Foreign exchange service submitted data verification method and device

Abstract

The invention discloses a foreign exchange service submitted data verification method and device which can be used in the financial field, and the method comprises the steps: obtaining historical foreign exchange service submitted data; repeatedly executing entity extraction on the historical foreign exchange service submitted data, and verifying the extracted entities until a verification result is consistent with a submission specification; repeatedly executing attribute extraction and relationship extraction on the extracted entities, and verifying the extracted attributes and relationships until a verification result is that the extracted attributes and relationships accord with submission specifications; establishing a knowledge graph of the foreign exchange service submitted data by utilizing a machine learning algorithm according to the extracted entities, attributes and relationships; acquiring real-time foreign exchange service submitted data; and according to the knowledge graph of the foreign exchange service submitted data, carrying out data checking on the real-time foreign exchange service submitted data, so that the accuracy of the bank foreign exchange service submitted data can be improved.

Description

Technical Field

[0001] The present invention relates to the financial field, and in particular to a method and device for verifying foreign exchange business reporting data. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] At present, the systems for commercial banks to report foreign exchange business data are mainly divided into three parts: bank transaction system, reporting system and supervision system. The bank transaction system is a system owned by the bank, which is used for the acceptance of specific foreign exchange business between customers and banks, such as handling foreign exchange deposits, foreign exchange loans, foreign exchange remittances, etc. The reporting system is a system owned by the bank, which is used to report transaction details to the supervision when the customer's transaction occurs, and report its own foreign exchange business assets and liabilities, such as the signing and balance of interbank deposits and interbank loans. The supervision system is an application system owned by the regulatory agency and is used to receive and verify the data reported by commercial banks.

[0004] The main problem currently faced is that banks have numerous and complex foreign exchange transaction subsystems, and data comes from different transaction subsystems. Different dimensional data sources of the same transaction subsystem collect information and report it to regulators. The accuracy of bank foreign exchange business data reporting is low, resulting in errors in copying data of different dimensions reported in the same period during the associated verification when the regulatory perspective summarizes and reviews them. Summary of the invention

[0005] The embodiment of the present invention provides a method for verifying foreign exchange business reporting data, which is used to improve the accuracy of foreign exchange business reporting data of a bank. The method includes:

[0006] Obtaining historical foreign exchange business reporting data; the historical foreign exchange business reporting data is verified and marked foreign exchange business reporting data;

[0007] Repeat the entity extraction of historical foreign exchange business reporting data and verify the extracted entities until the verification results are in compliance with the reporting specifications;

[0008] Repeat the extraction of attributes and relationships of the extracted entities, and verify the extracted attributes and relationships until the verification results meet the reporting specifications;

[0009] Based on the extracted entities, attributes and relationships, a knowledge graph of foreign exchange business reporting data is established using machine learning algorithms;

[0010] Obtain real-time foreign exchange business reporting data;

[0011] According to the knowledge graph of foreign exchange business reporting data, data verification is performed on the real-time foreign exchange business reporting data.

[0012] The embodiment of the present invention also provides a foreign exchange business reporting data verification device, which is used to ensure that the export data reported by the bank are logical to each other, and improve the accuracy and effectiveness of the bank's foreign exchange business reporting data. The device includes:

[0013] A historical data acquisition module, used to acquire historical foreign exchange business reporting data; the historical foreign exchange business reporting data is verified and marked foreign exchange business reporting data;

[0014] The entity extraction module is used to repeatedly extract entities from historical foreign exchange business reporting data and verify the extracted entities until the verification result is in compliance with the reporting specifications;

[0015] The attribute and relationship extraction module is used to repeatedly perform attribute extraction and relationship extraction on the extracted entities, and verify the extracted attributes and relationships until the verification results meet the reporting specifications;

[0016] The knowledge graph building module is used to build a knowledge graph of foreign exchange business reporting data based on the extracted entities, attributes and relationships using machine learning algorithms;

[0017] Real-time data acquisition module, used to obtain real-time foreign exchange business reporting data;

[0018] The data verification module is used to verify the real-time foreign exchange business reporting data based on the knowledge graph of the foreign exchange business reporting data.

[0019] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned foreign exchange business reporting data verification method when executing the computer program.

[0020] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned foreign exchange business reporting data verification method is implemented.

[0021] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned foreign exchange business reporting data verification method is implemented.

[0022] Compared with the prior art, the embodiment of the present invention obtains historical foreign exchange business reporting data; the historical foreign exchange business reporting data is foreign exchange business reporting data that has been manually verified and manually marked; repeatedly performs entity extraction on the historical foreign exchange business reporting data, verifies the extracted entities, until the verification result is in compliance with the reporting specification; repeatedly performs attribute extraction and relationship extraction on the extracted entities, verifies the extracted attributes and relationships, until the verification result is in compliance with the reporting specification; establishes a knowledge graph of the foreign exchange business reporting data using a machine learning algorithm based on the extracted entities, attributes and relationships; obtains real-time foreign exchange business reporting data; and verifies the real-time foreign exchange business reporting data based on the knowledge graph of the foreign exchange business reporting data, thereby improving the accuracy of the bank's foreign exchange business reporting data. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0024] Figure 1 It is a flow chart of a method for verifying foreign exchange business reporting data in an embodiment of the present invention;

[0025] Figure 2 It is a flowchart of a specific example of the method for verifying foreign exchange business reporting data in an embodiment of the present invention;

[0026] Figure 3 It is a flowchart of a specific example of the method for verifying foreign exchange business reporting data in an embodiment of the present invention;

[0027] Figure 4 A schematic diagram of a knowledge graph of foreign exchange business reporting data in an embodiment of the present invention;

[0028] Figure 5 It is a flowchart of a specific example of the method for verifying foreign exchange business reporting data in an embodiment of the present invention;

[0029] Figure 6 Schematic diagram of a foreign exchange business reporting data verification device in an embodiment of the present invention;

[0030] Figure 7 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0032] Figure 1 The flowchart of the method for verifying the foreign exchange business reporting data in an embodiment of the present invention includes:

[0033] Step 101, obtaining historical foreign exchange business reporting data; the historical foreign exchange business reporting data is verified and marked foreign exchange business reporting data;

[0034] Step 102, repeatedly extracting entities from historical foreign exchange business reporting data, and verifying the extracted entities until the verification result is in compliance with the reporting specifications;

[0035] Step 103, repeatedly extracting attributes and relationships from the extracted entities, and verifying the extracted attributes and relationships until the verification result meets the reporting specifications;

[0036] Step 104, using a machine learning algorithm to establish a knowledge graph of foreign exchange business reporting data based on the extracted entities, attributes and relationships;

[0037] Step 105, obtaining real-time foreign exchange business reporting data;

[0038] Step 106, performing data verification on the real-time foreign exchange business reporting data according to the knowledge graph of the foreign exchange business reporting data.

[0039] Figure 2 FIG. 1 is a flowchart of a specific example of a method for verifying foreign exchange business reporting data in an embodiment of the present invention. Figure 2 As shown, in order to achieve the purpose of the present invention, the overall structure of the foreign exchange business reporting data verification method of the embodiment of the present invention mainly includes three parts:

[0040] (1) A knowledge graph modeling subsystem in the field of financial regulatory data reporting. This subsystem is an offline subsystem that is guided by regulatory norms and error feedback and uses machine learning and other algorithms to build a knowledge graph in the field of regulatory data reporting, namely, a knowledge graph of foreign exchange business reporting data.

[0041] (2) Knowledge graph. The knowledge graph model in the field of financial regulatory data reporting is the key innovation of the embodiments of the present invention. It expands the entities in the knowledge graph and associates data verification rules and reasoning logic with entities in the form of attributes.

[0042] (3) Verification and cleaning of submitted data. This part and the knowledge graph together constitute the production subsystem. Driven by the knowledge graph, the submitted summary data and detailed data are verified and cleaned, and the source data and data verification / cleaning processing logs are stored locally to ensure data traceability. The data processed by this system is reported to the regulatory side to ensure the accuracy and compliance of the data, so as to improve the production efficiency of data reporting.

[0043] The core essence of the knowledge graph is the triple, which is composed of an entity, an attribute, and a relation in the form of <entity, relation, entity>. In the embodiment of the present invention, combined with the characteristics of the regulatory data reporting field, the attributes of the knowledge graph are mainly expanded, and the data verification rules and inference rules are associated with the reporting data entities in the form of attributes, thereby realizing the verification and cleaning of regulatory reporting data driven by the knowledge graph.

[0044] In one embodiment, historical foreign exchange business reporting data is used to establish a knowledge graph of foreign exchange business reporting data. The historical foreign exchange business reporting data is the historical reporting data of the original foreign exchange business. The erroneous data is manually checked and marked, so that the erroneous data (counterexamples) and the correct data (positive examples) can be correctly distinguished, so that entities, relationships, attributes, etc. can be correctly extracted.

[0045] In one embodiment, a knowledge graph of foreign exchange business reporting data is constructed based on regulatory specifications, error feedback and reporting data. In this embodiment of the present invention, the knowledge graph modeling of foreign exchange business reporting data is divided into three steps: (1) entity extraction of regulatory reporting data; (2) attribute extraction and relationship extraction; (3) rule learning. For the results of each step, manual verification is performed. If the verification is passed, the next step is entered. Otherwise, the previous step is returned to re-learning. Figure 3 FIG. 1 is a flowchart of a specific example of a method for verifying foreign exchange business reporting data in an embodiment of the present invention. Figure 3 As shown, learning data is obtained, that is, historical foreign exchange business reporting data that has been manually verified and manually annotated; entity extraction is performed on the learning data, and the extracted entities are manually verified. Manual verification is to verify the extracted entities, relationships, attributes, etc. according to the financial reporting specifications. If it meets the reporting specifications, it will pass, and if it does not meet the reporting specifications, it will fail. The reporting specifications involve naming specifications, account rules, numerical symbols / ranges, etc. Attribute extraction and relationship extraction are performed on the entities that have passed the manual verification, and the extracted attributes and relationships are manually verified. If it meets the reporting specifications, it will pass, and if it does not meet the reporting specifications, it will fail.

[0046] In this embodiment, attribute extraction of the extracted entities is repeatedly performed, including: repeatedly performing extraction of data constraint attributes, data format attributes, and correct processing method attributes of the extracted entities; the extracted data constraint attributes, data format attributes, and correct processing method attributes are embodied in the form of regular expressions and / or logical expressions.

[0047] In this embodiment, a machine learning algorithm is used to learn rules for entities, attributes, and relationships that have passed manual verification, and a knowledge graph of foreign exchange business reporting data is established. In the process of establishing a knowledge graph of financial reporting, entities involved in financial data are extracted, such as "account" and "relationship"; such as the affiliation and attributes between table fields and tables; such as the length limit of an account; such as the number of decimal places to be retained for a balance, etc.; a knowledge graph of financial reporting data is constructed with entities, relationships, attributes, restrictions (rules), etc.

[0048] Figure 4 Schematic diagram of the knowledge graph of foreign exchange business reporting data in an embodiment of the present invention. Figure 4 As shown, in this embodiment, taking the contract information data submitted every day as an example, the "contract" information data is an entity, and the data fields contained in the contract information are also entities. The "contract" entity is included in the "floating interest rate" and "foreign debt number" entities. The data constraints, data formats, correct processing methods, etc. of each data field are associated with the field in the form of attributes. This field attribute is based on the standard format and processing requirements of the regulatory data and is implemented in the form of regular expressions, logical expressions, etc.

[0049] In one embodiment, after the real-time foreign exchange business reporting data is verified, it also includes: data cleaning of the real-time foreign exchange business reporting data. Using the regulatory reporting data knowledge graph as a reference standard and driver, the financial reporting data is verified and cleaned, and all changes to the original reporting data are recorded and archived in the form of log files, thereby forming a data traceability path. The knowledge graph can be regarded as a reference manual for data standards and a guide for data modification (cleaning). Using the knowledge graph as a reference standard and driver means verifying the data according to the relationships, attributes, and rules restricted by the knowledge graph, and modifying the data (for example, the letter big X is modified to a small x as required, etc.).

[0050] Figure 5 FIG. 1 is a flowchart of a specific example of a method for verifying foreign exchange business reporting data in an embodiment of the present invention. Figure 5 As shown, in this embodiment, when verifying and cleaning the reported data, the knowledge graph is used as a reference, and the knowledge graph data attribute rules and reasoning logic are implemented in the system in the form of program routines, so that the knowledge graph structure ensures the integrity and correctness of the data verification.

[0051] In this embodiment, data verification is performed on the real-time foreign exchange business reporting data, including: performing error data verification on the real-time foreign exchange business reporting data, generating error data and data verification logs; and locally storing the error data and data verification logs.

[0052] In this embodiment, data cleaning is performed on real-time foreign exchange business reporting data, including: modifying erroneous data, generating modified data and data modification logs; and locally storing the modified data and data modification logs. Error data and modification records are important components, and the error data records, modification data records and original data form a complete traceability path for the reporting data. The data structure of the error data of the real-time foreign exchange business reporting data in the embodiment of the present invention is shown in Table 1, and the data structure of the data modification log is shown in Table 2:

[0053] Table 1

[0054]

[0055] Table 2

[0056]

[0057]

[0058] In this embodiment, after verifying the real-time foreign exchange business reporting data, the following steps are also included:

[0059] Determine the data quality score of the real-time foreign exchange business reporting data according to the data volume and erroneous data volume of the real-time foreign exchange business reporting data; the data quality score is used to reflect the quality of the real-time foreign exchange business reporting data;

[0060] If the data quality score of the real-time foreign exchange business reporting data is higher than the preset data quality threshold, the real-time foreign exchange business reporting data will be reported;

[0061] If the data quality score of the real-time foreign exchange business reporting data is not higher than the preset data quality threshold, the real-time foreign exchange business reporting data will be rejected.

[0062] In this embodiment, data quality calculation is to calculate the quality score of the data submitted this time. There can be many methods. The simplest method is, for example, to detect the percentage of erroneous data (excluding data that can be automatically corrected) in the data submitted this time. For example, if the proportion of erroneous data exceeds 1%, the data quality is unqualified.

[0063] In one embodiment, data verification is performed on real-time foreign exchange business reporting data according to the knowledge graph of foreign exchange business reporting data, including:

[0064] The entities, relationships and attributes restricted by the knowledge graph of foreign exchange business reporting data are used as reference standards to verify the real-time foreign exchange business reporting data.

[0065] The embodiment of the present invention also provides a foreign exchange business reporting data verification device, as described in the following embodiment. Since the principle of solving the problem by the device is similar to the foreign exchange business reporting data verification method, the implementation of the device can refer to the implementation of the foreign exchange business reporting data verification method, and the repeated parts will not be repeated.

[0066] Figure 6 Schematic diagram of a device for verifying foreign exchange business reporting data in an embodiment of the present invention. Figure 6 As shown, the foreign exchange business reporting data verification device in the embodiment of the present invention includes:

[0067] The historical data acquisition module 601 is used to acquire historical foreign exchange business reporting data; the historical foreign exchange business reporting data is the verified and marked foreign exchange business reporting data;

[0068] The entity extraction module 602 is used to repeatedly extract entities from historical foreign exchange business reporting data and verify the extracted entities until the verification result is in compliance with the reporting specifications;

[0069] The attribute and relationship extraction module 603 is used to repeatedly extract attributes and relationships from the extracted entities, and verify the extracted attributes and relationships until the verification result meets the reporting specification;

[0070] A knowledge graph building module 604 is used to build a knowledge graph of foreign exchange business reporting data using a machine learning algorithm based on the extracted entities, attributes and relationships;

[0071] A real-time data acquisition module 605 is used to acquire real-time foreign exchange business reporting data;

[0072] The data verification module 606 is used to perform data verification on the real-time foreign exchange business reporting data according to the knowledge graph of the foreign exchange business reporting data.

[0073] In one embodiment, the foreign exchange business reporting data verification device further includes:

[0074] The data cleaning module is used to clean the real-time foreign exchange business reporting data.

[0075] In this embodiment, the data verification module 606 is specifically used for:

[0076] Conduct error data inspection on real-time foreign exchange business reporting data and generate error data and data inspection logs;

[0077] Locally store error data and data verification logs.

[0078] In this embodiment, the data cleaning module is specifically used for:

[0079] Modify the erroneous data and generate the modified data and data modification log;

[0080] The modified data and data modification log are stored locally.

[0081] In one embodiment, the foreign exchange business reporting data verification device further includes:

[0082] Determine the data quality score of the real-time foreign exchange business reporting data according to the data volume and erroneous data volume of the real-time foreign exchange business reporting data; the data quality score is used to reflect the quality of the real-time foreign exchange business reporting data;

[0083] If the data quality score of the real-time foreign exchange business reporting data is higher than the preset data quality threshold, the real-time foreign exchange business reporting data will be reported;

[0084] If the data quality score of the real-time foreign exchange business reporting data is not higher than the preset data quality threshold, the real-time foreign exchange business reporting data will be rejected.

[0085] In one embodiment, the attribute and relationship extraction module 603 is specifically used to:

[0086] The data constraint attributes, data format attributes, and correct processing method attributes of the extracted entities are extracted repeatedly; the extracted data constraint attributes, data format attributes, and correct processing method attributes are embodied in the form of regular expressions and / or logical expressions.

[0087] In one embodiment, the data verification module 606 is specifically used to perform data verification on the real-time foreign exchange business reporting data using the entities, relationships and attributes restricted by the knowledge graph of the foreign exchange business reporting data as reference standards.

[0088] Compared with the prior art, the embodiment of the present invention obtains historical foreign exchange business reporting data; the historical foreign exchange business reporting data is foreign exchange business reporting data that has been manually verified and manually marked; repeatedly performs entity extraction on the historical foreign exchange business reporting data, verifies the extracted entities, until the verification result is in compliance with the reporting specification; repeatedly performs attribute extraction and relationship extraction on the extracted entities, verifies the extracted attributes and relationships, until the verification result is in compliance with the reporting specification; establishes a knowledge graph of the foreign exchange business reporting data using a machine learning algorithm based on the extracted entities, attributes and relationships; obtains real-time foreign exchange business reporting data; and verifies the real-time foreign exchange business reporting data based on the knowledge graph of the foreign exchange business reporting data, thereby improving the accuracy of the bank's foreign exchange business reporting data.

[0089] By implementing the solution of the present invention, a regulatory verification mechanism is preset in the commercial bank system and manually reviewed and corrected to ensure that the export data reported by the bank are logical, referenced and mutually verifiable. On the basis of ensuring the regulatory time limit, the accuracy and effectiveness of the data reported by the bank on external assets can be effectively improved.

[0090] An embodiment of the present invention further provides a computer device, Figure 7 Schematic diagram of a computer device in an embodiment of the present invention. The computer device 700 includes a memory 710, a processor 720, and a computer program 730 stored in the memory 710 and executable on the processor 720. When the processor 720 executes the computer program 730, the above-mentioned foreign exchange business reporting data verification method is implemented.

[0091] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned foreign exchange business reporting data verification method is implemented.

[0092] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned foreign exchange business reporting data verification method is implemented.

[0093] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0094] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0097] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for verifying foreign exchange business reporting data, characterized in that: include: Obtaining historical foreign exchange business reporting data; the historical foreign exchange business reporting data is verified and marked foreign exchange business reporting data; Repeat the entity extraction of historical foreign exchange business reporting data and verify the extracted entities until the verification results are in compliance with the reporting specifications; Repeat the extraction of attributes and relationships of the extracted entities, and verify the extracted attributes and relationships until the verification results meet the reporting specifications; Based on the extracted entities, attributes and relationships, a knowledge graph of foreign exchange business reporting data is established using machine learning algorithms; Obtain real-time foreign exchange business reporting data; According to the knowledge graph of foreign exchange business reporting data, data verification is performed on the real-time foreign exchange business reporting data.

2. The method according to claim 1, characterized in that After verifying the real-time foreign exchange business reporting data, it also includes: Clean the real-time foreign exchange business reporting data.

3. The method according to claim 1, characterized in that Verify the real-time foreign exchange business reporting data, including: Perform error data verification on real-time foreign exchange business reporting data and generate error data and data verification logs; Locally store error data and data verification logs.

4. The method according to claim 3, characterized in that Clean the real-time foreign exchange business reporting data, including: Modify the erroneous data and generate the modified data and data modification log; The modified data and data modification log are stored locally.

5. The method according to claim 1, characterized in that After verifying the real-time foreign exchange business reporting data, it also includes: Determine the data quality score of the real-time foreign exchange business reporting data according to the data volume and erroneous data volume of the real-time foreign exchange business reporting data; the data quality score is used to reflect the quality of the real-time foreign exchange business reporting data; If the data quality score of the real-time foreign exchange business reporting data is higher than the preset data quality threshold, the real-time foreign exchange business reporting data will be reported; If the data quality score of the real-time foreign exchange business reporting data is not higher than the preset data quality threshold, the real-time foreign exchange business reporting data will be rejected.

6. The method according to claim 1, characterized in that Repeat the process of extracting attributes from the extracted entities, including: The data constraint attributes, data format attributes, and correct processing method attributes of the extracted entities are extracted repeatedly; the extracted data constraint attributes, data format attributes, and correct processing method attributes are embodied in the form of regular expressions and / or logical expressions.

7. The method according to claim 1, characterized in that According to the knowledge graph of foreign exchange business reporting data, the real-time foreign exchange business reporting data is verified, including: The entities, relationships and attributes restricted by the knowledge graph of foreign exchange business reporting data are used as reference standards to verify the real-time foreign exchange business reporting data.

8. A foreign exchange business reporting data verification device, characterized in that: include: A historical data acquisition module, used to acquire historical foreign exchange business reporting data; the historical foreign exchange business reporting data is verified and marked foreign exchange business reporting data; The entity extraction module is used to repeatedly extract entities from historical foreign exchange business reporting data and verify the extracted entities until the verification result is in compliance with the reporting specifications; The attribute and relationship extraction module is used to repeatedly perform attribute extraction and relationship extraction on the extracted entities, and verify the extracted attributes and relationships until the verification results meet the reporting specifications; The knowledge graph building module is used to build a knowledge graph of foreign exchange business reporting data based on the extracted entities, attributes and relationships using machine learning algorithms; Real-time data acquisition module, used to obtain real-time foreign exchange business reporting data; The data verification module is used to verify the real-time foreign exchange business reporting data based on the knowledge graph of the foreign exchange business reporting data.

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

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

Images