Vehicle customs declaration data cross-system cooperative verification method and system based on RPA

Abstract

The invention provides a vehicle customs declaration data cross-system cooperative verification method and system based on RPA. The method comprises the steps of obtaining a VIN code of a customs declaration vehicle, obtaining a vehicle customs declaration cross-system data set according to the VIN code, performing processing through a preset cross-system data mapping model to obtain a vehicle customs declaration cross-system standard data set, then performing data verification through a preset cross-system verification rule to obtain verification evaluation data, and then performing data verification according to the verification evaluation data. Processing is carried out through a preset verification anomaly grading evaluation model to obtain an anomaly grade, and finally, evidence storage is carried out through a block chain, and a data cross-system collaborative verification report is generated; according to the method, cross-system cross check is realized by taking the VIN code as a core, the check abnormal level and the three-level rule are evaluated to correct the rule conflict, and the check process is ensured to be traceable through block chain evidence storage, so that the RPA-based cross-system cooperative check of the vehicle customs declaration data is realized.

Description

Technical Field

[0001] This application relates to the field of computer data processing technology, and more specifically, to a cross-system collaborative verification method and system for vehicle customs declaration data based on RPA. Background Technology

[0002] With the development of global trade and digital transformation, traditional vehicle customs declaration methods are insufficient. Traditional technologies have many shortcomings in handling massive amounts of data from multiple systems and responding to changes in customs policies. Traditional technologies mainly rely on manual execution for cross-system data verification in vehicle customs declaration, which is inefficient and has a high error rate. Automated processes only implement single systems and cannot effectively achieve accurate correlation verification and dynamic rule adaptation of data from multiple systems. At the same time, there is a lack of end-to-end data traceability and intelligent anomaly early warning mechanisms for cross-system verification, evaluation, and handling of vehicle customs declaration data. Therefore, there is an urgent need for a collaborative verification method for cross-system vehicle customs declaration data based on RPA.

[0003] Effective technical solutions are urgently needed to address the above problems. Summary of the Invention

[0004] The purpose of this application is to provide a cross-system collaborative verification method and system for vehicle customs declaration data based on RPA. It can realize cross-system cross-verification, evaluate the level of verification anomalies and correct rule conflicts by using VIN code as the core, and ensure the traceability of the verification process by storing evidence through blockchain, thereby realizing cross-system collaborative verification of vehicle customs declaration data based on RPA.

[0005] Firstly, this application provides a cross-system collaborative verification method for vehicle customs declaration data based on RPA, including the following steps: Obtain the VIN code of the vehicle for customs declaration, obtain the cross-system dataset of vehicle customs declaration based on the VIN code, and process it through a preset cross-system data mapping model to obtain the standard cross-system dataset of vehicle customs declaration. The cross-system standard dataset for vehicle customs declaration is validated using preset cross-system validation rules to obtain validation evaluation data. The verification evaluation data is processed through a preset verification anomaly classification evaluation model to obtain the anomaly level; Anomalies are handled according to the anomaly level, and evidence is stored on the blockchain to generate a cross-system collaborative verification report.

[0006] Optionally, in the RPA-based cross-system collaborative verification method for vehicle customs declaration data described in this application, the step of obtaining the VIN code of the vehicle, obtaining the cross-system dataset of vehicle customs declaration based on the VIN code, and processing it through a preset cross-system data mapping model to obtain the standard cross-system dataset of vehicle customs declaration includes: Obtain the VIN code of the vehicle being declared for customs and verify the VIN code; If the VIN code verification is successful, the cross-system dataset for vehicle customs declaration is obtained based on the VIN code, including manufacturing data from the production system, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data. The manufacturing data, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data of the production system are processed through a preset cross-system data mapping model to obtain a cross-system standard dataset for vehicle customs declaration, including standard data for manufacturing, logistics and transportation, tax collection and administration, and customs declaration and clearance. If the VIN code verification fails, an early warning response will be output.

[0007] Optionally, the RPA-based cross-system collaborative verification method for vehicle customs declaration data described in this application further includes: Obtain cross-system field metadata for vehicle customs declaration, including field metadata from the production system, logistics and transportation system, tax collection and administration system, and customs declaration system. The metadata of the production system fields, logistics and transportation system fields, tax collection and administration system fields, and customs declaration system fields are processed by NLP and regular expression matching to obtain field event categories, including new field events, updated field events, or terminated field events. If it is a new field event or an updated field event, semantic parsing is performed, and matching is done through a preset historical cross-system data mapping model to obtain mapping matching rules; Update the preset historical cross-system data mapping model according to the mapping matching rules to obtain the preset cross-system data mapping model; If it is a termination field event, then the deletion process is performed to obtain the preset cross-system data mapping model.

[0008] Optionally, in the RPA-based cross-system collaborative verification method for vehicle customs declaration data described in this application, the step of verifying the cross-system standard dataset of vehicle customs declarations through preset cross-system verification rules to obtain verification evaluation data includes: The manufacturing standard data, logistics and transportation standard data, tax collection and administration standard data, and customs declaration and clearance standard data of the production system are verified using preset cross-system verification rules to obtain verification and evaluation data. The preset cross-system verification rules include field compliance verification rules, logical association verification rules, and threshold comparison verification rules; The verification and evaluation data includes field compliance verification and evaluation data, logical association verification and evaluation data, and threshold comparison verification and evaluation data.

[0009] Optionally, in the RPA-based cross-system collaborative verification method for vehicle customs declaration data described in this application, the step of processing the verification evaluation data through a preset verification anomaly classification evaluation model to obtain the anomaly level includes: The field compliance verification assessment data, logical association verification assessment data, and threshold comparison verification assessment data are input into a preset verification anomaly classification assessment model for analysis and processing to obtain the verification anomaly assessment index. The anomaly evaluation index is compared with the preset anomaly evaluation threshold to obtain the anomaly level. The preset anomaly evaluation threshold includes a first preset anomaly evaluation threshold and a second preset anomaly evaluation threshold. If the verification anomaly evaluation index is less than or equal to the first preset verification anomaly evaluation threshold, the anomaly level is determined to be a level three anomaly. If the verification anomaly evaluation index is greater than the first preset verification anomaly evaluation threshold and less than or equal to the second preset verification anomaly evaluation threshold, then the anomaly level is determined to be a level two anomaly. If the verification anomaly evaluation index is greater than the second preset verification anomaly evaluation threshold, the anomaly level is determined to be a level one anomaly.

[0010] Optionally, in the RPA-based cross-system collaborative verification method for vehicle customs declaration data described in this application, the step of performing anomaly processing according to the anomaly level and generating a cross-system collaborative verification report through blockchain storage includes: Based on the anomaly level, perform anomaly handling to obtain an anomaly handling strategy; If the anomaly level is Level 1, the vehicle customs declaration process will be suspended and a warning response will be issued. If the anomaly level is level 2, a corresponding customs declaration correction strategy is generated based on the logical association verification evaluation data and the threshold comparison verification evaluation data. If the anomaly level is level three, then activate the field format optimization processing strategy based on the field compliance verification assessment data. The VIN code, verification evaluation data, anomaly level, and anomaly handling strategy are used to generate corresponding hash values ​​through a preset encryption algorithm, written to preset cross-system multi-storage nodes, and a cross-system collaborative data verification report is generated.

[0011] Optionally, in the RPA-based cross-system collaborative verification method for vehicle customs declaration data described in this application, if the event is a newly added field or an updated field, semantic parsing is performed, and matching is conducted through a preset historical cross-system data mapping model to obtain mapping matching rules, including: If the mapping matching rule conflicts with the historical mapping matching rule in the preset historical cross-system data mapping model, the rule priority of the mapping matching rule is obtained, including first-level rule priority, second-level rule priority or third-level rule priority; If it is a first-level rule priority, then the preset historical cross-system data mapping model is modified according to the mapping matching rule to obtain the preset cross-system data mapping model; If it is a secondary rule priority, then determine whether the historical mapping matching rule is the preset core field mapping matching rule. If it is, then retain it; if not, then modify the historical mapping matching rule according to the mapping matching rule. If it is a level 3 rule priority, then the historical mapping matching rule is corrected based on the conflict fields between the mapping matching rule and the historical mapping matching rule.

[0012] Secondly, this application provides a cross-system collaborative verification system for vehicle customs declaration data based on RPA. The system includes a memory and a processor. The memory includes a program for a cross-system collaborative verification method for vehicle customs declaration data based on RPA. When the program for the cross-system collaborative verification method for vehicle customs declaration data based on RPA is executed by the processor, it implements the following steps: Obtain the VIN code of the vehicle for customs declaration, obtain the cross-system dataset of vehicle customs declaration based on the VIN code, and process it through a preset cross-system data mapping model to obtain the standard cross-system dataset of vehicle customs declaration. The cross-system standard dataset for vehicle customs declaration is validated using preset cross-system validation rules to obtain validation evaluation data. The verification evaluation data is processed through a preset verification anomaly classification evaluation model to obtain the anomaly level; Anomalies are handled according to the anomaly level, and evidence is stored on the blockchain to generate a cross-system collaborative verification report.

[0013] Optionally, in the RPA-based cross-system collaborative verification system for vehicle customs declaration data described in this application, the step of obtaining the VIN code of the vehicle, obtaining the cross-system dataset of vehicle customs declaration based on the VIN code, and processing it through a preset cross-system data mapping model to obtain the standard cross-system dataset of vehicle customs declaration includes: Obtain the VIN code of the vehicle being declared for customs and verify the VIN code; If the VIN code verification is successful, the cross-system dataset for vehicle customs declaration is obtained based on the VIN code, including manufacturing data from the production system, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data. The manufacturing data, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data of the production system are processed through a preset cross-system data mapping model to obtain a cross-system standard dataset for vehicle customs declaration, including standard data for manufacturing, logistics and transportation, tax collection and administration, and customs declaration and clearance. If the VIN code verification fails, an early warning response will be output.

[0014] Optionally, the RPA-based cross-system collaborative verification system for vehicle customs declaration data described in this application further includes: Obtain cross-system field metadata for vehicle customs declaration, including field metadata from the production system, logistics and transportation system, tax collection and administration system, and customs declaration system. The metadata of the production system fields, logistics and transportation system fields, tax collection and administration system fields, and customs declaration system fields are processed by NLP and regular expression matching to obtain field event categories, including new field events, updated field events, or terminated field events. If it is a new field event or an updated field event, semantic parsing is performed, and matching is done through a preset historical cross-system data mapping model to obtain mapping matching rules; Update the preset historical cross-system data mapping model according to the mapping matching rules to obtain the preset cross-system data mapping model; If it is a termination field event, then the deletion process is performed to obtain the preset cross-system data mapping model.

[0015] As can be seen from the above, the RPA-based cross-system collaborative verification method and system for vehicle customs declaration data provided in this application achieves cross-system cross-verification of vehicle customs declaration data by using the VIN code as the core, evaluating the level of verification anomalies and correcting rule conflicts using three-level rules, and ensuring the traceability of the verification process through blockchain storage.

[0016] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of a cross-system collaborative verification method for vehicle customs declaration data based on RPA provided in this application embodiment; Figure 2 A flowchart illustrating the process of obtaining a cross-system standard dataset for vehicle customs declaration data using an RPA-based cross-system collaborative verification method provided in this application embodiment; Figure 3 A flowchart illustrating the process of obtaining a preset cross-system data mapping model for the RPA-based cross-system collaborative verification method for vehicle customs declaration data provided in this application embodiment; Figure 4 A high-level flowchart of the RPA-based cross-system collaborative verification method for vehicle customs declaration data provided in this application embodiment; Figure 5 This is a system block diagram of an RPA-based cross-system collaborative verification system for vehicle customs declaration data, provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0021] Please refer to Figure 1 , Figure 1This is a flowchart of an RPA-based cross-system collaborative verification method for vehicle customs declaration data, as described in some embodiments of this application. This RPA-based cross-system collaborative verification method for vehicle customs declaration data is used in terminal devices, such as computers and mobile terminals. The RPA-based cross-system collaborative verification method for vehicle customs declaration data includes the following steps: S11. Obtain the VIN code of the vehicle for customs declaration, obtain the cross-system dataset of vehicle customs declaration based on the VIN code, and process it through the preset cross-system data mapping model to obtain the standard cross-system dataset of vehicle customs declaration. S12. Verify the cross-system standard dataset of vehicle customs declaration through preset cross-system verification rules to obtain verification evaluation data; S13. The verification evaluation data is processed through a preset verification anomaly classification evaluation model to obtain the anomaly level; S14. Perform anomaly processing based on the anomaly level, and generate a cross-system collaborative verification report for data through blockchain evidence storage.

[0022] It should be noted that, in order to achieve cross-system data collaborative verification based on RPA during vehicle customs declaration, firstly, based on the vehicle's unique VIN code, a multi-protocol adaptation module supporting HTTP, FTP, direct database connection, and interface capture was designed. This module non-intrusively extracts key evaluation data from multiple systems for cross-comparison and performs data standardization mapping to solve the data silo problem. Secondly, based on the cross-system standard dataset for vehicle customs declaration, a three-level verification process is performed: field compliance verification of basic rules, logical association verification of business rules, and threshold comparison verification of custom rules. Thirdly, based on the verification results, anomaly levels are assessed using a pre-set anomaly classification assessment model. Finally, corresponding handling strategies are implemented according to the anomaly level, and blockchain evidence is used to ensure the traceability of the entire data collaborative verification process. Simultaneously, a cross-system data collaborative verification report is generated for maintenance personnel to view and further analyze.

[0023] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the process of obtaining a cross-system standard dataset for vehicle customs declaration data based on RPA in some embodiments of this application. According to embodiments of the present invention, obtaining the VIN code of the vehicle being declared, obtaining the cross-system dataset for vehicle customs declaration based on the VIN code, and processing it through a preset cross-system data mapping model to obtain the standard dataset for vehicle customs declaration includes: S21. Obtain the VIN code of the vehicle being declared for customs and verify the VIN code; S221. If the VIN code verification is successful, the cross-system dataset for vehicle customs declaration is obtained based on the VIN code, including manufacturing data from the production system, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data. S23. The manufacturing data, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data of the production system are processed through a preset cross-system data mapping model to obtain a cross-system standard dataset for vehicle customs declaration, including standard data of manufacturing, logistics and transportation, tax collection and administration data, and customs declaration and clearance data. S222. If the VIN code verification fails, an early warning response will be output.

[0024] It should be noted that the VIN code is the unique identifier of the vehicle being declared for customs. A cross-system data association mechanism is established based on the VIN code to ensure full data traceability. First, the obtained VIN code is verified to determine if it meets the format requirements. Then, corresponding production system manufacturing data, logistics and transportation data, tax administration data, and customs declaration data are extracted from the production system, logistics and transportation system, tax administration data, and customs declaration data. Production system manufacturing data includes vehicle model, engine number, and vehicle configuration parameters; logistics and transportation data includes bill of lading serial number, logistics node characteristic data, logistics volume, and transportation trajectory data; tax administration data includes invoice number, tax paid amount, and tax rate; and customs declaration data includes customs declaration number, declared price, and date. The collected data is then processed using a pre-set cross-system data mapping model. For example, the vehicle model is mapped to a vehicle type code; transportation trajectory data (structured storage of time and location) is precisely matched with the departure date in the customs declaration system; and a logical relationship is established between the tax paid amount in the tax administration system and the declared price in the customs declaration system (the tax paid amount is the product of the declared price and the tax rate).

[0025] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the process of obtaining a preset cross-system data mapping model in some embodiments of the RPA-based cross-system collaborative verification method for vehicle customs declaration data. According to embodiments of the present application, it further includes: S31. Obtain the cross-system field metadata dataset for vehicle customs declaration, including field metadata from the production system, the logistics and transportation system, the tax collection and administration system, and the customs declaration system. S32. Perform NLP and regular expression matching analysis on the metadata of the production system field, the logistics and transportation system field, the tax collection and administration system field, and the customs declaration system field to obtain the field event categories, including new field events, updated field events, or terminated field events. S331. If it is a new field event or an updated field event, semantic parsing is performed, and matching is performed through a preset historical cross-system data mapping model to obtain mapping matching rules; S34. Update the preset historical cross-system data mapping model according to the mapping matching rules to obtain the preset cross-system data mapping model; S332. If it is a termination field event, perform deletion processing to obtain the preset cross-system data mapping model.

[0026] It should be noted that, in order to achieve automatic and dynamic updates of the cross-system data mapping model, metadata such as field names and data types from the open APIs of different systems are collected periodically. The collected metadata is analyzed by NLP (Natural Language Processing) and regular expression matching to identify three types of events, including field addition events, field update events, and field termination events. The preset historical cross-system data mapping model is optimized and updated according to the event type. For added or changed events, the mapping between the added field and the associated fields of other systems is established. For example, the battery code of the customs declaration system is mapped to the battery model of the production system. Then, the format is converted to meet the requirements, such as the battery code being letters plus a number of digits.

[0027] According to an embodiment of the present invention, the step of verifying the cross-system standard dataset of vehicle customs declarations through preset cross-system verification rules to obtain verification evaluation data includes: The manufacturing standard data, logistics and transportation standard data, tax collection and administration standard data, and customs declaration and clearance standard data of the production system are verified using preset cross-system verification rules to obtain verification and evaluation data. The preset cross-system verification rules include field compliance verification rules, logical association verification rules, and threshold comparison verification rules; The verification and evaluation data includes field compliance verification and evaluation data, logical association verification and evaluation data, and threshold comparison verification and evaluation data.

[0028] It should be noted that the collected standard data will be verified by three levels of dynamic rules, including field compliance verification for basic consistency, logical association verification of dynamic business logic rules, and threshold comparison verification based on custom rules. See Table 1 for examples of field compliance checks: Table 1

[0029] Examples of logical association verification are shown in Table 2: Table 2

[0030] Examples of threshold comparison and verification are shown in Table 3:

[0031] Based on the verification results, structured data is output, generating corresponding field compliance verification assessment data, logical association verification assessment data, and threshold comparison verification assessment data.

[0032] According to an embodiment of the present invention, processing the verification evaluation data through a preset verification anomaly classification evaluation model to obtain an anomaly level includes: The field compliance verification assessment data, logical association verification assessment data, and threshold comparison verification assessment data are input into a preset verification anomaly classification assessment model for analysis and processing to obtain the verification anomaly assessment index. The anomaly evaluation index is compared with the preset anomaly evaluation threshold to obtain the anomaly level. The preset anomaly evaluation threshold includes a first preset anomaly evaluation threshold and a second preset anomaly evaluation threshold. If the verification anomaly evaluation index is less than or equal to the first preset verification anomaly evaluation threshold, the anomaly level is determined to be a level three anomaly. If the verification anomaly evaluation index is greater than the first preset verification anomaly evaluation threshold and less than or equal to the second preset verification anomaly evaluation threshold, then the anomaly level is determined to be a level two anomaly. If the verification anomaly evaluation index is greater than the second preset verification anomaly evaluation threshold, the anomaly level is determined to be a level one anomaly.

[0033] It should be noted that a preset verification anomaly classification assessment model is obtained by training a large amount of historical sample field compliance verification assessment data, logical association verification assessment data, threshold comparison verification assessment data, and corresponding verification anomaly assessment index. Then, real-time assessment data is input into the pre-trained model to obtain the real-time verification anomaly assessment index. For example, logical association verification assessment data: the declared quantity of 50 vehicles is greater than the logistics arrival quantity of 45 vehicles (logical conflict). Threshold comparison verification assessment data: the declared price is 150,000 yuan, which exceeds the dynamic threshold (100,000-120,000 yuan) for the same vehicle model, with a deviation rate of +25%. The core business fields (quantity and price) are in violation, affecting compliance but can be corrected. The model's verification anomaly assessment index score is 68 points. At the same time, it is compared with the first preset verification anomaly assessment threshold and the second preset verification anomaly assessment threshold. In this embodiment, the first preset verification anomaly assessment threshold is set to 60, and the second preset verification anomaly assessment threshold is set to 80. The anomaly level is determined to be level two anomaly, level one anomaly is the highest level of anomaly, and level three anomaly is the lowest level of anomaly.

[0034] According to an embodiment of the present invention, the step of performing anomaly handling based on the anomaly level and generating a cross-system collaborative verification report through blockchain notarization includes: Based on the anomaly level, perform anomaly handling to obtain an anomaly handling strategy; If the anomaly level is Level 1, the vehicle customs declaration process will be suspended and a warning response will be issued. If the anomaly level is level 2, a corresponding customs declaration correction strategy is generated based on the logical association verification evaluation data and the threshold comparison verification evaluation data. If the anomaly level is level three, then activate the field format optimization processing strategy based on the field compliance verification assessment data. The VIN code, verification evaluation data, anomaly level, and anomaly handling strategy are used to generate corresponding hash values ​​through a preset encryption algorithm, written to preset cross-system multi-storage nodes, and a cross-system collaborative data verification report is generated.

[0035] It should be noted that anomalies are handled in tiers. Level 1 anomalies are those that prevent the customs declaration process from proceeding normally and cannot be corrected automatically. In these cases, customs declaration must be suspended and handled manually, such as those involving policy regulations or data authenticity issues. Level 2 anomalies are those involving inconsistent data logic, missing key fields, or exceeding reasonable thresholds. These require manual verification or automatic system completion before customs declaration can continue, such as those involving declared prices, quantities, or missing fields. Level 3 anomalies are those involving non-standard data formats, excessive redundant information, or minor deviations in non-critical logic that do not affect customs review results and can be eliminated through automatic correction, such as those involving formatting issues. Finally, to achieve end-to-end traceability, a hash value is generated using an encryption algorithm, written to multiple storage nodes across systems, and a cross-system collaborative data verification report is generated for viewing and analysis by system maintenance personnel.

[0036] According to an embodiment of the present invention, if the event is a newly added field or an updated field, semantic parsing is performed, and matching is conducted through a preset historical cross-system data mapping model to obtain mapping matching rules, including: If the mapping matching rule conflicts with the historical mapping matching rule in the preset historical cross-system data mapping model, the rule priority of the mapping matching rule is obtained, including first-level rule priority, second-level rule priority or third-level rule priority; If it is a first-level rule priority, then the preset historical cross-system data mapping model is modified according to the mapping matching rule to obtain the preset cross-system data mapping model; If it is a secondary rule priority, then determine whether the historical mapping matching rule is the preset core field mapping matching rule. If it is, then retain it; if not, then modify the historical mapping matching rule according to the mapping matching rule. If it is a level 3 rule priority, then the historical mapping matching rule is corrected based on the conflict fields between the mapping matching rule and the historical mapping matching rule.

[0037] It should be noted that when real-time dynamic mapping matching rules conflict with historical rules, a three-level priority judgment and correction is implemented. The first-level rule priority refers to policy-related rules, which have the highest priority and directly replace historical rules. The second-level rule priority refers to field mapping rules that are strongly related to the core business process of vehicle customs declaration and affect customs clearance efficiency or compliance. In this case, the preset core field mapping matching rules are retained, and non-core fields are matched with core fields. The third-level rule priority refers to mapping rules that have no policy requirements or are non-core business fields. In this case, only the conflicting parts need to be updated.

[0038] Please refer to Figure 4 , Figure 4 This is a high-level flowchart of a cross-system collaborative verification method for vehicle customs declaration data based on RPA in some embodiments of this application.

[0039] Please refer to Figure 5 , Figure 5 This is a system block diagram of a cross-system collaborative verification system for vehicle customs declaration data based on RPA, as described in some embodiments of this application.

[0040] It should be noted that the multi-source data acquisition module collects cross-system field metadata datasets to build a preset cross-system data mapping model. At the same time, the vehicle customs declaration cross-system dataset is collected, and after being standardized by the data processing module, it is used to perform data verification according to preset cross-system verification rules to obtain verification evaluation data. Then, after being processed by the three-level rule engine module, the anomaly handling module performs anomaly evaluation to determine the anomaly level and generate corresponding anomaly handling strategies. Meanwhile, the blockchain evidence storage module realizes full-process recording from data acquisition, processing, rule verification and anomaly handling, achieving full-process traceability.

[0041] This invention also discloses an RPA-based cross-system collaborative verification system for vehicle customs declaration data, comprising a memory and a processor. The memory includes an RPA-based cross-system collaborative verification method program for vehicle customs declaration data. When the processor executes the RPA-based cross-system collaborative verification method program for vehicle customs declaration data, it performs the following steps: Obtain the VIN code of the vehicle for customs declaration, obtain the cross-system dataset of vehicle customs declaration based on the VIN code, and process it through a preset cross-system data mapping model to obtain the standard cross-system dataset of vehicle customs declaration. The cross-system standard dataset for vehicle customs declaration is validated using preset cross-system validation rules to obtain validation evaluation data. The verification evaluation data is processed through a preset verification anomaly classification evaluation model to obtain the anomaly level; Anomalies are handled according to the anomaly level, and evidence is stored on the blockchain to generate a cross-system collaborative verification report.

[0042] It should be noted that, in order to achieve cross-system data collaborative verification based on RPA during vehicle customs declaration, firstly, based on the vehicle's unique VIN code, a multi-protocol adaptation module supporting HTTP, FTP, direct database connection, and interface capture was designed. This module non-intrusively extracts key evaluation data from multiple systems for cross-comparison and performs data standardization mapping to solve the data silo problem. Secondly, based on the cross-system standard dataset for vehicle customs declaration, a three-level verification process is performed: field compliance verification of basic rules, logical association verification of business rules, and threshold comparison verification of custom rules. Thirdly, based on the verification results, anomaly levels are assessed using a pre-set anomaly classification assessment model. Finally, corresponding handling strategies are implemented according to the anomaly level, and blockchain evidence is used to ensure the traceability of the entire data collaborative verification process. Simultaneously, a cross-system data collaborative verification report is generated for maintenance personnel to view and further analyze.

[0043] According to an embodiment of the present invention, the step of obtaining the VIN code of the vehicle for customs declaration, obtaining the cross-system dataset of vehicle customs declaration based on the VIN code, and processing it through a preset cross-system data mapping model to obtain the standard cross-system dataset of vehicle customs declaration includes: Obtain the VIN code of the vehicle being declared for customs and verify the VIN code; If the VIN code verification is successful, the cross-system dataset for vehicle customs declaration is obtained based on the VIN code, including manufacturing data from the production system, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data. The manufacturing data, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data of the production system are processed through a preset cross-system data mapping model to obtain a cross-system standard dataset for vehicle customs declaration, including standard data for manufacturing, logistics and transportation, tax collection and administration, and customs declaration and clearance. If the VIN code verification fails, an early warning response will be output.

[0044] It should be noted that the VIN code is the unique identifier of the vehicle being declared for customs. A cross-system data association mechanism is established based on the VIN code to ensure full data traceability. First, the obtained VIN code is verified to determine if it meets the format requirements. Then, corresponding production system manufacturing data, logistics and transportation data, tax administration data, and customs declaration data are extracted from the production system, logistics and transportation system, tax administration data, and customs declaration data. Production system manufacturing data includes vehicle model, engine number, and vehicle configuration parameters; logistics and transportation data includes bill of lading serial number, logistics node characteristic data, logistics volume, and transportation trajectory data; tax administration data includes invoice number, tax paid amount, and tax rate; and customs declaration data includes customs declaration number, declared price, and date. The collected data is then processed using a pre-set cross-system data mapping model. For example, the vehicle model is mapped to a vehicle type code; transportation trajectory data (structured storage of time and location) is precisely matched with the departure date in the customs declaration system; and a logical relationship is established between the tax paid amount in the tax administration system and the declared price in the customs declaration system (the tax paid amount is the product of the declared price and the tax rate).

[0045] According to an embodiment of the present invention, it further includes: Obtain cross-system field metadata for vehicle customs declaration, including field metadata from the production system, logistics and transportation system, tax collection and administration system, and customs declaration system. The metadata of the production system fields, logistics and transportation system fields, tax collection and administration system fields, and customs declaration system fields are processed by NLP and regular expression matching to obtain field event categories, including new field events, updated field events, or terminated field events. If it is a new field event or an updated field event, semantic parsing is performed, and matching is done through a preset historical cross-system data mapping model to obtain mapping matching rules; Update the preset historical cross-system data mapping model according to the mapping matching rules to obtain the preset cross-system data mapping model; If it is a termination field event, then the deletion process is performed to obtain the preset cross-system data mapping model.

[0046] It should be noted that, in order to achieve automatic and dynamic updates of the cross-system data mapping model, metadata such as field names and data types from the open APIs of different systems are collected periodically. The collected metadata is analyzed by NLP (Natural Language Processing) and regular expression matching to identify three types of events, including field addition events, field update events, and field termination events. The preset historical cross-system data mapping model is optimized and updated according to the event type. For added or changed events, the mapping between the added field and the associated fields of other systems is established. For example, the battery code of the customs declaration system is mapped to the battery model of the production system. Then, the format is converted to meet the requirements, such as the battery code being letters plus a number of digits.

[0047] According to an embodiment of the present invention, the step of verifying the cross-system standard dataset of vehicle customs declarations through preset cross-system verification rules to obtain verification evaluation data includes: The manufacturing standard data, logistics and transportation standard data, tax collection and administration standard data, and customs declaration and clearance standard data of the production system are verified using preset cross-system verification rules to obtain verification and evaluation data. The preset cross-system verification rules include field compliance verification rules, logical association verification rules, and threshold comparison verification rules; The verification and evaluation data includes field compliance verification and evaluation data, logical association verification and evaluation data, and threshold comparison verification and evaluation data.

[0048] It should be noted that the collected standard data undergoes three levels of dynamic rule-based layer-by-layer verification, including basic consistency field compliance verification, business logic dynamic rule logical association verification, and threshold comparison verification based on custom rules. Examples of field compliance verification are shown in Table 1, examples of logical association verification are shown in Table 2, and examples of threshold comparison verification are shown in Table 3. Based on the verification results, structured data is output, generating corresponding field compliance verification evaluation data, logical association verification evaluation data, and threshold comparison verification evaluation data.

[0049] According to an embodiment of the present invention, processing the verification evaluation data through a preset verification anomaly classification evaluation model to obtain an anomaly level includes: The field compliance verification assessment data, logical association verification assessment data, and threshold comparison verification assessment data are input into a preset verification anomaly classification assessment model for analysis and processing to obtain the verification anomaly assessment index. The anomaly evaluation index is compared with the preset anomaly evaluation threshold to obtain the anomaly level. The preset anomaly evaluation threshold includes a first preset anomaly evaluation threshold and a second preset anomaly evaluation threshold. If the verification anomaly evaluation index is less than or equal to the first preset verification anomaly evaluation threshold, the anomaly level is determined to be a level three anomaly. If the verification anomaly evaluation index is greater than the first preset verification anomaly evaluation threshold and less than or equal to the second preset verification anomaly evaluation threshold, then the anomaly level is determined to be a level two anomaly. If the verification anomaly evaluation index is greater than the second preset verification anomaly evaluation threshold, the anomaly level is determined to be a level one anomaly.

[0050] It should be noted that a preset verification anomaly classification assessment model is obtained by training a large amount of historical sample field compliance verification assessment data, logical association verification assessment data, threshold comparison verification assessment data, and corresponding verification anomaly assessment index. Then, real-time assessment data is input into the pre-trained model to obtain the real-time verification anomaly assessment index. For example, logical association verification assessment data: the declared quantity of 50 vehicles is greater than the logistics arrival quantity of 45 vehicles (logical conflict). Threshold comparison verification assessment data: the declared price is 150,000 yuan, which exceeds the dynamic threshold (100,000-120,000 yuan) for the same vehicle model, with a deviation rate of +25%. The core business fields (quantity and price) are in violation, affecting compliance but can be corrected. The model's verification anomaly assessment index score is 68 points. At the same time, it is compared with the first preset verification anomaly assessment threshold and the second preset verification anomaly assessment threshold. In this embodiment, the first preset verification anomaly assessment threshold is set to 60, and the second preset verification anomaly assessment threshold is set to 80. The anomaly level is determined to be level two anomaly, level one anomaly is the highest level of anomaly, and level three anomaly is the lowest level of anomaly.

[0051] According to an embodiment of the present invention, the step of performing anomaly handling based on the anomaly level and generating a cross-system collaborative verification report through blockchain notarization includes: Based on the anomaly level, perform anomaly handling to obtain an anomaly handling strategy; If the anomaly level is Level 1, the vehicle customs declaration process will be suspended and a warning response will be issued. If the anomaly level is level 2, a corresponding customs declaration correction strategy is generated based on the logical association verification evaluation data and the threshold comparison verification evaluation data. If the anomaly level is level three, then activate the field format optimization processing strategy based on the field compliance verification assessment data. The VIN code, verification evaluation data, anomaly level, and anomaly handling strategy are used to generate corresponding hash values ​​through a preset encryption algorithm, written to preset cross-system multi-storage nodes, and a cross-system collaborative data verification report is generated.

[0052] It should be noted that anomalies are handled in tiers. Level 1 anomalies are those that prevent the customs declaration process from proceeding normally and cannot be corrected automatically. In these cases, customs declaration must be suspended and handled manually, such as those involving policy regulations or data authenticity issues. Level 2 anomalies are those involving inconsistent data logic, missing key fields, or exceeding reasonable thresholds. These require manual verification or automatic system completion before customs declaration can continue, such as those involving declared prices, quantities, or missing fields. Level 3 anomalies are those involving non-standard data formats, excessive redundant information, or minor deviations in non-critical logic that do not affect customs review results and can be eliminated through automatic correction, such as those involving formatting issues. Finally, to achieve end-to-end traceability, a hash value is generated using an encryption algorithm, written to multiple storage nodes across systems, and a cross-system collaborative data verification report is generated for viewing and analysis by system maintenance personnel.

[0053] According to an embodiment of the present invention, if the event is a newly added field or an updated field, semantic parsing is performed, and matching is conducted through a preset historical cross-system data mapping model to obtain mapping matching rules, including: If the mapping matching rule conflicts with the historical mapping matching rule in the preset historical cross-system data mapping model, the rule priority of the mapping matching rule is obtained, including first-level rule priority, second-level rule priority or third-level rule priority; If it is a first-level rule priority, then the preset historical cross-system data mapping model is modified according to the mapping matching rule to obtain the preset cross-system data mapping model; If it is a secondary rule priority, then determine whether the historical mapping matching rule is the preset core field mapping matching rule. If it is, then retain it; if not, then modify the historical mapping matching rule according to the mapping matching rule. If it is a level 3 rule priority, then the historical mapping matching rule is corrected based on the conflict fields between the mapping matching rule and the historical mapping matching rule.

[0054] It should be noted that when real-time dynamic mapping matching rules conflict with historical rules, a three-level priority judgment and correction is implemented. The first-level rule priority refers to policy-related rules, which have the highest priority and directly replace historical rules. The second-level rule priority refers to field mapping rules that are strongly related to the core business process of vehicle customs declaration and affect customs clearance efficiency or compliance. In this case, the preset core field mapping matching rules are retained, and non-core fields are matched with core fields. The third-level rule priority refers to mapping rules that have no policy requirements or are non-core business fields. In this case, only the conflicting parts need to be updated.

[0055] The present invention discloses a cross-system collaborative verification method and system for vehicle customs declaration data based on RPA. By using the VIN code as the core to achieve cross-system cross-verification, evaluating the level of verification anomalies and correcting rule conflicts with three-level rules, and ensuring the traceability of the verification process through blockchain storage, the present invention achieves cross-system collaborative verification of vehicle customs declaration data based on RPA.

[0056] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0057] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0058] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0059] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0060] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A cross-system collaborative verification method for vehicle customs declaration data based on RPA, characterized in that, Includes the following steps: Obtain the VIN code of the vehicle for customs declaration, obtain the cross-system dataset of vehicle customs declaration based on the VIN code, and process it through a preset cross-system data mapping model to obtain the standard cross-system dataset of vehicle customs declaration. The cross-system standard dataset for vehicle customs declaration is validated using preset cross-system validation rules to obtain validation evaluation data. The verification evaluation data is processed through a preset verification anomaly classification evaluation model to obtain the anomaly level; Anomalies are handled according to the anomaly level, and evidence is stored on the blockchain to generate a cross-system collaborative verification report.

2. The cross-system collaborative verification method for vehicle customs declaration data based on RPA according to claim 1, characterized in that, The process involves obtaining the VIN code of the vehicle being declared for customs clearance, retrieving the cross-system dataset for vehicle customs clearance based on the VIN code, and processing it using a preset cross-system data mapping model to obtain a standard cross-system dataset for vehicle customs clearance, including: Obtain the VIN code of the vehicle being declared for customs and verify the VIN code; If the VIN code verification is successful, the cross-system dataset for vehicle customs declaration is obtained based on the VIN code, including manufacturing data from the production system, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data. The manufacturing data, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data of the production system are processed through a preset cross-system data mapping model to obtain a cross-system standard dataset for vehicle customs declaration, including standard data for manufacturing, logistics and transportation, tax collection and administration, and customs declaration and clearance. If the VIN code verification fails, an early warning response will be output.

3. The cross-system collaborative verification method for vehicle customs declaration data based on RPA according to claim 2, characterized in that, Also includes: Obtain cross-system field metadata for vehicle customs declaration, including field metadata from the production system, logistics and transportation system, tax collection and administration system, and customs declaration system. The metadata of the production system fields, logistics and transportation system fields, tax collection and administration system fields, and customs declaration system fields are processed by NLP and regular expression matching to obtain field event categories, including new field events, updated field events, or terminated field events. If it is a new field event or an updated field event, semantic parsing is performed, and matching is done through a preset historical cross-system data mapping model to obtain mapping matching rules; Update the preset historical cross-system data mapping model according to the mapping matching rules to obtain the preset cross-system data mapping model; If it is a termination field event, then the deletion process is performed to obtain the preset cross-system data mapping model.

4. The cross-system collaborative verification method for vehicle customs declaration data based on RPA according to claim 2, characterized in that, The step of verifying the cross-system standard dataset of vehicle customs declarations using preset cross-system verification rules to obtain verification evaluation data includes: The manufacturing standard data, logistics and transportation standard data, tax collection and administration standard data, and customs declaration and clearance standard data of the production system are verified using preset cross-system verification rules to obtain verification and evaluation data. The preset cross-system verification rules include field compliance verification rules, logical association verification rules, and threshold comparison verification rules; The verification and evaluation data includes field compliance verification and evaluation data, logical association verification and evaluation data, and threshold comparison verification and evaluation data.

5. The cross-system collaborative verification method for vehicle customs declaration data based on RPA according to claim 4, characterized in that, The step of processing the verification evaluation data through a preset verification anomaly classification evaluation model to obtain the anomaly level includes: The field compliance verification assessment data, logical association verification assessment data, and threshold comparison verification assessment data are input into a preset verification anomaly classification assessment model for analysis and processing to obtain the verification anomaly assessment index. The anomaly evaluation index is compared with the preset anomaly evaluation threshold to obtain the anomaly level. The preset anomaly evaluation threshold includes a first preset anomaly evaluation threshold and a second preset anomaly evaluation threshold. If the verification anomaly evaluation index is less than or equal to the first preset verification anomaly evaluation threshold, the anomaly level is determined to be a level three anomaly. If the verification anomaly evaluation index is greater than the first preset verification anomaly evaluation threshold and less than or equal to the second preset verification anomaly evaluation threshold, then the anomaly level is determined to be a level two anomaly. If the verification anomaly evaluation index is greater than the second preset verification anomaly evaluation threshold, the anomaly level is determined to be a level one anomaly.

6. The cross-system collaborative verification method for vehicle customs declaration data based on RPA according to claim 5, characterized in that, The process of handling anomalies based on the anomaly level and generating a cross-system collaborative data verification report via blockchain storage includes: Based on the anomaly level, perform anomaly handling to obtain an anomaly handling strategy; If the anomaly level is Level 1, the vehicle customs declaration process will be suspended and a warning response will be issued. If the anomaly level is level 2, a corresponding customs declaration correction strategy is generated based on the logical association verification evaluation data and the threshold comparison verification evaluation data. If the anomaly level is level three, then activate the field format optimization processing strategy based on the field compliance verification assessment data. The VIN code, verification evaluation data, anomaly level, and anomaly handling strategy are used to generate corresponding hash values ​​through a preset encryption algorithm, written to preset cross-system multi-storage nodes, and a cross-system collaborative data verification report is generated.

7. The cross-system collaborative verification method for vehicle customs declaration data based on RPA according to claim 3, characterized in that, If the event is a newly added field or an updated field, semantic parsing is performed, and matching is conducted using a preset historical cross-system data mapping model to obtain mapping matching rules, including: If the mapping matching rule conflicts with the historical mapping matching rule in the preset historical cross-system data mapping model, the rule priority of the mapping matching rule is obtained, including first-level rule priority, second-level rule priority or third-level rule priority; If it is a first-level rule priority, then the preset historical cross-system data mapping model is modified according to the mapping matching rule to obtain the preset cross-system data mapping model; If it is a secondary rule priority, then determine whether the historical mapping matching rule is the preset core field mapping matching rule. If it is, then retain it; if not, then modify the historical mapping matching rule according to the mapping matching rule. If it is a level 3 rule priority, then the historical mapping matching rule is corrected based on the conflict fields between the mapping matching rule and the historical mapping matching rule.

8. A cross-system collaborative verification system for vehicle customs declaration data based on RPA, characterized in that, The system includes a memory and a processor. The memory contains a program for a cross-system collaborative verification method for vehicle customs declaration data based on RPA. When the program for the cross-system collaborative verification method for vehicle customs declaration data based on RPA is executed by the processor, it performs the following steps: Obtain the VIN code of the vehicle for customs declaration, obtain the cross-system dataset of vehicle customs declaration based on the VIN code, and process it through a preset cross-system data mapping model to obtain the standard cross-system dataset of vehicle customs declaration. The cross-system standard dataset for vehicle customs declaration is validated using preset cross-system validation rules to obtain validation evaluation data. The verification evaluation data is processed through a preset verification anomaly classification evaluation model to obtain the anomaly level; Anomalies are handled according to the anomaly level, and evidence is stored on the blockchain to generate a cross-system collaborative verification report.

9. The RPA-based cross-system collaborative verification system for vehicle customs declaration data according to claim 8, characterized in that, The process involves obtaining the VIN code of the vehicle being declared for customs clearance, retrieving the cross-system dataset for vehicle customs clearance based on the VIN code, and processing it using a preset cross-system data mapping model to obtain a standard cross-system dataset for vehicle customs clearance, including: Obtain the VIN code of the vehicle being declared for customs and verify the VIN code; If the VIN code verification is successful, the cross-system dataset for vehicle customs declaration is obtained based on the VIN code, including manufacturing data from the production system, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data. The manufacturing data, logistics and transportation data, tax collection and administration data, and customs declaration and clearance data of the production system are processed through a preset cross-system data mapping model to obtain a cross-system standard dataset for vehicle customs declaration, including standard data for manufacturing, logistics and transportation, tax collection and administration, and customs declaration and clearance. If the VIN code verification fails, an early warning response will be output.

10. The RPA-based cross-system collaborative verification system for vehicle customs declaration data according to claim 9, characterized in that, Also includes: Obtain cross-system field metadata for vehicle customs declaration, including field metadata from the production system, logistics and transportation system, tax collection and administration system, and customs declaration system. The metadata of the production system fields, logistics and transportation system fields, tax collection and administration system fields, and customs declaration system fields are processed by NLP and regular expression matching to obtain field event categories, including new field events, updated field events, or terminated field events. If it is a new field event or an updated field event, semantic parsing is performed, and matching is done through a preset historical cross-system data mapping model to obtain mapping matching rules; Update the preset historical cross-system data mapping model according to the mapping matching rules to obtain the preset cross-system data mapping model; If it is a termination field event, then the deletion process is performed to obtain the preset cross-system data mapping model.

Images