An intelligent accounting information processing system based on cloud computing

Abstract

The present invention relates to the technical field of accounting information processing, and in particular to an intelligent accounting information processing system based on cloud computing. The present invention obtains seals in account information to be identified through a cloud information acquisition module, and an information classification module determines a seal confidence representation value according to a chromaticity deviation value combined with the completeness of the seal contour in the account information to be identified, divides the category of the image to be identified, selects a verification unit to verify the seal in the image to be identified according to the category of the image to be identified, and adaptively adopts different methods to verify whether the seal in the image to be identified of the account information to be identified meets the verification standard. The present invention can classify the seals in the image to be identified, and can determine whether different categories of images to be identified meet the verification standard, thereby improving the verification capability of the intelligent accounting information processing system for the account information to be identified and ensuring the reliability of the intelligent accounting information processing system.

Description

Technical Field

[0001] The present invention relates to the technical field of accounting information processing, and in particular to an intelligent accounting information processing system based on cloud computing. Background Art

[0002] With the development of computer technology and Internet technology, the integrated accounting information system platform for business, finance and taxation can collect terminal business data in an all-round way, complete modular accounting processing, realize financial work such as financial data reconciliation, bookkeeping, and report issuance, and realize the standardization, process and informatization of data collection and financial processing. It relies on the integrated effect of management informatization to force the standardization of business processes, and relies on the comprehensive means of auditing to force the standardization of financial and tax processes, thereby improving the overall development of the accounting industry. Therefore, the development of related accounting information systems is valued by people.

[0003] For example, Chinese patent publication number: CN114997974A, discloses an accounting management system based on big data application, which relates to the field of accounting management. Its technical solution includes a platform construction system, an information system, a management platform and a cloud storage module. The platform construction system and the information system are communicated and connected. The information system stores the enterprise's data. The information system transmits the enterprise's usual data to the platform construction system. The platform construction system includes a deep learning module. The platform construction system and the cloud storage module are communicated and connected; the deep learning module performs deep learning on the received data to obtain the relationship between the data, thereby establishing a management platform. The deep learning module inside the platform construction system can perform deep learning on the data inside the information system and the cloud storage module, thereby establishing a management platform. The management platform facilitates the effective processing of the overall financial data within the enterprise.

[0004] For example, China Patent Publication No.: CN115545863A discloses an accounting information service platform based on blockchain, which can be used as a national enterprise transaction and accounting information service platform serving all enterprises. The accounting information service platform of the present invention solves the problem of the authenticity and reliability of the original basis of accounting through a tamper-proof and traceable alliance chain transaction information storage system and a private chain accounting event information storage system; the platform solves the problem of easy leakage of enterprise transaction privacy data on the centralized accounting service platform through the transaction information isolation function of the alliance chain transaction channel; the platform can realize the automation of accounting operations through the accounting service system; the platform introduces government regulatory departments such as tax departments and market management departments into the alliance chain transaction information storage system to further improve the authenticity and authority of blockchain transaction information storage.

[0005] However, the prior art still has the following problems:

[0006] In the prior art, in the accounting field, it is often necessary to verify the authenticity of the seal information of relevant documents. In the cloud platform, the verification can be carried out by uploading pictures. However, for pictures containing seals, they can be forged directly by the determination machine or by using the real picture to be identified, resulting in the problem of low accuracy in the verification and judgment of the seal of the picture to be identified. Summary of the invention

[0007] To this end, the present invention provides an intelligent accounting information processing system based on cloud computing to overcome the problem in the prior art that in the accounting field, the authenticity of the seal information of relevant documents often needs to be verified. In the cloud platform, verification can be carried out by uploading pictures, but for pictures containing seals, they can be forged directly by a determination machine or by converting them into real pictures to be identified, resulting in a low accuracy problem in the verification and judgment of the seals on the pictures to be identified.

[0008] To achieve the above objectives, the present invention provides an intelligent accounting information processing system based on cloud computing, comprising:

[0009] A cloud information acquisition module, which is connected to the user end and is used to acquire the account information to be identified uploaded by the user end, wherein the account information to be identified includes several categories of pictures to be identified;

[0010] An information classification module is connected to the image acquisition module to be identified, and is used to divide the image to be identified into a number of sub-images, obtain the chromaticity value of the seal part in each sub-image and extract the seal outline in the image to be identified, determine the seal confidence representation value according to the chromaticity deviation value combined with the seal outline integrity, and classify the image to be identified;

[0011] An information verification module, which is connected to the cloud information acquisition module and the information classification module respectively, and includes a selected verification unit and a storage unit;

[0012] The selected verification unit is used to verify the image to be identified according to the category of the image to be identified, including:

[0013] Obtaining the chromaticity values ​​of several feature points in the image to be identified, and determining whether the image to be identified meets the verification criteria according to the chromaticity values ​​of the feature points;

[0014] Or, obtaining the clarity of the seal edge in the image to be identified, and determining whether the image to be identified meets the verification standard;

[0015] A database module is connected to the information verification module and is used to store the verified pictures to be identified.

[0016] Furthermore, the information classification module is used to obtain the chromaticity deviation value of the image to be identified, including:

[0017] To extract the chromaticity values ​​of a number of points of the stamp part of each sub-image and determine the average chromaticity value of the stamp part of the sub-image;

[0018] Determine the average color value of the seal to be verified according to the average color value of the seal part of each sub-image;

[0019] It is used to obtain the difference between the chromaticity average value of the seal part of each sub-image and the chromaticity average value of the seal to be verified, and the sum of the differences is the chromaticity deviation value of the image to be identified.

[0020] Furthermore, the information classification module is used to obtain the completeness of the seal outline.

[0021] Used to obtain the image to be identified;

[0022] To obtain the seal outline and the overall seal outline of the seal whose chromaticity value in the image to be identified is the average chromaticity value of the seal to be verified;

[0023] To obtain the proportion of the seal outline whose chromaticity value in the image to be identified is the average chromaticity value of the seal to be verified in the overall seal outline;

[0024] Used to record the proportion as the completeness of the seal outline.

[0025] Furthermore, the information classification module is used to determine the seal confidence representation value according to the chromaticity deviation value combined with the seal outline integrity, including:

[0026] for determining the ratio of the seal chromaticity deviation value to a preset chromaticity deviation value threshold as a first confidence feature;

[0027] for determining the ratio of a preset seal outline integrity threshold to the seal outline integrity as a second confidence feature;

[0028] Used to determine the sum of the first confidence feature and the second confidence feature as the seal confidence representation value.

[0029] Furthermore, the information classification module divides the pictures to be identified into categories.

[0030] The information classification module compares the seal confidence representation value with a preset seal confidence representation value comparison threshold value,

[0031] If the seal confidence representation value of the image to be identified is less than the preset seal confidence representation value comparison threshold, the category of the image to be identified is a pseudo-tendency image to be identified category;

[0032] If the seal confidence representation value of the image to be identified is greater than or equal to the preset seal confidence representation value comparison threshold, then the category of the image to be identified is the true tendency category of the image to be identified.

[0033] Furthermore, the selected verification unit is used to verify the image to be identified according to the category of the image to be identified, wherein:

[0034] If the category of the image to be identified is a pseudo-tendency image to be identified category, then obtaining the chromaticity values ​​of several feature points in the image to be identified, and determining whether the seal in the image to be identified meets the verification standard according to the chromaticity values ​​of the feature points;

[0035] If the category of the image to be identified is the category of the image to be identified that is truly inclined, the edge clarity of the seal in the image to be identified is obtained to determine whether the seal in the image to be identified meets the verification standard.

[0036] Furthermore, the selected verification unit obtains the chromaticity values ​​of a plurality of feature points in the image to be identified, wherein the feature points are points where characters and seals overlap.

[0037] Furthermore, the selected verification unit is used to determine whether the seal in the image to be identified meets the verification standard according to the chromaticity value of the feature point.

[0038] To obtain the difference between the average chromaticity value of the feature points and the average chromaticity value of the non-feature points;

[0039] Used to compare the difference between the average chromaticity value of the feature point and the average chromaticity value of the non-feature point with a preset difference comparison threshold;

[0040] If the difference between the average chromaticity value of the feature point and the average chromaticity value of the non-feature point is less than a preset difference comparison threshold, it is determined that the seal in the image to be identified does not meet the verification standard.

[0041] Furthermore, the selected verification unit is used to compare the clarity of the seal edge with a preset clarity comparison threshold.

[0042] If the edge clarity of the seal in the image to be identified is less than a preset clarity comparison threshold, it is determined that the seal in the image to be identified does not meet the verification standard.

[0043] Furthermore, the storage unit is used to store the pictures to be identified whose seals do not meet the verification standard.

[0044] Compared with the prior art, the present invention obtains the image to be identified through a cloud information acquisition module, and the information classification module determines the seal confidence representation value according to the chromaticity deviation value combined with the seal contour completeness, divides the image to be identified into categories, and selects a verification unit to verify the image to be identified according to the category of the image to be identified, including obtaining the chromaticity values ​​of several feature points in the image to be identified, and determining whether the seal in the image to be identified meets the verification standard according to the chromaticity values ​​of the feature points, or obtaining the edge clarity of the seal in the image to be identified, and determining whether the seal in the image to be identified meets the verification standard. The present invention can adopt different verification strategies for different categories of images to be identified by classifying the images to be identified, thereby improving the reliability of the verification of the images to be identified.

[0045] In particular, the information classification module of the present invention determines the seal confidence characterization value based on the chromaticity deviation value combined with the seal contour completeness. In actual situations, a forged seal may show overly uniform characteristics in chromaticity values, while a real seal will have certain non-uniformity in chromaticity values ​​due to factors such as pressure and ink distribution when stamping. The uniformity of the chromaticity of the seal in the image to be identified can be reliably characterized based on the chromaticity deviation value and the seal contour completeness. By determining the seal confidence characterization value, the seal in the image to be identified can be verified more reliably, and the image to be identified can be divided into different categories.

[0046] In particular, the information classification module of the present invention classifies the pictures to be identified according to the seal confidence representation value. When the seal confidence representation value of the picture to be identified is high, there is a certain chromaticity value difference between the seals in the picture to be identified. When the seal confidence representation value of the picture to be identified is small, the chromaticity value difference between the seals in the picture to be identified is small. By classifying the pictures to be identified, it can be determined whether the pictures to be identified of different categories meet the verification standards, thereby improving the reliability of the verification of the pictures to be identified.

[0047] In particular, the verification unit selected by the present invention determines whether the seal in the image to be identified meets the verification standards based on the chromaticity value of the feature point. In actual situations, when the seal in the image to be identified is printed on a document, the text or signature under the seal may be revealed through the seal ink. If there is text showing under the seal, the color of the seal area may be unevenly distributed, because the text will affect the color and density of the seal ink. By obtaining the chromaticity value of the feature point, the phenomenon of the text or signature showing under the seal can be characterized, so that the verification of the seal can be judged more reliably.

[0048] In particular, the verification unit selected by the present invention determines whether the seal in the picture to be identified meets the verification standards based on the clarity of the seal edge in the picture to be identified. In actual situations, the seal in the real seal picture may be accurately separated by image editing software and placed in another image or background, which may cause the clarity of the seal edge to decrease. By obtaining the clarity of the seal edge, it is possible to more reliably verify whether the seal in the picture to be identified meets the verification standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A diagram of the structure of an intelligent accounting information processing system based on cloud computing according to an embodiment of the invention;

[0050] Figure 2 It is a structural diagram of the information classification module of an embodiment of the invention;

[0051] Figure 3 A logical decision diagram for dividing the categories of pictures to be identified by the information classification module of the embodiment of the invention;

[0052] Figure 4 This is a logical decision diagram for the selected verification unit of an embodiment of the present invention to determine whether the seal in the image to be identified meets the verification standard. DETAILED DESCRIPTION

[0053] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0054] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0055] See also Figure 1-Figure 4 As shown, Figure 1 This is a diagram of the structure of an intelligent accounting information processing system based on cloud computing according to an embodiment of the invention. Figure 2 This is a structural diagram of the information classification module of an embodiment of the invention. Figure 3 A logical decision diagram for classifying the categories of pictures to be identified by the information classification module of the embodiment of the invention, Figure 4 The selected verification unit of the embodiment of the invention determines whether the seal in the image to be identified meets the verification standard logic determination diagram. The cloud computing-based intelligent accounting information processing system of the present invention includes:

[0056] A cloud information acquisition module, which is connected to the user end and is used to acquire the account information to be identified uploaded by the user end, wherein the account information to be identified includes several categories of pictures to be identified;

[0057] An information classification module is connected to the image acquisition module to be identified, and is used to divide the image to be identified into a number of sub-images, obtain the chromaticity value of the seal part in each sub-image and extract the seal outline in the image to be identified, determine the seal confidence representation value according to the chromaticity deviation value combined with the seal outline integrity, and classify the image to be identified;

[0058] An information verification module, which is connected to the cloud information acquisition module and the information classification module respectively, and includes a selected verification unit and a storage unit;

[0059] The selected verification unit is used to verify the image to be identified according to the category of the image to be identified, including:

[0060] Obtaining the chromaticity values ​​of several feature points in the image to be identified, and determining whether the image to be identified meets the verification criteria according to the chromaticity values ​​of the feature points;

[0061] Or, obtaining the clarity of the seal edge in the image to be identified, and determining whether the image to be identified meets the verification standard;

[0062] A database module is connected to the information verification module and is used to store the verified pictures to be identified.

[0063] Specifically, the present invention does not limit the specific structure of the cloud information acquisition module, the information classification module and the information verification module, which can all be composed of logical components or a combination of logical components. The logical components include a field programmable processor, a determination machine or a microprocessor in the determination machine. This is a prior art and will not be repeated here.

[0064] Specifically, the present invention does not limit the specific method of obtaining the chromaticity value of the seal part in the image to be identified, and it can be obtained through Python.

[0065] Specifically, the present invention does not limit the specific method of obtaining the seal outline in the image to be identified, and it can be obtained through Python.

[0066] Specifically, the information classification module is used to obtain the chromaticity deviation value of the image to be identified, including:

[0067] To extract the chromaticity values ​​of a number of points of the stamp part of each sub-image and determine the average chromaticity value of the stamp part of the sub-image;

[0068] Determine the average color value of the seal to be verified according to the average color value of the seal part of each sub-image;

[0069] It is used to obtain the difference between the chromaticity average value of the seal part of each sub-image and the chromaticity average value of the seal to be verified, and the sum of the differences is the chromaticity deviation value of the image to be identified.

[0070] Specifically, the information classification module obtains the completeness of the seal outline.

[0071] Used to obtain the image to be identified;

[0072] To obtain the seal outline and the overall seal outline of the seal whose chromaticity value in the image to be identified is the average chromaticity value of the seal to be verified;

[0073] To obtain the proportion of the seal outline whose chromaticity value in the image to be identified is the average chromaticity value of the seal to be verified in the overall outline of the seal;

[0074] Used to record the proportion as the completeness of the seal outline.

[0075] Specifically, the information classification module determines the seal confidence representation value based on the chromaticity deviation value and the seal outline integrity, including:

[0076] for determining the ratio of the seal chromaticity deviation value to a preset chromaticity deviation value threshold as a first confidence feature;

[0077] for determining the ratio of a preset seal outline integrity threshold to the seal outline integrity as a second confidence feature;

[0078] Used to determine the sum of the first confidence feature and the second confidence feature as the seal confidence representation value.

[0079] In this embodiment, the preset chromaticity deviation value threshold and the preset seal outline integrity are obtained in advance through experiments. A number of real seal images are obtained, the chromaticity deviation value and the seal outline integrity of each real seal are obtained, the average chromaticity deviation value and the average seal outline integrity of each real seal are determined, the preset chromaticity deviation value threshold is the product of the chromaticity deviation coefficient and the average chromaticity deviation value of the real seal, the average chromaticity deviation value and the average seal outline integrity of each real seal are calculated, and the preset chromaticity deviation value threshold is set to be between 0.9 times and 1.1 times the average chromaticity deviation value, and the preset seal outline integrity is set to be between 0.9 times and 1.1 times the average seal outline integrity.

[0080] Specifically, the information classification module of the present invention determines the seal confidence characterization value based on the chromaticity deviation value combined with the seal contour completeness. In actual situations, the seal in the forged image to be identified may show overly uniform characteristics in chromaticity value, while the chromaticity value of the real seal will have a certain degree of unevenness due to factors such as pressure and ink distribution when stamping. The uniformity of the chromaticity of the seal in the image to be identified can be reliably characterized based on the chromaticity deviation value and the seal contour completeness. By determining the seal confidence characterization value, the seal in the image to be identified can be verified more reliably, and the image to be identified can be divided into different categories.

[0081] Specifically, the information classification module divides the categories of pictures to be identified into:

[0082] The information classification module compares the seal confidence representation value with a preset seal confidence representation value comparison threshold value,

[0083] If the seal confidence representation value of the image to be identified is less than the preset seal confidence representation value comparison threshold, the category of the image to be identified is a pseudo-tendency image to be identified category;

[0084] If the seal confidence representation value of the image to be identified is greater than or equal to the preset seal confidence representation value comparison threshold, then the category of the image to be identified is the true tendency category of the image to be identified.

[0085] In this embodiment, the preset seal confidence representation value comparison threshold is selected within the range of [2.15, 2.30].

[0086] Specifically, the information classification module of the present invention classifies the picture to be identified according to the seal confidence representation value. When the seal confidence representation value of the picture to be identified is high, there is a certain chromaticity value difference between the seals in the picture to be identified. When the seal confidence representation value of the picture to be identified is small, the chromaticity value difference between the seals in the picture to be identified is small. By classifying the pictures to be identified, different verification strategies can be adopted for pictures of different categories to be identified, thereby improving the reliability of verification of the pictures to be identified.

[0087] Specifically, the selected verification unit is used to verify the image to be identified according to the category of the image to be identified, wherein:

[0088] If the category of the image to be identified is a pseudo-tendency image to be identified category, then obtaining the chromaticity values ​​of several feature points in the image to be identified, and determining whether the seal in the image to be identified meets the verification standard according to the chromaticity values ​​of the feature points;

[0089] If the category of the image to be identified is the category of the image to be identified that is truly inclined, then the seal quality parameters in the image to be identified are obtained, and the seal quality parameters include the seal edge clarity and the seal integrity, to determine whether the seal in the image to be identified meets the verification standard.

[0090] Specifically, the selected verification unit obtains the chromaticity values ​​of a number of feature points in the image to be identified, wherein the feature points are points where characters and seals overlap.

[0091] It is understandable that in actual situations, the seal in the image to be identified is often printed on the text of the document, or on the signature of the image to be identified, so there are several feature points, and the feature points exist both the seal and the text. When the seal is printed on the document, the text or signature under the seal may be visible to varying degrees through the seal ink. If the seal does not meet the verification standards, there may be a phenomenon that the seal cannot be seen to varying degrees through the seal ink.

[0092] Specifically, the selected verification unit is used to determine whether the seal in the image to be identified meets the verification standard according to the chromaticity value of the feature point.

[0093] To obtain the difference between the average chromaticity value of the feature points and the average chromaticity value of the non-feature points;

[0094] Used to compare the difference between the average chromaticity value of the feature point and the average chromaticity value of the non-feature point with a preset difference comparison threshold;

[0095] If the difference between the average chromaticity value of the feature point and the average chromaticity value of the non-feature point is less than a preset difference comparison threshold, it is determined that the seal in the image to be identified does not meet the verification standard.

[0096] In this embodiment, the preset difference comparison threshold is obtained in advance through experiments. Several real seal images are obtained, and the difference between the average chromaticity value of the feature points of each real seal image and the average chromaticity value of the non-feature points is obtained to determine the average difference. The preset difference comparison threshold is the product of the difference coefficient and the average difference, and the difference coefficient is selected within the interval [0.9,1.1].

[0097] Specifically, the verification unit selected by the present invention determines whether the seal in the image to be identified meets the verification standards based on the chromaticity value of the feature point. In actual situations, when the seal in the image to be identified is printed on a document, the text or signature under the seal may be revealed through the seal ink. If there is text showing under the seal, the color of the seal area may be unevenly distributed, because the text will affect the color and density of the seal ink. By obtaining the chromaticity value of the feature point, the phenomenon of the text or signature showing under the seal can be characterized, so that the verification of the seal can be judged more reliably.

[0098] Specifically, the selected verification unit is used to compare the clarity of the seal edge with a preset clarity comparison threshold.

[0099] If the edge clarity of the seal in the image to be identified is less than a preset clarity comparison threshold, it is determined that the seal in the image to be identified does not meet the verification standard.

[0100] It is understandable that in actual situations, it is possible to accurately separate the seal from a real seal image through image editing software and place it in another image or background, which may cause a decrease in the clarity of the seal edge.

[0101] In this embodiment, the preset clarity contrast threshold is pre-measured in experiments, the clarity of the seal edge in several real seal images is obtained, and the average seal edge clarity is determined. The preset clarity contrast threshold is the product of the seal edge clarity coefficient and the average seal edge clarity. The seal edge clarity coefficient satisfies [0.9, 1.1].

[0102] In this embodiment, an edge detection algorithm is used to evaluate the clarity of the seal edge. The clearer the edge, the higher the image quality.

[0103] Specifically, the verification unit selected by the present invention determines whether the seal in the picture to be identified meets the verification standards according to the clarity of the seal edge in the picture to be identified. In actual situations, the seal in the real seal picture may be accurately separated by image editing software and placed in another image or background, which may cause the clarity of the seal edge to decrease. By obtaining the clarity of the seal edge, the verification of the seal can be more reliably verified.

[0104] Specifically, the storage unit is used to store the pictures to be identified in which the seals do not meet the verification standard.

[0105] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An intelligent accounting information processing system based on cloud computing, characterized in that: include: A cloud information acquisition module, which is connected to the user end and is used to acquire the account information to be identified uploaded by the user end, wherein the account information to be identified includes several categories of pictures to be identified; An information classification module is connected to the image acquisition module to be identified, and is used to divide the image to be identified into a number of sub-images, obtain the chromaticity value of the seal part in each sub-image and extract the seal outline in the image to be identified, determine the seal confidence representation value according to the chromaticity deviation value combined with the seal outline integrity, and classify the image to be identified; An information verification module, which is connected to the cloud information acquisition module and the information classification module respectively, and includes a selected verification unit and a storage unit; The selected verification unit is used to verify the image to be identified according to the category of the image to be identified, including: Obtaining the chromaticity values ​​of several feature points in the image to be identified, and determining whether the image to be identified meets the verification criteria according to the chromaticity values ​​of the feature points; Or, obtaining the clarity of the seal edge in the image to be identified, and determining whether the image to be identified meets the verification standard; A database module is connected to the information verification module and is used to store the verified pictures to be identified.

2. The intelligent accounting information processing system based on cloud computing according to claim 1 is characterized in that: The information classification module is used to obtain the chromaticity deviation value of the image to be identified, including: To extract the chromaticity values ​​of a number of points of the stamp part of each sub-image and determine the average chromaticity value of the stamp part of the sub-image; Determine the average chromaticity of the seal to be verified according to the average chromaticity of the seal part of each sub-image; It is used to obtain the difference between the chromaticity average value of the seal part of each sub-image and the chromaticity average value of the seal to be verified, and the sum of the differences is the chromaticity deviation value of the image to be identified.

3. The intelligent accounting information processing system based on cloud computing according to claim 2 is characterized in that: The information classification module is used to obtain the completeness of the seal outline, including: Used to obtain the image to be identified; To obtain the seal outline and the overall seal outline of the seal whose chromaticity value in the image to be identified is the average chromaticity value of the seal to be verified; To obtain the proportion of the seal outline whose chromaticity value in the image to be identified is the average chromaticity value of the seal to be verified in the overall outline of the seal; Used to record the proportion as the completeness of the seal outline.

4. The intelligent accounting information processing system based on cloud computing according to claim 1 is characterized in that: The information classification module is used to determine the seal confidence representation value according to the color deviation value combined with the seal outline integrity, including: for determining the ratio of the seal chromaticity deviation value to a preset chromaticity deviation value threshold as a first confidence feature; for determining the ratio of a preset seal outline integrity threshold to the seal outline integrity as a second confidence feature; Used to determine the sum of the first confidence feature and the second confidence feature as the seal confidence representation value.

5. The intelligent accounting information processing system based on cloud computing according to claim 4 is characterized in that: The information classification module divides the categories of the pictures to be identified into: The information classification module compares the seal confidence representation value with a preset seal confidence representation value comparison threshold value, If the seal confidence representation value of the image to be identified is less than the preset seal confidence representation value comparison threshold, the category of the image to be identified is a pseudo-tendency image to be identified category; If the seal confidence representation value of the image to be identified is greater than or equal to the preset seal confidence representation value comparison threshold, then the category of the image to be identified is the true tendency category of the image to be identified.

6. The intelligent accounting information processing system based on cloud computing according to claim 5 is characterized in that: The selected verification unit is used to verify the image to be identified according to the category of the image to be identified, wherein: If the category of the image to be identified is a pseudo-tendency image to be identified category, then obtaining the chromaticity values ​​of several feature points in the image to be identified, and determining whether the seal in the image to be identified meets the verification standard according to the chromaticity values ​​of the feature points; If the category of the image to be identified is the category of the image to be identified that is truly inclined, the edge clarity of the seal in the image to be identified is obtained to determine whether the seal in the image to be identified meets the verification standard.

7. The intelligent accounting information processing system based on cloud computing according to claim 1 is characterized in that: The selected verification unit obtains the chromaticity values ​​of a plurality of feature points in the image to be identified, wherein the feature points are points where characters and seals overlap.

8. The intelligent accounting information processing system based on cloud computing according to claim 1 is characterized in that: The selected verification unit is used to determine whether the seal in the image to be identified meets the verification standard according to the chromaticity value of the feature point, including: To obtain the difference between the average chromaticity value of the feature points and the average chromaticity value of the non-feature points; The difference between the average chromaticity value of the feature point and the average chromaticity value of the non-feature point is compared with a preset difference comparison threshold; If the difference between the average chromaticity value of the feature point and the average chromaticity value of the non-feature point is less than a preset difference comparison threshold, it is determined that the seal in the image to be identified does not meet the verification standard.

9. The intelligent accounting information processing system based on cloud computing according to claim 1 is characterized in that: The selected verification unit compares the seal edge clarity with a preset clarity comparison threshold, If the edge clarity of the seal in the image to be identified is less than a preset clarity comparison threshold, it is determined that the seal in the image to be identified does not meet the verification standard.

10. The intelligent accounting information processing system based on cloud computing according to claim 9 is characterized in that: The storage unit is used to store the pictures to be identified in which the seals do not meet the verification standard.

Images