Tax compliance intelligent inspection method and platform

Abstract

The invention provides a tax compliance intelligent inspection method and platform, and relates to an image processing technology, and the method comprises the steps: obtaining an electronic layout sequence corresponding to electronic data based on a document recognition model, determining a customized capping region of each document page in the electronic data according to the electronic layout sequence, obtaining the capping range of each customized capping region, and determining the customized capping region of each document page in the electronic data; the method comprises the steps of obtaining a capping range of each document page, determining a capping identification type according to the capping range, cutting an anti-counterfeiting identification based on the capping identification type and the capping range to obtain sub-anti-counterfeiting identification of each document page, updating the electronic data based on the sub-anti-counterfeiting identification to obtain archived data, and storing the archived data in the corresponding document page. And in response to compliance verification information of the management end, verifying the current anti-counterfeiting mark corresponding to the current archived data based on the mark verification model to obtain compliance detection data, and sending the compliance detection data to the management end. According to the method, the risk that the electronic perforation seal is forged or tampered can be reduced, and the authenticity and integrity of electronic data are ensured.

Description

Technical Field

[0001] The present invention relates to image processing technology, and in particular to a tax compliance intelligent inspection method and platform. Background Art

[0002] In tax compliance inspections, the authenticity and integrity of electronic data are crucial. As an advanced anti-counterfeiting technology, electronic saddle stamps are widely used on multi-page documents or contracts to ensure the integrity and authenticity of electronic files or contracts.

[0003] In the prior art, electronic interleaving seals on electronic data often have the risk of being forged or tampered with. One important reason for this is that the spacing between interleaving seals may be too uniform and standardized. If the spacing between electronic interleaving seals is fixed or highly standardized, then it may be easier for a counterfeiter to imitate this spacing through technical means such as image processing software, thereby making fake electronic interleaving seals, which may in turn lead to the replacement of electronic data.

[0004] Therefore, how to reduce the risk of electronic saddle stamps being forged or tampered with and ensure the authenticity and integrity of electronic data has become an urgent problem that needs to be solved. Summary of the invention

[0005] The present invention provides a tax compliance intelligent inspection method and platform, which can reduce the risk of electronic interline seals being forged or tampered with, and ensure the authenticity and integrity of electronic data.

[0006] A first aspect of the present invention provides a tax compliance intelligent inspection method, comprising: Acquire an electronic layout sequence corresponding to the electronic data based on the document recognition model, and determine a customized cover area of ​​each document page in the electronic data according to the electronic layout sequence; Acquire the stamping range of each customized stamping area, and determine the stamping mark type according to the stamping range, wherein the stamping mark type includes a single mark type and a multiple mark type; Cutting the anti-counterfeiting mark based on the stamping mark type and stamping range to obtain the sub-anti-counterfeiting mark of each document page, and updating the electronic data based on the sub-anti-counterfeiting mark to obtain archived data; In response to the compliance verification information of the management end, the current anti-counterfeiting mark corresponding to the current archived data is verified based on the mark verification model to obtain compliance detection data and send it to the management end.

[0007] Optionally, in a possible implementation of the first aspect, acquiring an electronic layout sequence corresponding to the electronic data based on a document recognition model, and determining a customized cover area of ​​each document page in the electronic data according to the electronic layout sequence includes: Determine the evaluation index of each document page corresponding to the electronic data according to the document recognition model, and arrange the document pages from large to small based on the evaluation index to obtain an electronic layout sequence; Acquire the first document page in the electronic layout sequence as a reference page, and calculate the index difference between the evaluation index of the reference page and the evaluation index of the remaining document pages; Determine a first capping distance corresponding to the reference page, offset the first capping distance according to the index difference, and obtain a second capping distance corresponding to the remaining document pages; Determine the capping edge of each of the document pages, and based on the capping edge, generate a customized edge parallel to the capping edge at the first capping distance or the second capping distance from the capping edge in the capping direction; A page area corresponding to the capping edge and the customized edge in the document page is determined as the customized capping area.

[0008] Optionally, in a possible implementation manner of the first aspect, determining the evaluation index of each document page corresponding to the electronic data according to the document recognition model includes: Performing text recognition on each of the document pages based on the document recognition model to determine keywords corresponding to each of the document pages; When the keyword is a seal indicator word, the center point of the seal indicator word is determined as the center of the circle, a traversal range is determined according to a preset radius, and the document seal within the traversal range is identified; The first importance index corresponding to each of the keywords and the second importance index of the document seal are determined, and the first importance index and the second importance index corresponding to the document page are added together to obtain an evaluation index.

[0009] Optionally, in a possible implementation manner of the first aspect, determining a first capping distance corresponding to the reference page, offsetting the first capping distance according to the index difference, and obtaining second capping distances corresponding to the remaining document pages includes: Counting the index mean of each evaluation index, and determining the optimal capping range corresponding to the index mean as the first capping distance corresponding to the reference page; Obtaining a shift coefficient according to a ratio of the index difference value to the reference index difference value, and obtaining distance shift values ​​of the remaining document pages based on a product of the shift coefficient and the reference shift value; Based on the difference between the first capping distance and the distance offset value, second capping distances corresponding to the remaining document pages are determined.

[0010] Optionally, in a possible implementation of the first aspect, the stamping range of each customized stamping area is obtained, and the stamping mark type is determined according to the stamping range, and the stamping mark type includes a single mark type and a multiple mark type, including: Determine the document page number of each of the document pages, and arrange the document pages in an arrangement direction from small to large according to the document page number to obtain a stamped document sequence; Acquire the capping distance of each document page in the capping document sequence in the arrangement direction, the capping range includes the capping distance, and sum up each capping distance to obtain a total capping distance corresponding to the capping document sequence; Determine the diameter of the anti-counterfeiting mark, the anti-counterfeiting mark is a circular mark, and obtain the number of marks according to the rounded-up value of the ratio of the total capping distance to the mark diameter; When the number of the logos is equal to a preset odd number, the stamped logo type is determined to be a single logo type; when the number of the logos is greater than the preset odd number, the stamped logo type is determined to be a multiple logo type.

[0011] Optionally, in a possible implementation of the first aspect, the anti-counterfeiting mark is cut based on the stamping mark type and stamping range to obtain a sub-anti-counterfeiting mark of each document page, and the electronic data is updated based on the sub-anti-counterfeiting mark to obtain archived data, including: When the stamped mark type is a single mark type, sequentially obtaining stamped distances of each document page in the stamped document sequence as cutting distances, cutting the anti-counterfeiting mark according to the cutting distances, and obtaining sub-anti-counterfeiting marks corresponding to each document page; When the stamped mark type is a multiple mark type, the anti-counterfeiting mark is copied according to the number of marks to obtain an anti-counterfeiting mark group, and the anti-counterfeiting mark group is cut according to the cutting distance to obtain a sub-anti-counterfeiting mark corresponding to each of the document pages; Determine the edge of the region in the customized capping area that is perpendicular to the arrangement direction as the first target edge, and determine the cutting edge of each of the sub-anti-counterfeiting marks as the second target edge; After the anti-counterfeiting mark is cut, the sub-anti-counterfeiting mark on the left is taken as the starting mark, the sub-anti-counterfeiting mark in the middle is taken as the middle mark, and the sub-anti-counterfeiting mark on the right is taken as the ending mark; The second target edge of the starting mark is connected with the first target edge on the right side of the customized cover area, the second target edges on both sides of the middle mark are connected with the first target edges on both sides of the customized cover area, and the second target edge of the ending mark is connected with the first target edge on the left side of the customized cover area to obtain archived data.

[0012] Optionally, in a possible implementation manner of the first aspect, when the stamped mark type is a single mark type, sequentially obtaining stamped distances of each document page in the stamped document sequence as cutting distances, cutting the anti-counterfeiting mark according to the cutting distances, and obtaining sub-anti-counterfeiting marks corresponding to each document page, including: According to the arrangement direction, a plurality of first cutting lines with a spacing of the cutting distance are sequentially generated on the anti-counterfeiting mark, wherein the first cutting lines are perpendicular to the arrangement direction; Cutting the anti-counterfeiting mark based on the first cutting line to obtain a plurality of sub-anti-counterfeiting marks, and arranging the sub-anti-counterfeiting marks based on the arrangement direction to obtain a mark sequence; The document pages and the sub-anti-counterfeiting marks that are arranged in the same position in the stamped document sequence and the mark sequence are matched to obtain the sub-anti-counterfeiting marks corresponding to each of the document pages.

[0013] Optionally, in a possible implementation of the first aspect, when the stamped mark type is a multiple mark type, the anti-counterfeiting mark is copied according to the number of marks to obtain an anti-counterfeiting mark group, and the anti-counterfeiting mark group is cut according to the cutting distance to obtain a sub-anti-counterfeiting mark corresponding to each of the document pages, including: Generate an arrangement reference line parallel to the arrangement direction, locate the center point of each anti-counterfeiting mark based on the arrangement reference line, arrange each anti-counterfeiting mark side by side to obtain an anti-counterfeiting mark group, and the interval distance between the center points of adjacent anti-counterfeiting marks is the distance corresponding to the mark diameter; Obtaining a total mark distance covered by the anti-counterfeiting mark group on the arrangement reference line, and when the total mark distance is greater than the total covering distance corresponding to each of the document pages, rotating the anti-counterfeiting mark group according to a preset rotation direction; Acquire in real time the real-time total distance of the anti-counterfeiting mark group in the arrangement direction during the rotation process, and stop the rotation of the anti-counterfeiting mark group when the real-time total distance is less than the total capping distance; According to the arrangement direction, a plurality of second cutting lines with a spacing of the cutting distance are sequentially generated on the anti-counterfeiting mark group, wherein the second cutting lines are perpendicular to the arrangement reference line; Cutting the anti-counterfeiting mark group based on the second cutting line to obtain a plurality of sub-anti-counterfeiting marks, and arranging the sub-anti-counterfeiting marks based on the arrangement direction to obtain a mark sequence; The document pages and the sub-anti-counterfeiting marks that are arranged in the same position in the stamped document sequence and the mark sequence are matched to obtain the sub-anti-counterfeiting marks corresponding to each of the document pages.

[0014] Optionally, in a possible implementation of the first aspect, in response to the compliance verification information of the management end, verifying the current anti-counterfeiting identification corresponding to the current archived data based on the identification verification model to obtain compliance detection data and sending it to the management end includes: Based on the identification verification model, multiple sub-archive identifications corresponding to the current archive data are retrieved from the database, and the sub-archive identifications are arranged in sequence according to the arrangement direction to obtain an archive identification sequence; Extracting a plurality of current anti-counterfeiting marks corresponding to the current archived data, and arranging the current anti-counterfeiting marks according to the arrangement direction to obtain a sequence to be verified; sequentially determining the sub-archiving identifiers in the archiving identifier sequence as compliance identifiers, and determining the current anti-counterfeiting identifier corresponding to the arrangement position of the compliance identifier in the to-be-verified sequence as the to-be-verified identifier; Determine the compliance mark and the mark to be verified as a verification group, and obtain a first coordinate position of the compliance mark and a second coordinate position of the mark to be verified; When the distance difference between the first coordinate position and the second coordinate position is less than a distance difference threshold, obtaining a first distance of the compliance mark in the arrangement direction and a second distance of the mark to be verified in the arrangement direction; When the difference between the first distance and the second distance is less than the identification stamping threshold, the verification group is determined to be a compliance group. When all verification groups are the compliance groups, the current archived data is determined to be compliance detection data and sent to the management end.

[0015] A second aspect of the present invention provides a tax compliance intelligent inspection platform, comprising: An acquisition module, used for acquiring an electronic layout sequence corresponding to the electronic data based on a document recognition model, and determining a customized cover area of ​​each document page in the electronic data according to the electronic layout sequence; A determination module, used for obtaining the stamping range of each customized stamping area, and determining the stamping mark type according to the stamping range, wherein the stamping mark type includes a single mark type and a multiple mark type; An updating module, configured to cut the anti-counterfeiting mark based on the stamping mark type and stamping range to obtain a sub-anti-counterfeiting mark of each document page, and update the electronic data based on the sub-anti-counterfeiting mark to obtain archived data; The verification module is used to respond to the compliance verification information of the management end, verify the current anti-counterfeiting mark corresponding to the current archived data based on the mark verification model, and obtain compliance detection data and send it to the management end.

[0016] The beneficial effects of the present invention are as follows: 1. When generating an electronic saddle seal, the present invention can customize the stamping range of the saddle seal on each page of the document in combination with the actual situation of the electronic document, thereby reducing the risk of the saddle seal being forged and the risk of the electronic document being replaced, and ensuring the authenticity and integrity of the electronic data. When generating a customized stamping area corresponding to each document page, the present invention can generate it accordingly in combination with the importance of each document page, ensuring that the stamping position of the saddle seal matches the importance of the document, thereby reducing the risk of the saddle seal being forged and improving the security of the electronic document.

[0017] 2. The present invention can determine the stamping mark type of the anti-counterfeiting mark according to the total stamping distance corresponding to all document pages, and generate a corresponding number of electronic saddle seals for the electronic document in combination with the corresponding stamping mark type, thereby ensuring that each document page can be stamped with an electronic saddle seal, reducing the risk of electronic documents being replaced and improving the security of electronic documents.

[0018] 3. The present invention can cut the anti-counterfeiting mark in different ways in combination with the stamping mark type and the stamping range to obtain the sub-anti-counterfeiting mark corresponding to each document page, which can ensure that the anti-counterfeiting mark on each document page accurately matches the corresponding stamping range, and can accurately connect the sub-anti-counterfeiting mark corresponding to each document page in the corresponding customized stamping area, thereby reducing the risk of electronic documents being replaced. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of a tax compliance intelligent inspection method provided by an embodiment of the present invention; Figure 2 is a schematic diagram of a first cutting line provided by an embodiment of the present invention; Figure 3 is a schematic diagram of a second cutting line provided by an embodiment of the present invention; Figure 4 is a schematic diagram of determining a second target edge provided by an embodiment of the present invention; Figure 5 It is a structural diagram of the tax compliance intelligent inspection platform provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] 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 only 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.

[0021] See also Figure 1 , is a schematic diagram of a tax compliance intelligent inspection method provided by an embodiment of the present invention, Figure 1 The execution subject of the method shown may be a software and / or hardware device. The execution subject of the present application may include but is not limited to at least one of the following: user equipment, network equipment, etc. Among them, user equipment may include but is not limited to computers, smart phones, personal digital assistants (PDA) and the electronic devices mentioned above. Network equipment may include but is not limited to a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers, wherein cloud computing is a type of distributed computing, a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. It includes steps S1 to S4, as follows: S1, acquiring an electronic layout sequence corresponding to the electronic data based on a document recognition model, and determining a customized cover area of ​​each document page in the electronic data according to the electronic layout sequence.

[0022] Among them, the document recognition model refers to a model that can determine the stamp-stamping area corresponding to each document page of an electronic document, electronic data refers to an electronic document, an electronic layout sequence refers to a sequence of multiple document pages arranged in combination with the importance of each page of the electronic document, a document page refers to each page of an electronic document, and a customized stamp-stamping area refers to the stamp-stamping area corresponding to each document page determined in combination with the importance of different document pages of the electronic document.

[0023] In actual applications, electronic data is increasingly used in tax inspections, and ensuring the authenticity and integrity of these electronic data has become a major challenge for tax compliance inspections. As an important anti-counterfeiting technology, electronic saddle stamps play a key role in ensuring the integrity and authenticity of electronic documents or contracts. When generating electronic saddle stamps, this solution can make personalized adjustments to the spacing between saddle stamps on each page of the document based on the actual situation of the electronic document, thereby reducing the risk of saddle stamps being forged and the risk of electronic documents being replaced, and ensuring the authenticity and integrity of electronic data.

[0024] It is understandable that since an electronic document may contain multiple document pages, the importance of each document page may be different. For example, the last page of an electronic document may contain an official seal, signature, etc. These elements are usually regarded as the core part of the document, so their importance is relatively high. In contrast, some pages in the middle may only contain background information, auxiliary data, etc., and their importance may be lower. In order to improve the security of electronic documents, when stamping the interline seal, the stamping area can be determined based on the importance of different pages, thereby reducing the risk of the interline seal being forged and improving the security of electronic documents.

[0025] Specifically, a document recognition model can be retrieved that can analyze the electronic document and determine the cover area of ​​each document page. The electronic document can be analyzed by the document recognition model, so that each document page can be sorted according to its importance to obtain an electronic layout sequence corresponding to the electronic document. In the electronic layout sequence, the importance of each document page is different. The cover area corresponding to each document page, that is, the customized cover area, can be determined according to the importance of different pages. The more important the document page, the larger the corresponding customized cover area may be.

[0026] In some embodiments, the specific implementation of step S1 may be: S11, determining the evaluation index of each document page corresponding to the electronic data according to the document recognition model, and arranging the document pages from large to small based on the evaluation index to obtain an electronic layout sequence.

[0027] The evaluation index refers to an index that can represent the importance of each document page. The more important the document page is, the larger the corresponding evaluation index is.

[0028] Specifically, a document recognition model can be called up to analyze the electronic data. The document recognition model can be pre-trained with a large number of electronic documents and can identify key information in electronic documents, such as official seal images, electronic signatures, etc. According to the key information corresponding to each document page identified, the evaluation index corresponding to each document page can be determined, and the corresponding document pages are arranged in order from large to small in terms of the evaluation index to obtain the corresponding electronic layout sequence. In the electronic layout sequence, the document page with a larger evaluation index is arranged closer to the front.

[0029] In some embodiments, the step S11 of “determining the evaluation index of each document page corresponding to the electronic data according to the document recognition model” includes the following steps: S111, performing text recognition on each of the document pages based on the document recognition model to determine keywords corresponding to each of the document pages.

[0030] Specifically, in an electronic document, the importance of each document page may be different, and the evaluation index corresponding to each document page is also different. When determining the evaluation index corresponding to the document page, the document recognition model can be used to first perform text recognition on each document page. If the document page contains keywords, such as signature, seal, etc., it can be considered that the document page contains more important content. By identifying the keywords corresponding to the document page, the evaluation index corresponding to each document page can be determined.

[0031] When performing text recognition on a document page, each document page may be scanned by a pre-trained document recognition model, and the document recognition model may extract corresponding keywords, where keywords refer to words that may represent key information of the document page.

[0032] S112, when the keyword is a seal indicator word, determining the center point of the seal indicator word as the center of the circle, determining a traversal range according to a preset radius, and identifying the document seal within the traversal range.

[0033] In actual applications, some tax-related document pages may need to be stamped, so the keywords recognized by the document recognition model may be words that indicate the stamping area, that is, stamp indicator words. When the keyword is a stamp indicator word, for example, when the keyword is stamping, since the seal is generally located near the seal indicator word, the center point of the seal indicator word can be determined as the center of the circle, and a circular area can be determined according to a pre-configured preset radius. The area can be determined as the traversal range for traversing the seal, and the document seal in the document page can be quickly extracted within the traversal range, which can improve efficiency.

[0034] Among them, the seal indicator word refers to a word that can indicate the seal area, the preset radius refers to a pre-configured radius that can be used to determine the range for seal recognition, the traversal range refers to the range for seal recognition, and the document seal refers to the seal in the document page.

[0035] S113, determining a first importance index corresponding to each of the keywords and a second importance index of the document seal, and adding the first importance index and the second importance index corresponding to the document page to obtain an evaluation index.

[0036] In actual applications, different keywords and different document seals have different corresponding importance in different documents. Corresponding importance indexes can be pre-configured for different keywords and different document seals. For example, some keywords closely related to taxation, such as "signature", "seal", "tax declaration", etc., because they usually represent key information in the document, they can be given a higher importance index. Similarly, some specific types of document seals, such as official seals, financial seals, etc., because they often have strong legal effect and proof function, they can also be given a higher importance index. Therefore, the importance index corresponding to the keywords of each document page can be determined, that is, the first importance index, and the importance index corresponding to the document seal of each document page can be determined, that is, the second importance index. By adding the first importance index and the second importance index corresponding to each document page, the evaluation index corresponding to each document page can be obtained.

[0037] Among them, the first importance index refers to the importance index corresponding to the keyword, and the second importance index refers to the importance index corresponding to the document seal.

[0038] Through the above implementation, key information and seals in the document can be automatically identified, thereby improving information recognition efficiency.

[0039] S12, obtaining the first document page in the electronic layout sequence as a reference page, and calculating the index difference between the evaluation index of the reference page and the evaluation indexes of the remaining document pages.

[0040] Among them, the reference page refers to the document page ranked first in the electronic layout sequence. The cover area range corresponding to this document page can be referred to to determine the cover area range of the remaining document pages. The index difference refers to the difference between the evaluation index of the reference page and the evaluation index of the remaining document pages.

[0041] In the electronic layout sequence, the document page arranged in the first position can be considered as the most important, and the range of the corresponding cover area is optimal and possibly the largest. This document page can be determined as a reference page, and the range of the cover area corresponding to each document page arranged after the reference page can be determined based on the difference between the evaluation index of the reference page and the evaluation index of each document page.

[0042] S13, determining a first capping distance corresponding to the reference page, offsetting the first capping distance according to the index difference, and obtaining second capping distances corresponding to the remaining document pages.

[0043] Specifically, since the interleaving seal is generally stamped on the edge area of ​​the document page, the distance to the stamped area corresponding to the reference page can be obtained according to the evaluation index corresponding to each document page in the electronic layout sequence, that is, the first stamped distance. According to the index difference between the evaluation index corresponding to the reference page and the evaluation index corresponding to the remaining document pages, the first stamped distance is offset to obtain the distance to the stamped area corresponding to the remaining document pages, that is, the second stamped distance.

[0044] The first capping distance refers to the capping distance corresponding to the capping area of ​​the reference page, and the second capping distance refers to the capping distance corresponding to the capping areas of the remaining document pages.

[0045] Based on the above embodiment, the specific implementation of step S13 may be: S131, counting the index mean values ​​of the evaluation indexes, and determining that the optimal capping range corresponding to the index mean value is the first capping distance corresponding to the reference page.

[0046] Specifically, when determining the first overlapping distance, a pre-configured distance correspondence table can be retrieved. In the distance correspondence table, there are multiple mean intervals, and each mean interval has a corresponding optimal overlapping range. The larger the evaluation index, the greater the importance of the corresponding document page, the larger the proportion of the interline seal in the corresponding document page, and the larger the corresponding optimal overlapping range. Therefore, after obtaining the evaluation index corresponding to each document page, the average of multiple evaluation indices can be calculated to obtain the corresponding index mean. By comparing the index mean with the distance correspondence table, the mean interval where the index mean is located can be determined, and the optimal overlapping range corresponding to the mean interval where the index mean is located can be determined. The optimal overlapping range can be determined as the first overlapping distance corresponding to the reference page.

[0047] The index mean refers to the average value of the evaluation indexes corresponding to each document page, and the optimal covering range refers to the range of the covering area corresponding to the index mean.

[0048] S132, obtaining a shift coefficient according to a ratio of the index difference value to the reference index difference value, and obtaining distance shift values ​​of the remaining document pages based on a product of the shift coefficient and the reference shift value.

[0049] Among them, the offset coefficient refers to the coefficient that can offset the first overlay distance. The larger the offset coefficient, the greater the degree of offset of the first overlay distance. The benchmark index difference refers to the pre-configured standard index difference. The benchmark offset value refers to the pre-configured standard value for offsetting the first overlay distance. The distance offset value refers to the value for offsetting the first overlay distance corresponding to each document page.

[0050] After determining the first overlapping distance corresponding to the reference page, the first overlapping distance can be offset according to the index difference values ​​corresponding to the remaining document pages to obtain the second overlapping distance corresponding to each document page. Specifically, the offset coefficient corresponding to each document page can be obtained by calculating the ratio of the index difference value corresponding to the document page and the pre-configured benchmark index difference value. The distance offset value corresponding to each document page can be obtained by multiplying the offset coefficient corresponding to each document page with the pre-configured benchmark offset value. The second overlapping distance corresponding to each document page can be determined according to the distance offset value.

[0051] S133: Determine second capping distances corresponding to the remaining document pages based on the difference between the first capping distance and the distance offset value.

[0052] Specifically, the difference between the first capping distance and the distance offset values ​​corresponding to the remaining document pages is calculated respectively, so as to obtain the second capping distances corresponding to the remaining document pages.

[0053] Through the above implementation, the covering range corresponding to each document page can be determined more accurately.

[0054] S14, determining the capping edge of each document page, and taking the capping edge as a reference, generating a customized edge parallel to the capping edge at the first capping distance or the second capping distance from the capping edge in the capping direction.

[0055] It can be understood that the saddle stamp is generally stamped on the side area of ​​the document page, and the document page generally has four sides, namely the upper side, the lower side, the left side, and the right side. One of the four sides can be selected as the stamped edge of the document page, and the direction perpendicular to the stamped edge can be determined as the stamping direction. For example, the right side corresponding to the document page can be selected as the stamped edge of the document page, then the stamping direction can be the direction from the right side to the left side. In the stamping direction, at the first stamping distance from the stamping edge, an edge parallel to the stamping edge can be generated, and this edge is the custom edge corresponding to the reference page. According to the second stamping distances corresponding to the remaining document pages, the corresponding custom edges of the document pages can be generated in the stamping direction at the second stamping distance from the stamping edge.

[0056] S15, determining that a page area corresponding to the capping edge and the customized edge in the document page is the customized capping area.

[0057] Specifically, the page area between the capping edge and the customized edge in the document page can be determined as the customized capping area corresponding to each document page. The page area refers to the area on the document page.

[0058] Through the above implementation, it can be ensured that the stamping position of the interline seal matches the importance of the document, reducing the risk of forgery and tampering and improving the security of the electronic document.

[0059] S2, obtaining the stamping range of each customized stamping area, and determining the stamping mark type according to the stamping range, wherein the stamping mark type includes a single mark type and a multiple mark type.

[0060] After determining the customized stamping area corresponding to each document page, the distance between each customized stamping area in the arrangement direction, that is, the stamping range, can be obtained. The size specifications of the electronic saddle seal for anti-counterfeiting in this scheme are determined. If the electronic document has many pages, then there may be a situation where one electronic saddle seal cannot completely cover all the document pages. In order to ensure that each page of the document can be stamped with an electronic saddle seal and improve the security of the electronic document, multiple electronic saddle seals can be generated at the same time to prevent electronic documents from being counterfeited.

[0061] Specifically, the stamping mark type can be determined according to the total stamping range corresponding to the electronic document. If an electronic saddle seal can completely cover the total stamping range corresponding to the electronic document, the corresponding stamping mark type can be determined to be a single mark type. If an electronic saddle seal cannot completely cover the total stamping range corresponding to the electronic document, the corresponding stamping mark type can be determined to be a multiple mark type. A corresponding number of electronic saddle seals can be generated for the electronic document according to the corresponding stamping mark type.

[0062] Among them, the stamping range refers to the distance of the customized stamping area in the arrangement direction, the stamping identification type refers to the stamping type of the saddle seal determined according to the stamping range, the single identification type refers to the stamping type corresponding to stamping one saddle seal on the electronic document, and the multiple identification type refers to the stamping type corresponding to stamping multiple saddle seals on the electronic document.

[0063] Based on the above embodiment, the specific implementation of step S2 may be: S21, determining the document page number of each of the document pages, and arranging the document pages in an arrangement direction from small to large according to the document page number to obtain a stamped document sequence.

[0064] Specifically, in an electronic document, the page number corresponding to each document page, that is, the document page number, can be determined, and the arrangement direction can be pre-configured, and the arrangement direction is parallel to and opposite to the stamping direction. For example, when the stamping direction is from the right edge to the left edge, the arrangement direction can be parallel to the stamping direction and from left to right. By arranging each document page in order from small to large in the document page number, a stamped document sequence can be obtained.

[0065] Among them, the number of document pages refers to the number of pages corresponding to each document page in the electronic document, the arrangement direction refers to the direction in which each document page is arranged according to the number of document pages, and the stamped document sequence refers to the sequence obtained by arranging each document page in the order of the number of document pages from small to large in the arrangement direction. The size of the saddle stamp corresponding to each document page can be determined in sequence according to the stamped document sequence.

[0066] S22, obtaining the capping distance of each document page in the capping document sequence in the arrangement direction, wherein the capping range includes the capping distance, and summing up each of the capping distances to obtain a total capping distance corresponding to the capping document sequence.

[0067] Specifically, the distance of the customized overlay area of ​​each document page in the arrangement direction, ie, the overlay distance, can be obtained, and the total overlay distance corresponding to the overlay document sequence can be obtained by summing up the overlay distances corresponding to each document page.

[0068] The capping distance refers to the distance of the customized capping area of ​​the document page in the arrangement direction, and the total capping distance refers to the sum of the capping distances of each document page.

[0069] S23, determining the diameter of the anti-counterfeiting mark, wherein the anti-counterfeiting mark is a circular mark, and obtaining the number of marks by rounding up the ratio of the total capping distance to the mark diameter.

[0070] Among them, the anti-counterfeiting mark refers to the mark for preventing electronic documents from being counterfeited, for example, it can be a circular electronic saddle seal, the mark diameter refers to the diameter corresponding to the circular anti-counterfeiting mark, and the number of marks refers to the number of anti-counterfeiting marks required for the electronic document.

[0071] Specifically, the anti-counterfeiting mark in the present scheme can be a circular electronic saddle seal, and the diameter corresponding to the circular electronic saddle seal, that is, the mark diameter, can be obtained. By calculating the ratio of the total stamping distance to the mark diameter, a ratio can be obtained. Since the anti-counterfeiting mark is circular, its coverage area is a fixed circular area. When the total stamping distance cannot be divided by the diameter of the anti-counterfeiting mark, the remaining distance may not be sufficient to accommodate a complete anti-counterfeiting mark. However, in order to ensure that every page of the electronic document can be stamped with the saddle seal and improve the security of the electronic document, the remaining stamping distance still needs to be covered. The obtained ratio can be rounded up to obtain the number of anti-counterfeiting marks required to stamp the document sequence, that is, the number of marks, so as to ensure that the total stamping distance corresponding to the stamped document sequence can be completely covered by the anti-counterfeiting mark.

[0072] S24, when the number of the logos is equal to the preset odd number, determining the stamped logo type is a single logo type; when the number of the logos is greater than the preset odd number, determining the stamped logo type is a multiple logo type.

[0073] The preset singular number is 1. Specifically, if the number of marks is equal to the preset singular number, it can be considered that the total stamping distance corresponding to the stamped document sequence can be completely covered by one anti-counterfeiting mark, and the corresponding stamping mark type can be determined to be a single-mark type; if the number of marks is greater than or equal to the preset singular number, it can be considered that the total stamping distance corresponding to the stamped document sequence cannot be completely covered by one anti-counterfeiting mark, and multiple anti-counterfeiting marks may need to be stamped, and the corresponding stamping mark type can be determined to be a multiple-mark type.

[0074] Through the above implementation, it can be ensured that each document page can be effectively stamped, thereby improving the anti-counterfeiting capability of the electronic document.

[0075] S3, cutting the anti-counterfeiting mark based on the stamping mark type and stamping range to obtain the sub-anti-counterfeiting mark of each document page, and updating the electronic data based on the sub-anti-counterfeiting mark to obtain archived data.

[0076] After obtaining the stamping mark type corresponding to the stamped document sequence and the stamping range corresponding to each document page, when stamping the electronic version of the anti-counterfeiting mark on the electronic data, in order to ensure that the anti-counterfeiting mark on each document page matches the corresponding stamping range, the anti-counterfeiting mark can be cut in combination with the stamping mark type and the stamping range to obtain a sub-anti-counterfeiting mark corresponding to the stamping range of each document page, and the sub-anti-counterfeiting mark corresponding to each document page is stamped into the corresponding customized stamping area to realize the update of the electronic data and obtain the corresponding archived data.

[0077] Among them, the sub-anti-counterfeiting mark refers to the partial anti-counterfeiting mark corresponding to each document page, and the archived data refers to the electronic data stamped with the anti-counterfeiting mark.

[0078] In some embodiments, step S3 includes S31 to S35, which are specifically as follows: S31, when the stamped mark type is a single mark type, sequentially obtain the stamped distance of each document page in the stamped document sequence as a cutting distance, cut the anti-counterfeiting mark according to the cutting distance, and obtain the sub-anti-counterfeiting mark corresponding to each document page.

[0079] Specifically, when the stamped mark type is a single mark type, only a single anti-counterfeiting mark needs to be cut. When cutting, the stamped distances corresponding to each document page in the stamped document sequence can be obtained in turn, and the stamped distances corresponding to each document page can be determined as the cutting distances in turn. The complete anti-counterfeiting mark can be cut according to the cutting distance, and a sub-anti-counterfeiting mark that matches the stamped distance of each document page can be generated.

[0080] The cutting distance may be the distance corresponding to each sub-anti-counterfeiting mark.

[0081] In some embodiments, the specific implementation of step S31 may be: S311, sequentially generating a plurality of first cutting lines with a spacing of the cutting distance on the anti-counterfeiting mark according to the arrangement direction, wherein the first cutting lines are perpendicular to the arrangement direction.

[0082] The first cutting line refers to a line segment for cutting the anti-counterfeiting mark.

[0083] See also Figure 2 , is a schematic diagram of a first cutting line provided by an embodiment of the present invention, such as Figure 2 As shown in , when the anti-counterfeiting mark is cut, a first cutting line tangent to the anti-counterfeiting mark and perpendicular to the arrangement direction can be generated on the leftmost side of the anti-counterfeiting mark. When there are three document pages in the stamped document sequence, in the arrangement direction, the cutting distance corresponding to the first document page in the stamped document sequence can be used as the spacing distance. At the spacing distance corresponding to the first cutting line, a second first cutting line perpendicular to the arrangement direction can be generated. The cutting distance corresponding to the second document page in the stamped document sequence can be used as the spacing distance. At the spacing distance corresponding to the second first cutting line, a third first cutting line perpendicular to the arrangement direction can be generated.

[0084] S312: Cut the anti-counterfeiting mark based on the first cutting line to obtain a plurality of sub-anti-counterfeiting marks, and arrange the sub-anti-counterfeiting marks based on the arrangement direction to obtain a mark sequence.

[0085] like Figure 2 As shown in , the anti-counterfeiting mark can be cut into three sub-anti-counterfeiting marks by three first cutting lines. In the arrangement direction, the sub-anti-counterfeiting marks can be arranged, for example, Figure 2 The sub-anti-counterfeiting mark on the left is ranked first, the sub-anti-counterfeiting mark in the middle is ranked second, and the sub-anti-counterfeiting mark on the right is ranked third to obtain the corresponding identification sequence. The identification sequence refers to the sequence obtained by arranging each sub-anti-counterfeiting mark in the arrangement direction.

[0086] S313, matching the document pages and the sub-anti-counterfeiting marks that are arranged in the same position in the stamped document sequence and the mark sequence to obtain the sub-anti-counterfeiting marks corresponding to each of the document pages.

[0087] Specifically, after obtaining the identification sequence, the document pages and sub-anti-counterfeiting identifications in the stamped document sequence that are arranged in the same position as the identification sequence can be matched. For example, in the identification sequence, the sub-anti-counterfeiting identification on the left is ranked first, the sub-anti-counterfeiting identification in the middle is ranked second, and the sub-anti-counterfeiting identification on the right is ranked third. Then the sub-anti-counterfeiting identification on the left can be matched with the first document page in the stamped document sequence, the sub-anti-counterfeiting identification in the middle can be matched with the second document page in the stamped document sequence, and the sub-anti-counterfeiting identification on the right can be matched with the third document page in the stamped document sequence, so that the sub-anti-counterfeiting identifications corresponding to each document page can be obtained.

[0088] S32, when the stamped mark type is a multi-mark type, the anti-counterfeiting mark is copied according to the number of marks to obtain an anti-counterfeiting mark group, and the anti-counterfeiting mark group is cut according to the cutting distance to obtain sub-anti-counterfeiting marks corresponding to each of the document pages.

[0089] Specifically, when the stamped mark type is a multiple-mark type, it means that the stamped document sequence needs to be stamped with multiple anti-counterfeiting marks. At this time, the anti-counterfeiting mark can be copied according to the number of marks corresponding to the stamped document sequence to obtain an anti-counterfeiting mark group containing multiple identical anti-counterfeiting marks. For example, when the number of marks corresponding to the stamped document sequence is 3, two more anti-counterfeiting marks can be copied to obtain an anti-counterfeiting mark group containing 3 anti-counterfeiting marks. The stamping distance corresponding to each document page in the stamped document sequence can be obtained in turn, and the stamping distance corresponding to each document page can be determined as the cutting distance in turn. The anti-counterfeiting mark group containing multiple complete anti-counterfeiting marks can be cut according to the cutting distance to obtain the sub-anti-counterfeiting mark corresponding to each document page.

[0090] The anti-counterfeiting mark group refers to a group consisting of the same number of anti-counterfeiting marks.

[0091] In some embodiments, the specific implementation of step S32 may be: S321, generating an arrangement reference line parallel to the arrangement direction, locating the center point of each anti-counterfeiting mark based on the arrangement reference line, arranging each anti-counterfeiting mark side by side to obtain an anti-counterfeiting mark group, and the interval distance between the center points of adjacent anti-counterfeiting marks is the distance corresponding to the mark diameter.

[0092] Specifically, in order to ensure that each document page has a corresponding saddle stamp for anti-counterfeiting, when cutting multiple anti-counterfeiting marks, an arrangement reference line parallel to the arrangement direction can be generated first. By positioning the center points of each anti-counterfeiting mark on the arrangement reference line, multiple anti-counterfeiting marks can be arranged side by side to obtain a corresponding anti-counterfeiting mark group. In the anti-counterfeiting mark group, the interval distance between the center points of adjacent anti-counterfeiting marks is the mark diameter, ensuring that the various anti-counterfeiting marks in the anti-counterfeiting mark group are closely connected, thereby ensuring that each document page can be covered by the saddle stamp.

[0093] The arrangement reference line refers to a line on which multiple anti-counterfeiting marks can be arranged side by side.

[0094] S322, obtaining a total mark distance covered by the anti-counterfeiting mark group on the arrangement reference line, and when the total mark distance is greater than the total covering distance corresponding to each of the document pages, rotating the anti-counterfeiting mark group according to a preset rotation direction.

[0095] Since the value obtained when obtaining the number of anti-counterfeiting marks corresponding to the stamped document sequence is rounded up, the total distance covered by the anti-counterfeiting marks may be greater than the total stamped distance corresponding to the stamped document sequence. In order to ensure that each anti-counterfeiting mark can be fully displayed on the electronic document, the anti-counterfeiting mark group can be rotated to ensure the integrity of the anti-counterfeiting mark.

[0096] Specifically, after obtaining the anti-counterfeiting mark group, the total mark distance covered by the anti-counterfeiting mark group on the arrangement reference line can be obtained. For example, when there are three anti-counterfeiting marks in the anti-counterfeiting mark group, since the three anti-counterfeiting marks are arranged side by side, the total mark distance covered by the anti-counterfeiting mark group on the arrangement reference line can be the sum of the three mark diameters. If the total mark distance is greater than the total stamped distance corresponding to the stamped document sequence, in this case, some anti-counterfeiting marks in the anti-counterfeiting mark group may not be fully displayed on the document page, thereby affecting its integrity and anti-counterfeiting effect. At this time, the anti-counterfeiting mark group can be rotated according to a pre-configured rotation direction, for example, a clockwise rotation direction, so that the anti-counterfeiting mark in the anti-counterfeiting mark group can be fully displayed on the electronic document.

[0097] The total identification distance refers to the total distance covered by the anti-counterfeiting identifications in the anti-counterfeiting identification group in the arrangement direction, and the preset rotation direction refers to the pre-configured direction in which the anti-counterfeiting identification group is rotated.

[0098] S323, acquiring in real time the real-time total distance of the anti-counterfeiting mark group in the arrangement direction during the rotation process, and when the real-time total distance is less than the total capping distance, stopping the rotation of the anti-counterfeiting mark group.

[0099] During the process of rotating the anti-counterfeiting mark group, the rotation angle of the anti-counterfeiting mark group in the preset rotation direction can be obtained in real time. According to the total mark distance and the real-time rotation angle, the total distance of the anti-counterfeiting mark group in the arrangement direction can be calculated in real time through the cosine function in the trigonometric function, that is, the real-time total distance. When the real-time total distance is less than the total stamping distance, it can be considered that each anti-counterfeiting mark in the anti-counterfeiting mark group can be fully displayed on the electronic document at this time, and the rotation of the anti-counterfeiting mark group can be stopped at this time.

[0100] The real-time total distance refers to the coverage distance of the anti-counterfeiting mark group in the arrangement direction obtained in real time.

[0101] S324, sequentially generating a plurality of second cutting lines with a spacing of the cutting distance on the anti-counterfeiting mark group according to the arrangement direction, wherein the second cutting lines are perpendicular to the arrangement reference line.

[0102] See also Figure 3 , is a schematic diagram of a second cutting line provided by an embodiment of the present invention, such as Figure 3 As shown in , when the anti-counterfeiting mark group rotates a certain angle according to the preset rotation direction, the anti-counterfeiting mark group is in an inclined state. At this time, when the anti-counterfeiting mark group is cut, a first second cutting line that is tangent to the leftmost anti-counterfeiting mark and perpendicular to the arrangement reference line can be generated on the leftmost side of the anti-counterfeiting mark group. When there are multiple document pages in the stamped document sequence, in the arrangement direction, the cutting distance corresponding to the first document page in the stamped document sequence can be used as the spacing distance. At the spacing distance corresponding to the first second cutting line, a second second cutting line perpendicular to the arrangement reference line can be generated. By analogy, multiple second cutting lines perpendicular to the arrangement reference line can be generated. Among them, the second cutting line refers to the line for cutting the anti-counterfeiting mark group.

[0103] S325, cutting the anti-counterfeiting mark group based on the second cutting line to obtain a plurality of sub-anti-counterfeiting marks, and arranging the sub-anti-counterfeiting marks based on the arrangement direction to obtain a mark sequence.

[0104] like Figure 3 As shown in , the anti-counterfeiting mark group can be cut into multiple sub-anti-counterfeiting marks by multiple second cutting lines, and the sub-anti-counterfeiting marks can be arranged in the arrangement direction to obtain a corresponding mark sequence.

[0105] S326, matching the document pages and the sub-anti-counterfeiting marks that are arranged in the same position in the stamped document sequence and the mark sequence to obtain the sub-anti-counterfeiting marks corresponding to each of the document pages.

[0106] Specifically, by matching the document pages in the stamped document sequence that are arranged in the same position as the identification sequence with the sub-anti-counterfeiting identification, the sub-anti-counterfeiting identification corresponding to each document page can be obtained.

[0107] S33, determining the edge of the area in the customized capping area that is perpendicular to the arrangement direction as the first target edge, and determining the cutting edge of each of the sub-anti-counterfeiting marks as the second target edge.

[0108] Specifically, the edge of the area in the customized overlay area in each document page that is perpendicular to the arrangement direction can be determined as the first target edge. Each customized overlay area has two first target edges that are perpendicular to the arrangement direction, one on the left and one on the right. When the anti-counterfeiting mark is cut to obtain a sub-anti-counterfeiting mark, each sub-anti-counterfeiting mark has a corresponding cutting edge. Some sub-anti-counterfeiting marks may have one cutting edge, and some sub-anti-counterfeiting marks may have two cutting edges. The cutting edge corresponding to each sub-anti-counterfeiting mark can be determined as the second target edge.

[0109] Among them, the area edge refers to the four mutually perpendicular edges that constitute the customized covering area, the first target edge refers to the area edge in the customized covering area that is perpendicular to the arrangement direction, the cutting edge refers to the edge that separates the anti-counterfeiting mark, and the second target edge refers to the cutting edge corresponding to the sub-anti-counterfeiting mark.

[0110] S34, obtaining the sub-anti-counterfeiting mark located on the left side after the anti-counterfeiting mark is cut as the starting mark, the sub-anti-counterfeiting mark located in the middle as the middle mark, and the sub-anti-counterfeiting mark located on the right side as the end mark.

[0111] Specifically, after the anti-counterfeiting mark is cut, the anti-counterfeiting mark is cut into multiple sub-anti-counterfeiting marks. The sub-anti-counterfeiting mark on the left side of each anti-counterfeiting mark can be determined as the starting mark, the sub-anti-counterfeiting mark in the middle can be determined as the middle mark, and the sub-anti-counterfeiting mark on the right side can be determined as the end mark.

[0112] Among them, the starting mark refers to the sub-anti-counterfeiting mark located on the left, the middle mark refers to the sub-anti-counterfeiting mark located in the middle, and the end mark refers to the anti-counterfeiting mark located on the right.

[0113] S35, connect the second target edge of the starting mark with the first target edge on the right side of the customized cover area, connect the second target edges on both sides of the middle mark with the first target edges on both sides of the customized cover area, and connect the second target edge of the ending mark with the first target edge on the left side of the customized cover area to obtain archived data.

[0114] See also Figure 4 , which is a schematic diagram of determining a second target edge provided by an embodiment of the present invention, from Figure 4It can be seen that each sub-anti-counterfeiting mark has a corresponding cutting edge. The starting mark on the left has a cutting edge on the right, and the cutting edge on the right can be determined as the second target edge corresponding to the starting mark. The middle mark in the middle position has two cutting edges on both sides, and the corresponding two cutting edges can be determined as the second target edge corresponding to the middle mark. The end mark on the right has a cutting edge on the left, and the cutting edge on the left can be determined as the second target edge corresponding to the end mark.

[0115] If the sub-anti-counterfeiting mark corresponding to the document page is a starting mark, the second target edge of the starting mark on the right side can be connected with the first target edge on the right side of the customized stamping area of ​​the document page. If the sub-anti-counterfeiting mark corresponding to the document page is a middle mark, the second target edges on both sides of the middle mark can be connected with the first target edges on both sides of the customized stamping area of ​​the document page respectively. If the sub-anti-counterfeiting mark corresponding to the document page is an ending mark, the second target edge of the ending mark on the left side can be connected with the first target edge on the left side of the customized stamping area of ​​the document page, so that the electronic saddle seal can be stamped on the electronic document to obtain the corresponding archived data.

[0116] Through the above implementation, it can be ensured that the anti-counterfeiting mark on each document page accurately matches its stamped range, thereby improving the security of the electronic document.

[0117] S4, responding to the compliance verification information of the management end, verifying the current anti-counterfeiting mark corresponding to the current archived data based on the mark verification model to obtain compliance detection data and sending it to the management end.

[0118] Among them, the management end refers to the terminal held by the management personnel, the compliance verification information refers to the information for compliance verification of archived data, the identification verification model refers to the model that can verify the anti-counterfeiting identification in the archived data, the current archived data refers to the archived data to be verified for authenticity, the current anti-counterfeiting identification refers to the anti-counterfeiting identification to be verified on the current archived data, and the compliance detection data refers to the data obtained after the compliance verification of the current anti-counterfeiting identification in the archived data.

[0119] After obtaining the archived data, the corresponding multiple sub-anti-counterfeiting logos in the archived data can be spliced. If the spliced ​​anti-counterfeiting logo is highly consistent with the original anti-counterfeiting logo, the sub-anti-counterfeiting logo in the archived data can be verified, and the management personnel on the management end can send corresponding verification information. After the compliance verification information sent by the corresponding management end, the logo verification model that has been pre-trained with a large amount of historical data can be retrieved, and the anti-counterfeiting logo in the archived data to be verified can be verified according to the historical data corresponding to the current archived data in the database to verify whether the anti-counterfeiting logo is compliant. If the anti-counterfeiting logo in the archived data is compliant, the corresponding compliance detection data can be obtained and sent to the management end for the management personnel to view.

[0120] Based on the above embodiment, the specific implementation of step S4 may be: S41, based on the identification verification model, retrieve multiple sub-archive identifications corresponding to the current archive data in the database, and arrange the sub-archive identifications in sequence according to the arrangement direction to obtain an archive identification sequence.

[0121] Specifically, in the database, there are a large number of historical archived data corresponding to the current archived data, and each historical archived data has a corresponding sub-anti-counterfeiting mark. Through the mark verification model, multiple historical sub-anti-counterfeiting marks corresponding to the current archived data to be verified can be retrieved from the database, that is, sub-archive marks. By arranging multiple sub-archive marks in the arrangement direction, the corresponding archive mark sequence can be obtained.

[0122] Among them, the sub-archive identifier refers to the sub-anti-counterfeiting identifier corresponding to the current archive identifier in the database, and the archive identifier sequence refers to the sequence obtained by arranging the sub-archive identifiers in the arrangement direction.

[0123] S42, extracting a plurality of current anti-counterfeiting marks corresponding to the current archived data, and arranging the current anti-counterfeiting marks according to the arrangement direction to obtain a sequence to be verified.

[0124] Specifically, a plurality of corresponding sub-anti-counterfeiting marks, namely, the current anti-counterfeiting mark, may be extracted from the current archived data, and the plurality of current anti-counterfeiting marks may be arranged in an arrangement direction to obtain a corresponding sequence to be verified.

[0125] The current anti-counterfeiting mark refers to the sub-anti-counterfeiting mark in the current archived data, and the sequence to be verified refers to the sequence obtained by arranging multiple current anti-counterfeiting marks in the arrangement direction.

[0126] S43, determining in sequence the sub-archiving identifiers in the archiving identifier sequence as compliance identifiers, and determining the current anti-counterfeiting identifier corresponding to the arrangement position of the compliance identifier in the to-be-verified sequence as the to-be-verified identifier.

[0127] For example, in the archive identification sequence, the first sub-archive identification is determined as the compliance identification. Then, in the sequence to be verified, the first current anti-counterfeiting identification can be determined as the identification to be verified, and then the second sub-archive identification in the archive identification sequence can be determined as the compliance identification. Similarly, the second current anti-counterfeiting identification in the sequence to be verified can be determined as the identification to be verified. Similarly, each sub-archive identification in the archive identification sequence can be determined as a compliance identification in turn. Similarly, the current anti-counterfeiting identification corresponding to the arrangement position of the compliance identification in the sequence to be verified can be determined as the identification to be verified in turn.

[0128] Among them, the compliance mark refers to the sub-archive mark in the archive mark sequence, and the pending verification mark refers to the current anti-counterfeiting mark that needs to be verified in the pending verification sequence.

[0129] S44, determining the compliance mark and the mark to be verified as a verification group, and obtaining a first coordinate position of the compliance mark and a second coordinate position of the mark to be verified.

[0130] Specifically, the corresponding compliance identification and the identification to be verified can be determined as the same verification group. For example, the first compliance identification in the archived identification sequence and the first identification to be verified in the identification to be verified sequence can be determined as the same verification group, and the coordinate position corresponding to the center point of the compliance identification, that is, the first coordinate position, and the coordinate position corresponding to the center point of the identification to be verified, that is, the second coordinate position, can be obtained. Subsequently, whether the identification to be verified is compliant can be judged based on the first coordinate position and the second coordinate position.

[0131] Among them, the verification group refers to a group consisting of a compliance mark and a corresponding mark to be verified. The first coordinate position can be used to identify the position corresponding to the compliance mark, and the second coordinate position can be used to indicate the position corresponding to the mark to be verified.

[0132] S45, when the distance difference between the first coordinate position and the second coordinate position is less than a distance difference threshold, obtaining a first distance of the compliance mark in the arrangement direction and a second distance of the mark to be verified in the arrangement direction.

[0133] Specifically, after obtaining the first coordinate position and the second coordinate position, the distance difference corresponding to the first coordinate position and the second coordinate position can be obtained according to the distance formula between the two coordinates. If the distance difference is less than the distance difference threshold, it can be considered that the position of the mark to be verified is almost the same as the position of the compliance mark. In order to more accurately judge the authenticity of the mark to be verified, the overlapped distance of the compliance mark in the arrangement direction, that is, the first distance, and the overlapped distance of the mark to be verified in the arrangement direction, that is, the second distance, can be obtained. A secondary judgment is made on the authenticity of the mark to be verified based on the overlapped distance.

[0134] Among them, the distance difference refers to the distance between the first coordinate position and the second coordinate position, and the distance difference threshold refers to the threshold that can be used to determine whether the first coordinate position and the second coordinate position are consistent. If the distance difference is less than the distance difference threshold, it can be considered that the first coordinate position and the second coordinate position are almost consistent. If the distance difference is greater than the distance difference threshold, it can be considered that there is a difference between the first coordinate position and the second coordinate position.

[0135] S46, when the difference between the first distance and the second distance is less than the identification stamping threshold, the verification group is determined to be a compliance group, and when all verification groups are the compliance groups, the current archived data is determined to be compliance detection data and sent to the management end.

[0136] Specifically, if the difference between the first distance and the second distance is less than the mark stamping threshold, it can be considered that the stamping distance of the compliant mark and the stamping distance of the mark to be verified are almost the same, and the corresponding verification group can be determined as the compliance group. The other verification groups can be verified in the same way. If all verification groups are compliance groups, the current archived data can be determined as compliance detection data, and the compliance detection data can be sent to the management end.

[0137] Among them, the identification stamping threshold refers to a threshold that can be used to determine whether the verification group is compliant. If the difference between the first distance and the second distance is less than the identification stamping threshold, the corresponding verification group can be considered to be compliant. If the difference between the first distance and the second distance is greater than the identification stamping threshold, the corresponding verification group can be considered to be non-compliant. The compliant group refers to the verification group in which the difference between the first distance and the second distance is less than the identification stamping threshold.

[0138] Through the above implementation, the anti-counterfeiting mark in the archived data can be fully and carefully verified, reducing the risk of electronic documents being forged or tampered with.

[0139] See also Figure 5 , is a schematic diagram of the structure of a tax compliance intelligent inspection platform provided by an embodiment of the present invention. The data processing system based on the tax compliance intelligent inspection platform includes: An acquisition module, used for acquiring an electronic layout sequence corresponding to the electronic data based on a document recognition model, and determining a customized cover area of ​​each document page in the electronic data according to the electronic layout sequence; A determination module, used for obtaining the stamping range of each customized stamping area, and determining the stamping mark type according to the stamping range, wherein the stamping mark type includes a single mark type and a multiple mark type; An updating module, configured to cut the anti-counterfeiting mark based on the stamping mark type and stamping range to obtain a sub-anti-counterfeiting mark of each document page, and update the electronic data based on the sub-anti-counterfeiting mark to obtain archived data; The verification module is used to respond to the compliance verification information of the management end, verify the current anti-counterfeiting mark corresponding to the current archived data based on the mark verification model, and obtain compliance detection data and send it to the management end.

[0140] Figure 5 The apparatus of the embodiment shown can be used to perform Figure 1 The implementation principles and technical effects of the steps in the method embodiment shown are similar and will not be repeated here.

[0141] 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A tax compliance intelligent inspection method, characterized in that: include: Acquire an electronic layout sequence corresponding to the electronic data based on the document recognition model, and determine a customized cover area of ​​each document page in the electronic data according to the electronic layout sequence; Acquire the stamping range of each customized stamping area, and determine the stamping mark type according to the stamping range, wherein the stamping mark type includes a single mark type and a multiple mark type; Cutting the anti-counterfeiting mark based on the stamping mark type and stamping range to obtain the sub-anti-counterfeiting mark of each document page, and updating the electronic data based on the sub-anti-counterfeiting mark to obtain archived data; In response to the compliance verification information of the management end, the current anti-counterfeiting mark corresponding to the current archived data is verified based on the mark verification model to obtain compliance detection data and send it to the management end.

2. The method according to claim 1, characterized in that Acquiring an electronic layout sequence corresponding to the electronic data based on a document recognition model, and determining a customized cover area of ​​each document page in the electronic data according to the electronic layout sequence, including: Determine the evaluation index of each document page corresponding to the electronic data according to the document recognition model, and arrange the document pages from large to small based on the evaluation index to obtain an electronic layout sequence; Acquire the first document page in the electronic layout sequence as a reference page, and calculate the index difference between the evaluation index of the reference page and the evaluation index of the remaining document pages; Determine a first capping distance corresponding to the reference page, offset the first capping distance according to the index difference, and obtain a second capping distance corresponding to the remaining document pages; Determine the capping edge of each of the document pages, and based on the capping edge, generate a customized edge parallel to the capping edge at the first capping distance or the second capping distance from the capping edge in the capping direction; A page area corresponding to the capping edge and the customized edge in the document page is determined as the customized capping area.

3. The method according to claim 2, characterized in that Determining the evaluation index of each document page corresponding to the electronic data according to the document recognition model includes: Performing text recognition on each of the document pages based on the document recognition model to determine keywords corresponding to each of the document pages; When the keyword is a seal indicator word, the center point of the seal indicator word is determined as the center of the circle, a traversal range is determined according to a preset radius, and the document seal within the traversal range is identified; The first importance index corresponding to each of the keywords and the second importance index of the document seal are determined, and the first importance index and the second importance index corresponding to the document page are added together to obtain an evaluation index.

4. The method according to claim 2, characterized in that: Determining a first capping distance corresponding to the reference page, offsetting the first capping distance according to the index difference, and obtaining second capping distances corresponding to the remaining document pages, including: Counting the index mean of each evaluation index, and determining the optimal capping range corresponding to the index mean as the first capping distance corresponding to the reference page; Obtaining a shift coefficient according to a ratio of the index difference value to the reference index difference value, and obtaining distance shift values ​​of the remaining document pages based on a product of the shift coefficient and the reference shift value; Based on the difference between the first capping distance and the distance offset value, second capping distances corresponding to the remaining document pages are determined.

5. The method according to claim 1, characterized in that The stamping range of each customized stamping area is obtained, and the stamping mark type is determined according to the stamping range. The stamping mark type includes a single mark type and a multiple mark type, including: Determine the document page number of each of the document pages, and arrange the document pages in an arrangement direction from small to large according to the document page number to obtain a stamped document sequence; Acquire the capping distance of each document page in the capping document sequence in the arrangement direction, the capping range includes the capping distance, and sum up each capping distance to obtain a total capping distance corresponding to the capping document sequence; Determine the diameter of the anti-counterfeiting mark, the anti-counterfeiting mark is a circular mark, and obtain the number of marks according to the rounded-up value of the ratio of the total capping distance to the mark diameter; When the number of the logos is equal to a preset odd number, the stamped logo type is determined to be a single logo type; when the number of the logos is greater than the preset odd number, the stamped logo type is determined to be a multiple logo type.

6. The method according to claim 5, characterized in that Cutting the anti-counterfeiting mark based on the stamping mark type and stamping range to obtain the sub-anti-counterfeiting mark of each document page, and updating the electronic data based on the sub-anti-counterfeiting mark to obtain archived data, including: When the stamped mark type is a single mark type, sequentially obtaining stamped distances of each document page in the stamped document sequence as cutting distances, cutting the anti-counterfeiting mark according to the cutting distances, and obtaining sub-anti-counterfeiting marks corresponding to each document page; When the stamped mark type is a multiple mark type, the anti-counterfeiting mark is copied according to the number of marks to obtain an anti-counterfeiting mark group, and the anti-counterfeiting mark group is cut according to the cutting distance to obtain a sub-anti-counterfeiting mark corresponding to each of the document pages; Determine the edge of the region in the customized capping area that is perpendicular to the arrangement direction as the first target edge, and determine the cutting edge of each of the sub-anti-counterfeiting marks as the second target edge; After the anti-counterfeiting mark is cut, the sub-anti-counterfeiting mark on the left is taken as the starting mark, the sub-anti-counterfeiting mark in the middle is taken as the middle mark, and the sub-anti-counterfeiting mark on the right is taken as the ending mark; The second target edge of the starting mark is connected with the first target edge on the right side of the customized cover area, the second target edges on both sides of the middle mark are connected with the first target edges on both sides of the customized cover area, and the second target edge of the ending mark is connected with the first target edge on the left side of the customized cover area to obtain archived data.

7. The method according to claim 6, characterized in that When the stamped mark type is a single mark type, sequentially obtaining stamped distances of each document page in the stamped document sequence as cutting distances, cutting the anti-counterfeiting mark according to the cutting distances, and obtaining sub-anti-counterfeiting marks corresponding to each document page, including: According to the arrangement direction, a plurality of first cutting lines with a spacing of the cutting distance are sequentially generated on the anti-counterfeiting mark, wherein the first cutting lines are perpendicular to the arrangement direction; Cutting the anti-counterfeiting mark based on the first cutting line to obtain a plurality of sub-anti-counterfeiting marks, and arranging the sub-anti-counterfeiting marks based on the arrangement direction to obtain a mark sequence; The document pages and the sub-anti-counterfeiting marks that are arranged in the same position in the stamped document sequence and the mark sequence are matched to obtain the sub-anti-counterfeiting marks corresponding to each of the document pages.

8. The method according to claim 6, characterized in that When the stamped mark type is a multiple mark type, the anti-counterfeiting mark is copied according to the number of marks to obtain an anti-counterfeiting mark group, and the anti-counterfeiting mark group is cut according to the cutting distance to obtain the sub-anti-counterfeiting marks corresponding to each document page, including: Generate an arrangement reference line parallel to the arrangement direction, locate the center point of each anti-counterfeiting mark based on the arrangement reference line, arrange each anti-counterfeiting mark side by side to obtain an anti-counterfeiting mark group, and the interval distance between the center points of adjacent anti-counterfeiting marks is the distance corresponding to the mark diameter; Obtaining a total mark distance covered by the anti-counterfeiting mark group on the arrangement reference line, and when the total mark distance is greater than the total covering distance corresponding to each of the document pages, rotating the anti-counterfeiting mark group according to a preset rotation direction; Acquire in real time the real-time total distance of the anti-counterfeiting mark group in the arrangement direction during the rotation process, and stop the rotation of the anti-counterfeiting mark group when the real-time total distance is less than the total capping distance; According to the arrangement direction, a plurality of second cutting lines with a spacing of the cutting distance are sequentially generated on the anti-counterfeiting mark group, wherein the second cutting lines are perpendicular to the arrangement reference line; Cutting the anti-counterfeiting mark group based on the second cutting line to obtain a plurality of sub-anti-counterfeiting marks, and arranging the sub-anti-counterfeiting marks based on the arrangement direction to obtain a mark sequence; The document pages and the sub-anti-counterfeiting marks that are arranged in the same position in the stamped document sequence and the mark sequence are matched to obtain the sub-anti-counterfeiting marks corresponding to each of the document pages.

9. The method according to claim 1, characterized in that: In response to the compliance verification information of the management end, the current anti-counterfeiting mark corresponding to the current archived data is verified based on the mark verification model to obtain compliance detection data and send it to the management end, including: Based on the identification verification model, multiple sub-archive identifications corresponding to the current archive data are retrieved from the database, and the sub-archive identifications are arranged in sequence according to the arrangement direction to obtain an archive identification sequence; Extracting a plurality of current anti-counterfeiting marks corresponding to the current archived data, and arranging the current anti-counterfeiting marks according to the arrangement direction to obtain a sequence to be verified; sequentially determining the sub-archiving identifiers in the archiving identifier sequence as compliance identifiers, and determining the current anti-counterfeiting identifier corresponding to the arrangement position of the compliance identifier in the to-be-verified sequence as the to-be-verified identifier; Determine the compliance mark and the mark to be verified as a verification group, and obtain a first coordinate position of the compliance mark and a second coordinate position of the mark to be verified; When the distance difference between the first coordinate position and the second coordinate position is less than a distance difference threshold, obtaining a first distance of the compliance mark in the arrangement direction and a second distance of the mark to be verified in the arrangement direction; When the difference between the first distance and the second distance is less than the identification stamping threshold, the verification group is determined to be a compliance group. When all verification groups are the compliance groups, the current archived data is determined to be compliance detection data and sent to the management end.

10. A tax compliance intelligent inspection platform, characterized in that: include: An acquisition module, used for acquiring an electronic layout sequence corresponding to the electronic data based on a document recognition model, and determining a customized cover area of ​​each document page in the electronic data according to the electronic layout sequence; A determination module, used for obtaining the stamping range of each customized stamping area, and determining the stamping mark type according to the stamping range, wherein the stamping mark type includes a single mark type and a multiple mark type; An updating module, configured to cut the anti-counterfeiting mark based on the stamping mark type and stamping range to obtain a sub-anti-counterfeiting mark of each document page, and update the electronic data based on the sub-anti-counterfeiting mark to obtain archived data; The verification module is used to respond to the compliance verification information of the management end, verify the current anti-counterfeiting mark corresponding to the current archived data based on the mark verification model, and obtain compliance detection data and send it to the management end.

Images