Customs shipping order and customs declaration order comparative analysis method based on neural network

Abstract

The invention relates to the field of real-time comparative analysis of customs shipping orders and customs declaration orders, in particular to a comparative analysis method of customs shipping orders and customs declaration orders based on a neural network, which comprises the following steps: respectively acquiring text data characteristics of customs shipping orders and customs declaration orders; establishing a customs shipping order data association model based on a neural network by using the text data features of the customs shipping order, and establishing a customs declaration data comparison model based on the neural network by using the text data features of the customs declaration; and obtaining a comparison analysis result of the customs shipping order and the customs declaration order by using the customs shipping order data association model and the customs declaration order data comparison model, optimizing the data matching logic through deep learning, reducing the misjudgment rate, improving the reliability of the comparison result, processing structured and unstructured data, adapting to different formats of shipping orders and customs declaration orders, and improving the user experience. And a feedback verification mechanism is adopted, the model is continuously optimized, and the stability and adaptability of long-term use are improved.

Description

Technical Field

[0001] The present invention relates to the field of real-time comparison and analysis of a customs manifest and a customs declaration form, and in particular to a method for comparing and analyzing a customs manifest and a customs declaration form based on a neural network. Background Art

[0002] With the rapid development of international trade, the complexity and data volume of customs supervision have increased dramatically. The comparison and analysis of customs manifests and customs declarations has become an important part of ensuring trade security and improving customs clearance efficiency. Traditional manual comparison methods are inefficient, prone to errors, and difficult to cope with the real-time processing needs of large-scale data. Existing automated comparison systems are mostly based on rule matching or simple data verification algorithms, lacking the ability to deeply mine and intelligently analyze text data features, resulting in insufficient accuracy and adaptability of the comparison results. In addition, the existing technology for comparing customs manifests and customs declarations is usually limited to single-dimensional data verification, lacking the ability to comprehensively model data location, type, content and historical correlation, resulting in insufficient integrity and reliability of the comparison results. Therefore, how to use neural network technology to construct an association model and comparison model between customs manifests and customs declarations to achieve efficient and accurate automated analysis has become a technical problem that needs to be solved in the current field of intelligent processing of customs data. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a method for comparing and analyzing the customs manifest and the customs declaration form based on a neural network. By extracting the data feature content of different customs documents and establishing a multi-level model based on a neural network, the analysis and comparison results can be obtained efficiently and accurately.

[0004] To achieve the above object, the present invention provides a method for comparing and analyzing a customs manifest and a customs declaration form based on a neural network, comprising: S1. Obtain the text data features of the customs manifest and customs declaration form respectively; S2. Establishing a customs manifest data association model based on a neural network using the text data features of the customs manifest; S3, using the text data features of the customs declaration form to establish a customs declaration form data comparison model based on a neural network; S4. Obtain the comparison and analysis results of the customs manifest and the customs declaration form by using the customs manifest data association model and the customs declaration form data comparison model.

[0005] Preferably, the steps of respectively obtaining the text data features of the customs manifest and the customs declaration form include: Obtain the text data volume, text data type, and text data content of real-time customs manifests; Obtain the text data volume, text data type, and text data content of the real-time customs declaration form; Acquiring customs manifest text table data according to the text data content of the real-time customs manifest; Acquiring customs declaration form text data according to the text data content of the real-time customs declaration form; Using the text data volume, text data type, text data content, and text table data of the customs manifest and the text data volume, text data type, text data content, and text table data of the real-time customs declaration as text data features of the customs manifest and the customs declaration; The customs manifest text table data includes text table type, text table content and text table arrangement order, and the customs declaration form text table data includes text table type, text table content and text table arrangement order.

[0006] Furthermore, establishing a customs manifest data association model based on a neural network using the text data features of the customs manifest includes: S2-1, using the text data features of the customs manifest corresponding to the text data volume, text data type, and text data content of the customs manifest to establish a customs manifest data analysis model based on a neural network; S2-2, using the customs manifest text table data to establish a customs manifest data verification model based on a neural network; S2-3. Utilize the customs manifest data analysis model and the customs manifest data verification model as a customs manifest data association model.

[0007] Furthermore, establishing a customs manifest data analysis model based on a neural network using the text data features of the customs manifest corresponding to the text data volume, text data type, and text data content of the customs manifest includes: According to the text data volume and text data content corresponding to the customs manifest of the text data features of the customs manifest, respectively obtain the historical text data volume and historical text data content corresponding to the customs manifest; The historical text data content is used as input, the historical text data volume is used as output, the text data features of the customs manifest correspond to the text data type of the customs manifest to obtain the hidden layer structure, and the basic corresponding model of the customs manifest data is established based on neural network training.

[0008] Further, using the customs manifest text table data to establish a customs manifest data verification model based on a neural network includes: S2-2-1, using the customs manifest text table data to obtain the data position mark of the customs manifest according to the text data features of the customs manifest and the text data content; S2-2-2, using the customs manifest text table data to obtain a data corresponding mark of the customs manifest according to the text data characteristics of the customs manifest and the text data type; S2-2-3, using the text table data of the customs manifest as input, the data position mark and data corresponding mark of the customs manifest as output, the text data features of the customs manifest corresponding to the text data type to obtain the hidden layer structure, and establish an initial customs manifest data verification model based on neural network training; S2-2-4. Obtain corresponding historical customs manifest text table data, historical data position mark of the customs manifest and historical data corresponding mark according to the customs manifest text table data; S2-2-5, using the historical customs manifest text table data to input the initial customs manifest data verification model to obtain the initial customs manifest data verification result; S2-2-6. Determine whether the initial customs manifest data verification result corresponds to the historical data position mark and historical data corresponding mark of the customs manifest. If so, use the initial customs manifest data verification model as the customs manifest data verification model. Otherwise, use the non-corresponding initial customs manifest data verification result to correspond to the historical customs manifest text table data to update the customs manifest text table data, and return to S2-2-3.

[0009] Furthermore, using the text data features of the customs declaration form to establish a customs declaration form data comparison model based on a neural network includes: S3-1, using the text data features of the customs declaration form to establish a customs declaration form data self-checking model based on a neural network; S3-2, using the customs declaration data self-checking model to perform feedback verification processing to obtain a customs declaration data comparison model.

[0010] Furthermore, using the text data features of the customs declaration form to establish a customs declaration form data self-checking model based on a neural network includes: S3-1-1, obtaining the historical text data volume, historical text data type, historical text data content and historical customs declaration text table data corresponding to the real-time customs declaration according to the text data characteristics of the customs declaration; S3-1-2, using the historical text data type and the text table type of the historical customs declaration text table data as input, and the association result between the historical text data type and the text table type of the historical customs declaration text table data as output, and training based on a neural network to obtain a primary proofreading model; S3-1-3, using the historical text data content and the text table content of the historical customs declaration form text table data as input, and the association result of the historical text data content and the text table content of the historical customs declaration form text table data as output, and training based on a neural network to obtain a secondary proofreading model; S3-1-4. Use the first-level proofreading model and the second-level proofreading model as a self-proofreading model for customs declaration data.

[0011] Furthermore, the customs declaration data comparison model is obtained by using the customs declaration data self-checking model to perform feedback verification processing, including: S3-2-1, using the text table arrangement order of the customs declaration text table data as a model output verification label; S3-2-2, using the text data type of the real-time customs declaration form and the text table type of the customs declaration form text table data to input the first-level proofreading model of the customs declaration form data self-proofreading model to obtain a first-level proofreading result; S3-2-3, using the text data type of the real-time customs declaration form and the text table type of the customs declaration form text table data to input the secondary proofreading model of the customs declaration form data self-proofreading model to obtain the secondary proofreading result; S3-2-4, determine whether the text table arrangement order of the first-level proofreading result corresponds to the text table data of the historical customs declaration form text table data, if so, execute S3-2-5, otherwise, obtain the text data type corresponding to the first-level proofreading result that does not correspond and the text table type of the customs declaration form text table data, update the historical text data type and the text table type of the historical customs declaration form text table data, and return to S3-1-2; S3-2-5. Determine whether the secondary proofreading result corresponds to the text table arrangement order of the historical customs declaration text table data. If so, use the customs declaration data self-proofreading model as the customs declaration data comparison model. Otherwise, obtain the text data content corresponding to the non-corresponding secondary proofreading result and the text table content of the customs declaration text table data to update the historical text data content and the text table content of the historical customs declaration text table data, and return to S3-1-3.

[0012] Furthermore, the comparison analysis results of the customs manifest and the customs declaration form obtained by using the customs manifest data association model and the customs declaration form data comparison model include: S4-1, respectively obtain the real-time text data features of the customs manifest and the customs declaration form; S4-2, using the real-time text data features of the customs manifest to input the customs manifest data association model to obtain the real-time customs manifest data basic corresponding results and the real-time customs manifest data verification results in turn; S4-3, using the real-time text data features of the customs declaration form to input into the customs declaration form data comparison model to obtain a real-time customs declaration form data comparison result; S4-4, judging whether the real-time customs manifest data basic corresponding result and the real-time customs declaration form data comparison result are completely corresponding, if so, executing S4-5, otherwise, outputting the non-corresponding content of the real-time customs manifest data basic corresponding result and the real-time customs declaration form data comparison result as the customs manifest and customs declaration form comparison analysis result; S4-5, judging whether the real-time customs manifest data verification result and the real-time customs declaration form data comparison result are completely corresponding, if so, outputting the real-time customs manifest data basic corresponding result, the real-time customs manifest data verification result and the real-time customs declaration form data comparison result as the customs manifest and customs declaration form comparison analysis result, otherwise, outputting the non-corresponding content of the real-time customs manifest data verification result and the real-time customs declaration form data comparison result as the customs manifest and customs declaration form comparison analysis result.

[0013] Compared with the closest prior art, the present invention has the following beneficial effects: Improve comparison efficiency: Use neural networks to automatically extract data features and establish association models, reduce manual intervention, and significantly improve data processing speed; Enhanced accuracy: Optimize data matching logic through deep learning, reduce the misjudgment rate, and improve the reliability of comparison results; Adapt to complex data: Able to process structured and unstructured data, adapt to manifests and customs declarations in different formats, and improve the versatility of the system; Dynamic optimization capability: Adopt feedback verification mechanism to continuously optimize the model and improve stability and adaptability for long-term use. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The present invention provides a flow chart of a method for comparing and analyzing a customs manifest and a customs declaration form based on a neural network. DETAILED DESCRIPTION

[0015] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0016] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1:

[0018] The present invention provides a method for comparing and analyzing customs manifests and customs declarations based on neural networks. Figure 1 As shown, including: S1. Obtain the text data features of the customs manifest and customs declaration form respectively; S2. Establishing a customs manifest data association model based on a neural network using the text data features of the customs manifest; S3, using the text data features of the customs declaration form to establish a customs declaration form data comparison model based on a neural network; S4. Obtain the comparison and analysis results of the customs manifest and the customs declaration form by using the customs manifest data association model and the customs declaration form data comparison model.

[0019] S1 specifically includes: S1-1. Obtain the text data volume, text data type, and text data content of the real-time customs manifest; S1-2, obtaining the text data volume, text data type, and text data content of the real-time customs declaration form; S1-3, obtaining customs manifest text table data according to the text data content of the real-time customs manifest; S1-4, obtaining the customs declaration form text data according to the text data content of the real-time customs declaration form; S1-5, using the text data volume, text data type, text data content, and text table data of the customs manifest and the text data volume, text data type, text data content, and text table data of the real-time customs declaration as text data features of the customs manifest and the customs declaration; The customs manifest text table data includes text table type, text table content and text table arrangement order, and the customs declaration form text table data includes text table type, text table content and text table arrangement order.

[0020] S2 specifically includes: S2-1, using the text data features of the customs manifest corresponding to the text data volume, text data type, and text data content of the customs manifest to establish a customs manifest data analysis model based on a neural network; S2-2, using the customs manifest text table data to establish a customs manifest data verification model based on a neural network; S2-3. Utilize the customs manifest data analysis model and the customs manifest data verification model as a customs manifest data association model.

[0021] In this embodiment, a method for comparing and analyzing a customs manifest and a customs declaration form based on a neural network is provided. The specific definitions of the customs manifest data analysis model and the customs manifest data verification model include: Data analysis model: Input: historical manifest data content; Output: historical manifest data volume; Training method: Training based on neural networks (such as LSTM, Transformer) to establish a mapping relationship between data volume and content; Data verification model: Input: manifest form data; Output: data location mark, data corresponding mark; Training method: Use CNN or graph neural network (GNN) to process tabular data to ensure matching of data location and type.

[0022] S2-1 specifically includes: S2-1-1, obtaining the historical text data volume and historical text data content of the corresponding customs manifest according to the text data volume and text data content of the customs manifest corresponding to the text data features of the customs manifest; S2-1-2. Using the content of the historical text data as input and the amount of historical text data as output, the text data features of the customs manifest correspond to the text data type of the customs manifest to obtain the hidden layer structure, and establish a corresponding model based on the customs manifest data through training based on a neural network.

[0023] S2-2 specifically includes: S2-2-1, using the customs manifest text table data to obtain the data position mark of the customs manifest according to the text data features of the customs manifest and the text data content; S2-2-2, using the customs manifest text table data to obtain a data corresponding mark of the customs manifest according to the text data characteristics of the customs manifest and the text data type; S2-2-3, using the text table data of the customs manifest as input, the data position mark and data corresponding mark of the customs manifest as output, the text data features of the customs manifest corresponding to the text data type to obtain the hidden layer structure, and establish an initial customs manifest data verification model based on neural network training; S2-2-4. Obtain corresponding historical customs manifest text table data, historical data position mark of the customs manifest and historical data corresponding mark according to the customs manifest text table data; S2-2-5, using the historical customs manifest text table data to input the initial customs manifest data verification model to obtain the initial customs manifest data verification result; S2-2-6. Determine whether the initial customs manifest data verification result corresponds to the historical data position mark and historical data corresponding mark of the customs manifest. If so, use the initial customs manifest data verification model as the customs manifest data verification model. Otherwise, use the non-corresponding initial customs manifest data verification result to correspond to the historical customs manifest text table data to update the customs manifest text table data, and return to S2-2-3.

[0024] S3 specifically includes: S3-1, using the text data features of the customs declaration form to establish a customs declaration form data self-checking model based on a neural network; S3-2, using the customs declaration data self-checking model to perform feedback verification processing to obtain a customs declaration data comparison model.

[0025] In this embodiment, a method for comparing and analyzing a customs manifest and a customs declaration form based on a neural network is provided. The specific definition of the customs declaration form data comparison model includes: Self-correcting model: First-level proofreading: check whether the data type matches the table type; Secondary proofreading: check whether the data content matches the table content; Feedback verification: If the comparison result is inconsistent with historical data, adjust the model parameters and retrain to improve accuracy.

[0026] S3-1 specifically includes: S3-1-1, obtaining the historical text data volume, historical text data type, historical text data content and historical customs declaration text table data corresponding to the real-time customs declaration according to the text data characteristics of the customs declaration; S3-1-2, using the historical text data type and the text table type of the historical customs declaration text table data as input, and the association result between the historical text data type and the text table type of the historical customs declaration text table data as output, and training based on a neural network to obtain a primary proofreading model; S3-1-3, using the historical text data content and the text table content of the historical customs declaration form text table data as input, and the association result of the historical text data content and the text table content of the historical customs declaration form text table data as output, and training based on a neural network to obtain a secondary proofreading model; S3-1-4. Use the first-level proofreading model and the second-level proofreading model as a self-proofreading model for customs declaration data.

[0027] S3-2 specifically includes: S3-2-1, using the text table arrangement order of the customs declaration text table data as a model output verification label; S3-2-2, using the text data type of the real-time customs declaration form and the text table type of the customs declaration form text table data to input the first-level proofreading model of the customs declaration form data self-proofreading model to obtain a first-level proofreading result; S3-2-3, using the text data type of the real-time customs declaration form and the text table type of the customs declaration form text table data to input the secondary proofreading model of the customs declaration form data self-proofreading model to obtain the secondary proofreading result; S3-2-4, determine whether the text table arrangement order of the first-level proofreading result corresponds to the text table data of the historical customs declaration form text table data, if so, execute S3-2-5, otherwise, obtain the text data type corresponding to the first-level proofreading result that does not correspond and the text table type of the customs declaration form text table data, update the historical text data type and the text table type of the historical customs declaration form text table data, and return to S3-1-2; S3-2-5. Determine whether the secondary proofreading result corresponds to the text table arrangement order of the historical customs declaration text table data. If so, use the customs declaration data self-proofreading model as the customs declaration data comparison model. Otherwise, obtain the text data content corresponding to the non-corresponding secondary proofreading result and the text table content of the customs declaration text table data to update the historical text data content and the text table content of the historical customs declaration text table data, and return to S3-1-3.

[0028] S4 specifically includes: S4-1, respectively obtain the real-time text data features of the customs manifest and the customs declaration form; S4-2, using the real-time text data features of the customs manifest to input the customs manifest data association model to obtain the real-time customs manifest data basic corresponding results and the real-time customs manifest data verification results in turn; S4-3, using the real-time text data features of the customs declaration form to input into the customs declaration form data comparison model to obtain a real-time customs declaration form data comparison result; S4-4, judging whether the real-time customs manifest data basic corresponding result and the real-time customs declaration form data comparison result are completely corresponding, if so, executing S4-5, otherwise, outputting the non-corresponding content of the real-time customs manifest data basic corresponding result and the real-time customs declaration form data comparison result as the customs manifest and customs declaration form comparison analysis result; S4-5, judging whether the real-time customs manifest data verification result and the real-time customs declaration form data comparison result are completely corresponding, if so, outputting the real-time customs manifest data basic corresponding result, the real-time customs manifest data verification result and the real-time customs declaration form data comparison result as the customs manifest and customs declaration form comparison analysis result, otherwise, outputting the non-corresponding content of the real-time customs manifest data verification result and the real-time customs declaration form data comparison result as the customs manifest and customs declaration form comparison analysis result.

[0029] It will be appreciated by those skilled in the art 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. Furthermore, 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.

[0030] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the 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 generate 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.

[0031] 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.

[0032] 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 The steps for the functions specified in one or more boxes.

[0033] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for comparing and analyzing customs manifest and customs declaration based on neural network, characterized in that: include: S1. Obtain the text data features of the customs manifest and customs declaration form respectively; S2. Establishing a customs manifest data association model based on a neural network using the text data features of the customs manifest; S3, using the text data features of the customs declaration form to establish a customs declaration form data comparison model based on a neural network; S4. Obtain the comparison and analysis results of the customs manifest and the customs declaration form by using the customs manifest data association model and the customs declaration form data comparison model.

2. A method for comparing and analyzing customs manifest and customs declaration form based on neural network as claimed in claim 1, characterized in that: The text data features of the customs manifest and the customs declaration form are obtained separately, including: Obtain the text data volume, text data type, and text data content of real-time customs manifests; Obtain the text data volume, text data type, and text data content of the real-time customs declaration form; Acquiring customs manifest text table data according to the text data content of the real-time customs manifest; Acquiring customs declaration form text data according to the text data content of the real-time customs declaration form; Using the text data volume, text data type, text data content, and text table data of the customs manifest and the text data volume, text data type, text data content, and text table data of the real-time customs declaration as text data features of the customs manifest and the customs declaration; The customs manifest text table data includes text table type, text table content and text table arrangement order, and the customs declaration form text table data includes text table type, text table content and text table arrangement order.

3. A method for comparing and analyzing customs manifest and customs declaration form based on neural network as claimed in claim 2, characterized in that: Using the text data features of the customs manifest to establish a customs manifest data association model based on a neural network includes: S2-1, using the text data features of the customs manifest corresponding to the text data volume, text data type, and text data content of the customs manifest to establish a customs manifest data analysis model based on a neural network; S2-2, using the customs manifest text table data to establish a customs manifest data verification model based on a neural network; S2-3. Utilize the customs manifest data analysis model and the customs manifest data verification model as a customs manifest data association model.

4. A method for comparing and analyzing customs manifest and customs declaration form based on neural network as claimed in claim 3, characterized in that: Establishing a customs manifest data analysis model based on a neural network using the text data features of the customs manifest corresponding to the text data volume, text data type, and text data content of the customs manifest includes: According to the text data volume and text data content corresponding to the customs manifest of the text data features of the customs manifest, respectively obtain the historical text data volume and historical text data content corresponding to the customs manifest; The historical text data content is used as input, the historical text data volume is used as output, the text data features of the customs manifest correspond to the text data type of the customs manifest to obtain the hidden layer structure, and the basic corresponding model of the customs manifest data is established based on neural network training.

5. A method for comparing and analyzing customs manifest and customs declaration form based on neural network as claimed in claim 4, characterized in that: Using the customs manifest text table data to establish a customs manifest data verification model based on a neural network includes: S2-2-1, using the customs manifest text table data to obtain the data position mark of the customs manifest according to the text data features of the customs manifest and the text data content; S2-2-2, using the customs manifest text table data to obtain a data corresponding mark of the customs manifest according to the text data characteristics of the customs manifest and the text data type; S2-2-3, using the text table data of the customs manifest as input, the data position mark and data corresponding mark of the customs manifest as output, the text data features of the customs manifest corresponding to the text data type to obtain the hidden layer structure, and establish an initial customs manifest data verification model based on neural network training; S2-2-4. Obtain corresponding historical customs manifest text table data, historical data position mark of the customs manifest and historical data corresponding mark according to the customs manifest text table data; S2-2-5, using the historical customs manifest text table data to input the initial customs manifest data verification model to obtain the initial customs manifest data verification result; S2-2-6. Determine whether the initial customs manifest data verification result corresponds to the historical data position mark and historical data corresponding mark of the customs manifest. If so, use the initial customs manifest data verification model as the customs manifest data verification model. Otherwise, use the non-corresponding initial customs manifest data verification result to correspond to the historical customs manifest text table data to update the customs manifest text table data, and return to S2-2-3.

6. A method for comparing and analyzing customs manifest and customs declaration form based on neural network as claimed in claim 3, characterized in that: Using the text data features of the customs declaration form to establish a customs declaration form data comparison model based on a neural network includes: S3-1, using the text data features of the customs declaration form to establish a customs declaration form data self-checking model based on a neural network; S3-2, using the customs declaration data self-checking model to perform feedback verification processing to obtain a customs declaration data comparison model.

7. A method for comparing and analyzing customs manifest and customs declaration form based on neural network as claimed in claim 6, characterized in that: Using the text data features of the customs declaration form to establish a customs declaration form data self-checking model based on a neural network includes: S3-1-1, obtaining the historical text data volume, historical text data type, historical text data content and historical customs declaration text table data corresponding to the real-time customs declaration according to the text data characteristics of the customs declaration; S3-1-2, using the historical text data type and the text table type of the historical customs declaration text table data as input, and the association result between the historical text data type and the text table type of the historical customs declaration text table data as output, and training based on a neural network to obtain a primary proofreading model; S3-1-3, using the historical text data content and the text table content of the historical customs declaration form text table data as input, and the association result of the historical text data content and the text table content of the historical customs declaration form text table data as output, and training based on a neural network to obtain a secondary proofreading model; S3-1-4. Use the first-level proofreading model and the second-level proofreading model as a self-proofreading model for customs declaration data.

8. A method for comparing and analyzing customs manifest and customs declaration form based on neural network as claimed in claim 7, characterized in that: The customs declaration data comparison model obtained by using the customs declaration data self-checking model for feedback verification processing includes: S3-2-1, using the text table arrangement order of the customs declaration text table data as a model output verification label; S3-2-2, using the text data type of the real-time customs declaration form and the text table type of the customs declaration form text table data to input the first-level proofreading model of the customs declaration form data self-proofreading model to obtain a first-level proofreading result; S3-2-3, using the text data type of the real-time customs declaration form and the text table type of the customs declaration form text table data to input the secondary proofreading model of the customs declaration form data self-proofreading model to obtain the secondary proofreading result; S3-2-4, determine whether the text table arrangement order of the first-level proofreading result corresponds to the text table data of the historical customs declaration form text table data, if so, execute S3-2-5, otherwise, obtain the text data type corresponding to the first-level proofreading result that does not correspond and the text table type of the customs declaration form text table data, update the historical text data type and the text table type of the historical customs declaration form text table data, and return to S3-1-2; S3-2-5. Determine whether the secondary proofreading result corresponds to the text table arrangement order of the historical customs declaration text table data. If so, use the customs declaration data self-proofreading model as the customs declaration data comparison model. Otherwise, obtain the text data content corresponding to the non-corresponding secondary proofreading result and the text table content of the customs declaration text table data to update the historical text data content and the text table content of the historical customs declaration text table data, and return to S3-1-3.

9. A method for comparing and analyzing customs manifest and customs declaration form based on neural network as claimed in claim 4, characterized in that: The comparison analysis results of the customs manifest and the customs declaration form obtained by using the customs manifest data association model and the customs declaration form data comparison model include: S4-1, respectively obtain the real-time text data features of the customs manifest and the customs declaration form; S4-2, using the real-time text data features of the customs manifest to input the customs manifest data association model to obtain the real-time customs manifest data basic corresponding results and the real-time customs manifest data verification results in turn; S4-3, using the real-time text data features of the customs declaration form to input into the customs declaration form data comparison model to obtain a real-time customs declaration form data comparison result; S4-4, judging whether the real-time customs manifest data basic corresponding result and the real-time customs declaration form data comparison result are completely corresponding, if so, executing S4-5, otherwise, outputting the non-corresponding content of the real-time customs manifest data basic corresponding result and the real-time customs declaration form data comparison result as the customs manifest and customs declaration form comparison analysis result; S4-5, judging whether the real-time customs manifest data verification result and the real-time customs declaration form data comparison result are completely corresponding, if so, outputting the real-time customs manifest data basic corresponding result, the real-time customs manifest data verification result and the real-time customs declaration form data comparison result as the customs manifest and customs declaration form comparison analysis result, otherwise, outputting the non-corresponding content of the real-time customs manifest data verification result and the real-time customs declaration form data comparison result as the customs manifest and customs declaration form comparison analysis result.

Images