An electronic document verification method and system for digital commerce

Abstract

The application discloses an electronic file verification method and system for digital business, which comprises the following steps: S1, identifying a plurality of abnormal areas existing in each scanning image according to the local pixel features of the scanning image; S2, selecting a verification area, and matching a plurality of associated areas with the verification area, wherein the similarity of the associated areas is greater than a similarity threshold; S3, obtaining a pixel correction value of each abnormal pixel point, and performing analog correction on the pixels of the verification area to generate a corresponding analog verification image; and S4, obtaining a plurality of image feature difference values of the analog verification image, analyzing the abnormal types of the corresponding scanning image set, and identifying the authenticity of the corresponding electronic file. The application can accurately distinguish the image errors caused by the scanning errors of the equipment hardware and the image errors caused by the modification of the scanning image, and realizes the authenticity identification of the electronic file of the corresponding paper file.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electronic file verification, in particular to an electronic file verification method and system for digital business. BACKGROUND

[0002] In today's digital age, digital business has become an important development direction. Digital business uses advanced technology such as big data, artificial intelligence, and cloud computing to bring comprehensive intelligent improvement in business processes, business development, and customer service.

[0003] The digital business industry chain covers multiple levels. First, the foundation layer is the cornerstone of digital business technology, including artificial intelligence, big data, cloud computing, and other technical infrastructure, as well as data sources and customer base. These infrastructures provide the necessary support and resources for digital business. At the technical level, cloud computing technology plays a crucial role. It provides flexible and scalable computing and storage resources for digital business, helping to improve operational efficiency, reduce costs, and quickly respond to market changes.

[0004] In existing application scenarios, when paper files are converted into electronic versions for sending and storage, manual review of the electronic version of the paper file is required to check for errors, especially for the review of seals. The labor cost of manual review is high, and the workload is large. The review efficiency is low, and the accuracy of the review is heavily dependent on the working state of the reviewer, which can easily cause review errors. When identifying the existence of image errors in the electronic version of the corresponding paper file due to scanning errors of the device hardware, the image cannot be corrected and responded to in a timely manner. SUMMARY

[0005] The purpose of the present application is to overcome the shortcomings of the prior art and provide an electronic file verification method and system for digital business, which can accurately distinguish between image errors caused by scanning errors of device hardware and image errors caused by human modification of scanned images, and realize the authenticity identification of the electronic version of the corresponding paper file.

[0006] The purpose of the present application is achieved by the following technical solution: an electronic file verification method for digital business, comprising the following steps:

[0007] S1. Identifying a number of abnormal areas existing in each scanned image in the electronic version of the file according to the local pixel features of each scanned image in the electronic version of the file;

[0008] S2. Selecting an abnormal region with the largest abnormal value from all abnormal regions corresponding to all scan images as a to-be-verified region of the corresponding scan image set, and matching a plurality of associated regions with a region similarity greater than a similarity threshold for the to-be-verified region from all scan images according to the first region feature of the to-be-verified region;

[0009] S3. Mapping the second region feature of each associated region to the to-be-verified region to obtain a pixel correction value of each abnormal pixel point, and performing analog correction on the pixels of the to-be-verified region according to the pixel correction value of each abnormal pixel point to generate a corresponding analog verification image;

[0010] S4. Comparing the analog verification image with a standard verification image to obtain a plurality of image feature difference values of the analog verification image, and obtaining an abnormal type of the corresponding scan image set according to the image feature difference value and a preset threshold value, to identify the file authenticity of the corresponding electronic version file.

[0011] The beneficial effects of the present application are: the present application identifies a plurality of abnormal regions with abnormal pixel values in the scan image of the corresponding paper file uploaded by the user terminal, corrects the pixels of the corresponding abnormal region according to the pixel correction value of the abnormal pixel point to generate a corresponding analog verification image, and then verifies the abnormal type of the corresponding scan image through the feature difference between the analog verification image and the standard verification image of the corresponding paper file, to automatically and accurately identify the reason for the pixel abnormality of the electronic version file of the corresponding paper file, accurately distinguish the image error caused by the scanning error of the device hardware and the image error caused by the modification of the scan image by human, and realize the authenticity identification of the electronic version file of the corresponding paper file. Therefore, the electronic file identification demand in the digital business scene can be well met, the consumption of manpower and material resources is reduced, and the processing efficiency of automation is improved. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 The method flowchart of the present application is shown in the figure;

[0013] Figure 2 The system principle schematic diagram of the present application is shown in the figure. DETAILED DESCRIPTION

[0014] The technical solutions of the present application will be further described in detail below with reference to the accompanying drawings, but the protection scope of the present application is not limited to the following description.

[0015] As shown in the figure, in one embodiment, the electronic file verification method for digital business of the present application includes: Figure 1

[0016] ​S1, a data acquisition module of a digital business cloud platform (for example, commonly used in the field of smart finance, which can be referred to as a smart financial cloud platform) receives an electronic version file uploaded by a user terminal and scanned by a scanner, and identifies a plurality of abnormal regions existing in the corresponding scanned image according to the local pixel features of each scanned image in the electronic version file, wherein the electronic version file includes a scanned image set, image page number, image format and image size.

[0017] Optionally, the scanned image set includes a plurality of scanned images, wherein each scanned image corresponds to a paper file; the image page number is the file page number of the corresponding paper file; and the image format can be bmp format, jpg format or png format.

[0018] Specifically, the data acquisition module identifies a plurality of abnormal regions existing in the corresponding scanned image according to the local pixel features of each scanned image in the electronic version file, including:

[0019] The data acquisition module identifies the occurrence frequency of all extreme points contained in each image local region in the corresponding scanned image according to the local pixel features of each scanned image, wherein the local pixel features are obtained by analyzing the pixel value and position information of each pixel point in the corresponding image local region;

[0020] The data acquisition module constructs a corresponding frequency curve for the corresponding image local region according to the pixel value and occurrence frequency of all extreme points, and compares the frequency curve of the corresponding image local region with the frequency curve of the adjacent image local region of the image local region to identify all abnormal extreme points existing in the image local region, wherein the abnormal extreme points are extreme points with an occurrence frequency greater than a frequency threshold in the corresponding frequency curve;

[0021] The data acquisition module performs abnormal marking on all abnormal extreme points in the corresponding image local region to obtain a plurality of abnormal pixel points existing in the image local region, and takes different image local regions with a plurality of abnormal pixel points as a plurality of abnormal regions of the corresponding scanned image.

[0022] Optionally, the occurrence frequency is used to represent the occurrence number and travel frequency of the corresponding extreme point; and the frequency threshold is a numerical value preset by the system to judge whether the occurrence frequency of the extreme point is abnormal.

[0023] Optionally, the extreme points include maximum value points and minimum value points of pixels in the corresponding image local region, wherein the maximum value point is a pixel point with the maximum pixel value compared with the pixel values of each pixel point in the adjacent region;

[0024] The minimum value point is a pixel point with the minimum pixel value compared with the pixel values of each pixel point in the adjacent region; and the adjacent region is a region range preset by the system.

[0025] S2, the region matching module selects an abnormal region with the largest abnormal value from all abnormal regions corresponding to all scan images as a to-be-verified region of a corresponding scan image set, and matches a plurality of associated regions with a region similarity greater than a similarity threshold for the to-be-verified region from all scan images according to a first region feature of the to-be-verified region.

[0026] Specifically, the region matching module selects an abnormal region with the largest abnormal value from all abnormal regions corresponding to all scan images as a to-be-verified region of a corresponding scan image set includes:

[0027] The region matching module counts the number of all abnormal pixel points in each abnormal region to obtain an abnormal pixel amount of each abnormal region, and identifies a plurality of edge abnormal pixel points in the corresponding abnormal region according to the position information of each abnormal pixel point, wherein the abnormal pixel amount is used to represent the proportion of abnormal pixel points and normal pixel points in the corresponding abnormal region.

[0028] The region matching module constructs a corresponding abnormal structure feature for the corresponding abnormal region according to the relative distance and relative angle between each edge abnormal pixel point, and analyzes the region shape indicated by the abnormal structure feature to obtain an abnormal region area of the corresponding abnormal region, wherein the abnormal structure feature is used to represent the region shape feature formed by all abnormal pixel points in the corresponding abnormal region.

[0029] The region matching module obtains a first abnormal coefficient corresponding to the abnormal region area of each abnormal region and a second abnormal coefficient corresponding to the abnormal pixel amount, and weights and fuses the abnormal region area and the abnormal pixel amount of each abnormal region to obtain an abnormal value of the corresponding abnormal region, and selects an abnormal region with the largest abnormal value from all abnormal regions as a to-be-verified region of a corresponding scan image set.

[0030] Optionally, the first abnormal coefficient is used to represent the weight value of the abnormal region area of the corresponding abnormal region in the abnormal value analysis process; the second abnormal coefficient is used to represent the weight value of the abnormal pixel amount of the corresponding abnormal region in the abnormal value analysis process, and the first abnormal coefficient and the second abnormal coefficient are both pre-set by the system.

[0031] Specifically, the region matching module matches a plurality of associated regions with a region similarity greater than a similarity threshold for the to-be-verified region from all scan images according to the first region feature of the to-be-verified region includes:

[0032] The region matching module takes an image centroid point of a corresponding scan image as a coordinate origin of a two-dimensional plane coordinate to obtain region position information of the to-be-verified region relative to the image centroid point of the corresponding scan image, the image centroid point being obtained by image shape and image area analysis of the corresponding scan image;

[0033] The region matching module performs region positioning on all remaining scan images according to the region position information of the to-be-verified region to obtain an image local region in each remaining scan image that is consistent with the position of the to-be-verified region and has the same area, and compares region structure features and region texture features of each image local region with the first region features to obtain region similarity of each image local region to the to-be-verified region, wherein the remaining scan images do not include the scan image corresponding to the to-be-verified region;

[0034] The region matching module takes the image local region with a region similarity greater than a similarity threshold as a correlation region of the to-be-verified region.

[0035] Optionally, the similarity threshold is a numerical value preset by the system for judging whether the corresponding to-be-verified region and the corresponding image local region are similar regions; and the region structure features and the region texture features are obtained by analyzing pixel values and position information of each pixel point in the corresponding image local region.

[0036] Optionally, the region position information includes a coordinate maximum value and a coordinate minimum value of the corresponding to-be-verified region; the coordinate minimum value is used to represent a minimum horizontal coordinate value and a minimum vertical coordinate value of the pixel points in the corresponding to-be-verified region;

[0037] The coordinate maximum value is used to represent a maximum horizontal coordinate value and a maximum vertical coordinate value of the pixel points in the corresponding to-be-verified region.

[0038] In another embodiment, the region matching module matches, according to the first region features of the to-be-verified region, a plurality of correlation regions with a region similarity greater than a similarity threshold for the to-be-verified region from all scan images further includes:

[0039] The region matching module obtains pixel positions and pixel values of each normal pixel point in the to-be-verified region, and identifies different local units in which the normal pixel points in the to-be-verified region are gathered according to the pixel positions of each normal pixel point, wherein the local unit is used to represent a local region in the corresponding to-be-verified region that does not contain abnormal pixel points;

[0040] The region matching module takes all normal pixel points belonging to the same local unit as the associated normal pixel points of the corresponding local unit, and analyzes the distance features and angle features between each associated normal pixel point according to the position information of each associated normal pixel point in the corresponding local unit, wherein the associated normal pixel points are all normal pixel points in the same local unit in the to-be-verified region, the distance features are used to represent the relative distances between the corresponding associated normal pixel points, and the angle features are used to represent the relative angles between the corresponding associated normal pixel points.

[0041] The region matching module analyzes the unit structure of the corresponding local unit according to the distance features and angle features between each associated normal pixel point to obtain the unit structure features and unit texture features of the local unit, and aggregates the unit structure features and unit texture features of all local units of the to-be-verified region to obtain the first region features of the to-be-verified region.

[0042] Optionally, the first region features are obtained by aggregating the unit structure features and unit texture features of all local units of the to-be-verified region.

[0043] S3, the image simulation module maps the second region features of each associated region to the to-be-verified region to obtain the pixel correction values of each abnormal pixel point, and simulates and corrects the pixels of the to-be-verified region according to the pixel correction values of each abnormal pixel point to generate a corresponding simulation verification image.

[0044] Specifically, the image simulation module maps the second region features of each associated region to the to-be-verified region to obtain the pixel correction values of each abnormal pixel point includes:

[0045] The image simulation module obtains the first feature matching degree between the feature vectors of each normal pixel point of the to-be-verified region and the feature vectors of each pixel point in the corresponding associated region, and establishes a corresponding pixel mapping relationship for each normal pixel point in the corresponding to-be-verified region according to the first feature matching degree of each feature vector, wherein the pixel mapping relationship is used to represent the corresponding relationship between the pixel points in the corresponding associated region and the normal pixel points in the to-be-verified region, the region feature quantity contained in the second region features is greater than the region feature quantity contained in the first region features, and the feature vectors include position feature vectors and pixel feature vectors of normal pixel points.

[0046] The image simulation module maps part of the feature vectors in the second region feature of each associated region to each abnormal pixel point in the to-be-verified region according to the pixel mapping relationship to obtain a mapping feature value of each abnormal pixel point, and takes the mapping feature value as a weight value of the corresponding abnormal pixel point, wherein the part of the feature vectors are pixel points in the corresponding associated region that have not established a pixel mapping relationship with the pixel points in the verification region.

[0047] The image simulation module obtains pixel values of each pixel point contained in each associated region, and performs weighted fusion on pixel values of each matching pixel point in the associated region according to the weight value of each abnormal pixel point in the to-be-verified region to obtain a pixel correction value of each abnormal pixel point, wherein the matching pixel point is a pixel point in the corresponding associated region that has the largest second feature matching degree with the corresponding abnormal pixel point.

[0048] Optionally, the first feature matching degree is used to represent the similarity between each normal pixel point in the to-be-verified region and the corresponding pixel point in the associated region; and the second feature matching degree is used to represent the similarity between each abnormal pixel point in the to-be-verified region and the corresponding pixel point in the associated region.

[0049] Optionally, the second region feature is obtained by analyzing a region structure feature and a region texture feature of the corresponding associated region.

[0050] S4, the image verification module performs feature comparison on the simulation verification image and a standard verification image to obtain a plurality of image feature difference values of the simulation verification image, and analyzes the abnormal types of the corresponding scanning image set according to the image feature difference values and a preset threshold value to identify the file authenticity of the corresponding electronic file, wherein the abnormal types include image abnormalities caused by scanning errors of device hardware and image abnormalities caused by human modification.

[0051] Optionally, the standard verification image is an archive of an original electronic file of the corresponding paper file that has existed and has not been modified; and the preset threshold value is a numerical value that is set by the system in advance to determine whether the file content displayed by the simulation verification image after pixel correction is consistent with the file content of the original paper file.

[0052] Optionally, when the abnormal type of the scanning image set is identified as the image abnormalities caused by human modification, the corresponding electronic file is determined to be a fake file; and when the abnormal type of the scanning image set is identified as the image errors caused by the scanning errors of the device hardware, the corresponding electronic file is determined to be a real file.

[0053] The technical scheme provided by the application obtains a group of equipment working values of the production equipment when the production equipment is in a normal state, analyzes the correlation between the change rules of the equipment working values of the production equipment, and detects the working state of the production equipment in a target monitoring period, that is, the change amount of the production equipment characteristic signal in the normal state is compared with the change amount of the production equipment characteristic signal in the target monitoring period, so that the abnormal state of the equipment can be accurately and efficiently detected without the need for technical personnel to have high professional level and rich field experience, labor cost is reduced, and the equipment maintenance cost is reduced.

[0054] Referring to Figure 2 In one embodiment, an electronic file verification system for performing the method of the application includes a digital business cloud platform (such as a smart financial cloud platform) and a user terminal. The digital business cloud platform is in communication connection with the user terminal. The user terminal is a device with computing, storage and communication functions used by the file uploader, including a smartphone, a desktop computer and a notebook computer.

[0055] The digital business cloud platform includes a data acquisition module, a region matching module, an image simulation module and an image verification module.

[0056] The data acquisition module is configured to receive an electronic version file obtained by scanning the file using a scanner and identify a plurality of abnormal regions in the corresponding scanned image according to the local pixel features of each scanned image in the electronic version file, wherein the electronic version file includes a scanned image set, image page number, image format and image size.

[0057] The region matching module is configured to select an abnormal region with the largest abnormal value from all abnormal regions corresponding to all scanned images as a to-be-verified region of the corresponding scanned image set, and match a plurality of associated regions with a region similarity greater than a similarity threshold for the to-be-verified region from all scanned images according to the first region feature of the to-be-verified region.

[0058] The image simulation module is configured to map the second region feature of each associated region to the to-be-verified region to obtain a pixel correction value of each abnormal pixel point, and simulate and correct the pixels of the to-be-verified region according to the pixel correction value of each abnormal pixel point to generate a corresponding simulation verification image.

[0059] The image verification module is configured to compare the simulation verification image with a standard verification image to obtain a plurality of image feature difference values of the simulation verification image, and analyze the image feature difference values and a preset threshold to obtain an abnormal type of the corresponding scanning image set, so as to identify a file authenticity of the corresponding electronic file, wherein the abnormal type includes an image abnormality caused by a scanning error of a device hardware and an image abnormality caused by a human modification.

[0060] In addition, although specific functionality is discussed above with reference to specific modules, it should be noted that the functionality of the various modules discussed herein can be split into multiple modules, and / or at least some functionality of multiple modules can be combined into a single module. In addition, a particular module performing an action as discussed herein includes the particular module itself performing the action, or alternatively, the particular module invoking or otherwise accessing another component or module to perform the action (or in combination with the particular module). Thus, a particular module performing an action can include the particular module itself performing the action, and / or the particular module invoking or otherwise accessing another module to perform the action.

Claims

1. An electronic document verification method for digital commerce, characterized by: The method comprises the following steps: S1. Identifying a plurality of abnormal regions existing in each corresponding scanned image according to local pixel features of each scanned image in the electronic version file; S2. Selecting an abnormal region with the largest abnormal value from all abnormal regions corresponding to all scanned images as a to-be-verified region of the corresponding scanned image set, and matching a plurality of associated regions with a region similarity greater than a similarity threshold for the to-be-verified region from all scanned images according to a first region feature of the to-be-verified region; S3. Mapping a second region feature of each associated region to the to-be-verified region to obtain a pixel correction value of each abnormal pixel point, and performing analog correction on pixels of the to-be-verified region according to the pixel correction value of each abnormal pixel point to generate a corresponding analog verification image; Mapping the second region feature of each associated region to the to-be-verified region to obtain a pixel correction value of each abnormal pixel point comprises: Obtaining a first feature matching degree between a feature vector of each normal pixel point of the to-be-verified region and a feature vector of each pixel point in the corresponding associated region, and establishing a corresponding pixel mapping relationship for each normal pixel point in the corresponding to-be-verified region according to the first feature matching degree of each feature vector, wherein the pixel mapping relationship is used to represent the corresponding relationship between the pixel points in the corresponding associated region and the normal pixel points in the to-be-verified region, the region feature quantity contained in the second region feature is greater than the region feature quantity contained in the first region feature, and the feature vector includes a position feature vector and a pixel feature vector of the normal pixel point; Mapping part of the feature vectors in the second region feature of each associated region to each abnormal pixel point in the to-be-verified region according to the pixel mapping relationship to obtain a mapping feature value of each abnormal pixel point, and taking the mapping feature value as a weight value of the corresponding abnormal pixel point, wherein the part of the feature vectors are pixel points in the corresponding associated region that have not established a pixel mapping relationship with the pixel points in the to-be-verified region; Obtaining pixel values of each pixel point contained in each associated region, and performing weighted fusion on the pixel values of each matching pixel point in the associated region according to the weight value of each abnormal pixel point in the to-be-verified region to obtain a pixel correction value of each abnormal pixel point, wherein the matching pixel point is a pixel point in the corresponding associated region with the largest second feature matching degree with the corresponding abnormal pixel point; S4. Comparing the analog verification image with a standard verification image to obtain a plurality of image feature difference values of the analog verification image, and analyzing the image feature difference values and a preset threshold to obtain an abnormal type of the corresponding scanned image set, so as to identify the file authenticity of the corresponding electronic version file.

2. The electronic document verification method for digital commerce according to claim 1, wherein: The electronic version file comprises a scanned image set, an image page number, an image format and an image size; The scanned image set comprises a plurality of scanned images, wherein each scanned image corresponds to a paper file; the image page number is the file page number of the corresponding paper file; and the image format is a bmp format, a jpg format or a png format.

3. The method for electronic document verification for digital commerce according to claim 2, wherein: The step S1 comprises: S101. Receiving an electronic version file obtained by scanning with a scanner and uploaded by a user terminal; S102. Identify a number of abnormal regions existing in the corresponding scanning image according to the local pixel features of each scanning image in the electronic version file: According to the local pixel features of each scanning image, identify the occurrence frequency of all extreme points contained in each image local region in the corresponding scanning image, wherein the local pixel features are obtained by analyzing the pixel value and position information of each pixel point in the corresponding image local region; According to the pixel value and occurrence frequency of all extreme points, construct a corresponding frequency curve for the corresponding image local region, and compare the frequency curve of the corresponding image local region with the frequency curve of the adjacent image local region of the image local region to identify all abnormal extreme points existing in the image local region, wherein the abnormal extreme points are the extreme points with a frequency greater than a frequency threshold in the corresponding frequency curve; Abnormal mark all abnormal extreme points in the corresponding image local region to obtain a number of abnormal pixel points existing in the image local region, and different image local regions with a number of abnormal pixel points are taken as a number of abnormal regions of the corresponding scanning image.

4. The method for electronic document verification for digital commerce according to claim 1, wherein: In step S2, the abnormal region with the maximum abnormal value is selected as the to-be-verified region of the corresponding scanning image set from all abnormal regions corresponding to all scanning images, which includes: Count the number of all abnormal pixel points in each abnormal region to obtain the abnormal pixel amount of each abnormal region, and identify a number of edge abnormal pixel points in the corresponding abnormal region according to the position information of each abnormal pixel point, wherein the abnormal pixel amount is used to represent the proportion of the abnormal pixel points and the normal pixel points in the corresponding abnormal region; According to the relative distance and relative angle between each edge abnormal pixel point, construct a corresponding abnormal structure feature for the corresponding abnormal region, and analyze the abnormal region area of the corresponding abnormal region according to the region shape indicated by the abnormal structure feature, wherein the abnormal structure feature is used to represent the region shape feature formed by all abnormal pixel points in the corresponding abnormal region; Obtain the first abnormal coefficient corresponding to the abnormal region area of each abnormal region and the second abnormal coefficient corresponding to the abnormal pixel amount, and weight and fuse the abnormal region area and the abnormal pixel amount of each abnormal region to obtain the abnormal value of the corresponding abnormal region, and select the abnormal region with the maximum abnormal value from all abnormal regions as the to-be-verified region of the corresponding scanning image set.

5. The method for electronic document verification for digital commerce according to claim 4, wherein: In step S2, according to the first region feature of the to-be-verified region, match a number of associated regions with a region similarity greater than a similarity threshold for the to-be-verified region from all scanning images, which includes: Take the image centroid point of the corresponding scanning image as the coordinate origin of the two-dimensional plane coordinates to obtain the region position information of the to-be-verified region relative to the image centroid point of the corresponding scanning image, wherein the image centroid point is obtained by analyzing the image shape and image area of the corresponding scanning image; According to the region position information of the to-be-verified region, region positioning is performed on all remaining scan images to obtain an image local region in each remaining scan image that is consistent with the position of the to-be-verified region and has the same area, and region structure features and region texture features of each image local region are compared with the first region features to obtain a region similarity of each image local region to the to-be-verified region, wherein the remaining scan images do not include the scan image corresponding to the to-be-verified region; An image local region with a region similarity greater than a similarity threshold value is taken as a relevant region of the to-be-verified region.

6. The method for electronic document verification for digital commerce according to claim 1, wherein: In the step S4, the abnormal types include an image abnormality caused by a scanning error of the device hardware and an image abnormality caused by human modification.

7. The method for electronic document verification for digital commerce according to claim 1, wherein: The standard verification image is an archived original electronic version file of the corresponding paper file that has no modification; and the preset threshold value is a numerical value set in advance by the system to determine whether the file content displayed by the simulation verification image after pixel correction is consistent with the file content of the original paper file. When the abnormal type of the scan image set is identified as the image abnormality caused by human modification, it is determined that the corresponding electronic version file is a fake file; and when the abnormal type of the scan image set is identified as the image abnormality caused by the scanning error of the device hardware, it is determined that the corresponding electronic version file is a real file.

8. An electronic document verification system for digital commerce, which performs electronic document verification by the method according to any one of claims 1 to 7, characterized by: The digital business cloud platform and the user terminal are in communication connection. The digital business cloud platform comprises: The data acquisition module is configured to receive an electronic version file obtained by scanning by a scanner uploaded by the user terminal, and identify a plurality of abnormal regions existing in the corresponding scan image according to local pixel features of each scan image in the electronic version file, wherein the electronic version file comprises a scan image set, image page number, image format and image size. The region matching module is configured to select an abnormal region with the largest abnormal value from all abnormal regions corresponding to all scan images as a to-be-verified region of the corresponding scan image set, and match a plurality of relevant regions with a region similarity greater than a similarity threshold value for the to-be-verified region from all scan images according to first region features of the to-be-verified region. The image simulation module is configured to map second region features of each relevant region to the to-be-verified region to obtain pixel correction values of each abnormal pixel point, and simulate and correct pixels of the to-be-verified region according to the pixel correction values of each abnormal pixel point to generate a corresponding simulation verification image. The image verification module is configured to compare features of the simulation verification image with features of a standard verification image to obtain a plurality of image feature difference values of the simulation verification image, and analyze the image feature difference values and the preset threshold value to obtain an abnormal type of the corresponding scan image set, so as to identify file authenticity of the corresponding electronic version file, wherein the abnormal type includes an image abnormality caused by a scanning error of the device hardware and an image abnormality caused by human modification.

Images