the target data. Next, the preset desensitization rules are obtained, and the target data is desensitized according to the preset desensitization rules, that is, the data content that needs to be desensitized is determined according to the desensitization requirements in the preset desensitization rules, that is, the sensitive information in each data is determined, and then, the sensitive information in each data is desensitized according to the desensitization method in the preset desensitization rules, that is, the sensitive information is encrypted through the reversible encryption algorithm AES (Advanced Encryption Standard), so as to obtain the data to be reconciled.

[0032] In this embodiment, by performing permission verification on user-related information, it is ensured that the user has access rights, avoiding information leakage and ensuring data security. The target data is desensitized by preset desensitization rules, which realizes encryption of sensitive information in the target data and protection of sensitive information.

[0033] In one embodiment, in step S20, that is, preprocessing the business data and the financial data to obtain standard business data and standard financial data, includes: S201, performing data conversion on the business data and the financial data according to a conversion rule to obtain converted business data and converted financial data.

[0034] S202, performing standardization processing on the converted business data and the converted financial data according to standard rules to obtain standard business data and standard financial data.

[0035] It can be understood that converting business data refers to converting the format of business data. Converting financial data refers to converting the format of financial data. Conversion rules refer to rules for converting data formats. Standard rules refer to rules for standardizing data.

[0036] Specifically, after obtaining the data to be reconciled, the conversion rules are obtained, and the business data and the financial data are converted by the conversion rules, that is, the business data is formatted by the business conversion rules in the conversion rules, so as to obtain the converted business data. Similarly, the financial data is formatted by the financial conversion rules in the conversion rules, so as to obtain the converted financial data. Further, the standard rules are obtained, and the converted business data and the converted financial data are standardized by the standard rules, that is, the converted business data is standardized by the business standard rules in the standard rules, so as to obtain the standard business data. Similarly, the converted financial data is standardized by the financial standard rules in the standard rules, so as to obtain the standard financial data.

[0037] In this embodiment, the business data and financial data are converted by conversion rules, so as to obtain the converted business data and the converted financial data, and to convert the data format. The converted business data and the converted financial data are standardized by standard rules, so as to obtain the standard business data and the standard financial data, which facilitates the subsequent screening of data and improves the accuracy of the subsequent model in identifying the difference items.

[0038] In one embodiment, in step S30, the standard business data and the standard financial data are screened and processed by the preset reconciliation rule to obtain target business data and target financial data, including: S301, filtering and processing the standard business data through the reconciliation scenario corresponding to the reconciliation link in the preset reconciliation rule to obtain target business data.

[0039] S302, filtering and processing the standard financial data through the reconciliation scenario corresponding to the reconciliation link in the preset reconciliation rule to obtain target financial data.

[0040] Understandably, the reconciliation link refers to the node of reconciliation, such as financial business interaction. The reconciliation scenario refers to the specific type of data corresponding to, such as premium, compensation, handling fee and other scenarios.

[0041] Specifically, after obtaining the preset reconciliation rules, the reconciliation scenarios in the reconciliation link in the preset reconciliation rules are determined, so as to obtain the reconciliation scenarios corresponding to the business and the reconciliation scenarios corresponding to the finance. Then, the standard business data is screened and processed by the reconciliation scenarios corresponding to the reconciliation link in the preset reconciliation rules, that is, the reconciliation scenarios of the standard business data are scene-matched by the reconciliation scenarios in the preset reconciliation rules, so as to determine whether the reconciliation scenarios of the standard business data belong to the preset reconciliation rules. If they belong to the preset reconciliation rules, the standard business data is determined as the target business data, so as to filter out the target business data from all the standard business data. Similarly, the standard financial data is screened and processed by the reconciliation scenarios corresponding to the reconciliation link in the preset reconciliation rules, that is, the reconciliation scenarios of the standard financial data are scene-matched by the reconciliation scenarios in the preset reconciliation rules, so as to determine whether the reconciliation scenarios of the standard financial data belong to the preset reconciliation rules. If they belong to the preset reconciliation rules, the standard financial data is determined as the target business data, so as to filter out the target financial data from all the standard financial data.

[0042] In this embodiment, the standard business data is screened and processed through the reconciliation scenario, so as to realize the screening of the target business data, reduce the number of subsequent reconciliations, and improve the efficiency of reconciliation. The standard financial data is screened and processed through the reconciliation scenario, so as to realize the screening of the target financial data, reduce the number of subsequent reconciliations, and improve the efficiency of reconciliation.

[0043] In one embodiment, in step S40, the target business data and the target financial data are subjected to difference identification using a difference identification model to obtain a difference identification result, including: S401, matching the target business data and the target financial data one by one through a difference identification model, if the target business data are all matched with the same data as the target financial data, and the data amounts are the same, a difference identification result indicating that there is no difference is obtained.

[0044] S402: If the target business data does not match the target financial data, a difference recognition result of a data difference item of the business-no-finance type is determined.

[0045] S403: If the target financial data does not match the target business data, a difference identification result of a data difference item of the business type with finance but without finance is determined.

[0046] S404: If data identical to the target business data is matched in the target financial data and there is a difference in the data amount, a difference identification result of data difference items of different types of amounts is determined.

[0047] Understandably, the business without finance type means that the data is not included in the business data but included in the financial data. The business with finance without type means that the data is not included in the financial data but included in the business data. The amount of different types means that the amount of data in the business data and the amount of data in the financial data are different. The difference recognition result of no difference means that the amount of data in the target business data and the amount of data in the target financial data are the same.

[0048] Specifically, after obtaining the target business data and the target financial data, a difference recognition model is obtained, and all the target business data and all the target financial data are input into the difference recognition model, and the target business data and the target financial data are matched one by one through the difference recognition model, that is, through the ability learned by the difference recognition model during training, the target business data is matched to the corresponding target financial data, that is, each target business data is matched with the target financial data respectively, so as to determine the target financial data corresponding to the target business data, and the remaining target business data that is not matched to the corresponding data is determined as the difference recognition result of the data difference item of the business with financial but not type. Similarly, the remaining target financial data that is not matched to the corresponding data is determined as the difference recognition result of the data difference item of the business with financial but not type. The successfully matched target business data and target financial data are verified in amount, that is, the data amount in the target business data and the data amount in the target financial data are compared to see whether they are equal. If the data amount in the target business data and the data amount in the target financial data are equal, a difference recognition result indicating that there is no difference is obtained. If the data amount in the target business data and the data amount in the target financial data are not equal, it is determined as the difference recognition result of the data difference item of different types of amount.

[0049] In this embodiment, the target business data and the target financial data are matched one by one through the difference identification model, so that the difference identification results are obtained, thereby realizing the determination of different types of data difference items, thereby improving the efficiency and accuracy of difference item identification.

[0050] In one embodiment, before step S40, that is, before the difference identification model is used to identify the difference between the target business data and the target financial data, the method further includes: S404, obtaining a sample data set, where the sample data set includes at least one sample training data and a sample label corresponding to each sample training data.

[0051] Understandably, the sample training data refers to historical business data and historical financial data. One sample training data is associated with a sample label, and the sample label is used to characterize the difference between the historical business data and the historical financial data in the sample training data. The sample training data and the sample label can be collected from different databases, or they can be prepared in advance and sent from the client to the database. Then, a sample training data set is constructed based on all the sample training data obtained and the sample labels corresponding to each sample training data.

[0052] S405: performing identification and prediction on all the sample training data through a preset training model to obtain a prediction result corresponding to each of the sample training data.

[0053] It can be understood that the prediction result refers to the result obtained by the preset training model identifying the sample training data. In this embodiment, the preset training model adopts a convolutional neural network.

[0054] Specifically, a preset training model is obtained, and all sample training data are input into the preset training model, and all sample training data are identified and predicted through the preset training model, that is, the preset training model compares the historical business data and the historical financial data in the sample training data, that is, the historical business data and the historical financial data are matched one by one, so as to determine the difference items between the historical business data and the historical financial data, that is, the historical business data has a type that the historical financial data does not have, the historical business data does not have a type but the historical financial data has a type, and the types of amounts in the historical business data and the historical financial data are different, and all the difference items are determined as prediction results.

[0055] S406: Determine a prediction loss value of a preset training model according to sample labels and prediction results corresponding to the same sample training data.

[0056] Understandably, the prediction loss value is generated during the prediction process of the sample training data.

[0057] Specifically, after obtaining the prediction result, all prediction results corresponding to the sample data are arranged according to the order of the sample data in the sample data set, and then the prediction results associated with the sample data are compared with the sample labels of the sample data with the same sequence; that is, according to the sorting of the sample data, the sample label corresponding to the first sample data is compared with the prediction result corresponding to the first sample data, and the loss value between the sample label and the prediction result is determined by the loss function; the sample label corresponding to the second sample data is compared with the prediction result corresponding to the second sample data, and the loss value between the sample label and the prediction result is determined by the loss function, until all sample labels are compared with the prediction results, the prediction loss value of the preset training model can be obtained.

[0058] S407, when the predicted loss value reaches a preset convergence condition, determining the preset training model after convergence as a difference recognition model.

[0059] Understandably, the convergence condition may be that the predicted loss value is less than a set threshold, or that the predicted loss value is very small and will not decrease after 50,000 calculations, and the training is stopped.

[0060] Specifically, after obtaining the predicted loss value, when the predicted loss value does not reach the preset convergence condition, the initial parameters of the preset training model are adjusted according to the predicted loss value, and all sample training data are re-input into the preset training model with the adjusted initial parameters, and the preset training model with the adjusted initial parameters is iteratively trained to obtain the predicted loss value corresponding to the preset training model with the adjusted initial parameters. Furthermore, when the predicted loss value does not reach the preset convergence condition, the initial parameters of the preset training model are adjusted again according to the predicted loss value, so that the predicted loss value of the preset training model with the adjusted initial parameters reaches the preset convergence condition. In this way, the accuracy of the preset training model becomes higher and higher, and the quality inspection results obtained are constantly approaching the correct results, until the predicted loss value of the preset training model reaches the preset convergence condition, and the preset training model after convergence is determined as the difference recognition model.

[0061] In the embodiment of the present invention, the preset training model is iteratively trained through a large amount of sample training data, and the overall loss value of the preset training model is calculated through the comparison loss function, so as to determine the predicted loss value of the preset training model. The initial parameters of the preset training model are adjusted according to the predicted loss value until the model converges, so as to realize the training of the difference recognition model, thereby ensuring that the difference recognition model has a higher expected effect.

[0062] In one embodiment, if Figure 3 As shown, after step S50, that is, when the difference identification result indicates that there is at least one data difference item, data analysis is performed on all the data difference items to obtain the difference reasons corresponding to each of the data difference items, and the following further includes: S60, obtaining a preset solution set, performing information matching on the difference cause and preset information in the preset solution set, and obtaining an information matching result.

[0063] S70, when the information matching result indicates that the difference cause is matched successfully, obtaining a preset solution corresponding to the preset information that successfully matches the difference cause, and processing the data difference item according to the preset solution.

[0064] S80: When the information matching result indicates that the difference reason matching fails, a notification is sent to a preset relevant person.

[0065] Understandably, the preset solution set refers to a set of solutions set in advance. The preset information refers to the difference reasons set in advance. The information matching result is used to indicate whether the difference reasons are matched successfully. The preset solution refers to the solution set in advance, such as data correction, process optimization, etc.

[0066] Specifically, after obtaining the difference reasons corresponding to each of the data difference items, a preset solution set is obtained, and then the difference reasons corresponding to each of the data difference items are matched with the preset information in the preset solution set, that is, all the difference reasons are matched with the preset information in the preset solution set one by one, so as to obtain the information matching result. Then, when the information matching result indicates that the difference reason matching fails, that is, when the preset solution is not matched in the preset solution set, a notification is sent to the preset relevant personnel. When the information matching result indicates that the difference reason is matched successfully, the preset solution corresponding to the preset information that successfully matches the difference reason is obtained, that is, when the difference reason and the preset information in the preset solution set are matched successfully, it is determined that the preset solution set includes a preset solution that solves the difference reason, so as to obtain the preset solution. And the data difference items are processed according to the preset solution, that is, the data difference items are processed according to the processing method in the preset solution.

[0067] In this embodiment, the information matching result is obtained through information matching, thereby obtaining the preset solution, and then processing the data difference items, ensuring the accuracy of the data.

[0068] 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.

[0069] In one embodiment, a reconciliation device is provided, which corresponds one-to-one to the reconciliation method in the above embodiment. Figure 4 As shown, the reconciliation device includes a data acquisition module 11, a data processing module 12, a data screening module 13, a difference identification module 14 and a report generation module 15. The functional modules are described in detail as follows: A data acquisition module 11 is used to acquire data to be reconciled, wherein the data to be reconciled includes business data in the business system and financial data in the financial system; A data processing module 12, used for preprocessing the business data and the financial data to obtain standard business data and standard financial data; The data screening module 13 is used to obtain a preset reconciliation rule, and screen the standard business data and the standard financial data according to the preset reconciliation rule to obtain target business data and target financial data; A difference identification module 14 is used to identify the difference between the target business data and the target financial data through a difference identification model to obtain a difference identification result; The report generation module 15 is used to perform data analysis on all the data difference items when the difference identification result indicates that there is at least one data difference item, obtain the difference reason corresponding to each data difference item, and generate a reconciliation report corresponding to the data to be reconciled based on the data difference items and the difference reason.

[0070] In one embodiment, the data acquisition module 11 includes: An authority verification unit, used to obtain an account reconciliation access request including user-related information, and verify whether the user-related information has access rights; A target data unit, used for acquiring target data in a target system when the user-related information has access rights; the target system refers to at least one of the business system and the financial system; The desensitization processing unit is used to perform desensitization processing on the target data according to preset desensitization rules to obtain data to be reconciled.

[0071] In one embodiment, the data processing module 12 includes: A data conversion unit, used to perform data conversion on the business data and the financial data according to a conversion rule to obtain converted business data and converted financial data; The standardization processing unit is used to perform standardization processing on the converted business data and the converted financial data through standard rules to obtain standard business data and standard financial data.

[0072] In one embodiment, the data screening module 13 includes: A target business data unit, used to filter and process the standard business data through the reconciliation scenario corresponding to the reconciliation link in the preset reconciliation rule to obtain target business data; The target financial data unit is used to filter and process the standard financial data through the reconciliation scenario corresponding to the reconciliation link in the preset reconciliation rule to obtain the target financial data.

[0073] In one embodiment, the difference identification module 14 includes: The first type unit is used to match the target business data and the target financial data one by one through a difference identification model, and if the target business data are all matched with the same data as the target financial data, and the data amounts are the same, a difference identification result indicating that there is no difference is obtained; A second type unit is used to determine a difference recognition result of a data difference item of the business-no-finance type if no data identical to the target financial data is matched in the target business data; A third type unit is used to determine a difference recognition result of a data difference item of the business type with finance but without type if no data identical to the target business data is matched in the target financial data; The fourth type unit is used to determine the difference identification result of the data difference item of different types of amounts if the same data as the target business data is matched in the target financial data and there is a difference in the data amounts.

[0074] In one embodiment, the device further comprises: An information matching result module is used to obtain a preset solution set, perform information matching on the difference cause and preset information in the preset solution set, and obtain an information matching result; a difference item processing module, configured to obtain a preset solution corresponding to the preset information that successfully matches the difference cause when the information matching result indicates that the difference cause is successfully matched, and process the data difference item according to the preset solution; The notification sending module is used to send a notification to a preset relevant person when the information matching result indicates that the difference reason matching fails.

[0075] In one embodiment, the device further comprises: A training data unit, used to obtain a sample data set, wherein the sample data set includes at least one sample training data and a sample label corresponding to each sample training data; A prediction result unit, used to identify and predict all the sample training data through a preset training model to obtain a prediction result corresponding to each of the sample training data; A loss prediction unit, used to determine a predicted loss value of a preset training model according to a sample label and a prediction result corresponding to the same sample training data; The model convergence unit is used to determine the preset training model after convergence as the difference recognition model when the predicted loss value reaches the preset convergence condition.

[0076] For the specific definition of the reconciliation device, please refer to the definition of the reconciliation method above, which will not be repeated here. Each module in the above reconciliation device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above 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.

[0077] 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 5 As shown. The computer device includes a processor, a memory, a network interface and a database connected via 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, 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 database of the computer device is used to store data used in the reconciliation method in the above embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a reconciliation method is implemented.

[0078] 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 above-mentioned reconciliation method when executing the computer program.

[0079] In one embodiment, 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 above-mentioned reconciliation method is implemented.

[0080] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented 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 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of 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), etc.

[0081] 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.

[0082] 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, a person 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 be included in the protection scope of the present invention.

Claims

1. A reconciliation method, characterized in that: include: Acquire the data to be reconciled, wherein the data to be reconciled includes business data in the business system and financial data in the financial system; Preprocessing the business data and the financial data to obtain standard business data and standard financial data; Obtaining a preset reconciliation rule, and filtering and processing the standard business data and the standard financial data according to the preset reconciliation rule to obtain target business data and target financial data; Performing difference identification on the target business data and the target financial data through a difference identification model to obtain a difference identification result; When the difference identification result indicates that there is at least one data difference item, data analysis is performed on all the data difference items to obtain the difference reasons corresponding to each of the data difference items, and a reconciliation report corresponding to the data to be reconciled is generated based on the data difference items and the difference reasons.

2. The reconciliation method according to claim 1, characterized in that: The difference identification model is used to identify the difference between the target business data and the target financial data to obtain a difference identification result, including: The target business data and the target financial data are matched one by one through the difference identification model. If the target business data are all matched with the same data as the target financial data and the data amounts are the same, a difference identification result indicating that there is no difference is obtained; If the target business data does not match the target financial data, a difference identification result of a data difference item of the business-no-finance type is determined; If the target financial data does not match the target business data, it is determined as a difference identification result of a data difference item of the business type with finance but without type; If data identical to the target business data is matched in the target financial data and there is a difference in the data amount, a difference identification result of data difference items of different types of amounts is determined.

3. The reconciliation method according to claim 1, characterized in that: The preprocessing of the business data and the financial data to obtain standard business data and standard financial data includes: Performing data conversion on the business data and the financial data according to the conversion rules to obtain converted business data and converted financial data; The converted business data and the converted financial data are standardized by standard rules to obtain standard business data and standard financial data.

4. The reconciliation method according to claim 1, characterized in that: The screening and processing of the standard business data and the standard financial data by the preset reconciliation rule to obtain target business data and target financial data includes: The standard business data is screened and processed by using the reconciliation scenario corresponding to the reconciliation link in the preset reconciliation rule to obtain target business data; The standard financial data is screened and processed through the reconciliation scenario corresponding to the reconciliation link in the preset reconciliation rule to obtain the target financial data.

5. The reconciliation method according to claim 1, characterized in that: Before obtaining the data to be reconciled, the method further includes: Obtaining a reconciliation access request including user-related information, and verifying whether the user-related information has access rights; When the user-related information has access rights, obtaining target data in a target system; the target system refers to at least one of the business system and the financial system; The target data is desensitized using preset desensitization rules to obtain the data to be reconciled.

6. The reconciliation method according to claim 1, characterized in that: When the difference identification result indicates that there is at least one data difference item, after performing data analysis on all the data difference items and obtaining the difference reasons corresponding to each of the data difference items, the method further includes: Obtaining a preset solution set, performing information matching on the difference cause and preset information in the preset solution set, and obtaining an information matching result; When the information matching result indicates that the difference cause is successfully matched, obtaining a preset solution corresponding to the preset information that successfully matches the difference cause, and processing the data difference item according to the preset solution; When the information matching result indicates that the difference reason matching fails, a notification is sent to a preset relevant person.

7. The reconciliation method according to claim 1, characterized in that: Before the difference identification of the target business data and the target financial data is performed by the difference identification model, the method includes: Acquire a sample data set, wherein the sample data set includes at least one sample training data and a sample label corresponding to each sample training data; Identify and predict all the sample training data using a preset training model to obtain a prediction result corresponding to each of the sample training data; Determining a prediction loss value of a preset training model according to sample labels and prediction results corresponding to the same sample training data; When the predicted loss value reaches a preset convergence condition, the preset training model after convergence is determined as the difference recognition model.

8. A reconciliation device, characterized in that: include: A data acquisition module, used to acquire data to be reconciled, wherein the data to be reconciled includes business data in the business system and financial data in the financial system; A data processing module, used for preprocessing the business data and the financial data to obtain standard business data and standard financial data; A data screening module, used to obtain preset reconciliation rules, and screen the standard business data and the standard financial data according to the preset reconciliation rules to obtain target business data and target financial data; A difference identification module, used to identify the difference between the target business data and the target financial data through a difference identification model to obtain a difference identification result; A report generation module is used to perform data analysis on all the data difference items when the difference identification result indicates the existence of at least one data difference item, obtain the difference reason corresponding to each data difference item, and generate a reconciliation report corresponding to the data to be reconciled based on the data difference items and the difference reason.

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 reconciliation method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the reconciliation method according to any one of claims 1 to 7 is implemented.

Images