Data verification and estimation method, electronic equipment and storage medium

By acquiring and clearing abnormal items in customs declaration data, and using the reference value of the preset data reference database for verification and estimation, the transportation extension and cost increase caused by abnormal customs declaration form data is solved, and more accurate and efficient customs declaration data processing is achieved.

CN118941188APending Publication Date: 2024-11-12ZTE CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310523844.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-10
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the prior art, data abnormalities in customs declaration forms will lead to an extended transportation time of physical goods, increase the transportation costs of enterprises, and lack effective data verification methods to improve the quality of customs declaration data.

Method used

By obtaining the customs declaration data to be verified, querying the preset data reference database to obtain the preset reference value, verifying and estimating the customs declaration value based on the reference value, clearing abnormal data, obtaining target customs declaration data, and ensuring data accuracy and quality.

Benefits of technology

It improves the quality of customs declaration data, reduces the transmission time of physical goods, and reduces the transportation costs of enterprises.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941188A_ABST
    Figure CN118941188A_ABST
Patent Text Reader

Abstract

The invention provides a data checking and estimating method, electronic equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: obtaining customs declaration data to be verified and estimated, wherein the customs declaration data to be verified and estimated comprises attribute information of a commodity to be verified and estimated and a corresponding customs declaration numerical value; according to the attribute information of the to-be-verified and estimated commodity, a preset data reference library is inquired, a preset reference value corresponding to the to-be-verified and estimated commodity is obtained, and the preset data reference library is a database obtained by screening out abnormal data in historical customs declaration data; according to a preset reference value corresponding to the to-be-assessed commodity, performing assessment on the customs declaration value corresponding to the attribute information of the to-be-assessed commodity, and determining that abnormal data exist in the customs declaration value corresponding to the attribute information of the to-be-assessed commodity; and clearing the abnormal data to obtain target customs declaration data. The quality of customs declaration data is improved, the transmission time of entity goods is shortened, and the transportation cost of enterprises is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data verification method, an electronic device and a storage medium. Background Art

[0002] The data in the customs declaration form is used to verify the relevant parameters of the physical goods that need to be cleared to determine whether the physical goods meet the requirements. If it is confirmed that there are abnormalities in the data in the customs declaration form, it will affect the transportation of the physical goods. For example, the customs declaration form needs to be rewritten and then submitted to the customs for review, or the quantity or category of the goods needs to be verified based on the declaration form. The above operations will prolong the transmission time of the physical goods, thereby increasing the transportation costs of the enterprise.

[0003] How to improve the quality of customs declarations to reduce the transmission time of physical goods and reduce the transportation costs of enterprises has become an urgent problem to be solved. Summary of the invention

[0004] The present application provides a data verification method, an electronic device and a storage medium.

[0005] The embodiment of the present application provides a data verification method, which includes: obtaining customs declaration data to be verified, the customs declaration data to be verified including attribute information of the commodity to be verified and its corresponding customs declaration value; querying a preset data reference library according to the attribute information of the commodity to be verified, and obtaining a preset benchmark value corresponding to the commodity to be verified, wherein the preset data reference library is a database obtained by screening out abnormal data in historical customs declaration data; verifying the customs declaration value corresponding to the attribute information of the commodity to be verified based on the preset benchmark value corresponding to the commodity to be verified, and determining that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be verified; and clearing the abnormal data to obtain target customs declaration data.

[0006] An embodiment of the present application provides an electronic device, comprising: one or more processors; a memory, on which one or more programs are stored. When the one or more programs are executed by one or more processors, the one or more processors implement any one of the data verification methods in the embodiments of the present application.

[0007] An embodiment of the present application provides a readable storage medium, which stores a computer program. When the computer program is executed by a processor, any one of the data verification methods in the embodiments of the present application is implemented.

[0008] According to the data verification method, electronic device and storage medium of the embodiment of the present application, by acquiring the customs declaration data to be verified, the attribute information of the commodity to be verified and its corresponding customs declaration value are clarified; according to the attribute information of the commodity to be verified, the preset data reference library is queried to obtain the preset reference value corresponding to the commodity to be verified, wherein the preset data reference library is a database obtained by screening out abnormal data in the historical customs declaration data, which can ensure the accuracy of the verification of the customs declaration data; according to the preset reference value corresponding to the commodity to be verified, the customs declaration value corresponding to the attribute information of the commodity to be verified is verified, and it is determined that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be verified, and the customs declaration data can be checked to reduce the possibility of abnormal data in the customs declaration data. When it is determined that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be verified, the target customs declaration data is obtained by clearing the abnormal data, so that the target customs declaration data can accurately reflect the data that needs to be declared, improve the quality of the customs declaration data, reduce the transmission time of physical goods, and reduce the transportation cost of the enterprise.

[0009] With regard to the above embodiments and other aspects of the present application and their implementation, further description is provided in the accompanying drawings, detailed description and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a data verification method provided in an embodiment of the present application is shown.

[0011] Figure 2 A schematic diagram showing a flow chart of a method for obtaining a preset data reference library provided in an embodiment of the present application.

[0012] Figure 3 A schematic diagram showing the manner of numerical ratios provided in an embodiment of the present application.

[0013] Figure 4 A schematic diagram showing data aggregation to form value clusters provided by an embodiment of the present application.

[0014] Figure 5 A block diagram showing the composition of a data verification device provided in an embodiment of the present application is shown.

[0015] Figure 6 A block diagram showing the composition of a data verification system provided in an embodiment of the present application is shown.

[0016] Figure 7 A schematic diagram showing updating of a preset data reference library provided in an embodiment of the present application is shown.

[0017] Figure 8 A structural diagram showing an exemplary hardware architecture of a computing device capable of implementing the data verification method and apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] The specific embodiments of the present application are described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present application and are not intended to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of the specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0020] Figure 1 The flowchart of the data verification method provided by the embodiment of the present application is shown. The data verification method can be applied to a data verification device. Figure 1 As shown, the data verification method in the embodiment of the present application includes but is not limited to the following steps.

[0021] Step S101, obtaining customs declaration data to be verified and estimated.

[0022] The declaration data to be inspected and assessed includes the attribute information of the goods to be inspected and assessed and their corresponding declaration values.

[0023] Step S102: querying a preset data reference library according to the attribute information of the commodity to be evaluated, and obtaining a preset reference value corresponding to the commodity to be evaluated.

[0024] Among them, the preset data reference library is a database obtained by screening out abnormal data in historical customs declaration data.

[0025] Step S103 , based on the preset reference value corresponding to the commodity to be evaluated, the customs declaration value corresponding to the attribute information of the commodity to be evaluated is evaluated, and it is determined that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be evaluated.

[0026] Step S104, clearing abnormal data and obtaining target customs declaration data.

[0027] In this embodiment, by acquiring the customs declaration data to be verified and evaluated, the attribute information of the commodity to be verified and evaluated and its corresponding customs declaration value are clarified; according to the attribute information of the commodity to be verified and evaluated, the preset data reference library is queried to obtain the preset reference value corresponding to the commodity to be verified and evaluated, wherein the preset data reference library is a database obtained by screening out abnormal data in the historical customs declaration data, which can ensure the accuracy of the verification of the customs declaration data; according to the preset reference value corresponding to the commodity to be verified and evaluated, the customs declaration value corresponding to the attribute information of the commodity to be verified and evaluated is verified and evaluated, and it is determined that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be verified and evaluated, and the customs declaration data can be checked to reduce the possibility of abnormal data in the customs declaration data. When it is determined that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be verified and evaluated, the target customs declaration data is obtained by clearing the abnormal data, so that the target customs declaration data can accurately reflect the data that needs to be declared, thereby improving the quality of the customs declaration data, reducing the transmission time of the physical goods, and reducing the transportation cost of the enterprise.

[0028] In some exemplary embodiments, the attribute information of the commodity to be evaluated includes the name of the commodity to be evaluated and the specification information of the commodity to be evaluated, and the declared value corresponding to the attribute information of the commodity to be evaluated includes at least one of the price of the commodity to be evaluated, the declared weight of the commodity to be evaluated and the specification value of the commodity to be evaluated; the preset reference value corresponding to the commodity to be evaluated includes at least one of a preset price threshold, a preset weight threshold and a preset specification threshold.

[0029] It should be noted that, through the name of the commodity to be evaluated, it can be clearly seen that the declaration value corresponding to the attribute information of the commodity to be evaluated includes the price of the commodity to be evaluated, the declaration weight of the commodity to be evaluated, etc. It is necessary to further verify each declaration value to ensure whether there is any abnormal data in the declaration value.

[0030] In step S103, based on the preset reference value corresponding to the commodity to be evaluated, the declared value corresponding to the attribute information of the commodity to be evaluated is evaluated, and it is determined that there is abnormal data in the declared value corresponding to the attribute information of the commodity to be evaluated. This can be achieved in the following manner: when it is determined that any one or more of the following conditions are met, it is determined that there is abnormal data in the declared value corresponding to the attribute information of the commodity to be evaluated: the price of the commodity to be evaluated is not within the range of the preset price threshold; the declared weight of the commodity to be evaluated is not within the range of the preset weight threshold; the specification value of the commodity to be evaluated is not within the range of the preset specification threshold.

[0031] Among them, the specification value of the commodity to be evaluated refers to the physical shape of the commodity to be evaluated. For example, the specification of the commodity to be evaluated includes any one of the volume, length and area of ​​the commodity to be evaluated. Correspondingly, the specification value of the commodity to be evaluated may include: any one of the volume value, length value and area value of the commodity to be evaluated.

[0032] The above specification values ​​of the goods to be inspected and evaluated are only examples, and corresponding settings can be made according to actual needs. Other specification values ​​of the goods to be inspected and evaluated that are not described are also within the protection scope of this application and will not be repeated here.

[0033] It should be noted that the range of the preset price threshold is a numerical floating range centered on the preset price threshold. For example, if the preset price threshold is 25 yuan, the range of the preset price threshold can be within the range of 23 to 27 yuan. Similarly, the range of the preset weight threshold is a numerical floating range centered on the preset weight threshold; the range of the preset specification threshold is a numerical floating range centered on the preset specification threshold. For example, if the preset weight threshold is set to 10 grams, the range of the preset weight threshold can be within the range of 8 to 12 grams.

[0034] By evaluating the price, weight and specification values ​​of the goods to be evaluated in different ranges, the goods to be evaluated can be comprehensively verified, so as to quickly and accurately determine whether there are abnormal data in the customs declaration values ​​corresponding to the attribute information of the goods to be evaluated, as well as the location corresponding to the abnormal data; further, the abnormal data is processed to reduce the proportion of abnormal data in the customs declaration values ​​corresponding to the attribute information of the goods to be evaluated, thereby improving the accuracy of the data.

[0035] In some exemplary embodiments, after executing step S104 to clear abnormal data and obtain target customs declaration data, the method further includes: updating a preset data reference library based on the acquired actual verification data at preset time intervals.

[0036] The actual verification data includes: actual customs declaration data and / or actual inspection data. The actual customs declaration data and / or actual inspection data may be data that has been manually corrected, or data obtained in real time by the customs declaration system.

[0037] It should be noted that the actual customs declaration data and the actual inspection data correspond to different weight values. According to different weight values, the actual customs declaration data and the actual inspection data can be merged with the historical customs declaration data, and then the data stored in the preset data reference library can be updated based on the merged customs declaration data.

[0038] For example, the smaller the difference between the time when the actual customs declaration data is obtained and the current time, the higher the weight value corresponding to the actual customs declaration data; similarly, the smaller the difference between the time when the actual inspection data is obtained and the current time, the higher the weight value corresponding to the actual inspection data.

[0039] The actual customs declaration data and the actual inspection data are processed separately by using different weight values ​​at each preset time interval (for example, a unit time of one week or one day) to reflect the update degree of the actual customs declaration data and the actual inspection data; and the data stored in the preset data reference library is updated based on the merged customs declaration data to make the updated preset data reference library more accurate.

[0040] In some exemplary embodiments, before executing step S102 of querying a preset data reference library according to the attribute information of the commodity to be evaluated to obtain a preset benchmark value corresponding to the commodity to be evaluated, the method further includes: constructing a preset data reference library.

[0041] Figure 2 A schematic diagram of a process for constructing a preset data reference library provided in an embodiment of the present application is shown. Figure 2 As shown, the method for constructing the preset data reference library includes but is not limited to the following steps:

[0042] Step S201, classifying the acquired historical customs declaration data based on the declaration elements of the sample commodities and the attribute information of the sample commodities to obtain sample data.

[0043] The sample data includes the commodity categories to which the multiple sample commodities belong, as well as the attribute information of each category of sample commodities and their corresponding customs declaration values.

[0044] In some exemplary embodiments, the declaration elements of the sample commodity include: at least one of: the commodity category to which the sample commodity belongs, attribute information of the sample commodity, the customs declaration value corresponding to the attribute information of the sample commodity, and origin information of the sample commodity.

[0045] Among them, the attribute information of the sample commodity includes the name of the sample commodity and / or the specifications of the sample commodity (for example, the specifications of the sample commodity include any one of the volume, length and area of ​​the sample commodity); the declaration value corresponding to the attribute information of the sample commodity includes the price of the sample commodity (for example, the unit price of the sample commodity, etc.) and / or the commodity weight information of the sample commodity (for example, the total weight of the sample commodity and / or the single weight of the sample commodity, etc.).

[0046] By using the customs declaration values ​​corresponding to attribute information such as the price of sample goods and the weight of sample goods, it is possible to obtain numerical statistics of different dimensions for sample goods of different categories to enrich the sample data.

[0047] Step S202, respectively determine the preset distribution range of the customs declaration value corresponding to the attribute information of each type of sample commodity.

[0048] Among them, the sample goods of a commodity category correspond to a preset distribution range, and each preset distribution range is a range determined based on the commodity category to which the sample goods belong and the distribution of the customs declaration value corresponding to the attribute information of the sample goods.

[0049] By determining the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each category of sample goods, the reasonable distribution of the customs declaration values ​​corresponding to the attribute information of each category of sample goods can be obtained, which facilitates the subsequent analysis of customs declaration values ​​of different categories and improves data analysis efficiency.

[0050] Step S203, based on the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each type of sample goods, the customs declaration values ​​corresponding to the attribute information of each type of sample goods are screened respectively to obtain abnormal values ​​corresponding to each type of sample goods.

[0051] For example, for Class A sample commodities, the customs declaration values ​​corresponding to the attribute information of multiple sample commodities belonging to Class A can be screened based on the preset distribution range A1 of the customs declaration values ​​corresponding to the attribute information of the Class A sample commodities, to determine whether there are abnormal values ​​among the customs declaration values ​​corresponding to the attribute information of the multiple sample commodities belonging to Class A, and when it is determined that there are abnormal values ​​among the customs declaration values ​​corresponding to the attribute information of the multiple sample commodities belonging to Class A, the abnormal values ​​corresponding to the Class A sample commodities are obtained.

[0052] Among them, the abnormal value corresponding to the Class A sample product is a value that is not within the preset distribution range of the customs declaration value corresponding to the attribute information of the Class A sample product.

[0053] The above processing method for Class A sample goods is only an example. The processing method for the customs declaration values ​​corresponding to the attribute information of sample goods of other different commodity categories is the same as that for Class A sample goods, which will not be repeated here.

[0054] Step S204, based on the commodity categories to which the multiple sample commodities belong, respectively remove the abnormal values ​​corresponding to each category of sample commodities from the historical customs declaration data to obtain a preset data reference library.

[0055] For example, assume that there are N different commodity categories, where N is an integer greater than or equal to 1. It is necessary to remove abnormal values ​​corresponding to sample commodities in N commodity categories from the historical customs declaration data, so as to obtain a preset data reference library, so that the data in the preset data reference library are all data that meet the preset distribution range of customs declaration values ​​corresponding to the attribute information of each commodity category, thereby improving the accuracy of the data and facilitating the subsequent use of the preset data reference library to match the attribute information of the commodity to be evaluated, thereby speeding up the processing speed of the commodity to be evaluated.

[0056] In some exemplary embodiments, the step S202 of determining the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each category of sample commodities can be implemented in the following manner: for each category of sample commodities, the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each category of sample commodities is determined based on the numerical ratio.

[0057] Among them, the numerical ratio method is a method of selecting the difference between the value farthest from the average value and the average value from multiple preset values, and screening the multiple preset values ​​based on the ratio of the difference to the average value, wherein the average value is the mean of the multiple preset values; or, the numerical ratio method is a method of screening to obtain the maximum and minimum values ​​from multiple preset values, and screening the multiple preset values ​​based on the ratio of the average of the maximum and minimum values ​​to the average of the multiple preset values.

[0058] Figure 3 A schematic diagram showing the numerical ratio provided in the embodiment of the present application. Figure 3 In, mid=(max+min) / 2; half=(max-min) / 2.

[0059] Among them, max represents the maximum value among multiple preset values; min represents the minimum value among multiple preset values; mid represents the average of the sum of the maximum value and the minimum value; half represents the average of the difference between the maximum value and the minimum value; mean represents the average of multiple preset values; A represents the value of mean.

[0060] exist Figure 3 In (1), B = |mean-mid| + half; percent = B / A.

[0061] exist Figure 3 In (2), B = |mid-mean| + half; percent = B / A.

[0062] Among them, B represents the difference between the value farthest from the average value selected from multiple preset values ​​and the average value, or represents the average value of the maximum value and the minimum value obtained by screening from multiple preset values; percent represents the ratio between the values ​​B and A.

[0063] Through the above-mentioned different numerical ratio calculation methods, the dispersion degree of the customs declaration values ​​corresponding to the attribute information of the same category of goods can be calculated, so as to determine which customs declaration values ​​are within the preset distribution range and which customs declaration values ​​are outside the preset distribution range (i.e., abnormal values) based on the dispersion degree. The preset distribution range is the range after the abnormal values ​​are removed. In other words, the values ​​within the preset distribution range are the values ​​that meet the verification requirements.

[0064] In some exemplary embodiments, before executing step S203, the customs declaration values ​​corresponding to the attribute information of each category of sample commodities are screened according to the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each category of sample commodities, and before obtaining the abnormal values ​​corresponding to each category of sample commodities, the method further includes: for each category of sample commodities, when it is determined that the customs declaration values ​​corresponding to the attribute information of the sample commodities are not within the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample commodities, determining that the category of the sample commodities is an abnormal category.

[0065] In step S203, based on the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each category of sample commodities, the customs declaration values ​​corresponding to the attribute information of each category of sample commodities are screened respectively to obtain abnormal values ​​corresponding to each category of sample commodities. This can be achieved in the following way: based on the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category, the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category are screened to obtain abnormal values ​​corresponding to the sample commodities of the abnormal category.

[0066] By first determining the abnormal category and then analyzing the customs declaration values ​​corresponding to the attribute information of the sample goods of the abnormal category, if it is determined that the customs declaration values ​​corresponding to the attribute information of the sample goods of the abnormal category are not within the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample goods of the abnormal category, it can be known that the customs declaration values ​​corresponding to the attribute information of the sample goods of the abnormal category are abnormal values, thereby quickly screening out the abnormal values ​​corresponding to the sample goods of the abnormal category, accelerating the screening speed of the values, and improving the data processing efficiency.

[0067] In some exemplary embodiments, the preset distribution range is a numerical floating range centered on a preset reference value. Based on the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category, the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category are screened to obtain the abnormal values ​​corresponding to the sample commodities of the abnormal category, including:

[0068] Compare the preset benchmark value and the customs declaration value corresponding to the attribute information of the sample product to obtain a comparison result; determine based on the comparison result that the customs declaration value corresponding to the attribute information of the sample product is not within the preset distribution range of the customs declaration value corresponding to the attribute information of the sample product, and obtain the abnormal value corresponding to the sample product of the abnormal category.

[0069] The preset reference value is a value determined based on aggregating adjacent values ​​to form multiple value clusters and based on the ratio of the number of values ​​in the value clusters to the number of all customs declaration values ​​corresponding to the attribute information of the sample product.

[0070] For example, Figure 4 A schematic diagram showing data aggregation to form a value cluster provided by an embodiment of the present application is shown. Figure 4 As shown, there are multiple declaration values ​​between the values ​​3.0 and 3.2, and these declaration values ​​are all close to each other, and can form a first value cluster (Value Cluster).

[0071] However, at the values ​​62.4 and 374.8, there are only two relatively independent isolated points. In other words, a second value cluster and a third value cluster with a single value can be formed.

[0072] However, for all customs declaration values ​​corresponding to the attribute information of a certain type of sample goods, the first ratio can be determined based on the ratio between the number of values ​​in the first value cluster and the number of all customs declaration values ​​corresponding to the attribute information of this type of sample goods; similarly, the second ratio can be determined based on the ratio between the number of values ​​in the second value cluster and the number of all customs declaration values ​​corresponding to the attribute information of this type of sample goods; and the third ratio can be determined based on the ratio between the number of values ​​in the third value cluster and the number of all customs declaration values ​​corresponding to the attribute information of this type of sample goods.

[0073] Among them, since the first ratio is obviously larger than the second ratio, and the first ratio is also obviously larger than the third ratio, the preset benchmark value can be determined based on the first value cluster formed between 3.0 and 3.2, so that the preset benchmark value can better reflect the degree of change of all customs declaration values ​​corresponding to the attribute information of this type of sample goods.

[0074] Furthermore, by comparing the preset reference value and the customs declaration value corresponding to the attribute information of the sample commodity, it is determined whether the customs declaration value corresponding to the attribute information of the sample commodity is within the preset distribution range of the customs declaration value corresponding to the attribute information of the sample commodity. When the customs declaration value corresponding to the attribute information of the sample commodity is not within the preset distribution range of the customs declaration value corresponding to the attribute information of the sample commodity, it can be determined that the category of the sample commodity is an abnormal category. By first distinguishing the categories of commodities, and then processing the customs declaration values ​​corresponding to the attribute information of commodities determined to be abnormal categories, the processing speed of abnormal values ​​is accelerated.

[0075] Figure 5 FIG. 2 shows a block diagram of the data verification device provided in an embodiment of the present application. Figure 5 As shown, the data verification device 500 includes but is not limited to the following modules.

[0076] The acquisition module 501 is configured to acquire the customs declaration data to be verified and estimated, and the customs declaration data to be verified and estimated includes the attribute information of the commodity to be verified and estimated and its corresponding customs declaration value.

[0077] The query module 502 is configured to query a preset data reference library according to the attribute information of the commodity to be evaluated, and obtain a preset reference value corresponding to the commodity to be evaluated, wherein the preset data reference library is a database obtained by screening out abnormal data in historical customs declaration data.

[0078] The verification module 503 is configured to verify the customs declaration values ​​corresponding to the attribute information of the commodity to be verified based on the preset reference value corresponding to the commodity to be verified, and determine whether there is abnormal data in the customs declaration values ​​corresponding to the attribute information of the commodity to be verified.

[0079] The clearing module 504 is configured to clear abnormal data and obtain target customs declaration data.

[0080] It should be noted that the data verification device 500 in this embodiment can implement any data verification method in the embodiments of the present application.

[0081] According to the data verification device of the embodiment of the present application, the customs declaration data to be verified is obtained through the acquisition module, and the attribute information of the commodity to be verified and its corresponding customs declaration value are clarified; the query module is used to query the preset data reference library according to the attribute information of the commodity to be verified, and the preset benchmark value corresponding to the commodity to be verified is obtained, wherein the preset data reference library is a database obtained by screening out abnormal data in the historical customs declaration data, which can ensure the accuracy of the verification of the customs declaration data; the verification module is used to verify the customs declaration value corresponding to the attribute information of the commodity to be verified based on the preset benchmark value corresponding to the commodity to be verified, and it is determined that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be verified, and the customs declaration data can be checked to reduce the possibility of abnormal data in the customs declaration data. When it is determined that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be verified, the abnormal data is cleared by the clearing module to obtain the target customs declaration data, so that the target customs declaration data can accurately reflect the data that needs to be declared, improve the quality of the customs declaration data, reduce the transmission time of physical goods, and reduce the transportation cost of the enterprise.

[0082] Figure 6 FIG. 1 is a block diagram showing the composition of the data verification system provided by the embodiment of the present application. Figure 6 As shown, the data verification system 610 is in communication connection with the customs declaration system 620. The data verification system 610 includes but is not limited to the following devices: a preset data reference library 611, a training module 612 and an interface module 613.

[0083] The customs declaration system 620 is used to construct a pre-verification customs declaration form, which includes the customs declaration data to be verified, and can encapsulate the customs declaration data to be verified into a pre-verification request, and send the pre-verification request to the data verification system 610. The customs declaration system 620 can also be used to verify the customs declaration data to be verified when receiving the pre-verification response, and perform the subsequent customs declaration process.

[0084] The data verification system 610 is used to verify the customs declaration data to be verified included in the pre-verification request to determine whether there is any abnormal data in the customs declaration data to be verified, and to feed back a pre-verification response to the customs declaration system 620 so that the customs declaration system 620 knows whether there is any abnormal data in the customs declaration data to be verified.

[0085] It should be noted that the data verification system 610 in this embodiment can implement any data verification method in the embodiments of the present application.

[0086] When the interface module 613 receives the pre-verification request sent by the customs declaration system 620, the interface module 613 parses the pre-verification request to obtain the customs declaration data to be verified (for example, the customs declaration data to be verified includes the attribute information of the goods to be verified and its corresponding customs declaration value, etc.), and then sends the customs declaration data to be verified to the preset data reference library 611 by querying the data, so that the preset data reference library 611 can query the customs declaration data to be verified to obtain the preset reference value corresponding to the goods to be verified.

[0087] The preset data reference library 611 is used to receive the query data request sent by the interface module 613, obtain the preset reference value corresponding to the product to be evaluated; and send a response of return data to the interface module 613 so that the interface module 613 can know the preset reference value corresponding to the product to be evaluated.

[0088] The interface module 613 is also used to receive a response to the return data sent by the preset data reference library 611, and obtain the preset reference value corresponding to the commodity to be inspected and evaluated; compare the customs declaration value corresponding to the attribute information of the commodity to be inspected and evaluated, and the preset reference value corresponding to the commodity to be inspected and evaluated, and determine whether there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be inspected and evaluated.

[0089] The training module 612 is used for model training, that is, obtaining the data stored in the preset data reference library by processing the sample data, and saving the data in the preset data reference library 611.

[0090] For example, the training module 612 classifies the acquired historical customs declaration data based on the declaration elements of the sample commodities and the attribute information of the sample commodities to obtain sample data, which includes the commodity categories to which the multiple sample commodities belong, and the attribute information of each category of sample commodities and its corresponding customs declaration values; respectively determines the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each category of sample commodities; based on the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each category of sample commodities, respectively screens the customs declaration values ​​corresponding to the attribute information of each category of sample commodities to obtain abnormal values ​​corresponding to each category of sample commodities; based on the commodity categories to which the multiple sample commodities belong, respectively eliminates the abnormal values ​​corresponding to each category of sample commodities from the historical customs declaration data to obtain the data in the preset data reference library 611, and saves the data in the preset data reference library 611.

[0091] In some optional embodiments, the training module 612 is further configured to perform the following operations:

[0092] Firstly, the acquired historical customs declaration data is classified based on the declaration elements and attribute information of the sample commodities to obtain sample data.

[0093] The sample data includes the commodity categories to which the multiple sample commodities belong, and the attribute information of each category of the sample commodities and their corresponding customs declaration values. For example, the historical customs declaration data may be preliminarily processed by removing null values ​​and / or negative values ​​in the historical customs declaration data.

[0094] The attribute information of each type of sample commodity includes at least one of the name of the sample commodity, the product model of the sample commodity, and the specifications of the sample commodity (for example, at least one of the volume, length, and shape of the sample commodity); the declaration value corresponding to the attribute information of the sample commodity includes the price of the sample commodity and / or the product weight information of the sample commodity (for example, the total weight of the sample commodity, the single weight of the sample commodity, etc.).

[0095] It should be noted that for sample products of the same category, they have different product models and specifications, and the unit price and single weight of each sample product are also different. The sample data of different categories can be obtained by conducting a comprehensive analysis of the sample product name, product model, and specification information. This can reduce the proportion of sample products with different prices being classified into one category for comparative analysis and reduce classification errors of sample products.

[0096] Secondly, for each type of sample goods, a preset distribution range of the customs declaration value corresponding to the attribute information of each type of sample goods is determined based on the value ratio.

[0097] Among them, the numerical ratio method is a method of selecting the difference between the value farthest from the average value and the average value from multiple preset values, and screening the multiple preset values ​​based on the ratio of the difference to the average value, wherein the average value is the mean of the multiple preset values; or, the numerical ratio method is a method of screening to obtain the maximum and minimum values ​​from multiple preset values, and screening the multiple preset values ​​based on the ratio of the average of the maximum and minimum values ​​to the average of the multiple preset values.

[0098] By processing the customs declaration values ​​in the above-mentioned numerical ratio method, it is possible to analyze the dispersion of the customs declaration values ​​corresponding to the attribute information of sample products of the same category, so as to identify which customs declaration values ​​are abnormal values. Figure 3 By using the numerical ratio method shown in the figure, it is determined which customs declaration values ​​are within the preset distribution range and which customs declaration values ​​are outside the preset distribution range (i.e., abnormal values). By using the numerical ratio method shown in the figure, if it is determined that the customs declaration value corresponding to the attribute information of the sample commodity is not within the preset distribution range of the customs declaration value corresponding to the attribute information of the sample commodity, then the category of the sample commodity can be determined to be an abnormal category.

[0099] In some exemplary embodiments, multiple value clusters are formed based on aggregating adjacent values, and a preset reference value is determined based on the ratio of the number of values ​​in the value cluster to the number of all customs declaration values ​​corresponding to the attribute information of the sample goods, and then a preset distribution range is determined with the preset reference value as the center.

[0100] Thirdly, according to the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category, the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category are screened to obtain the abnormal values ​​corresponding to the sample commodities of the abnormal category. For example, by comparing the preset reference value with the customs declaration value corresponding to the attribute information of the sample commodities, when the customs declaration value corresponding to the attribute information of the sample commodities of the abnormal category is not within the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category, the abnormal values ​​corresponding to the sample commodities of the abnormal category can be obtained.

[0101] For example, Figure 4 The diagram shown is a schematic diagram of data aggregation to form value clusters, wherein the first value cluster formed by values ​​between 3.0 and 3.2 occupies a proportional advantage among multiple value clusters, so that a preset benchmark value can be determined based on the first value cluster, so that the preset benchmark value can better reflect the degree of change of all customs declaration values ​​corresponding to the attribute information of this type of sample goods.

[0102] Furthermore, according to the commodity categories to which the multiple sample commodities belong, abnormal values ​​corresponding to each category of sample commodities are respectively removed from the historical customs declaration data to obtain data stored in the preset data reference library 611.

[0103] Figure 7 FIG. 1 is a schematic diagram showing an example of updating a preset data reference library provided by an embodiment of the present application. Figure 7 As shown, the customs declaration system 620 pushes batch data to the data verification system 610, so that the interface module 613 pre-processes the obtained batch data, and then sends the actual verification data after pre-processing to the training module 612; so that the training module 612 can update the model and update the data stored in the preset data reference library 611.

[0104] In some optional real-time methods, the method for updating the preset data reference library includes:

[0105] First, the customs declaration system 620 periodically (for example, with a period of one month or two weeks) pushes the actual verification data (for example, the actual verification data includes actual customs declaration data and / or actual inspection data) in the previous period to the data verification system 610. The actual customs declaration data and / or actual inspection data may be data that has been manually corrected, or may be actual data obtained by the customs declaration system 620.

[0106] Then, the data verification system 610 processes the obtained batch actual verification data through the receiving module 613, wherein the actual customs declaration data and the actual inspection data correspond to different weight values ​​respectively. According to the different weight values, the actual customs declaration data and the actual inspection data are merged with the historical customs declaration data respectively, and then the merged customs declaration data is sent to the training module 612 for the training module 612 to update the data.

[0107] It should be noted that the smaller the difference between the time when the actual customs declaration data is obtained and the current time, the higher the weight value corresponding to the actual customs declaration data; similarly, the smaller the difference between the time when the actual inspection data is obtained and the current time, the higher the weight value corresponding to the actual inspection data.

[0108] Furthermore, the preset data reference library 611 updates the data stored in the preset data reference library 611 according to the data fed back by the training module 612 to ensure the real-time performance of the data in the preset data reference library 611 .

[0109] According to the data verification system in the embodiment of the present application, the historical customs declaration data is classified, and the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each type of sample goods is determined by means of numerical ratios. When it is determined that the customs declaration values ​​corresponding to the attribute information of the sample goods are not within the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample goods, the category of the sample goods can be determined to be an abnormal category, thereby speeding up the processing of the sample goods; then, by comparing the preset benchmark value (which is based on aggregating adjacent values ​​to form multiple value clusters, and a value determined based on the ratio of the number of values ​​in the value clusters to the number of all customs declaration values ​​corresponding to the attribute information of the sample goods) and the customs declaration values ​​corresponding to the attribute information of the sample goods, a comparison result is obtained; based on the comparison result, it is determined that the customs declaration values ​​corresponding to the attribute information of the sample goods are not within the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample goods, and the abnormal values ​​corresponding to the sample goods of the abnormal category are obtained. By clearing the abnormal values ​​corresponding to the sample commodities of the abnormal category from the historical customs declaration data, the data stored in the preset data reference library is obtained, and then the customs declaration data to be evaluated is evaluated using the data stored in the preset data reference library. It is possible to quickly and accurately determine whether there is abnormal data in the customs declaration data to be evaluated, and when it is determined that the abnormal data is stored, the target customs declaration data is obtained by clearing the abnormal data, so that the target customs declaration data can accurately reflect the data that needs to be declared, thereby improving the quality of the customs declaration data, reducing the transmission time of physical goods, and reducing the transportation costs of enterprises.

[0110] It should be clear that the present application is not limited to the specific configurations and processes described in the above embodiments and shown in the figures. For the convenience and brevity of description, a detailed description of the known methods is omitted here, and the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, which will not be repeated here.

[0111] Figure 8 A structural diagram showing an exemplary hardware architecture of a computing device capable of implementing the data verification method and apparatus according to an embodiment of the present application.

[0112] like Figure 8 As shown, the computing device 800 includes an input device 801, an input interface 802, a central processing unit 803, a memory 804, an output interface 805, and an output device 806. The input interface 802, the central processing unit 803, the memory 804, and the output interface 805 are connected to each other via a bus 807, and the input device 801 and the output device 806 are connected to the bus 807 via the input interface 802 and the output interface 805, respectively, and then connected to other components of the computing device 800.

[0113] Specifically, the input device 801 receives input information from the outside and transmits the input information to the central processing unit 803 through the input interface 802; the central processing unit 803 processes the input information based on the computer executable instructions stored in the memory 804 to generate output information, temporarily or permanently stores the output information in the memory 804, and then transmits the output information to the output device 806 through the output interface 805; the output device 806 outputs the output information to the outside of the computing device 800 for user use.

[0114] In one embodiment, Figure 8 The computing device shown may be implemented as an electronic device, which may include: a memory configured to store a program; and a processor configured to run the program stored in the memory to execute the data verification method described in the above embodiment.

[0115] In one embodiment, Figure 8 The computing device shown may be implemented as a data verification system, which may include: a memory configured to store a program; and a processor configured to run the program stored in the memory to execute the data verification method described in the above embodiment.

[0116] The above is only an exemplary embodiment of the present application and is not intended to limit the scope of protection of the present application. In general, various embodiments of the present application can be implemented in hardware or special circuits, software, logic or any combination thereof. For example, some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software that can be executed by a controller, a microprocessor or other computing device, although the present application is not limited thereto.

[0117] Embodiments of the present application may be implemented by a processor executing computer program instructions, such as in a processor entity, or by hardware, or by a combination of software and hardware. The computer program instructions may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages.

[0118] The block diagram of any logic flow in the accompanying drawings of the present application can represent program steps, or can represent interconnected logic circuits, modules and functions, or can represent a combination of program steps and logic circuits, modules and functions. The computer program can be stored on a memory. The memory can have any type suitable for the local technical environment and can be implemented using any suitable data storage technology, such as but not limited to read-only memory (ROM), random access memory (RAM), optical memory device and system (digital versatile disc DVD or CD disc), etc. Computer-readable media may include non-transient storage media. The processor can be any type suitable for the local technical environment, such as but not limited to a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (FGPA) and a processor based on a multi-core processor architecture.

[0119] By way of exemplary and non-limiting examples, a detailed description of exemplary embodiments of the present application has been provided above. However, various modifications and adjustments to the above embodiments will be apparent to those skilled in the art when considered in conjunction with the accompanying drawings and claims, but will not depart from the scope of the present application. Therefore, the proper scope of the present application will be determined according to the claims.

Claims

1. A data verification method, characterized in that: The method comprises: Obtaining customs declaration data to be verified and estimated, wherein the customs declaration data to be verified and estimated includes attribute information of the goods to be verified and estimated and the corresponding customs declaration values; According to the attribute information of the commodity to be evaluated, a preset data reference database is queried to obtain a preset reference value corresponding to the commodity to be evaluated, wherein the preset data reference database is a database obtained by screening out abnormal data in historical customs declaration data; According to a preset reference value corresponding to the commodity to be evaluated, the customs declaration value corresponding to the attribute information of the commodity to be evaluated is evaluated, and it is determined that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be evaluated; The abnormal data is cleared to obtain target customs declaration data.

2. The method according to claim 1, characterized in that Before querying a preset data reference library according to the attribute information of the commodity to be evaluated to obtain a preset reference value corresponding to the commodity to be evaluated, the method further includes: Classifying the acquired historical customs declaration data based on the declaration elements and attribute information of the sample commodities to obtain sample data, wherein the sample data includes commodity categories to which the multiple sample commodities belong, and attribute information of each category of sample commodities and its corresponding customs declaration value; Determining respectively the preset distribution range of the customs declaration value corresponding to the attribute information of each type of sample goods; According to the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each type of sample goods, the customs declaration values ​​corresponding to the attribute information of each type of sample goods are screened respectively to obtain abnormal values ​​corresponding to each type of sample goods; According to the commodity categories to which the multiple sample commodities belong, abnormal values ​​corresponding to each category of the sample commodities are respectively removed from the historical customs declaration data to obtain the preset data reference library.

3. The method according to claim 2, characterized in that The step of respectively determining the preset distribution range of the customs declaration value corresponding to the attribute information of each type of sample commodity includes: For each type of sample commodity, determine a preset distribution range of the customs declaration value corresponding to the attribute information of each type of sample commodity based on a value ratio; The numerical ratio method is a method of selecting a difference between a value farthest from an average value and the average value from a plurality of preset values, and screening the plurality of preset values ​​based on the ratio of the difference to the average value, wherein the average value is the mean of the plurality of preset values; Alternatively, the numerical ratio method is a method of filtering the maximum and minimum values ​​from the multiple preset values, and filtering the multiple preset values ​​based on the ratio of the average value of the maximum and the minimum value to the average value of the multiple preset values.

4. The method according to claim 2, characterized in that: The declaration elements of the sample commodity include: at least one of: the commodity category to which the sample commodity belongs, the attribute information of the sample commodity, the declaration value corresponding to the attribute information of the sample commodity, and the origin information of the sample commodity; Among them, the attribute information of the sample commodity includes the name of the sample commodity and / or the specifications of the sample commodity; the customs declaration value corresponding to the attribute information of the sample commodity includes the price of the sample commodity and / or the commodity weight information of the sample commodity.

5. The method according to claim 2, characterized in that: Before screening the customs declaration values ​​corresponding to the attribute information of each type of sample goods according to the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each type of sample goods and obtaining the abnormal values ​​corresponding to each type of sample goods, the method further includes: For each category of sample commodities, when it is determined that the customs declaration value corresponding to the attribute information of the sample commodities is not within a preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample commodities, determining that the category of the sample commodities is an abnormal category; The method of screening the customs declaration values ​​corresponding to the attribute information of each type of sample goods according to the preset distribution range of the customs declaration values ​​corresponding to the attribute information of each type of sample goods to obtain abnormal values ​​corresponding to each type of sample goods includes: According to the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category, the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category are screened to obtain the abnormal values ​​corresponding to the sample commodities of the abnormal category.

6. The method according to claim 5, characterized in that The preset distribution range is a numerical floating range centered on a preset reference value; The method of screening the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category according to the preset distribution range of the customs declaration values ​​corresponding to the attribute information of the sample commodities of the abnormal category to obtain the abnormal values ​​corresponding to the sample commodities of the abnormal category includes: Comparing the preset reference value with the customs declaration value corresponding to the attribute information of the sample commodity to obtain a comparison result, wherein the preset reference value is a value determined based on aggregating adjacent values ​​to form a plurality of value clusters and based on the ratio of the number of values ​​in the value cluster to the number of all customs declaration values ​​corresponding to the attribute information of the sample commodity; According to the comparison result, it is determined that the customs declaration value corresponding to the attribute information of the sample product is not within the preset distribution range of the customs declaration value corresponding to the attribute information of the sample product, and the abnormal value corresponding to the sample product of the abnormal category is obtained.

7. The method according to any one of claims 1 to 6, characterized in that The attribute information of the commodity to be evaluated includes the name of the commodity to be evaluated and the specification information of the commodity to be evaluated; the declaration value corresponding to the attribute information of the commodity to be evaluated includes at least one of the price of the commodity to be evaluated, the declaration weight of the commodity to be evaluated and the specification value of the commodity to be evaluated; the preset reference value corresponding to the commodity to be evaluated includes at least one of a preset price threshold, a preset weight threshold and a preset specification threshold; The step of evaluating the customs declaration value corresponding to the attribute information of the commodity to be evaluated based on the preset reference value corresponding to the commodity to be evaluated, and determining that abnormal data exists in the customs declaration value corresponding to the attribute information of the commodity to be evaluated, includes: When it is determined that any one or more of the following conditions are met, it is determined that there is abnormal data in the customs declaration value corresponding to the attribute information of the commodity to be evaluated: The price of the commodity to be evaluated is not within the range of the preset price threshold; The declared weight of the commodity to be assessed is not within the range of the preset weight threshold; The specification value of the commodity to be evaluated is not within the range of the preset specification threshold.

8. The method according to any one of claims 1 to 6, characterized in that After clearing the abnormal data and obtaining the target customs declaration data, the method further includes: At each preset time interval, the preset data reference library is updated according to the acquired actual verification data; The actual evaluation data includes: actual customs declaration data and / or actual inspection data, and the actual customs declaration data and the actual inspection data correspond to different weight values ​​respectively.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the data verification method according to any one of claims 1 to 8.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the data verification method according to any one of claims 1 to 8 is implemented.